Use Actions tokens for Copilot test workflows

Remove Copilot PAT secrets from integration and sample validation workflows, grant Copilot request permission at the required caller and job boundaries, and preserve the environment variable expected by the tests.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Copilot-Session: d9fa4e9c-c32d-42fb-8ee4-4772473e6479

.devcontainer/devcontainer.json

@@ -1,15 +1,19 @@
 {
   "name": "Python 3",
-  "image": "mcr.microsoft.com/devcontainers/python:3.13-bullseye",
+  "image": "mcr.microsoft.com/devcontainers/python:3.14-bookworm",
   "features": {
     "ghcr.io/va-h/devcontainers-features/uv:1": {},
-    "ghcr.io/devcontainers/features/azure-cli:1.2.8": {}
+    "ghcr.io/devcontainers/features/docker-in-docker:3": {},
+    "ghcr.io/devcontainers/features/azure-cli:1.2.9": {},
+    "ghcr.io/devcontainers/features/copilot-cli:1": {}
   },
   "postCreateCommand": "bash ./devsetup.sh",
   "workspaceFolder": "/workspaces/agent-framework/python/",
   "customizations": {
     "vscode": {
       "extensions": [
+        "GitHub.copilot",
+        "GitHub.vscode-github-actions",
         "ms-python.python",
         "ms-windows-ai-studio.windows-ai-studio",
         "littlefoxteam.vscode-python-test-adapter"

.github/.linkspector.yml

@@ -8,7 +8,7 @@ ignorePatterns:
   - pattern: "./blob"
   - pattern: "./issues"
   - pattern: "./discussions"
-  - pattern: "./pulls"
+  - pattern: "./pull"
   - pattern: "https:\/\/platform.openai.com"
   - pattern: "http:\/\/localhost"
   - pattern: "http:\/\/127.0.0.1"
@@ -20,7 +20,10 @@ ignorePatterns:
   - pattern: "https://your-resource.openai.azure.com/"
   - pattern: "http://host.docker.internal"
   - pattern: "https://openai.github.io/openai-agents-js/openai/agents/classes/"
-  - pattern: "https:\/\/dotnet.microsoft.com\/download"
+  # dotnet.microsoft.com bot-blocks CI link checkers with intermittent 403s on any
+  # path (including localized variants like /en-us/download/...), so ignore the
+  # whole domain rather than just /download.
+  - pattern: "https:\/\/dotnet.microsoft.com"
   - pattern: "https://github.com/Rel1cx/eslint-react"
 # excludedDirs:
   # Folders which include links to localhost, since it's not ignored with regular expressions

.github/ISSUE_TEMPLATE/dotnet-issue.yml

@@ -1,7 +1,7 @@
 name: .NET Bug Report
 description: Report a bug in the Agent Framework .NET SDK
 title: ".NET: [Bug]: "
-labels: ["bug", ".NET"]
+labels: [".NET"]
 type: bug
 body:
   - type: textarea

.github/ISSUE_TEMPLATE/python-issue.yml

@@ -1,7 +1,7 @@
 name: Python Bug Report
 description: Report a bug in the Agent Framework Python SDK
 title: "Python: [Bug]: "
-labels: ["bug", "Python"]
+labels: ["Python"]
 type: bug
 body:
   - type: textarea

.github/actions/free-runner-disk-space/action.yml

@@ -0,0 +1,64 @@
+name: Free runner disk space
+description: |
+  Reclaims disk space on GitHub-hosted Ubuntu runners by removing
+  pre-installed toolchains we do not use (Android SDK, GHC/Haskell,
+  CodeQL bundle), Docker images, and swap. Also relocates the
+  NuGet package cache to /mnt (which has ~75 GB free vs ~14 GB
+  on /). No-op on non-Linux runners.
+
+runs:
+  using: composite
+  steps:
+    - name: Free disk space (Linux only)
+      if: runner.os == 'Linux'
+      shell: bash
+      run: |
+        set -euo pipefail
+        echo "::group::Disk usage before cleanup"
+        df -h /
+        echo "::endgroup::"
+
+        # Remove pre-installed toolchains we never use on this repo's
+        # dotnet/python jobs. These reclaim ~25-30 GB on ubuntu-latest.
+        sudo rm -rf \
+          /usr/local/lib/android \
+          /usr/share/dotnet/sdk/NuGetFallbackFolder \
+          /opt/ghc \
+          /usr/local/.ghcup \
+          /opt/hostedtoolcache/CodeQL \
+          /opt/hostedtoolcache/PyPy \
+          /opt/hostedtoolcache/Ruby \
+          /opt/hostedtoolcache/go \
+          /usr/local/share/boost \
+          /usr/local/share/powershell \
+          /usr/local/share/chromium \
+          /usr/local/share/vcpkg \
+          /usr/local/lib/heroku \
+          "${AGENT_TOOLSDIRECTORY:-/opt/hostedtoolcache}/PyPy" \
+          "${AGENT_TOOLSDIRECTORY:-/opt/hostedtoolcache}/Ruby" \
+          "${AGENT_TOOLSDIRECTORY:-/opt/hostedtoolcache}/go" || true
+
+        # Drop docker images shipped on the runner; jobs that need
+        # docker pull what they need fresh.
+        if command -v docker >/dev/null 2>&1; then
+          sudo docker image prune --all --force >/dev/null 2>&1 || true
+        fi
+
+        # Disable swap to free its backing file.
+        sudo swapoff -a || true
+        sudo rm -f /mnt/swapfile /swapfile || true
+
+        echo "::group::Disk usage after cleanup"
+        df -h /
+        echo "::endgroup::"
+
+    - name: Relocate NuGet package cache to /mnt (Linux only)
+      if: runner.os == 'Linux'
+      shell: bash
+      run: |
+        set -euo pipefail
+        sudo mkdir -p /mnt/nuget
+        sudo chown -R "$USER":"$USER" /mnt/nuget
+        echo "NUGET_PACKAGES=/mnt/nuget" >> "$GITHUB_ENV"
+        echo "Relocated NuGet package cache to /mnt/nuget"
+        df -h /mnt || true

.github/actions/github-app-token/action.yml

@@ -0,0 +1,112 @@
+name: Get GitHub automation token
+description: Creates a GitHub App installation token with a temporary PAT fallback
+
+inputs:
+  mode:
+    description: Authentication mode (app, app-with-fallback, or pat)
+    required: false
+    default: app-with-fallback
+  azure-client-id:
+    description: Client ID of the Azure workload identity
+    required: false
+  azure-tenant-id:
+    description: Azure tenant ID
+    required: false
+  azure-subscription-id:
+    description: Azure subscription containing the Key Vault
+    required: false
+  key-vault-name:
+    description: Azure Key Vault name
+    required: false
+  key-name:
+    description: Key Vault key used to sign the GitHub App JWT
+    required: false
+  github-app-client-id:
+    description: GitHub App client ID
+    required: false
+  github-app-installation-id:
+    description: GitHub App installation ID
+    required: false
+  repository:
+    description: Repository to include in the installation token
+    required: false
+  fallback-token:
+    description: PAT used temporarily when app authentication is unavailable
+    required: false
+
+outputs:
+  token:
+    description: GitHub App installation token or fallback PAT
+    value: ${{ steps.select-token.outputs.token }}
+  source:
+    description: Selected authentication source
+    value: ${{ steps.select-token.outputs.source }}
+
+runs:
+  using: composite
+  steps:
+    - name: Validate authentication mode
+      shell: bash
+      env:
+        AUTH_MODE: ${{ inputs.mode || 'app-with-fallback' }}
+      run: |
+        if [[ "$AUTH_MODE" != "app" && "$AUTH_MODE" != "app-with-fallback" && "$AUTH_MODE" != "pat" ]]; then
+          echo "::error::Unsupported GitHub authentication mode."
+          exit 1
+        fi
+
+    - name: Sign in to Azure
+      id: azure-login
+      if: ${{ (inputs.mode || 'app-with-fallback') != 'pat' }}
+      continue-on-error: true
+      uses: azure/login@a457da9ea143d694b1b9c7c869ebb04ebe844ef5 # v2
+      with:
+        client-id: ${{ inputs.azure-client-id }}
+        tenant-id: ${{ inputs.azure-tenant-id }}
+        subscription-id: ${{ inputs.azure-subscription-id }}
+
+    - name: Create GitHub App installation token
+      id: app-token
+      if: ${{ (inputs.mode || 'app-with-fallback') != 'pat' && steps.azure-login.outcome == 'success' }}
+      continue-on-error: true
+      shell: bash
+      env:
+        AZURE_SUBSCRIPTION_ID: ${{ inputs.azure-subscription-id }}
+        KEY_VAULT_NAME: ${{ inputs.key-vault-name }}
+        KEY_NAME: ${{ inputs.key-name }}
+        GITHUB_APP_CLIENT_ID: ${{ inputs.github-app-client-id }}
+        GITHUB_APP_INSTALLATION_ID: ${{ inputs.github-app-installation-id }}
+        TARGET_REPOSITORY: ${{ inputs.repository }}
+      run: |
+        token="$(node "$GITHUB_ACTION_PATH/create-token.js")"
+        echo "::add-mask::$token"
+        echo "token=$token" >> "$GITHUB_OUTPUT"
+
+    - name: Select authentication token
+      id: select-token
+      shell: bash
+      env:
+        AUTH_MODE: ${{ inputs.mode || 'app-with-fallback' }}
+        APP_TOKEN: ${{ steps.app-token.outputs.token }}
+        FALLBACK_TOKEN: ${{ inputs.fallback-token }}
+      run: |
+        if [[ "$AUTH_MODE" != "pat" && -n "$APP_TOKEN" ]]; then
+          token="$APP_TOKEN"
+          source="app"
+          echo "::notice::GitHub authentication source: app"
+        elif [[ "$AUTH_MODE" == "app-with-fallback" && -n "$FALLBACK_TOKEN" ]]; then
+          token="$FALLBACK_TOKEN"
+          source="pat-fallback"
+          echo "::warning::GitHub authentication source: PAT fallback"
+        elif [[ "$AUTH_MODE" == "pat" && -n "$FALLBACK_TOKEN" ]]; then
+          token="$FALLBACK_TOKEN"
+          source="pat-forced"
+          echo "::warning::GitHub authentication source: PAT (forced rollout mode)"
+        else
+          echo "::error::GitHub App authentication is unavailable and no fallback PAT was provided."
+          exit 1
+        fi
+
+        echo "::add-mask::$token"
+        echo "token=$token" >> "$GITHUB_OUTPUT"
+        echo "source=$source" >> "$GITHUB_OUTPUT"

.github/actions/github-app-token/create-token.js

@@ -0,0 +1,133 @@
+// Copyright (c) Microsoft. All rights reserved.
+
+const crypto = require('node:crypto');
+const { execFileSync } = require('node:child_process');
+
+function base64Url(value) {
+  return Buffer.from(value).toString('base64url');
+}
+
+function base64ToBase64Url(value) {
+  return Buffer.from(value, 'base64').toString('base64url');
+}
+
+function createJwtSigningInput(clientId, nowSeconds) {
+  const header = base64Url(JSON.stringify({ alg: 'RS256', typ: 'JWT' }));
+  const payload = base64Url(JSON.stringify({
+    iat: nowSeconds - 60,
+    exp: nowSeconds + 540,
+    iss: clientId,
+  }));
+  return `${header}.${payload}`;
+}
+
+function signJwt(signingInput, config, execute = execFileSync) {
+  const digest = crypto.createHash('sha256').update(signingInput).digest('base64');
+  const signature = execute(
+    'az',
+    [
+      'keyvault', 'key', 'sign',
+      '--subscription', config.azureSubscriptionId,
+      '--vault-name', config.keyVaultName,
+      '--name', config.keyName,
+      '--algorithm', 'RS256',
+      '--digest', digest,
+      '--query', 'signature',
+      '--output', 'tsv',
+      '--only-show-errors',
+    ],
+    { encoding: 'utf8' },
+  ).trim();
+
+  if (!signature) {
+    throw new Error('Key Vault returned an empty signature.');
+  }
+
+  return `${signingInput}.${base64ToBase64Url(signature)}`;
+}
+
+async function createInstallationToken(config, dependencies = {}) {
+  const execute = dependencies.execute ?? execFileSync;
+  const request = dependencies.fetch ?? fetch;
+  const nowSeconds = dependencies.nowSeconds ?? Math.floor(Date.now() / 1000);
+  const repositoryParts = config.targetRepository.split('/');
+
+  if (repositoryParts.length !== 2 || repositoryParts.some((part) => part.length === 0)) {
+    throw new Error('TARGET_REPOSITORY must use the owner/repository format.');
+  }
+
+  const [, repository] = repositoryParts;
+  const signingInput = createJwtSigningInput(config.githubAppClientId, nowSeconds);
+  const jwt = signJwt(signingInput, config, execute);
+
+  const response = await request(
+    `https://api.github.com/app/installations/${config.githubAppInstallationId}/access_tokens`,
+    {
+      method: 'POST',
+      headers: {
+        Accept: 'application/vnd.github+json',
+        Authorization: `Bearer ${jwt}`,
+        'X-GitHub-Api-Version': '2022-11-28',
+      },
+      body: JSON.stringify({
+        repositories: [repository],
+        permissions: {
+          contents: 'read',
+          issues: 'write',
+          members: 'read',
+          pull_requests: 'write',
+        },
+      }),
+    },
+  );
+
+  if (!response.ok) {
+    throw new Error(`GitHub installation token request failed with HTTP ${response.status}.`);
+  }
+
+  const result = await response.json();
+  if (typeof result.token !== 'string' || result.token.length === 0) {
+    throw new Error('GitHub returned an empty installation token.');
+  }
+
+  return result.token;
+}
+
+function readConfig(environment) {
+  const config = {
+    azureSubscriptionId: environment.AZURE_SUBSCRIPTION_ID,
+    keyVaultName: environment.KEY_VAULT_NAME,
+    keyName: environment.KEY_NAME,
+    githubAppClientId: environment.GITHUB_APP_CLIENT_ID,
+    githubAppInstallationId: environment.GITHUB_APP_INSTALLATION_ID,
+    targetRepository: environment.TARGET_REPOSITORY,
+  };
+
+  if (Object.values(config).some((value) => !value)) {
+    throw new Error('Required GitHub App authentication configuration is missing.');
+  }
+
+  return config;
+}
+
+async function main() {
+  try {
+    const token = await createInstallationToken(readConfig(process.env));
+    process.stdout.write(token);
+  } catch {
+    console.error('GitHub App token generation failed.');
+    process.exitCode = 1;
+  }
+}
+
+if (require.main === module) {
+  void main();
+}
+
+module.exports = {
+  base64ToBase64Url,
+  createInstallationToken,
+  createJwtSigningInput,
+  readConfig,
+  signJwt,
+};

.github/actions/python-setup/action.yml

@@ -17,7 +17,7 @@ runs:
     using: "composite"
     steps:
       - name: Set up uv
-        uses: astral-sh/setup-uv@v6
+        uses: astral-sh/setup-uv@11f9893b081a58869d3b5fccaea48c9e9e46f990 # v8.3.2
         with:
             version-file: "python/pyproject.toml"
             enable-cache: true
@@ -32,7 +32,13 @@ runs:
               if grep -q "name = \"$pkg\"" "$f"; then
                 pkg_dir=$(dirname "$f" | sed 's|python/||')
                 echo "Excluding workspace package: $pkg ($pkg_dir)"
-                sed -i.bak '/\[tool\.uv\.workspace\]/a\exclude = ["'"$pkg_dir"'"]' python/pyproject.toml
+                if awk '/^\[tool\.uv\.workspace\]/{f=1;next} /^\[/{f=0} f && /^exclude = \[/{found=1} END{exit !found}' python/pyproject.toml; then
+                  if ! awk '/^\[tool\.uv\.workspace\]/{f=1;next} /^\[/{f=0} f && /^exclude = \[/ && index($0, "\"'"$pkg_dir"'\"")' python/pyproject.toml | grep -q .; then
+                    sed -i.bak '/\[tool\.uv\.workspace\]/,/^\[/ { /^exclude = \[/ s|\]|, "'"$pkg_dir"'"]| }' python/pyproject.toml
+                  fi
+                else
+                  sed -i.bak '/\[tool\.uv\.workspace\]/a\exclude = ["'"$pkg_dir"'"]' python/pyproject.toml
+                fi
                 sed -i.bak '/'"$pkg"' = { workspace = true }/d' python/pyproject.toml
               fi
             done
@@ -40,4 +46,4 @@ runs:
       - name: Install the project
         shell: bash
         run: |
-          cd python && uv sync --all-packages --all-extras --dev -U --prerelease=if-necessary-or-explicit
+          cd python && uv sync --all-packages --all-extras --all-groups --prerelease=if-necessary-or-explicit

.github/actions/sample-validation-setup/action.yml

@@ -24,7 +24,7 @@ runs:
   using: "composite"
   steps:
     - name: Set up Node.js environment
-      uses: actions/setup-node@v6
+      uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6
       with:
         node-version: 22
 
@@ -37,7 +37,7 @@ runs:
       run: copilot --version && copilot -p "What can you do in one sentence?"
 
     - name: Azure CLI Login
-      uses: azure/login@v2
+      uses: azure/login@a457da9ea143d694b1b9c7c869ebb04ebe844ef5 # v2
       with:
         client-id: ${{ inputs.azure-client-id }}
         tenant-id: ${{ inputs.azure-tenant-id }}

.github/dependabot.yml

@@ -24,12 +24,14 @@ updates:
       - ".NET"
       - "dependencies"
 
-  # Maintain dependencies for python
+  # Maintain dependencies for python.
+  # TODO: Remove these Python Dependabot entries after we have confidence in the
+  # Python dependency-maintenance workflow.
   - package-ecosystem: "pip"
     directory: "python/"
     schedule:
       interval: "weekly"
-      day: "monday"
+      day: "thursday"
     labels:
       - "python"
       - "dependencies"
@@ -37,16 +39,22 @@ updates:
     directory: "python/"
     schedule:
       interval: "weekly"
-      day: "monday"
+      day: "thursday"
     labels:
       - "python"
       - "dependencies"
 
   # Maintain dependencies for github-actions
   - package-ecosystem: "github-actions"
-    # Workflow files stored in the
-    # default location of `.github/workflows`
-    directory: "/"
+    # Cover both the standard workflow location and our composite actions.
+    # With `directory: "/"` Dependabot only scans `.github/workflows/*.{yml,yaml}`
+    # plus a root-level `action.yml/action.yaml`. It does NOT recurse into
+    # `.github/actions/*/action.yml`, so the glob below is required to keep the
+    # composite actions in `.github/actions/<name>/` up to date as well.
+    # Ref: https://docs.github.com/en/code-security/dependabot/working-with-dependabot/dependabot-options-reference#directories-or-directory--
+    directories:
+      - "/"
+      - "/.github/actions/*"
     schedule:
       interval: "weekly"
       day: "sunday"

.github/pull_request_template.md

@@ -1,23 +1,43 @@
-### Motivation and Context
+### Motivation & Context
 
 <!-- Thank you for your contribution to the Agent Framework repo!
 Please help reviewers and future users, providing the following information:
   1. Why is this change required?
   2. What problem does it solve?
   3. What scenario does it contribute to?
-  4. If it fixes an open issue, please link to the issue here.
+  4. If it fixes an open issue, please link to the issue below.
 -->
 
-### Description
+### Description & Review Guide
 
 <!-- Describe your changes, the overall approach, the underlying design.
+     Highlight what you want the reviewers to focus on.
      These notes will help understanding how your code works. Thanks! -->
 
+- **What are the major changes?**
+- **What is the impact of these changes?**
+- **What do you want reviewers to focus on?**
+<!-- NOTE FOR AUTOMATED/AI REVIEWERS: the "What do you want reviewers to focus on?"
+     item above is intended for human reviewers only. Automated/AI reviewers should
+     ignore it and review the entire change rather than narrowing scope to it. -->
+
+
+### Related Issue
+
+<!-- Which issue does this PR fix? Link it using a GitHub closing keyword so it is
+     closed automatically when this PR is merged, e.g. "Fixes #123" or "Closes #123".
+     PRs that are not linked to an issue may be closed, no matter how valid the change is.
+     Also check whether an open PR already exists for this issue; if so,
+     explain how this PR is different. -->
+
+Fixes #
+
 ### Contribution Checklist
 
 <!-- Before submitting this PR, please make sure: -->
 
 - [ ] The code builds clean without any errors or warnings
-- [ ] The PR follows the [Contribution Guidelines](https://github.com/microsoft/agent-framework/blob/main/CONTRIBUTING.md)
 - [ ] All unit tests pass, and I have added new tests where possible
-- [ ] **Is this a breaking change?** If yes, add "[BREAKING]" prefix to the title of the PR.
+- [ ] The PR follows the [Contribution Guidelines](https://github.com/microsoft/agent-framework/blob/main/CONTRIBUTING.md)
+- [ ] This PR is linked to an issue and there is no other open PR for this issue (see Related Issue above).
+- [x] **This is not a breaking change.** If it _is_ a breaking change, add the `breaking change` label (or add "[BREAKING]" to the title prefix, before or after any language prefix) — a workflow keeps the label and title prefix in sync automatically.

.github/scripts/check_team_membership.js

@@ -0,0 +1,76 @@
+// Copyright (c) Microsoft. All rights reserved.
+
+/**
+ * Resolve the issue or pull request author and check their team membership.
+ *
+ * @param {object} opts
+ * @param {object} opts.github - Octokit REST client from actions/github-script
+ * @param {object} opts.context - GitHub Actions context
+ * @param {object} opts.core - GitHub Actions core toolkit
+ * @param {string} opts.teamSlug - Team slug to check membership against
+ * @param {string|number} opts.issueNumber - Issue or pull request number to resolve author for
+ * @param {string} [opts.username] - Explicit user to check instead of the issue or pull request author
+ * @returns {Promise<{author: string|null, isTeamMember: boolean}>}
+ */
+async function checkTeamMembership({ github, context, core, teamSlug, issueNumber, username = '' }) {
+  let author = username.trim() || (
+    context.payload.issue?.user?.login ??
+    context.payload.pull_request?.user?.login
+  );
+
+  if (!author) {
+    const number = Number(issueNumber);
+    if (context.payload.pull_request) {
+      const { data: pr } = await github.rest.pulls.get({
+        owner: context.repo.owner,
+        repo: context.repo.repo,
+        pull_number: number,
+      });
+      author = pr.user?.login;
+    } else {
+      const { data: issue } = await github.rest.issues.get({
+        owner: context.repo.owner,
+        repo: context.repo.repo,
+        issue_number: number,
+      });
+      author = issue.user?.login;
+    }
+  }
+
+  if (!author) {
+    core.setFailed('Could not determine issue author (user may be deleted).');
+    return { author: null, isTeamMember: false };
+  }
+
+  try {
+    await github.rest.teams.getByName({
+      org: context.repo.owner,
+      team_slug: teamSlug,
+    });
+  } catch (error) {
+    core.setFailed(`Team lookup failed for ${teamSlug}: ${error.message}`);
+    throw error;
+  }
+
+  let isTeamMember = false;
+  try {
+    const teamMembership = await github.rest.teams.getMembershipForUserInOrg({
+      org: context.repo.owner,
+      team_slug: teamSlug,
+      username: author,
+    });
+    isTeamMember = teamMembership.data.state === 'active';
+  } catch (error) {
+    if (error.status === 404) {
+      core.info(`Author ${author} is not a member of team ${teamSlug}.`);
+      isTeamMember = false;
+    } else {
+      core.setFailed(`Team membership lookup failed for ${author}: ${error.message}`);
+      throw error;
+    }
+  }
+
+  return { author, isTeamMember };
+}
+
+module.exports = checkTeamMembership;

.github/scripts/pr_limit_moderation.js

@@ -0,0 +1,181 @@
+// Copyright (c) Microsoft. All rights reserved.
+
+function getPullRequest(context) {
+  const pullRequest = context.payload.pull_request;
+  if (!pullRequest?.number || !pullRequest.user?.login) {
+    throw new Error('This script must be run from a pull_request_target event.');
+  }
+
+  return {
+    author: pullRequest.user.login,
+    authorType: pullRequest.user.type,
+    labels: pullRequest.labels?.map((label) => label.name).filter(Boolean) ?? [],
+    number: pullRequest.number,
+  };
+}
+
+async function ensureLabel({ github, owner, repo, labelName }) {
+  try {
+    await github.rest.issues.getLabel({
+      owner,
+      repo,
+      name: labelName,
+    });
+  } catch (error) {
+    if (error.status !== 404) {
+      throw error;
+    }
+
+    try {
+      await github.rest.issues.createLabel({
+        owner,
+        repo,
+        name: labelName,
+        color: 'd93f0b',
+        description: 'Community author has exceeded the open pull request limit.',
+      });
+    } catch (createError) {
+      if (createError.status !== 422) {
+        throw createError;
+      }
+    }
+  }
+}
+
+function hasLabel(labels, labelName) {
+  if (!labelName) {
+    return false;
+  }
+
+  return labels.some((label) => label.toLowerCase() === labelName.toLowerCase());
+}
+
+function isDependabotAuthor({ author, authorType }) {
+  return authorType === 'Bot' && author.toLowerCase() === 'dependabot[bot]';
+}
+
+function buildLimitMessage({ author, exemptLabelName, maxOpenPrs, openPrCount }) {
+  return [
+    `Thank you for your contribution, @${author}.`,
+    '',
+    `To keep the review queue manageable, we currently limit community contributors to ${maxOpenPrs} `
+      + `open pull requests at a time. This PR would put you at ${openPrCount} open pull requests, `
+      + 'so we are closing it automatically.',
+    '',
+    'Please focus on getting your existing PRs reviewed, merged, or closed before opening another one. '
+      + `If a maintainer asked you to open this PR, they can apply the \`${exemptLabelName}\` label and reopen it.`,
+  ].join('\n');
+}
+
+async function getOpenPrCount({ github, owner, repo, author, pullRequestNumber }) {
+  const openPullRequests = await github.paginate(github.rest.pulls.list, {
+    owner,
+    repo,
+    state: 'open',
+    per_page: 100,
+  });
+
+  const authorOpenPullRequestNumbers = openPullRequests
+    .filter((pullRequest) => pullRequest.user?.login === author)
+    .map((pullRequest) => pullRequest.number);
+  const currentPrIsOpen = authorOpenPullRequestNumbers.includes(pullRequestNumber);
+  const existingOpenPrCount = currentPrIsOpen
+    ? authorOpenPullRequestNumbers.length - 1
+    : authorOpenPullRequestNumbers.length;
+
+  return existingOpenPrCount + 1;
+}
+
+async function enforcePrLimit({ github, context, core, exemptLabelName, maxOpenPrs, labelName }) {
+  const { owner, repo } = context.repo;
+  const { author, authorType, labels, number } = getPullRequest(context);
+
+  if (isDependabotAuthor({ author, authorType })) {
+    core.info(`Author ${author} is Dependabot; skipping open PR limit enforcement.`);
+    return {
+      author,
+      closed: false,
+      dependabotExempt: true,
+      openPrCount: null,
+    };
+  }
+
+  if (hasLabel(labels, exemptLabelName)) {
+    core.info(`PR #${number} has the ${exemptLabelName} label; skipping open PR limit enforcement.`);
+    return {
+      author,
+      closed: false,
+      exempt: true,
+      openPrCount: null,
+    };
+  }
+
+  const openPrCount = await getOpenPrCount({
+    github,
+    owner,
+    repo,
+    author,
+    pullRequestNumber: number,
+  });
+
+  if (openPrCount <= maxOpenPrs) {
+    core.info(
+      `${author} has ${openPrCount} open pull request(s), which is within the limit of ${maxOpenPrs}.`,
+    );
+    return {
+      author,
+      closed: false,
+      openPrCount,
+    };
+  }
+
+  await ensureLabel({
+    github,
+    owner,
+    repo,
+    labelName,
+  });
+
+  await github.rest.issues.addLabels({
+    owner,
+    repo,
+    issue_number: number,
+    labels: [labelName],
+  });
+
+  await github.rest.issues.createComment({
+    owner,
+    repo,
+    issue_number: number,
+    body: buildLimitMessage({
+      author,
+      exemptLabelName,
+      maxOpenPrs,
+      openPrCount,
+    }),
+  });
+
+  await github.rest.pulls.update({
+    owner,
+    repo,
+    pull_number: number,
+    state: 'closed',
+  });
+
+  core.info(
+    `${author} has ${openPrCount} open pull request(s), which exceeds the limit of ${maxOpenPrs}. `
+      + `Closed PR #${number}.`,
+  );
+
+  return {
+    author,
+    closed: true,
+    openPrCount,
+  };
+}
+
+module.exports = {
+  buildLimitMessage,
+  enforcePrLimit,
+  getOpenPrCount,
+};

.github/scripts/python_check_coverage.py

@@ -0,0 +1,212 @@
+# Copyright (c) Microsoft. All rights reserved.
+"""Enforce Python package coverage according to package lifecycle."""
+
+# ruff:file-ignore[print]
+# ruff:file-ignore[implicit-namespace-package]
+
+from __future__ import annotations
+
+import re
+import sys
+import xml.etree.ElementTree as ET  # ruff:ignore[suspicious-xml-etree-import]
+from dataclasses import dataclass
+from pathlib import Path
+
+import tomllib
+
+DEVELOPMENT_STATUS_PREFIX = "Development Status :: "
+ENFORCED_DEVELOPMENT_STATUS = 4
+EXEMPT_PACKAGES = {"devui", "lab"}
+
+
+@dataclass(frozen=True)
+class PackagePolicy:
+    """Coverage policy derived from a package's project metadata."""
+
+    directory: str
+    distribution_name: str
+    development_status: int
+    development_status_label: str
+    enforced: bool
+    exempt: bool
+
+
+@dataclass
+class CoverageStats:
+    """Line and branch coverage counters."""
+
+    lines_valid: int = 0
+    lines_covered: int = 0
+    branches_valid: int = 0
+    branches_covered: int = 0
+
+    @property
+    def line_coverage_percent(self) -> float:
+        """Return line coverage as a percentage."""
+        if not self.lines_valid:
+            return 0
+        return self.lines_covered / self.lines_valid * 100
+
+
+def normalize_coverage_path(path: str) -> str:
+    """Normalize a coverage path for matching."""
+    return path.replace("\\", "/").lstrip("./")
+
+
+def load_package_policies(packages_dir: Path) -> list[PackagePolicy]:
+    """Load lifecycle-based coverage policies from package pyproject files."""
+    policies: list[PackagePolicy] = []
+    for pyproject_path in sorted(packages_dir.glob("*/pyproject.toml")):
+        with pyproject_path.open("rb") as pyproject_file:
+            pyproject = tomllib.load(pyproject_file)
+
+        project = pyproject.get("project", {})
+        distribution_name = str(project.get("name", "")).strip()
+        if not distribution_name:
+            raise ValueError(f"{pyproject_path}: project.name is required")
+
+        status_classifiers = [
+            classifier
+            for classifier in project.get("classifiers", [])
+            if classifier.startswith(DEVELOPMENT_STATUS_PREFIX)
+        ]
+        if len(status_classifiers) != 1:
+            raise ValueError(
+                f"{pyproject_path}: expected exactly one Development Status classifier, found {len(status_classifiers)}"
+            )
+
+        match = re.fullmatch(r"Development Status :: (\d+) - (.+)", status_classifiers[0])
+        if match is None:
+            raise ValueError(f"{pyproject_path}: malformed Development Status classifier")
+
+        directory = pyproject_path.parent.name
+        development_status = int(match.group(1))
+        exempt = directory in EXEMPT_PACKAGES
+        policies.append(
+            PackagePolicy(
+                directory=directory,
+                distribution_name=distribution_name,
+                development_status=development_status,
+                development_status_label=match.group(2),
+                enforced=development_status >= ENFORCED_DEVELOPMENT_STATUS and not exempt,
+                exempt=exempt,
+            )
+        )
+
+    if not policies:
+        raise ValueError(f"No package pyproject.toml files found below {packages_dir}")
+    return policies
+
+
+def parse_coverage_xml(xml_path: Path) -> tuple[dict[str, CoverageStats], float, float]:
+    """Parse Cobertura XML and aggregate coverage by package directory."""
+    root = ET.parse(xml_path).getroot()  # ruff:ignore[suspicious-xml-element-tree-usage]  # Trusted CI-generated coverage report.
+    package_stats: dict[str, CoverageStats] = {}
+
+    for class_elem in root.findall(".//class"):
+        file_path = normalize_coverage_path(class_elem.get("filename", ""))
+        path_parts = file_path.split("/")
+        try:
+            packages_index = path_parts.index("packages")
+            package_directory = path_parts[packages_index + 1]
+        except (ValueError, IndexError):
+            continue
+
+        stats = package_stats.setdefault(package_directory, CoverageStats())
+        for line in class_elem.findall(".//line"):
+            stats.lines_valid += 1
+            if int(line.get("hits", 0)) > 0:
+                stats.lines_covered += 1
+
+            if line.get("branch") != "true":
+                continue
+            condition_coverage = line.get("condition-coverage", "")
+            match = re.search(r"\((\d+)/(\d+)\)", condition_coverage)
+            if match is not None:
+                stats.branches_covered += int(match.group(1))
+                stats.branches_valid += int(match.group(2))
+
+    return (
+        package_stats,
+        float(root.get("line-rate", 0)) * 100,
+        float(root.get("branch-rate", 0)) * 100,
+    )
+
+
+def check_coverage(xml_path: Path, threshold: float, packages_dir: Path) -> bool:
+    """Check all lifecycle-enforced packages against the coverage threshold."""
+    policies = load_package_policies(packages_dir)
+    package_stats, overall_line_coverage, overall_branch_coverage = parse_coverage_xml(xml_path)
+
+    print("\n" + "=" * 110)
+    print("PYTHON PACKAGE TEST COVERAGE")
+    print("=" * 110)
+    print(f"Overall Line Coverage:   {overall_line_coverage:.1f}%")
+    print(f"Overall Branch Coverage: {overall_branch_coverage:.1f}%")
+    print(f"Enforced Threshold:      {threshold:.1f}%")
+    print("-" * 110)
+    print(f"{'Package':<48} {'Stage':<20} {'Policy':<14} {'Lines':<12} {'Line Cov':<10}")
+    print("-" * 110)
+
+    failed_packages: list[str] = []
+    for policy in sorted(policies, key=lambda item: (not item.enforced, item.distribution_name)):
+        stats = package_stats.get(policy.directory)
+        if policy.exempt:
+            policy_label = "EXEMPT"
+        elif policy.enforced:
+            policy_label = "ENFORCED"
+        else:
+            policy_label = "REPORT ONLY"
+
+        if stats is None:
+            lines = "-"
+            coverage = "missing"
+            if policy.enforced:
+                failed_packages.append(f"{policy.distribution_name} (missing from coverage report)")
+        else:
+            lines = f"{stats.lines_covered}/{stats.lines_valid}"
+            coverage = f"{stats.line_coverage_percent:.1f}%"
+            if policy.enforced and stats.line_coverage_percent < threshold:
+                failed_packages.append(f"{policy.distribution_name} ({coverage})")
+
+        stage = f"{policy.development_status} - {policy.development_status_label}"
+        print(f"{policy.distribution_name:<48} {stage:<20} {policy_label:<14} {lines:<12} {coverage:<10}")
+
+    print("-" * 110)
+    if failed_packages:
+        print(f"\nFAILED: Enforced packages below {threshold:.1f}% or missing:")
+        for package in failed_packages:
+            print(f"  - {package}")
+        return False
+
+    print(f"\nPASSED: All non-exempt Beta-or-higher packages meet {threshold:.1f}% line coverage.")
+    return True
+
+
+def main() -> int:
+    """Run the coverage policy check."""
+    if len(sys.argv) != 3:
+        print(f"Usage: {sys.argv[0]} <coverage-xml-path> <threshold>")
+        return 1
+
+    try:
+        threshold = float(sys.argv[2])
+    except ValueError:
+        print(f"Error: Invalid threshold value: {sys.argv[2]}")
+        return 1
+
+    repository_root = Path(__file__).resolve().parents[2]
+    try:
+        passed = check_coverage(
+            Path(sys.argv[1]),
+            threshold,
+            repository_root / "python" / "packages",
+        )
+    except (FileNotFoundError, ET.ParseError, ValueError) as error:
+        print(f"Error: {error}")
+        return 1
+    return 0 if passed else 1
+
+
+if __name__ == "__main__":
+    sys.exit(main())

.github/scripts/resolve_integration_test_target.js

@@ -0,0 +1,170 @@
+// Copyright (c) Microsoft. All rights reserved.
+
+const DECISIVE_REVIEW_STATES = new Set(['APPROVED', 'CHANGES_REQUESTED', 'DISMISSED']);
+const SHA_PATTERN = /^[0-9a-f]{40}$/;
+const BRANCH_PATTERN = /^[a-zA-Z0-9_./-]+$/;
+
+function assertValidSha(sha, description) {
+  if (!SHA_PATTERN.test(sha)) {
+    throw new Error(`GitHub returned an invalid ${description} SHA.`);
+  }
+}
+
+function hasWritePermission(permissionData) {
+  return permissionData.user?.permissions?.push === true
+    || ['admin', 'maintain', 'write'].includes(permissionData.permission);
+}
+
+function latestDecisiveReviews(reviews) {
+  const latestByReviewer = new Map();
+  const sortedReviews = [...reviews].sort((left, right) => {
+    const submittedComparison = (left.submitted_at || '').localeCompare(right.submitted_at || '');
+    return submittedComparison || Number(left.id) - Number(right.id);
+  });
+
+  for (const review of sortedReviews) {
+    const state = review.state?.toUpperCase();
+    const reviewer = review.user?.login?.toLowerCase();
+    if (reviewer && DECISIVE_REVIEW_STATES.has(state)) {
+      latestByReviewer.set(reviewer, review);
+    }
+  }
+
+  return latestByReviewer;
+}
+
+async function resolvePullRequest({ github, context, core, prNumber, requiredApprovals }) {
+  if (!/^[0-9]+$/.test(prNumber)) {
+    throw new Error('Invalid PR number. Only numeric values are allowed.');
+  }
+
+  const pullNumber = Number(prNumber);
+  const { data: pullRequest } = await github.rest.pulls.get({
+    ...context.repo,
+    pull_number: pullNumber,
+  });
+
+  if (pullRequest.state !== 'open') {
+    throw new Error(`PR #${pullNumber} is not open (state: ${pullRequest.state}).`);
+  }
+
+  const headSha = pullRequest.head.sha;
+  const baseSha = pullRequest.base.sha;
+  assertValidSha(headSha, 'PR head');
+  assertValidSha(baseSha, 'PR base');
+
+  const reviews = await github.paginate(github.rest.pulls.listReviews, {
+    ...context.repo,
+    pull_number: pullNumber,
+    per_page: 100,
+  });
+  const latestReviews = latestDecisiveReviews(reviews);
+  const author = pullRequest.user?.login?.toLowerCase();
+  const approvalCandidates = [...latestReviews.entries()]
+    .filter(([, review]) => review.state.toUpperCase() === 'APPROVED')
+    .filter(([, review]) => review.commit_id === headSha)
+    .filter(([reviewer]) => reviewer !== author);
+
+  const approvedMaintainers = [];
+  for (const [reviewer] of approvalCandidates) {
+    const { data: permissionData } = await github.rest.repos.getCollaboratorPermissionLevel({
+      ...context.repo,
+      username: reviewer,
+    });
+    if (hasWritePermission(permissionData)) {
+      approvedMaintainers.push(reviewer);
+    } else {
+      core.info(`Ignoring approval from ${reviewer}: reviewer does not have write permission.`);
+    }
+  }
+
+  if (approvedMaintainers.length < requiredApprovals) {
+    throw new Error(
+      `PR #${pullNumber} head ${headSha} requires ${requiredApprovals} approvals from unique `
+      + `write-capable maintainers; found ${approvedMaintainers.length}.`,
+    );
+  }
+
+  core.info(
+    `PR #${pullNumber} head ${headSha} approved by: ${approvedMaintainers.join(', ')}.`,
+  );
+  return {
+    baseRef: baseSha,
+    checkoutRef: headSha,
+    description: `PR #${pullNumber}`,
+  };
+}
+
+async function resolveBranch({ github, context, core, branch }) {
+  if (!BRANCH_PATTERN.test(branch)) {
+    throw new Error(
+      'Invalid branch name. Only alphanumeric characters, hyphens, underscores, dots, and slashes '
+      + 'are allowed.',
+    );
+  }
+
+  const [{ data: repository }, { data: targetBranch }] = await Promise.all([
+    github.rest.repos.get(context.repo),
+    github.rest.repos.getBranch({ ...context.repo, branch }),
+  ]);
+  const { data: baseBranch } = await github.rest.repos.getBranch({
+    ...context.repo,
+    branch: repository.default_branch,
+  });
+
+  const checkoutRef = targetBranch.commit.sha;
+  const baseRef = baseBranch.commit.sha;
+  assertValidSha(checkoutRef, 'branch head');
+  assertValidSha(baseRef, 'default branch');
+  core.info(`Branch ${branch} resolved to immutable commit ${checkoutRef}.`);
+
+  return {
+    baseRef,
+    checkoutRef,
+    description: `branch ${branch}`,
+  };
+}
+
+/**
+ * Resolve a manually requested integration-test target to an immutable commit.
+ *
+ * Pull requests must have fresh approvals from two unique write-capable
+ * maintainers for the exact head commit. Branches are limited to branches in
+ * the base repository and are pinned to their current commit.
+ */
+async function resolveIntegrationTestTarget({
+  github,
+  context,
+  core,
+  prNumber = '',
+  branch = '',
+  requiredApprovals = 2,
+}) {
+  const normalizedPrNumber = prNumber.trim();
+  const normalizedBranch = branch.trim();
+
+  if (normalizedPrNumber && normalizedBranch) {
+    throw new Error('Please provide either a PR number or a branch name, not both.');
+  }
+  if (!normalizedPrNumber && !normalizedBranch) {
+    throw new Error('Please provide either a PR number or a branch name.');
+  }
+
+  if (normalizedPrNumber) {
+    return resolvePullRequest({
+      github,
+      context,
+      core,
+      prNumber: normalizedPrNumber,
+      requiredApprovals,
+    });
+  }
+  return resolveBranch({
+    github,
+    context,
+    core,
+    branch: normalizedBranch,
+  });
+}
+
+module.exports = resolveIntegrationTestTarget;

.github/scripts/title_prefix.js

@@ -0,0 +1,253 @@
+// Copyright (c) Microsoft. All rights reserved.
+
+const BREAKING_CHANGE_LABEL = 'breaking change';
+const BREAKING_PREFIX = '[BREAKING]';
+
+const DEFAULT_PREFIX_LABELS = Object.freeze({
+  python: 'Python',
+  '.NET': '.NET',
+});
+
+const DEFAULT_BRACKET_PREFIX_LABELS = Object.freeze({
+  [BREAKING_CHANGE_LABEL]: BREAKING_PREFIX,
+});
+
+function escapeRegExp(value) {
+  return value.replace(/[.*+?^${}()|[\]\\]/g, '\\$&');
+}
+
+function getMatchingValueByKey(valuesByKey, keyToFind) {
+  const matchingKey = Object.keys(valuesByKey).find((key) => key.toLowerCase() === keyToFind.toLowerCase());
+  return matchingKey === undefined ? null : valuesByKey[matchingKey];
+}
+
+function getPrefixPattern(prefixes) {
+  return prefixes.map(escapeRegExp).join('|');
+}
+
+function canonicalizePrefix(prefix, prefixes) {
+  return prefixes.find((knownPrefix) => knownPrefix.toLowerCase() === prefix.toLowerCase()) ?? prefix;
+}
+
+function normalizeLeadingBracketPrefix(title, bracketPrefixes) {
+  const bracketPattern = getPrefixPattern(bracketPrefixes);
+  if (!bracketPattern) {
+    return title;
+  }
+
+  const leadingBracketPrefix = new RegExp(`^(${bracketPattern})(?=\\s|$)`, 'i');
+  return title.replace(
+    leadingBracketPrefix,
+    (bracketPrefix) => canonicalizePrefix(bracketPrefix, bracketPrefixes),
+  );
+}
+
+function parseLeadingTitlePrefix(title, titlePrefixes) {
+  const titlePrefixPattern = getPrefixPattern(titlePrefixes);
+  if (!titlePrefixPattern) {
+    return null;
+  }
+
+  const match = title.match(new RegExp(`^(${titlePrefixPattern}):\\s*`, 'i'));
+  if (!match) {
+    return null;
+  }
+
+  return {
+    prefix: canonicalizePrefix(match[1], titlePrefixes),
+    rest: title.slice(match[0].length).trimStart(),
+  };
+}
+
+function removeBracketPrefixToken(title, bracketPrefix) {
+  const bracketPrefixPattern = escapeRegExp(bracketPrefix);
+  return title
+    .replace(new RegExp(`(^|\\s+)${bracketPrefixPattern}(?=\\s|$)`, 'ig'), '$1')
+    .replace(/\s{2,}/g, ' ')
+    .trim();
+}
+
+function addTitlePrefix(title, prefix, bracketPrefixes = Object.values(DEFAULT_BRACKET_PREFIX_LABELS)) {
+  const bracketPattern = getPrefixPattern(bracketPrefixes);
+  const prefixPattern = escapeRegExp(prefix);
+
+  if (bracketPattern) {
+    const bracketThenTitlePrefix = new RegExp(`^(${bracketPattern})(\\s+)(${prefixPattern})(?=:)`, 'i');
+    if (bracketThenTitlePrefix.test(title)) {
+      return title.replace(
+        bracketThenTitlePrefix,
+        (match, bracketPrefix, spacing) => `${canonicalizePrefix(bracketPrefix, bracketPrefixes)}${spacing}${prefix}`,
+      );
+    }
+
+    title = normalizeLeadingBracketPrefix(title, bracketPrefixes);
+  }
+
+  if (!title.startsWith(`${prefix}: `)) {
+    const existingTitlePrefix = new RegExp(`^${prefixPattern}:\\s*`, 'i');
+    if (existingTitlePrefix.test(title)) {
+      return title.replace(existingTitlePrefix, `${prefix}: `);
+    }
+
+    return `${prefix}: ${title}`;
+  }
+
+  return title;
+}
+
+function hasBracketPrefix(title, bracketPrefix, titlePrefixes = Object.values(DEFAULT_PREFIX_LABELS)) {
+  const bracketPrefixPattern = escapeRegExp(bracketPrefix);
+  const leadingBracketPrefix = new RegExp(`^${bracketPrefixPattern}(?=\\s|$)`, 'i');
+  if (leadingBracketPrefix.test(title)) {
+    return true;
+  }
+
+  const leadingTitlePrefix = parseLeadingTitlePrefix(title, titlePrefixes);
+  if (!leadingTitlePrefix) {
+    return false;
+  }
+
+  return leadingBracketPrefix.test(leadingTitlePrefix.rest);
+}
+
+function addBracketPrefix(title, bracketPrefix, titlePrefixes = Object.values(DEFAULT_PREFIX_LABELS)) {
+  const bracketPrefixPattern = escapeRegExp(bracketPrefix);
+  const leadingBracketPrefix = new RegExp(`^${bracketPrefixPattern}(?=\\s|$)`, 'i');
+  if (leadingBracketPrefix.test(title)) {
+    return title.replace(leadingBracketPrefix, bracketPrefix);
+  }
+
+  const leadingTitlePrefix = parseLeadingTitlePrefix(title, titlePrefixes);
+  if (leadingTitlePrefix) {
+    if (leadingBracketPrefix.test(leadingTitlePrefix.rest)) {
+      const normalizedRest = leadingTitlePrefix.rest.replace(leadingBracketPrefix, bracketPrefix);
+      return `${leadingTitlePrefix.prefix}: ${normalizedRest}`;
+    }
+
+    const titleWithoutBracketPrefix = removeBracketPrefixToken(leadingTitlePrefix.rest, bracketPrefix);
+    return `${leadingTitlePrefix.prefix}: ${bracketPrefix}`
+      + (titleWithoutBracketPrefix ? ` ${titleWithoutBracketPrefix}` : '');
+  }
+
+  const titleWithoutBracketPrefix = removeBracketPrefixToken(title, bracketPrefix);
+  return `${bracketPrefix}${titleWithoutBracketPrefix ? ` ${titleWithoutBracketPrefix}` : ''}`;
+}
+
+function hasLabel(labels, labelName) {
+  return labels.some((label) => label.toLowerCase() === labelName.toLowerCase());
+}
+
+function getCurrentTitle(context) {
+  switch (context.eventName) {
+    case 'issues':
+      return context.payload.issue.title;
+    case 'pull_request_target':
+      return context.payload.pull_request.title;
+    default:
+      throw new Error(`Unrecognized eventName: ${context.eventName}`);
+  }
+}
+
+async function updateTitleForAddedLabel({
+  github,
+  context,
+  core,
+  prefixLabels = DEFAULT_PREFIX_LABELS,
+  bracketPrefixLabels = DEFAULT_BRACKET_PREFIX_LABELS,
+}) {
+  const labelAdded = context.payload.label?.name;
+  if (!labelAdded) {
+    throw new Error('This script must be run from a labeled event.');
+  }
+
+  const currentTitle = getCurrentTitle(context);
+  let newTitle = null;
+
+  const titlePrefix = getMatchingValueByKey(prefixLabels, labelAdded);
+  if (titlePrefix !== null) {
+    newTitle = addTitlePrefix(currentTitle, titlePrefix, Object.values(bracketPrefixLabels));
+  }
+
+  const bracketPrefix = getMatchingValueByKey(bracketPrefixLabels, labelAdded);
+  if (bracketPrefix !== null) {
+    newTitle = addBracketPrefix(currentTitle, bracketPrefix, Object.values(prefixLabels));
+  }
+
+  if (newTitle === null) {
+    core.info(`No title prefix configured for label "${labelAdded}".`);
+    return { updated: false, newTitle: currentTitle };
+  }
+
+  if (newTitle === currentTitle) {
+    core.info(`Title already includes the prefix for label "${labelAdded}".`);
+    return { updated: false, newTitle };
+  }
+
+  switch (context.eventName) {
+    case 'issues':
+      await github.rest.issues.update({
+        issue_number: context.issue.number,
+        owner: context.repo.owner,
+        repo: context.repo.repo,
+        title: newTitle,
+      });
+      break;
+
+    case 'pull_request_target':
+      await github.rest.pulls.update({
+        pull_number: context.issue.number,
+        owner: context.repo.owner,
+        repo: context.repo.repo,
+        title: newTitle,
+      });
+      break;
+
+    default:
+      throw new Error(`Unrecognized eventName: ${context.eventName}`);
+  }
+
+  return { updated: true, newTitle };
+}
+
+async function syncBreakingChangeLabelFromTitle({
+  github,
+  context,
+  core,
+  labelName = BREAKING_CHANGE_LABEL,
+  bracketPrefix = BREAKING_PREFIX,
+  titlePrefixes = Object.values(DEFAULT_PREFIX_LABELS),
+}) {
+  const pullRequest = context.payload.pull_request;
+  if (!pullRequest) {
+    throw new Error('This script must be run from a pull_request_target event.');
+  }
+
+  const title = pullRequest.title || '';
+  if (!hasBracketPrefix(title, bracketPrefix, titlePrefixes)) {
+    core.info(`Title does not include ${bracketPrefix} in the title prefix.`);
+    return { added: false };
+  }
+
+  const labels = pullRequest.labels?.map((label) => label.name).filter(Boolean) ?? [];
+  if (hasLabel(labels, labelName)) {
+    core.info(`PR already has the "${labelName}" label.`);
+    return { added: false };
+  }
+
+  await github.rest.issues.addLabels({
+    issue_number: context.issue.number,
+    owner: context.repo.owner,
+    repo: context.repo.repo,
+    labels: [labelName],
+  });
+
+  return { added: true };
+}
+
+module.exports = {
+  addBracketPrefix,
+  addTitlePrefix,
+  hasBracketPrefix,
+  syncBreakingChangeLabelFromTitle,
+  updateTitleForAddedLabel,
+};

.github/skills/pull-requests/SKILL.md

@@ -0,0 +1,116 @@
+---
+name: pull-requests
+description: >
+  Guidance for creating pull requests and handling PR review comments in the
+  Agent Framework repository. Use this when writing a PR description (filling out
+  the PR template) or when responding to and resolving review comments on an
+  existing PR.
+---
+
+# Pull Request Workflow
+
+This skill covers two tasks: (1) writing a high-quality PR description, and
+(2) handling review comments on an existing PR.
+
+## 1. Writing the PR description
+
+Always follow the repository PR template at
+[`.github/pull_request_template.md`](../../pull_request_template.md). Keep its
+exact structure and headings. Fill every section:
+
+### `### Motivation & Context`
+Explain *why* the change is needed: the problem it solves and the scenario it
+contributes to. Describe the net change relative to `main` — this is implied, so
+do **not** spell out "vs main" explicitly.
+
+### `### Description & Review Guide`
+Describe the changes, the overall approach, and the design. Answer the three
+prompts:
+- **What are the major changes?**
+- **What is the impact of these changes?**
+- **What do you want reviewers to focus on?** — This item is for **human
+  reviewers only**. Automated/AI reviewers must ignore it and review the entire
+  change rather than narrowing scope to it.
+
+### `### Related Issue`
+Link the issue the PR fixes using a GitHub closing keyword (`Fixes #123` /
+`Closes #123`) so it closes automatically on merge. A PR with no linked issue may
+be closed regardless of how valid the change is. Before opening, confirm there is
+no other open PR for the same issue; if there is, explain how this PR differs.
+
+### `### Contribution Checklist`
+Check every item that applies. For the breaking-change item:
+- Leave **"This is not a breaking change."** checked for the common case.
+- If the change **is** breaking, add the `breaking change` label **or** put
+  `[BREAKING]` in the title prefix, before or after a language prefix such as
+  `Python:` or `.NET:` — workflows keep the label and the title prefix in sync
+  automatically (see `.github/workflows/label-title-prefix.yml` and
+  `.github/workflows/label-pr.yml`).
+
+### Do not
+- Do **not** add ad-hoc sections such as "Validation" or "Tests run"; CI/CD and
+  the checklist already cover validation status.
+- Do **not** remove or reorder the template's headings.
+
+### Creating the PR
+Open new PRs as **drafts** until they are ready for review. Example:
+
+```bash
+gh pr create --repo microsoft/agent-framework --base main \
+  --head <your-fork-owner>:<branch> --draft \
+  --title "<concise title>" --body "<body following the template>"
+```
+
+## 2. Handling review comments
+
+When a PR receives review comments, follow this sequence — **do not start editing
+code before the user has reviewed the plan**:
+
+1. **Review the comments.** Read every review comment and thread on the PR,
+   including inline code comments and general review summaries.
+2. **Make a plan.** Produce a concrete plan describing how each comment will be
+   addressed (or why it should not be, with reasoning).
+3. **Let the user review the plan.** Present the plan and wait for the user's
+   approval or adjustments before implementing anything.
+4. **Implement.** Make the agreed changes.
+5. **Reply to every comment.** Add a reply to **all** comments explaining how it
+   was addressed (or the agreed outcome) — leave none unanswered.
+6. **Resolve resolved threads.** Mark a review thread as resolved only when the
+   comment has actually been addressed.
+
+### Useful commands
+
+List review comments and threads:
+
+```bash
+# Inline review comments
+gh api repos/{owner}/{repo}/pulls/{pr}/comments
+
+# Review threads with resolution state (GraphQL)
+gh api graphql -f query='
+  query($owner:String!,$repo:String!,$pr:Int!){
+    repository(owner:$owner,name:$repo){
+      pullRequest(number:$pr){
+        reviewThreads(first:100){
+          nodes{ id isResolved comments(first:50){ nodes{ id body author{login} } } }
+        }
+      }
+    }
+  }' -F owner={owner} -F repo={repo} -F pr={pr}
+```
+
+Reply to an inline review comment:
+
+```bash
+gh api repos/{owner}/{repo}/pulls/{pr}/comments/{comment_id}/replies \
+  -f body="Addressed in <commit>: <explanation>"
+```
+
+Resolve a review thread (needs the thread node id from the GraphQL query above):
+
+```bash
+gh api graphql -f query='
+  mutation($threadId:ID!){
+    resolveReviewThread(input:{threadId:$threadId}){ thread{ isResolved } }
+  }' -F threadId={thread_id}
+```

.github/tests/test_check_team_membership.js

@@ -0,0 +1,249 @@
+// Copyright (c) Microsoft. All rights reserved.
+
+/**
+ * Tests for check_team_membership.js.
+ *
+ * Run with: node --test .github/tests/test_check_team_membership.js
+ */
+
+const { describe, it } = require('node:test');
+const assert = require('node:assert/strict');
+
+const checkTeamMembership = require('../scripts/check_team_membership.js');
+
+
+// ---------------------------------------------------------------------------
+// Helpers
+// ---------------------------------------------------------------------------
+
+function createMocks({
+  payloadIssue = undefined,
+  payloadPullRequest = undefined,
+  apiUser = 'api-user',
+  teamState = 'active',
+} = {}) {
+  const core = {
+    _infoMessages: [],
+    _failedMessages: [],
+    info(msg) { this._infoMessages.push(msg); },
+    setFailed(msg) { this._failedMessages.push(msg); },
+  };
+
+  const payload = {};
+  if (payloadIssue !== undefined) {
+    payload.issue = payloadIssue;
+  }
+  if (payloadPullRequest !== undefined) {
+    payload.pull_request = payloadPullRequest;
+  }
+
+  const context = {
+    payload,
+    repo: { owner: 'test-org', repo: 'test-repo' },
+  };
+
+  const github = {
+    rest: {
+      issues: {
+        get: async () => ({
+          data: { user: apiUser ? { login: apiUser } : null },
+        }),
+      },
+      pulls: {
+        get: async () => ({
+          data: { user: apiUser ? { login: apiUser } : null },
+        }),
+      },
+      teams: {
+        getByName: async () => ({}),
+        getMembershipForUserInOrg: async () => ({
+          data: { state: teamState },
+        }),
+      },
+    },
+  };
+
+  return { core, context, github };
+}
+
+const BASE_OPTS = { teamSlug: 'my-team', issueNumber: '123' };
+
+
+// ---------------------------------------------------------------------------
+// Author resolution
+// ---------------------------------------------------------------------------
+
+describe('author resolution', () => {
+  it('uses an explicit username instead of the issue author', async () => {
+    const { github, context, core } = createMocks({
+      payloadIssue: { user: { login: 'issue-author' } },
+    });
+    let issuesGetCalled = false;
+    github.rest.issues.get = async () => {
+      issuesGetCalled = true;
+      return { data: { user: { login: 'api-user' } } };
+    };
+
+    const result = await checkTeamMembership({
+      github,
+      context,
+      core,
+      ...BASE_OPTS,
+      username: 'comment-author',
+    });
+
+    assert.equal(result.author, 'comment-author');
+    assert.equal(issuesGetCalled, false);
+  });
+
+  it('resolves author from event payload', async () => {
+    const { github, context, core } = createMocks({
+      payloadIssue: { user: { login: 'payload-user' } },
+    });
+    const result = await checkTeamMembership({ github, context, core, ...BASE_OPTS });
+    assert.equal(result.author, 'payload-user');
+  });
+
+  it('resolves author from pull_request event payload', async () => {
+    const { github, context, core } = createMocks({
+      payloadPullRequest: { user: { login: 'pr-author' } },
+    });
+    let issuesGetCalled = false;
+    github.rest.issues.get = async () => {
+      issuesGetCalled = true;
+      return { data: { user: { login: 'api-user' } } };
+    };
+
+    const result = await checkTeamMembership({ github, context, core, ...BASE_OPTS });
+    assert.equal(result.author, 'pr-author');
+    assert.equal(issuesGetCalled, false);
+  });
+
+  it('resolves author via pulls API when pull_request payload user is null', async () => {
+    const { github, context, core } = createMocks({
+      payloadPullRequest: { user: null },
+      apiUser: 'fetched-pr-author',
+    });
+    let pullsGetCalled = false;
+    github.rest.pulls.get = async () => {
+      pullsGetCalled = true;
+      return { data: { user: { login: 'fetched-pr-author' } } };
+    };
+
+    const result = await checkTeamMembership({ github, context, core, ...BASE_OPTS });
+    assert.equal(result.author, 'fetched-pr-author');
+    assert.equal(pullsGetCalled, true);
+  });
+
+  it('resolves author via API when payload issue is absent', async () => {
+    const { github, context, core } = createMocks({ apiUser: 'api-user' });
+    const result = await checkTeamMembership({ github, context, core, ...BASE_OPTS });
+    assert.equal(result.author, 'api-user');
+  });
+
+  it('resolves author via API when payload issue user is null (deleted account)', async () => {
+    const { github, context, core } = createMocks({
+      payloadIssue: { user: null },
+      apiUser: 'fetched-user',
+    });
+    const result = await checkTeamMembership({ github, context, core, ...BASE_OPTS });
+    assert.equal(result.author, 'fetched-user');
+  });
+
+  it('handles deleted account when API also returns null user', async () => {
+    const { github, context, core } = createMocks({ apiUser: null });
+    const result = await checkTeamMembership({ github, context, core, ...BASE_OPTS });
+    assert.equal(result.author, null);
+    assert.equal(result.isTeamMember, false);
+    assert.ok(core._failedMessages.some(m => m.includes('deleted')));
+  });
+});
+
+
+// ---------------------------------------------------------------------------
+// Team lookup
+// ---------------------------------------------------------------------------
+
+describe('team lookup', () => {
+  it('fails the job when team lookup errors', async () => {
+    const { github, context, core } = createMocks({
+      payloadIssue: { user: { login: 'user1' } },
+    });
+    const error = new Error('Bad credentials');
+    github.rest.teams.getByName = async () => { throw error; };
+
+    await assert.rejects(
+      () => checkTeamMembership({ github, context, core, ...BASE_OPTS }),
+      (err) => err === error,
+    );
+    assert.ok(core._failedMessages.some(m => m.includes('Team lookup failed')));
+  });
+});
+
+
+// ---------------------------------------------------------------------------
+// Team membership
+// ---------------------------------------------------------------------------
+
+describe('team membership', () => {
+  it('returns true for active team member', async () => {
+    const { github, context, core } = createMocks({
+      payloadIssue: { user: { login: 'member' } },
+      teamState: 'active',
+    });
+    const result = await checkTeamMembership({ github, context, core, ...BASE_OPTS });
+    assert.equal(result.isTeamMember, true);
+  });
+
+  it('returns false for pending team member', async () => {
+    const { github, context, core } = createMocks({
+      payloadIssue: { user: { login: 'pending-user' } },
+      teamState: 'pending',
+    });
+    const result = await checkTeamMembership({ github, context, core, ...BASE_OPTS });
+    assert.equal(result.isTeamMember, false);
+  });
+
+  it('treats 404 membership response as non-member without failing', async () => {
+    const { github, context, core } = createMocks({
+      payloadIssue: { user: { login: 'outsider' } },
+    });
+    const notFoundError = new Error('Not Found');
+    notFoundError.status = 404;
+    github.rest.teams.getMembershipForUserInOrg = async () => { throw notFoundError; };
+
+    const result = await checkTeamMembership({ github, context, core, ...BASE_OPTS });
+    assert.equal(result.isTeamMember, false);
+    assert.equal(core._failedMessages.length, 0);
+    assert.ok(core._infoMessages.some(m => m.includes('not a member')));
+  });
+
+  it('fails the job on non-404 membership errors', async () => {
+    const { github, context, core } = createMocks({
+      payloadIssue: { user: { login: 'user1' } },
+    });
+    const serverError = new Error('Internal Server Error');
+    serverError.status = 500;
+    github.rest.teams.getMembershipForUserInOrg = async () => { throw serverError; };
+
+    await assert.rejects(
+      () => checkTeamMembership({ github, context, core, ...BASE_OPTS }),
+      (err) => err === serverError,
+    );
+    assert.ok(core._failedMessages.some(m => m.includes('membership lookup failed')));
+  });
+
+  it('fails the job on membership errors without status code', async () => {
+    const { github, context, core } = createMocks({
+      payloadIssue: { user: { login: 'user1' } },
+    });
+    const networkError = new Error('ECONNREFUSED');
+    github.rest.teams.getMembershipForUserInOrg = async () => { throw networkError; };
+
+    await assert.rejects(
+      () => checkTeamMembership({ github, context, core, ...BASE_OPTS }),
+      (err) => err === networkError,
+    );
+    assert.ok(core._failedMessages.some(m => m.includes('membership lookup failed')));
+  });
+});

.github/tests/test_create_github_app_token.js

@@ -0,0 +1,125 @@
+// Copyright (c) Microsoft. All rights reserved.
+
+const { describe, it } = require('node:test');
+const assert = require('node:assert/strict');
+
+const {
+  base64ToBase64Url,
+  createInstallationToken,
+  createJwtSigningInput,
+  readConfig,
+} = require('../actions/github-app-token/create-token.js');
+
+const CONFIG = {
+  azureSubscriptionId: 'subscription-id',
+  keyVaultName: 'vault-name',
+  keyName: 'key-name',
+  githubAppClientId: 'client-id',
+  githubAppInstallationId: '12345',
+  targetRepository: 'microsoft/agent-framework',
+};
+
+describe('GitHub App token creation', () => {
+  it('creates a short-lived GitHub App JWT', () => {
+    const signingInput = createJwtSigningInput('client-id', 1_000);
+    const [encodedHeader, encodedPayload] = signingInput.split('.');
+    const header = JSON.parse(Buffer.from(encodedHeader, 'base64url').toString());
+    const payload = JSON.parse(Buffer.from(encodedPayload, 'base64url').toString());
+
+    assert.deepEqual(header, { alg: 'RS256', typ: 'JWT' });
+    assert.deepEqual(payload, { iat: 940, exp: 1_540, iss: 'client-id' });
+  });
+
+  it('converts Key Vault signatures to unpadded base64url', () => {
+    assert.equal(base64ToBase64Url('+/8='), '-_8');
+  });
+
+  it('requests a repository-scoped installation token', async () => {
+    let request;
+    const token = await createInstallationToken(CONFIG, {
+      nowSeconds: 1_000,
+      execute: (command, args) => {
+        assert.equal(command, 'az');
+        assert.ok(args.includes('RS256'));
+        return '+/8=\n';
+      },
+      fetch: async (url, options) => {
+        request = { url, options };
+        return {
+          ok: true,
+          json: async () => ({ token: 'installation-token' }),
+        };
+      },
+    });
+
+    assert.equal(token, 'installation-token');
+    assert.equal(request.url, 'https://api.github.com/app/installations/12345/access_tokens');
+    assert.match(request.options.headers.Authorization, /^Bearer [^.]+\.[^.]+\.-_8$/);
+    assert.deepEqual(JSON.parse(request.options.body), {
+      repositories: ['agent-framework'],
+      permissions: {
+        contents: 'read',
+        issues: 'write',
+        members: 'read',
+        pull_requests: 'write',
+      },
+    });
+  });
+
+  it('rejects incomplete configuration', () => {
+    assert.throws(
+      () => readConfig({}),
+      /Required GitHub App authentication configuration is missing/,
+    );
+  });
+
+  it('rejects repository values with extra path segments before signing', async () => {
+    let signed = false;
+
+    await assert.rejects(
+      createInstallationToken(
+        { ...CONFIG, targetRepository: 'microsoft/agent-framework/extra' },
+        {
+          execute: () => {
+            signed = true;
+            return '+/8=\n';
+          },
+        },
+      ),
+      /TARGET_REPOSITORY must use the owner\/repository format/,
+    );
+    assert.equal(signed, false);
+  });
+
+  it('rejects an empty Key Vault signature', async () => {
+    await assert.rejects(
+      createInstallationToken(CONFIG, {
+        execute: () => '\n',
+      }),
+      /Key Vault returned an empty signature/,
+    );
+  });
+
+  it('rejects a failed GitHub token request', async () => {
+    await assert.rejects(
+      createInstallationToken(CONFIG, {
+        execute: () => '+/8=\n',
+        fetch: async () => ({ ok: false, status: 403 }),
+      }),
+      /GitHub installation token request failed with HTTP 403/,
+    );
+  });
+
+  it('rejects an empty GitHub installation token', async () => {
+    await assert.rejects(
+      createInstallationToken(CONFIG, {
+        execute: () => '+/8=\n',
+        fetch: async () => ({
+          ok: true,
+          json: async () => ({ token: '' }),
+        }),
+      }),
+      /GitHub returned an empty installation token/,
+    );
+  });
+});

.github/tests/test_pr_limit_moderation.js

@@ -0,0 +1,341 @@
+// Copyright (c) Microsoft. All rights reserved.
+
+/**
+ * Tests for pr_limit_moderation.js.
+ *
+ * Run with: node --test .github/tests/test_pr_limit_moderation.js
+ */
+
+const { describe, it } = require('node:test');
+const assert = require('node:assert/strict');
+
+const { enforcePrLimit } = require('../scripts/pr_limit_moderation.js');
+
+
+// ---------------------------------------------------------------------------
+// Helpers
+// ---------------------------------------------------------------------------
+
+function createContext({ author = 'community-user', authorType = 'User', labels = [], number = 123 } = {}) {
+  return {
+    repo: {
+      owner: 'microsoft',
+      repo: 'agent-framework',
+    },
+    payload: {
+      pull_request: {
+        number,
+        labels: labels.map((name) => ({ name })),
+        user: {
+          login: author,
+          type: authorType,
+        },
+      },
+    },
+  };
+}
+
+function createCore() {
+  const messages = [];
+  return {
+    messages,
+    info(message) {
+      messages.push(message);
+    },
+  };
+}
+
+function createGithub({
+  itemNumbers,
+  labelExists = true,
+  pullRequests = createPullRequestPage({ numbers: itemNumbers }),
+}) {
+  const calls = [];
+
+  return {
+    calls,
+    async paginate(method, params) {
+      calls.push({ api: 'paginate', method, params });
+      return pullRequests;
+    },
+    rest: {
+      issues: {
+        async getLabel(params) {
+          calls.push({ api: 'issues.getLabel', params });
+          if (!labelExists) {
+            const error = new Error('Not Found');
+            error.status = 404;
+            throw error;
+          }
+          return { data: { name: params.name } };
+        },
+        async createLabel(params) {
+          calls.push({ api: 'issues.createLabel', params });
+          return { data: { name: params.name } };
+        },
+        async addLabels(params) {
+          calls.push({ api: 'issues.addLabels', params });
+          return { data: [] };
+        },
+        async createComment(params) {
+          calls.push({ api: 'issues.createComment', params });
+          return { data: { id: 1 } };
+        },
+      },
+      pulls: {
+        async list(params) {
+          calls.push({ api: 'pulls.list', params });
+          return { data: pullRequests };
+        },
+        async update(params) {
+          calls.push({ api: 'pulls.update', params });
+          return { data: { state: params.state } };
+        },
+      },
+    },
+  };
+}
+
+function createPullRequestPage({ author = 'community-user', numbers }) {
+  return numbers.map((number) => ({
+    number,
+    user: {
+      login: author,
+    },
+  }));
+}
+
+
+// ---------------------------------------------------------------------------
+// PR limit enforcement
+// ---------------------------------------------------------------------------
+
+describe('PR limit enforcement', () => {
+  it('does not close the PR when the author is at the open PR limit', async () => {
+    const github = createGithub({
+      itemNumbers: [1, 2, 3, 4, 5, 6, 7, 8, 9, 123],
+    });
+
+    const result = await enforcePrLimit({
+      github,
+      context: createContext(),
+      core: createCore(),
+      exemptLabelName: 'pr-limit-exempt',
+      maxOpenPrs: 10,
+      labelName: 'too-many-prs',
+    });
+
+    assert.equal(result.closed, false);
+    assert.equal(result.openPrCount, 10);
+    assert.deepEqual(
+      github.calls.map((call) => call.api),
+      ['paginate'],
+    );
+  });
+
+  it('counts the new PR when the pull list includes it', async () => {
+    const github = createGithub({
+      itemNumbers: [123, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10],
+    });
+
+    const result = await enforcePrLimit({
+      github,
+      context: createContext(),
+      core: createCore(),
+      exemptLabelName: 'pr-limit-exempt',
+      maxOpenPrs: 10,
+      labelName: 'too-many-prs',
+    });
+
+    assert.equal(result.closed, true);
+    assert.equal(result.openPrCount, 11);
+    assert.deepEqual(
+      github.calls.map((call) => call.api),
+      [
+        'paginate',
+        'issues.getLabel',
+        'issues.addLabels',
+        'issues.createComment',
+        'pulls.update',
+      ],
+    );
+  });
+
+  it('counts the current PR on top of existing open PRs', async () => {
+    const github = createGithub({
+      itemNumbers: [123, ...Array.from({ length: 24 }, (_, index) => index + 1)],
+      pullRequests: createPullRequestPage({
+        numbers: [123, ...Array.from({ length: 25 }, (_, index) => index + 1)],
+      }),
+    });
+
+    const result = await enforcePrLimit({
+      github,
+      context: createContext(),
+      core: createCore(),
+      exemptLabelName: 'pr-limit-exempt',
+      maxOpenPrs: 10,
+      labelName: 'too-many-prs',
+    });
+
+    assert.equal(result.closed, true);
+    assert.equal(result.openPrCount, 26);
+    const comment = github.calls.find((call) => call.api === 'issues.createComment').params.body;
+    assert.match(comment, /This PR would put you at 26 open pull requests/);
+  });
+
+  it('creates the label when it does not already exist', async () => {
+    const github = createGithub({
+      itemNumbers: [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 123],
+      labelExists: false,
+    });
+
+    const result = await enforcePrLimit({
+      github,
+      context: createContext(),
+      core: createCore(),
+      exemptLabelName: 'pr-limit-exempt',
+      maxOpenPrs: 10,
+      labelName: 'too-many-prs',
+    });
+
+    assert.equal(result.closed, true);
+    assert.deepEqual(
+      github.calls.map((call) => call.api),
+      [
+        'paginate',
+        'issues.getLabel',
+        'issues.createLabel',
+        'issues.addLabels',
+        'issues.createComment',
+        'pulls.update',
+      ],
+    );
+    assert.equal(
+      github.calls.find((call) => call.api === 'issues.createLabel').params.name,
+      'too-many-prs',
+    );
+  });
+
+  it('tolerates a 422 race when creating the label', async () => {
+    const github = createGithub({
+      itemNumbers: [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 123],
+      labelExists: false,
+    });
+    github.rest.issues.createLabel = async (params) => {
+      github.calls.push({ api: 'issues.createLabel', params });
+      const error = new Error('Validation Failed');
+      error.status = 422;
+      throw error;
+    };
+
+    const result = await enforcePrLimit({
+      github,
+      context: createContext(),
+      core: createCore(),
+      exemptLabelName: 'pr-limit-exempt',
+      maxOpenPrs: 10,
+      labelName: 'too-many-prs',
+    });
+
+    assert.equal(result.closed, true);
+    assert.deepEqual(
+      github.calls.map((call) => call.api),
+      [
+        'paginate',
+        'issues.getLabel',
+        'issues.createLabel',
+        'issues.addLabels',
+        'issues.createComment',
+        'pulls.update',
+      ],
+    );
+  });
+
+  it('uses a diplomatic close message with the configured limit', async () => {
+    const github = createGithub({
+      itemNumbers: [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 123],
+      pullRequests: createPullRequestPage({
+        author: 'octo-contributor',
+        numbers: [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 123],
+      }),
+    });
+
+    await enforcePrLimit({
+      github,
+      context: createContext({ author: 'octo-contributor' }),
+      core: createCore(),
+      exemptLabelName: 'pr-limit-exempt',
+      maxOpenPrs: 10,
+      labelName: 'too-many-prs',
+    });
+
+    const comment = github.calls.find((call) => call.api === 'issues.createComment').params.body;
+    assert.match(comment, /Thank you for your contribution/);
+    assert.match(comment, /limit community contributors to 10 open pull requests/);
+    assert.match(comment, /@octo-contributor/);
+    assert.match(comment, /`pr-limit-exempt` label and reopen/);
+  });
+
+  it('does not close an exempt PR when it is reopened', async () => {
+    const github = createGithub({
+      itemNumbers: [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 123],
+    });
+
+    const result = await enforcePrLimit({
+      github,
+      context: createContext({ labels: ['PR-LIMIT-EXEMPT'] }),
+      core: createCore(),
+      exemptLabelName: 'pr-limit-exempt',
+      maxOpenPrs: 10,
+      labelName: 'too-many-prs',
+    });
+
+    assert.equal(result.closed, false);
+    assert.equal(result.exempt, true);
+    assert.equal(result.openPrCount, null);
+    assert.deepEqual(github.calls, []);
+  });
+
+  it('does not close Dependabot PRs', async () => {
+    const github = createGithub({
+      itemNumbers: [123, ...Array.from({ length: 25 }, (_, index) => index + 1)],
+      pullRequests: createPullRequestPage({
+        author: 'dependabot[bot]',
+        numbers: [123, ...Array.from({ length: 25 }, (_, index) => index + 1)],
+      }),
+    });
+
+    const result = await enforcePrLimit({
+      github,
+      context: createContext({ author: 'dependabot[bot]', authorType: 'Bot' }),
+      core: createCore(),
+      exemptLabelName: 'pr-limit-exempt',
+      maxOpenPrs: 10,
+      labelName: 'too-many-prs',
+    });
+
+    assert.equal(result.closed, false);
+    assert.equal(result.dependabotExempt, true);
+    assert.equal(result.openPrCount, null);
+    assert.deepEqual(github.calls, []);
+  });
+
+  it('counts the current PR when the author has more than one page of open PRs', async () => {
+    const github = createGithub({
+      itemNumbers: [123, ...Array.from({ length: 100 }, (_, index) => index + 1)],
+    });
+
+    const result = await enforcePrLimit({
+      github,
+      context: createContext({ number: 123 }),
+      core: createCore(),
+      exemptLabelName: 'pr-limit-exempt',
+      maxOpenPrs: 10,
+      labelName: 'too-many-prs',
+    });
+
+    assert.equal(result.closed, true);
+    assert.equal(result.openPrCount, 101);
+  });
+});

.github/tests/test_python_check_coverage.py

@@ -0,0 +1,134 @@
+# Copyright (c) Microsoft. All rights reserved.
+
+# ruff:file-ignore[implicit-namespace-package, undocumented-public-class, undocumented-public-method]
+
+from __future__ import annotations
+
+import importlib.util
+import sys
+import tempfile
+import unittest
+from pathlib import Path
+
+SCRIPT_PATH = Path(__file__).parents[1] / "scripts" / "python_check_coverage.py"
+SPEC = importlib.util.spec_from_file_location("python_check_coverage", SCRIPT_PATH)
+if SPEC is None or SPEC.loader is None:
+    raise RuntimeError(f"Unable to load {SCRIPT_PATH}")
+coverage_checker = importlib.util.module_from_spec(SPEC)
+sys.modules[SPEC.name] = coverage_checker
+SPEC.loader.exec_module(coverage_checker)
+
+
+class CoveragePolicyTests(unittest.TestCase):
+    def setUp(self) -> None:
+        self.temp_dir = tempfile.TemporaryDirectory()
+        self.root = Path(self.temp_dir.name)
+        self.packages_dir = self.root / "packages"
+        self.packages_dir.mkdir()
+
+    def tearDown(self) -> None:
+        self.temp_dir.cleanup()
+
+    def write_package(self, directory: str, name: str, status: str) -> None:
+        package_dir = self.packages_dir / directory
+        package_dir.mkdir()
+        (package_dir / "pyproject.toml").write_text(
+            f"""
+[project]
+name = "{name}"
+classifiers = ["Development Status :: {status}"]
+""".strip()
+        )
+
+    def write_coverage(self, files: dict[str, list[int]]) -> Path:
+        classes = []
+        total_lines = 0
+        covered_lines = 0
+        for file_path, hits in files.items():
+            lines = []
+            for line_number, hit_count in enumerate(hits, start=1):
+                total_lines += 1
+                covered_lines += hit_count > 0
+                lines.append(f'<line number="{line_number}" hits="{hit_count}"/>')
+            classes.append(f'<class filename="{file_path}"><lines>{"".join(lines)}</lines></class>')
+
+        line_rate = covered_lines / total_lines if total_lines else 0
+        xml_path = self.root / "coverage.xml"
+        xml_path.write_text(
+            f"""
+<coverage line-rate="{line_rate}" branch-rate="0">
+  <packages>
+    <package name="test">
+      <classes>{"".join(classes)}</classes>
+    </package>
+  </packages>
+</coverage>
+""".strip()
+        )
+        return xml_path
+
+    def test_load_package_policies_uses_lifecycle_exemptions(self) -> None:
+        self.write_package("alpha", "agent-framework-alpha", "3 - Alpha")
+        self.write_package("beta", "agent-framework-beta", "4 - Beta")
+        self.write_package("stable", "agent-framework-stable", "5 - Production/Stable")
+        self.write_package("devui", "agent-framework-devui", "4 - Beta")
+        self.write_package("lab", "agent-framework-lab", "4 - Beta")
+
+        policies = {policy.directory: policy for policy in coverage_checker.load_package_policies(self.packages_dir)}
+
+        self.assertFalse(policies["alpha"].enforced)
+        self.assertTrue(policies["beta"].enforced)
+        self.assertTrue(policies["stable"].enforced)
+        self.assertTrue(policies["devui"].exempt)
+        self.assertFalse(policies["devui"].enforced)
+        self.assertTrue(policies["lab"].exempt)
+        self.assertFalse(policies["lab"].enforced)
+
+    def test_load_package_policies_rejects_missing_lifecycle(self) -> None:
+        package_dir = self.packages_dir / "missing"
+        package_dir.mkdir()
+        (package_dir / "pyproject.toml").write_text('[project]\nname = "agent-framework-missing"\n')
+
+        with self.assertRaisesRegex(ValueError, "exactly one Development Status"):
+            coverage_checker.load_package_policies(self.packages_dir)
+
+    def test_parse_coverage_aggregates_nested_modules_by_distribution(self) -> None:
+        xml_path = self.write_coverage({
+            "packages/core/agent_framework/_agents.py": [1, 0],
+            "packages/core/agent_framework/_workflows/_workflow.py": [1, 1],
+        })
+
+        package_stats, _, _ = coverage_checker.parse_coverage_xml(xml_path)
+
+        self.assertEqual(package_stats["core"].lines_valid, 4)
+        self.assertEqual(package_stats["core"].lines_covered, 3)
+
+    def test_beta_package_below_threshold_fails(self) -> None:
+        self.write_package("beta", "agent-framework-beta", "4 - Beta")
+        xml_path = self.write_coverage({"packages/beta/agent_framework_beta/client.py": [1, 0]})
+
+        self.assertFalse(coverage_checker.check_coverage(xml_path, 85, self.packages_dir))
+
+    def test_missing_beta_package_fails(self) -> None:
+        self.write_package("beta", "agent-framework-beta", "4 - Beta")
+        xml_path = self.write_coverage({})
+
+        self.assertFalse(coverage_checker.check_coverage(xml_path, 85, self.packages_dir))
+
+    def test_alpha_and_exempt_packages_do_not_fail(self) -> None:
+        self.write_package("alpha", "agent-framework-alpha", "3 - Alpha")
+        self.write_package("devui", "agent-framework-devui", "4 - Beta")
+        self.write_package("lab", "agent-framework-lab", "4 - Beta")
+        xml_path = self.write_coverage({})
+
+        self.assertTrue(coverage_checker.check_coverage(xml_path, 85, self.packages_dir))
+
+    def test_beta_package_at_threshold_passes(self) -> None:
+        self.write_package("beta", "agent-framework-beta", "4 - Beta")
+        xml_path = self.write_coverage({"packages/beta/agent_framework_beta/client.py": [1] * 17 + [0] * 3})
+
+        self.assertTrue(coverage_checker.check_coverage(xml_path, 85, self.packages_dir))
+
+
+if __name__ == "__main__":
+    unittest.main()

.github/tests/test_resolve_integration_test_target.js

@@ -0,0 +1,212 @@
+// Copyright (c) Microsoft. All rights reserved.
+
+/**
+ * Tests for resolve_integration_test_target.js.
+ *
+ * Run with: node --test .github/tests/test_resolve_integration_test_target.js
+ */
+
+const { describe, it } = require('node:test');
+const assert = require('node:assert/strict');
+
+const resolveIntegrationTestTarget = require('../scripts/resolve_integration_test_target.js');
+
+const HEAD_SHA = 'a'.repeat(40);
+const BASE_SHA = 'b'.repeat(40);
+
+function review({
+  id,
+  login,
+  state = 'APPROVED',
+  commitId = HEAD_SHA,
+  submittedAt = `2026-07-13T00:00:${String(id).padStart(2, '0')}Z`,
+}) {
+  return {
+    id,
+    state,
+    commit_id: commitId,
+    submitted_at: submittedAt,
+    user: { login },
+  };
+}
+
+function createMocks({
+  pullState = 'open',
+  pullAuthor = 'contributor',
+  reviews = [],
+  permissions = {},
+} = {}) {
+  const core = {
+    infoMessages: [],
+    info(message) {
+      this.infoMessages.push(message);
+    },
+  };
+  const context = {
+    repo: { owner: 'microsoft', repo: 'agent-framework' },
+  };
+  const github = {
+    paginate: async () => reviews,
+    rest: {
+      pulls: {
+        get: async () => ({
+          data: {
+            state: pullState,
+            user: { login: pullAuthor },
+            head: { sha: HEAD_SHA },
+            base: { sha: BASE_SHA },
+          },
+        }),
+        listReviews: async () => {},
+      },
+      repos: {
+        get: async () => ({ data: { default_branch: 'main' } }),
+        getBranch: async ({ branch }) => ({
+          data: { commit: { sha: branch === 'main' ? BASE_SHA : HEAD_SHA } },
+        }),
+        getCollaboratorPermissionLevel: async ({ username }) => ({
+          data: permissions[username] || {
+            permission: 'read',
+            user: { permissions: { push: false } },
+          },
+        }),
+      },
+    },
+  };
+
+  return { core, context, github };
+}
+
+const WRITE_PERMISSION = {
+  permission: 'write',
+  user: { permissions: { push: true } },
+};
+
+describe('input validation', () => {
+  it('rejects missing and conflicting targets', async () => {
+    const mocks = createMocks();
+    await assert.rejects(
+      () => resolveIntegrationTestTarget(mocks),
+      /provide either a PR number or a branch name/,
+    );
+    await assert.rejects(
+      () => resolveIntegrationTestTarget({ ...mocks, prNumber: '1', branch: 'feature' }),
+      /not both/,
+    );
+  });
+
+  it('rejects invalid PR numbers and branch names', async () => {
+    const mocks = createMocks();
+    await assert.rejects(
+      () => resolveIntegrationTestTarget({ ...mocks, prNumber: '1;echo' }),
+      /Invalid PR number/,
+    );
+    await assert.rejects(
+      () => resolveIntegrationTestTarget({ ...mocks, branch: 'feature branch' }),
+      /Invalid branch name/,
+    );
+  });
+});
+
+describe('pull request resolution', () => {
+  it('pins an open PR with two fresh write-capable approvals', async () => {
+    const mocks = createMocks({
+      reviews: [
+        review({ id: 1, login: 'maintainer-one' }),
+        review({ id: 2, login: 'maintainer-two' }),
+      ],
+      permissions: {
+        'maintainer-one': WRITE_PERMISSION,
+        'maintainer-two': WRITE_PERMISSION,
+      },
+    });
+
+    const result = await resolveIntegrationTestTarget({ ...mocks, prNumber: '123' });
+
+    assert.deepEqual(result, {
+      baseRef: BASE_SHA,
+      checkoutRef: HEAD_SHA,
+      description: 'PR #123',
+    });
+  });
+
+  it('rejects closed PRs', async () => {
+    const mocks = createMocks({ pullState: 'closed' });
+    await assert.rejects(
+      () => resolveIntegrationTestTarget({ ...mocks, prNumber: '123' }),
+      /is not open/,
+    );
+  });
+
+  it('ignores stale, self, and read-only approvals', async () => {
+    const mocks = createMocks({
+      reviews: [
+        review({ id: 1, login: 'stale', commitId: 'c'.repeat(40) }),
+        review({ id: 2, login: 'contributor' }),
+        review({ id: 3, login: 'reader' }),
+        review({ id: 4, login: 'maintainer' }),
+      ],
+      permissions: {
+        contributor: WRITE_PERMISSION,
+        reader: { permission: 'read', user: { permissions: { push: false } } },
+        maintainer: WRITE_PERMISSION,
+      },
+    });
+
+    await assert.rejects(
+      () => resolveIntegrationTestTarget({ ...mocks, prNumber: '123' }),
+      /found 1/,
+    );
+  });
+
+  it('uses each reviewer latest decisive review and ignores later comments', async () => {
+    const mocks = createMocks({
+      reviews: [
+        review({ id: 1, login: 'changes-requested' }),
+        review({ id: 2, login: 'changes-requested', state: 'CHANGES_REQUESTED' }),
+        review({ id: 3, login: 'maintainer-one' }),
+        review({ id: 4, login: 'maintainer-one', state: 'COMMENTED' }),
+        review({ id: 5, login: 'maintainer-two' }),
+      ],
+      permissions: {
+        'changes-requested': WRITE_PERMISSION,
+        'maintainer-one': WRITE_PERMISSION,
+        'maintainer-two': WRITE_PERMISSION,
+      },
+    });
+
+    const result = await resolveIntegrationTestTarget({ ...mocks, prNumber: '123' });
+    assert.equal(result.checkoutRef, HEAD_SHA);
+  });
+
+  it('does not count a dismissed approval', async () => {
+    const mocks = createMocks({
+      reviews: [
+        review({ id: 1, login: 'dismissed', state: 'DISMISSED' }),
+        review({ id: 2, login: 'maintainer' }),
+      ],
+      permissions: {
+        dismissed: WRITE_PERMISSION,
+        maintainer: WRITE_PERMISSION,
+      },
+    });
+
+    await assert.rejects(
+      () => resolveIntegrationTestTarget({ ...mocks, prNumber: '123' }),
+      /found 1/,
+    );
+  });
+});
+
+describe('branch resolution', () => {
+  it('pins base-repository branches and their comparison base to SHAs', async () => {
+    const mocks = createMocks();
+    const result = await resolveIntegrationTestTarget({ ...mocks, branch: 'feature/test' });
+
+    assert.deepEqual(result, {
+      baseRef: BASE_SHA,
+      checkoutRef: HEAD_SHA,
+      description: 'branch feature/test',
+    });
+  });
+});

.github/upgrades/prompts/SemanticKernelToAgentFramework.md

@@ -23,16 +23,16 @@ For each project that needs to be migrated, you need to do the following:
 - Identify the specific Semantic Kernel agent types being used:
   - `ChatCompletionAgent` → `ChatClientAgent`
   - `OpenAIAssistantAgent` → `assistantsClient.CreateAIAgent()` (via OpenAI Assistants client extension)
-  - `AzureAIAgent` → `persistentAgentsClient.CreateAIAgent()` (via Azure AI Foundry client extension)
+  - `AzureAIAgent` → `persistentAgentsClient.CreateAIAgent()` (via Microsoft Foundry client extension)
   - `OpenAIResponseAgent` → `responsesClient.CreateAIAgent()` (via OpenAI Responses client extension)
   - `A2AAgent` → `AIAgent` (via A2A card resolver)
   - `BedrockAgent` → Custom implementation required (not supported)
 - Determine if agents are being created new or retrieved from hosted services:
   - **New agents**: Use `CreateAIAgent()` methods
-  - **Existing hosted agents**: Use `GetAIAgent(agentId)` methods for OpenAI Assistants and Azure AI Foundry
+  - **Existing hosted agents**: Use `GetAIAgent(agentId)` methods for OpenAI Assistants and Microsoft Foundry
 </agent_type_identification>
 
-- Determine the AI provider being used (OpenAI, Azure OpenAI, Azure AI Foundry, etc.)
+- Determine the AI provider being used (OpenAI, Azure OpenAI, Microsoft Foundry, etc.)
 - Analyze tool/function registration patterns
 - Review thread management and invocation patterns
 
@@ -90,7 +90,7 @@ below in wrong order or skip any of them):
    you generate report when migration complete. Report should contain:
      - all project dependencies changes (mention what was changed, added or removed, including provider-specific packages)
      - all code files that were changed (mention what was changed in the file, if it was not changed, just mention that the file was not changed)
-     - provider-specific migration patterns used (OpenAI, Azure OpenAI, Azure AI Foundry, A2A, ONNX, etc.)
+     - provider-specific migration patterns used (OpenAI, Azure OpenAI, Microsoft Foundry, A2A, ONNX, etc.)
      - all cases where you could not convert the code because of unsupported features and you were unable to find a workaround
      - unsupported providers that require custom implementation (Bedrock, CopilotStudio)
      - breaking glass pattern migrations (InnerContent → RawRepresentation) and any CodeInterpreter or advanced tool usage
@@ -223,7 +223,7 @@ using Microsoft.Agents.AI;
 // Provider-specific namespaces (add only if needed):
 using OpenAI; // For OpenAI provider
 using Azure.AI.OpenAI; // For Azure OpenAI provider
-using Azure.AI.Agents.Persistent; // For Azure AI Foundry provider
+using Azure.AI.Agents.Persistent; // For Microsoft Foundry provider
 using Azure.Identity; // For Azure authentication
 ```
 </configuration_changes>
@@ -499,7 +499,7 @@ For every thread created if there's intent to cleanup, the caller should track a
 var assistantClient = new OpenAIClient(apiKey).GetAssistantClient();
 await assistantClient.DeleteThreadAsync(thread.ConversationId);
 
-// For Azure AI Foundry (when cleanup is needed):
+// For Microsoft Foundry (when cleanup is needed):
 var persistentClient = new PersistentAgentsClient(endpoint, credential);
 await persistentClient.Threads.DeleteThreadAsync(thread.ConversationId);
 
@@ -514,7 +514,7 @@ await persistentClient.Threads.DeleteThreadAsync(thread.ConversationId);
 1. Remove `thread.DeleteAsync()` calls
 2. Use provider-specific client for cleanup when required
 3. Access thread ID via `thread.ConversationId` property
-4. Only implement cleanup for providers that require it (Assistants, Azure AI Foundry)
+4. Only implement cleanup for providers that require it (Assistants, Microsoft Foundry)
 </api_changes>
 
 ### Provider-Specific Creation Patterns
@@ -550,13 +550,13 @@ AIAgent agent = new AzureOpenAIClient(endpoint, credential)
     .CreateAIAgent(instructions: instructions);
 ```
 
-**Azure AI Foundry (New):**
+**Microsoft Foundry (New):**
 ```csharp
 AIAgent agent = new PersistentAgentsClient(endpoint, credential)
     .CreateAIAgent(model: deploymentName, instructions: instructions);
 ```
 
-**Azure AI Foundry (Existing):**
+**Microsoft Foundry (Existing):**
 ```csharp
 AIAgent agent = await new PersistentAgentsClient(endpoint, credential)
     .GetAIAgentAsync(agentId);
@@ -1079,7 +1079,7 @@ AgentThread thread = agent.GetNewThread();
 ```
 </api_changes>
 
-### 4. Azure AI Foundry (AzureAIAgent) Migration
+### 4. Microsoft Foundry (AzureAIAgent) Migration
 
 <configuration_changes>
 **Remove Semantic Kernel Packages:**

.github/workflows/codeql-analysis.yml

@@ -32,13 +32,13 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v6
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
         with:
           persist-credentials: false
 
       # Initializes the CodeQL tools for scanning.
       - name: Initialize CodeQL
-        uses: github/codeql-action/init@v4
+        uses: github/codeql-action/init@99df26d4f13ea111d4ec1a7dddef6063f76b97e9 # v4
         with:
           languages: ${{ matrix.language }}
           # If you wish to specify custom queries, you can do so here or in a config file.
@@ -51,7 +51,7 @@ jobs:
       # Autobuild attempts to build any compiled languages  (C/C++, C#, Go, or Java).
       # If this step fails, then you should remove it and run the build manually (see below)
       - name: Autobuild
-        uses: github/codeql-action/autobuild@v4
+        uses: github/codeql-action/autobuild@99df26d4f13ea111d4ec1a7dddef6063f76b97e9 # v4
 
       # ℹ️ Command-line programs to run using the OS shell.
       # 📚 See https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions#jobsjob_idstepsrun
@@ -64,6 +64,6 @@ jobs:
       #     ./location_of_script_within_repo/buildscript.sh
 
       - name: Perform CodeQL Analysis
-        uses: github/codeql-action/analyze@v4
+        uses: github/codeql-action/analyze@99df26d4f13ea111d4ec1a7dddef6063f76b97e9 # v4
         with:
           category: "/language:${{matrix.language}}"

.github/workflows/devflow-pr-review.yml

@@ -0,0 +1,215 @@
+name: DevFlow PR Review
+
+on:
+  pull_request_target:
+    types:
+      - opened
+      - reopened
+      - ready_for_review
+  issue_comment:
+    types:
+      - created
+  workflow_dispatch:
+    inputs:
+      pr_number:
+        description: Pull request number to review
+        required: true
+        type: string
+
+permissions:
+  contents: read
+  id-token: write
+  issues: write
+  pull-requests: write
+
+concurrency:
+  group: devflow-pr-review-${{ github.repository }}-${{ github.event.pull_request.number || github.event.issue.number || inputs.pr_number || github.run_id }}
+  cancel-in-progress: true
+
+env:
+  DEVFLOW_REPOSITORY: ${{ vars.DF_REPO }}
+  DEVFLOW_REF: main
+  TARGET_REPO_PATH: ${{ github.workspace }}/target-repo
+  DEVFLOW_PATH: ${{ github.workspace }}/devflow
+  MODEL_CONFIG_PATH: ${{ github.workspace }}/devflow/config.ci.yaml
+
+jobs:
+  team_check:
+    if: >-
+      github.event_name != 'issue_comment' ||
+      (
+        github.event.issue.pull_request &&
+        github.event.comment.body == '@devflow /review' &&
+        (
+          github.event.comment.author_association == 'MEMBER' ||
+          github.event.comment.author_association == 'OWNER'
+        )
+      )
+    runs-on: ubuntu-latest
+    environment: github-app-auth
+    outputs:
+      is_team_member: ${{ steps.check.outputs.is_team_member }}
+      pr_number: ${{ steps.pr.outputs.pr_number }}
+      pr_url: ${{ steps.pr.outputs.pr_url }}
+      repo: ${{ steps.pr.outputs.repo }}
+    steps:
+      - name: Resolve PR metadata
+        id: pr
+        shell: bash
+        env:
+          PR_HTML_URL: ${{ github.event.pull_request.html_url }}
+          PR_NUMBER_COMMENT: ${{ github.event.issue.number }}
+          PR_NUMBER_EVENT: ${{ github.event.pull_request.number }}
+          PR_NUMBER_INPUT: ${{ inputs.pr_number }}
+        run: |
+          set -euo pipefail
+
+          if [[ "${GITHUB_EVENT_NAME}" == "pull_request_target" ]]; then
+            pr_number="${PR_NUMBER_EVENT}"
+            pr_url="${PR_HTML_URL}"
+          elif [[ "${GITHUB_EVENT_NAME}" == "issue_comment" ]]; then
+            pr_number="${PR_NUMBER_COMMENT}"
+            pr_url="https://github.com/${GITHUB_REPOSITORY}/pull/${pr_number}"
+          else
+            pr_number="${PR_NUMBER_INPUT}"
+            pr_url="https://github.com/${GITHUB_REPOSITORY}/pull/${pr_number}"
+          fi
+
+          if [[ ! "$pr_number" =~ ^[1-9][0-9]*$ ]]; then
+            echo "Could not determine PR number; for workflow_dispatch runs, the 'pr_number' input is required when not running on pull_request_target." >&2
+            exit 1
+          fi
+
+          echo "pr_url=${pr_url}" >> "$GITHUB_OUTPUT"
+          echo "pr_number=${pr_number}" >> "$GITHUB_OUTPUT"
+          echo "repo=${GITHUB_REPOSITORY}" >> "$GITHUB_OUTPUT"
+
+      - name: Checkout GitHub automation
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
+        with:
+          ref: ${{ github.event_name == 'pull_request_target' && github.event.pull_request.base.sha || github.sha }}
+          sparse-checkout: |
+            .github/actions/github-app-token
+            .github/scripts/check_team_membership.js
+          fetch-depth: 1
+          persist-credentials: false
+
+      - name: Get GitHub automation token
+        id: github-auth
+        uses: ./.github/actions/github-app-token
+        with:
+          mode: ${{ vars.GH_APP_AUTH_MODE }}
+          azure-client-id: ${{ secrets.GH_APP_AZURE_CLIENT_ID }}
+          azure-tenant-id: ${{ secrets.GH_APP_AZURE_TENANT_ID }}
+          azure-subscription-id: ${{ secrets.GH_APP_AZURE_SUBSCRIPTION_ID }}
+          key-vault-name: ${{ secrets.GH_APP_KEY_VAULT_NAME }}
+          key-name: ${{ secrets.GH_APP_KEY_NAME }}
+          github-app-client-id: ${{ secrets.GH_APP_CLIENT_ID }}
+          github-app-installation-id: ${{ secrets.GH_APP_INSTALLATION_ID }}
+          repository: ${{ github.repository }}
+          fallback-token: ${{ secrets.GH_ACTIONS_PR_WRITE }}
+
+      - name: Check review requester team membership
+        id: check
+        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
+        env:
+          MEMBERSHIP_USER: ${{ github.event_name == 'issue_comment' && github.event.comment.user.login || '' }}
+          TEAM_NAME: ${{ secrets.DEVELOPER_TEAM }}
+          PR_NUMBER: ${{ steps.pr.outputs.pr_number }}
+        with:
+          github-token: ${{ steps.github-auth.outputs.token }}
+          script: |
+            const checkTeamMembership = require('./.github/scripts/check_team_membership.js');
+            const { author, isTeamMember } = await checkTeamMembership({
+              github,
+              context,
+              core,
+              teamSlug: process.env.TEAM_NAME,
+              issueNumber: process.env.PR_NUMBER,
+              username: process.env.MEMBERSHIP_USER,
+            });
+            core.setOutput('is_team_member', isTeamMember ? 'true' : 'false');
+            if (isTeamMember) {
+              core.info(`User ${author} is a team member; proceeding with review.`);
+            } else {
+              core.info(`User ${author} is not a member of ${process.env.TEAM_NAME}; skipping review.`);
+            }
+
+      - name: React to authorized review command
+        if: ${{ github.event_name == 'issue_comment' && steps.check.outputs.is_team_member == 'true' }}
+        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
+        with:
+          github-token: ${{ steps.github-auth.outputs.token }}
+          script: |
+            await github.rest.reactions.createForIssueComment({
+              ...context.repo,
+              comment_id: context.payload.comment.id,
+              content: 'eyes',
+            });
+
+  review:
+    runs-on: ubuntu-latest
+    needs: team_check
+    if: ${{ needs.team_check.outputs.is_team_member == 'true' }}
+    permissions:
+      copilot-requests: write
+      contents: read
+      issues: write
+      pull-requests: write
+    timeout-minutes: 60
+    # Advisory check: failures here should not block the PR. The reviewer
+    # posts comments as a best-effort signal; if the pipeline breaks, the
+    # PR author should still be able to merge without a red required check.
+    continue-on-error: true
+
+    steps:
+      # Safe checkout: base repo only, not the untrusted PR head.
+      - name: Checkout target repo base
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
+        with:
+          ref: ${{ github.event_name == 'pull_request_target' && github.event.pull_request.base.sha || github.sha }}
+          fetch-depth: 0
+          persist-credentials: false
+          path: target-repo
+
+      # Private DevFlow checkout: the PAT/token grants access to this repo's code.
+      - name: Checkout DevFlow
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
+        with:
+          repository: ${{ env.DEVFLOW_REPOSITORY }}
+          ref: ${{ env.DEVFLOW_REF }}
+          token: ${{ secrets.DEVFLOW_TOKEN }}
+          fetch-depth: 1
+          persist-credentials: false
+          path: devflow
+
+      - name: Set up Python
+        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5
+        with:
+          python-version: "3.13"
+
+      - name: Set up uv
+        uses: astral-sh/setup-uv@11f9893b081a58869d3b5fccaea48c9e9e46f990 # v8.3.2
+        with:
+          version: "0.11.x"
+          enable-cache: true
+
+      - name: Install DevFlow dependencies
+        working-directory: ${{ env.DEVFLOW_PATH }}
+        run: uv sync --frozen
+
+      - name: Run PR review
+        id: review
+        working-directory: ${{ env.DEVFLOW_PATH }}
+        env:
+          DEVFLOW_TOKEN: ${{ secrets.DEVFLOW_TOKEN }}
+          GITHUB_TOKEN: ${{ github.token }}
+          SK_REPO_PATH: ${{ env.TARGET_REPO_PATH }}
+          AGENT_REPO_PATH: ${{ env.TARGET_REPO_PATH }}
+          PR_URL: ${{ needs.team_check.outputs.pr_url }}
+        run: |
+          uv run python scripts/trigger_pr_review.py \
+            --pr-url "$PR_URL" \
+            --github-username "$GITHUB_ACTOR" \
+            --review-compare \
+            --no-require-comment-selection

.github/workflows/dotnet-build-and-test.yml

@@ -37,9 +37,12 @@ jobs:
     outputs:
       dotnetChanges: ${{ steps.filter.outputs.dotnet }}
       cosmosDbChanges: ${{ steps.filter.outputs.cosmosdb }}
+      foundryHostingChanges: ${{ steps.filter.outputs.foundryHosting }}
+      functionsChanged: ${{ steps.filter.outputs.functions }}
+      coreChanged: ${{ steps.filter.outputs.core }}
     steps:
-      - uses: actions/checkout@v6
-      - uses: dorny/paths-filter@v3
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
+      - uses: dorny/paths-filter@7b450fff21473bca461d4b92ce414b9d0420d706 # v4.0.2
         id: filter
         with:
           filters: |
@@ -47,6 +50,40 @@ jobs:
               - 'dotnet/**'
             cosmosdb:
               - 'dotnet/src/Microsoft.Agents.AI.CosmosNoSql/**'
+            # The Foundry hosted-agent IT is costly (builds a container, pushes to ACR,
+            # provisions live agents). Only run it when the project under test, its
+            # dependency chain, the test container, the test fixture, or their tooling
+            # changed. Keep this list in sync with $hashedDirs in scripts/it-build-image.ps1.
+            foundryHosting:
+              - 'dotnet/src/Microsoft.Agents.AI.Foundry.Hosting/**'
+              - 'dotnet/src/Microsoft.Agents.AI.Foundry/**'
+              - 'dotnet/src/Microsoft.Agents.AI/**'
+              - 'dotnet/src/Microsoft.Agents.AI.Abstractions/**'
+              - 'dotnet/src/Microsoft.Agents.AI.Workflows/**'
+              - 'dotnet/tests/Foundry.Hosting.IntegrationTests/**'
+              - 'dotnet/tests/Foundry.Hosting.IntegrationTests.TestContainer/**'
+              - 'dotnet/samples/04-hosting/FoundryHostedAgents/responses/Hosted-AzureSearchRag/**'
+              - 'dotnet/Directory.Packages.props'
+              - 'dotnet/tests/Foundry.Hosting.IntegrationTests/scripts/it-build-image.ps1'
+              - '.github/workflows/dotnet-build-and-test.yml'
+            functions:
+              - 'dotnet/src/Microsoft.Agents.AI.DurableTask/**'
+              - 'dotnet/src/Microsoft.Agents.AI.Hosting.AzureFunctions/**'
+              - 'dotnet/tests/Microsoft.Agents.AI.DurableTask.IntegrationTests/**'
+              - 'dotnet/tests/Microsoft.Agents.AI.Hosting.AzureFunctions.IntegrationTests/**'
+              - '.github/actions/azure-functions-integration-setup/**'
+              - '.github/workflows/dotnet-build-and-test.yml'
+            core:
+              - 'dotnet/src/Microsoft.Agents.AI/**'
+              - 'dotnet/src/Microsoft.Agents.AI.Abstractions/**'
+              - 'dotnet/src/Microsoft.Agents.AI.OpenAI/**'
+              - 'dotnet/src/Microsoft.Agents.AI.Workflows/**'
+              - 'dotnet/src/Microsoft.Agents.AI.Workflows.Generators/**'
+              - 'dotnet/eng/scripts/New-FilteredSolution.ps1'
+              - 'dotnet/tests/Directory.Build.props'
+              - 'dotnet/Directory.Packages.props'
+              - 'dotnet/global.json'
+              - '.github/workflows/dotnet-build-and-test.yml'
       # run only if 'dotnet' files were changed
       - name: dotnet tests
         if: steps.filter.outputs.dotnet == 'true'
@@ -74,7 +111,7 @@ jobs:
 
     runs-on: ${{ matrix.os }}
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
         with:
             persist-credentials: false
             sparse-checkout: |
@@ -84,8 +121,11 @@ jobs:
               python
               declarative-agents
 
+      - name: Free runner disk space
+        uses: ./.github/actions/free-runner-disk-space
+
       - name: Setup dotnet
-        uses: actions/setup-dotnet@v5.2.0
+        uses: actions/setup-dotnet@c2fa09f4bde5ebb9d1777cf28262a3eb3db3ced7 # v5.2.0
         with:
           global-json-file: ${{ github.workspace }}/dotnet/global.json
       - name: Build dotnet solutions
@@ -123,6 +163,7 @@ jobs:
           # Change to project directory to ensure local nuget.config is used
           pushd consoleapp
           dotnet add packcheck.csproj package Microsoft.Agents.AI --prerelease
+          dotnet add packcheck.csproj package Microsoft.Agents.AI.LocalCodeAct --prerelease
           dotnet build -f ${{ matrix.targetFramework }} -c ${{ matrix.configuration }} packcheck.csproj
 
           # Clean up
@@ -144,7 +185,7 @@ jobs:
     runs-on: ${{ matrix.os }}
     environment: ${{ matrix.environment }}
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
         with:
             persist-credentials: false
             sparse-checkout: |
@@ -154,6 +195,9 @@ jobs:
               python
               declarative-agents
 
+      - name: Free runner disk space
+        uses: ./.github/actions/free-runner-disk-space
+
       # Start Cosmos DB Emulator for all integration tests and only for unit tests when CosmosDB changes happened)
       - name: Start Azure Cosmos DB Emulator
         if: ${{ runner.os == 'Windows' && (needs.paths-filter.outputs.cosmosDbChanges == 'true' || (github.event_name != 'pull_request' && matrix.integration-tests)) }}
@@ -165,7 +209,7 @@ jobs:
           echo "COSMOSDB_EMULATOR_AVAILABLE=true" >> $env:GITHUB_ENV
 
       - name: Setup dotnet
-        uses: actions/setup-dotnet@v5.2.0
+        uses: actions/setup-dotnet@c2fa09f4bde5ebb9d1777cf28262a3eb3db3ced7 # v5.2.0
         with:
           global-json-file: ${{ github.workspace }}/dotnet/global.json
 
@@ -194,10 +238,11 @@ jobs:
             Verbose         = $true
           }
           ./dotnet/eng/scripts/New-FilteredSolution.ps1 @commonArgs `
-            -TestProjectNameFilter "*UnitTests*" `
+            -TestProjectNameIncludeFilter "*UnitTests*" `
             -OutputPath dotnet/filtered-unit.slnx
           ./dotnet/eng/scripts/New-FilteredSolution.ps1 @commonArgs `
-            -TestProjectNameFilter "*IntegrationTests*" `
+            -TestProjectNameIncludeFilter "*IntegrationTests*" `
+            -TestProjectNameExcludeFilter "*DurableTask.IntegrationTests*","*AzureFunctions.IntegrationTests*" `
             -OutputPath dotnet/filtered-integration.slnx
 
       - name: Run Unit Tests
@@ -233,20 +278,12 @@ jobs:
 
       - name: Azure CLI Login
         if: github.event_name != 'pull_request' && matrix.integration-tests
-        uses: azure/login@v2
+        uses: azure/login@a457da9ea143d694b1b9c7c869ebb04ebe844ef5 # v2
         with:
           client-id: ${{ secrets.AZURE_CLIENT_ID }}
           tenant-id: ${{ secrets.AZURE_TENANT_ID }}
           subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
 
-        # This setup action is required for both Durable Task and Azure Functions integration tests.
-        # We only run it on Ubuntu since the Durable Task and Azure Functions features are not available
-        # on .NET Framework (net472) which is what we use the Windows runner for.
-      - name: Set up Durable Task and Azure Functions Integration Test Emulators
-        if: github.event_name != 'pull_request' && matrix.integration-tests && matrix.os == 'ubuntu-latest'
-        uses: ./.github/actions/azure-functions-integration-setup
-        id: azure-functions-setup
-
       - name: Run Integration Tests
         shell: pwsh
         working-directory: dotnet
@@ -257,8 +294,11 @@ jobs:
             -c ${{ matrix.configuration }} `
             --no-build -v Normal `
             --report-xunit-trx `
+            --report-junit `
+            --results-directory ../IntegrationTestResults/ `
             --ignore-exit-code 8 `
             --filter-not-trait "Category=IntegrationDisabled" `
+            --filter-not-trait "Category=FoundryHostedAgents" `
             --parallel-algorithm aggressive `
             --max-threads 2.0x
         env:
@@ -273,15 +313,20 @@ jobs:
           AZURE_OPENAI_DEPLOYMENT_NAME: ${{ vars.AZURE_OPENAI_DEPLOYMENT_NAME }}
           AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ vars.AZURE_OPENAI_DEPLOYMENT_NAME }}
           AZURE_OPENAI_ENDPOINT: ${{ vars.AZURE_OPENAI_ENDPOINT }}
-          # Azure AI Foundry
+          # Microsoft Foundry
           AZURE_AI_PROJECT_ENDPOINT: ${{ vars.AZURE_AI_PROJECT_ENDPOINT }}
           AZURE_AI_MODEL_DEPLOYMENT_NAME: ${{ vars.AZURE_AI_MODEL_DEPLOYMENT_NAME }}
           AZURE_AI_BING_CONNECTION_ID: ${{ vars.AZURE_AI_BING_CONNECTION_ID }}
+          # Anthropic Models
+          # Disable Anthropic tests by not providing environment vars until 404 failure is resolved
+          # ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
+          # ANTHROPIC_CHAT_MODEL_NAME: ${{ vars.ANTHROPIC_CHAT_MODEL_NAME }}
+          # ANTHROPIC_REASONING_MODEL_NAME: ${{ vars.ANTHROPIC_REASONING_MODEL_NAME }}
 
       # Generate test reports and check coverage
       - name: Generate test reports
         if: matrix.targetFramework == env.COVERAGE_FRAMEWORK
-        uses: danielpalme/ReportGenerator-GitHub-Action@5.5.3
+        uses: danielpalme/ReportGenerator-GitHub-Action@2a82782178b2816d9d6960a7345fdd164791b323 # 5.5.3
         with:
           reports: "./TestResults/Coverage/**/*.cobertura.xml"
           targetdir: "./TestResults/Reports"
@@ -289,7 +334,7 @@ jobs:
 
       - name: Upload coverage report artifact
         if: matrix.targetFramework == env.COVERAGE_FRAMEWORK
-        uses: actions/upload-artifact@v7
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
         with:
           name: CoverageReport-${{ matrix.os }}-${{ matrix.targetFramework }}-${{ matrix.configuration }} # Artifact name
           path: ./TestResults/Reports # Directory containing files to upload
@@ -299,11 +344,209 @@ jobs:
         shell: pwsh
         run: ./dotnet/eng/scripts/dotnet-check-coverage.ps1 -JsonReportPath "TestResults/Reports/Summary.json" -CoverageThreshold $env:COVERAGE_THRESHOLD
 
+      - name: Upload integration test results
+        if: always() && github.event_name != 'pull_request' && matrix.integration-tests
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
+        with:
+          name: dotnet-test-results-${{ matrix.targetFramework }}-${{ matrix.os }}
+          path: IntegrationTestResults/**/*.junit
+          if-no-files-found: ignore
+
+  # The Foundry hosted-agent IT is costly (it builds a container, pushes to ACR, and provisions
+  # live agents on a separate Foundry project). Running it in its own job keeps the overall
+  # workflow time roughly flat: it executes in parallel to dotnet-build and dotnet-test and is
+  # gated on paths-filter.outputs.foundryHostingChanges so unrelated edits skip the work.
+  dotnet-foundry-hosted-it:
+    needs: paths-filter
+    if: github.event_name != 'pull_request' && needs.paths-filter.outputs.foundryHostingChanges == 'true'
+    runs-on: ubuntu-latest
+    environment: integration
+    env:
+      configuration: Release
+    steps:
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
+        with:
+          persist-credentials: false
+          sparse-checkout: |
+            .
+            .github
+            dotnet
+            python
+
+      - name: Free runner disk space
+        uses: ./.github/actions/free-runner-disk-space
+
+      - name: Setup dotnet
+        uses: actions/setup-dotnet@c2fa09f4bde5ebb9d1777cf28262a3eb3db3ced7 # v5.2.0
+        with:
+          global-json-file: ${{ github.workspace }}/dotnet/global.json
+
+      # Build the test csproj directly instead of a filtered slnx + -f override.
+      # The test project pins TargetFrameworks=net10.0 and its ProjectReference closure
+      # gives MSBuild a single-rooted graph, so each multi-targeted dependency is invoked
+      # exactly once for net10.0. This avoids the MSB3026/MSB3491/MSB4018/MSB3883 file-lock
+      # collisions caused by parallel inner-builds racing on shared bin/obj output paths
+      # under the previous slnx + global TFM override approach.
+      - name: Build Foundry hosted IT (and its deps)
+        shell: bash
+        run: dotnet build dotnet/tests/Foundry.Hosting.IntegrationTests/Foundry.Hosting.IntegrationTests.csproj -c "$configuration" --warnaserror
+
+      - name: Azure CLI Login
+        uses: azure/login@a457da9ea143d694b1b9c7c869ebb04ebe844ef5 # v2
+        with:
+          client-id: ${{ secrets.AZURE_CLIENT_ID }}
+          tenant-id: ${{ secrets.AZURE_TENANT_ID }}
+          subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
+
+      # We rebuild and push the test container image on every IT run so framework code changes
+      # are picked up; the image tag is content-hashed across the test container source AND its
+      # framework project references, so identical content is a no-op push.
+      #
+      # The script always passes --no-dependencies to dotnet publish so publish never re-touches
+      # the framework lib DLLs the prior "Build Foundry hosted IT (and its deps)" step produced.
+      # This structurally eliminates the MSB3026 collision that VBCSCompiler from the prebuild
+      # would otherwise cause by holding file handles to those DLLs. Do not remove the prebuild
+      # step: the subsequent `dotnet test --no-build` step and the publish's ProjectReference
+      # resolution both depend on the prebuilt outputs being present.
+      - name: Build and push Foundry Hosted Agents test container
+        id: build-foundry-hosted-image
+        shell: pwsh
+        working-directory: ${{ github.workspace }}
+        run: |
+          $registry = "${{ vars.IT_HOSTED_AGENT_REGISTRY }}"
+          if ([string]::IsNullOrWhiteSpace($registry)) {
+            throw "IT_HOSTED_AGENT_REGISTRY not set in the integration environment."
+          }
+          & "${{ github.workspace }}/dotnet/tests/Foundry.Hosting.IntegrationTests/scripts/it-build-image.ps1" -Registry $registry | Tee-Object -FilePath $env:GITHUB_ENV -Append
+
+      - name: Run Foundry Hosted Agents Integration Tests
+        shell: pwsh
+        working-directory: dotnet
+        run: |
+          dotnet test --project tests/Foundry.Hosting.IntegrationTests/Foundry.Hosting.IntegrationTests.csproj `
+            -c $env:configuration `
+            --no-build -v Normal `
+            --report-xunit-trx `
+            --ignore-exit-code 8 `
+            --filter-trait "Category=FoundryHostedAgents"
+        env:
+          AZURE_AI_PROJECT_ENDPOINT: ${{ vars.IT_HOSTED_AGENT_PROJECT_ENDPOINT }}
+          AZURE_AI_MODEL_DEPLOYMENT_NAME: ${{ vars.IT_HOSTED_AGENT_MODEL_DEPLOYMENT_NAME }}
+          # Azure AI Search (for the azure-search-rag scenario). Reuses the integration
+          # environment secrets shared with python-sample-validation.yml. The index is
+          # provisioned out of band; see dotnet/tests/Foundry.Hosting.IntegrationTests/README.md
+          # for the required schema and seed content.
+          AZURE_SEARCH_ENDPOINT: ${{ secrets.AZURE_SEARCH_ENDPOINT }}
+          AZURE_SEARCH_INDEX_NAME: ${{ secrets.AZURE_SEARCH_INDEX_NAME }}
+          # IT_HOSTED_AGENT_IMAGE was exported into $GITHUB_ENV by the previous step.
+
+  # DurableTask and AzureFunctions integration tests (ubuntu/net10.0 only).
+  # Split from main dotnet-test job for path-based filtering and parallelism.
+  dotnet-test-functions:
+    needs: [paths-filter]
+    if: >
+      github.event_name != 'pull_request' &&
+      (needs.paths-filter.outputs.functionsChanged == 'true' ||
+       needs.paths-filter.outputs.coreChanged == 'true' ||
+       github.event_name == 'schedule' ||
+       github.event_name == 'workflow_dispatch')
+    runs-on: ubuntu-latest
+    environment: integration
+    steps:
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
+        with:
+          persist-credentials: false
+          sparse-checkout: |
+            .
+            .github
+            dotnet
+            python
+            declarative-agents
+
+      - name: Free runner disk space
+        uses: ./.github/actions/free-runner-disk-space
+
+      - name: Setup dotnet
+        uses: actions/setup-dotnet@c2fa09f4bde5ebb9d1777cf28262a3eb3db3ced7 # v5.2.0
+        with:
+          global-json-file: ${{ github.workspace }}/dotnet/global.json
+
+      - name: Build functions integration test projects
+        shell: bash
+        working-directory: dotnet
+        run: |
+          dotnet build ./tests/Microsoft.Agents.AI.DurableTask.IntegrationTests -c Release -f net10.0 --warnaserror
+          dotnet build ./tests/Microsoft.Agents.AI.Hosting.AzureFunctions.IntegrationTests -c Release -f net10.0 --warnaserror
+
+      - name: Azure CLI Login
+        uses: azure/login@a457da9ea143d694b1b9c7c869ebb04ebe844ef5 # v2
+        with:
+          client-id: ${{ secrets.AZURE_CLIENT_ID }}
+          tenant-id: ${{ secrets.AZURE_TENANT_ID }}
+          subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
+
+      - name: Set up Durable Task and Azure Functions Integration Test Emulators
+        uses: ./.github/actions/azure-functions-integration-setup
+        id: azure-functions-setup
+
+      - name: Run Functions Integration Tests
+        shell: pwsh
+        working-directory: dotnet
+        run: |
+          # Run DurableTask integration tests
+          dotnet test `
+            --project ./tests/Microsoft.Agents.AI.DurableTask.IntegrationTests `
+            -f net10.0 `
+            -c Release `
+            --no-build -v Normal `
+            --report-xunit-trx `
+            --report-junit `
+            --results-directory ../IntegrationTestResults/ `
+            --ignore-exit-code 8 `
+            --filter-not-trait "Category=IntegrationDisabled" `
+            --parallel-algorithm aggressive `
+            --max-threads 2.0x
+
+          # Run AzureFunctions integration tests
+          dotnet test `
+            --project ./tests/Microsoft.Agents.AI.Hosting.AzureFunctions.IntegrationTests `
+            -f net10.0 `
+            -c Release `
+            --no-build -v Normal `
+            --report-xunit-trx `
+            --report-junit `
+            --results-directory ../IntegrationTestResults/ `
+            --ignore-exit-code 8 `
+            --filter-not-trait "Category=IntegrationDisabled" `
+            --parallel-algorithm aggressive `
+            --max-threads 2.0x
+        env:
+          # OpenAI Models
+          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+          OPENAI_CHAT_MODEL_NAME: ${{ vars.OPENAI_CHAT_MODEL_NAME }}
+          OPENAI_REASONING_MODEL_NAME: ${{ vars.OPENAI_REASONING_MODEL_NAME }}
+          # Azure OpenAI Models
+          AZURE_OPENAI_DEPLOYMENT_NAME: ${{ vars.AZURE_OPENAI_DEPLOYMENT_NAME }}
+          AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ vars.AZURE_OPENAI_DEPLOYMENT_NAME }}
+          AZURE_OPENAI_ENDPOINT: ${{ vars.AZURE_OPENAI_ENDPOINT }}
+          # Microsoft Foundry
+          AZURE_AI_PROJECT_ENDPOINT: ${{ vars.AZURE_AI_PROJECT_ENDPOINT }}
+          AZURE_AI_MODEL_DEPLOYMENT_NAME: ${{ vars.AZURE_AI_MODEL_DEPLOYMENT_NAME }}
+          AZURE_AI_BING_CONNECTION_ID: ${{ vars.AZURE_AI_BING_CONNECTION_ID }}
+
+      - name: Upload functions test results
+        if: always()
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
+        with:
+          name: dotnet-test-results-functions-net10.0-ubuntu-latest
+          path: IntegrationTestResults/**/*.junit
+          if-no-files-found: ignore
+
   # This final job is required to satisfy the merge queue. It must only run (or succeed) if no tests failed
   dotnet-build-and-test-check:
     if: always()
     runs-on: ubuntu-latest
-    needs: [dotnet-build, dotnet-test]
+    needs: [dotnet-build, dotnet-test, dotnet-foundry-hosted-it, dotnet-test-functions]
     steps:
       - name: Get Date
         shell: bash
@@ -331,13 +574,74 @@ jobs:
       - name: Fail workflow if tests failed
         id: check_tests_failed
         if: contains(join(needs.*.result, ','), 'failure')
-        uses: actions/github-script@v8
+        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
         with:
           script: core.setFailed('Integration Tests Failed!')
 
       - name: Fail workflow if tests cancelled
         id: check_tests_cancelled
         if: contains(join(needs.*.result, ','), 'cancelled')
-        uses: actions/github-script@v8
+        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
         with:
           script: core.setFailed('Integration Tests Cancelled!')
+
+  # Integration test trend report (aggregates JUnit XML results from dotnet test jobs)
+  dotnet-integration-test-report:
+    name: Integration Test Report
+    if: >
+      always() &&
+      github.event_name != 'pull_request' &&
+      (contains(join(needs.*.result, ','), 'success') ||
+       contains(join(needs.*.result, ','), 'failure'))
+    needs: [dotnet-test, dotnet-test-functions]
+    runs-on: ubuntu-latest
+    defaults:
+      run:
+        working-directory: python
+    steps:
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
+        with:
+          persist-credentials: false
+          sparse-checkout: |
+            .github/actions/python-setup
+            python
+      - name: Set up python and install the project
+        uses: ./.github/actions/python-setup
+        with:
+          python-version: "3.13"
+          os: ${{ runner.os }}
+      - name: Download all test results from current run
+        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
+        with:
+          pattern: dotnet-test-results-*
+          path: dotnet-test-results/
+      - name: Restore report history cache
+        uses: actions/cache/restore@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
+        with:
+          path: python/dotnet-integration-report-history.json
+          key: dotnet-integration-report-history-${{ github.run_id }}
+          restore-keys: |
+            dotnet-integration-report-history-
+      - name: Generate trend report
+        run: >
+          uv run python scripts/integration_test_report/aggregate.py
+          ../dotnet-test-results/
+          dotnet-integration-report-history.json
+          dotnet-integration-test-report.md
+      - name: Post to Job Summary
+        if: always()
+        run: cat dotnet-integration-test-report.md >> $GITHUB_STEP_SUMMARY
+      - name: Save report history cache
+        if: always()
+        uses: actions/cache/save@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
+        with:
+          path: python/dotnet-integration-report-history.json
+          key: dotnet-integration-report-history-${{ github.run_id }}
+      - name: Upload trend report
+        if: always()
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
+        with:
+          name: dotnet-integration-test-report
+          path: |
+            python/dotnet-integration-test-report.md
+            python/dotnet-integration-report-history.json

.github/workflows/dotnet-format.yml

@@ -30,7 +30,7 @@ jobs:
 
     steps:
       - name: Check out code
-        uses: actions/checkout@v6
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
         with:
           fetch-depth: 0
           persist-credentials: false
@@ -42,7 +42,7 @@ jobs:
       - name: Get changed files
         id: changed-files
         if: github.event_name == 'pull_request'
-        uses: jitterbit/get-changed-files@v1
+        uses: jitterbit/get-changed-files@b17fbb00bdc0c0f63fcf166580804b4d2cdc2a42 # v1
         continue-on-error: true
 
       - name: No C# files changed
@@ -54,11 +54,14 @@ jobs:
       - name: Find csproj files
         id: find-csproj
         if: github.event_name != 'pull_request' || steps.changed-files.outputs.added_modified != '' || steps.changed-files.outcome == 'failure'
+        env:
+          ADDED_MODIFIED: ${{ steps.changed-files.outputs.added_modified }}
         run: |
           csproj_files=()
           exclude_files=("Experimental.Orchestration.Flow.csproj" "Experimental.Orchestration.Flow.UnitTests.csproj" "Experimental.Orchestration.Flow.IntegrationTests.csproj")
+          set -f
           if [[ ${{ steps.changed-files.outcome }} == 'success' ]]; then
-            for file in ${{ steps.changed-files.outputs.added_modified }}; do
+            for file in $ADDED_MODIFIED; do
               echo "$file was changed"
               dir="./$file"
               while [[ $dir != "." && $dir != "/" && $dir != $GITHUB_WORKSPACE ]]; do
@@ -80,6 +83,7 @@ jobs:
           csproj_files=($(printf "%s\n" "${csproj_files[@]}" | sort -u))
           echo "Found ${#csproj_files[@]} unique csproj/slnx files: ${csproj_files[*]}"
           echo "csproj_files=${csproj_files[*]}" >> $GITHUB_OUTPUT
+          set +f
 
       - name: Pull container dotnet/sdk:${{ matrix.dotnet }}
         if: steps.find-csproj.outputs.csproj_files != ''
@@ -88,8 +92,11 @@ jobs:
       # This step will run dotnet format on each of the unique csproj files and fail if any changes are made
       - name: Run dotnet format
         if: steps.find-csproj.outputs.csproj_files != ''
+        env:
+          CSPROJ_FILES: ${{ steps.find-csproj.outputs.csproj_files }}
         run: |
-          for csproj in ${{ steps.find-csproj.outputs.csproj_files }}; do
+          set -f
+          for csproj in $CSPROJ_FILES; do
             echo "Running dotnet format on $csproj"
-            docker run --rm -v $(pwd):/app -w /app mcr.microsoft.com/dotnet/sdk:${{ matrix.dotnet }} /bin/sh -c "dotnet format $csproj --verify-no-changes --verbosity diagnostic"
+            docker run --rm -v "$(pwd):/app" -w /app mcr.microsoft.com/dotnet/sdk:${{ matrix.dotnet }} dotnet format "$csproj" --verify-no-changes --verbosity diagnostic
           done

.github/workflows/dotnet-integration-tests.yml

@@ -9,16 +9,30 @@ on:
   workflow_call:
     inputs:
       checkout-ref:
-        description: "Git ref to checkout (e.g., refs/pull/123/head)"
+        description: "Immutable commit SHA to check out"
         required: true
         type: string
+    secrets:
+      AZURE_CLIENT_ID:
+        required: true
+      AZURE_TENANT_ID:
+        required: true
+      AZURE_SUBSCRIPTION_ID:
+        required: true
+      AZUREAI__ENDPOINT:
+        required: true
+      OPENAI__APIKEY:
+        required: true
 
 permissions:
   contents: read
-  id-token: write
 
 jobs:
   dotnet-integration-tests:
+    permissions:
+      copilot-requests: write
+      contents: read
+      id-token: write
     strategy:
       fail-fast: false
       matrix:
@@ -29,7 +43,7 @@ jobs:
     environment: integration
     timeout-minutes: 60
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
         with:
           ref: ${{ inputs.checkout-ref }}
           persist-credentials: false
@@ -50,7 +64,7 @@ jobs:
           echo "COSMOS_EMULATOR_AVAILABLE=true" >> $env:GITHUB_ENV
 
       - name: Setup dotnet
-        uses: actions/setup-dotnet@v5.2.0
+        uses: actions/setup-dotnet@c2fa09f4bde5ebb9d1777cf28262a3eb3db3ced7 # v5.2.0
         with:
           global-json-file: ${{ github.workspace }}/dotnet/global.json
 
@@ -63,7 +77,7 @@ jobs:
           done
 
       - name: Azure CLI Login
-        uses: azure/login@v2
+        uses: azure/login@a457da9ea143d694b1b9c7c869ebb04ebe844ef5 # v2
         with:
           client-id: ${{ secrets.AZURE_CLIENT_ID }}
           tenant-id: ${{ secrets.AZURE_TENANT_ID }}
@@ -88,6 +102,7 @@ jobs:
         env:
           COSMOSDB_ENDPOINT: https://localhost:8081
           COSMOSDB_KEY: C2y6yDjf5/R+ob0N8A7Cgv30VRDJIWEHLM+4QDU5DE2nQ9nDuVTqobD4b8mGGyPMbIZnqyMsEcaGQy67XIw/Jw==
+          COPILOT_GITHUB_TOKEN: ${{ github.token }}
           OpenAI__ApiKey: ${{ secrets.OPENAI__APIKEY }}
           OpenAI__ChatModelId: ${{ vars.OPENAI__CHATMODELID }}
           OpenAI__ChatReasoningModelId: ${{ vars.OPENAI__CHATREASONINGMODELID }}

.github/workflows/dotnet-verify-samples.yml

@@ -41,7 +41,7 @@ jobs:
     environment: 'integration'
     timeout-minutes: 90
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
         with:
           persist-credentials: false
           sparse-checkout: |
@@ -52,13 +52,13 @@ jobs:
             declarative-agents
 
       - name: Setup dotnet
-        uses: actions/setup-dotnet@v5.2.0
+        uses: actions/setup-dotnet@c2fa09f4bde5ebb9d1777cf28262a3eb3db3ced7 # v5.2.0
         with:
           global-json-file: ${{ github.workspace }}/dotnet/global.json
 
       - name: Azure CLI Login
         if: github.event_name != 'pull_request'
-        uses: azure/login@v2
+        uses: azure/login@a457da9ea143d694b1b9c7c869ebb04ebe844ef5 # v2
         with:
           client-id: ${{ secrets.AZURE_CLIENT_ID }}
           tenant-id: ${{ secrets.AZURE_TENANT_ID }}
@@ -105,10 +105,13 @@ jobs:
           AZURE_OPENAI_DEPLOYMENT_NAME: ${{ vars.AZURE_OPENAI_DEPLOYMENT_NAME }}
           AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ vars.AZURE_OPENAI_DEPLOYMENT_NAME }}
           AZURE_OPENAI_ENDPOINT: ${{ vars.AZURE_OPENAI_ENDPOINT }}
-          # Azure AI Foundry
+          # Microsoft Foundry
           AZURE_AI_PROJECT_ENDPOINT: ${{ vars.AZURE_AI_PROJECT_ENDPOINT }}
           AZURE_AI_MODEL_DEPLOYMENT_NAME: ${{ vars.AZURE_AI_MODEL_DEPLOYMENT_NAME }}
           AZURE_AI_BING_CONNECTION_ID: ${{ vars.AZURE_AI_BING_CONNECTION_ID }}
+          # Foundry
+          FOUNDRY_PROJECT_ENDPOINT: ${{ vars.FOUNDRY_PROJECT_ENDPOINT }}
+          FOUNDRY_MODEL: ${{ vars.FOUNDRY_MODEL }}
 
       - name: Write Job Summary
         if: always()
@@ -123,7 +126,7 @@ jobs:
 
       - name: Upload results
         if: always()
-        uses: actions/upload-artifact@v7
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
         with:
           name: verify-samples-results
           path: |

.github/workflows/github-automation-tests.yml

@@ -0,0 +1,42 @@
+name: GitHub automation tests
+
+on:
+  pull_request:
+    paths:
+      - ".github/actions/**"
+      - ".github/scripts/**"
+      - ".github/tests/**"
+      - ".github/workflows/python-test-coverage.yml"
+      - ".github/workflows/github-automation-tests.yml"
+  push:
+    branches:
+      - main
+    paths:
+      - ".github/actions/**"
+      - ".github/scripts/**"
+      - ".github/tests/**"
+      - ".github/workflows/python-test-coverage.yml"
+      - ".github/workflows/github-automation-tests.yml"
+
+permissions:
+  contents: read
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
+
+      - uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6
+        with:
+          node-version: "22"
+
+      - uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5
+        with:
+          python-version: "3.11"
+
+      - name: Run JavaScript tests
+        run: node --test .github/tests/*.js
+
+      - name: Run Python tests
+        run: python .github/tests/test_python_check_coverage.py

.github/workflows/integration-tests-manual.yml

@@ -3,7 +3,7 @@
 # Go to Actions → "Integration Tests (Manual)" → Run workflow → enter a PR number or branch name.
 #
 # It calls dedicated integration-only workflows (dotnet-integration-tests and python-integration-tests),
-# passing a ref so they check out and test the correct code.
+# passing an immutable commit SHA so they check out and test the approved code.
 # Changed paths are detected here so only the relevant test suites run.
 #
 
@@ -26,7 +26,6 @@ on:
 permissions:
   contents: read
   pull-requests: read
-  id-token: write
 
 concurrency:
   group: integration-tests-manual-${{ github.event.inputs.pr-number || github.event.inputs.branch }}
@@ -38,67 +37,50 @@ jobs:
     runs-on: ubuntu-latest
     outputs:
       checkout-ref: ${{ steps.resolve.outputs.checkout-ref }}
+      base-ref: ${{ steps.resolve.outputs.base-ref }}
       dotnet-changes: ${{ steps.detect-changes.outputs.dotnet }}
       python-changes: ${{ steps.detect-changes.outputs.python }}
     steps:
-      - name: Resolve checkout ref
+      - name: Check out trusted workflow helpers
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
+        with:
+          ref: ${{ github.sha }}
+          persist-credentials: false
+          sparse-checkout: .github/scripts
+
+      - name: Resolve and authorize checkout ref
         id: resolve
+        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
+        with:
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+          script: |
+            const resolveIntegrationTestTarget = require(
+              './.github/scripts/resolve_integration_test_target.js'
+            );
+            const target = await resolveIntegrationTestTarget({
+              github,
+              context,
+              core,
+              prNumber: process.env.PR_NUMBER,
+              branch: process.env.BRANCH,
+            });
+            core.setOutput('checkout-ref', target.checkoutRef);
+            core.setOutput('base-ref', target.baseRef);
+            core.info(`Running integration tests for ${target.description} at ${target.checkoutRef}.`);
         env:
-          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
           PR_NUMBER: ${{ github.event.inputs.pr-number }}
           BRANCH: ${{ github.event.inputs.branch }}
-          REPO: ${{ github.repository }}
-        run: |
-          if [ -n "$PR_NUMBER" ] && [ -n "$BRANCH" ]; then
-            echo "::error::Please provide either a PR number or a branch name, not both."
-            exit 1
-          fi
-
-          if [ -z "$PR_NUMBER" ] && [ -z "$BRANCH" ]; then
-            echo "::error::Please provide either a PR number or a branch name."
-            exit 1
-          fi
-
-          if [ -n "$PR_NUMBER" ]; then
-            if ! echo "$PR_NUMBER" | grep -Eq '^[0-9]+$'; then
-              echo "::error::Invalid PR number. Only numeric values are allowed."
-              exit 1
-            fi
-
-            PR_DATA=$(gh pr view "$PR_NUMBER" --repo "$REPO" --json state)
-            PR_STATE=$(echo "$PR_DATA" | jq -r '.state')
-
-            if [ "$PR_STATE" != "OPEN" ]; then
-              echo "::error::PR #$PR_NUMBER is not open (state: $PR_STATE)"
-              exit 1
-            fi
-
-            echo "checkout-ref=refs/pull/$PR_NUMBER/head" >> "$GITHUB_OUTPUT"
-            echo "Running integration tests for PR #$PR_NUMBER"
-          else
-            if ! echo "$BRANCH" | grep -Eq '^[a-zA-Z0-9_./-]+$'; then
-              echo "::error::Invalid branch name. Only alphanumeric characters, hyphens, underscores, dots, and slashes are allowed."
-              exit 1
-            fi
-
-            echo "checkout-ref=$BRANCH" >> "$GITHUB_OUTPUT"
-            echo "Running integration tests for branch $BRANCH"
-          fi
 
       - name: Detect changed paths
         id: detect-changes
         env:
           GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-          PR_NUMBER: ${{ github.event.inputs.pr-number }}
-          BRANCH: ${{ github.event.inputs.branch }}
+          BASE_REF: ${{ steps.resolve.outputs.base-ref }}
+          CHECKOUT_REF: ${{ steps.resolve.outputs.checkout-ref }}
           REPO: ${{ github.repository }}
         run: |
-          if [ -n "$PR_NUMBER" ]; then
-            CHANGED_FILES=$(gh pr diff "$PR_NUMBER" --repo "$REPO" --name-only)
-          else
-            # For branches, compare against main using the GitHub API
-            CHANGED_FILES=$(gh api "repos/$REPO/compare/main...$BRANCH" --jq '.files[].filename')
-          fi
+          CHANGED_FILES=$(gh api "repos/$REPO/compare/$BASE_REF...$CHECKOUT_REF" \
+            --jq '.files[].filename')
 
           DOTNET_CHANGES=false
           PYTHON_CHANGES=false
@@ -113,22 +95,41 @@ jobs:
 
           echo "dotnet=$DOTNET_CHANGES" >> "$GITHUB_OUTPUT"
           echo "python=$PYTHON_CHANGES" >> "$GITHUB_OUTPUT"
-          echo "Detected changes — dotnet: $DOTNET_CHANGES, python: $PYTHON_CHANGES"
+          echo "Detected changes; dotnet: $DOTNET_CHANGES, python: $PYTHON_CHANGES"
 
   dotnet-integration-tests:
     name: .NET Integration Tests
     needs: resolve-ref
     if: needs.resolve-ref.outputs.dotnet-changes == 'true'
+    permissions:
+      copilot-requests: write
+      contents: read
+      id-token: write
     uses: ./.github/workflows/dotnet-integration-tests.yml
     with:
       checkout-ref: ${{ needs.resolve-ref.outputs.checkout-ref }}
-    secrets: inherit
+    secrets:
+      AZURE_CLIENT_ID: ${{ secrets.AZURE_CLIENT_ID }}
+      AZURE_TENANT_ID: ${{ secrets.AZURE_TENANT_ID }}
+      AZURE_SUBSCRIPTION_ID: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
+      AZUREAI__ENDPOINT: ${{ secrets.AZUREAI__ENDPOINT }}
+      OPENAI__APIKEY: ${{ secrets.OPENAI__APIKEY }}
 
   python-integration-tests:
     name: Python Integration Tests
     needs: resolve-ref
     if: needs.resolve-ref.outputs.python-changes == 'true'
+    permissions:
+      copilot-requests: write
+      contents: read
+      id-token: write
     uses: ./.github/workflows/python-integration-tests.yml
     with:
       checkout-ref: ${{ needs.resolve-ref.outputs.checkout-ref }}
-    secrets: inherit
+    secrets:
+      ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
+      AZURE_CLIENT_ID: ${{ secrets.AZURE_CLIENT_ID }}
+      AZURE_TENANT_ID: ${{ secrets.AZURE_TENANT_ID }}
+      AZURE_SUBSCRIPTION_ID: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
+      FOUNDRY_MODELS_API_KEY: ${{ secrets.FOUNDRY_MODELS_API_KEY }}
+      OPENAI__APIKEY: ${{ secrets.OPENAI__APIKEY }}

.github/workflows/issue-triage.yml

@@ -0,0 +1,240 @@
+name: Issue Triage
+
+on:
+  issues:
+    types: [opened, typed]
+  workflow_dispatch:
+    inputs:
+      issue_number:
+        description: Issue number to triage
+        required: true
+        type: string
+
+permissions:
+  contents: read
+  issues: write
+  id-token: write
+
+concurrency:
+  group: >-
+    issue-triage-${{ github.repository }}-${{
+      github.event_name == 'workflow_dispatch' && inputs.issue_number
+      || github.event.issue.type.name == 'Bug' && github.event.issue.number
+      || github.run_id
+    }}
+  cancel-in-progress: true
+
+env:
+  DEVFLOW_REPOSITORY: ${{ vars.DF_REPO }}
+  DEVFLOW_REF: main
+  TARGET_REPO_PATH: ${{ github.workspace }}/target-repo
+  DEVFLOW_PATH: ${{ github.workspace }}/devflow
+  MODEL_CONFIG_PATH: ${{ github.workspace }}/devflow/config.ci.yaml
+
+jobs:
+  team_check:
+    runs-on: ubuntu-latest
+    environment: github-app-auth
+    if: >-
+      ${{
+        github.event_name == 'workflow_dispatch'
+        || github.event.issue.type.name == 'Bug'
+      }}
+    outputs:
+      is_team_member: ${{ steps.check.outputs.is_team_member }}
+      issue_number: ${{ steps.issue.outputs.issue_number }}
+      repo: ${{ steps.issue.outputs.repo }}
+    steps:
+      - name: Resolve issue metadata
+        id: issue
+        shell: bash
+        env:
+          ISSUE_NUMBER: >-
+            ${{
+              github.event_name == 'workflow_dispatch' && inputs.issue_number
+              || github.event.issue.number
+            }}
+        run: |
+          set -euo pipefail
+
+          issue_number="${ISSUE_NUMBER}"
+
+          if [[ ! "$issue_number" =~ ^[1-9][0-9]*$ ]]; then
+            echo "Could not determine issue number from event payload or manual input." >&2
+            exit 1
+          fi
+
+          echo "issue_number=${issue_number}" >> "$GITHUB_OUTPUT"
+          echo "repo=${GITHUB_REPOSITORY}" >> "$GITHUB_OUTPUT"
+
+      - name: Checkout scripts
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
+        with:
+          sparse-checkout: |
+            .github/actions/github-app-token
+            .github/scripts
+          fetch-depth: 1
+          persist-credentials: false
+
+      - name: Get GitHub automation token
+        id: github-auth
+        uses: ./.github/actions/github-app-token
+        with:
+          mode: ${{ vars.GH_APP_AUTH_MODE }}
+          azure-client-id: ${{ secrets.GH_APP_AZURE_CLIENT_ID }}
+          azure-tenant-id: ${{ secrets.GH_APP_AZURE_TENANT_ID }}
+          azure-subscription-id: ${{ secrets.GH_APP_AZURE_SUBSCRIPTION_ID }}
+          key-vault-name: ${{ secrets.GH_APP_KEY_VAULT_NAME }}
+          key-name: ${{ secrets.GH_APP_KEY_NAME }}
+          github-app-client-id: ${{ secrets.GH_APP_CLIENT_ID }}
+          github-app-installation-id: ${{ secrets.GH_APP_INSTALLATION_ID }}
+          repository: ${{ github.repository }}
+          fallback-token: ${{ secrets.GH_ACTIONS_PR_WRITE }}
+
+      - name: Check issue author team membership
+        if: ${{ github.event_name != 'workflow_dispatch' }}
+        id: check
+        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
+        env:
+          TEAM_NAME: ${{ secrets.DEVELOPER_TEAM }}
+          ISSUE_NUMBER: ${{ steps.issue.outputs.issue_number }}
+        with:
+          github-token: ${{ steps.github-auth.outputs.token }}
+          script: |
+            const checkTeamMembership = require('./.github/scripts/check_team_membership.js');
+            const { author, isTeamMember } = await checkTeamMembership({
+              github,
+              context,
+              core,
+              teamSlug: process.env.TEAM_NAME,
+              issueNumber: process.env.ISSUE_NUMBER,
+            });
+            core.setOutput('is_team_member', isTeamMember ? 'true' : 'false');
+            if (isTeamMember) {
+              core.info(`Author ${author} is a team member; skipping auto-triage.`);
+            } else {
+              core.info(`Author ${author} is not a team member; proceeding with triage.`);
+            }
+
+  triage:
+    runs-on: ubuntu-latest
+    needs: team_check
+    if: >-
+      ${{
+        github.event_name == 'workflow_dispatch'
+        || needs.team_check.outputs.is_team_member == 'false'
+      }}
+    environment: integration
+    permissions:
+      copilot-requests: write
+      contents: read
+      id-token: write
+      issues: write
+    timeout-minutes: 60
+
+    steps:
+      # Safe checkout: base repo only.
+      - name: Checkout target repo base
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
+        with:
+          fetch-depth: 0
+          persist-credentials: false
+          path: target-repo
+
+      # Private DevFlow (maf-dashboard) checkout.
+      - name: Checkout DevFlow
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
+        with:
+          repository: ${{ env.DEVFLOW_REPOSITORY }}
+          ref: ${{ env.DEVFLOW_REF }}
+          token: ${{ secrets.DEVFLOW_TOKEN }}
+          fetch-depth: 1
+          persist-credentials: false
+          path: devflow
+
+      - name: Set up Python
+        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5
+        with:
+          python-version: "3.13"
+
+      - name: Set up uv
+        uses: astral-sh/setup-uv@11f9893b081a58869d3b5fccaea48c9e9e46f990 # v8.3.2
+        with:
+          version: "0.11.x"
+          enable-cache: true
+
+      - name: Install DevFlow dependencies
+        working-directory: ${{ env.DEVFLOW_PATH }}
+        run: uv sync --frozen
+
+      - name: Azure CLI Login
+        uses: azure/login@a457da9ea143d694b1b9c7c869ebb04ebe844ef5 # v2
+        with:
+          client-id: ${{ secrets.AZURE_CLIENT_ID }}
+          tenant-id: ${{ secrets.AZURE_TENANT_ID }}
+          subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
+
+      - name: Classify issue relevance
+        id: spam
+        working-directory: ${{ env.DEVFLOW_PATH }}
+        env:
+          GITHUB_TOKEN: ${{ github.token }}
+          DEVFLOW_TOKEN: ${{ secrets.DEVFLOW_TOKEN }}
+          SK_REPO_PATH: ${{ env.TARGET_REPO_PATH }}
+          AGENT_REPO_PATH: ${{ env.TARGET_REPO_PATH }}
+          ISSUE_REPO: ${{ needs.team_check.outputs.repo }}
+          ISSUE_NUMBER: ${{ needs.team_check.outputs.issue_number }}
+        run: |
+          uv run python scripts/classify_issue_spam.py \
+            --repo "$ISSUE_REPO" \
+            --issue-number "$ISSUE_NUMBER" \
+            --repo-path "${TARGET_REPO_PATH}" \
+            --apply-labels
+
+      - name: Stop after spam gate
+        if: ${{ steps.spam.outputs.allow_triage != 'true' }}
+        shell: bash
+        run: |
+          echo "Stopping: issue triage preflight did not allow automation."
+          exit 1
+
+      - name: Reproduce reported issue
+        if: ${{ steps.spam.outputs.allow_triage == 'true' }}
+        id: repro
+        working-directory: ${{ env.DEVFLOW_PATH }}
+        env:
+          GITHUB_TOKEN: ${{ github.token }}
+          # Not seen by the agent prompt; used only to push a paper-trail
+          # branch back to maf-dashboard at run end.
+          DEVFLOW_TOKEN: ${{ secrets.DEVFLOW_TOKEN }}
+          SK_REPO_PATH: ${{ env.TARGET_REPO_PATH }}
+          AGENT_REPO_PATH: ${{ env.TARGET_REPO_PATH }}
+          ISSUE_REPO: ${{ needs.team_check.outputs.repo }}
+          ISSUE_NUMBER: ${{ needs.team_check.outputs.issue_number }}
+          # Model-provider settings for generated repro code. Never enter the
+          # agent prompt; consumed by SDK constructors via os.environ. Azure
+          # OpenAI and Foundry auth via AAD from the azure/login step above.
+          OPENAI_API_KEY: ${{ secrets.OPENAI__APIKEY }}
+          OPENAI_CHAT_COMPLETION_MODEL: ${{ vars.OPENAI__CHATMODELID }}
+          OPENAI_CHAT_MODEL: ${{ vars.OPENAI__RESPONSESMODELID }}
+          OPENAI_MODEL: ${{ vars.OPENAI__RESPONSESMODELID }}
+          OPENAI_EMBEDDING_MODEL: ${{ vars.OPENAI_EMBEDDING_MODEL_ID }}
+          AZURE_OPENAI_ENDPOINT: ${{ vars.AZUREOPENAI__ENDPOINT }}
+          AZURE_OPENAI_CHAT_COMPLETION_MODEL: ${{ vars.AZUREOPENAI__CHATDEPLOYMENTNAME }}
+          AZURE_OPENAI_CHAT_MODEL: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
+          AZURE_OPENAI_MODEL: ${{ vars.AZUREOPENAI__RESPONSESDEPLOYMENTNAME }}
+          AZURE_OPENAI_EMBEDDING_MODEL: ${{ vars.AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME }}
+          FOUNDRY_PROJECT_ENDPOINT: ${{ vars.FOUNDRY_PROJECT_ENDPOINT }}
+          FOUNDRY_MODEL: ${{ vars.FOUNDRY_MODEL }}
+          FOUNDRY_AGENT_NAME: ${{ vars.FOUNDRY_AGENT_NAME }}
+          FOUNDRY_AGENT_VERSION: ${{ vars.FOUNDRY_AGENT_VERSION }}
+          FOUNDRY_MODELS_ENDPOINT: ${{ vars.FOUNDRY_MODELS_ENDPOINT || '' }}
+          FOUNDRY_MODELS_API_KEY: ${{ secrets.FOUNDRY_MODELS_API_KEY || '' }}
+          FOUNDRY_EMBEDDING_MODEL: ${{ vars.FOUNDRY_EMBEDDING_MODEL || '' }}
+          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
+          ANTHROPIC_CHAT_MODEL: ${{ vars.ANTHROPIC_CHAT_MODEL_ID }}
+        run: |
+          uv run python scripts/trigger_issue_repro.py \
+            --repo "$ISSUE_REPO" \
+            --issue-number "$ISSUE_NUMBER" \
+            --github-username "$GITHUB_ACTOR"

.github/workflows/label-issues.yml

@@ -10,12 +10,39 @@ jobs:
     name: "Issue: add labels"
     if: ${{ github.event.action == 'opened' || github.event.action == 'reopened' }}
     runs-on: ubuntu-latest
+    environment: github-app-auth
     permissions:
+      contents: read
+      id-token: write
       issues: write
     steps:
-      - uses: actions/github-script@v8
+      - name: Checkout GitHub automation
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
         with:
-          github-token: ${{ secrets.GH_ACTIONS_PR_WRITE }}
+          sparse-checkout: |
+            .github/actions/github-app-token
+            .github/scripts/check_team_membership.js
+          fetch-depth: 1
+          persist-credentials: false
+
+      - name: Get GitHub automation token
+        id: github-auth
+        uses: ./.github/actions/github-app-token
+        with:
+          mode: ${{ vars.GH_APP_AUTH_MODE }}
+          azure-client-id: ${{ secrets.GH_APP_AZURE_CLIENT_ID }}
+          azure-tenant-id: ${{ secrets.GH_APP_AZURE_TENANT_ID }}
+          azure-subscription-id: ${{ secrets.GH_APP_AZURE_SUBSCRIPTION_ID }}
+          key-vault-name: ${{ secrets.GH_APP_KEY_VAULT_NAME }}
+          key-name: ${{ secrets.GH_APP_KEY_NAME }}
+          github-app-client-id: ${{ secrets.GH_APP_CLIENT_ID }}
+          github-app-installation-id: ${{ secrets.GH_APP_INSTALLATION_ID }}
+          repository: ${{ github.repository }}
+          fallback-token: ${{ secrets.GH_ACTIONS_PR_WRITE }}
+
+      - uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
+        with:
+          github-token: ${{ steps.github-auth.outputs.token }}
           script: |
             // Get the issue body and title
             const body = context.payload.issue.body
@@ -24,21 +51,14 @@ jobs:
             // Define the labels array
             let labels = []
 
-            // Check if the issue author is in the agentframework-developers team
-            let isTeamMember = false
-            try {
-              const teamMembership = await github.rest.teams.getMembershipForUserInOrg({
-                org: context.repo.owner,
-                team_slug: process.env.TEAM_NAME,
-                username: context.payload.issue.user.login
-              })
-              console.log("Team Membership Data:", teamMembership);
-              isTeamMember = teamMembership.data.state === 'active'
-            } catch (error) {
-              // User is not in the team or team doesn't exist
-              console.error("Error fetching team membership:", error);
-              isTeamMember = false
-            }
+            const checkTeamMembership = require('./.github/scripts/check_team_membership.js')
+            const { isTeamMember } = await checkTeamMembership({
+              github,
+              context,
+              core,
+              teamSlug: process.env.TEAM_NAME,
+              issueNumber: context.issue.number,
+            })
 
             // Only add triage label if the author is not in the team
             if (!isTeamMember) {
@@ -90,9 +110,7 @@ jobs:
             // Check for issue type from issue form dropdown
             const issueTypeField = getFormFieldValue(body, 'Type of Issue')
             if (issueTypeField) {
-              if (issueTypeField === 'Bug') {
-                labels.push("bug")
-              } else if (issueTypeField === 'Feature Request') {
+              if (issueTypeField === 'Feature Request') {
                 labels.push("enhancement")
               } else if (issueTypeField === 'Question') {
                 labels.push("question")

.github/workflows/label-pr.yml

@@ -6,16 +6,54 @@
 # https://github.com/actions/labeler
 
 name: Label pull request
-on: [pull_request_target]
+on:
+  pull_request_target:
+    types: [opened, synchronize, reopened, edited]
 
 jobs:
   add_label:
     runs-on: ubuntu-latest
+    environment: github-app-auth
     permissions:
       contents: read
+      id-token: write
+      issues: write
       pull-requests: write
 
     steps:
-      - uses: actions/labeler@v6
+      - name: Checkout scripts
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
         with:
-          repo-token: "${{ secrets.GH_ACTIONS_PR_WRITE }}"
+          ref: ${{ github.event.pull_request.base.sha }}
+          sparse-checkout: |
+            .github/actions/github-app-token
+            .github/scripts
+          fetch-depth: 1
+          persist-credentials: false
+
+      - name: Get GitHub automation token
+        id: github-auth
+        uses: ./.github/actions/github-app-token
+        with:
+          mode: ${{ vars.GH_APP_AUTH_MODE }}
+          azure-client-id: ${{ secrets.GH_APP_AZURE_CLIENT_ID }}
+          azure-tenant-id: ${{ secrets.GH_APP_AZURE_TENANT_ID }}
+          azure-subscription-id: ${{ secrets.GH_APP_AZURE_SUBSCRIPTION_ID }}
+          key-vault-name: ${{ secrets.GH_APP_KEY_VAULT_NAME }}
+          key-name: ${{ secrets.GH_APP_KEY_NAME }}
+          github-app-client-id: ${{ secrets.GH_APP_CLIENT_ID }}
+          github-app-installation-id: ${{ secrets.GH_APP_INSTALLATION_ID }}
+          repository: ${{ github.repository }}
+          fallback-token: ${{ secrets.GH_ACTIONS_PR_WRITE }}
+
+      - uses: actions/labeler@f27b608878404679385c85cfa523b85ccb86e213 # v6
+        with:
+          repo-token: ${{ steps.github-auth.outputs.token }}
+
+      - name: "PR: add breaking change label from title"
+        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
+        with:
+          github-token: ${{ steps.github-auth.outputs.token }}
+          script: |
+            const { syncBreakingChangeLabelFromTitle } = require('./.github/scripts/title_prefix.js');
+            await syncBreakingChangeLabelFromTitle({ github, context, core });

.github/workflows/label-title-prefix.yml

@@ -15,58 +15,17 @@ jobs:
       pull-requests: write
 
     steps:
-      - uses: actions/github-script@v8
+      - name: Checkout scripts
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
+        with:
+          sparse-checkout: .github/scripts
+          fetch-depth: 1
+          persist-credentials: false
+
+      - uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
         name: "Issue/PR: update title"
         with:
           github-token: ${{ secrets.GITHUB_TOKEN }}
           script: |
-            let prefixLabels = {
-              "python": "Python",
-              ".NET": ".NET"
-            };
-
-            function addTitlePrefix(title, prefix)
-            {
-              // Update the title based on the label and prefix
-              // Check if the title starts with the prefix (case-sensitive)
-              if (!title.startsWith(prefix + ": ")) {
-                // If not, check if the first word is the label (case-insensitive)
-                if (title.match(new RegExp(`^${prefix}`, 'i'))) {
-                  // If yes, replace it with the prefix (case-sensitive)
-                  title = title.replace(new RegExp(`^${prefix}`, 'i'), prefix);
-                } else {
-                  // If not, prepend the prefix to the title
-                  title = prefix + ": " + title;
-                }
-              }
-
-              return title;
-            }
-
-            labelAdded = context.payload.label.name
-
-            // Check if the issue or PR has the label
-            if (labelAdded in prefixLabels) {
-              let prefix = prefixLabels[labelAdded];
-              switch(context.eventName) {
-                case 'issues':
-                  github.rest.issues.update({
-                    issue_number: context.issue.number,
-                    owner: context.repo.owner,
-                    repo: context.repo.repo,
-                    title: addTitlePrefix(context.payload.issue.title, prefix)
-                  });
-                  break
-
-                case 'pull_request_target':
-                  github.rest.pulls.update({
-                    pull_number: context.issue.number,
-                    owner: context.repo.owner,
-                    repo: context.repo.repo,
-                    title: addTitlePrefix(context.payload.pull_request.title, prefix)
-                  });
-                  break
-                default:
-                  core.setFailed('Unrecognited eventName: ' + context.eventName);
-              }
-            }
+            const { updateTitleForAddedLabel } = require('./.github/scripts/title_prefix.js');
+            await updateTitleForAddedLabel({ github, context, core });

.github/workflows/limit-community-prs.yml

@@ -0,0 +1,122 @@
+name: Limit community pull requests
+
+on:
+  pull_request_target:
+    types: [opened, reopened]
+
+permissions:
+  contents: read
+  id-token: write
+  issues: write
+  pull-requests: write
+
+concurrency:
+  group: pr-limit-${{ github.repository }}-${{ github.event.pull_request.user.login }}
+  cancel-in-progress: false
+
+env:
+  MAX_OPEN_PULL_REQUESTS: '10'
+  PR_LIMIT_EXEMPT_LABEL: pr-limit-exempt
+  TOO_MANY_PRS_LABEL: too-many-prs
+
+jobs:
+  team_check:
+    runs-on: ubuntu-latest
+    environment: github-app-auth
+    outputs:
+      is_team_member: ${{ steps.check.outputs.is_team_member }}
+    steps:
+      - name: Checkout scripts
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
+        with:
+          ref: ${{ github.event.pull_request.base.sha }}
+          sparse-checkout: |
+            .github/actions/github-app-token
+            .github/scripts
+          fetch-depth: 1
+          persist-credentials: false
+
+      - name: Get GitHub automation token
+        id: github-auth
+        uses: ./.github/actions/github-app-token
+        with:
+          mode: ${{ vars.GH_APP_AUTH_MODE }}
+          azure-client-id: ${{ secrets.GH_APP_AZURE_CLIENT_ID }}
+          azure-tenant-id: ${{ secrets.GH_APP_AZURE_TENANT_ID }}
+          azure-subscription-id: ${{ secrets.GH_APP_AZURE_SUBSCRIPTION_ID }}
+          key-vault-name: ${{ secrets.GH_APP_KEY_VAULT_NAME }}
+          key-name: ${{ secrets.GH_APP_KEY_NAME }}
+          github-app-client-id: ${{ secrets.GH_APP_CLIENT_ID }}
+          github-app-installation-id: ${{ secrets.GH_APP_INSTALLATION_ID }}
+          repository: ${{ github.repository }}
+          fallback-token: ${{ secrets.GH_ACTIONS_PR_WRITE }}
+
+      - name: Check PR author team membership
+        id: check
+        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
+        env:
+          TEAM_NAME: ${{ secrets.DEVELOPER_TEAM }}
+          PR_NUMBER: ${{ github.event.pull_request.number }}
+        with:
+          github-token: ${{ steps.github-auth.outputs.token }}
+          script: |
+            const checkTeamMembership = require('./.github/scripts/check_team_membership.js');
+            const { author, isTeamMember } = await checkTeamMembership({
+              github,
+              context,
+              core,
+              teamSlug: process.env.TEAM_NAME,
+              issueNumber: process.env.PR_NUMBER,
+            });
+            core.setOutput('is_team_member', isTeamMember ? 'true' : 'false');
+            if (isTeamMember) {
+              core.info(`Author ${author} is a team member; skipping open PR limit.`);
+            } else {
+              core.info(`Author ${author} is not a team member; checking open PR limit.`);
+            }
+
+  limit_open_prs:
+    runs-on: ubuntu-latest
+    environment: github-app-auth
+    needs: team_check
+    if: ${{ needs.team_check.outputs.is_team_member == 'false' }}
+    steps:
+      - name: Checkout scripts
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
+        with:
+          ref: ${{ github.event.pull_request.base.sha }}
+          sparse-checkout: |
+            .github/actions/github-app-token
+            .github/scripts
+          fetch-depth: 1
+          persist-credentials: false
+
+      - name: Get GitHub automation token
+        id: github-auth
+        uses: ./.github/actions/github-app-token
+        with:
+          mode: ${{ vars.GH_APP_AUTH_MODE }}
+          azure-client-id: ${{ secrets.GH_APP_AZURE_CLIENT_ID }}
+          azure-tenant-id: ${{ secrets.GH_APP_AZURE_TENANT_ID }}
+          azure-subscription-id: ${{ secrets.GH_APP_AZURE_SUBSCRIPTION_ID }}
+          key-vault-name: ${{ secrets.GH_APP_KEY_VAULT_NAME }}
+          key-name: ${{ secrets.GH_APP_KEY_NAME }}
+          github-app-client-id: ${{ secrets.GH_APP_CLIENT_ID }}
+          github-app-installation-id: ${{ secrets.GH_APP_INSTALLATION_ID }}
+          repository: ${{ github.repository }}
+          fallback-token: ${{ secrets.GH_ACTIONS_PR_WRITE }}
+
+      - name: Enforce open PR limit
+        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
+        with:
+          github-token: ${{ steps.github-auth.outputs.token }}
+          script: |
+            const { enforcePrLimit } = require('./.github/scripts/pr_limit_moderation.js');
+            await enforcePrLimit({
+              github,
+              context,
+              core,
+              exemptLabelName: process.env.PR_LIMIT_EXEMPT_LABEL,
+              maxOpenPrs: Number.parseInt(process.env.MAX_OPEN_PULL_REQUESTS, 10),
+              labelName: process.env.TOO_MANY_PRS_LABEL,
+            });

.github/workflows/markdown-link-check.yml

@@ -19,13 +19,21 @@ jobs:
     runs-on: ubuntu-22.04
     # check out the latest version of the code
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
         with:
           persist-credentials: false
 
+      - name: Set up Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: 20
+
+      - name: Install Chrome for Puppeteer
+        run: npx puppeteer browsers install chrome
+
       # Checks the status of hyperlinks in all files
       - name: Run linkspector
-        uses: umbrelladocs/action-linkspector@v1
+        uses: umbrelladocs/action-linkspector@963b6264d7de32c904942a70b488d3407453049e # v1
         with:
           reporter: local
           filter_mode: nofilter

.github/workflows/merge-gatekeeper.yml

@@ -2,7 +2,7 @@ name: Merge Gatekeeper
 
 on:
   pull_request:
-    branches: [ "main", "feature*" ]
+    branches: ["main", "feature*"]
   merge_group:
     branches: ["main"]
 
@@ -13,23 +13,105 @@ concurrency:
 jobs:
   merge-gatekeeper:
     runs-on: ubuntu-latest
-    # Restrict permissions of the GITHUB_TOKEN.
-    # Docs: https://docs.github.com/en/actions/using-jobs/assigning-permissions-to-jobs
     permissions:
       checks: read
       statuses: read
     steps:
-      - name: Run Merge Gatekeeper
-        # NOTE: v1 is updated to reflect the latest v1.x.y. Please use any tag/branch that suits your needs:
-        #       https://github.com/upsidr/merge-gatekeeper/tags
-        #       https://github.com/upsidr/merge-gatekeeper/branches
-        uses: upsidr/merge-gatekeeper@v1
+      - name: Wait for required checks
         if: github.event_name == 'pull_request'
-        with:
-          token: ${{ secrets.GITHUB_TOKEN }}
-          timeout: 3600
-          interval: 30
+        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
+        env:
+          TIMEOUT_SECONDS: "3600"
+          INTERVAL_SECONDS: "30"
+          SELF_JOB_NAME: ${{ github.job }}
           # "Cleanup artifacts", "Agent", "Prepare", and "Upload results" are check runs
           # created by an org-level GitHub App (MSDO), not by any workflow in this repo.
           # They are outside our control and their transient failures should not block merges.
-          ignored: CodeQL,CodeQL analysis (csharp),Cleanup artifacts,Agent,Prepare,Upload results
+          IGNORED_NAMES: "CodeQL,CodeQL analysis (csharp),Cleanup artifacts,Agent,Prepare,Upload results,review"
+        with:
+          script: |
+            const timeoutSeconds = Number(process.env.TIMEOUT_SECONDS);
+            const intervalSeconds = Number(process.env.INTERVAL_SECONDS);
+            const selfName = process.env.SELF_JOB_NAME;
+            const ignored = new Set(
+              process.env.IGNORED_NAMES.split(',').map((s) => s.trim()).filter(Boolean),
+            );
+
+            const sha = context.payload.pull_request.head.sha;
+            const { owner, repo } = context.repo;
+
+            const sleep = (ms) => new Promise((r) => setTimeout(r, ms));
+
+            // Mirrors upsidr/merge-gatekeeper: merge combined-statuses and check-runs
+            // for the PR head SHA, with combined-statuses winning on name collision.
+            async function collectChecks() {
+              const merged = new Map();
+
+              const combined = await github.rest.repos.getCombinedStatusForRef({
+                owner, repo, ref: sha, per_page: 100,
+              });
+              for (const s of combined.data.statuses ?? []) {
+                if (!merged.has(s.context)) {
+                  // Combined-status states: success | pending | error | failure
+                  merged.set(s.context, { name: s.context, state: s.state });
+                }
+              }
+
+              const runs = await github.paginate(github.rest.checks.listForRef, {
+                owner, repo, ref: sha, per_page: 100,
+              });
+              for (const r of runs) {
+                if (merged.has(r.name)) continue;
+                let state;
+                if (r.status !== 'completed') {
+                  state = 'pending';
+                } else if (r.conclusion === 'skipped') {
+                  continue; // Skipped runs are dropped, matching the original action.
+                } else if (r.conclusion === 'success' || r.conclusion === 'neutral') {
+                  state = 'success';
+                } else {
+                  // cancelled | timed_out | action_required | stale | failure
+                  state = 'error';
+                }
+                merged.set(r.name, { name: r.name, state });
+              }
+
+              return [...merged.values()];
+            }
+
+            function evaluate(entries) {
+              const failed = [];
+              const pending = [];
+              const succeeded = [];
+              for (const e of entries) {
+                if (e.name === selfName || ignored.has(e.name)) continue;
+                if (e.state === 'success') succeeded.push(e.name);
+                else if (e.state === 'error' || e.state === 'failure') failed.push(e.name);
+                else pending.push(e.name);
+              }
+              return { failed, pending, succeeded };
+            }
+
+            const deadline = Date.now() + timeoutSeconds * 1000;
+            for (;;) {
+              const entries = await collectChecks();
+              const { failed, pending, succeeded } = evaluate(entries);
+
+              core.info(
+                `succeeded=${succeeded.length} pending=${pending.length} failed=${failed.length}`,
+              );
+              if (failed.length) {
+                core.setFailed(`Failing checks: ${failed.join(', ')}`);
+                return;
+              }
+              if (pending.length === 0) {
+                core.info(`All required checks passed: ${succeeded.join(', ') || '(none)'}`);
+                return;
+              }
+              if (Date.now() > deadline) {
+                core.setFailed(`Timed out waiting for: ${pending.join(', ')}`);
+                return;
+              }
+              core.info(`Waiting on (${pending.length}): ${pending.slice(0, 10).join(', ')}${pending.length > 10 ? ', …' : ''}`);
+              await sleep(intervalSeconds * 1000);
+            }

.github/workflows/python-check-coverage.py

@@ -1,382 +0,0 @@
-#!/usr/bin/env python3
-# Copyright (c) Microsoft. All rights reserved.
-"""Check Python test coverage against threshold for enforced targets.
-
-This script parses a Cobertura XML coverage report and enforces a minimum
-coverage threshold on specific targets. Targets can be package names
-(e.g., "packages.core.agent_framework") or individual Python file paths
-(e.g., "packages/core/agent_framework/observability.py").
-
-Non-enforced targets are reported for visibility but don't block the build.
-
-Usage:
-    python python-check-coverage.py <coverage-xml-path> <threshold>
-
-Example:
-    python python-check-coverage.py python-coverage.xml 85
-"""
-
-import sys
-import xml.etree.ElementTree as ET
-from dataclasses import dataclass
-
-# =============================================================================
-# ENFORCED TARGETS CONFIGURATION
-# =============================================================================
-# Add or remove entries from this set to control which targets must meet
-# the coverage threshold. Only these targets will fail the build if below
-# threshold. Other targets are reported for visibility only.
-#
-# Target values can be:
-# - Package paths as they appear in the coverage report
-#   (e.g., "packages.azure-ai.agent_framework_azure_ai")
-# - Python source file paths as they appear in the coverage report
-#   (e.g., "packages/core/agent_framework/observability.py")
-# =============================================================================
-ENFORCED_TARGETS: set[str] = {
-    # Packages (sorted alphabetically)
-    "packages.anthropic.agent_framework_anthropic",
-    "packages.azure-ai-search.agent_framework_azure_ai_search",
-    "packages.core.agent_framework",
-    "packages.core.agent_framework._workflows",
-    "packages.foundry.agent_framework_foundry",
-    "packages.openai.agent_framework_openai",
-    "packages.purview.agent_framework_purview",
-    # Individual files (if you want to enforce specific files instead of whole packages)
-    "packages/core/agent_framework/observability.py",
-    # Add more targets here as coverage improves
-}
-
-
-@dataclass
-class PackageCoverage:
-    """Coverage data for a single package."""
-
-    name: str
-    line_rate: float
-    branch_rate: float
-    lines_valid: int
-    lines_covered: int
-    branches_valid: int
-    branches_covered: int
-
-    @property
-    def line_coverage_percent(self) -> float:
-        """Return line coverage as a percentage."""
-        return self.line_rate * 100
-
-    @property
-    def branch_coverage_percent(self) -> float:
-        """Return branch coverage as a percentage."""
-        return self.branch_rate * 100
-
-
-def normalize_coverage_path(path: str) -> str:
-    """Normalize coverage paths for reliable matching."""
-    return path.replace("\\", "/").lstrip("./")
-
-
-def parse_coverage_xml(
-    xml_path: str,
-) -> tuple[dict[str, PackageCoverage], dict[str, PackageCoverage], float, float]:
-    """Parse Cobertura XML and extract per-package coverage data.
-
-    Args:
-        xml_path: Path to the Cobertura XML coverage report.
-
-    Returns:
-        A tuple of (packages_dict, files_dict, overall_line_rate, overall_branch_rate).
-    """
-    tree = ET.parse(xml_path)
-    root = tree.getroot()
-
-    # Get overall coverage from root element
-    overall_line_rate = float(root.get("line-rate", 0))
-    overall_branch_rate = float(root.get("branch-rate", 0))
-
-    packages: dict[str, PackageCoverage] = {}
-    file_stats: dict[str, dict[str, int]] = {}
-
-    for package in root.findall(".//package"):
-        package_path = package.get("name", "unknown")
-
-        line_rate = float(package.get("line-rate", 0))
-        branch_rate = float(package.get("branch-rate", 0))
-
-        # Count lines and branches from classes within this package
-        lines_valid = 0
-        lines_covered = 0
-        branches_valid = 0
-        branches_covered = 0
-
-        for class_elem in package.findall(".//class"):
-            file_path = normalize_coverage_path(class_elem.get("filename", ""))
-            if file_path and file_path not in file_stats:
-                file_stats[file_path] = {
-                    "lines_valid": 0,
-                    "lines_covered": 0,
-                    "branches_valid": 0,
-                    "branches_covered": 0,
-                }
-
-            for line in class_elem.findall(".//line"):
-                lines_valid += 1
-                if int(line.get("hits", 0)) > 0:
-                    lines_covered += 1
-
-                if file_path:
-                    file_stats[file_path]["lines_valid"] += 1
-                    if int(line.get("hits", 0)) > 0:
-                        file_stats[file_path]["lines_covered"] += 1
-
-                # Branch coverage from line elements
-                if line.get("branch") == "true":
-                    condition_coverage = line.get("condition-coverage", "")
-                    if condition_coverage:
-                        # Parse "X% (covered/total)" format
-                        try:
-                            coverage_parts = (
-                                condition_coverage.split("(")[1].rstrip(")").split("/")
-                            )
-                            branches_covered += int(coverage_parts[0])
-                            branches_valid += int(coverage_parts[1])
-                            if file_path:
-                                file_stats[file_path]["branches_covered"] += int(
-                                    coverage_parts[0]
-                                )
-                                file_stats[file_path]["branches_valid"] += int(
-                                    coverage_parts[1]
-                                )
-                        except (IndexError, ValueError):
-                            # Ignore malformed condition-coverage strings; treat this line as having no branch data.
-                            pass
-
-        # Use full package path as the key (no aggregation)
-        packages[package_path] = PackageCoverage(
-            name=package_path,
-            line_rate=line_rate if lines_valid == 0 else lines_covered / lines_valid,
-            branch_rate=branch_rate
-            if branches_valid == 0
-            else branches_covered / branches_valid,
-            lines_valid=lines_valid,
-            lines_covered=lines_covered,
-            branches_valid=branches_valid,
-            branches_covered=branches_covered,
-        )
-
-    files: dict[str, PackageCoverage] = {}
-    for file_path, stats in file_stats.items():
-        lines_valid = stats["lines_valid"]
-        lines_covered = stats["lines_covered"]
-        branches_valid = stats["branches_valid"]
-        branches_covered = stats["branches_covered"]
-
-        files[file_path] = PackageCoverage(
-            name=file_path,
-            line_rate=0 if lines_valid == 0 else lines_covered / lines_valid,
-            branch_rate=0 if branches_valid == 0 else branches_covered / branches_valid,
-            lines_valid=lines_valid,
-            lines_covered=lines_covered,
-            branches_valid=branches_valid,
-            branches_covered=branches_covered,
-        )
-
-    return packages, files, overall_line_rate, overall_branch_rate
-
-
-def format_coverage_value(coverage: float, threshold: float, is_enforced: bool) -> str:
-    """Format a coverage value with optional pass/fail indicator.
-
-    Args:
-        coverage: Coverage percentage (0-100).
-        threshold: Minimum required coverage percentage.
-        is_enforced: Whether this target is enforced.
-
-    Returns:
-        Formatted string like "85.5%" or "85.5% ✅" or "75.0% ❌".
-    """
-    formatted = f"{coverage:.1f}%"
-    if is_enforced:
-        icon = "✅" if coverage >= threshold else "❌"
-        formatted = f"{formatted} {icon}"
-    return formatted
-
-
-def print_coverage_table(
-    packages: dict[str, PackageCoverage],
-    files: dict[str, PackageCoverage],
-    threshold: float,
-    overall_line_rate: float,
-    overall_branch_rate: float,
-) -> None:
-    """Print a formatted coverage summary table.
-
-    Args:
-        packages: Dictionary of package name to coverage data.
-        files: Dictionary of file path to coverage data, used for per-file enforcement.
-        threshold: Minimum required coverage percentage.
-        overall_line_rate: Overall line coverage rate (0-1).
-        overall_branch_rate: Overall branch coverage rate (0-1).
-    """
-    print("\n" + "=" * 80)
-    print("PYTHON TEST COVERAGE REPORT")
-    print("=" * 80)
-
-    # Overall coverage
-    print(f"\nOverall Line Coverage:   {overall_line_rate * 100:.1f}%")
-    print(f"Overall Branch Coverage: {overall_branch_rate * 100:.1f}%")
-    print(f"Threshold:               {threshold}%")
-
-    enforced_targets = {normalize_coverage_path(t) for t in ENFORCED_TARGETS}
-
-    # Package table
-    print("\n" + "-" * 110)
-    print(f"{'Package':<80} {'Lines':<15} {'Line Cov':<15}")
-    print("-" * 110)
-
-    # Sort: enforced package targets first, then alphabetically
-    sorted_packages = sorted(
-        packages.values(),
-        key=lambda p: (p.name not in ENFORCED_TARGETS, p.name),
-    )
-
-    for pkg in sorted_packages:
-        is_enforced = normalize_coverage_path(pkg.name) in enforced_targets
-        enforced_marker = "[ENFORCED] " if is_enforced else ""
-        line_cov = format_coverage_value(
-            pkg.line_coverage_percent, threshold, is_enforced
-        )
-        lines_info = f"{pkg.lines_covered}/{pkg.lines_valid}"
-        package_label = f"{enforced_marker}{pkg.name}"
-
-        print(f"{package_label:<80} {lines_info:<15} {line_cov:<15}")
-
-    print("-" * 110)
-
-    # Enforced file/model entries (if configured)
-    enforced_files = [
-        files[target]
-        for target in sorted(enforced_targets)
-        if target in files and target.endswith(".py")
-    ]
-
-    if enforced_files:
-        print("\nEnforced Files/Models")
-        print("-" * 110)
-        print(f"{'File':<80} {'Lines':<15} {'Line Cov':<15}")
-        print("-" * 110)
-
-        for file_cov in enforced_files:
-            line_cov = format_coverage_value(
-                file_cov.line_coverage_percent, threshold, True
-            )
-            lines_info = f"{file_cov.lines_covered}/{file_cov.lines_valid}"
-            print(f"[ENFORCED] {file_cov.name:<69} {lines_info:<15} {line_cov:<15}")
-
-        print("-" * 110)
-
-
-def check_coverage(xml_path: str, threshold: float) -> bool:
-    """Check if all enforced targets meet the coverage threshold.
-
-    Args:
-        xml_path: Path to the Cobertura XML coverage report.
-        threshold: Minimum required coverage percentage.
-
-    Returns:
-        True if all enforced targets pass, False otherwise.
-    """
-    packages, files, overall_line_rate, overall_branch_rate = parse_coverage_xml(
-        xml_path
-    )
-
-    print_coverage_table(
-        packages, files, threshold, overall_line_rate, overall_branch_rate
-    )
-
-    # Check enforced targets
-    failed_targets: list[str] = []
-    missing_targets: list[str] = []
-
-    for target_name in ENFORCED_TARGETS:
-        normalized_target = normalize_coverage_path(target_name)
-        package_alias = normalized_target.replace("/", ".")
-
-        target_coverage = None
-        if target_name in packages:
-            target_coverage = packages[target_name]
-        elif normalized_target in files:
-            target_coverage = files[normalized_target]
-        elif package_alias in packages:
-            target_coverage = packages[package_alias]
-
-        if target_coverage is None:
-            missing_targets.append(target_name)
-            continue
-
-        if target_coverage.line_coverage_percent < threshold:
-            failed_targets.append(
-                f"{target_name} ({target_coverage.line_coverage_percent:.1f}%)"
-            )
-
-    # Report results
-    if missing_targets:
-        print(
-            f"\n❌ FAILED: Enforced targets not found in coverage report: {', '.join(missing_targets)}"
-        )
-        return False
-
-    if failed_targets:
-        print(
-            f"\n❌ FAILED: The following enforced targets are below {threshold}% coverage threshold:"
-        )
-        for target in failed_targets:
-            print(f"   - {target}")
-        print("\nTo fix: Add more tests to improve coverage for the failing targets.")
-        return False
-
-    if ENFORCED_TARGETS:
-        found_enforced = [
-            target
-            for target in ENFORCED_TARGETS
-            if target in packages or normalize_coverage_path(target) in files
-        ]
-        if found_enforced:
-            print(
-                f"\n✅ PASSED: All enforced targets meet the {threshold}% coverage threshold."
-            )
-
-    return True
-
-
-def main() -> int:
-    """Main entry point.
-
-    Returns:
-        Exit code: 0 for success, 1 for failure.
-    """
-    if len(sys.argv) != 3:
-        print(f"Usage: {sys.argv[0]} <coverage-xml-path> <threshold>")
-        print(f"Example: {sys.argv[0]} python-coverage.xml 85")
-        return 1
-
-    xml_path = sys.argv[1]
-    try:
-        threshold = float(sys.argv[2])
-    except ValueError:
-        print(f"Error: Invalid threshold value: {sys.argv[2]}")
-        return 1
-
-    try:
-        success = check_coverage(xml_path, threshold)
-        return 0 if success else 1
-    except FileNotFoundError:
-        print(f"Error: Coverage file not found: {xml_path}")
-        return 1
-    except ET.ParseError as e:
-        print(f"Error: Failed to parse coverage XML: {e}")
-        return 1
-
-
-if __name__ == "__main__":
-    sys.exit(main())

.github/workflows/python-code-quality.yml

@@ -6,6 +6,10 @@ on:
     branches: ["main"]
     paths:
       - "python/**"
+      - "!python/AGENTS.md"
+      - "!python/**/AGENTS.md"
+      - "!python/.github/skills/*"
+      - "!python/.github/skills/**"
 
 env:
   # Configure a constant location for the uv cache
@@ -27,7 +31,7 @@ jobs:
     env:
       UV_PYTHON: ${{ matrix.python-version }}
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
         with:
           fetch-depth: 0
       - name: Set up python and install the project
@@ -38,11 +42,11 @@ jobs:
           os: ${{ runner.os }}
         env:
           UV_CACHE_DIR: /tmp/.uv-cache
-      - uses: actions/cache@v5
+      - uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5
         with:
           path: ~/.cache/prek
           key: prek|${{ matrix.python-version }}|${{ hashFiles('python/.pre-commit-config.yaml') }}
-      - uses: j178/prek-action@v1
+      - uses: j178/prek-action@bdca6f102f98e2b4c7029491a53dfd366469e33d # v2.0.4
         name: Run Pre-commit Hooks (excluding poe-check)
         env:
           SKIP: poe-check
@@ -64,7 +68,7 @@ jobs:
     env:
       UV_PYTHON: ${{ matrix.python-version }}
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
         with:
           fetch-depth: 0
       - name: Set up python and install the project
@@ -93,7 +97,7 @@ jobs:
     env:
       UV_PYTHON: ${{ matrix.python-version }}
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
         with:
           fetch-depth: 0
       - name: Set up python and install the project
@@ -109,8 +113,8 @@ jobs:
       - name: Run markdown code lint
         run: uv run poe markdown-code-lint
 
-  mypy:
-    name: Mypy Checks
+  test-typing:
+    name: Test Typing Checks
     if: "!cancelled()"
     strategy:
       fail-fast: false
@@ -124,7 +128,7 @@ jobs:
     env:
       UV_PYTHON: ${{ matrix.python-version }}
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
         with:
           fetch-depth: 0
       - name: Set up python and install the project
@@ -135,7 +139,5 @@ jobs:
           os: ${{ runner.os }}
         env:
           UV_CACHE_DIR: /tmp/.uv-cache
-      - name: Run Mypy
-        env:
-          GITHUB_BASE_REF: ${{ github.event.pull_request.base.ref || github.base_ref || 'main' }}
-        run: uv run python scripts/workspace_poe_tasks.py ci-mypy
+      - name: Run tests/samples type checkers (mypy, pyrefly, ty)
+        run: uv run python scripts/workspace_poe_tasks.py ci-test-typing

.github/workflows/python-dependency-maintenance.yml

@@ -0,0 +1,431 @@
+name: Python - Dependency Maintenance
+
+on:
+  workflow_dispatch:
+  schedule:
+    - cron: "0 4 * * 1"
+
+permissions:
+  contents: write
+  issues: write
+
+concurrency:
+  group: python-dependency-maintenance
+  cancel-in-progress: false
+
+env:
+  UV_CACHE_DIR: /tmp/.uv-cache
+
+jobs:
+  dependency-maintenance:
+    name: Dependency Maintenance
+    runs-on: ubuntu-latest
+    env:
+      # Match the existing Python dependency maintenance workflows. Reevaluate if package
+      # installability starts differing across supported Python versions.
+      UV_PYTHON: "3.13"
+    steps:
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
+        with:
+          fetch-depth: 0
+
+      - name: Set up python and install the project
+        uses: ./.github/actions/python-setup
+        with:
+          python-version: ${{ env.UV_PYTHON }}
+          os: ${{ runner.os }}
+        env:
+          UV_CACHE_DIR: /tmp/.uv-cache
+
+      - name: Set dependency release cutoff
+        run: |
+          cutoff="$(date -u -d '7 days ago' '+%Y-%m-%dT%H:%M:%SZ')"
+          echo "DEPENDENCY_RELEASE_CUTOFF=${cutoff}" >> "$GITHUB_ENV"
+          echo "Using dependency release cutoff: ${cutoff}"
+
+      - name: Repin dev dependency declarations
+        run: uv run poe upgrade-dev-dependency-pins
+        working-directory: ./python
+
+      - name: Refresh lockfile after dev pin updates
+        run: uv lock
+        working-directory: ./python
+
+      - name: Save dev dependency changes
+        run: |
+          DEV_PATCH="${RUNNER_TEMP}/python-dev-dependency-updates.patch"
+          git diff -- python/pyproject.toml "python/packages/*/pyproject.toml" python/uv.lock > "${DEV_PATCH}"
+          if [ -s "${DEV_PATCH}" ]; then
+            echo "has_dev_changes=true" >> "$GITHUB_OUTPUT"
+          else
+            echo "has_dev_changes=false" >> "$GITHUB_OUTPUT"
+          fi
+          echo "patch=${DEV_PATCH}" >> "$GITHUB_OUTPUT"
+        id: dev_changes
+
+      - name: Run dependency bounds test scenarios
+        id: validate_bounds_test
+        continue-on-error: true
+        run: uv run poe validate-dependency-bounds-test --package "*"
+        working-directory: ./python
+
+      - name: Run dependency upper-bound validation
+        id: validate_ranges
+        if: steps.validate_bounds_test.outcome == 'success'
+        continue-on-error: true
+        run: uv run poe validate-dependency-bounds-project --mode upper --package "*"
+        working-directory: ./python
+
+      - name: Upload dependency validation reports
+        if: always()
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
+        with:
+          name: dependency-maintenance-results
+          path: |
+            python/scripts/dependencies/dependency-bounds-test-results.json
+            python/scripts/dependencies/dependency-range-results.json
+          if-no-files-found: warn
+
+      - name: Create issue for failed dependency bounds test
+        if: steps.validate_bounds_test.outcome != 'success'
+        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
+        with:
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+          script: |
+            const fs = require("fs")
+            const reportPath = "python/scripts/dependencies/dependency-bounds-test-results.json"
+
+            const owner = context.repo.owner
+            const repo = context.repo.repo
+            const openIssues = await github.paginate(github.rest.issues.listForRepo, {
+              owner,
+              repo,
+              state: "open",
+              per_page: 100,
+            })
+            const openIssueTitles = new Set(
+              openIssues.filter((issue) => !issue.pull_request).map((issue) => issue.title)
+            )
+
+            const formatError = (message) => String(message || "No error output captured.").replace(/```/g, "'''")
+            const title = "Dependency bounds test failed"
+            if (openIssueTitles.has(title)) {
+              core.info(`Issue already exists: ${title}`)
+              return
+            }
+
+            const bodyLines = [
+              "Automated dependency bounds test mode failed before dependency upper-bound validation could run.",
+              "",
+              "The weekly dependency maintenance workflow kept only dev dependency updates for the generated PR, if any, and skipped dependency range updates for this run.",
+              "",
+            ]
+
+            if (fs.existsSync(reportPath)) {
+              const report = JSON.parse(fs.readFileSync(reportPath, "utf8"))
+              const failedScenarios = (report.scenarios ?? []).filter((scenario) => scenario.status === "failed")
+              for (const scenario of failedScenarios) {
+                bodyLines.push(`### ${scenario.name} scenario (${scenario.resolution})`)
+                const failedPackages = (scenario.packages ?? []).filter((pkg) => pkg.status === "failed")
+                for (const pkg of failedPackages.slice(0, 10)) {
+                  bodyLines.push(
+                    "",
+                    `- Package: \`${pkg.package_name}\``,
+                    `- Project path: \`${pkg.project_path}\``,
+                    "",
+                    "```",
+                    formatError(pkg.error).slice(0, 3500),
+                    "```"
+                  )
+                }
+                if (failedPackages.length > 10) {
+                  bodyLines.push("", `_Additional failed packages omitted: ${failedPackages.length - 10}_`)
+                }
+              }
+            } else {
+              bodyLines.push(`No dependency bounds test report was found at \`${reportPath}\`.`)
+            }
+
+            bodyLines.push("", `Workflow run: ${context.serverUrl}/${owner}/${repo}/actions/runs/${context.runId}`)
+
+            await github.rest.issues.create({
+              owner,
+              repo,
+              title,
+              body: bodyLines.join("\n"),
+            })
+            core.info(`Created issue: ${title}`)
+
+      - name: Create issues for failed dependency candidates
+        if: always()
+        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
+        with:
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+          script: |
+            const fs = require("fs")
+            const reportPath = "python/scripts/dependencies/dependency-range-results.json"
+
+            if (!fs.existsSync(reportPath)) {
+              core.info(`No dependency range report found at ${reportPath}`)
+              return
+            }
+
+            const report = JSON.parse(fs.readFileSync(reportPath, "utf8"))
+            const dependencyFailures = []
+
+            for (const packageResult of report.packages ?? []) {
+              for (const dependency of packageResult.dependencies ?? []) {
+                const candidateVersions = new Set(dependency.candidate_versions ?? [])
+                const failedAttempts = (dependency.attempts ?? []).filter(
+                  (attempt) => attempt.status === "failed" && candidateVersions.has(attempt.trial_upper)
+                )
+                if (!failedAttempts.length) {
+                  continue
+                }
+
+                const failuresByVersion = new Map()
+                for (const attempt of failedAttempts) {
+                  const version = attempt.trial_upper || "unknown"
+                  if (!failuresByVersion.has(version)) {
+                    failuresByVersion.set(version, attempt.error || "No error output captured.")
+                  }
+                }
+
+                dependencyFailures.push({
+                  packageName: packageResult.package_name,
+                  projectPath: packageResult.project_path,
+                  dependencyName: dependency.name,
+                  originalRequirements: dependency.original_requirements ?? [],
+                  finalRequirements: dependency.final_requirements ?? [],
+                  failedVersions: [...failuresByVersion.entries()].map(([version, error]) => ({ version, error })),
+                })
+              }
+            }
+
+            if (!dependencyFailures.length) {
+              core.info("No failing dependency candidates found.")
+              return
+            }
+
+            const owner = context.repo.owner
+            const repo = context.repo.repo
+            const openIssues = await github.paginate(github.rest.issues.listForRepo, {
+              owner,
+              repo,
+              state: "open",
+              per_page: 100,
+            })
+            const openIssueTitles = new Set(
+              openIssues.filter((issue) => !issue.pull_request).map((issue) => issue.title)
+            )
+
+            const formatError = (message) => String(message || "No error output captured.").replace(/```/g, "'''")
+
+            for (const failure of dependencyFailures) {
+              const title = `Dependency validation failed: ${failure.dependencyName} (${failure.packageName})`
+              if (openIssueTitles.has(title)) {
+                core.info(`Issue already exists: ${title}`)
+                continue
+              }
+
+              const visibleFailures = failure.failedVersions.slice(0, 5)
+              const omittedCount = failure.failedVersions.length - visibleFailures.length
+              const failureDetails = visibleFailures
+                .map(
+                  (entry) =>
+                    `- \`${entry.version}\`\n\n\`\`\`\n${formatError(entry.error).slice(0, 3500)}\n\`\`\``
+                )
+                .join("\n\n")
+
+              const body = [
+                "Automated dependency range validation found candidate versions that failed checks.",
+                "",
+                `- Package: \`${failure.packageName}\``,
+                `- Project path: \`${failure.projectPath}\``,
+                `- Dependency: \`${failure.dependencyName}\``,
+                `- Original requirements: ${
+                  failure.originalRequirements.length
+                    ? failure.originalRequirements.map((value) => `\`${value}\``).join(", ")
+                    : "_none_"
+                }`,
+                `- Final requirements after run: ${
+                  failure.finalRequirements.length
+                    ? failure.finalRequirements.map((value) => `\`${value}\``).join(", ")
+                    : "_none_"
+                }`,
+                "",
+                "### Failed versions and errors",
+                failureDetails,
+                omittedCount > 0 ? `\n_Additional failed versions omitted: ${omittedCount}_` : "",
+                "",
+                `Workflow run: ${context.serverUrl}/${owner}/${repo}/actions/runs/${context.runId}`,
+              ].join("\n")
+
+              await github.rest.issues.create({
+                owner,
+                repo,
+                title,
+                body,
+              })
+              openIssueTitles.add(title)
+              core.info(`Created issue: ${title}`)
+            }
+
+      - name: Keep only dev updates when range validation fails
+        if: steps.validate_bounds_test.outcome != 'success' || steps.validate_ranges.outcome != 'success'
+        env:
+          DEV_PATCH: ${{ steps.dev_changes.outputs.patch }}
+          HAS_DEV_CHANGES: ${{ steps.dev_changes.outputs.has_dev_changes }}
+        run: |
+          git restore python/pyproject.toml python/packages/*/pyproject.toml python/uv.lock
+          if [ "${HAS_DEV_CHANGES}" = "true" ]; then
+            git apply "${DEV_PATCH}"
+          fi
+
+      - name: Refresh lockfile after dependency range updates
+        if: steps.validate_bounds_test.outcome == 'success' && steps.validate_ranges.outcome == 'success'
+        run: uv lock
+        working-directory: ./python
+
+      - name: Install final dependency set
+        run: uv run poe install
+        working-directory: ./python
+
+      - name: Run final checks
+        run: uv run poe check
+        working-directory: ./python
+
+      - name: Run final typing
+        run: uv run poe typing
+        working-directory: ./python
+
+      - name: Commit and push dependency updates
+        id: commit_updates
+        run: |
+          BRANCH="automation/python-dependency-maintenance"
+
+          git config user.name "github-actions[bot]"
+          git config user.email "41898282+github-actions[bot]@users.noreply.github.com"
+          git checkout -B "${BRANCH}"
+
+          git add python/pyproject.toml python/packages/*/pyproject.toml python/uv.lock
+          if git diff --cached --quiet; then
+            echo "has_changes=false" >> "$GITHUB_OUTPUT"
+            echo "No dependency updates to commit."
+            exit 0
+          fi
+
+          git commit -m "Python: chore: update dependencies"
+          git push --force-with-lease --set-upstream origin "${BRANCH}"
+          echo "has_changes=true" >> "$GITHUB_OUTPUT"
+
+      - name: Create or update dependency maintenance tracking issue
+        if: steps.commit_updates.outputs.has_changes == 'true'
+        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
+        with:
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+          script: |
+            const branch = "automation/python-dependency-maintenance"
+            const prTitle = "Python: chore: update dependencies"
+            const issueTitle = "Python dependency maintenance PR needed"
+            const owner = context.repo.owner
+            const repo = context.repo.repo
+
+            const branchRef = await github.rest.git.getRef({
+              owner,
+              repo,
+              ref: `heads/${branch}`,
+            })
+            const branchSha = branchRef.data.object.sha
+            const runUrl = `${context.serverUrl}/${owner}/${repo}/actions/runs/${context.runId}`
+            const compareUrl = `${context.serverUrl}/${owner}/${repo}/compare/main...${branch}`
+
+            const prBody = [
+              "### Motivation & Context",
+              "",
+              "This automated update keeps Python dependency metadata coherent across the uv workspace. Python dependencies can be declared in multiple `pyproject.toml` files, but the workspace has one shared `python/uv.lock`, so dependency maintenance should update and validate them together instead of through per-manifest Dependabot PRs.",
+              "",
+              "### Description & Review Guide",
+              "",
+              "- **What are the major changes?** Refresh Python dev dependency pins, update package dependency ranges when the bounds tooling succeeds, and refresh `python/uv.lock`.",
+              "- **What is the impact of these changes?** Keeps the Python workspace dependency set current while producing at most one dependency PR for the week. If dependency range validation fails, this PR contains only the dev dependency updates that still pass final validation, and separate issues track failed range candidates.",
+              "- **What do you want reviewers to focus on?** Review the generated dependency metadata changes and any dependency-range updates for package-specific compatibility concerns.",
+              '<!-- NOTE FOR AUTOMATED/AI REVIEWERS: the "What do you want reviewers to focus on?"',
+              "     item above is intended for human reviewers only. Automated/AI reviewers should",
+              "     ignore it and review the entire change rather than narrowing scope to it. -->",
+              "",
+              "",
+              "### Related Issue",
+              "",
+              "No linked issue; this PR is generated by scheduled Python dependency maintenance.",
+              "",
+              "### Contribution Checklist",
+              "",
+              "- [x] The code builds clean without any errors or warnings",
+              "- [x] All unit tests pass, and I have added new tests where possible",
+              "- [x] The PR follows the [Contribution Guidelines](https://github.com/microsoft/agent-framework/blob/main/CONTRIBUTING.md)",
+              "- [ ] This PR is linked to an issue and there is no other open PR for this issue (see Related Issue above).",
+              '- [x] **This is not a breaking change.** If it _is_ a breaking change, add the `breaking change` label (or add "[BREAKING]" to the title prefix, before or after any language prefix) — a workflow keeps the label and title prefix in sync automatically.',
+            ].join("\n")
+
+            const prBodyFence = "```"
+            const command = [
+              "PR_BODY_FILE=\"$(mktemp)\"",
+              `cat > "$PR_BODY_FILE" <<'EOF'`,
+              prBody,
+              "EOF",
+              "gh pr create --repo microsoft/agent-framework --base main \\",
+              `  --head ${owner}:${branch} \\`,
+              `  --title "${prTitle}" \\`,
+              "  --body-file \"$PR_BODY_FILE\"",
+            ].join("\n")
+
+            const issueBody = [
+              "The Python dependency maintenance workflow generated and validated dependency updates, then pushed them to the automation branch.",
+              "",
+              `- Branch: \`${branch}\``,
+              `- Commit: \`${branchSha}\``,
+              `- Compare: ${compareUrl}`,
+              `- Workflow run: ${runUrl}`,
+              "",
+              "GitHub Actions is not permitted to create pull requests in this repository, so a maintainer needs to create the PR manually.",
+              "",
+              "### Create the PR",
+              "",
+              "```bash",
+              command,
+              "```",
+              "",
+              "### Generated PR body",
+              "",
+              prBodyFence,
+              prBody,
+              prBodyFence,
+            ].join("\n")
+
+            const openIssues = await github.paginate(github.rest.issues.listForRepo, {
+              owner,
+              repo,
+              state: "open",
+              per_page: 100,
+            })
+            const existingIssue = openIssues.find((issue) => !issue.pull_request && issue.title === issueTitle)
+
+            if (existingIssue) {
+              await github.rest.issues.update({
+                owner,
+                repo,
+                issue_number: existingIssue.number,
+                title: issueTitle,
+                body: issueBody,
+              })
+              core.info(`Updated issue #${existingIssue.number}: ${issueTitle}`)
+            } else {
+              const createdIssue = await github.rest.issues.create({
+                owner,
+                repo,
+                title: issueTitle,
+                body: issueBody,
+              })
+              core.info(`Created issue #${createdIssue.data.number}: ${issueTitle}`)
+            }

.github/workflows/python-dependency-range-validation.yml

@@ -1,216 +0,0 @@
-# Probe the highest allowed dependency versions, then open issues/PRs from the passing updates.
-name: Python - Dependency Range Validation
-
-on:
-  workflow_dispatch:
-
-permissions:
-  contents: write
-  issues: write
-  pull-requests: write
-
-env:
-  UV_CACHE_DIR: /tmp/.uv-cache
-
-jobs:
-  dependency-range-validation:
-    name: Dependency Range Validation
-    runs-on: ubuntu-latest
-    env:
-      # For now only run 3.13, if we do encounter situations where there are mismatches between packages and python versions (other then 3.10 and 3.14 which are known to not be able to install everything)
-      # then we will have to reevaluate.
-      UV_PYTHON: "3.13"
-      GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-    steps:
-      - uses: actions/checkout@v6
-        with:
-          fetch-depth: 0
-
-      - name: Set up python and install the project
-        uses: ./.github/actions/python-setup
-        with:
-          python-version: ${{ env.UV_PYTHON }}
-          os: ${{ runner.os }}
-        env:
-          UV_CACHE_DIR: /tmp/.uv-cache
-
-      - name: Run dependency range validation
-        id: validate_ranges
-        # Keep workflow running so we can still publish diagnostics from this run.
-        continue-on-error: true
-        run: uv run poe validate-dependency-bounds-project --mode upper --package "*"
-        working-directory: ./python
-
-      - name: Upload dependency range report
-        # Always publish the report so failures are inspectable even when validation fails.
-        if: always()
-        uses: actions/upload-artifact@v7
-        with:
-          name: dependency-range-results
-          path: python/scripts/dependencies/dependency-range-results.json
-          if-no-files-found: warn
-
-      - name: Create issues for failed dependency candidates
-        # Always process the report so failed candidates create actionable tracking issues.
-        if: always()
-        uses: actions/github-script@v8
-        with:
-          script: |
-            const fs = require("fs")
-            const reportPath = "python/scripts/dependencies/dependency-range-results.json"
-
-            if (!fs.existsSync(reportPath)) {
-              core.warning(`No dependency range report found at ${reportPath}`)
-              return
-            }
-
-            const report = JSON.parse(fs.readFileSync(reportPath, "utf8"))
-            const dependencyFailures = []
-
-            for (const packageResult of report.packages ?? []) {
-              for (const dependency of packageResult.dependencies ?? []) {
-                const candidateVersions = new Set(dependency.candidate_versions ?? [])
-                const failedAttempts = (dependency.attempts ?? []).filter(
-                  (attempt) => attempt.status === "failed" && candidateVersions.has(attempt.trial_upper)
-                )
-                if (!failedAttempts.length) {
-                  continue
-                }
-
-                const failuresByVersion = new Map()
-                for (const attempt of failedAttempts) {
-                  const version = attempt.trial_upper || "unknown"
-                  if (!failuresByVersion.has(version)) {
-                    failuresByVersion.set(version, attempt.error || "No error output captured.")
-                  }
-                }
-
-                dependencyFailures.push({
-                  packageName: packageResult.package_name,
-                  projectPath: packageResult.project_path,
-                  dependencyName: dependency.name,
-                  originalRequirements: dependency.original_requirements ?? [],
-                  finalRequirements: dependency.final_requirements ?? [],
-                  failedVersions: [...failuresByVersion.entries()].map(([version, error]) => ({ version, error })),
-                })
-              }
-            }
-
-            if (!dependencyFailures.length) {
-              core.info("No failing dependency candidates found.")
-              return
-            }
-
-            const owner = context.repo.owner
-            const repo = context.repo.repo
-            const openIssues = await github.paginate(github.rest.issues.listForRepo, {
-              owner,
-              repo,
-              state: "open",
-              per_page: 100,
-            })
-            const openIssueTitles = new Set(
-              openIssues.filter((issue) => !issue.pull_request).map((issue) => issue.title)
-            )
-
-            const formatError = (message) => String(message || "No error output captured.").replace(/```/g, "'''")
-
-            for (const failure of dependencyFailures) {
-              const title = `Dependency validation failed: ${failure.dependencyName} (${failure.packageName})`
-              if (openIssueTitles.has(title)) {
-                core.info(`Issue already exists: ${title}`)
-                continue
-              }
-
-              const visibleFailures = failure.failedVersions.slice(0, 5)
-              const omittedCount = failure.failedVersions.length - visibleFailures.length
-              const failureDetails = visibleFailures
-                .map(
-                  (entry) =>
-                    `- \`${entry.version}\`\n\n\`\`\`\n${formatError(entry.error).slice(0, 3500)}\n\`\`\``
-                )
-                .join("\n\n")
-
-              const body = [
-                "Automated dependency range validation found candidate versions that failed checks.",
-                "",
-                `- Package: \`${failure.packageName}\``,
-                `- Project path: \`${failure.projectPath}\``,
-                `- Dependency: \`${failure.dependencyName}\``,
-                `- Original requirements: ${
-                  failure.originalRequirements.length
-                    ? failure.originalRequirements.map((value) => `\`${value}\``).join(", ")
-                    : "_none_"
-                }`,
-                `- Final requirements after run: ${
-                  failure.finalRequirements.length
-                    ? failure.finalRequirements.map((value) => `\`${value}\``).join(", ")
-                    : "_none_"
-                }`,
-                "",
-                "### Failed versions and errors",
-                failureDetails,
-                omittedCount > 0 ? `\n_Additional failed versions omitted: ${omittedCount}_` : "",
-                "",
-                `Workflow run: ${context.serverUrl}/${owner}/${repo}/actions/runs/${context.runId}`,
-              ].join("\n")
-
-              await github.rest.issues.create({
-                owner,
-                repo,
-                title,
-                body,
-              })
-              openIssueTitles.add(title)
-              core.info(`Created issue: ${title}`)
-            }
-
-      - name: Refresh lockfile
-        # Only refresh lockfile after a clean validation to avoid committing known-bad ranges.
-        if: steps.validate_ranges.outcome == 'success'
-        run: uv lock --upgrade
-        working-directory: ./python
-
-      - name: Commit and push dependency updates
-        id: commit_updates
-        if: steps.validate_ranges.outcome == 'success'
-        run: |
-          BRANCH="automation/python-dependency-range-updates"
-
-          git config user.name "github-actions[bot]"
-          git config user.email "41898282+github-actions[bot]@users.noreply.github.com"
-          git checkout -B "${BRANCH}"
-
-          git add python/packages/*/pyproject.toml python/uv.lock
-          if git diff --cached --quiet; then
-            echo "has_changes=false" >> "$GITHUB_OUTPUT"
-            echo "No dependency updates to commit."
-            exit 0
-          fi
-
-          git commit -m "chore: update dependency ranges"
-          git push --force-with-lease --set-upstream origin "${BRANCH}"
-          echo "has_changes=true" >> "$GITHUB_OUTPUT"
-
-      - name: Create or update pull request with GitHub CLI
-        # Only open/update PRs for validated updates to keep automation branches trustworthy.
-        if: steps.validate_ranges.outcome == 'success' && steps.commit_updates.outputs.has_changes == 'true'
-        run: |
-          BRANCH="automation/python-dependency-range-updates"
-          PR_TITLE="Python: chore: update dependency ranges"
-          PR_BODY_FILE="$(mktemp)"
-
-          cat > "${PR_BODY_FILE}" <<'EOF'
-          This PR was generated by the dependency range validation workflow.
-
-          - Ran `uv run poe validate-dependency-bounds-project --mode upper --package "*"`
-          - Updated package dependency bounds
-          - Refreshed `python/uv.lock` with `uv lock --upgrade`
-          EOF
-
-          PR_NUMBER="$(gh pr list --head "${BRANCH}" --base main --state open --json number --jq '.[0].number')"
-          if [ -n "${PR_NUMBER}" ]; then
-            gh pr edit "${PR_NUMBER}" --title "${PR_TITLE}" --body-file "${PR_BODY_FILE}"
-          else
-            gh pr create --base main --head "${BRANCH}" --title "${PR_TITLE}" --body-file "${PR_BODY_FILE}"
-          fi

.github/workflows/python-dev-dependency-upgrade.yml

@@ -1,91 +0,0 @@
-name: Python - Dev Dependency Upgrade
-
-on:
-  workflow_dispatch:
-
-permissions:
-  contents: write
-  pull-requests: write
-
-env:
-  UV_CACHE_DIR: /tmp/.uv-cache
-
-jobs:
-  upgrade-dev-dependencies:
-    name: Upgrade Dev Dependencies
-    runs-on: ubuntu-latest
-    env:
-      UV_PYTHON: "3.13"
-      GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-    steps:
-      - uses: actions/checkout@v6
-        with:
-          fetch-depth: 0
-
-      - name: Set up python and install the project
-        uses: ./.github/actions/python-setup
-        with:
-          python-version: ${{ env.UV_PYTHON }}
-          os: ${{ runner.os }}
-        env:
-          UV_CACHE_DIR: /tmp/.uv-cache
-
-      - name: Upgrade dev dependencies and validate workspace
-        run: uv run poe upgrade-dev-dependencies
-        working-directory: ./python
-
-      - name: Commit and push dev dependency updates
-        id: commit_updates
-        run: |
-          BRANCH="automation/python-dev-dependency-updates"
-
-          git config user.name "github-actions[bot]"
-          git config user.email "41898282+github-actions[bot]@users.noreply.github.com"
-          git checkout -B "${BRANCH}"
-
-          git add python/pyproject.toml python/packages/*/pyproject.toml python/uv.lock
-          if git diff --cached --quiet; then
-            echo "has_changes=false" >> "$GITHUB_OUTPUT"
-            echo "No dev dependency updates to commit."
-            exit 0
-          fi
-
-          git commit -F- <<'EOF'
-          Python: chore: upgrade dev dependencies
-          EOF
-          git push --force-with-lease --set-upstream origin "${BRANCH}"
-          echo "has_changes=true" >> "$GITHUB_OUTPUT"
-
-      - name: Create or update pull request with GitHub CLI
-        if: steps.commit_updates.outputs.has_changes == 'true'
-        run: |
-          BRANCH="automation/python-dev-dependency-updates"
-          PR_TITLE="Python: chore: upgrade dev dependencies"
-          PR_BODY_FILE="$(mktemp)"
-
-          cat > "${PR_BODY_FILE}" <<'EOF'
-          ### Motivation and Context
-
-          This automated update refreshes Python dev dependency pins across the workspace and reruns the repo validation gates before opening a pull request.
-
-          ### Description
-
-          - Ran `uv run poe upgrade-dev-dependencies`
-          - Refreshed dev dependency pins in workspace `pyproject.toml` files
-          - Refreshed `python/uv.lock` with `uv lock --upgrade`
-          - Reinstalled from the frozen lockfile and reran `check`, `typing`, and `test`
-
-          ### Contribution Checklist
-
-          - [x] The code builds clean without any errors or warnings
-          - [x] The PR follows the [Contribution Guidelines](https://github.com/microsoft/agent-framework/blob/main/CONTRIBUTING.md)
-          - [x] All unit tests pass, and I have added new tests where possible
-          - [ ] **Is this a breaking change?** If yes, add "[BREAKING]" prefix to the title of the PR.
-          EOF
-
-          PR_NUMBER="$(gh pr list --head "${BRANCH}" --base main --state open --json number --jq '.[0].number')"
-          if [ -n "${PR_NUMBER}" ]; then
-            gh pr edit "${PR_NUMBER}" --title "${PR_TITLE}" --body-file "${PR_BODY_FILE}"
-          else
-            gh pr create --base main --head "${BRANCH}" --title "${PR_TITLE}" --body-file "${PR_BODY_FILE}"
-          fi

.github/workflows/python-docs.yml

@@ -24,9 +24,9 @@ jobs:
       run:
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
       - name: Set up uv
-        uses: astral-sh/setup-uv@v7
+        uses: astral-sh/setup-uv@11f9893b081a58869d3b5fccaea48c9e9e46f990 # v8.3.2
         with:
           version-file: "python/pyproject.toml"
           enable-cache: true

.github/workflows/python-integration-tests.yml

@@ -13,13 +13,25 @@ on:
   workflow_call:
     inputs:
       checkout-ref:
-        description: "Git ref to checkout (e.g., refs/pull/123/head)"
+        description: "Immutable commit SHA to check out"
         required: true
         type: string
+    secrets:
+      ANTHROPIC_API_KEY:
+        required: true
+      AZURE_CLIENT_ID:
+        required: true
+      AZURE_TENANT_ID:
+        required: true
+      AZURE_SUBSCRIPTION_ID:
+        required: true
+      FOUNDRY_MODELS_API_KEY:
+        required: false
+      OPENAI__APIKEY:
+        required: true
 
 permissions:
   contents: read
-  id-token: write
 
 env:
   UV_CACHE_DIR: /tmp/.uv-cache
@@ -36,7 +48,7 @@ jobs:
       run:
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
         with:
           ref: ${{ inputs.checkout-ref }}
           persist-credentials: false
@@ -69,7 +81,7 @@ jobs:
       run:
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
         with:
           ref: ${{ inputs.checkout-ref }}
           persist-credentials: false
@@ -87,10 +99,21 @@ jobs:
           -n logical --dist worksteal
           --timeout=120 --session-timeout=900 --timeout_method thread
           --retries 2 --retry-delay 5
+          --junitxml=pytest.xml
+      - name: Upload test results
+        if: always()
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
+        with:
+          name: test-results-openai
+          path: ./python/pytest.xml
+          if-no-files-found: ignore
 
   # Azure OpenAI integration tests
   python-tests-azure-openai:
     name: Python Integration Tests - Azure OpenAI
+    permissions:
+      contents: read
+      id-token: write
     runs-on: ubuntu-latest
     environment: integration
     timeout-minutes: 60
@@ -104,7 +127,7 @@ jobs:
       run:
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
         with:
           ref: ${{ inputs.checkout-ref }}
           persist-credentials: false
@@ -115,7 +138,7 @@ jobs:
           python-version: ${{ env.UV_PYTHON }}
           os: ${{ runner.os }}
       - name: Azure CLI Login
-        uses: azure/login@v2
+        uses: azure/login@a457da9ea143d694b1b9c7c869ebb04ebe844ef5 # v2
         with:
           client-id: ${{ secrets.AZURE_CLIENT_ID }}
           tenant-id: ${{ secrets.AZURE_TENANT_ID }}
@@ -130,6 +153,14 @@ jobs:
           -n logical --dist worksteal
           --timeout=120 --session-timeout=900 --timeout_method thread
           --retries 2 --retry-delay 5
+          --junitxml=pytest.xml
+      - name: Upload test results
+        if: always()
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
+        with:
+          name: test-results-azure-openai
+          path: ./python/pytest.xml
+          if-no-files-found: ignore
 
   # Misc integration tests (Anthropic, Hyperlight, Ollama, MCP)
   python-tests-misc-integration:
@@ -141,11 +172,13 @@ jobs:
       ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
       ANTHROPIC_CHAT_MODEL: ${{ vars.ANTHROPIC_CHAT_MODEL_ID }}
       LOCAL_MCP_URL: ${{ vars.LOCAL_MCP__URL }}
+      OLLAMA_MODEL: qwen2.5:1.5b
+      OLLAMA_EMBEDDING_MODEL: nomic-embed-text
     defaults:
       run:
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
         with:
           ref: ${{ inputs.checkout-ref }}
           persist-credentials: false
@@ -155,6 +188,43 @@ jobs:
         with:
           python-version: ${{ env.UV_PYTHON }}
           os: ${{ runner.os }}
+      - name: Install Ollama
+        run: curl -fsSL https://ollama.com/install.sh | sh
+        working-directory: .
+      - name: Cache Ollama models
+        uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
+        with:
+          path: ~/.ollama/models
+          key: ollama-models-qwen2.5-1.5b-nomic-embed-text-v1
+      - name: Start Ollama and pull models
+        run: |
+          # Stop any Ollama instance auto-started by the install script
+          pkill ollama || true
+          sleep 2
+          ollama serve &
+          for i in $(seq 1 30); do
+            if curl -sf http://localhost:11434/api/tags > /dev/null 2>&1; then
+              break
+            fi
+            sleep 1
+          done
+          # Pull models with retry for transient 429 rate limits
+          for model in qwen2.5:1.5b nomic-embed-text; do
+            pulled=false
+            for attempt in 1 2 3; do
+              if ollama pull "$model"; then
+                pulled=true
+                break
+              fi
+              echo "Retry $attempt for $model (waiting 15s)..."
+              sleep 15
+            done
+            if [ "$pulled" != "true" ]; then
+              echo "ERROR: Failed to pull $model after 3 attempts"
+              exit 1
+            fi
+          done
+        working-directory: .
       - name: Start local MCP server
         id: local-mcp
         uses: ./.github/actions/setup-local-mcp-server
@@ -169,10 +239,19 @@ jobs:
           packages/hyperlight/tests
           packages/ollama/tests
           packages/core/tests/core/test_mcp.py
+          packages/hosting-mcp/tests
           -m integration
           -n logical --dist worksteal
           --timeout=120 --session-timeout=900 --timeout_method thread
           --retries 2 --retry-delay 30
+          --junitxml=pytest.xml
+      - name: Upload test results
+        if: always()
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
+        with:
+          name: test-results-misc
+          path: ./python/pytest.xml
+          if-no-files-found: ignore
       - name: Stop local MCP server
         if: always()
         shell: bash
@@ -197,6 +276,9 @@ jobs:
   # Azure Functions + Durable Task integration tests
   python-tests-functions:
     name: Python Integration Tests - Functions
+    permissions:
+      contents: read
+      id-token: write
     runs-on: ubuntu-latest
     environment: integration
     timeout-minutes: 60
@@ -220,7 +302,7 @@ jobs:
       run:
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
         with:
           ref: ${{ inputs.checkout-ref }}
           persist-credentials: false
@@ -231,7 +313,7 @@ jobs:
           python-version: ${{ env.UV_PYTHON }}
           os: ${{ runner.os }}
       - name: Azure CLI Login
-        uses: azure/login@v2
+        uses: azure/login@a457da9ea143d694b1b9c7c869ebb04ebe844ef5 # v2
         with:
           client-id: ${{ secrets.AZURE_CLIENT_ID }}
           tenant-id: ${{ secrets.AZURE_TENANT_ID }}
@@ -247,12 +329,23 @@ jobs:
           -m integration
           -n logical --dist worksteal
           -x
-          --timeout=360 --session-timeout=900 --timeout_method thread
+          --timeout=480 --session-timeout=900 --timeout_method thread
           --retries 2 --retry-delay 5
+          --junitxml=pytest.xml
+      - name: Upload test results
+        if: always()
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
+        with:
+          name: test-results-functions
+          path: ./python/pytest.xml
+          if-no-files-found: ignore
 
   # Foundry integration tests
   python-tests-foundry:
     name: Python Integration Tests - Foundry
+    permissions:
+      contents: read
+      id-token: write
     runs-on: ubuntu-latest
     environment: integration
     timeout-minutes: 60
@@ -270,7 +363,7 @@ jobs:
       run:
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
         with:
           ref: ${{ inputs.checkout-ref }}
           persist-credentials: false
@@ -281,7 +374,7 @@ jobs:
           python-version: ${{ env.UV_PYTHON }}
           os: ${{ runner.os }}
       - name: Azure CLI Login
-        uses: azure/login@v2
+        uses: azure/login@a457da9ea143d694b1b9c7c869ebb04ebe844ef5 # v2
         with:
           client-id: ${{ secrets.AZURE_CLIENT_ID }}
           tenant-id: ${{ secrets.AZURE_TENANT_ID }}
@@ -295,6 +388,64 @@ jobs:
           -n logical --dist worksteal
           --timeout=120 --session-timeout=900 --timeout_method thread
           --retries 2 --retry-delay 5
+          --junitxml=pytest.xml
+      - name: Upload test results
+        if: always()
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
+        with:
+          name: test-results-foundry
+          path: ./python/pytest.xml
+          if-no-files-found: ignore
+
+  # Foundry Hosting integration tests
+  python-tests-foundry-hosting:
+    name: Python Integration Tests - Foundry Hosting
+    permissions:
+      contents: read
+      id-token: write
+    runs-on: ubuntu-latest
+    environment: integration
+    timeout-minutes: 60
+    env:
+      FOUNDRY_PROJECT_ENDPOINT: ${{ vars.FOUNDRY_PROJECT_ENDPOINT }}
+      FOUNDRY_MODEL: ${{ vars.FOUNDRY_MODEL }}
+    defaults:
+      run:
+        working-directory: python
+    steps:
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
+        with:
+          ref: ${{ inputs.checkout-ref }}
+          persist-credentials: false
+      - name: Set up python and install the project
+        id: python-setup
+        uses: ./.github/actions/python-setup
+        with:
+          python-version: ${{ env.UV_PYTHON }}
+          os: ${{ runner.os }}
+      - name: Azure CLI Login
+        uses: azure/login@a457da9ea143d694b1b9c7c869ebb04ebe844ef5 # v2
+        with:
+          client-id: ${{ secrets.AZURE_CLIENT_ID }}
+          tenant-id: ${{ secrets.AZURE_TENANT_ID }}
+          subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
+      - name: Test with pytest (Foundry Hosting integration)
+        timeout-minutes: 15
+        run: >
+          uv run pytest --import-mode=importlib
+          packages/foundry_hosting/tests
+          -m integration
+          -n logical --dist worksteal
+          --timeout=120 --session-timeout=900 --timeout_method thread
+          --retries 2 --retry-delay 5
+          --junitxml=pytest.xml
+      - name: Upload test results
+        if: always()
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
+        with:
+          name: test-results-foundry-hosting
+          path: ./python/pytest.xml
+          if-no-files-found: ignore
 
   # Azure Cosmos integration tests
   python-tests-cosmos:
@@ -317,7 +468,7 @@ jobs:
       run:
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
         with:
           ref: ${{ inputs.checkout-ref }}
           persist-credentials: false
@@ -339,7 +490,124 @@ jobs:
           echo "Cosmos DB emulator did not become ready in time." >&2
           exit 1
       - name: Test with pytest (Cosmos integration)
-        run: uv run --directory packages/azure-cosmos poe integration-tests -n logical --dist worksteal --timeout=120 --session-timeout=900 --timeout_method thread --retries 2 --retry-delay 5
+        run: uv run --directory packages/azure-cosmos poe integration-tests -n logical --dist worksteal --timeout=120 --session-timeout=900 --timeout_method thread --retries 2 --retry-delay 5 --junitxml=${{ github.workspace }}/python/pytest.xml
+      - name: Upload test results
+        if: always()
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
+        with:
+          name: test-results-cosmos
+          path: ./python/pytest.xml
+          if-no-files-found: ignore
+
+  # GitHub Copilot integration tests
+  python-tests-github-copilot:
+    name: Python Integration Tests - GitHub Copilot
+    runs-on: ubuntu-latest
+    environment: integration
+    permissions:
+      copilot-requests: write
+      contents: read
+    timeout-minutes: 60
+    env:
+      COPILOT_GITHUB_TOKEN: ${{ github.token }}
+      GITHUB_COPILOT_TIMEOUT: "120"
+    defaults:
+      run:
+        working-directory: python
+    steps:
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
+        with:
+          ref: ${{ inputs.checkout-ref }}
+          persist-credentials: false
+      - name: Set up python and install the project
+        id: python-setup
+        uses: ./.github/actions/python-setup
+        with:
+          python-version: ${{ env.UV_PYTHON }}
+          os: ${{ runner.os }}
+      - name: Test with pytest (GitHub Copilot integration)
+        run: >
+          uv run pytest --import-mode=importlib
+          packages/github_copilot/tests
+          -m integration
+          --timeout=120 --session-timeout=900 --timeout_method thread
+          --retries 2 --retry-delay 5
+          --junitxml=pytest.xml
+      - name: Upload test results
+        if: always()
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
+        with:
+          name: test-results-github-copilot
+          path: ./python/pytest.xml
+          if-no-files-found: ignore
+
+  # Integration test trend report (aggregates per-job JUnit XML results)
+  python-integration-test-report:
+    name: Integration Test Report
+    if: >
+      always() &&
+      (contains(join(needs.*.result, ','), 'success') ||
+       contains(join(needs.*.result, ','), 'failure'))
+    needs:
+      [
+        python-tests-openai,
+        python-tests-azure-openai,
+        python-tests-misc-integration,
+        python-tests-functions,
+        python-tests-foundry,
+        python-tests-foundry-hosting,
+        python-tests-cosmos,
+        python-tests-github-copilot,
+      ]
+    runs-on: ubuntu-latest
+    defaults:
+      run:
+        working-directory: python
+    steps:
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
+        with:
+          ref: ${{ inputs.checkout-ref }}
+          persist-credentials: false
+      - name: Set up python and install the project
+        uses: ./.github/actions/python-setup
+        with:
+          python-version: ${{ env.UV_PYTHON }}
+          os: ${{ runner.os }}
+      - name: Download all test results from current run
+        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
+        with:
+          pattern: test-results-*
+          path: test-results/
+      - name: Restore report history cache
+        uses: actions/cache/restore@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
+        with:
+          path: python/integration-report-history.json
+          key: integration-report-history-integration-${{ github.run_id }}
+          restore-keys: |
+            integration-report-history-integration-
+      - name: Generate trend report
+        run: >
+          uv run python scripts/integration_test_report/aggregate.py
+          ../test-results/
+          integration-report-history.json
+          integration-test-report.md
+      - name: Post to Job Summary
+        if: always()
+        run: cat integration-test-report.md >> $GITHUB_STEP_SUMMARY
+      - name: Save report history cache
+        if: always()
+        uses: actions/cache/save@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
+        with:
+          path: python/integration-report-history.json
+          key: integration-report-history-integration-${{ github.run_id }}
+      - name: Upload unified trend report
+        if: always()
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
+        with:
+          name: integration-test-report
+          path: |
+            python/integration-test-report.md
+            python/integration-report-history.json
 
   python-integration-tests-check:
     if: always()
@@ -352,17 +620,19 @@ jobs:
         python-tests-misc-integration,
         python-tests-functions,
         python-tests-foundry,
-        python-tests-cosmos
+        python-tests-foundry-hosting,
+        python-tests-cosmos,
+        python-tests-github-copilot
       ]
     steps:
       - name: Fail workflow if tests failed
         if: contains(join(needs.*.result, ','), 'failure')
-        uses: actions/github-script@v8
+        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
         with:
           script: core.setFailed('Integration Tests Failed!')
 
       - name: Fail workflow if tests cancelled
         if: contains(join(needs.*.result, ','), 'cancelled')
-        uses: actions/github-script@v8
+        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
         with:
           script: core.setFailed('Integration Tests Cancelled!')

.github/workflows/python-lab-tests.yml

@@ -24,13 +24,17 @@ jobs:
     outputs:
       pythonChanges: ${{ steps.filter.outputs.python}}
     steps:
-      - uses: actions/checkout@v6
-      - uses: dorny/paths-filter@v3
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
+      - uses: dorny/paths-filter@7b450fff21473bca461d4b92ce414b9d0420d706 # v4.0.2
         id: filter
         with:
           filters: |
             python:
               - 'python/**'
+              - '!python/AGENTS.md'
+              - '!python/**/AGENTS.md'
+              - '!python/.github/skills/*'
+              - '!python/.github/skills/**'
       # run only if 'python' files were changed
       - name: python tests
         if: steps.filter.outputs.python == 'true'
@@ -59,7 +63,7 @@ jobs:
       run:
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
 
       - name: Set up python and install the project
         id: python-setup
@@ -67,7 +71,7 @@ jobs:
         with:
           python-version: ${{ matrix.python-version }}
           os: ${{ runner.os }}
-          exclude-packages: ${{ matrix.python-version == '3.10' && 'agent-framework-github-copilot' || '' }}
+          exclude-packages: ${{ matrix.python-version == '3.10' && 'agent-framework-github-copilot agent-framework-azure-cosmos-memory' || '' }}
         env:
           # Configure a constant location for the uv cache
           UV_CACHE_DIR: /tmp/.uv-cache
@@ -88,13 +92,10 @@ jobs:
       - name: Run lab type checking
         run: cd packages/lab && uv run poe pyright
 
-      - name: Run lab mypy
-        run: cd packages/lab && uv run poe mypy
-
       # Surface failing tests
       - name: Surface failing tests
         if: always()
-        uses: pmeier/pytest-results-action@v0.7.2
+        uses: pmeier/pytest-results-action@20b595761ba9bf89e115e875f8bc863f913bc8ad # v0.7.2
         with:
           path: ./python/packages/lab/**.xml
           summary: true

.github/workflows/python-merge-tests.yml

@@ -38,10 +38,12 @@ jobs:
       miscChanged: ${{ steps.filter.outputs.misc }}
       functionsChanged: ${{ steps.filter.outputs.functions }}
       foundryChanged: ${{ steps.filter.outputs.foundry }}
+      foundryHostingChanged: ${{ steps.filter.outputs.foundry_hosting }}
       cosmosChanged: ${{ steps.filter.outputs.cosmos }}
+      githubCopilotChanged: ${{ steps.filter.outputs.github_copilot }}
     steps:
-      - uses: actions/checkout@v6
-      - uses: dorny/paths-filter@v3
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
+      - uses: dorny/paths-filter@7b450fff21473bca461d4b92ce414b9d0420d706 # v4.0.2
         id: filter
         with:
           filters: |
@@ -69,6 +71,7 @@ jobs:
               - 'python/packages/ollama/**'
               - 'python/packages/core/agent_framework/_mcp.py'
               - 'python/packages/core/tests/core/test_mcp.py'
+              - 'python/packages/hosting-mcp/**'
               - 'python/scripts/local_mcp_streamable_http_server.py'
               - '.github/actions/setup-local-mcp-server/**'
               - '.github/workflows/python-merge-tests.yml'
@@ -80,8 +83,12 @@ jobs:
               - 'python/packages/foundry/**'
               - 'python/samples/**/providers/foundry/**'
               - 'python/samples/02-agents/embeddings/foundry_embeddings.py'
+            foundry_hosting:
+              - 'python/packages/foundry_hosting/**'
             cosmos:
               - 'python/packages/azure-cosmos/**'
+            github_copilot:
+              - 'python/packages/github_copilot/**'
       # run only if 'python' files were changed
       - name: python tests
         if: steps.filter.outputs.python == 'true'
@@ -103,7 +110,7 @@ jobs:
       run:
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
       - name: Set up python and install the project
         id: python-setup
         uses: ./.github/actions/python-setup
@@ -120,7 +127,7 @@ jobs:
         working-directory: ./python
       - name: Surface failing tests
         if: always()
-        uses: pmeier/pytest-results-action@v0.7.2
+        uses: pmeier/pytest-results-action@20b595761ba9bf89e115e875f8bc863f913bc8ad # v0.7.2
         with:
           path: ./python/pytest.xml
           summary: true
@@ -150,7 +157,7 @@ jobs:
       run:
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
       - name: Set up python and install the project
         id: python-setup
         uses: ./.github/actions/python-setup
@@ -174,13 +181,20 @@ jobs:
         working-directory: ./python
       - name: Surface failing tests
         if: always()
-        uses: pmeier/pytest-results-action@v0.7.2
+        uses: pmeier/pytest-results-action@20b595761ba9bf89e115e875f8bc863f913bc8ad # v0.7.2
         with:
           path: ./python/pytest.xml
           summary: true
           display-options: fEX
           fail-on-empty: false
           title: OpenAI integration test results
+      - name: Upload test results
+        if: always()
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
+        with:
+          name: test-results-openai
+          path: ./python/pytest.xml
+          if-no-files-found: ignore
 
   # Azure OpenAI integration tests
   python-tests-azure-openai:
@@ -204,7 +218,7 @@ jobs:
       run:
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
       - name: Set up python and install the project
         id: python-setup
         uses: ./.github/actions/python-setup
@@ -213,7 +227,7 @@ jobs:
           os: ${{ runner.os }}
       - name: Azure CLI Login
         if: github.event_name != 'pull_request'
-        uses: azure/login@v2
+        uses: azure/login@a457da9ea143d694b1b9c7c869ebb04ebe844ef5 # v2
         with:
           client-id: ${{ secrets.AZURE_CLIENT_ID }}
           tenant-id: ${{ secrets.AZURE_TENANT_ID }}
@@ -237,13 +251,20 @@ jobs:
         working-directory: ./python
       - name: Surface failing tests
         if: always()
-        uses: pmeier/pytest-results-action@v0.7.2
+        uses: pmeier/pytest-results-action@20b595761ba9bf89e115e875f8bc863f913bc8ad # v0.7.2
         with:
           path: ./python/pytest.xml
           summary: true
           display-options: fEX
           fail-on-empty: false
           title: Azure OpenAI integration test results
+      - name: Upload test results
+        if: always()
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
+        with:
+          name: test-results-azure-openai
+          path: ./python/pytest.xml
+          if-no-files-found: ignore
 
   # Misc integration tests (Anthropic, Ollama, MCP)
   python-tests-misc-integration:
@@ -261,17 +282,56 @@ jobs:
       ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
       ANTHROPIC_CHAT_MODEL: ${{ vars.ANTHROPIC_CHAT_MODEL_ID }}
       LOCAL_MCP_URL: ${{ vars.LOCAL_MCP__URL }}
+      OLLAMA_MODEL: qwen2.5:1.5b
+      OLLAMA_EMBEDDING_MODEL: nomic-embed-text
     defaults:
       run:
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
       - name: Set up python and install the project
         id: python-setup
         uses: ./.github/actions/python-setup
         with:
           python-version: ${{ env.UV_PYTHON }}
           os: ${{ runner.os }}
+      - name: Install Ollama
+        run: curl -fsSL https://ollama.com/install.sh | sh
+        working-directory: .
+      - name: Cache Ollama models
+        uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
+        with:
+          path: ~/.ollama/models
+          key: ollama-models-qwen2.5-1.5b-nomic-embed-text-v1
+      - name: Start Ollama and pull models
+        run: |
+          # Stop any Ollama instance auto-started by the install script
+          pkill ollama || true
+          sleep 2
+          ollama serve &
+          for i in $(seq 1 30); do
+            if curl -sf http://localhost:11434/api/tags > /dev/null 2>&1; then
+              break
+            fi
+            sleep 1
+          done
+          # Pull models with retry for transient 429 rate limits
+          for model in qwen2.5:1.5b nomic-embed-text; do
+            pulled=false
+            for attempt in 1 2 3; do
+              if ollama pull "$model"; then
+                pulled=true
+                break
+              fi
+              echo "Retry $attempt for $model (waiting 15s)..."
+              sleep 15
+            done
+            if [ "$pulled" != "true" ]; then
+              echo "ERROR: Failed to pull $model after 3 attempts"
+              exit 1
+            fi
+          done
+        working-directory: .
       - name: Start local MCP server
         id: local-mcp
         uses: ./.github/actions/setup-local-mcp-server
@@ -286,6 +346,7 @@ jobs:
           packages/hyperlight/tests
           packages/ollama/tests
           packages/core/tests/core/test_mcp.py
+          packages/hosting-mcp/tests
           -m integration
           -n logical --dist worksteal
           --timeout=120 --session-timeout=900 --timeout_method thread
@@ -314,13 +375,20 @@ jobs:
           kill -KILL -- "-$server_pid" 2>/dev/null || kill -KILL "$server_pid" 2>/dev/null || true
       - name: Surface failing tests
         if: always()
-        uses: pmeier/pytest-results-action@v0.7.2
+        uses: pmeier/pytest-results-action@20b595761ba9bf89e115e875f8bc863f913bc8ad # v0.7.2
         with:
           path: ./python/pytest.xml
           summary: true
           display-options: fEX
           fail-on-empty: false
           title: Misc integration test results
+      - name: Upload test results
+        if: always()
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
+        with:
+          name: test-results-misc
+          path: ./python/pytest.xml
+          if-no-files-found: ignore
 
   # Azure Functions + Durable Task integration tests
   python-tests-functions:
@@ -354,7 +422,7 @@ jobs:
       run:
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
       - name: Set up python and install the project
         id: python-setup
         uses: ./.github/actions/python-setup
@@ -363,7 +431,7 @@ jobs:
           os: ${{ runner.os }}
       - name: Azure CLI Login
         if: github.event_name != 'pull_request'
-        uses: azure/login@v2
+        uses: azure/login@a457da9ea143d694b1b9c7c869ebb04ebe844ef5 # v2
         with:
           client-id: ${{ secrets.AZURE_CLIENT_ID }}
           tenant-id: ${{ secrets.AZURE_TENANT_ID }}
@@ -379,19 +447,26 @@ jobs:
           -m integration
           -n logical --dist worksteal
           -x
-          --timeout=360 --session-timeout=900 --timeout_method thread
+          --timeout=480 --session-timeout=900 --timeout_method thread
           --retries 2 --retry-delay 5
           --junitxml=pytest.xml
         working-directory: ./python
       - name: Surface failing tests
         if: always()
-        uses: pmeier/pytest-results-action@v0.7.2
+        uses: pmeier/pytest-results-action@20b595761ba9bf89e115e875f8bc863f913bc8ad # v0.7.2
         with:
           path: ./python/pytest.xml
           summary: true
           display-options: fEX
           fail-on-empty: false
           title: Functions integration test results
+      - name: Upload test results
+        if: always()
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
+        with:
+          name: test-results-functions
+          path: ./python/pytest.xml
+          if-no-files-found: ignore
 
   python-tests-foundry:
     name: Python Integration Tests - Foundry
@@ -409,12 +484,16 @@ jobs:
       FOUNDRY_MODEL: ${{ vars.FOUNDRY_MODEL }}
       FOUNDRY_AGENT_NAME: ${{ vars.FOUNDRY_AGENT_NAME }}
       FOUNDRY_AGENT_VERSION: ${{ vars.FOUNDRY_AGENT_VERSION }}
+      FOUNDRY_MODELS_ENDPOINT: ${{ vars.FOUNDRY_MODELS_ENDPOINT || '' }}
+      FOUNDRY_MODELS_API_KEY: ${{ secrets.FOUNDRY_MODELS_API_KEY || '' }}
+      FOUNDRY_EMBEDDING_MODEL: ${{ vars.FOUNDRY_EMBEDDING_MODEL || '' }}
+      FOUNDRY_IMAGE_EMBEDDING_MODEL: ${{ vars.FOUNDRY_IMAGE_EMBEDDING_MODEL || '' }}
       LOCAL_MCP_URL: ${{ vars.LOCAL_MCP__URL }}
     defaults:
       run:
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
       - name: Set up python and install the project
         id: python-setup
         uses: ./.github/actions/python-setup
@@ -423,7 +502,7 @@ jobs:
           os: ${{ runner.os }}
       - name: Azure CLI Login
         if: github.event_name != 'pull_request'
-        uses: azure/login@v2
+        uses: azure/login@a457da9ea143d694b1b9c7c869ebb04ebe844ef5 # v2
         with:
           client-id: ${{ secrets.AZURE_CLIENT_ID }}
           tenant-id: ${{ secrets.AZURE_TENANT_ID }}
@@ -441,13 +520,81 @@ jobs:
         working-directory: ./python
       - name: Surface failing tests
         if: always()
-        uses: pmeier/pytest-results-action@v0.7.2
+        uses: pmeier/pytest-results-action@20b595761ba9bf89e115e875f8bc863f913bc8ad # v0.7.2
         with:
           path: ./python/pytest.xml
           summary: true
           display-options: fEX
           fail-on-empty: false
           title: Test results
+      - name: Upload test results
+        if: always()
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
+        with:
+          name: test-results-foundry
+          path: ./python/pytest.xml
+          if-no-files-found: ignore
+
+  # Foundry Hosting integration tests
+  python-tests-foundry-hosting:
+    name: Python Tests - Foundry Hosting Integration
+    needs: paths-filter
+    if: >
+      github.event_name != 'pull_request' &&
+      needs.paths-filter.outputs.pythonChanges == 'true' &&
+      (github.event_name != 'merge_group' ||
+       needs.paths-filter.outputs.foundryHostingChanged == 'true' ||
+       needs.paths-filter.outputs.coreChanged == 'true')
+    runs-on: ubuntu-latest
+    environment: integration
+    env:
+      FOUNDRY_PROJECT_ENDPOINT: ${{ vars.FOUNDRY_PROJECT_ENDPOINT }}
+      FOUNDRY_MODEL: ${{ vars.FOUNDRY_MODEL }}
+    defaults:
+      run:
+        working-directory: python
+    steps:
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
+      - name: Set up python and install the project
+        id: python-setup
+        uses: ./.github/actions/python-setup
+        with:
+          python-version: ${{ env.UV_PYTHON }}
+          os: ${{ runner.os }}
+      - name: Azure CLI Login
+        if: github.event_name != 'pull_request'
+        uses: azure/login@a457da9ea143d694b1b9c7c869ebb04ebe844ef5 # v2
+        with:
+          client-id: ${{ secrets.AZURE_CLIENT_ID }}
+          tenant-id: ${{ secrets.AZURE_TENANT_ID }}
+          subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
+      - name: Test with pytest (Foundry Hosting integration)
+        timeout-minutes: 15
+        run: >
+          uv run pytest --import-mode=importlib
+          packages/foundry_hosting/tests
+          -m integration
+          -n logical --dist worksteal
+          --timeout=120 --session-timeout=900 --timeout_method thread
+          --retries 2 --retry-delay 5
+          --junitxml=pytest.xml
+        working-directory: ./python
+      - name: Surface failing tests
+        if: always()
+        uses: pmeier/pytest-results-action@20b595761ba9bf89e115e875f8bc863f913bc8ad # v0.7.2
+        with:
+          path: ./python/pytest.xml
+          summary: true
+          display-options: fEX
+          fail-on-empty: false
+          title: Foundry Hosting integration test results
+      - name: Upload test results
+        if: always()
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
+        with:
+          name: test-results-foundry-hosting
+          path: ./python/pytest.xml
+          if-no-files-found: ignore
 
   # TODO: Add python-tests-lab
 
@@ -478,7 +625,7 @@ jobs:
       run:
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
       - name: Set up python and install the project
         id: python-setup
         uses: ./.github/actions/python-setup
@@ -497,17 +644,144 @@ jobs:
           echo "Cosmos DB emulator did not become ready in time." >&2
           exit 1
       - name: Test with pytest (Cosmos integration)
-        run: uv run --directory packages/azure-cosmos poe integration-tests -n logical --dist worksteal --timeout=120 --session-timeout=900 --timeout_method thread --retries 2 --retry-delay 5 --junitxml=pytest.xml
+        run: uv run --directory packages/azure-cosmos poe integration-tests -n logical --dist worksteal --timeout=120 --session-timeout=900 --timeout_method thread --retries 2 --retry-delay 5 --junitxml=${{ github.workspace }}/python/pytest.xml
         working-directory: ./python
       - name: Surface failing tests
         if: always()
-        uses: pmeier/pytest-results-action@v0.7.2
+        uses: pmeier/pytest-results-action@20b595761ba9bf89e115e875f8bc863f913bc8ad # v0.7.2
         with:
           path: ./python/pytest.xml
           summary: true
           display-options: fEX
           fail-on-empty: false
           title: Cosmos integration test results
+      - name: Upload test results
+        if: always()
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
+        with:
+          name: test-results-cosmos
+          path: ./python/pytest.xml
+          if-no-files-found: ignore
+
+  # GitHub Copilot integration tests
+  python-tests-github-copilot:
+    name: Python Tests - GitHub Copilot Integration
+    needs: paths-filter
+    if: >
+      github.event_name != 'pull_request' &&
+      needs.paths-filter.outputs.pythonChanges == 'true' &&
+      (github.event_name != 'merge_group' ||
+       needs.paths-filter.outputs.githubCopilotChanged == 'true' ||
+       needs.paths-filter.outputs.coreChanged == 'true')
+    runs-on: ubuntu-latest
+    environment: integration
+    permissions:
+      copilot-requests: write
+      contents: read
+    timeout-minutes: 60
+    env:
+      COPILOT_GITHUB_TOKEN: ${{ github.token }}
+      GITHUB_COPILOT_TIMEOUT: "120"
+    defaults:
+      run:
+        working-directory: python
+    steps:
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
+      - name: Set up python and install the project
+        id: python-setup
+        uses: ./.github/actions/python-setup
+        with:
+          python-version: ${{ env.UV_PYTHON }}
+          os: ${{ runner.os }}
+      - name: Test with pytest (GitHub Copilot integration)
+        run: >
+          uv run pytest --import-mode=importlib
+          packages/github_copilot/tests
+          -m integration
+          --timeout=120 --session-timeout=900 --timeout_method thread
+          --retries 2 --retry-delay 5
+          --junitxml=pytest.xml
+      - name: Surface failing tests
+        if: always()
+        uses: pmeier/pytest-results-action@20b595761ba9bf89e115e875f8bc863f913bc8ad # v0.7.2
+        with:
+          path: ./python/pytest.xml
+          summary: true
+          display-options: fEX
+          fail-on-empty: false
+          title: GitHub Copilot integration test results
+      - name: Upload test results
+        if: always()
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
+        with:
+          name: test-results-github-copilot
+          path: ./python/pytest.xml
+          if-no-files-found: ignore
+
+  # Integration test trend report (aggregates per-job JUnit XML results)
+  python-integration-test-report:
+    name: Integration Test Report
+    if: >
+      always() &&
+      (contains(join(needs.*.result, ','), 'success') ||
+       contains(join(needs.*.result, ','), 'failure'))
+    needs:
+      [
+        python-tests-openai,
+        python-tests-azure-openai,
+        python-tests-misc-integration,
+        python-tests-functions,
+        python-tests-foundry,
+        python-tests-foundry-hosting,
+        python-tests-cosmos,
+        python-tests-github-copilot,
+      ]
+    runs-on: ubuntu-latest
+    defaults:
+      run:
+        working-directory: python
+    steps:
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
+      - name: Set up python and install the project
+        uses: ./.github/actions/python-setup
+        with:
+          python-version: ${{ env.UV_PYTHON }}
+          os: ${{ runner.os }}
+      - name: Download all test results from current run
+        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
+        with:
+          pattern: test-results-*
+          path: test-results/
+      - name: Restore report history cache
+        uses: actions/cache/restore@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
+        with:
+          path: python/integration-report-history.json
+          key: integration-report-history-merge-${{ github.run_id }}
+          restore-keys: |
+            integration-report-history-merge-
+      - name: Generate trend report
+        run: >
+          uv run python scripts/integration_test_report/aggregate.py
+          ../test-results/
+          integration-report-history.json
+          integration-test-report.md
+      - name: Post to Job Summary
+        if: always()
+        run: cat integration-test-report.md >> $GITHUB_STEP_SUMMARY
+      - name: Save report history cache
+        if: always()
+        uses: actions/cache/save@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
+        with:
+          path: python/integration-report-history.json
+          key: integration-report-history-merge-${{ github.run_id }}
+      - name: Upload unified trend report
+        if: always()
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
+        with:
+          name: integration-test-report
+          path: |
+            python/integration-test-report.md
+            python/integration-report-history.json
 
   python-integration-tests-check:
     if: always()
@@ -520,19 +794,21 @@ jobs:
         python-tests-misc-integration,
         python-tests-functions,
         python-tests-foundry,
+        python-tests-foundry-hosting,
         python-tests-cosmos,
+        python-tests-github-copilot,
       ]
     steps:
       - name: Fail workflow if tests failed
         id: check_tests_failed
         if: contains(join(needs.*.result, ','), 'failure')
-        uses: actions/github-script@v8
+        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
         with:
           script: core.setFailed('Integration Tests Failed!')
 
       - name: Fail workflow if tests cancelled
         id: check_tests_cancelled
         if: contains(join(needs.*.result, ','), 'cancelled')
-        uses: actions/github-script@v8
+        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
         with:
           script: core.setFailed('Integration Tests Cancelled!')

.github/workflows/python-release.yml

@@ -23,7 +23,7 @@ jobs:
       run:
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
       - name: Set up python and install the project
         id: python-setup
         uses: ./.github/actions/python-setup
@@ -56,7 +56,7 @@ jobs:
       - name: Build the package
         run: uv run poe --directory packages/${{ env.PACKAGE }} build
       - name: Release
-        uses: softprops/action-gh-release@v2
+        uses: softprops/action-gh-release@718ea10b132b3b2eba29c1007bb80653f286566b # v3.0.1
         with:
           files: |
             python/dist/*

.github/workflows/python-sample-validation.yml

@@ -8,9 +8,6 @@ on:
 env:
   # Configure a constant location for the uv cache
   UV_CACHE_DIR: /tmp/.uv-cache
-  # GitHub Copilot configuration
-  GITHUB_COPILOT_MODEL: claude-opus-4.6
-  COPILOT_GITHUB_TOKEN: ${{ secrets.COPILOT_GITHUB_TOKEN }}
 
 permissions:
   contents: read
@@ -29,7 +26,7 @@ jobs:
       run:
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
 
       - name: Setup environment
         uses: ./.github/actions/sample-validation-setup
@@ -49,7 +46,7 @@ jobs:
           cd scripts && uv run python -m sample_validation --subdir 01-get-started --save-report --report-name 01-get-started
 
       - name: Upload validation report
-        uses: actions/upload-artifact@v7
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
         if: always()
         with:
           name: validation-report-01-get-started
@@ -82,7 +79,7 @@ jobs:
       run:
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
 
       - name: Setup environment
         uses: ./.github/actions/sample-validation-setup
@@ -111,7 +108,7 @@ jobs:
           cd scripts && uv run python -m sample_validation --subdir 02-agents --exclude providers --save-report --report-name 02-agents
 
       - name: Upload validation report
-        uses: actions/upload-artifact@v7
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
         if: always()
         with:
           name: validation-report-02-agents
@@ -130,7 +127,7 @@ jobs:
       run:
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
 
       - name: Setup environment
         uses: ./.github/actions/sample-validation-setup
@@ -152,7 +149,7 @@ jobs:
           cd scripts && uv run python -m sample_validation --subdir 02-agents/providers/openai --save-report --report-name 02-agents-openai
 
       - name: Upload validation report
-        uses: actions/upload-artifact@v7
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
         if: always()
         with:
           name: validation-report-02-agents-openai
@@ -170,7 +167,7 @@ jobs:
       run:
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
 
       - name: Setup environment
         uses: ./.github/actions/sample-validation-setup
@@ -191,7 +188,7 @@ jobs:
           cd scripts && uv run python -m sample_validation --subdir 02-agents/providers/azure --save-report --report-name 02-agents-azure
 
       - name: Upload validation report
-        uses: actions/upload-artifact@v7
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
         if: always()
         with:
           name: validation-report-02-agents-azure
@@ -208,7 +205,7 @@ jobs:
       run:
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
 
       - name: Setup environment
         uses: ./.github/actions/sample-validation-setup
@@ -228,7 +225,7 @@ jobs:
           cd scripts && uv run python -m sample_validation --subdir 02-agents/providers/anthropic --save-report --report-name 02-agents-anthropic
 
       - name: Upload validation report
-        uses: actions/upload-artifact@v7
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
         if: always()
         with:
           name: validation-report-02-agents-anthropic
@@ -238,11 +235,18 @@ jobs:
     name: Validate 02-agents/providers/github_copilot
     runs-on: ubuntu-latest
     environment: integration
+    permissions:
+      copilot-requests: write
+      contents: read
+      id-token: write
+    env:
+      COPILOT_GITHUB_TOKEN: ${{ github.token }}
+      GITHUB_COPILOT_MODEL: claude-opus-4.6
     defaults:
       run:
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
 
       - name: Setup environment
         uses: ./.github/actions/sample-validation-setup
@@ -257,7 +261,7 @@ jobs:
           cd scripts && uv run python -m sample_validation --subdir 02-agents/providers/github_copilot --save-report --report-name 02-agents-github-copilot
 
       - name: Upload validation report
-        uses: actions/upload-artifact@v7
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
         if: always()
         with:
           name: validation-report-02-agents-github-copilot
@@ -274,7 +278,7 @@ jobs:
       run:
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
 
       - name: Setup environment
         uses: ./.github/actions/sample-validation-setup
@@ -289,7 +293,7 @@ jobs:
           cd scripts && uv run python -m sample_validation --subdir 02-agents/providers/amazon --save-report --report-name 02-agents-amazon
 
       - name: Upload validation report
-        uses: actions/upload-artifact@v7
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
         if: always()
         with:
           name: validation-report-02-agents-amazon
@@ -306,7 +310,7 @@ jobs:
       run:
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
 
       - name: Setup environment
         uses: ./.github/actions/sample-validation-setup
@@ -321,7 +325,7 @@ jobs:
           cd scripts && uv run python -m sample_validation --subdir 02-agents/providers/ollama --save-report --report-name 02-agents-ollama
 
       - name: Upload validation report
-        uses: actions/upload-artifact@v7
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
         if: always()
         with:
           name: validation-report-02-agents-ollama
@@ -341,7 +345,7 @@ jobs:
       run:
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
 
       - name: Setup environment
         uses: ./.github/actions/sample-validation-setup
@@ -363,7 +367,7 @@ jobs:
           cd scripts && uv run python -m sample_validation --subdir 02-agents/providers/foundry --save-report --report-name 02-agents-foundry
 
       - name: Upload validation report
-        uses: actions/upload-artifact@v7
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
         if: always()
         with:
           name: validation-report-02-agents-foundry
@@ -383,7 +387,7 @@ jobs:
       run:
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
 
       - name: Setup environment
         uses: ./.github/actions/sample-validation-setup
@@ -405,7 +409,7 @@ jobs:
           cd scripts && uv run python -m sample_validation --subdir 02-agents/providers/copilotstudio --save-report --report-name 02-agents-copilotstudio
 
       - name: Upload validation report
-        uses: actions/upload-artifact@v7
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
         if: always()
         with:
           name: validation-report-02-agents-copilotstudio
@@ -419,7 +423,7 @@ jobs:
       run:
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
 
       - name: Setup environment
         uses: ./.github/actions/sample-validation-setup
@@ -434,7 +438,7 @@ jobs:
           cd scripts && uv run python -m sample_validation --subdir 02-agents/providers/custom --save-report --report-name 02-agents-custom
 
       - name: Upload validation report
-        uses: actions/upload-artifact@v7
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
         if: always()
         with:
           name: validation-report-02-agents-custom
@@ -451,7 +455,7 @@ jobs:
       run:
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
 
       - name: Setup environment
         uses: ./.github/actions/sample-validation-setup
@@ -471,7 +475,7 @@ jobs:
           cd scripts && uv run python -m sample_validation --subdir 03-workflows --save-report --report-name 03-workflows
 
       - name: Upload validation report
-        uses: actions/upload-artifact@v7
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
         if: always()
         with:
           name: validation-report-03-workflows
@@ -491,7 +495,7 @@ jobs:
       run:
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
 
       - name: Setup environment
         uses: ./.github/actions/sample-validation-setup
@@ -506,7 +510,7 @@ jobs:
           cd scripts && uv run python -m sample_validation --subdir 04-hosting --save-report --report-name 04-hosting
 
       - name: Upload validation report
-        uses: actions/upload-artifact@v7
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
         if: always()
         with:
           name: validation-report-04-hosting
@@ -534,7 +538,7 @@ jobs:
       run:
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
 
       - name: Setup environment
         uses: ./.github/actions/sample-validation-setup
@@ -549,7 +553,7 @@ jobs:
           cd scripts && uv run python -m sample_validation --subdir 05-end-to-end --save-report --report-name 05-end-to-end
 
       - name: Upload validation report
-        uses: actions/upload-artifact@v7
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
         if: always()
         with:
           name: validation-report-05-end-to-end
@@ -574,7 +578,7 @@ jobs:
       run:
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
 
       - name: Setup environment
         uses: ./.github/actions/sample-validation-setup
@@ -599,7 +603,7 @@ jobs:
           cd scripts && uv run python -m sample_validation --subdir autogen-migration --save-report --report-name autogen-migration
 
       - name: Upload validation report
-        uses: actions/upload-artifact@v7
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
         if: always()
         with:
           name: validation-report-autogen-migration
@@ -633,7 +637,7 @@ jobs:
       run:
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
 
       - name: Setup environment
         uses: ./.github/actions/sample-validation-setup
@@ -662,7 +666,7 @@ jobs:
           cd scripts && uv run python -m sample_validation --subdir semantic-kernel-migration --save-report --report-name semantic-kernel-migration
 
       - name: Upload validation report
-        uses: actions/upload-artifact@v7
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
         if: always()
         with:
           name: validation-report-semantic-kernel-migration
@@ -690,10 +694,10 @@ jobs:
       - validate-autogen-migration
       - validate-semantic-kernel-migration
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
 
       - name: Download all validation reports
-        uses: actions/download-artifact@v7
+        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
         with:
           pattern: validation-report-*
           path: reports/
@@ -701,7 +705,7 @@ jobs:
 
       - name: Restore validation history
         id: cache-restore
-        uses: actions/cache/restore@v4
+        uses: actions/cache/restore@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
         with:
           path: validation-history/
           key: validation-history-${{ github.run_id }}
@@ -719,13 +723,13 @@ jobs:
         run: cat trend-report.md >> "$GITHUB_STEP_SUMMARY"
 
       - name: Save validation history
-        uses: actions/cache/save@v4
+        uses: actions/cache/save@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
         with:
           path: validation-history/
           key: validation-history-${{ github.run_id }}
 
       - name: Upload trend report
-        uses: actions/upload-artifact@v7
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
         if: always()
         with:
           name: validation-trend-report

.github/workflows/python-test-coverage-report.yml

@@ -8,6 +8,7 @@ on:
 
 permissions:
   contents: read
+  actions: read
   pull-requests: write
 
 jobs:
@@ -19,36 +20,46 @@ jobs:
       run:
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
       - name: Download coverage report
-        uses: actions/download-artifact@v8
+        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8
         with:
-          github-token: ${{ secrets.GH_ACTIONS_PR_WRITE }}
+          github-token: ${{ github.token }}
           run-id: ${{ github.event.workflow_run.id }}
           path: ./python
           merge-multiple: true
       - name: Display structure of downloaded files
         run: ls
-      - name: Read and set PR number
-        # Need to read the PR number from the file saved in the previous workflow
-        # because the workflow_run event does not have access to the PR number
-        # The PR number is needed to post the comment on the PR
+      - name: Read and validate PR number
+        # Keep the artifact handoff aligned with the workflow run that produced it.
+        env:
+          GH_TOKEN: ${{ github.token }}
+          REPO: ${{ github.repository }}
+          RUN_HEAD_SHA: ${{ github.event.workflow_run.head_sha }}
         run: |
           if [ ! -s pr_number ]; then
             echo "PR number file 'pr_number' is missing or empty"
             exit 1
           fi
-          PR_NUMBER=$(head -1 pr_number | tr -dc '0-9')
-          if [ -z "$PR_NUMBER" ]; then
-            echo "PR number file 'pr_number' does not contain a valid PR number"
+
+          ARTIFACT_PR_NUMBER=$(cat pr_number)
+          if ! [[ "$ARTIFACT_PR_NUMBER" =~ ^[0-9]+$ ]]; then
+            echo "::error::PR number file contains invalid content"
             exit 1
           fi
-          echo "PR_NUMBER=$PR_NUMBER" >> "$GITHUB_ENV"
+
+          PR_HEAD_SHA=$(gh pr view "$ARTIFACT_PR_NUMBER" --repo "$REPO" --json headRefOid --jq '.headRefOid')
+          if [ "$PR_HEAD_SHA" != "$RUN_HEAD_SHA" ]; then
+            echo "::error::PR head SHA does not match the triggering workflow run"
+            exit 1
+          fi
+
+          echo "PR_NUMBER=$ARTIFACT_PR_NUMBER" >> "$GITHUB_ENV"
       - name: Pytest coverage comment
         id: coverageComment
-        uses: MishaKav/pytest-coverage-comment@v1.6.0
+        uses: MishaKav/pytest-coverage-comment@dd5b80bde6d16941f336518e92929e89069d8451 # v1.7.2
         with:
-          github-token: ${{ secrets.GH_ACTIONS_PR_WRITE }}
+          github-token: ${{ github.token }}
           issue-number: ${{ env.PR_NUMBER }}
           pytest-xml-coverage-path: python/python-coverage.xml
           title: "Python Test Coverage Report"

.github/workflows/python-test-coverage.yml

@@ -6,6 +6,9 @@ on:
     paths:
       - "python/packages/**"
       - "python/tests/unit/**"
+      - "python/scripts/workspace_poe_tasks.py"
+      - ".github/scripts/python_check_coverage.py"
+      - ".github/workflows/python-test-coverage.yml"
 env:
   # Configure a constant location for the uv cache
   UV_CACHE_DIR: /tmp/.uv-cache
@@ -22,7 +25,7 @@ jobs:
     env:
       UV_PYTHON: "3.11"
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
       # Save the PR number to a file since the workflow_run event
       # in the coverage report workflow does not have access to it
       - name: Save PR number
@@ -37,12 +40,12 @@ jobs:
         env:
           # Configure a constant location for the uv cache
           UV_CACHE_DIR: /tmp/.uv-cache
-      - name: Run all tests with coverage report
+      - name: Run aggregate tests with coverage report
         run: uv run poe test -A -C --cov-report=xml:python-coverage.xml -q --junitxml=pytest.xml
       - name: Check coverage threshold
-        run: python ${{ github.workspace }}/.github/workflows/python-check-coverage.py python-coverage.xml ${{ env.COVERAGE_THRESHOLD }}
+        run: python ${{ github.workspace }}/.github/scripts/python_check_coverage.py python-coverage.xml ${{ env.COVERAGE_THRESHOLD }}
       - name: Upload coverage report
-        uses: actions/upload-artifact@v7
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
         with:
           path: |
             python/python-coverage.xml

.github/workflows/python-tests.yml

@@ -5,6 +5,10 @@ on:
     branches: ["main", "feature*"]
     paths:
       - "python/**"
+      - "!python/AGENTS.md"
+      - "!python/**/AGENTS.md"
+      - "!python/.github/skills/*"
+      - "!python/.github/skills/**"
 env:
   # Configure a constant location for the uv cache
   UV_CACHE_DIR: /tmp/.uv-cache
@@ -27,14 +31,14 @@ jobs:
       run:
         working-directory: python
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
       - name: Set up python and install the project
         id: python-setup
         uses: ./.github/actions/python-setup
         with:
           python-version: ${{ matrix.python-version }}
           os: ${{ runner.os }}
-          exclude-packages: ${{ matrix.python-version == '3.10' && 'agent-framework-github-copilot' || '' }}
+          exclude-packages: ${{ matrix.python-version == '3.10' && 'agent-framework-github-copilot agent-framework-azure-cosmos-memory' || '' }}
         env:
           # Configure a constant location for the uv cache
           UV_CACHE_DIR: /tmp/.uv-cache
@@ -46,7 +50,7 @@ jobs:
       # Surface failing tests
       - name: Surface failing tests
         if: always()
-        uses: pmeier/pytest-results-action@v0.7.2
+        uses: pmeier/pytest-results-action@20b595761ba9bf89e115e875f8bc863f913bc8ad # v0.7.2
         with:
           path: ./python/pytest.xml
           summary: true

.github/workflows/stale-issue-pr-ping.yml

@@ -26,14 +26,31 @@ jobs:
   ping_stale:
     name: "Ping stale issues and PRs"
     runs-on: ubuntu-latest
+    environment: github-app-auth
     permissions:
       contents: read
+      id-token: write
       issues: write
       pull-requests: write
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
 
-      - uses: actions/setup-python@v5
+      - name: Get GitHub automation token
+        id: github-auth
+        uses: ./.github/actions/github-app-token
+        with:
+          mode: ${{ vars.GH_APP_AUTH_MODE }}
+          azure-client-id: ${{ secrets.GH_APP_AZURE_CLIENT_ID }}
+          azure-tenant-id: ${{ secrets.GH_APP_AZURE_TENANT_ID }}
+          azure-subscription-id: ${{ secrets.GH_APP_AZURE_SUBSCRIPTION_ID }}
+          key-vault-name: ${{ secrets.GH_APP_KEY_VAULT_NAME }}
+          key-name: ${{ secrets.GH_APP_KEY_NAME }}
+          github-app-client-id: ${{ secrets.GH_APP_CLIENT_ID }}
+          github-app-installation-id: ${{ secrets.GH_APP_INSTALLATION_ID }}
+          repository: ${{ github.repository }}
+          fallback-token: ${{ secrets.GH_ACTIONS_PR_WRITE }}
+
+      - uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5
         with:
           python-version: '3.13'
 
@@ -43,7 +60,7 @@ jobs:
       - name: Run stale issue/PR ping
         run: python .github/scripts/stale_issue_pr_ping.py
         env:
-          GITHUB_TOKEN: ${{ secrets.GH_ACTIONS_PR_WRITE }}
+          GITHUB_TOKEN: ${{ steps.github-auth.outputs.token }}
           TEAM_SLUG: ${{ secrets.DEVELOPER_TEAM }}
           DAYS_THRESHOLD: ${{ github.event.inputs.days_threshold || '4' }}
           DRY_RUN: ${{ github.event.inputs.dry_run || 'false' }}

.gitignore

@@ -136,6 +136,10 @@ celerybeat.pid
 .venv
 env/
 venv/
+
+# Foundry agent CLI (contains secrets, auto-generated)
+.foundry-agent.json
+.foundry-agent-build.log
 ENV/
 env.bak/
 venv.bak/
@@ -202,6 +206,7 @@ temp*/
 .temp/
 
 # AI
+**/.checkpoints/
 .claude/
 .omc/
 .omx/
@@ -209,6 +214,7 @@ WARP.md
 **/memory-bank/
 **/projectBrief.md
 **/tmpclaude*
+.kiro/
 # Dependency-bound validation reports
 python/scripts/dependency-*-results.json
 python/scripts/dependencies/dependency-*-results.json
@@ -238,3 +244,10 @@ python/dotnet-ref
 # Generated filtered solution files (created by eng/scripts/New-FilteredSolution.ps1)
 dotnet/filtered-*.slnx
 **/*.lscache
+
+# Local tool state
+.omc/
+.omx/
+
+**/issues/
+.test_*

README.md

@@ -6,8 +6,12 @@
 [![MS Learn Documentation](https://img.shields.io/badge/MS%20Learn-Documentation-blue)](https://learn.microsoft.com/en-us/agent-framework/)
 [![PyPI](https://img.shields.io/pypi/v/agent-framework)](https://pypi.org/project/agent-framework/)
 [![NuGet](https://img.shields.io/nuget/v/Microsoft.Agents.AI)](https://www.nuget.org/profiles/MicrosoftAgentFramework/)
+[![GitHub stars](https://img.shields.io/github/stars/microsoft/agent-framework?style=social)](https://github.com/microsoft/agent-framework)
 
-Welcome to Microsoft's comprehensive multi-language framework for building, orchestrating, and deploying AI agents with support for both .NET and Python implementations. This framework provides everything from simple chat agents to complex multi-agent workflows with graph-based orchestration.
+
+Microsoft Agent Framework (MAF) is an open, multi-language framework for building **production-grade AI agents and multi-agent workflows** in **.NET and Python**.
+
+Microsoft Agent Framework is built for teams taking agents from prototype to production. It provides a consistent foundation for building, orchestrating, and operating agent systems across Python and .NET, while keeping architecture choices open as requirements evolve, and supports a broad ecosystem including Microsoft Foundry, Azure OpenAI, OpenAI, and the GitHub Copilot SDK, with samples and hosting patterns for both local development and cloud deployment.
 
 <p align="center">
   <a href="https://www.youtube.com/watch?v=AAgdMhftj8w" title="Watch the full Agent Framework introduction (30 min)">
@@ -21,10 +25,54 @@ Welcome to Microsoft's comprehensive multi-language framework for building, orch
   </a>
 </p>
 
-## 📋 Getting Started
+## Is this the right framework for you?
 
-### 📦 Installation
+MAF is a strong fit if you:
+- are building agents and workflows you expect to run in production,
+- need orchestration beyond a single prompt or stateless chat loop,
+- want graph-based patterns such as sequential, concurrent, handoff, and group collaboration,
+- care about durability, restartability, observability, governance, or human-in-the-loop control,
+- need provider flexibility so your architecture can evolve without major rewrites.
 
+## Key Features
+Explore new MAF capabilities and real implementation patterns on the [official blog](https://devblogs.microsoft.com/agent-framework/).
+
+- **Python and C#/.NET Support**: Full framework support for both Python and C#/.NET implementations with consistent APIs
+  - [Python packages](./python/packages/) | [.NET source](./dotnet/src/)
+- **Multiple Agent Provider Support**: Support for various LLM providers with more being added continuously
+  - [Python examples](./python/samples/02-agents/providers/) | [.NET examples](./dotnet/samples/02-agents/AgentProviders/)
+- **Middleware**: Flexible middleware system for request/response processing, exception handling, and custom pipelines
+  - [Python middleware](./python/samples/02-agents/middleware/) | [.NET middleware](./dotnet/samples/02-agents/Agents/Agent_Step11_Middleware/)
+- **Orchestration Patterns & Workflows**: Build multi-agent systems with graph-based workflows supporting sequential, concurrent, handoff, and group collaboration patterns; includes checkpointing, streaming, human-in-the-loop, and time-travel
+  - [Python workflows](./python/samples/03-workflows/) | [.NET workflows](./dotnet/samples/03-workflows/)
+- **Foundry Hosted Agents (new)**: Deploy and host your agents to Foundry-hosted infrastructure with just 2 additional lines of code
+  - [Python samples](./python/samples/04-hosting/foundry-hosted-agents/) | [.NET samples](./dotnet/samples/04-hosting/FoundryHostedAgents/)
+- **Observability**: Built-in OpenTelemetry integration for distributed tracing, monitoring, and debugging
+  - [Python observability](./python/samples/02-agents/observability/) | [.NET telemetry](./dotnet/samples/02-agents/AgentOpenTelemetry/)
+- **Declarative Agents**: Define agents using YAML for faster setup and versioning
+  - [Declarative agent samples](./declarative-agents/)
+- **Agent Skills**: Build domain-specific knowledge bases from multiple sources—files, inline code, class libraries—for agents to discover and use
+  - [Skills design](./docs/decisions/0021-agent-skills-design.md)
+- **AF Labs**: Experimental packages for cutting-edge features including benchmarking, reinforcement learning, and research initiatives
+  - [Labs directory](./python/packages/lab/)
+- **DevUI**: Interactive developer UI for agent development, testing, and debugging workflows
+  - [See the DevUI in action](https://www.youtube.com/watch?v=mOAaGY4WPvc)
+
+## Table of Contents
+
+- [Getting Started](#getting-started)
+  - [Installation](#installation)
+  - [Learning Resources](#learning-resources)
+  - [Quickstart](#quickstart)
+    - [Basic Agent - Python](#basic-agent---python)
+    - [Basic Agent - .NET](#basic-agent---net)
+- [More Examples & Samples](#more-examples--samples)
+- [Community & Feedback](#community--feedback)
+- [Troubleshooting](#troubleshooting)
+- [Contributor Resources](#contributor-resources)
+
+## Getting Started
+### Installation
 Python
 
 ```bash
@@ -37,9 +85,13 @@ pip install agent-framework
 
 ```bash
 dotnet add package Microsoft.Agents.AI
+# For Foundry integration (used in the .NET quickstart below):
+dotnet add package Microsoft.Agents.AI.Foundry
+dotnet add package Azure.AI.Projects
+dotnet add package Azure.Identity
 ```
 
-### 📚 Documentation
+### Learning Resources
 
 - **[Overview](https://learn.microsoft.com/agent-framework/overview/agent-framework-overview)** - High level overview of the framework
 - **[Quick Start](https://learn.microsoft.com/agent-framework/tutorials/quick-start)** - Get started with a simple agent
@@ -48,44 +100,9 @@ dotnet add package Microsoft.Agents.AI
 - **[Migration from Semantic Kernel](https://learn.microsoft.com/en-us/agent-framework/migration-guide/from-semantic-kernel)** - Guide to migrate from Semantic Kernel
 - **[Migration from AutoGen](https://learn.microsoft.com/en-us/agent-framework/migration-guide/from-autogen)** - Guide to migrate from AutoGen
 
-Still have questions? Join our [weekly office hours](./COMMUNITY.md#public-community-office-hours) or ask questions in our [Discord channel](https://discord.gg/b5zjErwbQM) to get help from the team and other users.
+### Quickstart
 
-### ✨ **Highlights**
-
-- **Graph-based Workflows**: Connect agents and deterministic functions using data flows with streaming, checkpointing, human-in-the-loop, and time-travel capabilities
-  - [Python workflows](./python/samples/03-workflows/) | [.NET workflows](./dotnet/samples/03-workflows/)
-- **AF Labs**: Experimental packages for cutting-edge features including benchmarking, reinforcement learning, and research initiatives
-  - [Labs directory](./python/packages/lab/)
-- **DevUI**: Interactive developer UI for agent development, testing, and debugging workflows
-  - [DevUI package](./python/packages/devui/)
-
-<p align="center">
-  <a href="https://www.youtube.com/watch?v=mOAaGY4WPvc">
-    <img src="https://img.youtube.com/vi/mOAaGY4WPvc/hqdefault.jpg" alt="See the DevUI in action" width="480">
-  </a>
-</p>
-<p align="center">
-  <a href="https://www.youtube.com/watch?v=mOAaGY4WPvc">
-    See the DevUI in action (1 min)
-  </a>
-</p>
-
-- **Python and C#/.NET Support**: Full framework support for both Python and C#/.NET implementations with consistent APIs
-  - [Python packages](./python/packages/) | [.NET source](./dotnet/src/)
-- **Observability**: Built-in OpenTelemetry integration for distributed tracing, monitoring, and debugging
-  - [Python observability](./python/samples/02-agents/observability/) | [.NET telemetry](./dotnet/samples/02-agents/AgentOpenTelemetry/)
-- **Multiple Agent Provider Support**: Support for various LLM providers with more being added continuously
-  - [Python examples](./python/samples/02-agents/providers/) | [.NET examples](./dotnet/samples/02-agents/AgentProviders/)
-- **Middleware**: Flexible middleware system for request/response processing, exception handling, and custom pipelines
-  - [Python middleware](./python/samples/02-agents/middleware/) | [.NET middleware](./dotnet/samples/02-agents/Agents/Agent_Step11_Middleware/)
-
-### 💬 **We want your feedback!**
-
-- For bugs, please file a [GitHub issue](https://github.com/microsoft/agent-framework/issues).
-
-## Quickstart
-
-### Basic Agent - Python
+#### Basic Agent - Python
 
 Create a simple Azure Responses Agent that writes a haiku about the Microsoft Agent Framework
 
@@ -109,7 +126,7 @@ async def main():
           # project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
           # model=os.environ["FOUNDRY_MODEL_DEPLOYMENT_NAME"],
       ),
-      name="HaikuBot",
+      name="HaikuAgent",
       instructions="You are an upbeat assistant that writes beautifully.",
     )
 
@@ -119,40 +136,24 @@ if __name__ == "__main__":
     asyncio.run(main())
 ```
 
-### Basic Agent - .NET
-Create a simple Agent, using Microsoft Foundry with token-based auth, that writes a haiku about the Microsoft Agent Framework
+#### Basic Agent - .NET
+Create a simple Agent, using Microsoft Foundry that writes a haiku about the Microsoft Agent Framework
 
 ```c#
-// dotnet add package Microsoft.Agents.AI.Foundry
-// Use `az login` to authenticate with Azure CLI
-using Azure.AI.Projects;
-using Azure.Identity;
-using System;
+// This sample shows how to create and run a basic agent with AIProjectClient.AsAIAgent(...).
+
 using Azure.AI.Projects;
 using Azure.Identity;
+using Microsoft.Agents.AI;
 
-var endpoint = Environment.GetEnvironmentVariable("AZURE_AI_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("AZURE_AI_PROJECT_ENDPOINT is not set.");
-var deploymentName = Environment.GetEnvironmentVariable("AZURE_AI_MODEL_DEPLOYMENT_NAME") ?? "gpt-5.4-mini";
+string endpoint = Environment.GetEnvironmentVariable("AZURE_AI_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("AZURE_AI_PROJECT_ENDPOINT is not set.");
+string deploymentName = Environment.GetEnvironmentVariable("AZURE_AI_MODEL_DEPLOYMENT_NAME") ?? "gpt-5.4-mini";
 
-var agent = new AIProjectClient(new Uri(endpoint), new DefaultAzureCredential())
-    .AsAIAgent(model: deploymentName, name: "HaikuBot", instructions: "You are an upbeat assistant that writes beautifully.");
-
-Console.WriteLine(await agent.RunAsync("Write a haiku about Microsoft Agent Framework."));
-```
-
-Create a simple Agent, using OpenAI Responses, that writes a haiku about the Microsoft Agent Framework
-
-```c#
-// dotnet add package Microsoft.Agents.AI.OpenAI
-using System;
-using OpenAI;
-using OpenAI.Responses;
-
-// Replace the <apikey> with your OpenAI API key.
-var agent = new OpenAIClient("<apikey>")
-    .GetResponsesClient()
-    .AsAIAgent(model: "gpt-5.4-mini", name: "HaikuBot", instructions: "You are an upbeat assistant that writes beautifully.");
+AIAgent agent =
+    new AIProjectClient(new Uri(endpoint), new DefaultAzureCredential())
+    .AsAIAgent(model: deploymentName, instructions: "You are an upbeat assistant that writes beautifully.", name: "HaikuAgent");
 
+// Once you have the agent, you can invoke it like any other AIAgent.
 Console.WriteLine(await agent.RunAsync("Write a haiku about Microsoft Agent Framework."));
 ```
 
@@ -175,6 +176,12 @@ Console.WriteLine(await agent.RunAsync("Write a haiku about Microsoft Agent Fram
 - [Hosting](./dotnet/samples/04-hosting): A2A, Durable Agents, Durable Workflows
 - [End-to-End](./dotnet/samples/05-end-to-end): full applications and demos
 
+## Community & Feedback
+
+- **Found a bug?** File a [GitHub issue](https://github.com/microsoft/agent-framework/issues) to help us improve.
+- **Enjoying MAF?** [![GitHub stars](https://img.shields.io/badge/Star-us%20on%20GitHub-yellow)](https://github.com/microsoft/agent-framework) to show your support and help others discover the project.
+- **Have questions?** Join our [Discord](https://discord.gg/b5zjErwbQM) or visit [weekly office hours](./COMMUNITY.md#public-community-office-hours).
+
 ## Troubleshooting
 
 ### Authentication
@@ -187,16 +194,7 @@ Console.WriteLine(await agent.RunAsync("Write a haiku about Microsoft Agent Fram
 > **Tip:** `DefaultAzureCredential` is convenient for development but in production, consider using a specific credential (e.g., `ManagedIdentityCredential`) to avoid latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
 
 ### Environment Variables
-
-The samples typically read configuration from environment variables. Common required variables:
-
-| Variable | Used by | Purpose |
-|----------|---------|---------|
-| `AZURE_OPENAI_ENDPOINT` | Azure OpenAI samples | Your Azure OpenAI resource URL |
-| `AZURE_OPENAI_DEPLOYMENT_NAME` | Azure OpenAI samples | Model deployment name (e.g. `gpt-4o-mini`) |
-| `AZURE_AI_PROJECT_ENDPOINT` | Microsoft Foundry samples | Your Microsoft Foundry project endpoint |
-| `AZURE_AI_MODEL_DEPLOYMENT_NAME` | Microsoft Foundry samples | Model deployment name |
-| `OPENAI_API_KEY` | OpenAI (non-Azure) samples | Your OpenAI platform API key |
+For environment variable configuration specific to each sample, refer to the README in the sample directory ([Python samples](./python/samples/) | [.NET samples](./dotnet/samples/)).
 
 ## Contributor Resources
 

SUPPORT.md

@@ -1,17 +1,17 @@
-# Support
-
-## How to file issues and get help  
-
-This project uses GitHub Issues to track bugs and feature requests. Please search the existing 
-issues before filing new issues to avoid duplicates.  For new issues, file your bug or 
-feature request as a new Issue.
-
-For help and questions about using this project, please create a GitHub issue.
-
-AI Support team will support Microsoft Agent Framework issues for customers under a **Unified support agreement when the issue arises from usage of Azure AI services** (Foundry Models, Foundry Agents etc.) in conjunction with the SDK. Conversely, if customer has any other / non unified support agreement and/or Agent Framework SDK is used in a way **not involving an Azure service**, it is treated as a purely open-source tool – Microsoft’s support organization will not handle it, and users should use GitHub or forums for assistance
-
-For Copilot Studio SDK implementation issues, customers should use GitHub Issues for assistance, as outlined above. Conversely, for prerequisites managed within the Copilot Studio portal, customers can rely on the standard Microsoft Copilot Studio support channels.
-
-## Microsoft Support Policy  
-
-Support for this **PROJECT or PRODUCT** is limited to the resources listed above.
+# Support
+
+## How to file issues and get help  
+
+This project uses GitHub Issues to track bugs and feature requests. Please search the existing 
+issues before filing new issues to avoid duplicates.  For new issues, file your bug or 
+feature request as a new Issue.
+
+For help and questions about using this project, please create a GitHub issue.
+
+AI Support team will support Microsoft Agent Framework issues for customers under a **Unified support agreement when the issue arises from usage of Azure AI services** (Foundry Models, Foundry Agents etc.) in conjunction with the SDK. Conversely, if customer has any other / non unified support agreement and/or Agent Framework SDK is used in a way **not involving an Azure service**, it is treated as a purely open-source tool – Microsoft’s support organization will not handle it, and users should use GitHub or forums for assistance
+
+For Copilot Studio SDK implementation issues, customers should use GitHub Issues for assistance, as outlined above. Conversely, for prerequisites managed within the Copilot Studio portal, customers can rely on the standard Microsoft Copilot Studio support channels.
+
+## Microsoft Support Policy  
+
+Support for this **PROJECT or PRODUCT** is limited to the resources listed above.

TRANSPARENCY_FAQ.md

@@ -2,7 +2,7 @@
 
 **What is Microsoft Agent Framework?**
 
-Microsoft Agent Framework is a comprehensive multi-language (C#/.NET and Python) framework for building, orchestrating, and deploying AI agents and multi-agent workflows. The system takes user instructions and conversation inputs and produces intelligent responses through AI agents that can integrate with various LLM providers (OpenAI, Azure OpenAI, Azure AI Foundry). It provides both simple chat agents and complex multi-agent workflows with graph-based orchestration.
+Microsoft Agent Framework is a comprehensive multi-language (C#/.NET and Python) framework for building, orchestrating, and deploying AI agents and multi-agent workflows. The system takes user instructions and conversation inputs and produces intelligent responses through AI agents that can integrate with various LLM providers (OpenAI, Azure OpenAI, Microsoft Foundry). It provides both simple chat agents and complex multi-agent workflows with graph-based orchestration.
 
 **What can Microsoft Agent Framework do?**
 
@@ -12,7 +12,7 @@ The framework offers:
 - **Multi-Agent Orchestration**: Group chat, sequential, concurrent, and handoff patterns
 - **Graph-based Workflows**: Connect agents and deterministic functions using data flows with streaming, checkpointing, time-travel, and Human-in-the-loop
 - **Extensibility Framework**: Extend with native functions, A2A, Model Context Protocol (MCP)
-- **LLM Integration**: Support for OpenAI, Azure OpenAI, Azure AI Foundry, and other providers
+- **LLM Integration**: Support for OpenAI, Azure OpenAI, Microsoft Foundry, and other providers
 - **Runtime Support**: Both in-process and distributed agent execution
 
 **What is/are Microsoft Agent Framework's intended use(s)?**

declarative-agents/workflow-samples/MathChat.yaml

@@ -11,7 +11,7 @@ trigger:
   kind: OnConversationStart
   id: workflow_demo
   actions:
-
+ 
     - kind: InvokeAzureAgent
       id: question_student
       conversationId: =System.ConversationId

docs/assets/SVG/Microsoft Foundry Agent Framework - Color.svg

@@ -0,0 +1,55 @@
+<svg width="256" height="256" viewBox="0 0 256 256" fill="none" xmlns="http://www.w3.org/2000/svg">
+<rect width="256" height="256" transform="matrix(-1 0 0 1 256 0)" fill="white"/>
+<path d="M163.006 36.0262C155.129 31.4785 145.424 31.4759 137.533 36.0284L104.002 55.3877C107.838 53.2763 112.07 52.2274 116.296 52.2248C120.633 52.2231 124.976 53.3247 128.871 55.5411L174.091 81.6479C175.11 82.2362 175.738 83.3236 175.738 84.5004V151.263C175.738 152.716 177.313 153.621 178.568 152.895L196.967 142.28C204.845 137.732 209.704 129.326 209.704 120.221V77.7299C209.704 68.6342 204.855 60.227 196.967 55.6697L190.983 52.2141C190.65 52.0008 190.313 51.7921 189.969 51.5933L163.006 36.0262Z" fill="url(#paint0_linear_481_4810)"/>
+<path d="M163.006 36.0262C155.129 31.4785 145.424 31.4759 137.533 36.0284L104.002 55.3877C107.838 53.2763 112.07 52.2274 116.296 52.2248C120.633 52.2231 124.976 53.3247 128.871 55.5411L174.091 81.6479C175.11 82.2362 175.738 83.3236 175.738 84.5004V151.263C175.738 152.716 177.313 153.621 178.568 152.895L196.967 142.28C204.845 137.732 209.704 129.326 209.704 120.221V77.7299C209.704 68.6342 204.855 60.227 196.967 55.6697L190.983 52.2141C190.65 52.0008 190.313 51.7921 189.969 51.5933L163.006 36.0262Z" fill="url(#paint1_linear_481_4810)"/>
+<path d="M103.548 55.6397L103.557 55.6451L104.002 55.3877C103.851 55.471 103.698 55.5531 103.548 55.6397Z" fill="url(#paint2_linear_481_4810)"/>
+<path d="M103.548 55.6397L103.557 55.6451L104.002 55.3877C103.851 55.471 103.698 55.5531 103.548 55.6397Z" fill="url(#paint3_linear_481_4810)"/>
+<path d="M116.308 52.2209C111.903 52.2271 107.507 53.3498 103.561 55.6366C95.6702 60.1891 90.8239 68.6019 90.8231 77.6986L90.8223 167.846C90.8222 169.786 92.871 171.041 94.599 170.16L103.523 165.611C116.573 158.959 124.788 145.549 124.788 130.902V62.9894C124.778 58.6476 129.49 55.9209 133.25 58.0698L128.879 55.5453C124.976 53.3242 120.645 52.2192 116.308 52.2209Z" fill="url(#paint4_linear_481_4810)"/>
+<path d="M95.3068 221.682C103.184 226.23 112.889 226.232 120.78 221.68L154.311 202.32C150.475 204.432 146.243 205.481 142.018 205.483C137.68 205.485 133.337 204.383 129.442 202.167L84.2226 176.06C83.2035 175.472 82.5757 174.384 82.5757 173.208L82.5757 106.445C82.5757 104.992 81 104.087 79.7451 104.813L61.3465 115.428C53.4682 119.976 48.6091 128.382 48.6089 137.487L48.6089 179.978C48.6089 189.074 53.4585 197.481 61.3465 202.038L67.3303 205.494C67.6629 205.707 68.0002 205.916 68.3446 206.115L95.3068 221.682Z" fill="url(#paint5_linear_481_4810)"/>
+<path d="M95.3068 221.682C103.184 226.23 112.889 226.232 120.78 221.68L154.311 202.32C150.475 204.432 146.243 205.481 142.018 205.483C137.68 205.485 133.337 204.383 129.442 202.167L84.2226 176.06C83.2035 175.472 82.5757 174.384 82.5757 173.208L82.5757 106.445C82.5757 104.992 81 104.087 79.7451 104.813L61.3465 115.428C53.4682 119.976 48.6091 128.382 48.6089 137.487L48.6089 179.978C48.6089 189.074 53.4585 197.481 61.3465 202.038L67.3303 205.494C67.6629 205.707 68.0002 205.916 68.3446 206.115L95.3068 221.682Z" fill="url(#paint6_linear_481_4810)"/>
+<path d="M154.765 202.068L154.756 202.063L154.311 202.32C154.463 202.237 154.615 202.155 154.765 202.068Z" fill="url(#paint7_linear_481_4810)"/>
+<path d="M154.765 202.068L154.756 202.063L154.311 202.32C154.463 202.237 154.615 202.155 154.765 202.068Z" fill="url(#paint8_linear_481_4810)"/>
+<path d="M142.003 205.487C146.408 205.481 150.805 204.358 154.751 202.071C162.641 197.519 167.488 189.106 167.488 180.009L167.489 89.8618C167.489 87.9222 165.44 86.667 163.712 87.5479L154.788 92.0972C141.739 98.7494 133.523 112.159 133.523 126.806L133.523 194.719C133.533 199.06 128.821 201.787 125.061 199.638L129.432 202.163C133.336 204.384 137.666 205.489 142.003 205.487Z" fill="url(#paint9_linear_481_4810)"/>
+<defs>
+<linearGradient id="paint0_linear_481_4810" x1="207.413" y1="61.882" x2="148.999" y2="163.067" gradientUnits="userSpaceOnUse">
+<stop stop-color="#9189F7"/>
+<stop offset="1" stop-color="#4135E9"/>
+</linearGradient>
+<linearGradient id="paint1_linear_481_4810" x1="188.235" y1="204.189" x2="264.21" y2="152.592" gradientUnits="userSpaceOnUse">
+<stop stop-color="#4F42FD"/>
+<stop offset="1" stop-color="#7274FF"/>
+</linearGradient>
+<linearGradient id="paint2_linear_481_4810" x1="207.413" y1="61.882" x2="148.999" y2="163.067" gradientUnits="userSpaceOnUse">
+<stop stop-color="#9189F7"/>
+<stop offset="1" stop-color="#4135E9"/>
+</linearGradient>
+<linearGradient id="paint3_linear_481_4810" x1="188.235" y1="204.189" x2="264.21" y2="152.592" gradientUnits="userSpaceOnUse">
+<stop stop-color="#4F42FD"/>
+<stop offset="1" stop-color="#7274FF"/>
+</linearGradient>
+<linearGradient id="paint4_linear_481_4810" x1="93.1761" y1="128.826" x2="66.2399" y2="104.746" gradientUnits="userSpaceOnUse">
+<stop offset="0.25" stop-color="#4F42FD"/>
+<stop offset="1" stop-color="#2C08AC"/>
+</linearGradient>
+<linearGradient id="paint5_linear_481_4810" x1="50.9004" y1="195.826" x2="109.315" y2="94.6412" gradientUnits="userSpaceOnUse">
+<stop stop-color="#9189F7"/>
+<stop offset="1" stop-color="#4135E9"/>
+</linearGradient>
+<linearGradient id="paint6_linear_481_4810" x1="70.0787" y1="53.5188" x2="-5.89657" y2="105.116" gradientUnits="userSpaceOnUse">
+<stop stop-color="#4F42FD"/>
+<stop offset="1" stop-color="#7274FF"/>
+</linearGradient>
+<linearGradient id="paint7_linear_481_4810" x1="50.9004" y1="195.826" x2="109.315" y2="94.6412" gradientUnits="userSpaceOnUse">
+<stop stop-color="#9189F7"/>
+<stop offset="1" stop-color="#4135E9"/>
+</linearGradient>
+<linearGradient id="paint8_linear_481_4810" x1="70.0787" y1="53.5188" x2="-5.89657" y2="105.116" gradientUnits="userSpaceOnUse">
+<stop stop-color="#4F42FD"/>
+<stop offset="1" stop-color="#7274FF"/>
+</linearGradient>
+<linearGradient id="paint9_linear_481_4810" x1="165.135" y1="128.882" x2="192.072" y2="152.962" gradientUnits="userSpaceOnUse">
+<stop offset="0.25" stop-color="#4F42FD"/>
+<stop offset="1" stop-color="#2C08AC"/>
+</linearGradient>
+</defs>
+</svg>

docs/assets/SVG/Microsoft Foundry Agent Framework - Fill (Black).svg

@@ -0,0 +1,5 @@
+<svg width="256" height="256" viewBox="0 0 256 256" fill="none" xmlns="http://www.w3.org/2000/svg">
+<rect width="256" height="256" transform="matrix(-1 0 0 1 256 0)" fill="white"/>
+<path d="M167.489 89.8618C167.489 87.9224 165.441 86.667 163.713 87.5473L154.788 92.0971C141.739 98.7493 133.523 112.159 133.523 126.806V194.718C133.533 199.053 128.837 201.777 125.08 199.647L84.2227 176.06C83.2036 175.472 82.5762 174.384 82.5762 173.207V106.445C82.5759 104.992 80.9999 104.087 79.7451 104.813L61.3467 115.428C53.4685 119.976 48.6096 128.382 48.6094 137.487V179.978C48.6094 189.074 53.4588 197.481 61.3467 202.039L67.3301 205.494C67.6627 205.707 68.0004 205.916 68.3447 206.115L95.3066 221.682C103.184 226.23 112.889 226.232 120.779 221.679L154.312 202.32C154.271 202.342 154.23 202.362 154.189 202.384C154.283 202.333 154.375 202.281 154.468 202.229L154.312 202.32C154.463 202.237 154.615 202.154 154.765 202.068L154.762 202.065C162.646 197.511 167.487 189.102 167.488 180.009L167.489 89.8618Z" fill="black"/>
+<path d="M163.007 36.0259C155.13 31.4781 145.424 31.4763 137.533 36.0288L104.002 55.3882C104.029 55.3732 104.057 55.359 104.084 55.3442C104.02 55.3794 103.956 55.4159 103.893 55.4516L104.002 55.3882C103.851 55.4714 103.699 55.5536 103.549 55.6401L103.552 55.6411C95.6664 60.1948 90.8241 68.6053 90.8232 77.6987L90.8223 167.846C90.8223 169.786 92.8707 171.04 94.5986 170.16L103.523 165.611C116.573 158.959 124.788 145.549 124.788 130.902V62.9897C124.778 58.6479 129.49 55.9211 133.25 58.0698L174.091 81.6479C175.11 82.2363 175.737 83.3238 175.737 84.5005V151.263C175.738 152.716 177.314 153.621 178.568 152.895L196.967 142.28C204.845 137.732 209.704 129.326 209.704 120.221V77.73C209.704 68.6343 204.855 60.2267 196.967 55.6694L190.982 52.2143C190.65 52.0011 190.313 51.792 189.969 51.5932L163.007 36.0259Z" fill="black"/>
+</svg>

docs/assets/SVG/Microsoft Foundry Agent Framework - Fill (White).svg

@@ -0,0 +1,5 @@
+<svg width="256" height="256" viewBox="0 0 256 256" fill="none" xmlns="http://www.w3.org/2000/svg">
+<rect width="256" height="256" transform="matrix(-1 0 0 1 256 0)" fill="black"/>
+<path d="M167.489 89.8618C167.489 87.9224 165.441 86.667 163.713 87.5473L154.788 92.0971C141.739 98.7493 133.523 112.159 133.523 126.806V194.718C133.533 199.053 128.837 201.777 125.08 199.647L84.2227 176.06C83.2036 175.472 82.5762 174.384 82.5762 173.207V106.445C82.5759 104.992 80.9999 104.087 79.7451 104.813L61.3467 115.428C53.4685 119.976 48.6096 128.382 48.6094 137.487V179.978C48.6094 189.074 53.4588 197.481 61.3467 202.039L67.3301 205.494C67.6627 205.707 68.0004 205.916 68.3447 206.115L95.3066 221.682C103.184 226.23 112.889 226.232 120.779 221.679L154.312 202.32C154.271 202.342 154.23 202.362 154.189 202.384C154.283 202.333 154.375 202.281 154.468 202.229L154.312 202.32C154.463 202.237 154.615 202.154 154.765 202.068L154.762 202.065C162.646 197.511 167.487 189.102 167.488 180.009L167.489 89.8618Z" fill="white"/>
+<path d="M163.007 36.0259C155.13 31.4781 145.424 31.4763 137.533 36.0288L104.002 55.3882C104.029 55.3732 104.057 55.359 104.084 55.3442C104.02 55.3794 103.956 55.4159 103.893 55.4516L104.002 55.3882C103.851 55.4714 103.699 55.5536 103.549 55.6401L103.552 55.6411C95.6664 60.1948 90.8241 68.6053 90.8232 77.6987L90.8223 167.846C90.8223 169.786 92.8707 171.04 94.5986 170.16L103.523 165.611C116.573 158.959 124.788 145.549 124.788 130.902V62.9897C124.778 58.6479 129.49 55.9211 133.25 58.0698L174.091 81.6479C175.11 82.2363 175.737 83.3238 175.737 84.5005V151.263C175.738 152.716 177.314 153.621 178.568 152.895L196.967 142.28C204.845 137.732 209.704 129.326 209.704 120.221V77.73C209.704 68.6343 204.855 60.2267 196.967 55.6694L190.982 52.2143C190.65 52.0011 190.313 51.792 189.969 51.5932L163.007 36.0259Z" fill="white"/>
+</svg>

docs/assets/SVG/Microsoft Foundry Agent Framework - Stroke (Black).svg

@@ -0,0 +1,4 @@
+<svg width="256" height="256" viewBox="0 0 256 256" fill="none" xmlns="http://www.w3.org/2000/svg">
+<rect width="256" height="256" transform="matrix(-1 0 0 1 256 0)" fill="white"/>
+<path d="M48.6094 179.978V137.487C48.6096 128.382 53.4685 119.976 61.3467 115.428L79.7451 104.813C80.9999 104.087 82.5759 104.992 82.5762 106.445V173.207C82.5762 174.384 83.2036 175.472 84.2227 176.06L125.08 199.647C128.837 201.777 133.533 199.053 133.523 194.718V126.806C133.523 112.388 141.484 99.1684 154.18 92.4135L154.788 92.0971L163.713 87.5473C165.441 86.667 167.489 87.9224 167.489 89.8618L167.488 180.009L167.474 180.86C167.181 189.624 162.399 197.653 154.762 202.065L154.765 202.068C154.615 202.154 154.463 202.237 154.312 202.32L154.468 202.229C154.375 202.281 154.283 202.333 154.189 202.384C154.23 202.362 154.271 202.342 154.312 202.32L120.779 221.679L120.034 222.092C112.534 226.093 103.539 226.092 96.0508 222.095L95.3066 221.682L68.3447 206.115C68.0004 205.916 67.6627 205.707 67.3301 205.494L61.3467 202.039C53.7053 197.624 48.9149 189.595 48.623 180.829L48.6094 179.978ZM175.737 84.5005C175.737 83.3974 175.186 82.3728 174.277 81.7641L174.091 81.6479L133.25 58.0698C129.49 55.9211 124.778 58.6479 124.788 62.9897V130.902L124.782 131.587C124.53 145.966 116.369 159.063 103.523 165.611L94.5986 170.16L94.4355 170.236C92.799 170.938 90.9459 169.803 90.8281 168.026L90.8223 167.846L90.8232 77.6987C90.8241 68.6053 95.6664 60.1948 103.552 55.6411L103.549 55.6401C103.699 55.5536 103.851 55.4714 104.002 55.3882L103.893 55.4516C103.956 55.4159 104.02 55.3794 104.084 55.3442C104.057 55.359 104.029 55.3732 104.002 55.3882L137.533 36.0288C145.424 31.4763 155.13 31.4781 163.007 36.0259L189.969 51.5932C190.313 51.792 190.65 52.0011 190.982 52.2143L196.967 55.6694C204.855 60.2267 209.704 68.6343 209.704 77.73V120.221L209.689 121.073C209.397 129.848 204.599 137.874 196.967 142.28L178.568 152.895C177.314 153.621 175.738 152.716 175.737 151.263V84.5005ZM176.814 149.866L176.819 149.864L176.832 149.856C176.826 149.859 176.82 149.862 176.814 149.866ZM137.023 194.71L137.019 195.038C136.802 201.878 129.341 206.087 123.354 202.692L123.33 202.678L82.4727 179.091C80.3698 177.877 79.0762 175.634 79.0762 173.207V109.239L63.0957 118.458C56.5124 122.259 52.3745 129.183 52.1221 136.752L52.1094 137.487V179.978C52.1094 187.823 56.2909 195.075 63.0957 199.007H63.0967L69.0801 202.462L69.1504 202.503L69.2188 202.547C69.5212 202.741 69.8111 202.92 70.0947 203.083L97.0566 218.651L97.6982 219.007C104.372 222.569 112.434 222.453 119.029 218.648L152.514 199.316L152.512 199.312C152.581 199.274 152.65 199.236 152.752 199.178L152.753 199.181C152.775 199.169 152.796 199.158 152.815 199.147L153.011 199.035C159.81 195.107 163.987 187.854 163.988 180.009V91.3344L156.378 95.2153C144.501 101.27 137.023 113.475 137.023 126.806V194.71ZM94.3223 166.372L101.934 162.493C113.811 156.438 121.288 144.233 121.288 130.902V62.9897C121.278 55.9521 128.901 51.5532 134.986 55.0307L135 55.0385L175.841 78.6167L176.036 78.7339C178.023 79.9714 179.237 82.15 179.237 84.5005V148.468L195.217 139.249C202.013 135.326 206.204 128.075 206.204 120.221V77.73C206.204 69.8848 202.022 62.6318 195.217 58.6997L189.232 55.2456L189.162 55.2046L189.094 55.1606C188.788 54.9649 188.5 54.787 188.219 54.6245L161.257 39.0571C154.463 35.135 146.091 35.1311 139.282 39.0591L139.283 39.06L105.765 58.4106L105.767 58.4135C105.713 58.443 105.723 58.4383 105.602 58.5063L105.6 58.5034C105.535 58.5391 105.481 58.5691 105.433 58.5962L105.302 58.6723C98.5016 62.5995 94.324 69.8532 94.3232 77.6987L94.3223 166.372Z" fill="black"/>
+</svg>

docs/assets/SVG/Microsoft Foundry Agent Framework - Stroke (White).svg

@@ -0,0 +1,4 @@
+<svg width="256" height="256" viewBox="0 0 256 256" fill="none" xmlns="http://www.w3.org/2000/svg">
+<rect width="256" height="256" transform="matrix(-1 0 0 1 256 0)" fill="black"/>
+<path d="M48.6094 179.978V137.487C48.6096 128.382 53.4685 119.976 61.3467 115.428L79.7451 104.813C80.9999 104.087 82.5759 104.992 82.5762 106.445V173.207C82.5762 174.384 83.2036 175.472 84.2227 176.06L125.08 199.647C128.837 201.777 133.533 199.053 133.523 194.718V126.806C133.523 112.388 141.484 99.1684 154.18 92.4135L154.788 92.0971L163.713 87.5473C165.441 86.667 167.489 87.9224 167.489 89.8618L167.488 180.009L167.474 180.86C167.181 189.624 162.399 197.653 154.762 202.065L154.765 202.068C154.615 202.154 154.463 202.237 154.312 202.32L154.468 202.229C154.375 202.281 154.283 202.333 154.189 202.384C154.23 202.362 154.271 202.342 154.312 202.32L120.779 221.679L120.034 222.092C112.534 226.093 103.539 226.092 96.0508 222.095L95.3066 221.682L68.3447 206.115C68.0004 205.916 67.6627 205.707 67.3301 205.494L61.3467 202.039C53.7053 197.624 48.9149 189.595 48.623 180.829L48.6094 179.978ZM175.737 84.5005C175.737 83.3974 175.186 82.3728 174.277 81.7641L174.091 81.6479L133.25 58.0698C129.49 55.9211 124.778 58.6479 124.788 62.9897V130.902L124.782 131.587C124.53 145.966 116.369 159.063 103.523 165.611L94.5986 170.16L94.4355 170.236C92.799 170.938 90.9459 169.803 90.8281 168.026L90.8223 167.846L90.8232 77.6987C90.8241 68.6053 95.6664 60.1948 103.552 55.6411L103.549 55.6401C103.699 55.5536 103.851 55.4714 104.002 55.3882L103.893 55.4516C103.956 55.4159 104.02 55.3794 104.084 55.3442C104.057 55.359 104.029 55.3732 104.002 55.3882L137.533 36.0288C145.424 31.4763 155.13 31.4781 163.007 36.0259L189.969 51.5932C190.313 51.792 190.65 52.0011 190.982 52.2143L196.967 55.6694C204.855 60.2267 209.704 68.6343 209.704 77.73V120.221L209.689 121.073C209.397 129.848 204.599 137.874 196.967 142.28L178.568 152.895C177.314 153.621 175.738 152.716 175.737 151.263V84.5005ZM176.814 149.866L176.819 149.864L176.832 149.856C176.826 149.859 176.82 149.862 176.814 149.866ZM137.023 194.71L137.019 195.038C136.802 201.878 129.341 206.087 123.354 202.692L123.33 202.678L82.4727 179.091C80.3698 177.877 79.0762 175.634 79.0762 173.207V109.239L63.0957 118.458C56.5124 122.259 52.3745 129.183 52.1221 136.752L52.1094 137.487V179.978C52.1094 187.823 56.2909 195.075 63.0957 199.007H63.0967L69.0801 202.462L69.1504 202.503L69.2188 202.547C69.5212 202.741 69.8111 202.92 70.0947 203.083L97.0566 218.651L97.6982 219.007C104.372 222.569 112.434 222.453 119.029 218.648L152.514 199.316L152.512 199.312C152.581 199.274 152.65 199.236 152.752 199.178L152.753 199.181C152.775 199.169 152.796 199.158 152.815 199.147L153.011 199.035C159.81 195.107 163.987 187.854 163.988 180.009V91.3344L156.378 95.2153C144.501 101.27 137.023 113.475 137.023 126.806V194.71ZM94.3223 166.372L101.934 162.493C113.811 156.438 121.288 144.233 121.288 130.902V62.9897C121.278 55.9521 128.901 51.5532 134.986 55.0307L135 55.0385L175.841 78.6167L176.036 78.7339C178.023 79.9714 179.237 82.15 179.237 84.5005V148.468L195.217 139.249C202.013 135.326 206.204 128.075 206.204 120.221V77.73C206.204 69.8848 202.022 62.6318 195.217 58.6997L189.232 55.2456L189.162 55.2046L189.094 55.1606C188.788 54.9649 188.5 54.787 188.219 54.6245L161.257 39.0571C154.463 35.135 146.091 35.1311 139.282 39.0591L139.283 39.06L105.765 58.4106L105.767 58.4135C105.713 58.443 105.723 58.4383 105.602 58.5063L105.6 58.5034C105.535 58.5391 105.481 58.5691 105.433 58.5962L105.302 58.6723C98.5016 62.5995 94.324 69.8532 94.3232 77.6987L94.3223 166.372Z" fill="white"/>
+</svg>

docs/decisions/0001-agent-run-response.md

@@ -2,7 +2,7 @@
 # These are optional elements. Feel free to remove any of them.
 status: accepted
 contact: westey-m
-date: 2025-07-10 {YYYY-MM-DD when the decision was last updated}
+date: 2025-07-10
 deciders: sergeymenshykh, markwallace, rbarreto, dmytrostruk, westey-m, eavanvalkenburg, stephentoub
 consulted:
 informed:
@@ -139,7 +139,7 @@ Therefore something like `AgentResponse.Text` which also aggregates all `TextCon
 
 #### Option 1.2 Presence of Secondary Content is determined by a runtime parameter
 
-We can allow callers to choose whether to include secondary content in the list of reponse messages.
+We can allow callers to choose whether to include secondary content in the list of response messages.
 Open Question: Do we allow secondary content to use `TextContent` types?
 
 ```csharp

docs/decisions/0002-agent-tools.md

@@ -113,7 +113,7 @@ Implement a hybrid strategy where common tools use generic `AITool`-derived abst
 
 ### AI Agent Tool Types Availability
 
-Tool Type | Azure AI Foundry Agent Service | OpenAI Assistant API | OpenAI ChatCompletion API | OpenAI Responses API | Amazon Bedrock Agents | Google | Anthropic | Description
+Tool Type | Microsoft Foundry Agent Service | OpenAI Assistant API | OpenAI ChatCompletion API | OpenAI Responses API | Amazon Bedrock Agents | Google | Anthropic | Description
 -- | -- | -- | -- | -- | -- | -- | -- | --
 Function Calling | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | Enables custom, stateless functions to define specific agent behaviors.
 Code Interpreter | ✅ | ✅ | ❌ | ✅ | ✅ | ✅ | ✅ | Allows agents to execute code for tasks like data analysis or problem-solving.
@@ -132,7 +132,7 @@ Image Generation | ❌ | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ | Generates or edits
 
 #### Function Calling
 <details>
-  <summary>Azure AI Foundry Agent Service</summary>
+  <summary>Microsoft Foundry Agent Service</summary>
   Source: <a href="https://learn.microsoft.com/en-us/azure/ai-foundry/agents/how-to/tools/function-calling?pivots=rest">https://learn.microsoft.com/en-us/azure/ai-foundry/agents/how-to/tools/function-calling?pivots=rest</a>
 
   Message Request:
@@ -401,7 +401,7 @@ Image Generation | ❌ | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ | Generates or edits
 
 #### Code Interpreter
 <details>
-  <summary>Azure AI Foundry Agent Service</summary>
+  <summary>Microsoft Foundry Agent Service</summary>
   <p>Source: <a href="https://learn.microsoft.com/en-us/azure/ai-foundry/agents/how-to/tools/code-interpreter-samples?pivots=rest-api">https://learn.microsoft.com/en-us/azure/ai-foundry/agents/how-to/tools/code-interpreter-samples?pivots=rest-api</a></p>
 
   <p>.NET Support: ✅</p>
@@ -709,7 +709,7 @@ Image Generation | ❌ | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ | Generates or edits
 
 #### Search and Retrieval
 <details>
-  <summary>Azure AI Foundry Agent Service</summary>
+  <summary>Microsoft Foundry Agent Service</summary>
   Source: <a href="https://learn.microsoft.com/en-us/azure/ai-foundry/agents/how-to/tools/file-search-upload-files?pivots=rest">https://learn.microsoft.com/en-us/azure/ai-foundry/agents/how-to/tools/file-search-upload-files?pivots=rest</a>
 
   File Search Request:
@@ -1083,7 +1083,7 @@ Image Generation | ❌ | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ | Generates or edits
 
 #### Web Search
 <details>
-  <summary>Azure AI Foundry Agent Service</summary>
+  <summary>Microsoft Foundry Agent Service</summary>
   Source: <a href="https://learn.microsoft.com/en-us/azure/ai-foundry/agents/how-to/tools/bing-code-samples?pivots=rest">https://learn.microsoft.com/en-us/azure/ai-foundry/agents/how-to/tools/bing-code-samples?pivots=rest</a>
 
   Bing Search Message Request:
@@ -1630,7 +1630,7 @@ Image Generation | ❌ | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ | Generates or edits
 
 #### OpenAPI Spec Tool
 <details>
-  <summary>Azure AI Foundry Agent Service</summary>
+  <summary>Microsoft Foundry Agent Service</summary>
   Source: <a href="https://learn.microsoft.com/en-us/azure/ai-foundry/agents/how-to/tools/openapi-spec-samples?pivots=rest-api">https://learn.microsoft.com/en-us/azure/ai-foundry/agents/how-to/tools/openapi-spec-samples?pivots=rest-api</a><br>
   Source: <a href="https://learn.microsoft.com/en-us/rest/api/aifoundry/aiagents/run-steps/get-run-step?view=rest-aifoundry-aiagents-v1&tabs=HTTP#runstepopenapitoolcall">https://learn.microsoft.com/en-us/rest/api/aifoundry/aiagents/run-steps/get-run-step?view=rest-aifoundry-aiagents-v1&tabs=HTTP#runstepopenapitoolcall</a>
 
@@ -1712,7 +1712,7 @@ Image Generation | ❌ | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ | Generates or edits
 
 #### Stateful Functions
 <details>
-  <summary>Azure AI Foundry Agent Service</summary>
+  <summary>Microsoft Foundry Agent Service</summary>
   Source: <a href="https://learn.microsoft.com/en-us/azure/ai-foundry/agents/how-to/tools/azure-functions-samples?pivots=rest">https://learn.microsoft.com/en-us/azure/ai-foundry/agents/how-to/tools/azure-functions-samples?pivots=rest</a>
 
   Message Request:
@@ -1832,7 +1832,7 @@ Image Generation | ❌ | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ | Generates or edits
 
 #### Microsoft Fabric
 <details>
-  <summary>Azure AI Foundry Agent Service</summary>
+  <summary>Microsoft Foundry Agent Service</summary>
   Source: <a href="https://learn.microsoft.com/en-us/azure/ai-foundry/agents/how-to/tools/fabric?pivots=rest">https://learn.microsoft.com/en-us/azure/ai-foundry/agents/how-to/tools/fabric?pivots=rest</a>
 
   Message Request:

docs/decisions/0006-userapproval.md

@@ -2,7 +2,7 @@
 # These are optional elements. Feel free to remove any of them.
 status: accepted
 contact: westey-m
-date: 2025-09-12 {YYYY-MM-DD when the decision was last updated}
+date: 2025-09-12
 deciders: sergeymenshykh, markwallace-microsoft, rogerbarreto, dmytrostruk, westey-m, eavanvalkenburg, stephentoub, peterychang
 consulted: 
 informed: 
@@ -25,7 +25,7 @@ See various features that would need to be supported via this type of mechanism,
 - Also see [the openai human-in-the-loop guide](https://openai.github.io/openai-agents-js/guides/human-in-the-loop/#approval-requests).
 - Also see [the openai MCP guide](https://openai.github.io/openai-agents-js/guides/mcp/#optional-approval-flow).
 - Also see [MCP Approval Requests from OpenAI](https://platform.openai.com/docs/guides/tools-remote-mcp#approvals).
-- Also see [Azure AI Foundry MCP Approvals](https://learn.microsoft.com/en-us/azure/ai-foundry/agents/how-to/tools/model-context-protocol-samples?pivots=rest#submit-your-approval).
+- Also see [Microsoft Foundry MCP Approvals](https://learn.microsoft.com/en-us/azure/ai-foundry/agents/how-to/tools/model-context-protocol-samples?pivots=rest#submit-your-approval).
 - Also see [MCP Elicitation requests](https://modelcontextprotocol.io/specification/draft/client/elicitation)
 
 ## Decision Drivers

docs/decisions/0007-agent-filtering-middleware.md

@@ -1125,7 +1125,7 @@ Naming (Python): N/A (Composable Components)
 Supports: N  
 Observation: No explicit middleware/filters; modularity allows composable units but no dedicated interception hooks or callbacks for custom reading/modification mid-execution.
 
-For more details, see the official documentation: [Atomic Agents Docs](https://brainblend-ai.github.io/atomic-agents/). No specific code examples available for interception.
+No specific code examples available for interception.
 
 #### Smolagents (Hugging Face)
 

docs/decisions/0009-support-long-running-operations.md

@@ -57,7 +57,7 @@ This section describes different options for various aspects required to add lon
 
 ### 1. Methods for Working with Long-Running Operations
 
-Based on the analysis of existing APIs that support long-running operations (such as OpenAI Responses, Azure AI Foundry Agents, and A2A), 
+Based on the analysis of existing APIs that support long-running operations (such as OpenAI Responses, Microsoft Foundry Agents, and A2A),
 the following operations are used for working with long-running operations:
 - Common operations:
   - **Start Long-Running Execution**: Initiates a long-running operation and returns its Id.
@@ -757,7 +757,7 @@ Some of them natively support resuming streaming from a specific point in the st
 | API                     | Can Resume Streaming                 | Model                                                                                                      |
 |-------------------------|--------------------------------------|------------------------------------------------------------------------------------------------------------|
 | OpenAI Responses        | Yes                                  | StreamingResponseUpdate.**SequenceNumber** + GetResponseStreamingAsync(responseId, **startingAfter**, ct)  |
-| Azure AI Foundry Agents | Emulated<sup>2</sup>                 | RunStep.**Id** + custom pseudo code: client.Runs.GetRunStepsAsync(...).AllStepsAfter(**stepId**)           |
+| Microsoft Foundry Agents | Emulated<sup>2</sup>                 | RunStep.**Id** + custom pseudo code: client.Runs.GetRunStepsAsync(...).AllStepsAfter(**stepId**)           |
 | A2A                     | Implementation dependent<sup>1</sup> |          																				                  |
 
 <sup>1</sup> The [A2A specification](https://github.com/a2aproject/A2A/blob/main/docs/topics/streaming-and-async.md#1-streaming-with-server-sent-events-sse)
@@ -765,7 +765,7 @@ allows an A2A agent implementation to decide how to handle streaming resumption:
 a task is still active (and the server hasn't sent a final: true event for that phase), the client can attempt to reconnect to the stream using the tasks/resubscribe RPC method. 
 The server's behavior regarding missed events during the disconnection period (e.g., whether it backfills or only sends new updates) is implementation-dependent._
 
-<sup>2</sup> The Azure AI Foundry Agents API has an API to start a streaming run but does not have an API to resume streaming from a specific point in the stream.
+<sup>2</sup> The Microsoft Foundry Agents API has an API to start a streaming run but does not have an API to resume streaming from a specific point in the stream.
 However, it has non-streaming APIs to access already started runs, which can be used to emulate streaming resumption by accessing a run and its steps and streaming all the steps after a specific step.
 
 #### Required Changes
@@ -828,7 +828,7 @@ Sequence of updates from OpenAI Responses API to answer the question "What time
 | resp_2 | 10 | resp.output_item.done    | -               | InProgress                |                                                   |
 | resp_2 | 11 | resp.completed           | Completed       | Completed                 |                                                   |
 
-Sequence of updates from Azure AI Foundry Agents API to answer the question "What time is it?" using a function call:
+Sequence of updates from Microsoft Foundry Agents API to answer the question "What time is it?" using a function call:
 | Id     | SN      | UpdateKind        | Run.Status     | Step.Status | Message.Status  | ChatResponseUpdate.Status | Description                                       |
 |--------|---------|-------------------|----------------|-------------|-----------------|---------------------------|---------------------------------------------------|
 | run_1  | -       | RunCreated        | Queued         | -           | -               | Queued                    |                                                   |
@@ -852,7 +852,7 @@ Sequence of updates from Azure AI Foundry Agents API to answer the question "Wha
 
 To support long-running operations, the following values need to be returned by the GetResponseAsync and GetStreamingResponseAsync methods:
 - `ResponseId` - identifier of the long-running operation or an entity representing it, such as a task.
-- `ConversationId` - identifier of the conversation or thread the long-running operation is part of. Some APIs, like Azure AI Foundry Agents, use 
+- `ConversationId` - identifier of the conversation or thread the long-running operation is part of. Some APIs, like Microsoft Foundry Agents, use
   this identifier together with the ResponseId to identify a run.
 - `SequenceNumber` - identifier of an update within a stream of updates. This is required to support streaming resumption by the GetStreamingResponseAsync method only.
 - `Status` - status of the long-running operation: whether it is queued, running, failed, cancelled, completed, etc.
@@ -1089,7 +1089,7 @@ public class ChatOptions
 
 ##### 6.1.5 Continuation Token of a Custom Type
 
-The option is similar the the "6.1.3 Continuation Token of System.ClientModel.ContinuationToken Type" option but suggests using a 
+The option is similar to the "6.1.3 Continuation Token of System.ClientModel.ContinuationToken Type" option but suggests using a 
 custom type for the continuation token instead of the `System.ClientModel.ContinuationToken` type.
 
 **Pros**
@@ -1203,7 +1203,7 @@ response = await agent.CancelRunAsync(response.ResponseId, new AgentCancelRunOpt
 In case an agent supports either or both cancellation and deletion of long-running operations, it will override the corresponding methods.
 Otherwise, it won't override them, and the base implementations will return null by default.
 
-Some agents, for example Azure AI Foundry Agents, require the thread identifier to cancel a run. To accommodate this requirement, the `CancelRunAsync` method
+Some agents, for example Microsoft Foundry Agents, require the thread identifier to cancel a run. To accommodate this requirement, the `CancelRunAsync` method
 accepts an optional `AgentCancelRunOptions` parameter that allows callers to specify the thread associated with the run they want to cancel.
 
 ```csharp
@@ -1574,7 +1574,7 @@ the thread is provided with background operations consistently for all runs.
 </details>
 
 <details>
-<summary>Azure AI Foundry Agents</summary>
+<summary>Microsoft Foundry Agents</summary>
 
 - Create a thread and run the agent against it and wait for it to complete using polling:
     ```csharp

docs/decisions/0021-provider-leading-clients.md

@@ -34,11 +34,11 @@ Key changes:
 1. **New `agent-framework-openai` package** with dependencies on `agent-framework-core`, `openai`, and `packaging` only.
 2. **Class renames**: `OpenAIResponsesClient` → `OpenAIChatClient` (Responses API), `OpenAIChatClient` → `OpenAIChatCompletionClient` (Chat Completions API). Old names remain as deprecated aliases.
 3. **Deprecated classes**: `OpenAIAssistantsClient`, all `AzureOpenAI*Client` classes, `AzureAIClient`, `AzureAIAgentClient`, and `AzureAIProjectAgentProvider` are marked deprecated.
-4. **New `FoundryChatClient`** in azure-ai for Azure AI Foundry Responses API access, built on `RawFoundryChatClient(RawOpenAIChatClient)`.
+4. **New `FoundryChatClient`** in azure-ai for Microsoft Foundry Responses API access, built on `RawFoundryChatClient(RawOpenAIChatClient)`.
 5. **All deprecated `AzureOpenAI*` classes** consolidated into a single file (`_deprecated_azure_openai.py`) in the azure-ai package for clean future deletion.
 6. **Core's `agent_framework.openai` and `agent_framework.azure` namespaces** become lazy-loading gateways, preserving backward-compatible import paths while removing hard dependencies.
 7. **Unified `model` parameter** replaces `model_id` (OpenAI), `deployment_name` (Azure OpenAI), and `model_deployment_name` (Azure AI) across all client constructors. The term `model` is intentionally generic: it naturally maps to an OpenAI model name *and* to an Azure OpenAI deployment name, making it straightforward to use `OpenAIChatClient` with either OpenAI or Azure OpenAI backends (via `AsyncAzureOpenAI`). Environment variables are similarly unified (e.g., `OPENAI_MODEL` instead of separate `OPENAI_CHAT_MODEL_ID` / `OPENAI_CHAT_COMPLETION_MODEL_ID`).
-8. **`FoundryAgent`** replaces the pattern of `Agent(client=AzureAIClient(...))` for connecting to pre-configured agents in Azure AI Foundry (PromptAgents and HostedAgents). The underlying `RawFoundryAgentChatClient` is an implementation detail — most users interact only with `FoundryAgent`. `AzureAIAgentClient` is separately deprecated as it refers to the V1 Agents Service API. See below for design rationale.
+8. **`FoundryAgent`** replaces the pattern of `Agent(client=AzureAIClient(...))` for connecting to pre-configured agents in Microsoft Foundry (PromptAgents and HostedAgents). The underlying `RawFoundryAgentChatClient` is an implementation detail — most users interact only with `FoundryAgent`. `AzureAIAgentClient` is separately deprecated as it refers to the V1 Agents Service API. See below for design rationale.
 
 ### Foundry Agent Design: `FoundryAgentClient` vs `FoundryAgent`
 

docs/decisions/0023-foundry-evals-integration.md

@@ -7,11 +7,11 @@ consulted: Pratyush Mishra, Shivam Shrivastava, Manni Arora (Centrica eval scena
 informed: Agent Framework team, Foundry Evals team
 ---
 
-# Agent Evaluation Architecture with Azure AI Foundry Integration
+# Agent Evaluation Architecture with Microsoft Foundry Integration
 
 ## Context and Problem Statement
 
-Azure AI Foundry provides a rich evaluation service for AI agents — built-in evaluators for agent behavior (task adherence, intent resolution), tool usage (tool call accuracy, tool selection), quality (coherence, fluency, relevance), and safety (violence, self-harm, prohibited actions). Results are viewable in the Foundry portal with dashboards and comparison views.
+Microsoft Foundry provides a rich evaluation service for AI agents — built-in evaluators for agent behavior (task adherence, intent resolution), tool usage (tool call accuracy, tool selection), quality (coherence, fluency, relevance), and safety (violence, self-harm, prohibited actions). Results are viewable in the Foundry portal with dashboards and comparison views.
 
 However, using Foundry Evals with an agent-framework agent today requires significant manual effort. Developers must:
 
@@ -445,7 +445,7 @@ These factorings produce different scores for the same conversation. The framewo
 
 ### Azure AI: FoundryEvals
 
-`Evaluator` implementation backed by Azure AI Foundry:
+`Evaluator` implementation backed by Microsoft Foundry:
 
 ```python
 class FoundryEvals:
@@ -812,4 +812,4 @@ public sealed class EvalItem
 
 ## More Information
 
-- [Foundry Evals documentation](https://learn.microsoft.com/azure/ai-foundry/concepts/evaluation-approach-gen-ai) — Azure AI Foundry evaluation overview
+- [Foundry Evals documentation](https://learn.microsoft.com/azure/ai-foundry/concepts/evaluation-approach-gen-ai) — Microsoft Foundry evaluation overview

docs/decisions/0024-prompt-injection-defense.md

@@ -0,0 +1,154 @@
+---
+status: proposed
+contact: shruti
+date: 2026-01-14
+deciders: {}
+consulted: {}
+informed: {}
+---
+
+# FIDES - Deterministic Prompt Injection Defense [Costa et al., 2025]
+
+## Context and Problem Statement
+
+AI agents are vulnerable to prompt injection attacks where malicious instructions embedded in external content (e.g., API responses, user input) can manipulate agent behavior. Traditional defenses rely on heuristics and prompt engineering, which are not deterministic and can be bypassed.
+
+We need a systematic, deterministic defense mechanism that prevents untrusted content from influencing agent behavior, provides verifiable security guarantees, maintains audit trails for compliance, and integrates seamlessly with the existing agent framework.
+
+## Decision Drivers
+
+- Agents must not execute actions influenced by untrusted external content (prompt injection defense).
+- The solution must provide deterministic, verifiable security guarantees — not heuristic-based.
+- The solution must maintain audit trails for compliance and security reviews.
+- The solution must integrate non-invasively with the existing middleware pipeline.
+- The solution must be opt-in and backwards compatible with existing agents.
+- Developer experience must remain simple with a clear security model.
+
+## Considered Options
+
+- Information-flow control with label-based middleware (FIDES)
+- Prompt engineering defense
+- Content sanitization
+- Separate agent instances
+- Runtime monitoring only
+
+## Decision Outcome
+
+Chosen option: "Information-flow control with label-based middleware (FIDES)", because it is the only option that provides deterministic, formally verifiable security guarantees while integrating non-invasively with the existing middleware pipeline and remaining fully backwards compatible.
+
+FIDES (Flow Integrity Deterministic Enforcement System) is a label-based security system with four core components:
+
+1. **Content Labeling System** — `IntegrityLabel` (TRUSTED/UNTRUSTED) and `ConfidentialityLabel` (PUBLIC/PRIVATE/USER_IDENTITY) with most-restrictive-wins combination policy.
+2. **Middleware-Based Enforcement** — `LabelTrackingFunctionMiddleware` for automatic label propagation and `PolicyEnforcementFunctionMiddleware` for pre-execution policy checks.
+3. **Variable Indirection** — `ContentVariableStore` and `VariableReferenceContent` for physical isolation of untrusted content from the LLM context.
+4. **Quarantined Execution** — `quarantined_llm` and `inspect_variable` tools for isolated processing of untrusted data with audit logging.
+
+In addition, remote MCP integrations are secured through two mechanisms:
+
+- **Hint-based tool auto-labeling**: MCP `ToolAnnotations` (`readOnlyHint`, `openWorldHint`, etc.) are mapped to FIDES tool properties (`source_integrity`, `accepts_untrusted`, `max_allowed_confidentiality`).
+- **Server `_meta.ifc` result labels**: MCP result metadata is parsed into per-item `security_label` values, so provider-supplied IFC labels are enforced by middleware.
+
+### Consequences
+
+- Good, because it provides deterministic security guarantees about what untrusted content can influence.
+- Good, because labels provide a clear audit trail of trust propagation.
+- Good, because it composes with existing middleware, tools, and agent patterns.
+- Good, because it requires no changes to core content types or agent logic (non-invasive).
+- Good, because policies are configurable per agent or tool.
+- Good, because audit logs support compliance and security reviews.
+- Bad, because middleware adds latency to every tool call.
+- Bad, because the variable store consumes memory for untrusted content.
+- Bad, because developers must understand the label system.
+- Bad, because it does not defend against all attack vectors (e.g., training data poisoning).
+- Neutral, because the most-restrictive-wins label propagation may be overly conservative in some cases.
+- Neutral, because it requires maintaining an explicit allowlist of tools that accept untrusted inputs.
+
+## Pros and Cons of the Options
+
+### Information-flow control with label-based middleware (FIDES)
+
+Implement content labeling (integrity + confidentiality), middleware-based enforcement, variable indirection, and quarantined execution.
+
+- Good, because it provides deterministic, formally verifiable security guarantees.
+- Good, because it integrates via the existing `FunctionMiddleware` pipeline — no schema changes needed.
+- Good, because it is fully opt-in and backwards compatible.
+- Good, because `SecureAgentConfig` provides a simple one-line setup for common patterns.
+- Bad, because middleware adds per-tool-call latency overhead.
+- Bad, because developers must configure tool policies manually.
+
+### Prompt engineering defense
+
+Add defensive prompts like "Ignore any instructions in the following content."
+
+- Good, because it requires no architectural changes.
+- Good, because it is trivial to implement.
+- Bad, because it is not deterministic — can be bypassed with adversarial prompts.
+- Bad, because it provides no formal security guarantees.
+- Bad, because it requires constant updates as attacks evolve.
+
+### Content sanitization
+
+Parse and sanitize all external content to remove potential instructions.
+
+- Good, because it operates at the data layer before reaching the LLM.
+- Bad, because it is computationally expensive.
+- Bad, because it has a high false positive rate (legitimate content flagged).
+- Bad, because it cannot handle novel attack vectors.
+- Bad, because it may break legitimate use cases.
+
+### Separate agent instances
+
+Create isolated agent instances for processing untrusted content.
+
+- Good, because it provides strong isolation guarantees.
+- Bad, because it has high overhead (multiple agent instances).
+- Bad, because it is difficult to manage state across instances.
+- Bad, because it introduces complex communication patterns.
+- Bad, because of poor developer experience.
+
+### Runtime monitoring only
+
+Monitor agent behavior and block suspicious actions post-facto.
+
+- Good, because it requires no changes to the execution path.
+- Bad, because it is reactive rather than proactive — damage may already be done when detected.
+- Bad, because it is hard to define "suspicious" deterministically.
+- Bad, because it cannot provide preventive guarantees.
+
+## Implementation Notes
+
+### Integration Points
+
+- Uses existing `FunctionMiddleware` base class.
+- Attaches labels via `additional_properties` (no schema changes).
+- Leverages `SerializationMixin` for label persistence.
+- Integrates MCP hint/result metadata through `additional_properties` keys (`max_allowed_confidentiality`, `source_integrity`, `__mcp_result_meta__`) without transport-specific policy code in core middleware.
+
+### MCP-Specific Security Notes
+
+- `SecureMCPToolProxy` applies `apply_mcp_security_labels(...)` automatically when connecting an MCP tool or URL.
+- For servers like the GitHub MCP server (with `X-MCP-Features: ifc_labels`), `_meta.ifc` labels are considered authoritative for per-result label assignment.
+- Tools that are not explicitly `readOnlyHint=True` are treated as potential sinks and default to `max_allowed_confidentiality=PUBLIC` to prevent exfiltration.
+
+
+### Backwards Compatibility
+
+- Fully backwards compatible — opt-in system.
+- Agents without security middleware function normally.
+- Unlabeled content defaults to UNTRUSTED (safer default).
+- No breaking changes to existing APIs.
+
+## Related Decisions
+
+- [ADR-0007: Agent Filtering Middleware](0007-agent-filtering-middleware.md) — Established middleware patterns we build upon.
+- [ADR-0006: User Approval](0006-userapproval.md) — Human-in-the-loop pattern we reference.
+
+## References
+
+- [Securing AI Agents with Information-Flow Control (Costa et al., 2025)](https://arxiv.org/abs/2505.23643)
+- [Prompt Injection Attack Examples](https://simonwillison.net/2023/Apr/14/worst-that-can-happen/)
+- [Information Flow Control](https://en.wikipedia.org/wiki/Information_flow_(information_theory))
+- [Taint Analysis](https://en.wikipedia.org/wiki/Taint_checking)
+- [Defense in Depth](https://en.wikipedia.org/wiki/Defense_in_depth_(computing))
+- [ ] Performance Benchmarks
+- [ ] User Acceptance Testing

docs/decisions/0025-foundry-toolbox-support.md

@@ -9,7 +9,7 @@ deciders: evmattso
 
 ## What is the goal of this feature?
 
-Enable Agent Framework users to consume Foundry **toolboxes** — named, versioned bundles of tool definitions stored server-side in an Azure AI Foundry project — directly from `FoundryChatClient`, without dropping to the raw `azure-ai-projects` SDK.
+Enable Agent Framework users to consume Foundry **toolboxes** — named, versioned bundles of tool definitions stored server-side in a Microsoft Foundry project — directly from `FoundryChatClient`, without dropping to the raw `azure-ai-projects` SDK.
 
 A user who has configured a toolbox in the Foundry portal (or via the raw SDK) should be able to load it into an agent with a single call:
 

docs/decisions/0026-hosted-session-identity-context.md

@@ -0,0 +1,86 @@
+---
+status: superseded by [ADR-0030](0030-hosted-platform-context-agentserver-2.0.md)
+contact: rogerbarreto
+date: 2026-06-29
+deciders: rogerbarreto
+consulted: []
+informed: []
+---
+
+# Hosted session identity context for Foundry Hosting
+
+> **Superseded by [ADR-0030](0030-hosted-platform-context-agentserver-2.0.md).** `Azure.AI.AgentServer.*` 2.0.0 (responses protocol `2.0.0`) replaced `ResponseContext.Isolation` (`UserIsolationKey` / `ChatIsolationKey`, headers `x-agent-user-isolation-key` / `x-agent-chat-isolation-key`) with `ResponseContext.PlatformContext` (`UserIdKey` / `CallId`, headers `x-agent-user-id` / `x-agent-foundry-call-id`). The chat isolation key was removed and `HostedSessionContext` is now user-only. This ADR is retained as the historical record of the original design.
+
+## Context and Problem Statement
+
+Server-hosted Foundry agents need a way to scope per-user state (most notably `FoundryMemoryProvider` memories) by the end user that initiated the request. The Foundry platform already injects `x-agent-user-isolation-key` and `x-agent-chat-isolation-key` headers on every Responses request, but the agent-framework hosting layer did not surface those values to `AIContextProvider` instances. The provider's `stateInitializer` only received an `AgentSession?` with no identity attached, so per-user scoping was impossible without out-of-band plumbing.
+
+## Decision Drivers
+
+- Memory and any future user-private context must be partitioned per end user without per-sample boilerplate.
+- The identity must be **read-only** from the perspective of `AIContextProvider`s, so a buggy or hostile provider cannot escalate or leak across users.
+- The persisted session must validate against the live request on every resume to defend against session-id leak and in-process tampering.
+- The change must work for every existing hosted-agent type (`ChatClientAgent`, `FoundryAgent`, future ones) without per-type refactoring of cast-heavy code paths in `Microsoft.Agents.AI`.
+- Local Docker debugging must remain possible when the platform headers are absent.
+
+## Considered Options
+
+1. **`HostedSessionContext` stored in `AgentSessionStateBag`, exposed via a public read accessor and an `internal` setter.** Hosting writes once on session creation and validates on every resume.
+2. **Specialised `HostedAgentSession : AgentSession` wrapper** that carries `UserId`/`ChatId` properties, with `GetService<ChatClientAgentSession>()` as the unwrap escape hatch.
+3. **New property on `AgentSession` base class** (`HostedSessionContext? HostedContext { get; internal set; }`).
+4. **AsyncLocal middleware** that reads the headers and stuffs them into a per-request `AsyncLocal<HostedSessionContext>` consumed by the provider.
+
+For the source of identity:
+- A. The platform-injected `IsolationContext` exposed by `ResponseContext.Isolation` (typed `UserIsolationKey`/`ChatIsolationKey`).
+- B. The OpenAI Responses spec's top-level `request.User` field.
+- C. A custom HTTP header `x-client-user`.
+
+## Decision Outcome
+
+**Option 1** was chosen for the storage shape, sourced from **Option A** (`ResponseContext.Isolation`).
+
+Rationale:
+
+- **Wrapper rejected (Option 2).** `ChatClientAgentSession` is `sealed` and `ChatClientAgent` rejects any other session type via direct `is not ChatClientAgentSession` checks at multiple call sites. Wrapping would force non-trivial refactors across `Microsoft.Agents.AI` and a corresponding repeat for every other agent type.
+- **Base-class property rejected (Option 3).** Leaks "hosted" semantics into the universal `AgentSession` abstraction used by Durable, A2A, and CopilotStudio agents that have no notion of a hosted user.
+- **AsyncLocal rejected (Option 4).** Surfaces the concept only locally, requires every consumer to re-implement the bridge, and cannot be enforced as read-only.
+- **`request.User` rejected (Option B).** Set by the caller, not the platform. Forging it client-side trivially defeats per-user partitioning.
+- **`x-client-user` rejected (Option C).** Non-standard, requires custom HTTP plumbing, and duplicates the platform-provided isolation contract.
+
+Implementation summary in `Microsoft.Agents.AI.Foundry.Hosting`:
+
+| Type | Visibility | Purpose |
+|---|---|---|
+| `HostedSessionContext` | public sealed | Captures `UserId` and `ChatId` (both required, non-whitespace). |
+| `HostedSessionContextExtensions.GetHostedContext` | public | Read accessor for `AIContextProvider`s. |
+| `HostedSessionContextExtensions.SetHostedContext` | internal | Writer reserved for the hosting assembly. Backed by `AgentSessionStateBag` under a well-known key for serialisation. |
+| `HostedSessionIsolationKeyProvider` (abstract) | public | DI-resolvable factory. Async signature: `ValueTask<HostedSessionContext?> GetKeysAsync(ResponseContext, CreateResponse, CancellationToken)`. |
+| `PlatformHostedSessionIsolationKeyProvider` | internal sealed | Default implementation. Maps `context.Isolation.UserIsolationKey` and `context.Isolation.ChatIsolationKey`. Returns `null` when either is absent. |
+
+Behaviour added to `AgentFrameworkResponseHandler.CreateAsync`:
+
+1. Resolve `HostedSessionIsolationKeyProvider` from DI; fall back to `PlatformHostedSessionIsolationKeyProvider`.
+2. Call `GetKeysAsync(context, request, cancellationToken)`. A `null` result throws `InvalidOperationException` (becomes 500). A null/whitespace `UserId` or `ChatId` is rejected by `HostedSessionContext`'s constructor.
+3. Branch on the **session's existing context**, not on whether a `conversation_id` was supplied:
+   - **No session (`session is null`):** nothing to stamp; skip.
+   - **Session present but un-stamped (`GetHostedContext() is null`):** treat as fresh. This covers both newly-created sessions and pre-existing sessions whose `conversation_id` was provisioned externally (e.g. via `conversations.CreateProjectConversationAsync()`) before the first hosted-agent request. Stamp the resolved identity now.
+   - **Session present with stamped context:** strict resume. The persisted `UserId` and `ChatId` must equal the resolved values exactly. Mismatch throws `ResponsesApiException` with status 403 and body `Hosted session identity context mismatch`.
+
+## Consequences
+
+Positive:
+
+- Per-user memory partitioning works out of the box for any agent that consumes a `Microsoft.Agents.AI.Foundry.FoundryMemoryProvider` configured to read `session.GetHostedContext().UserId`.
+- Cross-user session-id leak and in-process tampering of the persisted identity both surface as a 403 with a deliberately uninformative body.
+- The identity is opaque to the framework, matching the platform's semantics. The framework never inspects user identity; the `IsolationContext` keys are pre-partitioned per agent.
+
+Negative:
+
+- Every existing hosted sample fails locally without a `HostedSessionIsolationKeyProvider` registered, because the platform headers are absent outside the platform. Mitigated by shipping `Hosted_Shared_Contributor_Setup` with `DevTemporaryLocalSessionIsolationKeyProvider` and `AddDevTemporaryLocalContributorSetup`, and migrating all 9 existing responses samples.
+- An attacker who can plant an un-stamped session under a victim's `conversation_id` *before* the victim's first hosted-agent request would be stamped with the attacker's identity on that first request. This is not a regression vs. behaviour without this contract, and is mitigated in practice because the `conversation_id` namespace is allocated by the platform per project. Once a session is stamped, the strict equality check fully defends the resume path.
+
+## Out of scope
+
+- Per-request `User` field on `CreateResponse` is intentionally not consumed; only the platform `IsolationContext` headers carry trustworthy identity.
+- Generic (non-Foundry) hosting layers can re-define an equivalent type if needed; nothing in this ADR is moved into `Microsoft.Agents.AI.Hosting` because `Microsoft.Agents.AI.Foundry.Hosting` does not depend on it.
+- HMAC tamper signatures over the persisted context are not implemented; comparison against `ResponseContext.Isolation` on every request is sufficient because the platform sets those headers at the trust boundary.

docs/decisions/0027-hosting-channels.md

@@ -0,0 +1,524 @@
+---
+status: accepted
+contact: eavanvalkenburg
+date: 2026-06-30
+deciders: eavanvalkenburg
+consulted: rogerbarreto, moonbox3
+---
+
+# Python protocol helpers and optional execution state
+
+## Context and Problem Statement
+
+Agent Framework needs to help applications expose agents and workflows over external protocols such as OpenAI
+Responses, Telegram, Activity Protocol, and future transports.
+
+FastAPI, Starlette, Azure Functions, Django, Telegram SDKs, Bot Framework SDKs, and other app frameworks already own
+route registration, dependency injection, middleware, authentication, background tasks, lifecycle, and native client
+calls. Agent Framework should not duplicate those surfaces unless a specific hosting environment requires it.
+
+## Decision Drivers
+
+- Keep the released surface small enough to explain without first teaching a channel framework.
+- Provide reusable Agent Framework run translation that works with FastAPI, Django, and other web frameworks.
+- Let app/framework code own route declaration, auth, middleware, native SDK clients, command handling, and background
+  work.
+- Keep stateful execution support explicit: session lookup/storage and workflow checkpoint lookup/storage may still need
+  a small AF-owned home.
+
+## Considered Options
+
+1. Create protocol-specific hosts.
+2. Ship a full host/channel framework with route contribution and channel hooks.
+3. Ship protocol conversion helpers plus optional execution state.
+
+### 1. Create protocol-specific hosts
+
+- Good: no new shared abstraction.
+- Neutral: each protocol host can evolve independently.
+- Bad: every package reinvents AF input/result mapping, session-key conventions, and stateful execution helpers.
+
+### 2. Ship a full host/channel framework
+
+- Good: one object can assemble routes, channels, session handling, hooks, and lifecycle callbacks.
+- Good: app code using the supported host shape can be short.
+- Bad: the framework owns concerns already handled by web frameworks, protocol SDKs and/or other services.
+- Bad: users must understand `Channel`, contribution, hook, and host-dispatch concepts before they can see how a request
+  becomes `agent.run(...)`.
+- Bad: the abstraction is hard to reuse outside the chosen web framework.
+
+### 3. Ship protocol helpers plus optional execution state
+
+- Good: protocol packages provide the Agent Framework run value directly: `<protocol>_to_run(...)` and
+  `<protocol>_from_run(...)` style helpers.
+- Good: apps keep native FastAPI, Starlette, Azure Functions, Django, Bot Framework, or Telegram SDK code.
+- Good: helper functions can be tested without a web framework app or host pipeline.
+- Good: small state objects can still own target-coupled state: `AgentState` pairs an agent target with a `SessionStore`,
+  and `WorkflowState` resolves a workflow target while reusing the existing `CheckpointStorage` abstraction.
+- Good: provides maximum configurability in handling input and outputs (outside of the conversions)
+- Bad: building a first iteration of a new Host is more verbose.
+- Bad: samples show more explicit route/client code than a fully assembled channel host.
+
+## Decision Outcome
+
+Chosen option: **3. Ship protocol helpers plus optional execution state**.
+
+Protocol packages own:
+
+- parsing protocol-native input into Agent Framework run input and options;
+- rendering `AgentResponse`, `AgentResponseUpdate`, workflow results, or workflow updates back into protocol-native
+  response/event payloads;
+- protocol-specific isolation/session id helper functions when useful, such as `telegram_session_id(update)`;
+- protocol-specific typing/update event helpers where the protocol has a native concept.
+
+Application or web-framework code owns:
+
+- HTTP route declaration and route grouping;
+- dependency injection;
+- authentication and authorization;
+- middleware;
+- background tasks and webhook acknowledgement policy;
+- native protocol SDK clients and outbound calls;
+- command registration and command dispatch;
+- request/response status codes and framework-specific error handling;
+- choosing the isolation/session id source for the current deployment and route.
+
+The application builder can make the server exactly as they see fit, but this is outside the responsibilities of this proposed scheme.
+This might include implementing other known API surfaces from vendors like OpenAI, such as creating conversations, vector stores, deleting things, etc.
+If they want they can build the full OpenAI API, but it will include code that does not rely on agent-framework-hosting, which is fine.
+They are responsible for what they expose.
+
+The optional execution-state helpers, if provided, are limited to shared execution state:
+
+- `AgentState`: one `SupportsAgentRun`-compatible target plus a `SessionStore`;
+- `WorkflowState`: one `Workflow`, `WorkflowBuilder`-shaped builder, orchestration builder, or workflow factory;
+- `SessionStore`: plain async storage (`get` / `set` / `delete`) by an app-selected id.
+
+The store does not create sessions. `AgentState` provides the target-aware `get_or_create_session(...)` helper because
+only the state object has both the store and the resolved agent target. Workflow checkpointing should use the existing
+`CheckpointStorage` abstraction directly; app/state code may keep a small cursor (`session_id -> checkpoint_id`) when it
+needs to resume a workflow for a session.
+
+These objects are **not** app objects, channel registries, or route owners. They do not own FastAPI/Starlette setup,
+route contribution, protocol dispatch, command projection, or native SDK calls.
+
+### Helper naming and families
+
+Helpers should be protocol-specific, not generic. Avoid a generic `protocol_to_run(...)` name in public samples because it
+hides the protocol-specific contract behind a second abstraction.
+
+Protocol packages should consider these helper families. This table is a set of examples, not a required protocol or
+checklist. Not every protocol needs every helper, but when a protocol has the concept the naming should stay consistent:
+
+| Helper family | Shape | Purpose |
+| --- | --- | --- |
+| Run conversion | `<protocol>_to_run(...)` | Convert one protocol-native call/update/request into `Agent.run` or `Workflow.run` values. |
+| Final rendering | `<protocol>_from_run(...)` | Convert a final `AgentResponse` / workflow result into protocol-native response payloads or operations. |
+| Stream rendering | `<protocol>_from_streaming_run(...)` | Convert `ResponseStream` / workflow updates into protocol-native events or operations. |
+| Session id extraction | `<protocol>_session_id(...)` | Extract the protocol's natural continuation/partition key from the call, if present. |
+| Command/action parsing | `<protocol>_command(...)` | Parse a protocol-native command/action/operation name without deciding app policy. |
+
+Examples:
+
+- `responses_to_run(...)`, `responses_from_run(...)`, `responses_from_streaming_run(...)`,
+  `responses_session_id(...)`;
+- `telegram_to_run(...)`, `telegram_from_run(...)`, `telegram_from_streaming_run(...)`,
+  `telegram_session_id(...)`, `telegram_command(...)`;
+- `activity_to_run(...)`, `activity_from_run(...)`, `activity_session_id(...)`, `activity_command(...)`;
+- `discord_to_run(...)`, `discord_from_run(...)`, `discord_session_id(...)`, `discord_command(...)`.
+
+The app still owns what a parsed command means. For example, a Telegram `/new`, Discord slash command, Bot Framework
+command activity, or A2A cancellation/request action may parse through a command/action helper, but the route or SDK
+handler decides whether that command clears a session, cancels a task, calls an agent, or is ignored.
+
+Additional helper functions can be protocol-specific when the concept is not broadly shared. Examples include
+`telegram_chat_id(...)`, `telegram_callback_query_id(...)`, `telegram_media_file_id(...)`,
+`discord_interaction_id(...)`, `a2a_task_id(...)`, `a2a_context_id(...)`, and MCP tool/prompt/resource helpers. These
+helpers should still stay side-effect-free: they extract, normalize, or describe protocol data, while app/native SDK code
+performs acknowledgements, sends/edits messages, resolves protected file URLs, applies rate limits, and registers
+handlers.
+
+### Security responsibilities for application builders
+
+The application builder owns the trust boundary. Protocol helper packages can parse native payloads and expose candidate
+ids or operations, but they do not authenticate callers, authorize access to state, or decide which side effects are
+allowed.
+
+Application code that uses these helpers are responsible for (this means that we advice you to think through these topics,
+but ultimately, the choice of which controls are needed for the intended use case is up to the application builder):
+
+- authenticate the caller through the app's normal mechanism before using protocol-provided ids;
+- authorize any caller-supplied session, checkpoint, task, context, conversation, thread, or response id before loading
+  state for it;
+- bind externally supplied ids to the authenticated user, tenant, workspace, installation, or chat context before using
+  them as `SessionStore` keys or checkpoint cursor keys;
+- treat `<protocol>_session_id(...)` results as untrusted candidate keys until that ownership check has passed;
+- keep platform-provided isolation helpers fail-closed outside their trusted hosting environment;
+- authorize command/action effects such as reset, cancel, approve, submit, or tool invocation after parsing them;
+- opt in explicitly before resolving protected media/resource/file URLs and passing them to a remote model provider;
+- persist post-run session or checkpoint state only after `agent.run(...)`, `workflow.run(...)`, or stream finalization has
+  updated that state.
+
+For Foundry specifically, helpers may read values established by Foundry hosting middleware, but must not treat raw
+request headers as trusted Foundry isolation when the app is running outside Foundry. Implementations must test that
+non-Foundry requests do not accept spoofable isolation headers as platform-provided keys.
+
+For workflow checkpointing, the checkpoint boundary must be at least as specific as the authorized session/tenant
+boundary. A shared storage lookup such as "latest checkpoint for workflow name" is safe only when the storage is already
+scoped to the authorized session. In a shared durable store, map the authorized `session_id` to a checkpoint id or other
+cursor and load that specific checkpoint.
+
+### Session continuity
+
+Session continuity remains explicit. Run parsing and isolation/session id selection are separate operations because
+isolation can come from more than one source:
+
+- protocol input, such as OpenAI Responses `previous_response_id`, a Telegram chat id, or an Activity conversation id;
+- running environment, such as Foundry Hosted Agents user/chat isolation context;
+- app-specific trusted middleware or route state.
+
+The app chooses which helper to call for that route and deployment. For example:
+
+- `responses_session_id(body)` from `agent-framework-hosting-responses`, which can return either a `resp_*` previous
+  response id or a `conv_*` conversation id when present;
+- `telegram_session_id(update, bot_id=...)` from `agent-framework-hosting-telegram`, which uses the bot and sender for
+  private chats and the bot and chat for shared group sessions;
+- `activity_session_id(activity)`, `discord_session_id(interaction_or_message)`, or
+  `a2a_session_id(request_context)` from their respective protocol packages;
+- `foundry_user_isolation_key()` or `foundry_chat_isolation_key()` from `agent-framework-foundry-hosting`.
+
+Keep these helpers outside `responses_to_run(...)`, `telegram_to_run(...)`, and other run-input parsers. That makes the
+trust boundary visible: using a request-derived key is a different decision than using a platform-provided isolation key.
+
+The application builder is also responsible for deciding whether the hosting environment is **persistent** (for example,
+a long-running container or web app) or **transient** (for example, Azure Functions, Foundry Hosted Agents, or any
+environment where process memory is not a reliable continuity boundary). That decision controls which state mechanisms are
+safe to use:
+
+- persistent single-process apps may use in-memory state for local development or simple deployments, while still needing
+  durable state for multi-replica continuity;
+- transient apps must not rely on in-memory `SessionStore` state between calls and need a durable session store or a
+  service-owned continuation id;
+- workflow hosts must choose an explicit `CheckpointStorage` and, when they need per-session resume, a durable
+  `session_id -> checkpoint_id` cursor because in-process workflow state and in-memory checkpoint cursors do not survive
+  transient execution.
+
+A `SessionStore` stores `session_id -> AgentSession`, but it does not create sessions. `AgentState` resolves the agent
+target and creates the session on first use. Reads return independent working copies so running from one continuation
+point does not mutate the stored snapshot or another simultaneous branch:
+
+For agent targets:
+
+```python
+session = await state.get_or_create_session(session_id)
+target = await state.get_target()
+result = await target.run(messages, session=session, options=options)
+```
+
+If the protocol mints a new continuation id as part of the response being created (for example, OpenAI Responses
+`resp_*` ids), store the **post-run** session explicitly under that new id:
+
+```python
+session = await state.get_or_create_session(previous_response_id)
+target = await state.get_target()
+result = await target.run(messages, session=session, options=options)
+await state.set_session(response_id, session)
+```
+
+`agent.run(...)` may update the session object (for example, with service continuation state), so the explicit store call
+belongs after the run, not before it.
+
+Response ids are immutable continuation points, so simultaneous callers can branch from one `previous_response_id` and
+store their completed sessions under different new response ids. A stable `conversation_id` is a mutable head: the app
+must explicitly update it after the run and provide single-writer coordination. The hosting state helper does not lock
+an entire run or resolve concurrent updates to that stable key.
+
+The session id is a partition key, not proof of identity. App or platform code must authenticate and authorize any
+externally supplied key before using it.
+
+### Workflow checkpoints
+
+Workflow checkpointing is execution state, not protocol state. `WorkflowState` pairs a workflow target with checkpoint
+state, but it should not wrap or replace the existing `CheckpointStorage` abstraction. Apps should pass the actual
+`CheckpointStorage` they want the workflow to use. If an app needs per-session resume, it can keep a small cursor from
+authorized `session_id` to `checkpoint_id` (or an equivalent store-specific resume token).
+
+Workflow runs do not currently emit a checkpoint id on `WorkflowRunResult` or normal workflow events by default. The
+runner receives checkpoint ids internally from `CheckpointStorage.save(...)`. App/state code that owns the storage can
+observe the latest id by querying the storage after a run, for example
+`await storage.get_latest(workflow_name=target.name)`.
+
+For workflow targets, app code adapts the protocol helper output into the workflow's expected input and invokes the
+workflow through the state object's target:
+
+```python
+# session_id must already be authenticated and authorized for this caller
+target = await state.get_target()
+result = await target.run(message=workflow_input, checkpoint_storage=checkpoint_storage)
+latest = await checkpoint_storage.get_latest(workflow_name=target.name)
+if latest is not None:
+    await checkpoint_cursor_store.set(session_id, latest.checkpoint_id)
+```
+
+If a route wants to resume from a prior checkpoint, it explicitly chooses the checkpoint and passes it to
+`workflow.run(...)`:
+
+```python
+# session_id must already be authenticated and authorized for this caller
+target = await state.get_target()
+checkpoint_id = await checkpoint_cursor_store.get(session_id)
+if checkpoint_id is None:
+    result = await target.run(message=workflow_input, checkpoint_storage=checkpoint_storage)
+else:
+    result = await target.run(checkpoint_id=checkpoint_id, checkpoint_storage=checkpoint_storage)
+latest = await checkpoint_storage.get_latest(workflow_name=target.name)
+if latest is not None:
+    await checkpoint_cursor_store.set(session_id, latest.checkpoint_id)
+```
+
+`workflow.run(...)` writes checkpoints to the provided storage, so storage selection must be explicit at the route layer.
+Protocol helper packages should not own checkpoint layout, route lifecycle, or durable execution.
+
+## Non-goals for v1
+
+The following remain outside the v1 protocol-helper contract. Some are deliberately app-owned in v1; others are possible
+future framework work only after a separate design.
+
+### App-owned in v1
+
+The app builder owns these concerns with normal web-framework, SDK, platform, or application code:
+
+- authentication, authorization policy, and allowlists;
+- deciding whether identities across protocols map to the same `session_id`;
+- non-originating sends using native SDK clients;
+- background work, durable execution, retry, and replay when app code owns the work;
+- routing between multiple agents.
+
+This is easier in the protocol-helper model than it was in the host/channel model: app code already owns the native SDK
+clients, route handlers, authenticated caller context, session id selection, and outbound send calls. An app can link
+channels by choosing the same authorized `session_id` for multiple protocols, and can do non-originating delivery by
+calling the destination protocol's native client directly. That does not make a reusable framework feature safe by
+default; it just means the app-specific version no longer has to fight a host abstraction.
+
+### Future framework work
+
+The following require a reviewed identity, storage, delivery, replay, and observability model before becoming reusable
+framework features:
+
+- reusable cross-channel identity linking;
+- framework-owned proactive or non-originating delivery;
+- fan-out, multicast, selected-channel, active-channel, or all-linked delivery;
+- framework-owned delivery observability, dead-letter handling, and replay semantics;
+- cross-channel confidentiality and link policy.
+
+These possible framework enhancements are tracked by [ADR-0028](0028-hosting-linking-multicast-enhancements.md). They are
+not prerequisites for shipping or using the v1 protocol-helper surface. ADR-0028 was written against the earlier
+host/channel framing and must be revised to align with this protocol-helper and execution-state boundary before those
+enhancements are implemented.
+
+## Consequences
+
+Positive:
+
+- The released surface is smaller and easier to inspect: helpers plus state, not a channel framework.
+- Protocol helpers can be used from FastAPI, Starlette, Azure Functions, Django, CLI tools, tests, or native SDK webhook
+  handlers.
+- App authors can use the authentication, dependency injection, lifecycle, and background-task tools they already know.
+- Session continuity stays explicit and debuggable.
+- Workflow checkpointing can still be centralized if needed without making protocol packages own routing.
+
+Negative:
+
+- Multi-protocol samples include explicit route/client code.
+- Apps that want a batteries-included ASGI app must write or depend on an app-specific wrapper.
+- Existing unreleased code and docs that mention channels, contribution, or hooks must be revised before release.
+
+## More Information
+
+- Follow-up linking and multicast ADR: [ADR-0028](0028-hosting-linking-multicast-enhancements.md). That ADR still uses
+  some earlier host/channel terminology and must be aligned before implementation work starts.
+
+## Appendix: Developer experience sketch
+
+The examples below are sketches, not runtime-ready sample code. They show the minimum shape a developer would need to
+build: where protocol helpers are called, where app-owned auth/authorization belongs, where state is loaded/stored, and
+where native framework code remains in charge.
+
+### Optional execution state
+
+`AgentState` and `WorkflowState` stay small: they are target-specific state holders, not app hosts.
+
+```python
+from typing import Protocol
+
+from agent_framework import AgentSession, SupportsAgentRun, Workflow
+
+
+class SupportsBuild(Protocol):
+    def build(self) -> Workflow: ...
+
+
+class SessionStore:
+    async def get(self, session_id: str) -> AgentSession | None: ...
+    async def set(self, session_id: str, session: AgentSession) -> None: ...
+    async def delete(self, session_id: str) -> None: ...
+
+
+class CheckpointCursorStore:
+    async def get(self, session_id: str) -> str | None: ...
+    async def set(self, session_id: str, checkpoint_id: str) -> None: ...
+    async def delete(self, session_id: str) -> None: ...
+
+
+class AgentState:
+    def __init__(self, target: SupportsAgentRun, *, session_store: SessionStore | None = None) -> None: ...
+    async def get_target(self) -> SupportsAgentRun: ...
+    async def get_or_create_session(self, session_id: str) -> AgentSession: ...
+    async def set_session(self, session_id: str, session: AgentSession) -> None: ...
+
+
+class WorkflowState:
+    def __init__(self, target: Workflow | SupportsBuild) -> None: ...
+    async def get_target(self) -> Workflow: ...
+```
+
+`WorkflowState` accepts direct `Workflow` instances, workflow factories, and builder-shaped objects with
+`build() -> Workflow`. That structurally covers `WorkflowBuilder` and the builders in `agent_framework_orchestrations`
+without making `agent-framework-hosting` depend on the orchestration package.
+
+### Responses-only route
+
+This sketch shows the intended Responses-only shape. The protocol package owns the Agent Framework run conversion helpers and
+response-id minting details; the application owns FastAPI routing, auth, policy adjustment, and response construction.
+
+```python
+import os
+from collections.abc import AsyncIterator
+
+from agent_framework import Agent, ResponseStream
+from agent_framework.openai import OpenAIChatClient
+from agent_framework_hosting import AgentState  # pyright: ignore[reportAttributeAccessIssue]
+from agent_framework_hosting_responses import create_response_id, responses_from_run, responses_from_streaming_run, responses_session_id, responses_to_run  # pyright: ignore[reportAttributeAccessIssue]
+from fastapi import Body, FastAPI, Header, HTTPException
+from fastapi.responses import JSONResponse, StreamingResponse
+
+app = FastAPI()
+agent = Agent(
+    client=OpenAIChatClient(),
+    name="Assistant",
+    instructions="Be concise and helpful.",
+)
+state = AgentState(agent)
+
+
+@app.post("/responses")
+async def responses(body: dict = Body(...), x_api_key: str | None = Header(default=None)) -> JSONResponse | StreamingResponse:
+    if x_api_key != os.environ["RESPONSES_API_KEY"]:
+        raise HTTPException(status_code=401, detail="bad api key")
+
+    # parse the request body into a set of AF objects
+    run = responses_to_run(body)
+    # get the candidate session id from the body
+    # can be a resp_* for previous_response_id or a conv_* for a conversation
+    candidate_session_id = responses_session_id(body)
+    # create a new response_id for this run
+    response_id = create_response_id()
+
+    # the developer can make any adjustments to the request, i.e.:
+    run["options"]["store"] = False
+    run["options"].pop("model", None)
+    # the options here are of the shape defined by the ChatClient/Agent
+
+    # load the session (or create a new one) - this is optional
+    # verify this caller owns candidate_session_id before loading it; API-key auth
+    # alone does not prove ownership of a caller-supplied resp_* or conv_* id
+    session_id = candidate_session_id or response_id
+    session = await state.get_or_create_session(session_id)
+    target = await state.get_target()
+
+    if run["stream"]:
+        stream = target.run(
+            run["messages"],
+            stream=True,
+            session=session,
+            options=run["options"],
+        )
+        async def stream_events() -> AsyncIterator[str]:
+            async for event in responses_from_streaming_run(
+                stream,
+                response_id=response_id,
+                session_id=candidate_session_id,
+            ):
+                yield event
+            # agent.run may update the session during stream finalization, so store the post-run session explicitly
+            await state.set_session(response_id, session)
+
+        return StreamingResponse(stream_events(), media_type="text/event-stream")
+
+    result = await target.run(
+        run["messages"],
+        session=session,
+        options=run["options"],
+    )
+    # agent.run may update the session, so store the post-run session explicitly under the response id
+    # this might also be skipped, if the app chooses to respect `store=False` policy
+    await state.set_session(response_id, session)
+    return JSONResponse(responses_from_run(result, response_id=response_id, session_id=candidate_session_id))
+
+```
+
+### Responses-only Django class-based view
+
+The same helper surface can be used without FastAPI. A Django app owns URL routing, CSRF/auth policy, request parsing,
+and `JsonResponse` construction. In a real Django project this would live in the app's normal view module (for example
+`assistant/views.py`) and be routed from that app's `urls.py`; Django discovers it through its standard project/app
+layout, not through Agent Framework. This sketch shows the non-streaming path only; the streaming branch is the same
+state/finalization pattern shown in the FastAPI sketch and is omitted here to avoid duplicating it.
+
+```python
+import json
+import os
+
+from agent_framework import Agent
+from agent_framework.openai import OpenAIChatClient
+from agent_framework_hosting import AgentState  # pyright: ignore[reportAttributeAccessIssue]
+from agent_framework_hosting_responses import create_response_id, responses_from_run, responses_session_id, responses_to_run  # pyright: ignore[reportAttributeAccessIssue]
+from django.http import HttpRequest, HttpResponseBadRequest, HttpResponseForbidden, JsonResponse
+from django.views import View
+
+
+agent = Agent(
+    client=OpenAIChatClient(),
+    name="Assistant",
+    instructions="Be concise and helpful.",
+)
+state = AgentState(agent)
+
+
+class ResponsesView(View):
+    async def post(self, request: HttpRequest) -> JsonResponse:
+        if request.headers.get("x-api-key") != os.environ["RESPONSES_API_KEY"]:
+            return HttpResponseForbidden("bad api key")
+
+        try:
+            body = json.loads(request.body)
+        except json.JSONDecodeError:
+            return HttpResponseBadRequest("invalid json")
+
+        run = responses_to_run(body)
+        candidate_session_id = responses_session_id(body)
+        response_id = create_response_id()
+        options = run["options"]
+        # verify this caller owns candidate_session_id before loading it; API-key auth
+        # alone does not prove ownership of a caller-supplied resp_* or conv_* id
+        session_id = candidate_session_id or response_id
+        session = await state.get_or_create_session(session_id)
+        target = await state.get_target()
+        result = await target.run(
+            run["messages"],
+            session=session,
+            options=options,
+        )
+        await state.set_session(response_id, session)
+        return JsonResponse(responses_from_run(result, response_id=response_id, session_id=candidate_session_id))
+```

docs/decisions/0028-hosting-linking-multicast-enhancements.md

@@ -0,0 +1,132 @@
+---
+status: proposed
+contact: eavanvalkenburg
+date: 2026-06-11
+deciders: eavanvalkenburg
+---
+
+# Hosting linking and multicast enhancements
+
+## Context and Problem Statement
+
+[ADR-0027](0027-hosting-channels.md) defines the minimal v1 hosting core: originating-channel responses, explicit `ChannelSession.isolation_key`, and no host-level identity linking, push, multicast, background delivery, or durable runners.
+
+This ADR tracks the richer cross-channel behaviors that were removed from v1. These enhancements are **follow-up work** and are **not prerequisites** for shipping, using, or stabilizing the v1 host/channel core.
+
+## Decision Drivers
+
+- Cross-channel continuity must not create accidental cross-user, cross-tenant, or cross-channel data leaks.
+- Non-originating delivery must be observable, idempotent, retryable, and supportable.
+- Protocol payloads must remain channel-native while still being safe to persist and replay.
+- App authors need opt-in policy controls, not hidden defaults.
+- The enhancement stack should layer on top of the v1 host without reshaping the minimal channel contract.
+
+## Enhancement Areas
+
+The follow-up design should cover these capabilities together because they share identity, storage, delivery, and replay concerns:
+
+- **Cross-channel identity linking** — a user can connect multiple `ChannelIdentity` values to one channel-neutral `isolation_key`.
+- **Authorization and allowlist policy** — channels or hosts can require verified identity, allow specific native identities or claims, and deny unknown callers.
+- **Non-originating response delivery** — a run can respond somewhere other than the request's originating protocol when explicitly configured.
+- **Active-channel routing** — delivery can target the most recently observed linked channel for an `isolation_key`.
+- **Multicast / all-linked delivery** — delivery can fan out to every linked channel or a selected set.
+- **Background runs and continuation tokens** — long-running requests can return immediately and complete later, with a polling/status fallback.
+- **Durable delivery runners** — delivery work can survive process restarts and support dead-letter handling.
+- **Retry and replay semantics** — delivery attempts are bounded, deduplicated, and safe to replay.
+- **Payload serialization** — channel-specific payloads can be persisted, redacted, versioned, and reconstructed without losing protocol fidelity.
+
+Candidate API names from the broader design (`IdentityLinker`, `IdentityAllowlist`, `AuthPolicy`, `ResponseTarget`, `ChannelPush`, `ChannelPushCodec`, `DurableTaskRunner`, `InProcessTaskRunner`, `RetryPolicy`, `LinkPolicy`) remain design vocabulary for this ADR. They are not approved v1 APIs.
+
+## Considered Options
+
+### Option A — Leave all behavior to applications
+
+Applications implement linking, authorization, push, retry, and serialization independently.
+
+- Good: the hosting core stays very small.
+- Neutral: advanced apps can still build what they need.
+- Bad: every app must solve the same security and delivery problems, likely inconsistently.
+
+### Option B — Add the full enhancement stack to v1
+
+The first host release includes linking, authorization, active channel, multicast, background runs, durable runners, and codecs.
+
+- Good: the original cross-channel experience is available immediately.
+- Neutral: samples can demonstrate rich end-to-end flows.
+- Bad: v1 becomes security-sensitive, storage-heavy, and harder to stabilize.
+
+### Option C — Layer opt-in enhancement packages after v1
+
+Ship the minimal host first, then add linking, authorization, and delivery packages behind explicit configuration.
+
+- Good: v1 remains simple while leaving room for a reviewed, supportable enhancement stack.
+- Neutral: apps that need advanced delivery wait for follow-up packages.
+- Bad: the first release does not satisfy proactive or all-linked scenarios.
+
+### Option D — Build only platform-specific integrations
+
+Implement linking and proactive delivery separately in Telegram, Activity Protocol, Discord, and future channels.
+
+- Good: each package can match its protocol exactly.
+- Neutral: some shared abstractions may emerge later.
+- Bad: cross-channel behavior becomes fragmented and hard to reason about.
+
+## Decision Outcome
+
+Proposed direction: **Option C — layered opt-in enhancement packages after v1**.
+
+The minimal host remains the foundation. Follow-up packages may add linking, authorization, delivery, and durable execution, but must be explicitly enabled and must pass the validation gates below before becoming part of the public contract.
+
+## Safety Requirements
+
+### Threat model
+
+The design must account for:
+
+- spoofed channel-native identities,
+- stolen or replayed link challenges,
+- cross-tenant or cross-confidentiality data leakage,
+- unsolicited proactive messages,
+- malicious payloads persisted for replay,
+- denial-of-service through fan-out or retry storms, and
+- privacy leakage through logs, metrics, or support tooling.
+
+Required mitigations include verified identity claims where available, signed and expiring link challenges, explicit user consent, per-channel capability checks, default-deny policy options, tenant partitioning, and uninformative denial messages on shared channels.
+
+### Idempotency and replay
+
+Exactly-once delivery is not a realistic guarantee. The design must provide:
+
+- stable run, continuation, and delivery-attempt identifiers,
+- channel-level idempotency keys where protocols support them,
+- bounded retry with jitter and explicit terminal states,
+- replay windows and expiration,
+- duplicate suppression for persisted attempts, and
+- clear semantics for "delivered", "accepted by platform", and "observed by user".
+
+### Storage
+
+Enhancement storage must stay distinct from v1 `AgentSession` history and workflow checkpoints unless an implementation deliberately backs them with the same physical store.
+
+Stored data should be schema-versioned, minimized, encrypted or otherwise protected as appropriate, and partitioned by tenant/project. Link records, continuation records, active-channel state, delivery attempts, dead letters, and serialized payloads need independent TTL and deletion policies.
+
+### Observability and support
+
+The design must include structured logs, traces, and metrics for link attempts, authorization decisions, delivery scheduling, retries, replay, and dead-letter outcomes. Logs must avoid message content and sensitive identity claims by default. Operators need a way to inspect, revoke, replay, or purge stuck records safely.
+
+## Validation Gates
+
+Before these enhancements are accepted:
+
+- A reviewed threat model covers identity linking, authorization, non-originating delivery, multicast, and replay.
+- Cross-channel linking tests prove a verified identity can link two channels and that unlink/deny paths do not leak information.
+- Authorization tests cover native-id allowlists, verified-claim allowlists, default-deny behavior, and misconfiguration failures.
+- Delivery tests cover originating-only, specific-channel, active-channel, selected-channel, and all-linked routing.
+- Background/continuation tests cover polling fallback, cancellation or expiration, process restart, retry, and dead-letter behavior.
+- Codec tests prove payloads are versioned, redacted where needed, backward compatible, and rejected safely when unknown.
+- Multicast tests prove fan-out is bounded, independently retried, and idempotent per destination.
+- Observability tests or manual validation prove support operators can correlate a request to delivery attempts without exposing sensitive content.
+
+## Relationship to ADR-0027
+
+ADR-0027 remains valid without any of these enhancements. This ADR extends the hosting model only after the safety, storage, and support requirements above are satisfied.

docs/decisions/0029-mcp-skill-templates-and-direct-references.md

@@ -0,0 +1,641 @@
+---
+status: proposed
+contact: sergeymenshykh
+date: 2026-06-23
+deciders: sergeymenshykh
+---
+
+# Skills Over MCP: Implementation Design Options
+
+This document explores design options for two SEP-2640 features. The decisions are not yet finalized.
+
+- **Part 1: MCP Resource Template Skills** - skills described by a URI template with variables that must be resolved before loading.
+- **Part 2: Direct Skill References** - reading `skill://` URIs referenced directly (e.g., in server instructions) without being listed in the index.
+
+## Part 1: MCP Resource Template Skills
+
+### Context and Problem Statement
+
+The `AgentMcpSkillsSource` currently only supports `skill-md` type entries from `skill://index.json` (support for `archive` type is planned). The SEP-2640 specification also defines `mcp-resource-template` entries: **parameterized skill namespaces** described by a URI template with variables (e.g., `{product}`) that resolve to concrete `SKILL.md` URIs. Rather than materializing every skill in the index, the template's variables must be resolved before a skill can be loaded.
+
+### Index Entry Format
+
+```json
+{
+  "$schema": "https://schemas.agentskills.io/discovery/0.2.0/schema.json",
+  "skills": [
+    {
+      "name": "git-workflow",
+      "type": "skill-md",
+      "description": "Follow this team's Git conventions for branching and commits",
+      "url": "skill://git-workflow/SKILL.md"
+    },
+    {
+      "type": "mcp-resource-template",
+      "description": "Per-product documentation skill",
+      "url": "skill://docs/{product}/SKILL.md"
+    }
+  ]
+}
+```
+
+Key differences from `skill-md`:
+
+| Field | `skill-md` | `mcp-resource-template` |
+|-------|------------|-------------------------|
+| `name` | Required (the skill name) | **Omitted** (represents many skills) |
+| `type` | `"skill-md"` | `"mcp-resource-template"` |
+| `url` | Concrete URI to `SKILL.md` | URI template with variables |
+| `description` | Describes the skill | Describes the addressable skill space |
+
+### Use Cases
+
+Template skills address two scenarios where listing concrete skills is impractical:
+
+- **Large skill catalogs** - too many skills to enumerate every entry in the index.
+- **Dynamically generated skills** - skill content generated on the fly from parameters, so the set of valid skills is not known at index-creation time.
+
+### How Template Skills Are Consumed
+
+Per SEP-2640, the consumption flow relies on the MCP `completion/complete` method:
+
+1. **Server registers a resource template** - The MCP server registers the same `url` value (e.g., `skill://docs/{product}/SKILL.md`) as an MCP [resource template](https://modelcontextprotocol.io/specification/2025-11-25/server/resources#resource-templates), wiring template variables to the [completion API](https://modelcontextprotocol.io/specification/2025-11-25/server/utilities/completion).
+
+2. **Host reads `skill://index.json`** - Discovers the template entry with `type: "mcp-resource-template"`.
+
+3. **Host surfaces template in UI** - Presents the template as an interactive discovery point where the user fills in variables.
+
+4. **Host calls `completion/complete`** - For each template variable (e.g., `{product}`), the host calls the MCP completion API to get possible values from the server:
+   ```json
+   {
+     "method": "completion/complete",
+     "params": {
+       "ref": {
+         "type": "ref/resource",
+         "uri": "skill://docs/{product}/SKILL.md"
+       },
+       "argument": {
+         "name": "product",
+         "value": ""
+       }
+     }
+   }
+   ```
+   The server responds with possible completions:
+   ```json
+   {
+     "completion": {
+       "values": ["widgets", "billing", "auth", "payments"],
+       "hasMore": false,
+       "total": 4
+     }
+   }
+   ```
+
+5. **User selects a value** - The user picks a value (e.g., `"billing"`) from the list.
+
+6. **Host resolves the URI** - The template `skill://docs/{product}/SKILL.md` becomes the concrete URI `skill://docs/billing/SKILL.md`.
+
+7. **Host reads the resolved skill** - Calls `resources/read` with the concrete URI and proceeds as with any `skill-md` skill.
+
+### Potential Implementation Options
+
+### Option 1: Callback on `AgentMcpSkillsSource` for Variable Value Selection
+
+Add a callback to `AgentMcpSkillsSource` (or its options) that is invoked for each `mcp-resource-template` entry to let the caller select variable values.
+
+**Flow:**
+
+1. `AgentMcpSkillsSource.GetSkillsAsync()` reads `skill://index.json`
+2. For each entry with `type: "mcp-resource-template"`:
+   - Parse the URI template to extract variable names (e.g., `{product}`)
+   - Call the MCP `completion/complete` API to get possible values for each variable
+   - Invoke the caller-provided callback with the variable name, description, and possible values
+   - The callback returns a selected value and a `bool` indicating whether to include the skill
+3. Resolve the URI template with the selected values
+4. Create an `AgentMcpSkill` from the resolved URI and add it to the skills list
+
+**API sketch:**
+
+```csharp
+public delegate Task<(string? SelectedValue, bool IncludeSkill)> McpTemplateVariableSelector(
+    string templateDescription,
+    string variableName,
+    IReadOnlyList<string> possibleValues,
+    CancellationToken cancellationToken);
+
+// Usage via builder:
+var provider = new AgentSkillsProviderBuilder()
+    .UseMcpSkills(mcpClient, options => {
+        options.TemplateVariableSelector = async (description, variable, values, ct) =>
+        {
+            // Present to user, return selection
+            var selected = PromptUser(variable, values);
+            return (selected, IncludeSkill: selected is not null);
+        };
+    })
+    .Build();
+```
+
+**Pros:**
+- Simple implementation
+- Easy to understand and use
+
+**Cons:**
+- Cannot be used in server-side scenarios where there is no interactive user at skill-discovery time
+- Does not integrate with the agent's conversational flow
+
+---
+
+### Option 2: Integrate into Agent Conversation via `ChatClientAgent` Decorator
+
+Model the template variable resolution as a request/response interaction within the agent's conversational loop.
+
+**Flow:**
+
+1. A `DelegatingAIAgent` decorator (e.g., `McpTemplateSkillResolutionAgent`) intercepts `RunAsync`/`RunStreamingAsync` calls and checks whether the inner agent has an `AgentSkillsProvider` with an `AgentMcpSkillsSource` containing unresolved template entries. The check is performed via `GetService<AgentMcpSkillsSource>()` on the `AgentSkillsProvider`, which delegates to a `GetService` method on the `AgentSkillsSource` base class.
+
+2. The decorator calls an internal member on `AgentMcpSkillsSource` to get the list of `mcp-resource-template` entries from the index. The `AgentMcpSkillsSource` needs to be extended with an internal member that exposes unresolved template entries separately from concrete skills.
+
+3. For each template entry, the decorator calls an internal member on `AgentMcpSkillsSource` to retrieve possible values for the template's variables via the MCP `completion/complete` API.
+
+4. For each variable needing resolution, the decorator returns an `McpResourceTemplateValueRequestContent` (inherits from MEAI's `InputRequestContent`) in the agent response - bypassing the call to the inner agent. The content carries the template description, variable name, and possible values.
+
+5. The user app receives the response, identifies the `McpResourceTemplateValueRequestContent` content type, and displays UI to the user showing the variable name and possible values, or forwards it further downstream if the user app is a service.
+
+6. The user selects a value, and the user app calls the agent again with a corresponding `McpResourceTemplateValueResponseContent` (inherits from MEAI's `InputResponseContent`) containing the selected value. The `RequestId` property (inherited from the base classes) correlates the response with the original request.
+
+7. The decorator identifies the response content and provides the resolved values to `AgentMcpSkillsSource` so it can use them when constructing concrete skills.
+
+8. Having resolved all template variables, the decorator calls `RunAsync`/`RunStreamingAsync` on the inner agent.
+
+9. The inner agent invokes the `AgentSkillsProvider`, which calls `AgentMcpSkillsSource.GetSkillsAsync()`. The source now has all resolved variable values and constructs concrete `AgentMcpSkill` instances from the resolved URIs, so it can provide the skill content if requested by the model.
+
+**API sketch:**
+
+```csharp
+// New content types inheriting from MEAI's InputRequestContent/InputResponseContent:
+public sealed class McpResourceTemplateValueRequestContent : InputRequestContent
+{
+    public string TemplateDescription { get; }
+    public string VariableName { get; }
+    public IReadOnlyList<string> PossibleValues { get; }
+    public string TemplateUrl { get; }
+}
+
+public sealed class McpResourceTemplateValueResponseContent : InputResponseContent
+{
+    public string SelectedValue { get; }
+    public string TemplateUrl { get; }
+}
+
+// Decorator usage:
+var provider = new AgentSkillsProviderBuilder()
+    .UseMcpSkills(mcpClient)
+    .Build();
+
+AIAgent agent = new ChatClientAgent(chatClient, new ChatClientAgentOptions
+{
+    AIContextProviders = [provider],
+});
+agent = new McpTemplateSkillResolutionAgent(agent);
+```
+
+**Pros:**
+- Works in server-side scenarios
+- Fits the existing `DelegatingAIAgent` decorator pattern
+- Can be composed with other decorators (tool approval, etc.)
+
+**Cons:**
+- Complex implementation
+- Requires user app awareness of the new content types
+- Users need to know that an additional decorator is required for handling MCP template skills, in addition to registering the MCP skills source
+- Resolved template variable values must be persisted across conversation turns so the decorator does not re-prompt on subsequent agent runs within the same session
+
+**Note:** This writeup is high-level and may miss details that could change the design. A POC would be needed to validate the approach.
+
+### Open Questions
+
+1. **Completion API limit** - The MCP completion API returns at most 100 values per request and provides no offset/cursor mechanism for enumeration. If a variable has more than 100 possible values, it's unclear how to retrieve the rest - the API only supports prefix-based filtering (typeahead), not bulk pagination.
+
+2. **Multi-variable templates** - A template like `skill://{org}/{product}/SKILL.md` has multiple variables. Should they be resolved sequentially (org first, then product - since product values may depend on org) or presented together?
+
+3. **Caching** - Should resolved template values be saved in the `AgentSession` so the user isn't re-prompted on every agent run? How should they be persisted between sessions?
+
+---
+
+## Part 2: Direct Skill References
+
+This part covers how to let the model read `skill://` URIs referenced directly (e.g., in an MCP server's `instructions`, in a resource, or in another skill's content) without being listed in `skill://index.json`.
+
+### How MCP Skills and Relative Links Work Today
+
+The `AgentMcpSkillsSource` discovers skills by reading the well-known `skill://index.json` resource from the MCP server:
+
+```json
+{
+  "$schema": "https://schemas.agentskills.io/discovery/0.2.0/schema.json",
+  "skills": [
+    {
+      "name": "unit-converter",
+      "type": "skill-md",
+      "description": "Convert between common units.",
+      "url": "skill://unit-converter/SKILL.md"
+    },
+    {
+      "name": "currency-converter",
+      "type": "skill-md",
+      "description": "Convert between world currencies using live rates.",
+      "url": "skill://currency-converter/SKILL.md"
+    }
+  ]
+}
+```
+
+For each `skill-md` entry it creates an `AgentMcpSkill` instance - frontmatter (name/description) comes straight from the entry. The `AgentSkillsProvider` lists the discovered skills in the model's context (name + description):
+
+```xml
+<available_skills>
+  <skill>
+    <name>unit-converter</name>
+    <description>Convert between common units.</description>
+  </skill>
+  <skill>
+    <name>currency-converter</name>
+    <description>Convert between world currencies using live rates.</description>
+  </skill>
+</available_skills>
+```
+
+It also provides functions to the model so it can load a skill and access its resources:
+
+```csharp
+// Loads the full content of a specific skill.
+load_skill(string skillName)
+
+// Reads a resource associated with a skill (references, assets, dynamic data).
+read_skill_resource(string skillName, string resourceName)
+```
+
+The model calls `load_skill("unit-converter")` and receives the skill content:
+
+```markdown
+---
+name: unit-converter
+description: Convert between common units.
+---
+## Usage
+
+For the full conversion table, see references/units-table.md.
+```
+
+The skill body references `references/units-table.md` by relative path. The model calls `read_skill_resource("unit-converter", "references/units-table.md")` and receives the resource content:
+
+```markdown
+# Unit Conversion Table
+
+| From  | To   | Factor  |
+| miles | km   | 1.60934 |
+| kg    | lbs  | 2.20462 |
+```
+
+### Direct Reference Examples
+
+A `skill://` URI can appear in any of these locations:
+
+**Server instructions** - the MCP server advertises a skill the model should load:
+
+```text
+Follow our coding standards. Load skill://code-standards/SKILL.md for details.
+```
+
+**A skill body** - a skill's `SKILL.md` links to a sibling resource:
+
+```markdown
+---
+name: code-standards
+description: Coding standards and conventions.
+---
+## Naming
+
+Follow the naming rules in skill://code-standards/references/naming.md.
+```
+
+**A resource** - the linked resource holds the actual content:
+
+```markdown
+# Naming Rules
+
+- Use PascalCase for public members and type names.
+- Use camelCase for locals and parameters.
+- Prefix interfaces with `I` (e.g. `ISkillReader`).
+- Suffix async methods with `Async`.
+
+For examples, see skill://code-standards/references/naming-examples.md.
+```
+
+How can the model access content by direct reference?
+
+### Function for Reading Direct Skill References
+
+### Option 1: Extend existing `load_skill` and `read_skill_resource` functions
+
+```csharp
+// Added optional 'origin' and a direct skill:// URI is passed in 'skillName'.
+load_skill(string skillName, string? origin = null)
+
+// Added optional 'origin', made 'skillName' optional, and a direct skill:// URI is passed in 'resourceName'.
+read_skill_resource(string resourceName, string? skillName = null, string? origin = null)
+```
+
+The optional `origin` identifies the source/MCP server that should handle the direct URI.
+
+| Case | Call |
+|------|------|
+| Load skill | `load_skill("commit-guidelines")` |
+| Relative resource | `read_skill_resource("commit-guidelines", "examples/COMMIT_EXAMPLES.md")` |
+| `skill://` link (skill) | `load_skill(skillName: "skill://commit-guidelines/SKILL.md", origin: "DirectRefServer")` |
+| `skill://` link (resource) | `read_skill_resource(resourceName: "skill://commit-guidelines/examples/COMMIT_EXAMPLES.md", origin: "DirectRefServer")` |
+
+**Pros:**
+
+- No new functions added: existing tool surface stays at two functions.
+
+**Cons:**
+
+- Unreliable on some models (gpt-4o, gpt-4.1-mini): it often omits `origin` when it should not or calls the wrong function.
+- Optional parameters create silent ambiguity - the model can pass `origin` for non-MCP skills or omit it for `skill://` URIs.
+
+### Option 2 (Proposed): Add a dedicated `read_skill_uri` function alongside existing ones
+
+```csharp
+// Existing functions stay unchanged.
+load_skill(string skillName)
+read_skill_resource(string skillName, string resourceName)
+
+// New function added alongside: reads content by direct skill:// URI.
+read_skill_uri(string uri, string origin)
+```
+
+| Case | Call |
+|------|------|
+| Load skill | `load_skill("commit-guidelines")` |
+| Relative resource | `read_skill_resource("commit-guidelines", "examples/COMMIT_EXAMPLES.md")` |
+| `skill://` link (skill) | `read_skill_uri(uri: "skill://commit-guidelines/SKILL.md", origin:"DirectRefServer")` |
+| `skill://` link (resource) | `read_skill_uri(uri: "skill://commit-guidelines/examples/COMMIT_EXAMPLES.md", origin: "DirectRefServer")` |
+
+**Pros:**
+
+- Purely additive - no changes to existing functions needed; `read_skill_uri` can be deferred and added later when direct `skill://` reference support is needed.
+- Granular approval: each function can have its own approval gate (like the existing `ScriptApproval` for `run_skill_script`), making per-operation approval for skill loading, resource reading, and direct URI access straightforward to add.
+- Both `uri` and `origin` are required - no silent misuse through optional parameters.
+- Clean split: `load_skill`/`read_skill_resource` for named skills, `read_skill_uri` for `skill://` links - no parameter ambiguity.
+
+**Cons:**
+
+- Three read functions (`load_skill`, `read_skill_resource`, `read_skill_uri`), not counting `run_skill_script`: larger tool surface than a single-function design.
+
+### Option 3: Collapse `load_skill` and `read_skill_resource` into a single `read_resource` function
+
+```csharp
+// Single entrypoint for all skill content. 'uri' is required; 'origin' is optional.
+read_resource(string uri, string? origin = null)
+```
+
+- `uri` - what to read: a skill name, a relative resource path, or a `skill://` link.
+- `origin` - determines how `uri` is interpreted:
+  - **omitted** → load skill by name (`uri` is the skill name).
+  - **skill name** → read a relative resource (`uri` is the path within that skill).
+  - **server name** → read content by the `skill://` link (`uri` is handled by the source identified by the `[Origin: X]` marker).
+
+Dispatch is ordered: null `origin` routes to Case 1; if `origin` names a known skill, routes to Case 2; otherwise tries to find an `ISkillUriReader` whose `CanRead` returns true for `origin` (Case 3).
+
+| Case | Call |
+|------|------|
+| Load skill | `read_resource(uri: "commit-guidelines")` |
+| Relative resource | `read_resource(uri: "examples/COMMIT_EXAMPLES.md", origin: "commit-guidelines")` |
+| `skill://` link (skill) | `read_resource(uri: "skill://commit-guidelines/SKILL.md", origin: "DirectRefServer")` |
+| `skill://` link (resource) | `read_resource(uri: "skill://commit-guidelines/examples/COMMIT_EXAMPLES.md", origin: "DirectRefServer")` |
+
+**Pros:**
+
+- Minimal tool surface: one read function instead of two or three (not counting `run_skill_script`) reduces token usage and gives the model fewer choices.
+
+**Cons:**
+
+- No per-operation approval: all cases (skill loading, resource reading, direct URI access) share one function, so approval cannot be scoped to individual operations.
+- Unreliable on gpt-4.1-mini: omits `origin` when reading `skill://` links, passes skill name as `origin` when loading a plain skill (should be omitted), and hallucinates resource names (e.g. `API_SPECIFICATION.md`) that do not exist.
+
+
+---
+
+### Origin Marker
+
+A `skill://` URI does not carry an origin, but the model needs to provide one when reading it. The `origin` is what routes the read call to the source that can handle the URI - the provider uses it to pick the matching source. Since the URI itself carries no such hint, the MCP source injects an `[Origin: ...]` marker wherever a `skill://` URI appears, so the model can read it back and pass it as the `origin` argument.
+
+The marker is only added when the content actually contains `skill://` references. If a piece of content (server instructions, a skill body, or a resource) has no `skill://` URIs, there is nothing for the model to read back, so no marker is injected.
+
+Into **server instructions**, which may mention `skill://` URIs directly:
+
+```
+[Origin: code-standards-server]
+Follow our coding standards. Load skill://code-standards/SKILL.md for details.
+```
+
+Into **skill bodies**, since a `SKILL.md` may reference other `skill://` URIs (a resource file or a related skill):
+
+```
+[Origin: code-standards-server]
+# Code Standards
+
+For naming conventions, load skill://code-standards/references/naming.md.
+```
+
+Into **skill resources**, since a resource may itself reference further `skill://` URIs:
+
+```
+[Origin: code-standards-server]
+# Naming Rules
+
+- Use PascalCase for public members and type names.
+- Use camelCase for locals and parameters.
+
+For examples, see skill://code-standards/references/naming-examples.md.
+```
+
+---
+
+### Read-by-URI Capability: Interface vs Base Class Virtual Methods
+
+Now let's look at how an `AgentSkillsSource` can opt in to reading `skill://` URIs and signal that capability to the provider.
+
+### Option 1: New `ISkillUriReader` interface
+
+```csharp
+public interface ISkillUriReader
+{
+    // Returns true if this reader can handle the given skill:// URI from the given origin.
+    bool CanRead(string uri, string origin);
+
+    // Reads and returns the content for the given skill:// URI.
+    Task<object?> ReadByUriAsync(string uri, string origin, CancellationToken cancellationToken = default);
+}
+```
+
+Sources that support direct `skill://` URI reads - such as `AgentMcpSkillsSource` - implement this interface to opt in.
+
+The provider discovers readers via a service locator and dispatches to the first that can handle the URI:
+
+```csharp
+// Discover all registered readers.
+var readers = source.GetService<IEnumerable<ISkillUriReader>>();
+
+// Pick the first reader that can handle the URI.
+var reader = readers.FirstOrDefault(r => r.CanRead(uri, origin))
+    ?? throw new InvalidOperationException($"No reader can handle URI '{uri}' from origin '{origin}'.");
+
+// Delegate the read to it.
+return await reader.ReadByUriAsync(uri, origin, cancellationToken);
+```
+
+The provider may treat a source implementing `ISkillUriReader` as the signal to advertise `read_skill_uri`: if at least one registered source implements the interface, the function is exposed to the model; otherwise it is not.
+
+### Option 2 (Proposed): Virtual methods on `AgentSkillsSource` base class
+
+```csharp
+public abstract class AgentSkillsSource
+{
+    // New members for reading by URI.
+
+    // Whether this source can read by URI; drives whether read_skill_uri is advertised. Off by default.
+    public virtual bool SupportsReadByUri => false;
+
+    // Returns true if this source can handle the given skill:// URI from the given origin.
+    public virtual bool CanReadByUri(string uri, string origin) => false;
+
+    // Reads and returns the content for the given skill:// URI.
+    public virtual Task<object?> ReadByUriAsync(string uri, string origin, CancellationToken cancellationToken = default)
+        => Task.FromResult<object?>(null);
+
+    // Existing member.
+    public abstract Task<IList<AgentSkills>> GetSkillsAsync(CancellationToken cancellationToken = default);
+}
+```
+
+Sources opt in by overriding, and the provider calls them directly:
+
+```csharp
+// AgentMcpSkillsSource opts in by overriding the virtuals.
+public override bool SupportsReadByUri => true;
+
+// Handles the URI when its origin matches this source's MCP server.
+public override bool CanReadByUri(string uri, string origin)
+    => string.Equals(origin, this.Origin, StringComparison.OrdinalIgnoreCase);
+
+// Reads content by skill:// URI from the MCP server.
+public override Task<string?> ReadByUriAsync(string uri, string origin, CancellationToken cancellationToken)
+    => /* resolve uri via the MCP server identified by origin */;
+```
+
+All sources inherit the methods, so there is no type signal - `SupportsReadByUri` fills that role. The function is advertised when any registered source returns `true`.
+
+### Comparison
+
+| Aspect | Option 1: Interface | Option 2: Base class virtual methods |
+|--------|---------------------|--------------------------------------|
+| Discovery | Service locator | Direct call on source |
+| Advertising signal | Interface implementation | `SupportsReadByUri` flag |
+| Adding new members | Breaking change | Non-breaking |
+| Complexity | Higher | Lower |
+
+---
+
+### Include MCP Server Instructions Into Agent Instructions
+
+MCP server instructions may contain the `skill://` references the model needs, so we want to surface them in the agent's instructions. But they can also carry system prompts or behavioral directives irrelevant to the agent, polluting context - so inclusion is **opt-in** via the `IncludeServerInstructions` option:
+
+```csharp
+public sealed class AgentMcpSkillsSourceOptions
+{
+    // When true, the MCP server's instructions are injected into the agent instructions. Off by default.
+    public bool IncludeServerInstructions { get; set; }
+}
+
+builder.UseMcpSkills(mcpClient, options => options.IncludeServerInstructions = true);
+```
+
+When enabled, the instructions travel alongside the discovered skills on `AgentSkillsResult`:
+
+```csharp
+public class AgentSkillsResult
+{
+    // The skills discovered from the source.
+    public IList<AgentSkill> Skills { get; }
+
+    // The MCP server instructions, when IncludeServerInstructions is enabled; otherwise null.
+    public string? Instructions { get; }
+}
+```
+
+The `AgentSkillsProvider` then appends them to its own skill-usage guidance when building the agent's instructions:
+
+```csharp
+var result = await source.GetSkillsAsync(cancellationToken);
+
+var instructions = DefaultSkillsInstructionPrompt;
+if (!string.IsNullOrWhiteSpace(result.Instructions))
+{
+    // Combine the provider's skill-usage guidance with the server instructions.
+    instructions += Environment.NewLine + result.Instructions;
+}
+```
+
+### Enabling Direct Skill References
+
+Following direct `skill://` references is **disabled by default** and activated via an option. When enabled, the provider advertises the read function to the model, and the source injects the `[Origin: ...]` marker into all content provided by the MCP server that contains `skill://` references. When disabled, no function is advertised and no marker is injected.
+
+```csharp
+public sealed class AgentMcpSkillsSourceOptions
+{
+    public bool EnableDirectReferences { get; set; }
+}
+
+builder.UseMcpSkills(mcpClient, options => options.EnableDirectReferences = true);
+```
+
+## Decision Outcome
+
+### Template Variable Resolution: Callback vs Decorator (Part 1)
+
+**Postponed.** Deferring this decision until:
+
+- We have a concrete list of scenarios that require template variable resolution.
+- The skills-over-MCP spec is released (it is still a draft, so the design may change).
+- There is a strong signal of demand from users or the ecosystem.
+
+### Function for Reading Direct Skill References (Part 2)
+
+**Postponed.** Leaning toward **Option 2 - dedicated `read_skill_uri` function alongside existing ones** (purely additive, and each function can have its own approval gate for granular per-operation approval), but deferring the decision until:
+
+- The skills-over-MCP spec is released (it is still a draft, so the design may change).
+- There is a strong signal of demand from users or the ecosystem.
+
+### Read-by-URI Capability: Interface vs Base Class (Part 2)
+
+**Postponed.** Leaning toward **Option 2 - virtual methods on `AgentSkillsSource`** (non-breaking, lower complexity, and a natural fit with the existing base class hierarchy), but deferring the decision until:
+
+- The skills-over-MCP spec is released (it is still a draft, so the design may change).
+- There is a strong signal of demand from users or the ecosystem.
+
+The method naming (`SupportsReadByUri`, `CanReadByUri`, `ReadByUriAsync`) should also be abstracted a little more before adoption, so the same members can be reused when a similar direct-reference concept is needed for other skill types (e.g. file skills).
+
+## References
+
+- [SEP-2640: Skills Extension](https://github.com/modelcontextprotocol/modelcontextprotocol/pull/2640) - Draft proposal
+- [SEP-2640 Implementation Guidelines: Model-Driven Resource Loading](https://github.com/modelcontextprotocol/experimental-ext-skills/blob/main/docs/sep-draft-skills-extension.md#hosts-model-driven-resource-loading)
+- [MCP Completion API](https://modelcontextprotocol.io/specification/2025-11-25/server/utilities/completion) - Used for template variable resolution
+- [MCP Resource Templates](https://modelcontextprotocol.io/specification/2025-11-25/server/resources#resource-templates)
+- [Skills Over MCP Working Group](https://github.com/modelcontextprotocol/experimental-ext-skills)
+- [Open Question #4: Multi-server skill dependencies](https://github.com/modelcontextprotocol/experimental-ext-skills/issues/39)
+- [Anthropic Agent Skills - Overview](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/overview) - Prior art: single skill entrypoint + generic file reads
+- [Anthropic Agent Skills in the SDK](https://code.claude.com/docs/en/agent-sdk/skills) - The `Skill` tool exposed to the model

docs/decisions/0029-python-agent-session-identity.md

@@ -0,0 +1,356 @@
+---
+status: accepted
+contact: eavanvalkenburg
+date: 2026-06-19
+deciders: eavanvalkenburg, moonbox3, TaoChenOSU, chetantoshnival
+consulted: westey-m
+informed:
+---
+
+# Python identity lifetimes for sessions, tasks, and continuation
+
+## Context and Problem Statement
+
+Python `AgentSession` currently carries a local `session_id`, an optional opaque service continuation
+`service_session_id`, and provider state. `service_session_id` is any service-owned value that lets that service continue
+a conversation, session, or thread; chat clients happen to map it through the abstract `conversation_id` ChatOption, but
+other agent types can use it differently. It is not a generic correlation field, and generic correlation should not
+require parsing or understanding that opaque service-owned value.
+
+The related issues mix values with different lifetimes:
+
+- **Session / conversation identity**: values that group a multi-turn interaction. Examples: A2A `context_id`, OpenAI
+  Responses `conversation` (`conv_*`) or response-chain continuation (`previous_response_id`).
+- **Task identity**: values that identify a protocol task and may affect future protocol calls. Example: A2A `task_id`.
+- **Message / response identity**: values that identify an output message or response. Examples: A2A `message_id` /
+  `artifact_id`, OpenAI Responses response id (`resp_*`).
+- **Continuation token**: a framework resume payload for in-progress work. It may contain the same underlying value as a
+  protocol id, such as A2A `task_id`, but it only exists when there is an unfinished operation to resume.
+
+These values should not automatically live in the same object just because they all help "continue" something. A value
+belongs in `AgentSession` only when it is needed to continue future calls across turns. A value that identifies one
+result belongs on the response or message. A value that resumes in-progress work belongs in a `ContinuationToken`.
+
+An `AgentSession` created for one agent is not expected to be guaranteed to work against another agent. When a session is
+used with an incompatible agent, protocol, or service, the framework should still help users understand what is wrong as
+early as possible, preferably before calling out to the remote service.
+
+For #4673, native conversation identity propagation should be based on `AgentSession` where the value is durable session
+state. For #4893, A2A `context_id` and `task_id` need a coherent Agent Framework mapping.
+
+AG-UI is out of scope for the decision. Its `thread_id` already maps to `AgentSession.session_id` in the normal wrapper
+path, and `run_id` is wrapper-owned event correlation. If AG-UI run correlation needs framework telemetry integration
+later, that should be handled as a run-context/telemetry design, not as session identity.
+
+### Concrete gap example
+
+At the protocol level, the durable continuation payload shapes are different:
+
+```json
+// A2A: future calls may need multiple durable protocol fields
+{
+  "context_id": "ctx_123",
+  "task_id": "task_789",
+  "task_state": "input_required"
+}
+```
+
+```json
+// OpenAI Responses: future calls usually need one continuation value
+{
+  "previous_response_id": "resp_abc123"
+}
+```
+
+The gap is that A2A continuation state is multi-field while OpenAI continuation is
+typically single-field.
+
+## Current implementation notes
+
+- A2A currently has `A2AAgentSession`, but `A2AAgent.create_session(...)` does not automatically return it.
+- A2A currently mirrors `context_id` into `service_session_id`; that is current behavior, not necessarily the target
+  abstraction.
+- A2A `task_id` is not just cosmetic correlation. It is used for `task_id` when a task is `INPUT_REQUIRED`, for
+  `reference_task_ids` when refining a previous task, and inside `A2AContinuationToken` for in-progress tasks.
+- `RawAgent._prepare_run_context(...)` currently forwards `active_session.service_session_id` as chat `conversation_id`,
+  so any non-string or formatted value affects existing chat-client paths.
+- `OpenAIChatClient` maps chat options `conversation_id` to the Responses API as `previous_response_id` for `resp_*`,
+  `conversation` for `conv_*`, and defaults unrecognized strings to `previous_response_id`. When `store` is not `False`,
+  it returns `response.conversation.id` when available, otherwise `response.id`, as the next service continuation value.
+- For Responses API, the response id (`resp_*`) is also the response/message identity surfaced as
+  `ChatResponse.response_id`; when used for continuation on the next request, it becomes the `previous_response_id`
+  value.
+- Python A2A has not been released as stable yet, so its session factory or session shape can still be adjusted before
+  release.
+
+## Decision Drivers
+
+- Preserve `AgentSession.session_id` as the local/client conversation identity.
+- Preserve `AgentSession.service_session_id` as an opaque service-owned continuation handle.
+- Keep `AgentSession` for durable state needed across turns, not per-run bookkeeping.
+- Store values needed by future calls in durable session state; keep values that only resume in-progress work in
+  `ContinuationToken`.
+- Fix the current confusion where session, task, response, and continuation values can be treated as interchangeable
+  because they all participate in "continuing" something.
+- Make the implementation following this ADR preserve the lifetime split clearly: future-call state, in-progress resume
+  tokens, response/message ids, and protocol event correlation must not be silently mixed.
+- Expose durable continuation state in a typed way when future calls depend on it.
+- Let telemetry correlate runs without parsing opaque service continuation handles.
+- Reuse existing run/context surfaces before introducing a new identity abstraction.
+- Keep MCP and other remote tool boundaries safe: framework identity must not be forwarded to remote tools unless an
+  existing explicit opt-in mechanism says so.
+- Keep existing `AgentSession.to_dict()` / `from_dict()` migration and compatibility straightforward.
+- Stay close to .NET where there is already behavior to match, especially A2A's `ContextId`, `TaskId`, and `TaskState`.
+- Detect incompatible session identity shapes as early as practical, preferably before a remote service call.
+
+## Non-goals
+
+- Do not design a provider-agnostic conversation creation API here. That is tracked separately in #6622.
+- Do not make `service_session_id` a generic telemetry or run-correlation field.
+- Do not introduce a new identity object if existing run/context objects can carry the selected per-run correlation value.
+- Do not make a session from one agent guaranteed to work against another agent.
+- Do not optimize the public `agent.run(...)` API for protocol-wrapper internals.
+
+## Remaining question: durable shape for additional continuation state
+
+- Option A: Use protocol-specific `AgentSession` subclasses.
+- Option B: Extend `service_session_id` with richer service-owned values.
+- Option C: Add a dedicated dict for additional session details.
+- Option D: Store additional durable state inside `AgentSession.state`.
+
+### Option A: Use protocol-specific `AgentSession` subclasses
+
+Each protocol or agent type that needs additional durable state keeps a specialized `AgentSession` subclass. For A2A,
+that means keeping `A2AAgentSession` for A2A-specific durable state and changing `A2AAgent.create_session(...)` to return
+that type.
+
+Example:
+
+```python
+# First call returns a task that future A2A messages may need to reference.
+session = await a2a_agent.create_session()
+
+response = await a2a_agent.run(
+    message,
+    session=session,
+)
+
+# A2AAgent updates durable A2A protocol state from the returned task/status payload.
+# The user does not set these manually.
+assert isinstance(session, A2AAgentSession)
+assert session.task_id is not None
+assert session.task_state is not None
+
+# Later call reuses the durable A2A session state. A2AAgent decides whether to send task_id
+# for INPUT_REQUIRED or reference_task_ids for task refinement.
+next_response = await a2a_agent.run(
+    next_message,
+    session=session,
+)
+```
+
+- Good, because protocol-specific state stays in a protocol-specific type.
+- Good, because it aligns with .NET A2A's `A2AAgentSession` shape.
+- Good, because Python A2A can still make this pre-release session factory adjustment.
+- Good, because `task_state` does not get promoted to a base `AgentSession` concept.
+- Bad, because generic consumers cannot read protocol-specific state without knowing about the subclass or a helper API.
+- Bad, because it depends on each subclass consistently setting shared session fields such as `service_session_id` where
+  those are part of the shared abstraction.
+
+### Option B: Extend `service_session_id` with richer service-owned values
+
+Keep the common `service_session_id` case as a plain string. When an agent/service needs more than one service-owned
+continuation value, allow `service_session_id` to be a typed structured value, such as a `TypedDict`. The main session ID
+used for `gen_ai.conversation.id` should still be extracted by the owning agent, not inferred by generic telemetry code.
+
+Examples:
+
+```python
+simple_session = AgentSession(
+    service_session_id="resp_123",
+)
+
+structured_session = AgentSession(
+    service_session_id=A2AServiceSessionId(
+        context_id="ctx_123",
+        task_id="task_789",
+        task_state=TaskState.TASK_STATE_WORKING,
+    ),
+)
+```
+
+- Good, because the common case remains a plain string and stays simple.
+- Good, because richer service-owned continuation state stays under the existing continuation property.
+- Good, because a structured value can make framework-side validation possible before a value is sent back to a service.
+- Good, because A2A can keep `context_id`, `task_id`, and `task_state` together as the service/protocol-owned continuation
+  value without adding A2A fields to base `AgentSession`.
+- Neutral, because telemetry needs an agent-owned extractor to pick the `gen_ai.conversation.id` value from either a
+  string or structured `service_session_id`.
+- Neutral, because Python A2A would need a pre-release adjustment to stop relying on `A2AAgentSession` for these fields.
+- Bad, because changing the `service_session_id` type is a compatibility risk for users, providers, serialization, and
+  tests.
+- Bad, because every path that sends `service_session_id` back to a service must consistently extract/adapt the
+  service-owned continuation component.
+
+### Option C: Add a dedicated dict for additional session details
+
+Keep `service_session_id` as the primary opaque service-owned continuation handle, and add a separate dictionary for
+additional durable protocol/service values that need to travel with the session.
+
+Example:
+
+```python
+session = AgentSession(
+    service_session_id="ctx_123",
+    session_details={
+        "task_id": "task_456",
+        "task_state": TaskState.TASK_STATE_WORKING,
+    },
+)
+```
+
+- Good, because the main service continuation handle stays a plain `service_session_id` string.
+- Good, because extra state has an explicit home and does not overload `service_session_id`.
+- Good, because generic consumers can look in one documented place for additional session-scoped values.
+- Neutral, because helper APIs can hide the raw dictionary access.
+- Bad, because this still introduces string-keyed state unless the dict values are wrapped by typed helpers.
+- Bad, because it adds another public session field that needs serialization, naming, and compatibility rules.
+- Bad, because generic consumers still need to understand the shape or use helpers for the selected agent/session type.
+
+### Option D: Store additional durable state inside `AgentSession.state`
+
+Keep base `AgentSession` unchanged and store additional durable continuation/protocol state under namespaced keys in
+`session.state`.
+
+Example:
+
+```python
+session = AgentSession(session_id="ctx_123")
+
+session.state["a2a"] = {
+    "task_id": "task_456",
+    "task_state": TaskState.TASK_STATE_WORKING,
+}
+```
+
+- Good, because it avoids new public fields and avoids a subclass requirement.
+- Good, because `AgentSession.state` already exists for provider/session state.
+- Neutral, because helper APIs can hide the raw dictionary access.
+- Bad, because stringly typed state is easier to corrupt and harder to validate.
+- Bad, because generic consumers need helper APIs anyway; directly reading nested dictionaries is not a good abstraction.
+- Bad, because users may accidentally overwrite or persist invalid protocol state.
+
+## Decision
+
+Chosen decision criteria for the future: **split identity by lifecycle**.
+
+When a protocol emits an id/token, place it by answering "what lifecycle does this value serve?":
+
+- **Future-call continuation state** -> durable session state. Examples: A2A `context_id` + `task_id` + `task_state`;
+  OpenAI Responses `previous_response_id`/`conversation`.
+- **Single-result identity** -> response/message object only. Examples: OpenAI `resp_*`, A2A `message_id`,
+  A2A `artifact_id`.
+- **Resume unfinished work** -> `ContinuationToken` only. Example: a token carrying in-progress task resume data.
+- **Run-start-only request fields** -> run method arguments/options, not durable session state. Example: A2A
+  `reference_task_ids` for a specific follow-up/refinement request.
+- **Per-run correlation/telemetry** -> protocol wrapper or run context, not `AgentSession`. Example: wrapper-managed
+  `run_id` used only for tracing/events.
+
+Durable-state option decision: **Option B: Extend `service_session_id` with richer service-owned values**.
+This does **not** add a new top-level identity abstraction; it keeps continuation identity under
+`service_session_id` and keeps run correlation in existing run/telemetry context.
+The immediate implementation gap is mainly in A2A mapping clarity, but the lifecycle split applies
+consistently across providers.
+
+To support telemetry, `BaseAgent` should expose a method that accepts an `AgentSession | None` and returns the value to
+use for `gen_ai.conversation.id`. The default implementation should return `session.service_session_id` when it is a
+string. Agents that use a structured `service_session_id`, such as `A2AAgent`, should override that method and return the
+appropriate primary session/context value.
+
+## Appendix: A2A `task_id` and `reference_task_ids` implementation check
+
+The A2A protocol distinguishes a message's `task_id` from `reference_task_ids`:
+
+- `task_id` associates the message with a specific task.
+- `reference_task_ids` provides additional task context, for example when a new task refines or follows up on the result
+  of a previous task.
+
+The protocol does not appear to prescribe that `task_id` and `reference_task_ids` are mutually exclusive. If both are
+present, the natural reading is that the message is associated with one task while also referencing other tasks for
+context. The serving agent decides how to interpret that context.
+
+The Python implementation should check and likely adjust the current behavior:
+
+- `task_id` should be updated by the current run when the remote A2A service returns a task/status payload.
+- `task_id` should remain durable A2A session state when needed for future calls, for example when a task is
+  `INPUT_REQUIRED`.
+- `reference_task_ids` should be a run parameter / caller intent for the current request, not implicit durable session
+  continuation state.
+- A follow-up/refinement request should pass explicit `reference_task_ids` when it wants to reference previous tasks.
+- If both session `task_id` and run `reference_task_ids` are present, the wrapper should preserve the protocol
+  distinction rather than treating one as a replacement for the other.
+- If no `reference_task_ids` are supplied, the wrapper should not automatically infer them from the last session task
+  unless we deliberately keep that convenience for compatibility.
+
+## Appendix: implementation notes for Option B
+
+The exact names are implementation details, but the shape should be:
+
+```python
+class A2AServiceSessionId(TypedDict):
+    context_id: str
+    task_id: str | None
+    task_state: TaskState | None
+
+
+class AgentSession:
+    def __init__(
+        self,
+        *,
+        session_id: str | None = None,
+        service_session_id: str | ServiceSessionId | None = None,
+    ) -> None:
+        ...
+
+
+class BaseAgent:
+    def _get_otel_conversation_id(self, session: AgentSession | None) -> str | None:
+        service_session_id = session.service_session_id if session else None
+        return service_session_id if isinstance(service_session_id, str) else None
+
+
+class A2AAgent(BaseAgent):
+    def _get_otel_conversation_id(self, session: AgentSession | None) -> str | None:
+        service_session_id = session.service_session_id if session else None
+        if isinstance(service_session_id, Mapping):
+            return service_session_id.get("context_id")
+        return service_session_id if isinstance(service_session_id, str) else None
+
+
+class AgentTelemetryLayer:
+    def _trace_agent_invocation(...):
+        attributes = _get_span_attributes(
+            ...,
+            thread_id=self._get_otel_conversation_id(session),
+            ...,
+        )
+```
+
+This keeps the OpenTelemetry extraction decision with the agent that owns the service continuation shape. Generic OTel
+code should not parse structured `service_session_id` values directly.
+
+`AgentSession` must also be updated so `service_session_id` can store either the current string value or a structured
+service-owned value. Serialization must preserve both shapes, and existing serialized sessions with string
+`service_session_id` must continue to round-trip unchanged.
+
+## More Information
+
+Related work and issues:
+
+- #4673: native conversation ID propagation.
+- #4893: align A2A protocol concepts with Agent Framework session/continuation concepts.
+- #2931: Foundry-specific conversation creation helper, split into a separate Python PR.
+- #6622: broader provider-agnostic conversation creation API discussion requiring .NET sync.
+- [ADR-0015](0015-agent-run-context.md): AgentRunContext for Agent Run.
+- [ADR-0018](0018-agentthread-serialization.md): AgentSession serialization.
+- [ADR-0026](0026-hosted-session-identity-context.md): hosted session identity context.

docs/decisions/0030-hosted-platform-context-agentserver-2.0.md

@@ -0,0 +1,84 @@
+---
+status: accepted
+contact: rogerbarreto
+date: 2026-06-29
+deciders: rogerbarreto
+consulted: []
+informed: []
+---
+
+# Hosted platform context (user id + call id) for Foundry Hosting on AgentServer 2.0
+
+Supersedes [ADR-0026](0026-hosted-session-identity-context.md).
+
+## Context and Problem Statement
+
+[ADR-0026](0026-hosted-session-identity-context.md) sourced the hosted-agent end-user identity from `ResponseContext.Isolation` (an `IsolationContext` typed `UserIsolationKey` / `ChatIsolationKey`), injected by the platform as the `x-agent-user-isolation-key` and `x-agent-chat-isolation-key` headers.
+
+`Azure.AI.AgentServer.*` 2.0.0 (responses protocol `2.0.0`) removes that surface. `ResponseContext.Isolation` is gone; the platform now exposes `ResponseContext.PlatformContext` (a `PlatformContext` typed `UserIdKey` and `CallId`), populated from the `x-agent-user-id` and `x-agent-foundry-call-id` headers. The chat isolation key no longer exists, and a new per-request **call id** is introduced that first-party Foundry services (the toolbox proxy in particular) require on outbound calls to resolve the server-side-stored caller context. The hosting layer in `Microsoft.Agents.AI.Foundry.Hosting` had to migrate to this contract without changing the public shape that samples and providers depend on.
+
+## Decision Drivers
+
+- Track the breaking `Azure.AI.AgentServer.*` 2.0.0 surface (`PlatformContext` replacing `Isolation`) while keeping the same per-user partitioning guarantees from ADR-0026.
+- Keep the change **internal**: existing hosted samples and `AIContextProvider`s must not need code changes. `session.GetHostedContext().UserId`, `HostedSessionIsolationKeyProvider`, and `AddFoundryResponses` stay source-compatible.
+- Forward the new per-request call id verbatim on outbound calls to Foundry first-party services so per-user toolbox OAuth consent and other server-side caller-context lookups keep working.
+- Remain resilient on protocol `1.0.0`: when only the legacy headers are present, `UserIdKey` still resolves and `CallId` is simply absent.
+- Preserve the strict-resume tamper defense from ADR-0026 with identity now reduced to user only.
+
+## Considered Options
+
+For the identity source:
+
+1. **Map `ResponseContext.PlatformContext.UserIdKey`** into the existing `HostedSessionContext` (user only), keeping ADR-0026's storage shape and read accessor.
+2. Keep a `ChatId` slot on `HostedSessionContext` for backward source-compatibility, populated from `CallId` or left null.
+
+For the call id propagation:
+
+A. **A request-scoped ambient (`HostedCallContext`, an `AsyncLocal<string?>`)** set by the handler and re-applied before each egress point, read by the outbound delegating handler.
+B. Thread the call id through every method signature down to the toolbox bearer handler.
+
+For session keying (previously implied by the conversation/chat pairing):
+
+I. **`HostedConversationKey`** resolving a stable partition from `conversation_id ?? partition(previous_response_id) ?? partition(responseId)`.
+II. Continue keying on the container session id (`FOUNDRY_AGENT_SESSION_ID`).
+
+## Decision Outcome
+
+Chosen: **Option 1** for identity, **Option A** for call id, **Option I** for session keying.
+
+Rationale:
+
+- **`ChatId` dropped (Option 2 rejected).** The platform no longer supplies a chat key; carrying a synthetic one would invent identity the trust boundary does not provide. `HostedSessionContext` becomes user-only (`HostedSessionContext(string userId)` / `UserId`), and the strict-resume check validates `UserId` alone. The corresponding `HostedFoundryMemoryProviderScopes` values `PerChat` and `PerUserAndChat` are removed; `PerUser` is retained.
+- **Ambient call id (Option B rejected).** Writing `HostedCallContext.CallId` inside the streaming `async IAsyncEnumerable` iterator is reverted across each `yield`, so a single up-front assignment is lost before the toolbox/MCP egress runs. The handler therefore captures `context.PlatformContext?.CallId` once and **re-applies it immediately before each egress point**; `FoundryToolboxBearerTokenHandler` forwards it as `x-agent-foundry-call-id`. The ambient is request-scoped and never leaks into the caller's execution context (guarded by a unit test).
+- **`HostedConversationKey` (Option II rejected).** One container serves many conversations for its lifetime, so the container session id cannot key per-conversation state. The partition key is derived from the conversation/`previous_response_id`/minted response id instead.
+
+Implementation summary in `Microsoft.Agents.AI.Foundry.Hosting`:
+
+| Type | Visibility | Change vs ADR-0026 |
+|---|---|---|
+| `HostedSessionContext` | public sealed | Now user-only (`UserId`); `ChatId` removed. |
+| `PlatformHostedSessionIsolationKeyProvider` | internal sealed | Maps `context.PlatformContext.UserIdKey` (was `context.Isolation.UserIsolationKey` / `ChatIsolationKey`). |
+| `HostedCallContext` | internal static | New. Request-scoped `AsyncLocal<string?>` holding the `x-agent-foundry-call-id` value. |
+| `HostedConversationKey` | internal | New. Resolves the per-conversation partition key. |
+| `FoundryToolboxBearerTokenHandler` | internal | Now also forwards `x-agent-foundry-call-id` outbound. |
+| `HostedFoundryMemoryProviderScopes` | public | `PerChat` / `PerUserAndChat` removed; `PerUser` kept. |
+
+Package manifests bump the responses container protocol to `2.0.0` (invocations stays `1.0.0`).
+
+## Consequences
+
+Positive:
+
+- Per-user memory partitioning and the strict-resume tamper defense from ADR-0026 are preserved with no public API churn for samples or providers.
+- Per-user toolbox OAuth consent and other server-side caller-context lookups keep working because the per-request call id is forwarded on egress.
+- Works unchanged on protocol `1.0.0` (no call id) and `2.0.0`.
+
+Negative:
+
+- `HostedSessionContext.ChatId` and the `PerChat` / `PerUserAndChat` memory scopes are removed; any out-of-tree consumer that referenced them must move to user-scoped partitioning.
+- The call id must be re-applied before every egress point because of the async-iterator `AsyncLocal` revert; a missed re-apply silently drops the header. This is covered by unit tests.
+
+## Out of scope
+
+- HMAC tamper signatures over the persisted context remain unimplemented; equality comparison against `ResponseContext.PlatformContext` on every request is sufficient because the platform sets the header at the trust boundary.
+- The per-request `User` field on `CreateResponse` is still intentionally not consumed.

docs/decisions/0031-hosted-per-user-session-storage-isolation.md

@@ -0,0 +1,119 @@
+---
+status: accepted
+contact: rogerbarreto
+date: 2026-06-30
+deciders: rogerbarreto
+consulted: []
+informed: []
+---
+
+# Per-agent and per-user session-storage isolation for Foundry Hosting
+
+Builds on [ADR-0030](0030-hosted-platform-context-agentserver-2.0.md).
+
+## Context and Problem Statement
+
+A Foundry hosted container can serve many end users (and, in .NET, many agents) over its lifetime. The
+`AgentSessionStore` persists each turn's `AgentSession` (which for a workflow agent carries the workflow
+checkpoint, and which also carries the tool-approval mapping via `ToolApprovalIdMap` in the session state
+bag). [ADR-0030](0030-hosted-platform-context-agentserver-2.0.md) protected cross-user access only through
+the strict-resume identity check (a 403 when the persisted `HostedSessionContext.UserId` does not match the
+live request). The persisted artifacts themselves were keyed by `conversationId` (+ agent name), not
+physically partitioned per user, so a forged `conversation_id` would still resolve to another user's file
+path before the identity check rejected it.
+
+The Python hosting package added physical per-user partitioning (`<root>/<user_id>/<context_id>`) plus a
+reject-style path-traversal guard. We want .NET to provide the same defense-in-depth, adapted to the .NET
+hosting model.
+
+## Decision Drivers
+
+- Defense in depth: a forged/guessed id must not even resolve to another tenant's storage path, independent
+  of the identity check.
+- Multi-agent hosting: a single .NET container hosts multiple agents resolved from keyed DI, so the layout
+  must isolate per agent as well as per user (Python hosts a single agent and needs no agent layer).
+- Path-traversal safety (CWE-22) for the untrusted, platform-injected user id.
+- Back-compat for local development (no `x-agent-user-id` header) and for direct/non-hosted store use.
+- Keep the change contained and avoid the async-iterator `AsyncLocal` revert hazard from ADR-0030.
+
+## Considered Options
+
+- **Path partition inside `FileSystemAgentSessionStore`**, threading the user id explicitly through the
+  `AgentSessionStore` API, with self-describing prefixed segments.
+- A delegating store that prefixes the conversation id with the user id (the
+  `IsolationKeyScopedAgentSessionStore` pattern from `Microsoft.Agents.AI.Hosting`). Rejected: still needs the
+  user id on the read path and yields a flat key rather than nested per-tenant directories.
+- An `AsyncLocal<string?>` user-context set by the handler. Rejected: the session is saved in the handler's
+  `finally` after the streaming `yield`s, where an `AsyncLocal` set up front is reverted (the same hazard
+  that forced explicit call-id re-application in ADR-0030). Explicit threading is safer and clearer.
+- A separate per-user approval store (as in Python). Rejected as unnecessary: see below.
+
+## Decision Outcome
+
+Path layout with self-describing, prefixed segments; user id threaded explicitly:
+
+    {root}/ a-{agentName} / u-{userId} / c-{contextId}.json
+
+- `a-` (agent), `u-` (user), `c-` (context) are constant literals applied to the sanitized/validated value,
+  so a collapsed layout is never ambiguous and a user id can never masquerade as an agent name.
+- `contextId` is `HostedConversationKey.Resolve` (conversation_id, else the partition of
+  previous_response_id, else of the minted response id).
+- The agent and context layers are always present (Foundry always deploys a named agent). The only
+  collapse is the `u-` layer: present when a user id is resolved (Foundry header, or local dev fallback),
+  absent for raw local runs with no header (`{root}/a-{agent}/c-{conv}.json`). There is no user-only or
+  no-agent layout.
+
+Other elements:
+
+- `string? userId` was added as a **required** parameter (no default) on `AgentSessionStore.GetSessionAsync` /
+  `SaveSessionAsync` (a contained, breaking change to the experimental Foundry abstraction; both in-tree
+  implementations and the two handler call sites were updated). It is required rather than optional so a
+  caller can never silently persist a session unscoped; a genuine no-user caller (local without the header,
+  or a non-hosted direct caller) passes `null` explicitly. `AgentFrameworkResponseHandler` resolves the user
+  id before loading the session.
+- Path-traversal guard: the user id is rejected (not sanitized) when it is not a single safe path segment
+  (path separators, NUL, drive letters, rooted paths, all-dot segments). After building the path, the
+  fully-resolved path is asserted to remain under the storage root.
+- The strict-resume 403 identity check from ADR-0030 is **kept** as the second defense layer (it still
+  catches a session that reaches the wrong partition, e.g. via a non-partitioning custom store or in-process
+  tampering).
+- **No separate approval store.** The tool-approval mapping lives in `ToolApprovalIdMap` ->
+  `AgentSessionStateBag`, which is serialized into the session checkpoint, so partitioning the session path
+  isolates pending approvals per tenant automatically. (Python needs a separate per-user approval store only
+  because it models approvals as a standalone store.)
+
+## Consequences
+
+Positive:
+
+- Cross-tenant isolation is now defense-in-depth: physical per-agent/per-user partitioning plus the identity
+  check. Approvals and workflow checkpoints inherit the partitioning because they ride in the session.
+- Self-describing prefixes make the on-disk layout auditable and collision-free across collapse cases.
+
+Negative:
+
+- Breaking change to the experimental Foundry `AgentSessionStore` API (added `userId`).
+- The on-disk layout and leaf filename change (`<conv>.json` -> `c-<conv>.json`), orphaning sessions written
+  by the ADR-0030 release. Acceptable for an experimental package; a fresh session is created on next use.
+
+## Out of scope
+
+- Encryption at rest and quota enforcement remain platform concerns.
+- Non-Foundry hosting layers can adopt an equivalent scheme independently.
+
+## Update (2026-07-01): local runs no longer fail closed; sample dev provider removed
+
+Superseding the ADR-0026/0030 behavior where a `null` result from `HostedSessionIsolationKeyProvider`
+always became a 500, `AgentFrameworkResponseHandler` now branches on `FoundryEnvironment.IsHosted`:
+
+- **Hosted** (`IsHosted == true`, production): a `null` identity is still a hard error (500). Isolation
+  stays strict; the platform always injects `x-agent-user-id`.
+- **Not hosted** (local `docker run` / `dotnet run`): a `null` identity is tolerated. Per-user isolation
+  is simply not triggered — the handler passes `userId == null` to the store (the documented "no user
+  partition", `{root}/a-{agent}/c-{conv}.json`), stamps no `HostedSessionContext`, and runs no
+  strict-resume check. Contributors can run a hosted image locally with zero extra setup.
+
+Consequently the sample-side `DevTemporaryLocalUserIdProvider` and `AddDevTemporaryLocalContributorSetup`
+were removed. To simulate distinct users locally, send an `x-agent-user-id` request header; the default
+`PlatformHostedSessionIsolationKeyProvider` reads it via `ResponseContext.PlatformContext.UserIdKey`
+(the SDK's `PlatformContext.FromRequest` populates it from the header unconditionally, hosted or not).

docs/decisions/0032-dotnet-hosting-protocol-helpers.md

@@ -0,0 +1,177 @@
+---
+status: accepted
+contact: rogerbarreto
+date: 2026-07-08
+deciders: rogerbarreto
+consulted: eavanvalkenburg
+informed: []
+---
+
+# .NET hosting: OpenAI Responses protocol helpers for app-owned routing
+
+Realizes the helper-first direction of [ADR-0027](0027-hosting-channels.md) for .NET.
+
+## Context and Problem Statement
+
+[ADR-0027](0027-hosting-channels.md) refocused the (Python) hosting design away from a channel
+framework toward **protocol conversion helpers plus optional execution state**: Agent Framework owns
+protocol-native <-> run conversion, while the application owns HTTP routing, authentication,
+middleware, storage, and native SDK calls.
+
+.NET already ships `Microsoft.Agents.AI.Hosting.OpenAI`, a route-owning server that **exposes an
+`AIAgent` (or workflow) as the OpenAI Responses API** (`MapOpenAIResponses` + `IResponsesService`). It
+owns the routes, an in-memory response/conversation store, streaming, and lifecycle. The question is
+what, if anything, .NET must add to satisfy the ADR-0027 boundary.
+
+## Decision Drivers
+
+- Do not reinvent conversion logic that already exists and is battle-tested in `Hosting.OpenAI`.
+- Give applications a way to own their own route/auth/middleware/storage while reusing Agent Framework
+  conversion (the ADR-0027 boundary).
+- Keep the released public surface small.
+- Stay consistent with the existing .NET hosting stack, which deliberately does **not** use the OpenAI
+  SDK Responses types server-side (it hand-rolled its own wire model).
+
+## Considered Options
+
+1. Self-contained new package that reimplements conversion using the OpenAI SDK Responses types
+   (mirrors the Python `agent-framework-hosting-responses` lineage).
+2. New package that reuses `Hosting.OpenAI`'s internal converters (via `InternalsVisibleTo` or by
+   moving the conversion core out).
+3. Thin public helper facade **inside** `Hosting.OpenAI` over the existing internal converters, plus
+   protocol-neutral execution-state holders in `Microsoft.Agents.AI.Hosting`.
+
+### First-principles gap analysis
+
+A capability comparison of the ADR-0027 / PR #6891 helper surface against the existing .NET stack:
+
+| Python helper capability | .NET today | Status |
+| --- | --- | --- |
+| `responses_to_run` | `ResponseInput.GetInputMessages` + `InputMessage.ToChatMessage` + `OpenAIResponsesMapOptions.RunOptionsFactory` | exists, internal |
+| `responses_from_run` | `AgentResponseExtensions.ToResponse` | exists, internal |
+| `responses_from_streaming_run` | `AgentResponseUpdateExtensions.ToStreamingResponseAsync` + `SseJsonResult` (also renders workflow events) | exists, internal, richer |
+| `responses_session_id` | continuity resolved inside `InMemoryResponsesService` | exists, internal, not standalone |
+| `create_response_id` | `IdGenerator` | exists, internal |
+| `AgentState` (target + store, get-or-create, callable/awaitable target) | `AgentSessionStore` (get-or-create + save + serialize + isolation) + DI container (target lifetime + async setup) | create-on-miss lives in the store; per-run instance and deferred/async target come from DI, so no separate holder is needed |
+| `SessionStore` (get/set/delete) | `AgentSessionStore` + `InMemoryAgentSessionStore` | richer; `Delete` added |
+| `WorkflowState` + checkpoint resume | `WorkflowCatalog`/`HostedWorkflowBuilder`; workflow events already render over Responses; `CheckpointManager` is session-keyed | partial; no per-session checkpoint cursor |
+| App owns routing/auth/middleware/storage | `MapOpenAIResponses`/`IResponsesService` own routing + storage | **the one real gap** |
+
+.NET already covers ~90% of the capability, and more richly (its streaming renderer even emits workflow
+events; its session store serializes and supports per-principal isolation, neither of which Python's
+in-memory `SessionStore` does). The single genuine gap is the **ownership model**: every conversion
+primitive is bundled behind the route-owning server, so an application cannot own its own route and
+call just the conversion.
+
+Note on lineage: Python's Responses offering was introduced *as a channel* (PR #6580) and always used
+the `openai` SDK Responses types. .NET's `Hosting.OpenAI` predates and is independent of channels and
+hand-rolled its own server-side wire DTOs (the SDK's Responses types are client-shaped and awkward
+server-side). So Option 1 would both reinvent a working asset and contradict the .NET codebase's own
+precedent.
+
+## Decision Outcome
+
+Chosen option: **3. Thin public helper facade inside `Hosting.OpenAI` plus neutral state holders**,
+because the only real gap is the ownership model, so the work is to *un-bundle* the existing
+converters, not to rebuild them or add a package.
+
+### Public surface
+
+`Microsoft.Agents.AI.Hosting.OpenAI` gains a single public static facade, `OpenAIResponses`, whose
+boundary is `System.Text.Json` (`JsonElement`/streamed events), matching Python's dict boundary and
+keeping the hand-rolled wire DTOs internal:
+
+- `OpenAIResponses.ToAgentRunRequest(JsonElement body)` -> messages + `AgentRunOptions?`.
+- `OpenAIResponses.WriteResponse(AgentRunResponse response, string responseId, string? sessionId = null)`
+  -> a Responses-shaped `JsonElement`.
+- `OpenAIResponses.WriteResponseStreamAsync(IAsyncEnumerable<AgentRunResponseUpdate> updates, string responseId, ...)`
+  -> Responses SSE `data:` frames.
+- `OpenAIResponses.GetSessionId(JsonElement body)` -> `previous_response_id` or `conversation` id, or
+  `null`. Kept **separate** from `ToAgentRunRequest` so the trust boundary is visible: choosing to use
+  a request-derived key is an explicit application decision.
+- `OpenAIResponses.CreateResponseId()` -> a `resp_*` id.
+
+All helpers are side-effect-free and delegate to the existing internal converters. `MapOpenAIResponses`
+public behavior is unchanged; it and the facade share one internal conversion core (an internal
+`ToResponse` overload with an optional originating request is added so the facade can render without a
+request object).
+
+### Optional execution state (neutral package)
+
+`Microsoft.Agents.AI.Hosting` gains:
+
+- `AgentSessionStore.DeleteSessionAsync(...)` (+ `InMemoryAgentSessionStore` implementation and
+  isolation-decorator passthrough): the one missing store operation.
+- No agent-side holder. Applications use `AgentSessionStore` directly: `GetSessionAsync(agent, id)`
+  already creates on miss and returns an independent session instance per call (so concurrent calls fork
+  the same stored state rather than sharing an instance), `SaveSessionAsync(agent, id, session)` persists
+  post-run (including under a newly minted id), and `DeleteSessionAsync(agent, id)` removes it. An earlier
+  draft added a `HostedAgentState` holder, but once create-on-miss lives in the store and the store does no
+  cross-call locking, the holder would only bind the `agent` argument, which is not enough to justify a
+  public type. Any coordination for concurrent runs against the same id is the application's concern.
+  (Unlike Python, whose `SessionStore` is get/set-only and whose `AgentState` therefore owns
+  create-on-miss, .NET's store already owns it.)
+
+  Python's `AgentState` carries two further responsibilities beyond create-on-miss: it accepts a callable
+  or awaitable target so the host can (1) obtain a fresh agent instance per run and (2) defer expensive or
+  asynchronous agent setup while keeping server construction synchronous. In .NET these two concerns are
+  owned by the dependency-injection container, not by a hosting type. Per-run lifetime is expressed by the
+  registration lifetime (`AddScoped`/`AddTransient` yields a fresh `AIAgent` per request or scope, resolved
+  by the framework), and deferred or asynchronous construction is expressed by an async factory registration
+  (for example an `async` factory delegate, `ActivatorUtilities`, or resolving the agent inside the request
+  after any async warm-up), so the route handler resolves an already-built agent from the container. An
+  `AIAgent` is also safe to invoke concurrently (per-turn state lives in `AgentSession`, not the agent), so
+  the "fresh instance per run" motivation does not apply to it the way it does to a workflow. This is the
+  deliberate asymmetry with `HostedWorkflowState` below: a `Workflow` instance is a stateful run engine that
+  cannot be driven by two runners at once, so the factory/`cacheWorkflow` affordance is load-bearing there
+  for correctness, whereas for agents the container already provides both per-run instances and async setup.
+- `HostedWorkflowState`: a thin holder bundling a workflow target with a `CheckpointManager` and an
+  internal `sessionId -> CheckpointInfo` head cursor, exposing `RunOrResumeAsync`. .NET's checkpoint
+  store is already `sessionId`-keyed (unlike Python's workflow-name keying), but `CheckpointInfo` has
+  no ordering, so the holder remembers the head checkpoint per session to resume. On subsequent turns it
+  restores that checkpoint and runs the workflow forward with the new turn's input (mirroring the Python
+  host's restore-then-run semantics), rather than continuing a halted run with no input. When the
+  in-memory cursor misses (new holder / process restart) it reads the session's latest checkpoint from the
+  `CheckpointManager`, so a durable manager resumes across restarts. It accepts either a single workflow
+  instance (which cannot be run by two runners at once, so its turns are processed one at a time) or a
+  workflow factory (`Func<CancellationToken, ValueTask<Workflow>>`). By default the factory builds a fresh
+  instance per run so independent sessions run in parallel; with `cacheWorkflow: true` the factory is invoked
+  once lazily and its result is cached and reused (a deferred, cached target that, like the instance, cannot
+  run concurrent turns). A resume rehydrates an instance from the session's checkpoint in the shared store, so
+  per-run instances still continue the same run; concurrent turns against the same session id remain the
+  application's coordination responsibility.
+
+### Scope
+
+Responses only for v1; the facade is named so a parallel `OpenAIChatCompletions` facade can follow.
+No new package, no OpenAI-SDK-typed reimplementation, no change to `MapOpenAIResponses` public
+behavior.
+
+### Security responsibilities
+
+Consistent with ADR-0027, the application owns the trust boundary. `GetSessionId(...)` returns an
+untrusted candidate key; the application must authenticate the caller and authorize/bind the id before
+using it as an `AgentSessionStore` key or workflow checkpoint session id. Multi-user hosts must scope
+the session store per principal (`IsolationKeyScopedAgentSessionStore`). Helpers stay side-effect-free;
+persistence happens only after the run completes.
+
+## Consequences
+
+Positive:
+
+- Smallest possible surface: the released addition is one facade type plus one thin workflow state
+  holder and one new store method (agents use `AgentSessionStore` directly, no holder).
+- No duplicated conversion; the app-owned-routing path and the route-owning server share one core.
+- `MapOpenAIResponses` users are unaffected.
+
+Negative:
+
+- The facade's `JsonElement` boundary is less strongly typed than the internal DTOs (accepted to keep
+  the wire model internal and mirror Python's dict boundary).
+- Workflow resume relies on an in-memory head cursor by default; durable multi-replica hosts must
+  supply their own cursor persistence.
+
+## More Information
+
+- Parent ADR: [ADR-0027](0027-hosting-channels.md).
+- Spec: `docs/specs/003-dotnet-hosting-protocol-helpers.md`.

docs/decisions/0033-feature-usage-bitmask-user-agent.md

@@ -0,0 +1,642 @@
+---
+status: accepted
+contact: eavanvalkenburg
+date: 2026-07-22
+deciders: eavanvalkenburg, chetantoshniwal
+consulted: TaoChenOSU, moonbox3, peibekwe, rogerbarreto, westey-m
+informed:
+---
+
+# Feature-usage bitmask in the User-Agent
+
+## Context and Problem Statement
+
+We can see which Agent Framework packages are installed and that *some* framework
+call happened (via the existing `agent-framework-python/{version}` User-Agent),
+but we have no usage-based signal about **which features are actually exercised**
+at runtime, nor which are used *together* (e.g. workflows + MCP + Foundry). How
+can we collect a lightweight, privacy-respecting signal of feature usage for the
+traffic we can actually read, without standing up new event pipelines?
+
+The detailed mechanism is in [SPEC-004](../specs/004-feature-usage-telemetry.md);
+the per-language bit tables are in
+[feature-usage-bit-registry.md](../specs/feature-usage-bit-registry.md).
+
+## Decision Drivers
+
+- **Transparency** — openly documented, human-decodable, user-controllable. No
+  hidden or obfuscated telemetry.
+- **First-party scope / no third-party leakage** — emission requires both an
+  explicitly approved client/pipeline family and an approved actual HTTPS origin
+  on every request (including redirects). Credentials or an Azure setting alone
+  never approve a custom gateway/origin.
+- **Live signal** — read the process's observed-feature set *so far* at request
+  send time, rather than freezing it at client construction.
+- **Low cost / few moving parts** — reuse telemetry already in the request path;
+  bounded fixed-width processing; as little machinery as the job needs.
+- **Privacy** — encode only coarse "observed at least once" Boolean feature
+  state, never counts; no identifiers, arguments, prompts, payloads,
+  model/deployment names, endpoints, or customer-defined names.
+- **Use, not presence** — package-level indexes mean a capability reached its
+  first meaningful activation, not that a package was installed/imported or a
+  DI container constructed an unused service.
+- **Versioning discipline** — v1 is a point-in-time decision. Adding bits later is
+  easier than removing or redefining them, so the initial table should lean toward
+  fewer bits and avoid forcing v2 shortly after launch.
+- **Allocation discipline** — each bit represents a stable framework-owned
+  capability with a concrete product/support question and an actual-use mark
+  point; implementation detail and speculative distinctions stay out.
+
+## Considered Options
+
+The options below are grouped by the decisions that matter: the **transport**,
+the **granularity**, and the **registry sharing model**.
+
+### Transport
+
+#### A. User-Agent token, first-party only, per request (chosen)
+
+Stamp a `(feat=...)` comment onto the UA, but only on approved Azure/Foundry
+client pipelines, and re-evaluate it per request.
+
+- Good, reuses telemetry already sent to approved backends we can read.
+- Good, request-time stamping reflects the live mask (not frozen at construction).
+- Good, first-party scoping means no fingerprint leaks to third-party providers.
+- Good, two-factor destination approval (pipeline + actual origin) denies custom
+  `base_url` gateways and strips the token on unapproved redirect hops.
+- Good, maps onto .NET's existing per-request UA pipeline policies unchanged.
+- Neutral, v1 stamps only pipelines the framework creates or can configure
+  through supported public hooks. It does not mutate caller-owned clients or
+  reach into private SDK pipelines.
+- Bad, no signal for traffic that never hits a first-party endpoint (accepted —
+  we couldn't read it anyway).
+
+#### B. User-Agent token on all clients
+
+- Good, simplest to wire (one static header).
+- Bad, sends a deployment fingerprint to OpenAI/Anthropic/AWS/Google logs we
+  cannot read — privacy leak for zero benefit.
+- Bad, baked into static `default_headers`, so it freezes at client construction
+  and reports a near-empty mask.
+
+#### C. OpenTelemetry span/resource attribute
+
+- Good, precise per-call usage; no UA change.
+- Bad (**privacy — the main reason to hold it**), a span attribute broadcasts the
+  feature-combination fingerprint into the user's **general** telemetry pipeline,
+  which is typically exported to third-party APM vendors (Datadog, Honeycomb, …).
+  That re-introduces exactly the fingerprint leakage the first-party-only UA
+  scoping (A) was chosen to avoid — just into a different set of third parties.
+- Bad (secondary), also a cardinality footgun (a growing, combinatorial value
+  must never become a metric dimension).
+- Neutral, for the team's own goal it reaches us only if the user exports to
+  Azure Monitor and we query it.
+- **Deferred, not rejected.** The version prefix lets us add it later **if** the
+  User-Agent path cannot answer a concrete query and there is an acceptable
+  scoped/redacted variant.
+
+#### D. Bespoke usage events
+
+- Good, richest detail and flexibility.
+- Bad, new data flow and cost; larger privacy surface; heavy to build and review;
+  overkill for a coarse "which features" signal.
+
+#### E. Install/import-time signal only (status quo-ish)
+
+- Good, zero new runtime work.
+- Bad, measures installation, not usage; cannot capture feature combinations —
+  does not solve the problem.
+
+### Accumulation scope
+
+#### S1. Process-global, monotonic mask (chosen)
+
+A single mask per process; bits are OR-ed in as features are first used and never
+cleared. The token reflects "what this process has used so far."
+
+- **Binary interpretation:** a set bit means the feature was observed at least
+  once in this process before the request was sent. A bit repeated on later
+  requests is the same Boolean observation, not another feature use. It cannot be
+  summed into invocation, request, agent, user, or tenant counts.
+- Good, fits our **mixed feature lifecycle**: many features are *not* bound to an
+  outbound service request — an agent/workflow may first run or build, a
+  context/history provider may first participate in a session, and a host may
+  start serving before the request that later emits the token. A process-wide
+  mask can carry those activations forward.
+- Good, trivial and cheap: one OR under a lock (Python) / one atomic OR into one
+  of two 64-bit lanes (.NET); no per-request state plumbing.
+- Good, deliberately coarse for privacy: it avoids emitting a sequence of exact
+  per-call feature combinations that could reconstruct a workload's behavioral
+  trace.
+- Neutral, coarser than per-call — early requests carry fewer bits than later
+  ones, and the token says "this process used X", not "this call used X" or "X
+  was used this many times."
+
+For example, at time 1 Agent A can use MCP and a Foundry chat client. At time 2,
+Agent B in the same worker can make a normal Foundry chat call without MCP. The
+time-2 request still carries the MCP bit because MCP was previously observed in
+that process. It does **not** say Agent B used MCP, nor count a second MCP use.
+
+#### S2. Per-request set, reset between calls (botocore's model — rejected)
+
+AWS botocore scopes its `m/` feature codes to a `contextvars` set that is reset
+between requests, giving exact per-call attribution (and it deliberately no-ops
+when called outside a request context to avoid features bleeding across requests).
+See [Prior art](#prior-art).
+
+- Good, exact per-call attribution directly in the User-Agent.
+- Bad, **assumes every feature is exercised inside a single service request** —
+  true for botocore (an SDK natively bound to AWS service calls), but *not* for
+  us. Our features split into request-scoped ones (a chat call, an MCP tool
+  invocation) and decidedly non-request ones (workflow build/start, provider
+  participation, hosting startup). The latter have no service request to attach to, so a
+  per-request set would simply miss them.
+- Bad, needs `contextvars` propagation through every async/threaded path and a
+  reset discipline, plus enable/disable calls around every scoped operation; the
+  bleed-guard botocore documents is the warning sign.
+- Bad, creates a more detailed per-call behavioral trace, increasing the privacy
+  sensitivity and review burden compared with a coarse process-lifetime Boolean.
+- Note, per-call attribution for the request-scoped subset is better served by
+  the deferred OTel span path (option C) than by reshaping the UA token.
+
+### Granularity
+
+The mechanism can support several granularities. The remaining decision before
+implementation is how detailed v1 should be. The estimates below are
+intentionally rough; v1 uses a fixed 128-bit bound to leave useful headroom
+without making the registry unbounded.
+
+#### F0. Package-level bits
+
+One bit per package, set on first use of a package-owned public API, client,
+provider, or tool. It is **not** set on install, import, or assembly load.
+
+Examples that get bits:
+
+- `agent-framework-core` when `Agent`, `AgentSession`, `Workflow`, etc. is used.
+- `agent-framework-tools` when a `LocalShellTool` or `DockerShellTool` first
+  executes/probes its shell capability.
+- `agent-framework-foundry` when a `FoundryChatClient`, `FoundryAgent`, etc.
+  performs its first Foundry operation.
+- `agent-framework-openai` when `OpenAIChatClient`,
+  `OpenAIEmbeddingClient`, etc. performs its first provider operation.
+- `agent-framework-azure-ai-search` when `AzureAISearchContextProvider` is used.
+- `agent-framework-azure-cosmos` when `CosmosHistoryProvider` is used.
+- `agent-framework-redis` when `RedisContextProvider` or `RedisHistoryProvider`
+  is used.
+
+Examples that do **not** get separate bits: merely installed dependencies;
+imports or DI construction with no activation; `Agent` vs `AgentSession` vs
+`InMemoryHistoryProvider`; `FunctionTool` vs `MCPStdioTool` vs `LocalShellTool`
+vs `DockerShellTool`; `FoundryChatClient` vs `FoundryAgent`; `OpenAIChatClient`
+vs `OpenAIEmbeddingClient`.
+
+Rough estimate: Python ~25-35 bits; .NET ~15-25 bits.
+
+- Good, lowest specificity and simplest registry.
+- Good, clearly measures usage rather than dependency inventory if bits are set
+  only at package-owned public API/client/provider/tool use sites.
+- Bad, does not answer which major capability within a package is used.
+
+#### F1. Package + major capability bits
+
+Package bits plus selected major capabilities that are product-distinct and stable
+across implementations.
+
+Examples that get bits:
+
+- `agent-framework-core` plus `Agent`.
+- `AgentSession` plus `InMemoryHistoryProvider` / `FileHistoryProvider` as one
+  history capability.
+- `Workflow` / `FunctionalWorkflow` as one workflow capability.
+- `FunctionTool`; MCP transports as one MCP capability; shell tools as one shell
+  capability.
+- Skills provider plus stable source types: file, in-memory/programmatic, and
+  MCP-backed skills (with .NET inline/class skill distinctions).
+- Foundry chat/agent/embedding capabilities; OpenAI chat/embedding capabilities.
+
+Examples that do **not** get separate bits: `InMemoryHistoryProvider` vs
+`FileHistoryProvider`; `WorkflowBuilder`, `AgentExecutor`, `FunctionExecutor`, or
+`FanOutEdgeGroup`; `MCPStdioTool` vs `MCPStreamableHTTPTool` vs
+`MCPWebsocketTool`; `LocalShellTool` vs `DockerShellTool` vs
+`ShellEnvironmentProvider` vs `ShellPolicy`; `OpenAIChatClient` vs
+`OpenAIChatCompletionClient`; skill-source decorators such as caching, filtering,
+deduplication, and aggregation.
+
+Rough estimate: Python ~60-70 indexes; .NET ~45-55 indexes. The current candidate
+registry is at 63 Python / 52 .NET assigned indexes.
+
+- Good, likely answers the first product adoption questions while staying compact.
+- Good, fits comfortably within 128 bits while leaving room for additive package
+  and feature growth.
+- Neutral, some provider internals remain collapsed until a later additive bit is
+  justified.
+
+#### F2. Public construct / concrete type bits
+
+One bit per public construct that users intentionally instantiate or configure.
+
+Examples that get bits:
+
+- `Agent`, `AgentSession`, `InMemoryHistoryProvider`, `FileHistoryProvider`.
+- `Workflow`, `WorkflowBuilder`, `FunctionalWorkflow`.
+- `FunctionTool`, `MCPStdioTool`, `MCPStreamableHTTPTool`, `MCPWebsocketTool`.
+- `LocalShellTool`, `DockerShellTool`, `ShellEnvironmentProvider`, `ShellPolicy`.
+- `FoundryChatClient`, `FoundryAgent`, `OpenAIChatClient`,
+  `OpenAIChatCompletionClient`, `OpenAIEmbeddingClient`.
+
+Examples that do **not** get separate bits: `Agent.run` vs
+`Agent.run_streamed`; workflow edge/executor internals such as `AgentExecutor`,
+`FunctionExecutor`, or `FanOutEdgeGroup`; `LocalShellTool` persistent vs
+stateless mode; `ShellPolicy` allowlist vs denylist configuration; `FunctionTool`
+approval mode or result parser choices.
+
+Rough estimate: Python ~70-100 bits; .NET ~55-80 bits.
+
+- Good, concrete and directly tied to public API use.
+- Neutral, fits within 128 bits at the current estimate, but consumes much of the
+  deliberate growth reserve.
+- Bad, adds many call sites and more fingerprint specificity for v1.
+
+#### F3. Construct subtype / configuration bits
+
+Split important constructs by mode, transport, storage, or workflow primitive
+when that distinction matters.
+
+Examples that get bits:
+
+- `InMemoryHistoryProvider` and `FileHistoryProvider` separately.
+- `FunctionalWorkflow`, `WorkflowBuilder`, `AgentExecutor`, `FunctionExecutor`.
+- `FanOutEdgeGroup`, `FanInEdgeGroup`, `SwitchCaseEdgeGroup`.
+- `LocalShellTool` persistent, `LocalShellTool` stateless, `DockerShellTool`.
+- `MCPStdioTool`, `MCPStreamableHTTPTool`, `MCPWebsocketTool`;
+  `OpenAIChatClient` vs `OpenAIChatCompletionClient`.
+
+Examples that do **not** get separate bits: exact session id or persisted history
+file path; exact shell command, workdir, timeout, or output cap; exact MCP server
+command, URL, or tool names from the server; exact workflow graph shape or edge
+count; model/deployment names, prompts, tool arguments, payloads.
+
+Rough estimate: Python ~110-150 bits; .NET ~85-125 bits.
+
+- Good, useful where mode-level distinctions are decision-relevant.
+- Bad, trades simplicity for precision, increases fingerprint specificity, and
+  may exhaust or exceed 128 bits in Python.
+
+#### F4. Option / behavior flag bits
+
+The most detailed framework-owned option: bits for specific modes and behavior
+switches, still excluding customer/runtime values.
+
+Examples that get bits:
+
+- Agent streaming used vs non-streaming used.
+- `FunctionTool` `approval_mode="always_require"` vs `"never_require"`.
+- `FunctionTool` `SKIP_PARSING` / result-parser path used.
+- MCP sampling configured; MCP long-running task support used.
+- `LocalShellTool` `clean_env` / `confine_workdir`; `DockerShellTool` container
+  mode.
+
+Examples that do **not** get separate bits: function names wrapped by
+`FunctionTool`; approval rule arguments or approval decisions; MCP remote tool
+names or schemas; shell command text or policy regex patterns; prompt/message
+content, model names, URLs, tenant/user/session identifiers.
+
+Rough estimate: Python 150+ bits; .NET 120+ bits.
+
+- Good, maximum framework-owned detail.
+- Bad, exceeds or nearly exhausts 128 bits and is too detailed for v1 without a
+  concrete decision that requires it.
+
+### Registry sharing model
+
+#### H. Per-language bit lists (chosen)
+
+Each SDK owns an independent list; the decoder picks the list using the language
+already present in the UA product token.
+
+- Good, **no cross-language coordination**: each SDK numbers and evolves its
+  features independently; adding a Python feature never touches .NET numbering.
+- Good, no null placeholders for one-SDK features, no "same bit, same meaning"
+  rule, no SDK-aware decode caveats.
+- Good, decoding is trivial: language (from UA) + version -> list -> AND.
+- Neutral, two small lists to maintain instead of one (but they were going to
+  diverge anyway — the packages differ).
+
+#### I. Single shared cross-language registry
+
+- Good, one list, one number space.
+- Bad, forces synchronized numbering and null placeholders for features that
+  exist in only one SDK, plus SDK-aware decode rules.
+- Bad, the synchronization is pure accidental complexity — **the language is
+  already in the User-Agent**, so sharing the number space buys nothing.
+
+### Registry maintenance
+
+#### J. Package-local indexes + parity/no-overlap test (chosen)
+
+- Good, each package owns private `FeatureIndex` declarations only for its own
+  rows; adding an optional-provider index does not require a core release after
+  the marker API exists.
+- Good, one repository test compares the package-local declarations with the
+  per-language table and rejects missing rows, wrong ids, out-of-range indexes,
+  and any duplicate/overlapping index.
+- Good, no build step, no generator to own.
+
+#### K. Code-generate the enums from the registry
+
+- Bad, a generator + drift test + schema test to maintain a short list of
+  integer constants; likely justified only if v1 deliberately chooses the most
+  detailed L3/L4 granularities.
+
+### Representation (how the mask is rendered as text)
+
+All examples below encode the same mask — bits 0, 2, 32, 48, 56 set
+(agent + workflow + sequential-orchestration + foundry.chat_client + openai, in
+the Python v1 list) = decimal `72339073309605893`.
+
+#### L. Decimal — `feat=v1.72339073309605893`
+
+- Good, human-familiar; trivial to parse.
+- Neutral, no visual alignment to four-bit groups; slightly longer than hex for
+  large masks. No advantage over hex.
+
+#### M. Hex (chosen) — `feat=v1.101000100000005`
+
+- Good, compact (≤32 chars for a 128-bit mask).
+- Good, decodes with one stdlib call in every language (`int(x, 16)` /
+  two 64-bit lane parses in .NET); each hex character corresponds to four
+  consecutive bit positions.
+- Good, lowercase, no `0x` prefix, no leading zeros — unambiguous and stable.
+
+A grouped variant such as `feat=v1.101.0001.0000.0005` was also considered.
+Separators make the value longer and must be removed before `int(x, 16)` can
+parse it, while the ordinary hex digits already preserve fixed four-bit groups.
+
+#### N. Binary — `feat=v1.100000001000000000000000100000000000000000000000000000101`
+
+- Good, directly shows every zero/one position.
+- Bad, grows to 128 payload characters and is difficult to scan reliably.
+
+#### O. Bit-list — `feat=v1.0,2,32,48,56`
+
+- Good, most directly human-readable ("which bits").
+- Bad, needs delimiter handling and grows with the number of set bits; a full
+  128-bit list is substantially larger than every fixed-width representation.
+
+#### P. Alphabet / base-N (e.g. Crockford base32 `feat=v1.208004000005`, base62 `feat=v1.5LJRx1i6xJ`)
+
+- Good, shortest representation.
+- Bad, needs a custom alphabet + decode table on both ends; base62 is
+  case-sensitive (fragile through case-normalizing intermediaries); not
+  directly readable. Premature optimization for a value that is already ≤32
+  chars in hex.
+
+All forms are ASCII. The table shows total bytes added to the existing
+User-Agent, including the leading space and `(feat=v1.)` wrapper:
+
+| Representation | Example (5 bits) | All current Python rows (63) | All current .NET rows (52) | Full 128-bit v1 |
+| --- | ---: | ---: | ---: | ---: |
+| Hex | 26 | 34 | 30 | 43 |
+| Grouped hex | 29 | 39 | 34 | 50 |
+| Decimal | 28 | 38 | 34 | 50 |
+| Binary | 68 | 100 | 86 | 139 |
+| Bit-list | 23 | 189 | 156 | 412 |
+| Crockford base32 | 23 | 29 | 26 | 37 |
+| Base62 | 21 | 26 | 24 | 33 |
+
+There is no defensible average before rollout, and the design does not depend on
+one: a process-global mask may eventually contain every assigned row. There is
+no smaller per-request bit budget because the bits are not request-scoped; the
+registry allocation tenet controls how many distinctions v1 assigns. Client
+processing is bounded by the fixed 128-bit width: marking performs one
+lock/atomic OR, and request-time stamping reads the mask, formats at most 32 hex
+characters, and replaces one User-Agent comment. It performs no registry scan,
+network call, or per-feature enable/disable bookkeeping.
+
+## Decision Outcome
+
+Chosen: **a request-time-stamped, first-party-only User-Agent `(feat=...)` token (A),
+with a 128-bit process-global monotonic accumulator (S1), per-language bit lists
+(H), package-local index enums kept honest by parity and no-overlap tests (J),
+rendered as lowercase hex (M).**
+
+This is a bounded design with enough v1 headroom. A 128-bit
+**process-global, monotonic** mask accumulates from universal
+`mark_feature_used()` calls (so it spans build/start/participation activations
+that aren't bound to any service request — the per-request set model (S2) can't);
+the token is **stamped per request** only when both the client/pipeline and the
+actual HTTPS origin are approved, so custom origins and cross-origin redirects
+cannot inherit the fingerprint; each
+SDK owns an independent bit list selected by the language already in the UA; the
+mask is rendered as hex (`feat=v1.101000100000005`). The dedicated
+`AGENT_FRAMEWORK_FEATURE_MASK_DISABLED` opt-out drops only the mask while
+keeping the base SDK identity/version User-Agent. Python's existing
+`AGENT_FRAMEWORK_USER_AGENT_DISABLED` continues to suppress its entire
+contribution, including the mask; this decision does not introduce a matching
+whole-User-Agent switch in .NET. OTel (C) is deferred — mainly because a
+broadly-emitted span attribute would leak the fingerprint into the user's
+general telemetry, against the first-party-only stance and would require
+user-side OTel setup that may still not make the data available to us — but left
+open behind the version prefix. Per-request scoping (S2), a shared registry (I),
+codegen for the initial registry (K), and the decimal/grouped-hex/binary/bit-list/
+base-N representations (L, M variant, N, O, P) are rejected as complexity or
+length the problem does not require.
+
+The remaining choice before implementation is the **v1 granularity level** among
+F0-F4. This is a point-in-time decision: adding new bits later is easier than
+removing or redefining them, because removals/redefinitions require a new
+registry version and historical decode tables. For v1, prefer the least detailed
+level that answers the known product/support questions so we do not force a v2
+shortly after launch. The refreshed candidate registry uses **63 Python indexes and
+52 .NET indexes**, leaving 65 and 76 positions respectively. That headroom supports
+normal growth; it does not waive the registry's
+[allocation tenet](../specs/feature-usage-bit-registry.md#allocation-tenet).
+
+### Consequences
+
+- Good, adds a bounded-cost usage signal with no new data flow and few moving
+  parts.
+- Good, transparent (public registry, human-decodable token) and disabled by a
+  dedicated `AGENT_FRAMEWORK_FEATURE_MASK_DISABLED` mask-only opt-out. Python's
+  existing whole-User-Agent opt-out also suppresses the mask.
+- Good, first-party-only + request-time stamping gives a live mask and no
+  third-party fingerprint leak.
+- Good, 128 bits leaves useful v1 headroom; .NET remains lock-free by storing two
+  independently atomic 64-bit lanes; per-language lists remove all cross-language
+  sync; package-local enums avoid both codegen and provider→core release coupling.
+- Neutral, the token's reach equals eligible framework-configured first-party
+  traffic; broader per-call signal (OTel) can be added later if needed.
+- Neutral, every set bit is a repeated Boolean observation after first use;
+  request rows carrying it are not feature invocation counts.
+- Neutral, v1 granularity is intentionally a separate choice; the registry should
+  start with fewer bits unless a more detailed bit answers a concrete question.
+- Bad, each feature must add an activation mark, first-party clients need a
+  per-request destination-aware hook, and the registry validator must scan all
+  package-local index declarations.
+
+## Prior art
+
+SDK telemetry-in-the-User-Agent is well-established; this design is closest to
+AWS's, and conventional in the rest. Summary of what comparable SDKs do:
+
+| SDK | What's in the UA / headers | Usage-based? | Opt-out | Closest to ours? |
+| --- | --- | --- | --- | --- |
+| **AWS botocore** | structured UA with an `m/` token: a per-request set of **short feature codes** for features actually exercised (`WAITER`→`B`, `PAGINATOR`→`C`, retry mode, checksums, credential source, …) | **Yes** — registered at call time via `register_feature_id`, contextvar-scoped per request | `AWS_SDK_UA_APP_ID` sets app id (no opt-out for `m/`) | **Yes — direct analog** |
+| **OpenAI / Anthropic** (Stainless) | sidecar `X-Stainless-*` headers: lang, package version, OS, arch, runtime, runtime version; plus per-request `x-stainless-retry-count`, `x-stainless-read-timeout` | Mostly static identity (retry/timeout are per-request) | none | No (static identity) |
+| **Azure SDK** (`azure-core`) | `User-Agent: azsdk-python-{pkg}/{ver} Python/{pyver} ({platform})` | No | `AZURE_TELEMETRY_DISABLED` (tracing spans only, **not** the UA) | No |
+| **Google API core** | `x-goog-api-client: gl-python/… grpc/… gax/… gapic/…` | No | none | No |
+| **LangSmith** | `User-Agent: langsmith-py/{ver}`; usage lives in trace payloads | No (header) | opt-in via `LANGSMITH_TRACING_V2`/`LANGCHAIN_TRACING_V2`; `…HIDE_INPUTS/OUTPUTS` | No |
+
+Takeaways that shaped (or validate) our choices:
+
+- **AWS `m/` is the precedent for usage-based feature flags in a first-party
+  User-Agent.** It validates the core idea. Its key *difference* is the encoding:
+  AWS uses a **comma-separated set of 1–2 char short codes** (open-ended, no bit
+  coordination, but variable length), whereas we use a fixed-width **hex
+  bitmask** (compact, bounded, decode-by-AND, but needs per-language bit
+  allocation). We keep the bitmask for boundedness and trivial AND-decoding;
+  AWS's short-code set is recorded as a viable alternative if bit-position
+  coordination ever becomes painful (it would also drop the fixed 128-bit bound).
+- **A fixed-width bitmask gives bounded token size for free.** botocore must cap
+  the `m/` component at 1024 bytes and truncate at delimiter boundaries (with a
+  fallback log) precisely *because* its short-code set is unbounded. Our 128-bit
+  hex is ≤32 chars by construction — no size cap, no truncation logic.
+- **Scope is where we diverge most — and deliberately.** botocore collects
+  features into a per-request `contextvars` set that is **reset between
+  requests**, and no-ops outside a request context to prevent cross-request
+  bleed. That works because every botocore feature is exercised *inside* an AWS
+  service request. We are more general: some features are request-scoped (a chat
+  call, an MCP tool invocation) but many are **not bound to any request**
+  (workflow build/start, provider participation, hosting startup). So we use a
+  **process-global, monotonic** mask (option S1), which is the only scope that can
+  represent the non-request features. Our mask therefore intentionally "bleeds"
+  (accumulates) for the life of the process — the opposite of botocore's reset —
+  and that is the intended semantic, not the bug botocore guards against.
+- **The mechanism is private; the wire format is the contract.** botocore marks
+  its whole user-agent module private and "subject to abrupt breaking changes."
+  Same for us: the Python/.NET helpers are internal, and only the emitted token +
+  the per-language registry tables are the stable, decodable contract.
+- **First-party-only emission** is stricter than any of the above; the closest in
+  spirit is Stainless headers, which only reach the owning API. We make the
+  client/pipeline allowlist explicit (initially Foundry/Azure OpenAI) rather than
+  attempting to infer safety from arbitrary request URLs. Other Azure clients
+  join only after telemetry access is confirmed.
+- **Opt-out naming.** `AZURE_TELEMETRY_DISABLED` is the family precedent for our
+  `AGENT_FRAMEWORK_*_DISABLED` names. Separately, the cross-tool `DO_NOT_TRACK`
+  convention (honored by e.g. HuggingFace Hub) is worth considering — see Open
+  Questions.
+
+Sources: botocore [`useragent.py`](https://github.com/boto/botocore/blob/develop/botocore/useragent.py)
+(`_USERAGENT_FEATURE_MAPPINGS`, `register_feature_id`, `_build_feature_metadata`);
+openai-python [`_base_client.py` `platform_headers()`](https://github.com/openai/openai-python/blob/main/src/openai/_base_client.py);
+anthropic-sdk-python [`_base_client.py`](https://github.com/anthropics/anthropic-sdk-python/blob/main/src/anthropic/_base_client.py);
+azure-core [`_universal.py` `UserAgentPolicy`](https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/core/azure-core/azure/core/pipeline/policies/_universal.py);
+google-api-core [`client_info.py`](https://github.com/googleapis/python-api-core/blob/main/google/api_core/client_info.py);
+langsmith-sdk [`client.py`](https://github.com/langchain-ai/langsmith-sdk/blob/main/python/langsmith/client.py) /
+[`utils.py`](https://github.com/langchain-ai/langsmith-sdk/blob/main/python/langsmith/utils.py);
+huggingface_hub [`constants.py`](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/constants.py).
+
+## Registry versioning and migration (v1 → v2)
+
+The token carries a **per-language** version (`feat=v1.<hex>`); a version bump is
+independent for Python and .NET.
+
+- **Additive growth stays on v1 — no bump.** Allocating a new feature to a
+  reserved/unused bit is backward-compatible: an older decoder simply sees an
+  unknown bit and ignores it. Normal package growth never needs a new
+  version.
+- **A bump (v2) is required only for breaking changes:** renumbering or
+  re-partitioning existing bits, changing the *meaning* of an already-assigned
+  index, or widening beyond 128-bit. Within a version an index is **never** reused or
+  reassigned — that invariant is what lets old decoders stay correct.
+- **The draft 64→128 change is still v1.** No v1 token or enum has shipped, so
+  this pre-implementation repartition establishes the initial contract rather
+  than migrating an existing one.
+- **Mixed-version coexistence is the norm.** A fleet runs many SDK releases at
+  once, so `v1` and `v2` tokens appear simultaneously for a long time (old SDKs
+  keep emitting `v1`). The decoder keeps **every** published `(language,
+  version)` table and selects by the token's version; the `v1` table is retained
+  indefinitely for historical decode.
+- **Unknown version → do not guess.** A decoder without the `vN` table must
+  record "unknown registry version" rather than decode against an older table —
+  bit meanings may differ across versions, so mis-attribution is worse than
+  no data.
+- **Producing v2:** publish the v2 table alongside v1, update the affected
+  package-local `FeatureIndex` declarations and SDK version constant, and emit
+  `v2` from the release that ships them. Prefer staying on v1 (additive) and
+  reserving a clean v2 for an eventual deliberate re-partition.
+
+## Limitations
+
+| Limitation | Caused by (choice) | Why we accepted it |
+| --- | --- | --- |
+| **No signal for self-hosted or third-party-only traffic.** If a process never calls Azure/Foundry, we see nothing. | First-party-only emission (A) | We can't read third-party logs anyway, and must not leak a fingerprint into them. Reach traded for privacy. |
+| **Not every first-party client is stampable.** Caller-supplied `AIProjectClient` / OpenAI clients and toolkit-owned clients may not expose a supported per-request policy hook. | Supported-hook-only emission (A) | V1 does not mutate caller-owned clients or private SDK pipelines. Those features may still appear on another eligible request from the same process-global mask. |
+| **Custom origins intentionally receive no feature token.** A customer gateway may use Azure credentials or Azure-named settings but route to a non-approved origin. | Two-factor destination classification (A) | Credentials and configuration names are not proof of telemetry ownership. Unknown/custom origins and cross-origin redirects are denied by default. |
+| **No OTel / per-call signal in v1.** | OTel deferred (C) — primarily on **privacy** and availability grounds | A broadly-emitted span attribute would push the fingerprint into the user's general telemetry / third-party APM vendors, undoing the first-party-only scoping. It also requires customer/user OTel setup, and even Foundry users may not export data where we can query it. Left open only if there is a compelling reason to add. |
+| **Mask reflects "usage so far," not the whole session.** Early requests carry fewer bits than later ones. | Process-global accumulator + request-time stamping | Honest and still useful as a Boolean process-lifetime observation. Repeated request rows must not be summed as additional uses. Reading the mask at request time makes it *grow* rather than freeze. |
+| **No per-agent / per-call attribution.** The mask is one process-wide value — "this process used X", not "this agent/call used X". | Process-global monotonic scope (S1) | A deliberate choice, not a transport limit: botocore *does* per-call attribution in the UA via a per-request `contextvars` set, but many AF activations (workflow build/start, provider participation, hosting startup) occur outside the service request that later emits the token. Per-call detail remains deferred to OTel. |
+| **Shared processes intentionally carry usage across agents and tenants.** A request can include bits first set by another workload in the same worker. | Process-global monotonic scope (S1) | The token must be interpreted only as process-level "used so far," never as request/user/tenant attribution. Privacy review must explicitly accept this. |
+| **Bits are binary, sticky observations — not countable events.** Once set, a bit appears on every later eligible request from that process, so raw request counts repeat the same observation and long-lived/high-traffic processes dominate. | Monotonic mask stamped at request time | The signal supports coarse observed-feature and co-occurrence questions only. It cannot provide first-use counts, unique-process counts, request attribution, or feature invocation frequency. |
+| **Granularity may be too coarse or too detailed.** The chosen level may miss useful distinctions or create more specificity than needed. | v1 granularity choice (F0-F4) | This is the main remaining decision. Adding bits later is easier than removing/redefining them, so v1 should lean toward fewer bits that answer known questions. |
+| **.NET snapshots span two atomic lanes.** A bit can be marked between the low/high reads, so one request may omit that just-added bit. | 128-bit width without a global lock | The mask is monotonic: the snapshot cannot invent or clear a bit, and the next request includes the addition. This matches the existing "usage so far" timing semantics. |
+| **Fingerprinting risk is reduced, not eliminated.** A feature-combination mask is still a deployment signature, and it transits intermediaries (proxies/CDNs) even when first-party-scoped. | Emitting any feature-combination value | Scope + opt-out + coarse granularity mitigate it; v1 should avoid unnecessary detailed bits. |
+
+## Open Questions (for decider discussion)
+
+These are unresolved and should be decided before implementation:
+
+1. **Which v1 granularity level (F0-F4)?** This is the primary remaining choice.
+   Adding bits later is easier than removing or redefining bits, so v1 should
+   choose the least detailed level that answers known questions and avoids a quick
+   v2.
+2. **Privacy approval for the v1 User-Agent signal.** Before implementation,
+   confirm that a transparent, opt-out, first-party-only feature-combination
+   fingerprint is acceptable, including the exact client allowlist, retention,
+   access, and permitted product queries. This is a rollout precondition.
+3. **When (if ever) to add the OTel path?** Held back mainly for **privacy** and
+   data availability: a span attribute broadcasts the fingerprint into the user's
+   general telemetry and onward to third-party APM vendors, contradicting the
+   first-party-only stance, and it requires user-side OTel setup that may not make
+   the data available to us even for Foundry users. It also carries a
+   metric-cardinality hazard. Revisit only if the User-Agent path cannot answer a
+   concrete question.
+4. **Honor the cross-tool `DO_NOT_TRACK` convention?** Several ecosystems treat
+   `DO_NOT_TRACK=1` as a universal telemetry opt-out (HuggingFace Hub honors it;
+   see [Prior art](#prior-art)). Should our mask opt-out also respect
+   `DO_NOT_TRACK` (in addition to `AGENT_FRAMEWORK_FEATURE_MASK_DISABLED` and
+   Python's pre-existing whole-UA flag)? Cheap to add and
+   community-friendly, but it widens the opt-out surface and needs a clear
+   precedence rule. Recommend yes; confirm with the deciders.
+
+### Decided
+
+- **Dedicated opt-out flag — included.** In addition to the existing
+  Python `AGENT_FRAMEWORK_USER_AGENT_DISABLED` (drops the whole UA), v1 ships
+  `AGENT_FRAMEWORK_FEATURE_MASK_DISABLED`, which drops **only** the feature mask
+  while keeping the base SDK identity/version User-Agent. This lets a
+  privacy-conscious user withhold the usage signal without losing the
+  support/compat value of the SDK-version header. .NET adopts the dedicated
+  mask-only flag; adding a .NET whole-User-Agent switch is outside this decision.
+- **Caller-owned clients are not modified.** V1 stamps only framework-created
+  clients or clients with a supported public policy/hook registration point. It
+  does not patch private pipelines; injected clients are an explicit coverage
+  limitation.
+- **Destination approval is explicit and redirect-aware.** An eligible pipeline
+  still emits only to a reviewed HTTPS origin. Custom origins are default-deny,
+  and the token is removed on an unapproved redirect hop.
+- **Telemetry does not replace transport defaults.** Framework-created OpenAI
+  clients use the SDK's default async HTTP client with the request hook added,
+  preserving redirect, timeout, connection-limit, and pooling behavior.
+- **Marking uses activation, not DI construction.** Operational surfaces mark on
+  first real use; a constructor marks only when construction itself exercises or
+  registers the capability.
+
+## More Information
+
+- Mechanism & API: [SPEC-004](../specs/004-feature-usage-telemetry.md)
+- Per-language bit tables, encoding, opt-out, governance: [feature-usage-bit-registry.md](../specs/feature-usage-bit-registry.md)
+- Existing accumulator pattern: `python/packages/core/agent_framework/_telemetry.py`
+- .NET emission policies: `dotnet/src/Microsoft.Agents.AI.Foundry/AgentFrameworkUserAgentPolicy.cs`,
+  `dotnet/src/Microsoft.Agents.AI.Foundry.Hosting/HostedAgentUserAgentPolicy.cs`

docs/features/FIDES_IMPLEMENTATION_SUMMARY.md

@@ -0,0 +1,366 @@
+# FIDES Implementation Summary
+
+## Overview
+
+**FIDES**  is a comprehensive deterministic prompt injection defense system for the agent framework. The implementation provides label-based security mechanisms to defend against prompt injection attacks by tracking integrity and confidentiality of content throughout agent execution.
+
+**🚀 Key Features:**
+- **Context Provider Pattern** - `SecureAgentConfig` extends `ContextProvider`, injecting tools, instructions, and middleware automatically
+- **Automatic Variable Hiding** - UNTRUSTED content is automatically hidden without requiring manual intervention
+- **Per-Item Embedded Labels** - Tools return `list[Content]` with `Content.from_text()` for proper label propagation
+- **SecureMCPToolProxy Auto-Labeling** - MCP tools are labeled automatically from MCP `ToolAnnotations` hints
+- **MCP `_meta.ifc` Support** - Per-result IFC labels from servers (for example GitHub MCP with `X-MCP-Features: ifc_labels`) are parsed and enforced
+- **SecureAgentConfig** - One-line secure agent configuration via `context_providers=[config]`
+- **Data Exfiltration Prevention** - `max_allowed_confidentiality` prevents sensitive data leakage
+- **Message-Level Label Tracking** (Phase 1) - Track labels on every message in the conversation
+
+## Architecture Components
+
+The FIDES defense system consists of seven main components:
+
+1. **Content Labeling Infrastructure** - Labels for tracking integrity and confidentiality
+2. **Label Tracking Middleware** - Automatically assigns, propagates labels, and hides untrusted content
+3. **Per-Item Embedded Labels** - Tools can return mixed-trust data with per-item security labels
+4. **Policy Enforcement Middleware** - Blocks tool calls that violate security policies
+5. **Security Tools** - Specialized tools for safe handling of untrusted content (`quarantined_llm`, `inspect_variable`)
+6. **SecureAgentConfig** - Context provider for easy secure agent configuration
+7. **Message-Level Label Tracking** - Track labels on every message in the conversation (Phase 1)
+8. **MCP Tool/Result Label Integration** - MCP hint-based tool labeling and `_meta.ifc` result label parsing
+
+## Implementation Details
+
+### Files Created
+
+1. **`python/packages/core/agent_framework/security.py`** (~2950 lines — all security primitives, middleware, tools, and configuration in a single public module)
+   - `IntegrityLabel` enum (TRUSTED/UNTRUSTED)
+   - `ConfidentialityLabel` enum (PUBLIC/PRIVATE/USER_IDENTITY)
+   - `ContentLabel` class with serialization support
+   - `combine_labels()` function for label composition
+   - `ContentVariableStore` for client-side content storage
+   - `VariableReferenceContent` for variable indirection
+   - `LabeledMessage` class (inherits from `Message`) for message-level tracking
+   - `check_confidentiality_allowed()` helper for data exfiltration prevention
+   - `LabelTrackingFunctionMiddleware` - Tracks and propagates security labels
+   - `PolicyEnforcementFunctionMiddleware` - Enforces security policies
+   - `SecureAgentConfig` extends `ContextProvider` - automatic secure agent configuration
+   - `quarantined_llm()` - Isolated LLM calls with labeled data
+   - `inspect_variable()` - Controlled variable content inspection
+   - `store_untrusted_content()` - Helper for manual variable indirection (legacy)
+   - `get_security_tools()` - Returns list of security tools
+   - `SECURITY_TOOL_INSTRUCTIONS` - Detailed guidance for agents
+
+
+2. **`FIDES_DEVELOPER_GUIDE.md`** (~1250 lines)
+   - Located at `python/samples/02-agents/security/FIDES_DEVELOPER_GUIDE.md`
+   - Complete documentation of the FIDES security system
+   - Architecture overview and design rationale
+   - Usage examples (6+ comprehensive scenarios)
+   - Best practices and configuration options
+   - API reference with full parameter documentation
+   - Data exfiltration prevention documentation
+
+3. **`python/packages/core/tests/test_security.py`** (~800+ lines)
+   - Unit tests for ContentLabel and label operations
+   - Tests for ContentVariableStore functionality
+   - Tests for VariableReferenceContent
+   - Middleware behavior tests (label tracking and policy enforcement)
+   - Automatic hiding tests
+   - Per-item embedded label tests
+   - Context label tracking tests
+   - Message-level tracking tests (Phase 1)
+   - Data exfiltration prevention tests
+
+4. **`docs/decisions/0024-prompt-injection-defense.md`**
+   - Architecture Decision Record (ADR)
+   - Design rationale and alternatives considered
+   - Security properties and guarantees
+
+5. **`python/samples/02-agents/security/README.md`**
+   - Sample-focused entry point for the two runnable FIDES security samples
+   - Prerequisites, run commands, and links to the developer guide for deeper details
+
+### Files Modified
+
+1. **`python/packages/core/agent_framework/__init__.py`**
+   - Removed root-level security exports so `agent_framework.security` is the canonical import surface
+
+## Core Features
+
+### 1. Content Labeling Infrastructure
+
+- **IntegrityLabel**: TRUSTED (user input) vs UNTRUSTED (AI-generated, external)
+- **ConfidentialityLabel**: PUBLIC, PRIVATE, USER_IDENTITY
+- **Label Combination**: Most restrictive policy (UNTRUSTED + metadata merging)
+- **Serialization**: Full support for `to_dict()` and `from_dict()`
+
+### 2. Per-Item Embedded Labels
+
+Tools returning mixed-trust data embed labels on individual items using `Content.from_text()`:
+
+```python
+import json
+from agent_framework import Content, tool
+
+@tool(description="Fetch emails from inbox")
+async def fetch_emails(count: int = 5) -> list[Content]:
+    return [
+        Content.from_text(
+            json.dumps({
+                "id": email["id"],
+                "body": email["body"],
+            }),
+            additional_properties={
+                "security_label": {
+                    "integrity": "trusted" if email["internal"] else "untrusted",
+                    "confidentiality": "private",
+                }
+            ),
+        )
+        for email in emails
+    ]
+```
+
+These embedded labels are automatically consumed by `LabelTrackingFunctionMiddleware`, which:
+- Extracts the `security_label` from `additional_properties`
+- Uses the embedded label as the highest-priority source for that item
+- Automatically hides UNTRUSTED items in the variable store
+- Replaces hidden items with `VariableReferenceContent` in the LLM context
+- Preserves TRUSTED items visible to the LLM without tainting the context label
+
+This enables tools to return mixed-trust data where some items (internal emails) remain visible while untrusted items (external emails) are automatically hidden without manual intervention.
+           },
+        )
+        for email in emails
+    ]
+```
+
+### 3. Automatic Variable Hiding
+
+This feature automatically hides any UNTRUSTED content returned by tools while keeping the hiding logic transparent to the developer. Developers do not need to manually call `store_untrusted_content()`. This allows the LLM /agent's context to remain clean and secure. Key aspects include:
+
+- **Automatic Detection**: Middleware checks integrity label after each tool call
+- **Automatic Storage**: UNTRUSTED results/items stored in variable store
+- **Transparent Replacement**: LLM context receives `VariableReferenceContent`
+- **Context Label Protection**: Hidden content does NOT taint context label
+
+### 4. Context Label Tracking
+
+- Context label starts as TRUSTED + PUBLIC
+- Gets updated (tainted) when non-hidden untrusted content enters context
+- Policy enforcement uses context label for validation
+- Provides `get_context_label()` and `reset_context_label()` methods
+
+### 5. Data Exfiltration Prevention
+
+Tools declare `max_allowed_confidentiality` to prevent sensitive data leakage:
+
+```python
+@tool(
+    description="Post to public Slack channel",
+    additional_properties={
+        "max_allowed_confidentiality": "public",  # Blocks PRIVATE data
+    }
+)
+async def post_to_slack(channel: str, message: str) -> dict:
+    return {"status": "posted"}
+```
+
+### 6. SecureAgentConfig (Context Provider)
+
+SecureAgentConfig extends `ContextProvider` for automatic secure agent configuration:
+
+```python
+config = SecureAgentConfig(
+    auto_hide_untrusted=True,
+    allow_untrusted_tools={"search_web", "fetch_data"},
+    block_on_violation=True,
+    quarantine_chat_client=quarantine_client,  # Optional: real LLM for quarantine
+)
+
+# Context provider injects tools, instructions, and middleware automatically
+agent = Agent(
+    client=client,
+    name="secure_assistant",
+    instructions="You are a helpful assistant.",
+    tools=[my_tool],
+    context_providers=[config],  # That's it!
+)
+```
+
+### 7. MCP Labeling Pipeline (Hints + `_meta.ifc`)
+
+FIDES now secures remote MCP integration end-to-end:
+
+- **Tool labels from hints**: `apply_mcp_security_labels(...)` maps MCP hints (`readOnlyHint`, `openWorldHint`) to FIDES tool properties.
+- **Safe sink defaults**: tools not explicitly marked `readOnlyHint=True` are treated as potential sinks and receive `max_allowed_confidentiality=public`.
+- **Result labels from metadata**: MCP result `_meta` is propagated via `__mcp_result_meta__`; `_meta.ifc` is parsed into `security_label` per result item.
+- **`SecureMCPToolProxy` convenience**: wraps MCP tools/URLs and applies this labeling automatically on connect.
+
+This behavior is used with the GitHub MCP server when `X-MCP-Features: ifc_labels` is passed, which causes the server to return IFC labels in `_meta` (for example `{"ifc": {"integrity": "untrusted", "confidentiality": "public"}}`).
+
+## Security Properties
+
+### Deterministic Defense
+
+1. **Tiered label propagation**: Every tool result receives a label via 3-tier priority (embedded > source_integrity > input labels join)
+2. **Context tracking**: Cumulative security state tracked across turns
+3. **Policy enforcement**: Violations blocked before execution
+4. **Content isolation**: Untrusted content stored as variables
+5. **Taint propagation**: Once context becomes UNTRUSTED, it stays UNTRUSTED
+6. **Data exfiltration prevention**: `max_allowed_confidentiality` gates output destinations
+7. **Audit trail**: All security events logged
+8. **No runtime guessing**: Deterministic label assignment
+
+### Attack Prevention
+
+- **Direct prompt injection**: Variables hide actual content from LLM
+- **Indirect prompt injection**: Labels track untrusted AI-generated calls
+- **Privilege escalation**: Policy blocks untrusted calls to privileged tools
+- **Data exfiltration**: Confidentiality labels + `max_allowed_confidentiality` enforced
+- **Tool misuse**: Only whitelisted tools accept untrusted inputs
+
+## Configuration Options
+
+### LabelTrackingFunctionMiddleware
+- `default_integrity`: Default label for unknown sources
+- `default_confidentiality`: Default confidentiality level
+- `auto_hide_untrusted`: Enable automatic variable hiding (default: True)
+- `hide_threshold`: Integrity level at which hiding occurs (default: UNTRUSTED)
+
+### PolicyEnforcementFunctionMiddleware
+- `allow_untrusted_tools`: Set of tools accepting untrusted inputs
+- `block_on_violation`: Block vs warn on violations
+- `enable_audit_log`: Enable/disable audit logging
+
+### Tool Metadata (via `additional_properties`)
+- `confidentiality`: Tool's output confidentiality level
+- `source_integrity`: Fallback integrity for unlabeled results (data-producing tools only)
+- `accepts_untrusted`: Explicit untrusted input permission
+- `max_allowed_confidentiality`: Maximum allowed input confidentiality (for sink tools)
+- `requires_approval`: Human-in-the-loop requirement
+
+## Usage Pattern
+
+### Recommended: SecureAgentConfig as Context Provider
+
+```python
+from agent_framework.security import SecureAgentConfig
+
+config = SecureAgentConfig(
+    auto_hide_untrusted=True,
+    allow_untrusted_tools={"search_web"},
+    block_on_violation=True,
+)
+
+# Context provider injects everything automatically
+agent = Agent(
+    client=client,
+    name="secure_assistant",
+    instructions="You are a helpful assistant.",
+    tools=[search_web],
+    context_providers=[config],  # Tools, instructions, and middleware injected via before_run()
+)
+```
+
+### Processing Hidden Content with quarantined_llm
+
+```python
+from agent_framework.security import quarantined_llm
+
+# Agent automatically uses quarantined_llm with variable_ids
+result = await quarantined_llm(
+    prompt="Summarize this data",
+    variable_ids=["var_abc123"]  # Reference hidden content by ID
+)
+```
+
+## Testing
+
+Comprehensive test suite with:
+- 115+ unit tests covering all components
+- Label creation, serialization, combination
+- Variable store operations
+- Middleware behavior (tracking and enforcement)
+- Automatic hiding with per-item labels
+- Context label tracking
+- Message-level tracking (Phase 1)
+- Data exfiltration prevention
+- Policy violation scenarios
+- Audit log verification
+
+Run tests:
+```bash
+cd python/packages/core && ../../.venv/bin/pytest tests/test_security.py -v
+```
+
+## Code Statistics
+
+- **Total lines**: ~2,950+ lines (single `security.py` module)
+- **New modules**: 1 (`security.py` — consolidated from 3 original modules)
+- **Total tests**: 115+ unit tests
+- **Documentation**: 1,250+ lines in developer guide
+- **Examples**: 6+ comprehensive scenarios
+
+## Deliverables Checklist
+
+### Core Implementation
+✅ ContentLabel infrastructure with integrity and confidentiality
+✅ ContentVariableStore for variable indirection
+✅ VariableReferenceContent for safe context references
+✅ LabelTrackingFunctionMiddleware for automatic labeling
+✅ PolicyEnforcementFunctionMiddleware for policy enforcement
+✅ quarantined_llm tool for isolated processing
+✅ inspect_variable tool for controlled content access
+✅ store_untrusted_content helper for manual variable indirection
+
+### Automatic Hiding Enhancement
+✅ Auto-hide UNTRUSTED content with `auto_hide_untrusted` flag
+✅ Per-middleware ContentVariableStore instances
+✅ Thread-local storage for middleware access from tools
+✅ Automatic UNTRUSTED content replacement
+
+### Per-Item Embedded Labels
+✅ Support for `additional_properties.security_label` on individual items
+✅ Mixed-trust data handling (hide untrusted, keep trusted visible)
+✅ Fallback to `source_integrity` for unlabeled items
+
+### Context Label Tracking
+✅ Cumulative context label tracking across turns
+✅ Hidden content does NOT taint context
+✅ `get_context_label()` and `reset_context_label()` methods
+✅ Policy enforcement uses context label
+
+### Data Exfiltration Prevention
+✅ `max_allowed_confidentiality` tool property
+✅ `check_confidentiality_allowed()` helper function
+✅ Policy enforcement validates confidentiality flow
+
+### SecureAgentConfig
+✅ Context provider pattern with `ContextProvider` base class
+✅ `before_run()` hook for automatic injection of tools, instructions, and middleware
+✅ One-line secure agent configuration via `context_providers=[config]`
+✅ `get_tools()`, `get_instructions()`, `get_middleware()` methods (for manual use)
+✅ `quarantine_chat_client` support for real LLM calls
+✅ `SECURITY_TOOL_INSTRUCTIONS` constant
+
+### Documentation & Testing
+✅ Complete FIDES Developer Guide (~1250 lines)
+✅ Architecture Decision Record (ADR)
+✅ Quick Start Guide
+✅ Comprehensive test suite (115+ tests)
+✅ Example code with 6+ scenarios
+✅ 3 complete security examples (email, repo confidentiality, GitHub MCP labels)
+
+## Summary
+
+**FIDES** provides a comprehensive, deterministic defense against prompt injection attacks with:
+
+- **Zero-effort protection**: Automatic variable hiding for developers
+- **Context provider pattern**: `SecureAgentConfig` extends `ContextProvider` for automatic setup
+- **Granular control**: Per-item embedded labels via `Content.from_text()` for mixed-trust data
+- **Easy configuration**: `SecureAgentConfig` for one-line setup
+- **Data safety**: Exfiltration prevention via confidentiality gates
+- **Full traceability**: Message-level label tracking
+- **Complete auditability**: All security events logged
+
+The system ensures that untrusted content never directly reaches the LLM context and that all tool calls are policy-checked based on the cumulative security state before execution.

docs/specs/002-python-hosting-channels.md

@@ -0,0 +1,498 @@
+---
+status: proposed
+contact: eavanvalkenburg
+date: 2026-07-08
+deciders: eavanvalkenburg
+---
+
+# Python protocol helpers and optional execution state
+
+## Scope
+
+This specification is the Python implementation plan for
+[ADR-0027](../decisions/0027-hosting-channels.md). It documents the helper-first v1 contract for Python hosting.
+
+The v1 contract is:
+
+- protocol packages expose helper functions that convert protocol-native input to Agent Framework run values;
+- protocol packages expose helper functions that convert Agent Framework run results or streams back to protocol-native
+  payloads or operations;
+- application/framework code owns routes, native SDK clients, authentication, command policy, webhooks, response status
+  codes, and outbound sends;
+- `agent-framework-hosting` provides small optional state holders for Agent Framework targets;
+- state helpers do not own web apps, route contribution, protocol dispatch, command projection, or native SDK calls.
+
+## Goals
+
+- Let apps expose agents and workflows from FastAPI, Starlette, Django, Azure Functions, native SDK webhooks, CLIs, and
+  tests without adopting a host/channel framework.
+- Keep protocol parsing and response formatting inside protocol packages.
+- Keep session continuity explicit and app-owned at the trust boundary.
+- Reuse Agent Framework primitives: `AgentSession`, `CheckpointStorage`, `Agent.run(...)`, `Workflow.run(...)`, and
+  `ResponseStream`.
+- Preserve full-fidelity Agent Framework results until a protocol helper renders them.
+
+## Non-goals for v1
+
+### App-owned in v1
+
+The app builder owns these concerns with normal web-framework, SDK, platform, or application code:
+
+- authentication, authorization policy, and allowlists;
+- deciding whether identities across protocols map to the same `session_id`;
+- non-originating sends using native SDK clients;
+- background work, durable execution, retry, and replay when app code owns the work;
+- routing between multiple agents.
+
+The helper-first model makes app-owned linking and non-originating delivery easier than the old host/channel model because
+app code already owns the native SDK clients, authenticated caller context, session id selection, and outbound sends.
+
+### Future framework work
+
+The following require a separate reviewed design before becoming reusable framework features:
+
+- reusable cross-channel identity linking;
+- framework-owned proactive or non-originating delivery;
+- fan-out, multicast, selected-channel, active-channel, or all-linked delivery;
+- framework-owned delivery observability, dead-letter handling, and replay semantics;
+- cross-channel confidentiality and link policy.
+
+[ADR-0028](../decisions/0028-hosting-linking-multicast-enhancements.md) tracks possible follow-up work in this area and
+must be aligned with the helper-first model before implementation. Old vocabulary such as `IdentityLinker`,
+`ResponseTarget`, `ChannelPush`, `ChannelPushCodec`, `DurableTaskRunner`, `RetryPolicy`, and `LinkPolicy` is not v1 API.
+
+## Packages
+
+| Package | Import surface | v1 helper-first contents |
+|---|---|---|
+| `agent-framework-hosting` | `agent_framework_hosting` | `AgentState`, `WorkflowState`, `SessionStore`, and run-argument `TypedDict`s. |
+| `agent-framework-hosting-a2a` | `agent_framework_hosting_a2a` | A2A `Message` to run conversion and Agent Framework output to A2A `Part` conversion. |
+| `agent-framework-hosting-mcp` | `agent_framework_hosting_mcp` | Agent and workflow MCP tool adapters, MCP tool arguments to run conversion, and Agent Framework output to MCP `ContentBlock` conversion. |
+| `agent-framework-hosting-responses` | `agent_framework_hosting_responses` | Responses helpers: request parsing, session id extraction, response id creation, response rendering, streaming rendering. |
+| `agent-framework-hosting-telegram` | `agent_framework_hosting_telegram` | Telegram Bot API helpers: update parsing, chat/session/command/media extraction, final rendering, and streaming edit rendering. |
+| Future protocol packages | e.g. `agent_framework_hosting_activity_protocol` | Protocol-specific helpers such as `activity_to_run(...)`, `activity_from_run(...)`, `activity_session_id(...)`, and command/media helpers when useful. |
+
+The core hosting package must not depend on protocol SDKs. Protocol packages may depend on their native protocol SDKs if
+needed, but helper functions should stay usable from plain app code and tests.
+
+## Helper naming and families
+
+Helper names are protocol-specific. Avoid a generic `protocol_to_run(...)` public surface.
+
+Protocol packages may provide the following helper families when the protocol has the concept:
+
+| Helper family | Shape | Purpose |
+| --- | --- | --- |
+| Run conversion | `<protocol>_to_run(...)` | Convert one protocol-native call/update/request into `Agent.run` or `Workflow.run` values. |
+| Final rendering | `<protocol>_from_run(...)` | Convert a final `AgentResponse` or workflow result into protocol-native response payloads or operations. |
+| Stream rendering | `<protocol>_from_streaming_run(...)` | Convert `ResponseStream` or workflow updates into protocol-native events or operations. |
+| Session id extraction | `<protocol>_session_id(...)` | Extract the protocol's natural continuation/partition key from the call, if present. |
+| Command/action parsing | `<protocol>_command(...)` | Parse a protocol-native command/action/operation name without deciding app policy. |
+
+Examples:
+
+- `responses_to_run(...)`, `responses_from_run(...)`, `responses_from_streaming_run(...)`,
+  `responses_session_id(...)`;
+- `a2a_to_run(...)`, `a2a_from_run(...)`;
+- `telegram_to_run(...)`, `telegram_from_run(...)`, `telegram_from_streaming_run(...)`,
+  `telegram_session_id(...)`, `telegram_command(...)`;
+- `activity_to_run(...)`, `activity_from_run(...)`, `activity_session_id(...)`, `activity_command(...)`;
+- `discord_to_run(...)`, `discord_from_run(...)`, `discord_session_id(...)`, `discord_command(...)`.
+
+This table is a naming guide, not a required checklist. A protocol package should add only the helpers that match native
+protocol concepts and current samples.
+
+Protocol-specific helpers may also exist for native details such as `telegram_chat_id(...)`,
+`telegram_callback_query_id(...)`, `telegram_media_file_id(...)`, `discord_interaction_id(...)`, `a2a_task_id(...)`,
+`a2a_context_id(...)`, or MCP tool/prompt/resource helpers. These helpers should stay side-effect-free. App/native SDK
+code performs acknowledgements, sends/edits messages, resolves protected file URLs, applies rate limits, and registers
+handlers.
+
+## `agent-framework-hosting` state helpers
+
+### `SessionStore`
+
+`SessionStore` is an in-memory async lookup:
+
+```python
+class SessionStore:
+    async def get(self, session_id: str) -> AgentSession | None: ...
+    async def set(self, session_id: str, session: AgentSession) -> None: ...
+    async def delete(self, session_id: str) -> None: ...
+```
+
+The store does not create sessions. It stores `session_id -> AgentSession` values supplied by callers.
+
+The built-in store has no TTL or eviction. This is intentional for local/dev and simple process-local scenarios: protocols
+such as OpenAI Responses can continue from any prior response id. Durable or multi-replica deployments should provide a
+durable store and their own TTL/eviction policy.
+
+### `AgentState`
+
+`AgentState` holds an agent target and an optional `SessionStore`:
+
+```python
+state = AgentState(agent)
+state = AgentState(create_agent)
+state = AgentState(create_agent, cache_target=False)
+```
+
+The target may be:
+
+- a `SupportsAgentRun` instance;
+- a synchronous factory;
+- an asynchronous factory;
+- an awaitable target.
+
+`AgentState` provides:
+
+- `await get_target()`;
+- synchronous `target` only after a target is already available/resolved;
+- `session_store`;
+- `await get_or_create_session(session_id)`;
+- `await set_session(session_id, session)`.
+
+`get_or_create_session(...)` resolves the target and calls `target.create_session(session_id=...)` only when the store has
+no session for that id.
+
+Apps must store the post-run session explicitly after `agent.run(...)` or stream finalization:
+
+```python
+session = await state.get_or_create_session(session_id)
+target = await state.get_target()
+result = await target.run(messages, session=session, options=options)
+await state.set_session(response_id, session)
+```
+
+### `WorkflowState`
+
+`WorkflowState` resolves a workflow target. It does not own checkpoint storage.
+
+The target may be:
+
+- a `Workflow` instance;
+- a `WorkflowBuilder` or other object with `build() -> Workflow`;
+- a synchronous factory;
+- an asynchronous factory;
+- an awaitable target.
+
+`WorkflowState` provides:
+
+- `await get_target()`;
+- synchronous `target` only after a target is already available/resolved.
+
+A workflow instance permits one active run. Concurrent hosts use a factory or
+builder with `cache_target=False` to resolve a fresh instance per run.
+
+Workflow checkpointing uses Agent Framework's existing `CheckpointStorage` abstraction directly. Apps that need
+per-session workflow resume should keep an app-owned cursor such as `session_id -> checkpoint_id`. When the app uses
+file-backed cursor storage, the file-based checkpoint storage should share the same app storage root and should be
+scoped to the current authenticated user/tenant/session bucket, for example
+`storage/checkpoints/<session-bucket>/` beside `storage/checkpoint_cursors.json`:
+
+```python
+# session_id must already be authenticated and authorized for this caller
+target = await workflow_state.get_target()
+checkpoint_id = await checkpoint_cursor_store.get(session_id)
+if checkpoint_id is None:
+    result = await target.run(message=workflow_input, checkpoint_storage=checkpoint_storage)
+else:
+    result = await target.run(checkpoint_id=checkpoint_id, checkpoint_storage=checkpoint_storage)
+latest = await checkpoint_storage.get_latest(workflow_name=target.name)
+if latest is not None:
+    await checkpoint_cursor_store.set(session_id, latest.checkpoint_id)
+```
+
+`Workflow.run(...)` does not currently emit a checkpoint id on `WorkflowRunResult` or normal workflow events by default.
+The runner receives checkpoint ids internally from `CheckpointStorage.save(...)`. Apps that own the storage can query
+`get_latest(workflow_name=...)` after the run if they need to update a cursor.
+
+## `agent-framework-hosting-responses`
+
+The Responses package provides the helper-first surface for OpenAI Responses-shaped requests.
+
+### Request helpers
+
+- `messages_from_responses_input(input) -> list[Message]`
+- `responses_to_run(body) -> AgentRunArgs`
+- `responses_session_id(body) -> str | None`
+- `create_response_id() -> str`
+
+`responses_to_run(...)` returns values corresponding to `Agent.run(...)`:
+
+```python
+run = responses_to_run(body)
+messages = run["messages"]
+options = run["options"]
+stream = run["stream"]
+```
+
+It excludes protocol transport/session fields from `options` and remaps known Responses option names such as
+`max_output_tokens -> max_tokens`.
+
+`responses_session_id(...)` returns:
+
+- `previous_response_id` when present (`resp_*`);
+- otherwise `conversation_id` when present (`conv_*`);
+- otherwise `None`.
+
+The helper only extracts the candidate key. App code decides whether to trust and use that key.
+
+### Response helpers
+
+- `responses_from_run(result, *, response_id, session_id=None) -> dict[str, Any]`
+- `responses_from_streaming_run(stream, *, response_id, session_id=None) -> AsyncIterator[str]`
+
+`responses_from_run(...)` renders a full Responses JSON payload from an `AgentResponse`. It renders the full set of
+OpenAI Responses output item types supported by Agent Framework content.
+
+`responses_from_streaming_run(...)` renders Server-Sent Event strings for a `ResponseStream`. It emits a created event,
+text deltas, and a completed event. The final completed payload is produced through `responses_from_run(...)`; the helper
+also preserves the model id observed on streaming updates when the finalized `AgentResponse` no longer carries raw model
+metadata.
+
+## `agent-framework-hosting-a2a`
+
+The A2A package provides only the conversion seam between the native A2A SDK
+and Agent Framework:
+
+- `a2a_to_run(message, *, stream=False) -> AgentRunArgs`
+- `a2a_from_run(result) -> list[a2a.types.Part]`
+
+`a2a_to_run(...)` accepts a native A2A `Message` and converts its text, URL,
+raw-byte, and structured-data parts into one Agent Framework user message.
+
+`a2a_from_run(...)` accepts an `AgentResponse`, `Message`, or
+`AgentResponseUpdate` and converts supported text, URI, and data content into
+native A2A `Part` values. This one helper is usable for both completed and
+streaming runs.
+
+The package does not provide an A2A `AgentExecutor`, application, route,
+request handler, task store, event queue, `TaskUpdater`, task-state policy,
+artifact-id policy, or session-key policy. Application code composes the two
+helpers with those native A2A SDK constructs and may use any server framework
+supported by the SDK.
+
+## `agent-framework-hosting-mcp`
+
+The MCP package provides only the conversion seam between native MCP SDK values
+and Agent Framework:
+
+- `MCPAgentTool(target, ...)`
+- `MCPWorkflowTool(target, ...)`
+- `mcp_to_run(arguments, *, argument_name="task", chat_option_arguments=()) -> AgentRunArgs`
+- `mcp_from_run(result) -> list[mcp.types.ContentBlock]`
+
+`MCPAgentTool` represents one Agent Framework agent as one native MCP tool. It
+derives the default tool name and description from the agent, accepts
+overrides for those values and the main text parameter, includes app-owned
+additional parameter schemas, and explicitly maps selected parameter schemas
+to ChatOptions. Its asynchronous `list_tools()` returns the native `Tool` list,
+and `call_tool(...)` performs conversion, agent execution, and final result
+conversion.
+
+The adapter accepts either an agent or an existing `AgentState`. With a
+configured `session_id_parameter`, it loads and stores the corresponding
+`AgentSession`. The application remains responsible for deriving and
+authorizing the session id and preventing concurrent updates to the same
+session.
+
+`MCPWorkflowTool` represents one Agent Framework workflow as one native MCP
+tool. It derives the tool name and description from the workflow and derives
+the input schema from the start executor's single declared input type.
+Object-shaped dataclass and Pydantic inputs become top-level MCP arguments;
+primitive inputs are wrapped in one configurable argument. The adapter
+validates the arguments against that type, runs the workflow, and converts
+terminal outputs to MCP content blocks.
+
+Workflow instances preserve state and reject concurrent runs. Applications
+that need independent calls should provide a `WorkflowState` factory with
+`cache_target=False`. Checkpoint restoration, human-in-the-loop responses, and
+continuation identifiers remain application-owned contracts. If a workflow
+stops to request external input, the adapter raises rather than returning an
+empty successful tool result.
+
+`mcp_to_run(...)` accepts the argument mapping from a native MCP `call_tool`
+handler. The application owns the tool schema and may select which required
+string argument contains the user request. The application should define that
+argument name once and use the same value in the native tool schema and the
+`argument_name` parameter so those two sides of the contract remain aligned.
+Applications may also expose selected ChatOptions fields in their native tool
+schema and pass those names through `chat_option_arguments`. Only explicitly
+selected names are copied to run options; the helper does not forward all MCP
+arguments or own their JSON Schema validation.
+
+MCP `tools/call` arguments are JSON-only and do not have a native multimodal
+content-block union. The package does not impose a non-standard JSON
+representation for multimodal tool arguments.
+
+`mcp_from_run(...)` accepts an `AgentResponse` or `Message`. It converts text,
+URI, image data, audio data, and other binary data into native MCP content
+blocks.
+
+Its output is specifically the content union accepted by `CallToolResult`.
+Sampling-only values such as `ToolUseContent` belong to the separate MCP
+sampling response path and are not emitted by this hosting helper.
+
+MCP `tools/call` returns one final `CallToolResult`. Streamable HTTP can carry
+multiple MCP messages and progress notifications can report operation status,
+but the protocol does not define partial tool-result content chunks.
+Experimental MCP tasks defer retrieval of the same final result. Therefore the
+conversion helpers do not expose Agent Framework streaming updates.
+
+The package does not provide an MCP `Server`, handler registration, transport, route,
+session policy, authentication, authorization, or deployment wrapper.
+Application code composes the adapters and conversion helpers with native MCP SDK constructs and
+may use stdio, streamable HTTP, or another transport supported by the SDK.
+
+## `agent-framework-hosting-telegram`
+
+The Telegram package provides side-effect-free helpers around Telegram Bot API
+update and method payloads. It does not provide a Bot API client, polling loop,
+webhook route, command registry, retry policy, or rate limiter.
+
+### Update helpers
+
+- `telegram_to_run(update, *, resolve_file_url=None, stream=False) -> AgentRunArgs`
+- `telegram_chat_id(update) -> int | None`
+- `telegram_session_id(update, *, bot_id) -> str | None`
+- `telegram_command(update) -> str | None`
+- `telegram_callback_query_id(update) -> str | None`
+- `telegram_media_file_id(update_or_message) -> tuple[str, str] | None`
+
+`telegram_to_run(...)` handles `message`, `edited_message`, and
+`callback_query` updates. Text and captions become AF text content. When the
+app supplies an async `resolve_file_url` callback, supported Telegram media
+file ids can become AF URI content. The package does not call Telegram's
+`getFile` method itself.
+
+`telegram_session_id(..., bot_id=...)` includes the bot identity in every key.
+Private chats return `telegram:<bot_id>:<user_id>`; other chats return
+`telegram:<bot_id>:<chat_id>`, giving groups a shared session by default. This
+matches Telegram's native isolation boundaries while preventing two bots from
+sharing state accidentally. Apps that want per-user sessions inside a group
+can construct a key that includes both chat and sender ids. The app must
+authorize those Telegram identities before loading session state.
+
+`telegram_command(...)` parses Telegram's `/name` and `/name@bot` syntax. It
+does not register commands or invoke handlers.
+
+### Response helpers
+
+- `telegram_from_run(result, *, chat_id, parse_mode=None)`
+- `telegram_from_streaming_run(stream, *, chat_id, message_id, initial_text=None, parse_mode=None)`
+
+The helpers produce Telegram method/payload values for app-owned Bot API
+calls. Final rendering supports text and image URI output and applies
+Telegram's text-length boundary. Streaming rendering produces cumulative
+`editMessageText` payloads for a placeholder message id supplied by the app,
+omitting edits that match an optional `initial_text`, then renders the final
+rich output. Image-only responses remove the placeholder with `deleteMessage`
+before sending the image. The app owns the initial placeholder send, Bot API
+calls, edit throttling, retries, and failure policy.
+
+## Security responsibilities
+
+Protocol helper packages parse and render. They do not authenticate callers, authorize access to state, or decide which
+side effects are allowed.
+
+Application code that uses these helpers is responsible for:
+
+- authenticating the caller through the app's normal mechanism before using protocol-provided ids;
+- authorizing any caller-supplied session, checkpoint, task, context, conversation, thread, or response id before loading
+  state for it;
+- binding externally supplied ids to the authenticated user, tenant, workspace, installation, or chat context before
+  using them as `SessionStore` keys or checkpoint cursor keys;
+- treating `<protocol>_session_id(...)` results as untrusted candidate keys until that ownership check has passed;
+- keeping platform-provided isolation helpers fail-closed outside their trusted hosting environment;
+- authorizing command/action effects such as reset, cancel, approve, submit, or tool invocation after parsing them;
+- opting in explicitly before resolving protected media/resource/file URLs and passing them to a remote model provider;
+- persisting post-run session or checkpoint state only after `agent.run(...)`, `workflow.run(...)`, or stream finalization
+  has updated that state.
+
+## Persistent versus transient hosting
+
+The application builder decides whether the server is persistent or transient.
+
+- Persistent single-process apps, such as a long-running container or web app, may use in-memory state for local
+  development or simple deployments. Multi-replica persistent apps still need durable state for continuity.
+- Transient apps, such as Azure Functions, Foundry Hosted Agents, or any environment where process memory is not a
+  reliable boundary, must not rely on in-memory `SessionStore` state between calls. They need a durable session store or
+  a service-owned continuation id.
+- Workflow hosts must choose an explicit `CheckpointStorage` and, when they need per-session resume, a durable
+  `session_id -> checkpoint_id` cursor. File-backed checkpoint storage and file-backed cursor storage should live under
+  the same app storage root, with checkpoints scoped to the current authenticated user/tenant/session bucket so a
+  "latest checkpoint" lookup cannot cross conversations. In-process workflow state and in-memory checkpoint cursors do
+  not survive transient execution.
+
+## Minimal FastAPI Responses shape
+
+This is the shape the local Responses sample should demonstrate. It is not an app framework.
+
+```python
+from collections.abc import AsyncIterator
+
+from agent_framework import ResponseStream
+from agent_framework_hosting import AgentState
+from agent_framework_hosting_responses import (
+    create_response_id,
+    responses_from_run,
+    responses_from_streaming_run,
+    responses_session_id,
+    responses_to_run,
+)
+from fastapi import Body, FastAPI, HTTPException
+from fastapi.responses import JSONResponse, StreamingResponse
+
+app = FastAPI()
+state = AgentState(create_agent)
+
+
+@app.post("/responses", response_model=None)
+async def responses(body: dict = Body(...)) -> JSONResponse | StreamingResponse:
+    run = responses_to_run(body)
+    candidate_session_id = responses_session_id(body)
+    response_id = create_response_id()
+
+    # Verify this caller owns candidate_session_id before loading it.
+    session_id = candidate_session_id or response_id
+    session = await state.get_or_create_session(session_id)
+    target = await state.get_target()
+
+    if run["stream"]:
+        stream = target.run(run["messages"], stream=True, session=session, options=run["options"])
+        if not isinstance(stream, ResponseStream):
+            raise HTTPException(status_code=500, detail="agent did not return a response stream")
+
+        async def events() -> AsyncIterator[str]:
+            async for event in responses_from_streaming_run(
+                stream,
+                response_id=response_id,
+                session_id=candidate_session_id,
+            ):
+                yield event
+            await state.set_session(response_id, session)
+
+        return StreamingResponse(events(), media_type="text/event-stream")
+
+    result = await target.run(run["messages"], session=session, options=run["options"])
+    await state.set_session(response_id, session)
+    return JSONResponse(responses_from_run(result, response_id=response_id, session_id=candidate_session_id))
+```
+
+## Validation
+
+Implementation validation must cover:
+
+- `SessionStore` plain get/set/delete behavior;
+- `AgentState` target resolution, target caching, and get-or-create session behavior;
+- `WorkflowState` target resolution for direct workflows, factories, `WorkflowBuilder`, and orchestration-style builders;
+- Responses request parsing and option remapping;
+- Responses session id extraction;
+- Responses response rendering, including rich output item mapping;
+- Responses streaming SSE rendering;
+- HTTP round-trip tests showing a native FastAPI route using `AgentState` and Responses helpers;
+- sample type checking for the local Responses sample.
+- Telegram update parsing, chat/session/command/media extraction, final
+  rendering, and streaming edit rendering;
+- sample type checking for the local Telegram polling and webhook entry points.

docs/specs/003-dotnet-hosting-protocol-helpers.md

@@ -0,0 +1,246 @@
+---
+status: accepted
+contact: rogerbarreto
+date: 2026-07-08
+deciders: rogerbarreto
+consulted: eavanvalkenburg
+informed: []
+---
+
+# .NET hosting: OpenAI Responses protocol helpers and optional execution state
+
+Implements [ADR-0032](../decisions/0032-dotnet-hosting-protocol-helpers.md), which realizes the
+helper-first direction of [ADR-0027](../decisions/0027-hosting-channels.md) for .NET.
+
+## What is the goal of this feature?
+
+Let application developers expose an `AIAgent` or workflow over the OpenAI Responses protocol **while
+owning their own ASP.NET Core route, authentication, middleware, and storage**, by calling small,
+side-effect-free Agent Framework conversion helpers instead of adopting the batteries-included,
+route-owning `MapOpenAIResponses` server.
+
+Success: an application can implement a working `POST /responses` endpoint (sync + streaming) in its
+own minimal-API handler using only the public helpers plus its own auth/storage, with no dependency on
+`MapOpenAIResponses` or `IResponsesService`.
+
+## What is the problem being solved?
+
+.NET already exposes agents as the OpenAI Responses API, but only through the route-owning
+`MapOpenAIResponses`/`IResponsesService`, which also owns routing, response/conversation storage,
+streaming, and lifecycle. An application that wants its own routing (custom auth, middleware, status
+codes, durable storage, or a different framework surface) currently has no supported way to reuse the
+framework's Responses<->agent conversion. Every conversion primitive that would make this possible
+already exists in `Microsoft.Agents.AI.Hosting.OpenAI` but is `internal`.
+
+This feature un-bundles that conversion into a public, app-callable surface, and adds the minimal
+execution-state helpers an app needs for session continuity and workflow checkpoint resume.
+
+## API Changes
+
+### `Microsoft.Agents.AI.Hosting.OpenAI` (new public static facade `OpenAIResponses`)
+
+Boundary is `System.Text.Json`; the wire DTOs stay internal. All members are side-effect-free.
+
+```csharp
+namespace Microsoft.Agents.AI.Hosting.OpenAI;
+
+public static class OpenAIResponses
+{
+    // Wire -> Agent Framework run input.
+    public static OpenAIResponsesRunRequest ToAgentRunRequest(
+        JsonElement body,
+        OpenAIResponsesMapOptions? mapOptions = null);
+
+    // Agent Framework result -> Responses payload (no originating request required).
+    public static JsonElement WriteResponse(
+        AgentResponse response,
+        string responseId,
+        string? sessionId = null);
+
+    // Agent Framework stream -> Responses SSE `data:` frames.
+    public static IAsyncEnumerable<string> WriteResponseStreamAsync(
+        IAsyncEnumerable<AgentResponseUpdate> updates,
+        string responseId,
+        string? sessionId = null,
+        CancellationToken cancellationToken = default);
+
+    // Untrusted candidate continuation key: previous_response_id or conversation id (or null).
+    // Kept SEPARATE from ToAgentRunRequest so using a request-derived key is an explicit decision.
+    public static string? GetSessionId(JsonElement body);
+
+    // Mint a `resp_*` id.
+    public static string CreateResponseId();
+}
+
+// Result of ToAgentRunRequest.
+public sealed class OpenAIResponsesRunRequest
+{
+    public IList<ChatMessage> Messages { get; }
+    public AgentRunOptions? Options { get; }
+}
+```
+
+`ToAgentRunRequest` honors `OpenAIResponsesMapOptions.RunOptionsFactory` exactly as the route model
+does (by default no request setting is mapped onto the run; unsupported settings surface as a
+`NotSupportedException`). `WriteResponse`/`WriteResponseStreamAsync` reuse the existing internal
+`AgentResponseExtensions.ToResponse` / `AgentResponseUpdateExtensions.ToStreamingResponseAsync`
+converters (an internal `ToResponse` overload with an optional originating request is added so the
+facade can render without one). The streaming renderer's existing workflow-event support is preserved.
+
+### `Microsoft.Agents.AI.Hosting` (execution state, protocol-neutral)
+
+```csharp
+namespace Microsoft.Agents.AI.Hosting;
+
+public abstract class AgentSessionStore
+{
+    // ... existing members ...
+
+    // New: the one missing store operation. Virtual (not abstract) with a default that throws
+    // NotSupportedException, so existing external stores (e.g. the Foundry hosting stores) keep
+    // compiling; the in-box Hosting stores override it. In-box overrides treat deleting a missing
+    // session as a no-op.
+    public virtual ValueTask DeleteSessionAsync(
+        AIAgent agent, string conversationId, CancellationToken cancellationToken = default);
+}
+
+// Thin holder: pairs a workflow target with checkpointing + a per-session head cursor.
+public sealed class HostedWorkflowState
+{
+    // Shared-instance mode: one instance cannot be run by two runners at once, so turns run one at a time.
+    public HostedWorkflowState(Workflow workflow, CheckpointManager? checkpointManager = null);
+
+    // Factory mode: by default a fresh instance is built per run, so independent sessions run in parallel.
+    // With cacheWorkflow: true the factory is invoked once lazily and the built instance is cached and reused.
+    public HostedWorkflowState(Func<CancellationToken, ValueTask<Workflow>> workflowFactory, CheckpointManager? checkpointManager = null, bool cacheWorkflow = false);
+
+    // First turn runs forward from the start; subsequent turns restore the session's latest
+    // checkpoint and run forward with the new turn's input, then record the new head checkpoint.
+    public ValueTask<HostedWorkflowRunResult> RunOrResumeAsync(
+        string sessionId, object input, CancellationToken ct = default);
+}
+```
+
+For agents, the application uses `AgentSessionStore` directly: `GetSessionAsync(agent, id)` creates a
+session on miss and returns an independent instance per call (so concurrent calls can fork the same
+stored state — for example branching from a `previous_response_id` or managing several `conversation`
+ids side by side — without one branch observing another's in-flight mutations). The store performs no
+cross-call locking; an application that needs concurrent runs against the same id to be serialized owns
+that coordination. `SaveSessionAsync(agent, id, session)` persists post-run, including under a newly
+minted `resp_*` id when the protocol mints a new continuation id. `DeleteSessionAsync` uses the new
+store method. No agent-side holder is needed: create-on-miss already lives in the store, so a
+pass-through wrapper would only bind the `agent` argument.
+
+`HostedWorkflowState` defaults to `CheckpointManager.CreateInMemory()` and an in-memory
+`sessionId -> CheckpointInfo` cursor. Because the checkpoint store is already `sessionId`-keyed but
+`CheckpointInfo` carries no ordering, the holder remembers the head checkpoint per session so
+`RunOrResumeAsync` can resume the correct one. On subsequent turns it restores that checkpoint to
+rehydrate accumulated workflow state and then runs the workflow forward with the new turn's input,
+rather than continuing a halted run with no input (which would wait for input
+indefinitely). For agent (chat-protocol) workflows the new input is accompanied by a `TurnToken` so the
+turn is driven. When the in-memory cursor misses (a new holder or a process restart), the holder falls
+back to `CheckpointManager.GetLatestCheckpointAsync(sessionId)`, so a durable `CheckpointManager` resumes
+correctly across restarts (the default in-memory manager does not persist, so a restart starts fresh). A
+resume that produces no events is logged as a warning (possible stale checkpoint or mismatched input).
+Concurrency depends on how the holder is constructed. With a single shared workflow instance, concurrent runs
+are not supported, because a workflow instance cannot be run by two runners at once; process turns one at a
+time. With a workflow factory
+(`Func<CancellationToken, ValueTask<Workflow>>`) it builds a fresh instance per run by default, so independent
+sessions run in parallel; a resume rehydrates a fresh instance
+from the session's checkpoint in the shared store, and concurrent turns against the same session id remain the
+application's coordination responsibility. Passing `cacheWorkflow: true` instead builds the workflow once,
+lazily on first use, and reuses it (a deferred, cached target that — like the instance — cannot run concurrent
+turns). A
+streaming counterpart, `RunOrResumeStreamingAsync`, yields the turn's `WorkflowEvent`s as they occur (for
+example to render agent updates over the Responses SSE wire) and records the head checkpoint once the
+stream is fully enumerated, keeping the blocking and streaming workflow paths in lockstep.
+Because `RunOrResumeAsync`/`RunOrResumeStreamingAsync` are generic over the input type, the application
+adapts the Responses input into the workflow's start-executor input type at the call site (for example
+parsing a structured payload into a typed record), without coupling the holder to a specific wire type.
+
+## Non-goals for v1
+
+- ChatCompletions / Conversations helper surfaces (the facade is named so `OpenAIChatCompletions` can
+  follow).
+- Changing `MapOpenAIResponses` public behavior.
+- A new package or an OpenAI-SDK-typed reimplementation.
+- Durable/pluggable workflow checkpoint-cursor storage (in-memory default only for v1).
+
+## Security responsibilities (application-owned)
+
+- Authenticate the caller before using any `GetSessionId(...)` result.
+- Authorize and bind the candidate id to the authenticated principal/tenant before using it as an
+  `AgentSessionStore` key or a workflow checkpoint session id.
+- For multi-user hosts, wrap the store with `IsolationKeyScopedAgentSessionStore` (for example via
+  `UseClaimsBasedSessionIsolation(...)`), so the session namespace is scoped per principal.
+- Persist session/checkpoint state only after the run or stream has completed.
+
+## E2E Code Samples
+
+### Agent over Responses, app-owned route (non-streaming + SSE)
+
+```csharp
+var agent = /* an AIAgent */;
+AgentSessionStore sessionStore = new InMemoryAgentSessionStore(); // in-memory session store
+
+app.MapPost("/responses", async (HttpContext http, CancellationToken ct) =>
+{
+    using var doc = await JsonDocument.ParseAsync(http.Request.Body, cancellationToken: ct);
+    JsonElement body = doc.RootElement;
+
+    // App owns auth + id trust decisions.
+    string? candidate = OpenAIResponses.GetSessionId(body);
+    string sessionId = Authorize(http.User, candidate) ?? OpenAIResponses.CreateResponseId();
+
+    var run = OpenAIResponses.ToAgentRunRequest(body);
+    var session = await sessionStore.GetSessionAsync(agent, sessionId, ct);
+
+    string responseId = OpenAIResponses.CreateResponseId();
+
+    if (body.TryGetProperty("stream", out var s) && s.GetBoolean())
+    {
+        http.Response.ContentType = "text/event-stream";
+        var updates = agent.RunStreamingAsync(run.Messages, session, run.Options, ct);
+        await foreach (var frame in OpenAIResponses.WriteResponseStreamAsync(updates, responseId, sessionId, ct))
+        {
+            await http.Response.WriteAsync(frame, ct);
+            await http.Response.Body.FlushAsync(ct);
+        }
+        await sessionStore.SaveSessionAsync(agent, responseId, session, ct);
+        return Results.Empty;
+    }
+
+    var result = await agent.RunAsync(run.Messages, session, run.Options, ct);
+    await sessionStore.SaveSessionAsync(agent, responseId, session, ct);
+    return Results.Json(OpenAIResponses.WriteResponse(result, responseId, sessionId));
+});
+```
+
+### Workflow over Responses with checkpoint resume
+
+Workflow checkpoint resume requires a **stable** session key across turns. `previous_response_id` changes
+every turn, so it is not a valid checkpoint key; use the `conversation` id (constant for the conversation).
+Because `GetSessionId(...)` prefers `previous_response_id`, a workflow route reads the conversation id
+directly rather than calling `GetSessionId(...)`.
+
+```csharp
+var state = new HostedWorkflowState(workflow); // in-memory checkpoints + cursor
+
+app.MapPost("/responses", async (HttpContext http, CancellationToken ct) =>
+{
+    using var doc = await JsonDocument.ParseAsync(http.Request.Body, cancellationToken: ct);
+    JsonElement body = doc.RootElement;
+
+    // Stable, authorized checkpoint key. GetConversationId(...) reads the conversation id (string or object).
+    string sessionId = Authorize(http.User, GetConversationId(body))
+        ?? OpenAIResponses.CreateResponseId();
+
+    var run = OpenAIResponses.ToAgentRunRequest(body);
+
+    // Runs forward on first call, resumes from the session's head checkpoint thereafter.
+    var result = await state.RunOrResumeAsync(sessionId, run.Messages, ct);
+
+    return Results.Json(OpenAIResponses.WriteResponse(result.AsAgentResponse(),
+        OpenAIResponses.CreateResponseId(), sessionId));
+});
+```

docs/specs/004-feature-usage-telemetry.md

@@ -0,0 +1,500 @@
+---
+status: proposed
+contact: eavanvalkenburg
+date: 2026-07-22
+deciders: eavanvalkenburg
+consulted:
+informed:
+---
+
+# Feature-usage telemetry via an accumulating bitmask
+
+> Companion design for [ADR-0033](../decisions/0033-feature-usage-bitmask-user-agent.md).
+> The per-language bit tables, encoding, opt-out, and governance live in
+> [feature-usage-bit-registry.md](feature-usage-bit-registry.md). The registry
+> allocates indexes; package-local `FeatureIndex` declarations implement them.
+
+## What is the goal of this feature?
+
+Give the Agent Framework team a lightweight signal about **which framework
+features are actually exercised** at runtime (not merely installed), so we can
+prioritise investment based on real usage. We emit a single small number — a
+*feature mask* — on the User-Agent that already goes out with each request.
+
+**Reach is deliberately bounded.** The mask accumulates from *all* feature usage,
+but the `feat=` token is only stamped through an explicit allowlist of
+**first-party Azure/Foundry client pipelines** whose User-Agent telemetry the
+team can ingest (initially Foundry/Azure OpenAI). We do **not** send the token to
+third-party providers (OpenAI direct, Anthropic, Bedrock, Gemini, Ollama,
+Mistral), or to an Azure service merely because its hostname is first-party;
+doing so would leak a deployment fingerprint into logs we cannot read (see
+[Emission](#emission)).
+
+The current candidate uses package-level bits plus selected major capabilities:
+one bit per orchestration pattern (sequential / concurrent / group-chat /
+magentic / handoff), **one bit per built-in context/history provider**, selected
+skill source types, and separate Foundry chat/agent/memory/evals/toolbox bits
+(plus embedding in Python).
+See the
+[registry](feature-usage-bit-registry.md). ADR-0033 still leaves final v1
+granularity open. The refreshed candidate assigns 63 Python indexes and 52 .NET
+indexes. V1 uses 128 bits, leaving 65 Python and 76 .NET positions for additive
+growth.
+
+Success metric: within one release after rollout, ≥80% of **eligible,
+framework-created** first-party (Foundry) requests carry a **non-empty** feature
+token whose mask reflects features activated **after** client construction (i.e.
+the token is live, not frozen — see the request-time stamping requirement
+below). This measures transport coverage, not feature invocation volume.
+Secondary: ability to describe which process-lifetime feature bits are observed
+together in eligible traffic (e.g. "requests observed from processes that have
+used workflows"). Repeated requests carrying a bit are not additional uses.
+
+This is done **transparently**: the bit registry is public, the emitted value is
+human-decodable, and a dedicated `AGENT_FRAMEWORK_FEATURE_MASK_DISABLED`
+disables the mask while preserving the base User-Agent. Python's existing
+`AGENT_FRAMEWORK_USER_AGENT_DISABLED` continues to suppress its entire
+User-Agent contribution, mask included.
+
+## What is the problem being solved?
+
+Today we only know which packages are *installed* (from package telemetry) or
+that *some* Agent Framework call happened (the existing
+`agent-framework-python/{version}` User-Agent). We have no usage-based signal
+about feature combinations, and no way to tell that, say, a process uses
+workflows + MCP + Foundry together. Collecting this through bespoke events would
+add cost and new data flows; folding a tiny accumulating integer into telemetry
+we already send is far cheaper and easier to reason about for privacy.
+
+## Mechanism
+
+### Process-global accumulator in `core`
+
+The accumulator and its helpers live in the existing
+`agent_framework/_telemetry.py` (alongside `get_user_agent()` /
+`prepend_agent_framework_to_user_agent()`), so the User-Agent machinery stays in
+one module. It owns a process-global 128-bit accumulator. Python's arbitrary-size
+`int` stores it directly. A **dedicated**
+`AGENT_FRAMEWORK_FEATURE_MASK_DISABLED` that drops **only** the feature mask
+while keeping the base `agent-framework-python/{version}` User-Agent is
+introduced by this design. The existing Python
+`AGENT_FRAMEWORK_USER_AGENT_DISABLED` continues to drop the whole User-Agent
+contribution, mask included:
+
+```python
+# agent_framework/_telemetry.py (same module as get_user_agent)
+# IS_TELEMETRY_ENABLED already defined here (AGENT_FRAMEWORK_USER_AGENT_DISABLED)
+
+FEATURE_MASK_DISABLED_ENV_VAR = "AGENT_FRAMEWORK_FEATURE_MASK_DISABLED"
+REGISTRY_VERSION = 1
+
+_feature_mask = 0
+_feature_mask_lock = threading.Lock()
+
+
+def _feature_mask_enabled() -> bool:
+    """Mask is on unless the UA is disabled or the dedicated flag is set."""
+    if not IS_TELEMETRY_ENABLED:
+        return False
+    return os.environ.get(FEATURE_MASK_DISABLED_ENV_VAR, "false").lower() not in ("true", "1")
+
+
+def mark_feature_used(index: int) -> None:
+    """OR a feature bit into the process-global mask.
+
+    Called the first time a feature is exercised. Cheap and idempotent;
+    a no-op when the feature mask is disabled.
+    """
+    global _feature_mask
+    if not _feature_mask_enabled():
+        return
+    if not 0 <= index < 128:
+        raise ValueError(f"Feature index must be in range 0..127, got {index}")
+    with _feature_mask_lock:
+        _feature_mask |= 1 << index
+
+
+def get_feature_token() -> str | None:
+    """Return ``v<version>.<hex_mask>`` for the accumulated mask, or None."""
+    if not _feature_mask_enabled() or _feature_mask == 0:
+        return None
+    return f"v{REGISTRY_VERSION}.{_feature_mask:x}"
+```
+
+- **Per package/feature, usage-based:** `mark_feature_used()` is called at the
+  feature's first meaningful activation, never at import/install time. For
+  operational clients, tools, providers, and hosts, activation is the first
+  public operation that exercises the capability. Construction is a valid mark
+  point only when construction itself performs the capability (for example,
+  registering/starting runtime resources), not merely because a DI container
+  instantiated an otherwise-unused object.
+- **Process-global and monotonic — intentionally never reset.** Unlike a
+  per-request scheme (e.g. botocore's `contextvars` feature set that resets
+  between calls), our mask spans the whole process because many features are not
+  bound to any service request — an agent or workflow may first run, a provider
+  may first participate in a session, and a host may start serving independently
+  of the later request that emits the token. The single global
+  mask is the only scope that can represent them, and its monotonic "usage so
+  far" growth is the intended semantic, not a bleed bug. Concurrency-safe via the
+  module lock (Python) / two atomic 64-bit lanes in .NET.
+- **Binary and non-countable.** A set bit means "this feature was observed at
+  least once in this process before this request." Repeating that bit on every
+  later eligible request does not represent additional uses and must not be
+  interpreted as request, invocation, agent, user, or tenant counts.
+- **No scoped enable/disable bookkeeping.** Making the mask exact per operation
+  would add hot-path state changes, context propagation, and reset/error-path
+  handling. It would also produce a more detailed behavioral trace and therefore
+  increase privacy sensitivity. V1 deliberately keeps the coarser process-level
+  Boolean.
+- **Token is safe by construction.** The emitted value is `v{int}.{hex}` —
+  characters limited to `[0-9a-fv.]` — so no header-injection sanitization is
+  required. A 128-bit mask is at most 32 hex characters (contrast botocore,
+  which must sanitize and cap arbitrary component strings).
+- **Private API.** `mark_feature_used`, `get_feature_token`, `apply_feature_token`
+  and the mask itself are internal helpers; only the emitted token and the
+  per-language registry tables are the stable, decodable contract.
+- **No import cycles:** the accumulator lives in core, while each package owns
+  private index constants for its own features and calls the core marker. Core
+  never imports optional packages.
+
+### Interpretation contract
+
+At time 1, Agent A in a worker can use MCP and a Foundry chat client. At time 2,
+Agent B in the same worker can make a normal Foundry chat call without MCP. The
+time-2 request still carries the MCP bit because MCP was observed earlier in the
+process.
+
+That request means only "this process has used MCP." It does not mean Agent B
+used MCP, that MCP was used on the time-2 request, or that two requests carrying
+the bit equal two MCP uses. Without a separate stable process identifier, the
+signal also cannot produce unique-process counts. Supported analysis is limited
+to coarse observed-feature prevalence and feature co-occurrence, with the
+request-weighting limitation called out explicitly.
+
+### Bit constants
+
+The registry is the allocation authority. Each package defines a private,
+hand-written `FeatureIndex` IntEnum (or equivalent constants) containing only
+the rows it owns. Core owns core indexes plus the accumulator; optional packages
+can allocate and ship new indexes without requiring a core release after the
+marker API exists.
+
+```python
+# agent_framework_foundry/_feature_usage.py
+from enum import IntEnum
+
+from agent_framework._telemetry import mark_feature_used  # pyright: ignore[reportAttributeAccessIssue]
+
+
+class FeatureIndex(IntEnum):
+    FOUNDRY_CHAT_CLIENT = 48
+
+
+class RawFoundryChatClient:
+    async def _send_request(self) -> None:
+        mark_feature_used(FeatureIndex.FOUNDRY_CHAT_CLIENT)
+        ...
+```
+
+A repository validation test reads every package-local declaration and the
+matching language/version table. It fails when an index is out of range, missing
+from the registry, duplicated/overlapping across packages, or mapped to the wrong
+id. For reference, in v1 `FoundryChatClient` → index 48,
+`FoundryAgent` → index 49, Foundry memory → index 50.
+
+### Usage activation points
+
+- **Clients/embeddings/evals:** first outbound operation.
+- **Tools/MCP:** first connection, discovery, or invocation that exercises the
+  tool surface.
+- **Context/history providers:** first provider hook or load/save operation, not
+  constructor-only registration.
+- **Agents/workflows/orchestrations:** first run/build/start operation that
+  activates the defined runtime.
+- **Hosting:** first serve/start/route activation.
+- **Constructor marking:** allowed only when construction itself performs one of
+  those activations or acquires/registers the runtime resource.
+
+## Emission
+
+**One path in v1: the User-Agent `feat=` token, stamped at request time on an
+explicit allowlist of first-party Azure/Foundry client pipelines only.**
+
+Marking (`mark_feature_used`) is **universal** — every feature sets its index
+regardless of provider. Only **emission** is scoped. A user who never calls a
+first-party endpoint emits no token; this is the honest, intended behaviour (no
+third-party leakage, no signal we couldn't read anyway).
+
+The existing base User-Agent behavior (`agent-framework-python/{version}` plus
+any dynamically detected hosting prefix) is unchanged; packages continue using
+their current `default_headers`, `user_agent`, suffix, or policy mechanisms.
+`get_user_agent()` stays base-only (no `feat=`). The `feat=` token is
+**separate**, added **only** by eligible Azure/Foundry clients, and
+**re-evaluated on each request** so it reflects the mask accumulated so far. A
+helper stamps it:
+
+This request-time read does not make the signal request-scoped. The payload
+remains the process-global Boolean history described above.
+
+```python
+# agent_framework/_telemetry.py
+def apply_feature_token(user_agent: str) -> str:
+    """Append/refresh the live ``(feat=v<ver>.<hex>)`` comment on a UA string.
+
+    Re-reads the current mask on every call, so newly accumulated bits are
+    reflected immediately. Idempotent: replaces an existing ``(feat=...)``
+    comment rather than appending a second.
+    """
+    token = get_feature_token()  # None when disabled or mask == 0
+    base = _strip_feature_comment(user_agent)
+    return f"{base} (feat={token})" if token else base
+```
+
+Emission requires **both**:
+
+1. an explicitly approved framework client/pipeline family; and
+2. the actual request's normalized HTTPS origin matching that family's reviewed
+   first-party origin allowlist.
+
+Credentials, `use_azure`, or an Azure-named setting alone do not approve a
+destination. Approval depends on the **resolved origin**: customer-specific
+subdomains on reviewed Azure/Foundry suffixes remain eligible even when supplied
+through `base_url` / `AZURE_OPENAI_BASE_URL`, while customer gateways and unknown
+OpenAI-compatible origins are denied by default. The check runs on every actual
+request, including redirect hops; a cross-origin or otherwise unapproved redirect
+removes `(feat=...)` before sending.
+
+Eligible first-party clients install a **request hook** that performs this
+classification and calls `apply_feature_token()`:
+
+- **OpenAI-SDK clients created by Agent Framework**: construct the underlying
+  client with
+  `http_client=DefaultAsyncHttpxClient(event_hooks={"request": [_stamp_feat_hook]})`.
+  Using OpenAI's `DefaultAsyncHttpxClient` preserves the SDK's redirect,
+  connection-limit, and timeout defaults; a plain `httpx.AsyncClient` must not
+  replace them. The hook adds or removes the token based on the approved pipeline
+  plus actual-origin classification. Caller-supplied clients/transports are not
+  replaced or patched.
+- **azure-core pipeline clients**: start with `AIProjectClient` paths whose
+  telemetry is confirmed ingestible. When Agent Framework constructs/configures
+  an approved pipeline, add a separate per-call `SansIOHTTPPolicy` whose
+  `on_request` performs the same actual-origin check and calls
+  `apply_feature_token()` on
+  `request.http_request.headers["User-Agent"]`. Do not stamp `SearchClient`,
+  `CosmosClient`, or another Azure client merely because it is first-party; add
+  it to the allowlist only after confirming the data path. This mirrors .NET's
+  request-time `PipelinePolicy` exactly.
+
+This fixes the frozen-at-construction problem: the token is materialised at
+**send time**, not client-init time, so it carries features activated after the
+client was created. It also confines the token to first-party endpoints. Caller-owned
+clients are not patched, and toolkit-owned clients without a supported public
+hook are outside v1 coverage.
+
+Encoding uses the RFC 7231 **comment** form `(feat=v1.<hex>)` (metadata, not a
+product token), placed after the agent-framework product token, e.g.:
+
+```text
+foundry-hosting/agent-framework-python/1.2.3 (feat=v1.2a)
+```
+
+### OpenTelemetry — not in v1
+
+An OTel span attribute carrying the same value was considered but **deferred —
+primarily for privacy, not complexity**. Unlike the first-party-only UA token, a
+span attribute broadcasts the feature-combination fingerprint into the user's
+**general** telemetry pipeline, which is commonly exported to third-party APM
+vendors (Datadog, Honeycomb, …) — re-introducing exactly the leakage the
+first-party scoping was chosen to avoid. (It also carries a cardinality footgun:
+a monotonically-growing, combinatorial value must never become a metric
+dimension.) The version prefix leaves the door open to add it later **if** the
+User-Agent path cannot answer a concrete query and there is an acceptable
+scoped/redacted variant; v1 ships the UA path only. See
+[ADR-0033 → option C](../decisions/0033-feature-usage-bitmask-user-agent.md#considered-options).
+
+## API Changes
+
+New **internal cross-package** surface in
+`agent_framework._telemetry` (not exported from `agent_framework`):
+
+- `mark_feature_used(index: int) -> None`
+- `get_feature_token() -> str | None` — returns `v<ver>.<hex>` or `None`.
+- `apply_feature_token(user_agent: str) -> str` — live, idempotent UA stamper
+  used by first-party request hooks.
+- `FEATURE_MASK_DISABLED_ENV_VAR` constant — the dedicated mask-only opt-out env
+  var name (`AGENT_FRAMEWORK_FEATURE_MASK_DISABLED`).
+
+Each package also adds a private package-local `FeatureIndex` declaration for
+the rows it owns. The dedicated mask-only opt-out and Python's existing
+whole-User-Agent opt-out gate the Python mask; see [Opt-out](#opt-out).
+
+Behavioural change to existing API:
+
+- `get_user_agent()` / `prepend_agent_framework_to_user_agent()` are
+  **unchanged** — they keep returning the base UA with no `feat=` token. The
+  token is added only by first-party request hooks via
+  `apply_feature_token()`.
+
+No breaking changes: when the mask is empty or disabled, for any non-first-party
+client, or for an injected client outside the supported-hook set, output is
+byte-for-byte identical to today.
+
+## Opt-out
+
+The dedicated mask-only opt-out is shared by both SDKs. Python also retains its
+pre-existing whole-User-Agent opt-out:
+
+| Env var | SDKs | Effect |
+| --- | --- | --- |
+| `AGENT_FRAMEWORK_FEATURE_MASK_DISABLED` | Python and .NET | disables **only** the feature mask; the base `agent-framework-<lang>/{version}` User-Agent is still sent |
+| `AGENT_FRAMEWORK_USER_AGENT_DISABLED` | Python (existing behavior) | disables the **entire** Python AF User-Agent contribution, mask included |
+
+The flags accept `true`/`1` (case-insensitive). The dedicated flag lets a
+privacy-conscious user keep contributing the SDK identity/version (useful for
+support and compat triage) while withholding the feature-usage signal. The mask
+is also disabled implicitly whenever Python's whole User-Agent is disabled. A
+new whole-User-Agent opt-out for .NET is outside this design.
+
+## E2E example
+
+```python
+from agent_framework import Agent
+from agent_framework_foundry import FoundryChatClient
+from agent_framework_openai import OpenAIChatClient
+
+# First-party (Foundry) client: request hook stamps the live feat token.
+agent = Agent(client=FoundryChatClient(...), instructions="...")
+# Agent use marks bit 0; FoundryChatClient marks bit 48
+await agent.run("Hello")
+# Outgoing request to Foundry carries:
+#   User-Agent: agent-framework-python/1.2.3 (feat=v1.<mask-at-send-time>)
+
+# Third-party client: NO feat token is added (no first-party hook).
+other = Agent(client=OpenAIChatClient(...), instructions="...")
+await other.run("Hi")
+# Outgoing request to OpenAI carries only:
+#   User-Agent: agent-framework-python/1.2.3
+```
+
+Drop only the feature mask (keep the base User-Agent):
+
+```bash
+AGENT_FRAMEWORK_FEATURE_MASK_DISABLED=true python app.py
+# Foundry request User-Agent: agent-framework-python/1.2.3   (no (feat=...) comment)
+```
+
+Python only: use the existing flag to drop its entire User-Agent contribution
+(mask included):
+
+```bash
+AGENT_FRAMEWORK_USER_AGENT_DISABLED=true python app.py
+```
+
+## .NET mapping
+
+- Core owns `FeatureUsage.MarkUsed(int index)` plus the core package's private
+  index declaration. Each optional assembly owns a private `FeatureIndex` enum
+  containing only its allocated rows. These are index positions `0..127`, not
+  `[Flags]` values; `MarkUsed` performs the shift.
+- Store the 128-bit mask as **two `long` lanes** (`low` for bits 0–63, `high`
+  for 64–127). Marking touches one lane with `Interlocked.Or` where available
+  and a small `Interlocked.CompareExchange` loop on `netstandard2.0` / `net472`.
+  Read each lane atomically. Since bits only move from zero to one, a concurrent
+  two-lane snapshot may miss a just-added bit but can never invent or clear one;
+  the next request includes it.
+- Format without depending on `UInt128`: if `high == 0`, emit `low` as lowercase
+  hex; otherwise emit `high` without leading zeros followed by `low:x16`. Cast
+  each signed lane to `ulong` before formatting so bits 63 and 127 are preserved.
+  Reject indexes outside `0..127`.
+- **Emission is stamped at request time and first-party-scoped**, matching
+  Python. The
+  existing `AgentFrameworkUserAgentPolicy` / `HostedAgentUserAgentPolicy`
+  pipeline policies already run per request — extend them to apply the same
+  approved-pipeline + actual-origin classifier, append/refresh the `(feat=...)`
+  comment only for approved destinations, and remove it on unapproved redirect
+  hops. Do not register it on third-party `IChatClient`s.
+- Same **wire format** (`v<version>.<hex>` comment, hex encoding) and the same
+  dedicated mask-only opt-out (`AGENT_FRAMEWORK_FEATURE_MASK_DISABLED`). The
+  **mask is decoded per language**: indexes are not shared, so a decoder must
+  read the language from the UA product token and select that language's table
+  before decoding. (.NET's policy was already request-time, so there is no
+  Python/.NET timing asymmetry.) Adding a .NET whole-User-Agent opt-out is
+  outside this design.
+
+## Keeping the bitmap in sync
+
+[feature-usage-bit-registry.md](feature-usage-bit-registry.md) is the published
+allocation contract. Package-local `FeatureIndex` declarations are the runtime
+implementation. There is deliberately **no shared numbering across languages**
+and **no machine-readable registry file**.
+
+One repository validation test gathers every package-local declaration for one
+language/version and parses the matching Markdown table. It asserts:
+
+1. every declared index is within `0..127`;
+2. every `(index, id)` exactly matches one registry row;
+3. the union of declarations has no duplicate/overlapping indexes;
+4. every non-reserved registry row is declared exactly once.
+
+Adding an optional-package feature therefore changes that package and the
+registry, not core. If a programmatic decoder is built later, export the table
+to JSON then.
+
+### Decoding
+
+```
+UA: agent-framework-python/1.2.3 (feat=v1.2a)
+        │                          │   └ hex mask
+        │                          └ version
+        └ language → pick the Python table (version 1)
+```
+
+Read language → pick the table; read `vN` → pick that version; `AND` the hex mask
+against each bit. Unknown bits (from a newer SDK than the decoder's copy of the
+table) are ignored.
+
+## Implementation plan (post-approval)
+
+1. **Privacy approval** — confirm the first-party-only feature-combination
+   signal, retention, access, allowed queries, and opt-out behavior before code
+   ships.
+2. **Core accumulator** — in `agent_framework/_telemetry.py` add the 128-bit
+   mask, lock, `mark_feature_used(index)`, `get_feature_token`, and
+   `apply_feature_token`; `get_user_agent()` stays base-only.
+3. **Package-local indexes + validation** — add private `FeatureIndex`
+   declarations to packages and a repository test for exact registry parity,
+   complete coverage, range, and zero overlap.
+4. **First-party request-time hooks** — use OpenAI's
+   `DefaultAsyncHttpxClient` for framework-created clients and the separate
+   azure-core `SansIOHTTPPolicy`. Require approved pipeline **and** approved
+   actual origin on every request/redirect hop. Verify custom origins and
+   cross-origin redirects never carry the token.
+5. **Mark feature usage** — call `mark_feature_used(FeatureIndex.X)` at the
+   first meaningful activation. Operational clients/providers/tools mark on
+   their first real operation; build/start points mark compositional features.
+   Constructor-only marking requires construction itself to exercise the
+   capability.
+6. **.NET parity** — package-local index enums plus the two atomic 64-bit lanes
+   with `Interlocked.Or` / compare-exchange fallback; extend existing request-time
+   Foundry UA policies through the shared destination classifier and formatter.
+7. **Docs & tests** — update package `AGENTS.md`/skills; tests for **both**
+   Python opt-out paths (dedicated mask-only and existing whole-UA), the
+   dedicated .NET mask-only opt-out, first-party scoping, and the live
+   (non-frozen) UA.
+
+## Limitations & open questions
+
+The decision-level limitations and unresolved trade-offs — reach, per-process
+(not per-call) attribution, v1 granularity, fingerprinting residue, and the OTel
+question — are owned by the ADR (the dedicated mask-only opt-out is now decided
+and included). See
+**[ADR-0033 → Limitations](../decisions/0033-feature-usage-bitmask-user-agent.md#limitations)**
+and **[Open Questions](../decisions/0033-feature-usage-bitmask-user-agent.md#open-questions-for-decider-discussion)**.
+This spec is the implementation reference; it does not re-litigate those choices.
+
+Implementation-only note:
+
+- **Per-request hook overhead is negligible** (a flag check, one Python integer
+  snapshot or two atomic .NET lane reads, and a string concat per first-party
+  request), but benchmark the hot path once if a high-QPS Foundry scenario is in
+  scope.

docs/specs/004-python-function-calling-loop.md

@@ -0,0 +1,543 @@
+---
+status: proposed
+contact: eavanvalkenburg
+date: 2026-07-27
+deciders: eavanvalkenburg
+---
+
+# Python function-calling loop contract and validation matrix
+
+## Scope
+
+This specification defines the required behavior and validation coverage for the Python function-calling loop.
+It covers:
+
+- normal local function execution;
+- streaming and non-streaming response aggregation;
+- tool approval request and resume;
+- approved, rejected, mixed, and replayed approval rounds;
+- reasoning content and opaque reasoning signatures bound to function calls;
+- history persistence and service-side continuation;
+- error, user-input, middleware-termination, and loop-limit paths;
+- provider and transport serialization of function calls and results.
+
+The primary implementation is in `python/packages/core/agent_framework/_tools.py`. History replay behavior in
+`python/packages/core/agent_framework/_sessions.py`, provider serializers, hosting packages, and UI transports are
+part of the same contract when they carry function-call loop content.
+
+## Change sensitivity
+
+This code is high risk. Small changes can produce duplicate side effects, orphaned calls or results, invalid
+provider histories, invisible streaming results, stale approval authority, or loops that never terminate.
+Dropping reasoning content that a service binds to a tool call can also make an otherwise balanced call/result
+transcript invalid.
+
+Any change to the function-calling loop or its approval/history/serialization paths must:
+
+1. identify every affected row in the scenario matrix below;
+2. add or update the corresponding regression tests;
+3. validate streaming updates, streaming finalization, and non-streaming output where applicable;
+4. validate both model-bound history and caller-visible responses;
+5. run the full core package tests plus every affected provider or transport package;
+6. run source typing, test typing, and syntax checks for every affected package;
+7. receive extra review focused on call/result pairing, exactly-once execution, and history replay.
+
+A passing narrow regression test is not sufficient evidence for changes in this area.
+
+### Contribution ownership
+
+Issues involving this code must not be picked up by external contributors without first checking with the Agent
+Framework core team. The core team must confirm the intended behavior, affected scenario-matrix rows, ownership
+across core/providers/transports, and the required validation scope before implementation starts.
+
+## Flow diagrams and code map
+
+### Main function-calling flow
+
+The main control flow deliberately has separate streaming and non-streaming methods. They share policy helpers, but
+their output mechanics differ: one returns an aggregated `ChatResponse`; the other yields `ChatResponseUpdate`
+items and is finalized by `ResponseStream`.
+
+The diagrams use only the generic distinction between **local tools**, which Agent Framework executes, and
+**hosted-service tools**, whose calls and approval decisions are owned by a remote service. Provider-specific wire
+formats and regression tests appear later in the scenario matrix.
+
+```mermaid
+flowchart TD
+    Entry["FunctionInvocationLayer.get_response(...)"]
+    Setup["Prepare middleware, options, session, budget state,<br/>and execute_function_calls partial"]
+    Enabled{"Function invocation enabled?"}
+    Direct["Delegate directly to super().get_response(...)"]
+    Mode{"stream?"}
+    NonStream["_get_response_with_function_invocation(...)"]
+    Stream["_stream_response_with_function_invocation(...)"]
+    Resolve["_resolve_approval_responses(...)<br/>runs once before the model-iteration loop"]
+    ApprovalAction{"approval action"}
+    Immediate["Return/yield terminal result or user-input request<br/>without another model call"]
+    ApprovalPolicy["Record approval executions;<br/>apply stop/function-call-limit policy"]
+    Model["Call super_get_response(...)<br/>response may contain reasoning + function_call"]
+    Process["_process_model_function_calls(...)"]
+    FunctionAction{"function-processing action"}
+    Execute["_execute_function_calls(...)"]
+    Try["_try_execute_function_calls(...)"]
+    Single["_execute_single_function_call(...)"]
+    Handle["_handle_function_call_results(...)"]
+    PostCallPolicy["Record executions; apply error/function-call-limit policy;<br/>reset required tool choice"]
+    Advance["_prepare_messages_for_next_iteration(...)"]
+    More{"iteration budget remains?"}
+    Final["Final model call with tool_choice = none<br/>and deterministic fallback if needed"]
+    Output["Return ChatResponse or complete ResponseStream"]
+
+    Entry --> Setup --> Enabled
+    Enabled -- no --> Direct
+    Enabled -- yes --> Mode
+    Mode -- no --> NonStream
+    Mode -- yes --> Stream
+    NonStream --> Resolve
+    Stream --> Resolve
+    Resolve --> ApprovalAction
+    ApprovalAction -- return --> Immediate --> Output
+    ApprovalAction -- stop --> ApprovalPolicy
+    ApprovalAction -- continue --> ApprovalPolicy
+    ApprovalPolicy --> More
+    Model --> Process
+    Process --> Execute --> Try --> Single --> Handle --> FunctionAction
+    FunctionAction -- return --> Output
+    FunctionAction -- stop --> PostCallPolicy
+    FunctionAction -- continue --> PostCallPolicy
+    PostCallPolicy --> Advance
+    Advance --> More
+    More -- yes --> Model
+    More -- no --> Final --> Output
+```
+
+Code-reading landmarks:
+
+- `get_response(...)` owns setup and selects the response mode.
+- `_get_response_with_function_invocation(...)` owns non-streaming aggregation.
+- `_stream_response_with_function_invocation(...)` owns streamed emission/finalization.
+- `_resolve_approval_responses(...)` handles only inbound approval decisions.
+- `_process_model_function_calls(...)` handles only calls from a completed model response.
+- `_try_execute_function_calls(...)` decides approval/declaration/execution behavior for a batch.
+- `_replace_approval_contents_with_results(...)` is the occurrence-aware approval transcript normalizer.
+
+### Approval pause and resume
+
+```mermaid
+sequenceDiagram
+    participant Caller
+    participant History as HistoryProvider
+    participant Layer as FunctionInvocationLayer
+    participant Tool
+    participant Model
+
+    Caller->>Layer: Initial user request
+    Layer->>Model: Messages + tools
+    Model-->>Layer: reasoning content + function_call
+    Layer->>Layer: Tool requires approval
+    Layer-->>Caller: function_call + function_approval_request
+
+    Caller->>Layer: function_approval_response
+    Layer->>Layer: Copy caller-owned messages
+    Layer->>Layer: _resolve_approval_responses(...)
+
+    alt approved
+        Layer->>Tool: Execute exactly once
+        Tool-->>Layer: result or exception
+        Layer->>Layer: Create terminal function_result
+    else rejected
+        Layer->>Layer: Create synthetic rejection function_result
+    end
+
+    Layer-->>Caller: Terminal result message/update
+
+    alt tool requests more user input
+        Layer-->>Caller: User-input request with assistant role
+    else middleware terminates
+        Layer-->>Caller: Termination result
+    else error limit reached
+        Layer->>Model: Normalized reasoning/call/result history, tools disabled
+        Model-->>Layer: Final assistant response
+        Layer-->>Caller: Final assistant response
+    else continue normally
+        Layer->>Model: Normalized reasoning/call/result history
+        Model-->>Layer: Final assistant response or another function_call
+        Layer-->>Caller: Final assistant response / continued loop
+    end
+
+    Layer-->>History: Persist caller input + returned response
+    Note over History: Later model replay filters approval request/response wrappers
+```
+
+The terminal result is caller-visible in both modes. The private normalized message copy is model-visible. The
+original caller input and earlier response remain unchanged.
+
+### Reasoning-bound function-call groups
+
+Some hosted services bind reasoning content or an opaque reasoning signature to the function call that follows it.
+For those services, reasoning is not optional decoration; it is part of the provider-valid function-call group.
+
+```mermaid
+flowchart TD
+    Response["Assistant response:<br/>reasoning content + function_call"]
+    Group["One logical reasoning/function-call group"]
+    Owner{"local or hosted-service tool?"}
+    Local["Local execution"]
+    Hosted["Hosted service owns tool execution/state"]
+    Result["Terminal function_result or hosted result"]
+    Continuation{"continuation mode"}
+    Stateless["Stateless or framework-history replay"]
+    Replayable{"reasoning payload/signature<br/>is replayable?"}
+    Replay["Replay reasoning + call + result atomically"]
+    Reject["Fail before the service call;<br/>do not send a lossy transcript"]
+    Service["Hosted-service continuation"]
+    Reference["Reference service-stored reasoning/call;<br/>send only the new result or approval decision"]
+    Compact{"compaction needed?"}
+    Atomic["Keep or exclude the complete<br/>reasoning/call/result group"]
+    Caller["Caller-visible response retains reasoning<br/>with the function-call turn"]
+
+    Response --> Group --> Owner
+    Group --> Caller
+    Owner -- local --> Local --> Result
+    Owner -- hosted service --> Hosted --> Result
+    Result --> Compact
+    Compact -- yes --> Atomic --> Continuation
+    Compact -- no --> Continuation
+    Continuation -- stateless / local history --> Stateless --> Replayable
+    Replayable -- yes --> Replay
+    Replayable -- no --> Reject
+    Continuation -- service-managed --> Service --> Reference
+```
+
+The generic contract is:
+
+- reasoning content remains ordered immediately before or alongside the function call it explains;
+- a terminal result does not replace or discard the reasoning/call portion of the active group;
+- stateless replay includes the service-required reasoning payload or opaque signature;
+- if required reasoning cannot be reconstructed, the adapter fails before sending invalid or lossy history;
+- service-managed continuation may rely on the hosted service's stored reasoning/call items and send only new
+  outputs or approval decisions;
+- compaction keeps or removes the entire reasoning/call/result group atomically.
+
+In the code, core response aggregation preserves reasoning `Content` items, compaction annotations bind reasoning to
+the tool-call group, and provider adapters serialize or reconstruct the provider-specific reasoning representation.
+
+### Approval correlation, replay, and reused ids
+
+`call_id` is not globally unique forever. The normalizer therefore tracks open logical occurrences in transcript
+order instead of keeping one global result per id.
+
+```mermaid
+flowchart TD
+    Scan["Scan normalized messages in order"]
+    Kind{"content type"}
+    Call["function_call:<br/>open a call occurrence"]
+    Request["function_approval_request"]
+    Bind{"unbound call occurrence<br/>with same call_id?"}
+    BindExisting["Bind request id to existing occurrence<br/>and remove wrapper"]
+    Duplicate{"same request identity<br/>already restored?"}
+    DropDuplicate["Remove replayed duplicate wrapper"]
+    Restore["Restore embedded function_call<br/>as a new occurrence"]
+    Placeholder["function_result with APPROVAL_PENDING:<br/>attach placeholder to open occurrence"]
+    Completed["terminal function_result:<br/>close earliest open occurrence"]
+    Response["function_approval_response"]
+    Pending{"response still pending?"}
+    RemoveOld["Remove already-resolved historical response"]
+    Decision{"approved?"}
+    Approved["Pop next execution result for this call_id"]
+    Rejected["Create synthetic rejection result"]
+    HasPlaceholder{"occurrence has placeholder?"}
+    Replace["Replace placeholder and remove response wrapper"]
+    ReplaceResponse["Replace response wrapper with terminal content"]
+    Close["Close occurrence; append terminal content<br/>to resumed response"]
+    Next["Continue scan"]
+
+    Scan --> Kind
+    Kind -- function_call --> Call --> Next
+    Kind -- approval request --> Request --> Bind
+    Bind -- yes --> BindExisting --> Next
+    Bind -- no --> Duplicate
+    Duplicate -- yes --> DropDuplicate --> Next
+    Duplicate -- no --> Restore --> Next
+    Kind -- pending placeholder --> Placeholder --> Next
+    Kind -- terminal result --> Completed --> Next
+    Kind -- approval response --> Response --> Pending
+    Pending -- no --> RemoveOld --> Next
+    Pending -- yes --> Decision
+    Decision -- yes --> Approved --> HasPlaceholder
+    Decision -- no --> Rejected --> HasPlaceholder
+    HasPlaceholder -- yes --> Replace --> Close --> Next
+    HasPlaceholder -- no --> ReplaceResponse --> Close --> Next
+    Next --> Kind
+```
+
+This flow corresponds to `_ApprovalCallOccurrence`, `_collect_approval_responses(...)`, and
+`_replace_approval_contents_with_results(...)`.
+
+### History and service-side continuation
+
+```mermaid
+flowchart LR
+    Store["History backing store<br/>(may retain approval wrappers for audit)"]
+    Load{"HistoryProvider.load_messages?"}
+    Filter["_filter_approval_control_messages(...)"]
+    Context["SessionContext model history:<br/>function_call + terminal function_result"]
+    Current["Current caller input:<br/>new function_approval_response"]
+    Layer["FunctionInvocationLayer private copy"]
+    Local{"local or hosted-service approval?"}
+    LocalResult["Execute locally and normalize to function_result"]
+    Hosted["Hosted-service adapter"]
+    StoredRequest["Prior service-issued approval request"]
+    NewResponse["Current hosted approval decision"]
+    Skip["Do not replay the stored request inline"]
+    Send["Send the approval decision exactly once"]
+    Later["Later turn"]
+    Manual["Manual-history caller"]
+
+    Store --> Load
+    Load -- yes --> Filter --> Context --> Layer
+    Load -- no --> Layer
+    Current --> Layer
+    Layer --> Local
+    Local -- local --> LocalResult --> Later
+    Local -- hosted service --> Hosted
+    StoredRequest --> Hosted --> Skip
+    NewResponse --> Hosted --> Send --> Later
+    Later --> Store
+    Manual -. owns equivalent filtering .-> Layer
+```
+
+When `load_messages=False`, no history is replayed and the history filter is intentionally not invoked. Callers
+that manually replay messages own the equivalent rule: do not resend an approval response after its terminal result.
+
+## Normative contract
+
+### Function calls and results
+
+- Every actionable local `function_call` produces exactly one terminal `function_result`, unless execution pauses
+  for a new user-input request.
+- Parallel calls retain model order in the returned transcript.
+- Reused `call_id` values are correlated by logical occurrence, not one global value per id.
+- A completed function call/result pair is inert on later turns.
+- Informational-only and declaration-only calls are not executed as local tools.
+
+### Reasoning-bound calls
+
+- Reasoning content or opaque reasoning metadata that a service binds to a function call is part of the same logical
+  group as that call and its terminal result.
+- Active function loops preserve the reasoning content, function call, function result, and final assistant output
+  in caller-visible responses.
+- Framework-managed/stateless replay includes the service-required reasoning representation before the paired call.
+- Service-managed continuation may omit inline reasoning/call items only when the hosted service already owns them.
+- Missing non-reconstructable reasoning fails explicitly before a provider request instead of silently dropping the
+  content.
+- Compaction preserves or excludes the complete reasoning/call/result group atomically.
+
+### Approval request and resume
+
+- A tool that requires approval does not execute before an approved response.
+- An approved tool executes exactly once.
+- A rejected tool executes zero times and produces one synthetic rejection `function_result` using the original
+  function `call_id`.
+- The resumed response contains the newly resolved approved and rejected terminal results before any final assistant
+  message.
+- Streaming yields the same logical result content and ordering as non-streaming output and
+  `ResponseStream.get_final_response()`.
+- The function invocation layer normalizes a private copy of caller messages. It must not mutate the caller's
+  approval `Message`, approval `Content`, or an earlier returned response.
+- Approval-time `UserInputRequiredException` and `MiddlewareTermination` return immediately without another model
+  call.
+
+### Approval control content
+
+- `function_approval_request` and `function_approval_response` are control-plane contents, not durable model
+  transcript items.
+- A current hosted approval response must be sent once on the immediate resume request.
+- A server-issued approval request must not be replayed inline during service-side continuation.
+- History providers may retain approval control contents in their backing store for audit, but base history replay
+  filters them before later model calls.
+- Callers that manually own and replay message history without a loading `HistoryProvider` must likewise omit a
+  previously submitted approval response from later continuation requests.
+
+### History and continuation
+
+- Model-bound history contains one function call/result pair per completed logical occurrence.
+- Append-only history must not replay stale approval request/response wrappers to the model.
+- Framework-managed and service-managed continuation must preserve the same logical call/result transcript.
+- A terminal result consumes the corresponding approval authority in explicit stateless replay.
+
+## Scenario-to-test matrix
+
+### Normal function invocation
+
+| Scenario | Required invariant | Primary regression test |
+|---|---|---|
+| Single non-streaming call | Call, result, and final assistant message are returned in order. | `packages/core/tests/core/test_function_invocation_logic.py::test_base_client_with_function_calling` |
+| String input | Flexible string input follows the same loop behavior. | `test_base_client_with_function_calling_string_input` |
+| Multiple sequential rounds | Each round retains one call/result pair. | `test_base_client_with_function_calling_resets` |
+| Streaming call | Call chunks, one result update, and final text are emitted in order. | `test_base_client_with_streaming_function_calling` |
+| Reasoning-bound call | Finalized output retains reasoning, function call, function result, and final text. | `test_streaming_function_calling_response_includes_reasoning_and_tool_results` |
+| Calls across response messages | Every actionable call is executed once. | `test_base_client_executes_function_calls_across_multiple_response_messages` |
+| Parallel calls | Results retain the corresponding call ids and execution count. | `test_max_function_calls_limits_parallel_invocations`, `test_streaming_multiple_function_calls_parallel_execution` |
+| Informational-only call | The call is returned but not executed or approved. | `test_informational_only_function_call_is_not_invoked`, `test_informational_only_function_call_does_not_request_approval`, `test_streaming_informational_only_function_call_is_not_invoked` |
+| Declaration-only call | The call is surfaced as user input and is not executed. | `test_declaration_only_tool` |
+| Function invocation disabled | The client bypasses the invocation loop without losing invocation kwargs. | `test_function_invocation_config_enabled_false`, `test_function_invocation_config_enabled_false_preserves_invocation_kwargs`, `test_streaming_function_invocation_config_enabled_false` |
+| Runtime tool changes | Added tools become available on the next iteration and retain approval behavior. | `test_add_tools_available_next_iteration`, `test_add_tools_with_approval_required_tool` |
+
+### Approval pause and resume
+
+| Scenario | Required invariant | Primary regression test |
+|---|---|---|
+| Initial approval request | Assistant response contains the original call and approval request; tool does not execute. | `test_approval_requests_in_assistant_message`, `test_streaming_approval_request_generated`, `test_streaming_approval_requests_in_assistant_message` |
+| Approved non-streaming resume | Result precedes final text; tool executes once; inputs remain unchanged. | `packages/core/tests/core/test_harness_tool_approval.py::test_approval_resume_returns_result_without_mutating_inputs[non-streaming-approved]` |
+| Rejected non-streaming resume | Rejection result precedes final text; tool executes zero times; inputs remain unchanged. | `test_approval_resume_returns_result_without_mutating_inputs[non-streaming-rejected]` |
+| Approved streaming resume | Result update precedes final text and final response matches non-streaming shape. | `test_approval_resume_returns_result_without_mutating_inputs[streaming-approved]`, `test_streaming_approval_resume_yields_terminal_result_before_model_text[approved]` |
+| Rejected streaming resume | Rejection result update precedes final text and tool executes zero times. | `test_approval_resume_returns_result_without_mutating_inputs[streaming-rejected]`, `test_streaming_approval_resume_yields_terminal_result_before_model_text[rejected]` |
+| Mixed approved/rejected batch | Every call gets one correctly correlated terminal result. | `packages/core/tests/core/test_function_invocation_logic.py::test_rejected_approval` |
+| Persisted approval replay | Resume executes with the prior call available. | `test_persisted_approval_messages_replay_correctly` |
+| Hosted approval pass-through | Hosted requests/responses are not processed as local calls. | `test_hosted_tool_approval_response`, `test_hosted_mcp_approval_response_passthrough`, `test_mixed_local_and_hosted_approval_flow` |
+| Approval-time user input | Every user-input request from one approved execution returns in order with assistant role and no extra model call; the execution consumes one call-budget unit. | `packages/core/tests/core/test_harness_tool_approval.py::test_approval_resume_returns_all_user_input_requests_without_another_model_call`, `packages/core/tests/core/test_function_invocation_logic.py::test_approval_resume_user_input_counts_toward_function_call_budget` |
+| Mixed terminal result and follow-up input | Completed siblings remain tool-role while only follow-up input requests use assistant-role messages/updates. | `packages/core/tests/core/test_function_invocation_logic.py::test_approval_resume_separates_terminal_results_from_follow_up_requests`, `packages/openai/tests/openai/test_openai_chat_completion_client.py::test_mixed_approval_resume_roles_serialize_function_result_as_tool` |
+| Approval-time middleware termination | Terminal result returns with no extra model call in either response mode. | `packages/core/tests/core/test_function_invocation_logic.py::test_approval_resume_honors_middleware_termination` |
+| Approval re-entry after iteration budget | Pending approved calls resolve once even when prior model calls consumed `max_iterations`. | `packages/core/tests/core/test_harness_tool_approval.py::test_auto_approval_resolves_after_iteration_budget_is_exhausted` |
+| Approval resume with reasoning | Model-bound resume history retains reasoning before the call and terminal result in both modes. | `packages/core/tests/core/test_harness_tool_approval.py::test_approval_resume_replays_reasoning_with_function_call_group` |
+
+### Approval correlation and replay
+
+| Scenario | Required invariant | Primary regression test |
+|---|---|---|
+| Result matching without placeholders | Results match calls by id even when the result list is reordered. | `test_replace_approval_contents_with_results_uses_result_call_ids_without_placeholders` |
+| Reused id after completion | A later round with the same id creates a second valid pair. | `test_replace_approval_contents_with_results_allows_reused_call_id_after_completion` |
+| Replayed approval wrapper | A duplicated wrapper does not restore another function call. | `test_replace_approval_contents_with_results_deduplicates_replayed_approval_request` |
+| Historical resolved response plus new round | The old response is removed from normalized input and is not converted into a rejection result. | `test_replace_approval_contents_with_results_ignores_already_resolved_response` |
+| Multiple reused-id rounds | Approved and rejected rounds retain separate call/result occurrences. | `test_replace_approval_contents_with_results_correlates_reused_call_id_occurrences` |
+| Multi-content result with reused id | Every content produced by one execution stays with that approval occurrence and cannot bleed into the next reused-id round. | `test_replace_approval_contents_with_results_keeps_multi_content_group_with_reused_call_id` |
+| Follow-up request closes one occurrence | A user-input follow-up consumes only the preceding approval authority and leaves a later reused-id response pending. | `test_collect_approval_responses_consumes_matching_follow_up_request_occurrence` |
+| Reused-id placeholders | Placeholder results consume approved results by occurrence. | `test_replace_approval_contents_with_results_correlates_reused_call_id_placeholders` |
+| Rejected placeholder | Rejection replaces the pending placeholder instead of adding a second result. | `test_replace_approval_contents_with_results_replaces_rejected_placeholder` |
+| Results reordered with placeholders | Results still match the correct call ids. | `test_replace_approval_contents_with_results_uses_result_call_ids_for_placeholders` |
+| Missing result call id | A malformed result does not steal another approval's result. | `test_replace_approval_contents_with_results_skips_results_without_call_id` |
+| Empty approval message cleanup | Fully consumed approval messages are removed from normalized model input. | `test_replace_approval_contents_with_results_prunes_emptied_messages` |
+| Later stateless turn | A prior terminal approval response cannot execute again. | `test_resolved_approval_response_is_inert_on_later_stateless_turn` |
+| Pending history turn | An unresolved approval batch is omitted atomically from unrelated model input while a later decision can still resume it once. | `packages/core/tests/core/test_harness_tool_approval.py::test_pending_approval_from_file_history_stays_resumable_without_model_orphan` |
+| Duplicate function-call prevention | Approval normalization does not create a second call for one round. | `test_no_duplicate_function_calls_after_approval_processing` |
+| Rejection call id | Rejection result uses the function call id, not only the approval id. | `test_rejection_result_uses_function_call_id` |
+
+### Mixed batches and approval middleware
+
+| Scenario | Required invariant | Primary regression test |
+|---|---|---|
+| Safe and approval-required calls in one batch | Hidden safe calls replay only with the matching visible approval. | `packages/core/tests/core/test_harness_tool_approval.py::test_mixed_batch_hides_already_approved_request_until_approval_replay` |
+| Restored approval state | Serialized `ToolApprovalState` restores mixed-batch behavior. | `test_mixed_batch_accepts_restored_tool_approval_state` |
+| Unrelated turn before approval | Hidden calls do not execute on an unrelated turn. | `test_hidden_mixed_batch_requests_do_not_replay_on_unrelated_turn` |
+| Multiple abandoned batches | Hidden calls replay only for the matching batch. | `test_hidden_mixed_batch_requests_replay_only_for_matching_visible_approval` |
+| Queued approvals | One unresolved approval is surfaced per run without premature execution. | `test_tool_approval_middleware_queues_multiple_approval_requests`, `test_tool_approval_middleware_queues_streamed_approval_requests` |
+| Middleware state plus hidden core state | State saves do not discard hidden mixed-batch calls. | `test_tool_approval_middleware_preserves_hidden_mixed_batch_requests` |
+| Auto-approval callback | Callback receives the original function call and executes the approved set once. | `test_tool_approval_middleware_auto_approval_rule_receives_function_call` |
+| Shared call budget | Auto-approved re-entry does not reset `max_function_calls`, and every executed approval group counts even when it pauses for input. | `test_tool_approval_middleware_auto_approved_loops_share_function_call_budget`, `test_approval_resume_user_input_counts_toward_function_call_budget` |
+| Standing tool rule | Tool-level approval applies only to later matching tools. | `test_tool_approval_middleware_always_approve_tool_rule` |
+| Hosted server boundary | Standing approval does not cross `server_label`. | `test_tool_approval_middleware_standing_rules_include_hosted_server_boundary` |
+| Argument-scoped rule | Exact arguments are required; empty arguments are not tool-wide. | `test_tool_approval_middleware_always_approve_tool_with_arguments_rule`, `test_tool_approval_middleware_empty_arguments_rule_is_not_tool_wide` |
+
+### Errors, control flow, and limits
+
+| Scenario | Required invariant | Primary regression test |
+|---|---|---|
+| Rejected execution | Rejection is a normal terminal result, not an exception to the caller. | `test_unapproved_tool_execution_raises_exception` |
+| Approved tool exception | Generic and detailed error modes preserve one result and one execution. | `test_approved_function_call_with_error_without_detailed_errors`, `test_approved_function_call_with_error_with_detailed_errors` |
+| Approved validation error | Validation failure returns one result without invoking the function body. | `test_approved_function_call_with_validation_error` |
+| Approved success | Successful approved execution returns one result. | `test_approved_function_call_successful_execution` |
+| Consecutive error cap | Error threshold stops repeated failures, submits collected results, and makes only the required final no-tool model call. | `test_function_invocation_config_max_consecutive_errors`, `test_streaming_function_invocation_config_max_consecutive_errors`, `test_approval_resume_error_limit_forces_final_no_tool_response` |
+| Unknown call handling | Configured false returns an error result; configured true raises. | `test_function_invocation_config_terminate_on_unknown_calls_false`, `test_function_invocation_config_terminate_on_unknown_calls_true`, streaming equivalents |
+| Middleware termination | Normal non-approval loop stops without a second model call. | `test_terminate_loop_single_function_call`, `test_terminate_loop_multiple_function_calls_one_terminates`, `test_terminate_loop_streaming_single_function_call` |
+| Maximum iterations | No orphan calls; a final no-tool response or deterministic fallback is returned. | `test_max_iterations_limit`, `test_max_iterations_no_orphaned_function_calls`, `test_max_iterations_makes_final_toolchoice_none_call`, `test_max_iterations_blank_final_fallback_synthesizes_message`, streaming equivalents |
+| Maximum function calls | Parallel overshoot is bounded after the batch; every executed result group counts even without a `function_result`; blank final responses get fallback content. | `test_max_function_calls_limits_parallel_invocations`, `test_max_function_calls_single_calls_per_iteration`, `test_user_input_request_multiple_contents_propagate`, `test_approval_resume_user_input_counts_toward_function_call_budget`, `test_max_function_calls_blank_final_fallback_synthesizes_message`, streaming equivalent |
+| Conversation continuation | Conversation id updates between iterations and is cleared on stop where required. | `test_conversation_id_updated_in_options_between_tool_iterations`, `test_function_invocation_stop_clears_conversation_id_non_stream`, `test_streaming_function_invocation_stop_clears_conversation_id` |
+
+### History and provider serialization
+
+| Scenario | Required invariant | Primary regression test |
+|---|---|---|
+| Append-only history replay | Resolved approval wrappers do not reach a later model call; one call/result pair remains. | `packages/core/tests/core/test_harness_tool_approval.py::test_approval_resume_filters_resolved_control_items_from_file_history` |
+| Pending placeholder history | An approval response remains replayable while its only result is `[APPROVAL_PENDING]`. | `packages/core/tests/core/test_sessions.py::test_filter_approval_controls_keeps_response_for_pending_placeholder` |
+| Pending hosted history replay | Stateless hosted approval requests remain replayable until a response is recorded, then both controls become inert. | `packages/openai/tests/openai/test_openai_chat_client.py::test_stateless_history_preserves_pending_hosted_approval_request_until_response` |
+| Non-history provider plus session | Local history is still auto-injected for approval resume. | `packages/core/tests/core/test_agents.py::test_non_history_context_provider_still_injects_inmemory` |
+| OpenAI approval serialization | Approval id and decision serialize to `mcp_approval_response`. | `test_prepare_message_for_openai_with_function_approval_response`, `test_prepare_content_for_opentool_approval_response`, `test_function_approval_response_with_mcp_tool_call` |
+| OpenAI end-to-end hosted approval | Hosted request parses, response sends, and continuation completes. | `test_end_to_end_mcp_approval_flow` |
+| Stored function call/result | Service-side storage drops server-issued calls but keeps new outputs. | `test_prepare_options_with_conversation_id_strips_server_issued_items`, `test_prepare_messages_for_openai_full_conversation_with_reasoning` |
+| Stateless reasoning replay | Replay reconstructs reasoning, call, and result together; missing required reasoning fails before the request. | `test_tool_loop_store_false_replays_encrypted_reasoning_group`, `test_stateless_request_rejects_non_replayable_reasoning_bound_mcp_output`, `test_prepare_messages_for_openai_full_conversation_with_reasoning` |
+| Opaque reasoning signature replay | Provider-specific opaque reasoning metadata is captured and restored on reconstructed calls. | `packages/gemini/tests/test_gemini_client.py::test_function_call_part_captures_thought_signature_as_reasoning_content`, `test_reconstructed_function_call_replays_thought_signature_from_reasoning_content` |
+| Chat Completions approval wrappers | Framework approval wrappers are not sent as chat messages. | `packages/openai/tests/openai/test_openai_chat_completion_client.py` approval serialization tests |
+| AG-UI approval result event | Approved result emits once with content and persists in snapshot. | `packages/ag-ui/tests/ag_ui/test_approval_result_event.py::test_approval_resume_emits_tool_call_result`, `test_approval_resume_result_has_content`, `test_approval_resume_snapshot_replaces_approval_payload_with_tool_result`, `test_approval_resume_zero_updates_emits_tool_result` |
+| AG-UI rejection/mixed decision | Transport emits only the events defined for approved and rejected calls without duplicates. | `test_rejection_does_not_emit_tool_call_result`, `test_mixed_approve_reject_emits_only_approved_tool_result`, `test_resolve_approval_responses_returns_only_approved` |
+| AG-UI approval-time follow-up | The full grouped user-input pause remains in message history and emits no synthetic `TOOL_CALL_RESULT`. | `test_resolve_approval_responses_preserves_follow_up_user_input_group` |
+| AG-UI approval execution failure | A grouped executor failure becomes one deterministic terminal error result for the approved call. | `test_resolve_approval_responses_returns_failure_when_grouped_execution_raises` |
+| AG-UI no-approval path | Ordinary tool results do not gain an extra approval result event. | `test_no_approval_no_extra_tool_result` |
+| Compaction pair integrity | Function call/result groups remain atomic. | `packages/core/tests/core/test_compaction.py::test_group_annotations_keep_tool_call_and_tool_result_atomic`, `test_group_annotations_include_reasoning_in_tool_call_group` |
+
+## Required coverage gaps
+
+These scenarios are required but are not fully covered by merged tests on `main`:
+
+| Gap | Tracking |
+|---|---|
+| Non-adjacent and reused-id call/result occurrences remain atomic during compaction. | #7212 |
+| Provider-injected approval-required tools defer until `before_run` tools exist and still emit one result. | #7043 |
+| Service-side storage sends the current approval response while omitting the stored request. | #7125 |
+| Service-owned `previous_response_id` continuation cannot execute a terminal approval again on a later turn. | #6851 |
+| A provider that ignores `tool_choice="none"` after an invocation limit cannot expose an unanswered call. | #7045 |
+| Declaration-only streaming preserves request metadata without duplicating arguments. | #6973 |
+| AG-UI `confirm_changes` cleanup correlates one result by original function call id when several results exist. | #6828 |
+
+Do not mark these rows covered by nearby tests; each needs a dedicated regression at the owning layer.
+
+## Minimum validation commands
+
+Run from `python/` for any core function-loop change:
+
+```bash
+uv run poe test -P core
+uv run poe syntax -P core
+uv run poe pyright -P core
+uv run poe test-typing -P core
+```
+
+Also run every affected package. Common approval-loop changes require:
+
+```bash
+uv run poe test -P openai
+uv run poe syntax -P openai
+uv run poe pyright -P openai
+uv run poe test-typing -P openai
+uv run poe test -P ag-ui
+uv run --directory packages/foundry_hosting poe test
+```
+
+Run focused regression files first while iterating, but do not substitute them for the full package commands above.
+
+## Review checklist
+
+Before accepting an update, reviewers must confirm:
+
+- the changed behavior is represented in this specification;
+- the matrix names a regression test for every affected scenario;
+- approved tools cannot execute twice;
+- rejected tools cannot execute;
+- no call or result becomes orphaned or duplicated;
+- call/result matching does not assume `call_id` is globally unique forever;
+- reasoning content or opaque signatures remain in the same logical group as the paired call/result, or replay fails
+  explicitly before sending a lossy provider request;
+- caller messages and previous responses remain immutable;
+- streaming updates and final response agree with non-streaming output;
+- history replay does not reintroduce approval authority;
+- full package, syntax, source typing, and test typing checks were run.
+
+## Related issues
+
+- #7241 — approval-resolution result streaming
+- #7267 / #7271 and #7304 — replayed calls and reused ids
+- #6851 — duplicate side effects after approval continuation
+- #7383 — bind approval responses to framework-issued requests after this foundation merges
+- #6963 / #7095 — opaque reasoning-signature replay
+- #6074 / #7233 — reasoning-paired tool-call replay
+- #6450 / #6794 — provider message and tool-result serialization

docs/specs/feature-usage-bit-registry.md

@@ -0,0 +1,282 @@
+# Feature-usage bit registry (per-language)
+
+> **Status:** draft, accompanies [ADR-0033](../decisions/0033-feature-usage-bitmask-user-agent.md)
+> and [SPEC-004](004-feature-usage-telemetry.md).
+> **Version:** `1` per language · **Width:** 128-bit
+
+This document is the proposed human-readable registry for the feature-usage
+mask. Until ADR-0033 is accepted and the index declarations ship, these tables
+are a **candidate mapping**, not a stable wire contract. The table is the
+allocation authority and published decoder contract; package-local private
+`FeatureIndex` declarations implement the rows they own. There is no generated
+artifact.
+
+This telemetry is intentionally **transparent**: this registry is public, the
+emitted value is human-decodable, and a dedicated env var disables the mask
+without removing the base User-Agent. Python's existing whole-User-Agent opt-out
+also suppresses its mask; see [Opt-out](#opt-out).
+
+## What is collected
+
+A single 128-bit integer (the *feature mask*) describing **which Agent Framework
+features were exercised** in a process — not which packages are installed. The
+candidate below uses package-level bits plus selected major capabilities: core
+agent/workflow/MCP features, stable skill source types, each orchestration
+pattern, each individual built-in context/history provider, and distinct Foundry
+surfaces. ADR-0033 still leaves the final v1 granularity open. A feature sets its
+index at first meaningful activation; the SDK shifts that index, ORs the mask,
+and emits the value.
+
+No identifiers, arguments, prompts, payloads, or user data are encoded — only the
+coarse Boolean \"this feature was observed at least once in this process\" per
+registered bit. A repeated bit on later requests is the same observation, not
+another use and not a count.
+
+## Allocation tenet
+
+**An index represents a stable, framework-owned capability whose adoption answers a
+concrete product or support question.** It has a clear actual-use mark point in a
+public entry path, and the privacy review covers the resulting distinction.
+
+Keep imports, installation state, aliases, wrappers, internal helpers, and
+implementation decorators such as caching/filtering/deduplication within their
+own capability bit. Customer/runtime values — names, prompts, arguments, URLs,
+identifiers, configuration choices — never become bits. A proposed distinction
+without a concrete query and named decision owner waits.
+
+Operational clients, tools, providers, and hosts mark on their first real public
+operation/participation. Constructor marking is reserved for cases where
+construction itself activates or registers the capability; DI instantiation
+alone is not usage.
+
+Ids use the package/integration name for a package-level signal and add a
+capability suffix only when the row tracks a narrower surface. They describe the
+registered feature, not an inheritance hierarchy: for example, Python
+`hosting` is the base `agent-framework-hosting` package, while `hosting.a2a` is
+the separate hosting-A2A integration.
+
+## Per-language, not shared
+
+The two tables below are **independent**. Feature indexes are **not** shared across
+languages — Python bit 13 and .NET bit 13 do not mean the same thing. This is
+deliberate: the User-Agent product token already names the language
+(`agent-framework-python` vs `agent-framework-dotnet`), so a decoder selects the
+right table from the UA and decodes against it. Each SDK numbers and evolves its
+features independently — no cross-language synchronization, no null placeholders,
+no \"same bit, same meaning\" rule.
+
+## Encoding
+
+- **Width:** 128-bit unsigned integer per language.
+- **Versioning:** the emission carries the version so a decoder knows the bit
+  mapping in effect (version is per language).
+- **User-Agent:** the mask is an RFC 7231 **comment** (metadata, not a product
+  token), placed after the agent-framework product token:
+
+  ```text
+  agent-framework-python/1.2.3 (feat=v1.<hex_mask>)
+  ```
+
+  where `<hex_mask>` is lowercase hex, no leading zeros, no `0x` prefix. Example
+  for bits 0, 1, 5 set (`0b100011 = 0x23`):
+
+  ```text
+  agent-framework-python/1.2.3 (feat=v1.23)
+  ```
+
+- **Decoding:** read the **language** from the product token, pick that table;
+  read `vN`, pick that version; test `mask & (1 << index)` for each row. Unknown indexes
+  (newer SDK than the decoder's copy) are ignored.
+
+## Emission scope (where the mask is sent)
+
+- **Marking is universal:** every feature sets its index at first meaningful
+  activation, regardless of provider.
+- **User-Agent `(feat=...)` comment — approved first-party clients only,
+  stamped at request time.** Added only when both the **Azure / Foundry**
+  client/pipeline family and the actual HTTPS origin are approved, re-evaluated
+  on every request and redirect hop. Custom origins are default-deny and an
+  unapproved redirect removes the token. It is
+  **never** sent to third-party providers — a feature fingerprint must not leak
+  into logs we cannot read. See [SPEC-004](004-feature-usage-telemetry.md#emission).
+- **OpenTelemetry: not in v1.** Deferred primarily for privacy (a span attribute
+  would broadcast the fingerprint into the user's general telemetry / third-party
+  APM vendors). Left open behind the version prefix; see
+  [ADR-0033](../decisions/0033-feature-usage-bitmask-user-agent.md#considered-options).
+
+## Index table — Python (`agent-framework-python`, version 1)
+
+Layout: core features 0–31, orchestration patterns 32–47, and
+provider/integration packages from 48.
+
+The provider/integration block is intentionally **not** partitioned by vendor
+ownership. Some packages span first- and third-party services, ownership can
+change, and protocols/storage integrations do not fit a stable first/third-party
+taxonomy. Index ranges are allocation space, not privacy or emission policy;
+the explicit destination allowlist independently ensures that the mask is sent
+only to approved first-party endpoints.
+
+| Index | Id | Feature | Activated at (representative) |
+| --- | --- | --- | --- |
+| 0 | `core.agent` | Agent | `agent_framework.Agent` |
+| 1 | `core.harness_agent` | Harness agent | `agent_framework.create_harness_agent` |
+| 2 | `core.workflow` | Workflow engine (custom graphs) | `agent_framework.WorkflowBuilder` |
+| 3 | `core.mcp` | MCP tool (any transport) | `agent_framework.MCPStdioTool` |
+| 4 | `core.tool_approval` | Tool-approval harness | `agent_framework.ToolApprovalMiddleware` |
+| 5 | `core.memory_provider` | Memory context provider | `agent_framework.MemoryContextProvider` |
+| 6 | `core.skills_provider` | Skills provider | `agent_framework.SkillsProvider` |
+| 7 | `core.file_access_provider` | File-access provider | `agent_framework.FileAccessProvider` |
+| 8 | `core.compaction_provider` | Context compaction provider | `agent_framework.CompactionProvider` |
+| 9 | `core.todo_provider` | Todo provider | `agent_framework.TodoProvider` |
+| 10 | `core.agent_mode_provider` | Agent-mode provider | `agent_framework.AgentModeProvider` |
+| 11 | `core.background_agents_provider` | Background-agents provider | `agent_framework.BackgroundAgentsProvider` |
+| 12 | `core.in_memory_history_provider` | In-memory history provider | `agent_framework.InMemoryHistoryProvider` |
+| 13 | `core.file_history_provider` | File history provider | `agent_framework.FileHistoryProvider` |
+| 14 | `core.file_skills_source` | File-backed skills | `agent_framework.FileSkillsSource` |
+| 15 | `core.in_memory_skills_source` | In-memory / programmatic skills | `agent_framework.InMemorySkillsSource` |
+| 16 | `core.mcp_skills_source` | MCP-backed skills | `agent_framework.MCPSkillsSource` |
+| 17–31 | _reserved_ | core growth | — |
+| 32 | `orchestration.sequential` | Sequential orchestration | `agent_framework_orchestrations.SequentialBuilder` |
+| 33 | `orchestration.concurrent` | Concurrent orchestration | `agent_framework_orchestrations.ConcurrentBuilder` |
+| 34 | `orchestration.group_chat` | Group-chat orchestration | `agent_framework_orchestrations.GroupChatBuilder` |
+| 35 | `orchestration.magentic` | Magentic orchestration | `agent_framework_orchestrations.MagenticBuilder` |
+| 36 | `orchestration.handoff` | Handoff orchestration | `agent_framework_orchestrations.HandoffBuilder` |
+| 37–47 | _reserved_ | orchestration growth | — |
+| 48 | `foundry.chat_client` | Foundry chat client | `agent_framework_foundry.RawFoundryChatClient` |
+| 49 | `foundry.agent` | Foundry agent | `agent_framework_foundry.FoundryAgent` |
+| 50 | `foundry.memory` | Foundry memory provider | `agent_framework_foundry.FoundryMemoryProvider` |
+| 51 | `foundry.embedding` | Foundry embedding client | `agent_framework_foundry.RawFoundryEmbeddingClient` |
+| 52 | `foundry.evals` | Foundry evaluations | `agent_framework_foundry.FoundryEvals` |
+| 53 | `foundry.toolbox` | Foundry Toolbox MCP tool | `agent_framework_foundry_hosting.FoundryToolbox` |
+| 54 | `foundry_local` | Foundry Local client | `agent_framework_foundry_local.FoundryLocalClient` |
+| 55 | `foundry_hosting` | Foundry hosting layer | `agent_framework_foundry_hosting.ResponsesHostServer` / `InvocationsHostServer` |
+| 56 | `openai` | OpenAI clients | `agent_framework_openai` |
+| 57 | `anthropic` | Anthropic clients | `agent_framework_anthropic` |
+| 58 | `bedrock` | AWS Bedrock clients | `agent_framework_bedrock` |
+| 59 | `gemini` | Gemini chat client | `agent_framework_gemini` |
+| 60 | `mistral` | Mistral embedding client | `agent_framework_mistral` |
+| 61 | `ollama` | Ollama clients | `agent_framework_ollama` |
+| 62 | `claude` | Claude Agent SDK agent | `agent_framework_claude` |
+| 63 | `copilotstudio` | Copilot Studio agent | `agent_framework_copilotstudio` |
+| 64 | `github_copilot` | GitHub Copilot agent | `agent_framework_github_copilot` |
+| 65 | `azure_ai_search` | Azure AI Search context provider | `agent_framework_azure_ai_search` |
+| 66 | `azure_cosmos` | Azure Cosmos history / checkpoint store | `agent_framework_azure_cosmos` |
+| 67 | `azure_contentunderstanding` | Azure Content Understanding context provider | `agent_framework_azure_contentunderstanding.ContentUnderstandingContextProvider` |
+| 68 | `redis` | Redis context / history provider | `agent_framework_redis` |
+| 69 | `mem0` | Mem0 memory provider | `agent_framework_mem0.Mem0ContextProvider` |
+| 70 | `purview` | Purview client | `agent_framework_purview.PurviewClient` |
+| 71 | `a2a` | A2A agent / executor | `agent_framework_a2a.A2AAgent` / `A2AExecutor` |
+| 72 | `ag_ui` | AG-UI chat client / agent | `agent_framework_ag_ui` |
+| 73 | `chatkit` | ChatKit integration | `agent_framework_chatkit` |
+| 74 | `devui` | DevUI served | `agent_framework_devui.serve` |
+| 75 | `declarative.agent` | Declarative agent definitions | `agent_framework_declarative.AgentFactory` |
+| 76 | `declarative.workflow` | Declarative workflow definitions | `agent_framework_declarative.WorkflowFactory` |
+| 77 | `durabletask` | Durable task runtime | `agent_framework_durabletask` |
+| 78 | `azurefunctions` | Azure Functions agent host | `agent_framework_azurefunctions` |
+| 79 | `tools.shell` | Shell tools | `agent_framework_tools.shell.LocalShellTool` / `DockerShellTool` |
+| 80 | `monty` | Monty CodeAct provider | `agent_framework_monty.MontyCodeActProvider` |
+| 81 | `hyperlight` | Hyperlight CodeAct provider | `agent_framework_hyperlight.HyperlightCodeActProvider` |
+| 82 | `azure_cosmos_memory` | Azure Cosmos DB semantic-memory provider | `agent_framework_azure_cosmos_memory.CosmosMemoryContextProvider` |
+| 83 | `hosting` | App-owned agent/workflow hosting state | `agent_framework_hosting.AgentState` / `WorkflowState` |
+| 84 | `hosting.a2a` | A2A hosting converters | `agent_framework_hosting_a2a.a2a_to_run` / `a2a_from_run` |
+| 85 | `hosting.mcp` | MCP hosting adapters | `agent_framework_hosting_mcp.AgentMCPTool` / `WorkflowMCPTool` |
+| 86 | `hosting.responses` | OpenAI Responses hosting converters | `agent_framework_hosting_responses.responses_to_run` |
+| 87 | `hosting.telegram` | Telegram hosting converters | `agent_framework_hosting_telegram.telegram_to_run` |
+| 88 | `lab` | Experimental Agent Framework Lab features | `agent_framework.lab` feature entry points |
+| 89–127 | _reserved_ | future packages | — |
+
+## Index table — .NET (`agent-framework-dotnet`, version 1)
+
+| Index | Id | Feature | Activated at (representative) |
+| --- | --- | --- | --- |
+| 0 | `core.agent` | Agent | `Microsoft.Agents.AI.ChatClientAgent` |
+| 1 | `core.harness_agent` | Harness agent | `Microsoft.Agents.AI.HarnessAgent` |
+| 2 | `core.workflow` | Workflow engine (custom graphs) | `Microsoft.Agents.AI.Workflows.WorkflowBuilder` |
+| 3 | `core.tool_approval` | Tool-approval agent | `Microsoft.Agents.AI.ToolApprovalAgent` |
+| 4 | `core.chat_history_memory_provider` | Chat-history memory provider | `Microsoft.Agents.AI.ChatHistoryMemoryProvider` |
+| 5 | `core.file_memory_provider` | File memory provider | `Microsoft.Agents.AI.FileMemoryProvider` |
+| 6 | `core.text_search_provider` | Text-search provider | `Microsoft.Agents.AI.TextSearchProvider` |
+| 7 | `core.file_access_provider` | File-access provider | `Microsoft.Agents.AI.FileAccessProvider` |
+| 8 | `core.skills_provider` | Skills provider | `Microsoft.Agents.AI.AgentSkillsProviderBuilder` |
+| 9 | `core.compaction_provider` | Context compaction provider | `Microsoft.Agents.AI.Compaction.CompactionProvider` |
+| 10 | `core.todo_provider` | Todo provider | `Microsoft.Agents.AI.TodoProvider` |
+| 11 | `core.agent_mode_provider` | Agent-mode provider | `Microsoft.Agents.AI.AgentModeProvider` |
+| 12 | `core.background_agents_provider` | Background-agents provider | `Microsoft.Agents.AI.BackgroundAgentsProvider` |
+| 13 | `core.in_memory_history_provider` | In-memory history provider | `Microsoft.Agents.AI.InMemoryChatHistoryProvider` |
+| 14 | `core.mcp` | MCP tasks / skills integration | `Microsoft.Agents.AI.Mcp.McpClientTaskExtensions` |
+| 15 | `core.file_skills_source` | File-backed skills | `Microsoft.Agents.AI.AgentFileSkillsSource` |
+| 16 | `core.in_memory_skills_source` | In-memory skills | `Microsoft.Agents.AI.AgentInMemorySkillsSource` |
+| 17 | `core.inline_skill` | Inline programmatic skill | `Microsoft.Agents.AI.AgentInlineSkill` |
+| 18 | `core.class_skill` | Class-based programmatic skill | `Microsoft.Agents.AI.AgentClassSkill` |
+| 19 | `core.mcp_skills_source` | MCP-backed skills | `Microsoft.Agents.AI.AgentSkillsProviderBuilderMcpExtensions.UseMcpSkills` |
+| 20–31 | _reserved_ | core growth | — |
+| 32 | `orchestration.sequential` | Sequential orchestration | `Microsoft.Agents.AI.Workflows.SequentialWorkflowBuilder` |
+| 33 | `orchestration.concurrent` | Concurrent orchestration | `Microsoft.Agents.AI.Workflows.ConcurrentWorkflowBuilder` |
+| 34 | `orchestration.group_chat` | Group-chat orchestration | `Microsoft.Agents.AI.Workflows.GroupChatWorkflowBuilder` |
+| 35 | `orchestration.magentic` | Magentic orchestration | `Microsoft.Agents.AI.Workflows.MagenticWorkflowBuilder` |
+| 36 | `orchestration.handoff` | Handoff orchestration | `Microsoft.Agents.AI.Workflows.HandoffWorkflowBuilder` |
+| 37–47 | _reserved_ | orchestration growth | — |
+| 48 | `foundry.chat_client` | Foundry chat client | `Microsoft.Agents.AI.Foundry.FoundryChatClient` |
+| 49 | `foundry.agent` | Foundry agent | `Microsoft.Agents.AI.Foundry.FoundryAgent` |
+| 50 | `foundry.memory` | Foundry memory provider | `Microsoft.Agents.AI.Foundry.FoundryMemoryProvider` |
+| 51 | `foundry.evals` | Foundry evaluations | `Microsoft.Agents.AI.Foundry.FoundryEvals` |
+| 52 | `foundry.toolbox` | Foundry Toolbox MCP tool | `Microsoft.Agents.AI.Foundry.HostedMcpToolboxAITool` |
+| 53 | `foundry_hosting` | Foundry hosting layer | `Microsoft.Agents.AI.Foundry.Hosting.FoundryHostingExtensions.AddFoundryResponses` |
+| 54 | `openai` | OpenAI integration | `Microsoft.Agents.AI.OpenAI` |
+| 55 | `anthropic` | Anthropic integration | `Microsoft.Agents.AI.Anthropic` |
+| 56 | `copilotstudio` | Copilot Studio agent | `Microsoft.Agents.AI.CopilotStudio.CopilotStudioAgent` |
+| 57 | `github_copilot` | GitHub Copilot agent | `Microsoft.Agents.AI.GitHub.Copilot.GitHubCopilotAgent` |
+| 58 | `azure_cosmos` | Cosmos history / checkpoint store | `Microsoft.Agents.AI.CosmosChatHistoryProvider` |
+| 59 | `valkey` | Valkey chat-history provider | `Microsoft.Agents.AI.Valkey.ValkeyChatHistoryProvider` |
+| 60 | `mem0` | Mem0 memory provider | `Microsoft.Agents.AI.Mem0.Mem0Provider` |
+| 61 | `purview` | Purview integration | `Microsoft.Agents.AI.Purview` |
+| 62 | `a2a` | A2A agent | `Microsoft.Agents.AI.A2A.A2AAgent` |
+| 63 | `hosting.ag_ui` | AG-UI hosting endpoint | `Microsoft.Agents.AI.Hosting.AGUI.AspNetCore.AGUIEndpointRouteBuilderExtensions.MapAGUIServer` |
+| 64 | `devui` | DevUI served | `Microsoft.Agents.AI.DevUI` |
+| 65 | `declarative.agent` | Declarative agent definitions | `Microsoft.Agents.AI.PromptAgentFactory.CreateAsync` |
+| 66 | `declarative.workflow` | Declarative workflow definitions | `Microsoft.Agents.AI.Workflows.Declarative.DeclarativeWorkflowBuilder.Build` |
+| 67 | `durabletask` | Durable task runtime | `Microsoft.Agents.AI.DurableTask` |
+| 68 | `azurefunctions` | Azure Functions agent host | `Microsoft.Agents.AI.Hosting.AzureFunctions` |
+| 69 | `tools.shell` | Shell tools | `Microsoft.Agents.AI.Tools.Shell.ShellExecutor` |
+| 70 | `hyperlight` | Hyperlight CodeAct provider | `Microsoft.Agents.AI.Hyperlight.HyperlightCodeActProvider` |
+| 71 | `hosting.agent` | Hosted AF agent wrapper | `Microsoft.Agents.AI.Hosting.AIHostAgent` |
+| 72 | `local_codeact` | Local Python CodeAct provider | `Microsoft.Agents.AI.LocalCodeAct.LocalCodeActProvider` |
+| 73 | `hosting.a2a` | A2A hosting endpoints | `Microsoft.AspNetCore.Builder.A2AEndpointRouteBuilderExtensions.MapA2AJsonRpc` |
+| 74 | `hosting.openai` | OpenAI-compatible hosting endpoints | `Microsoft.AspNetCore.Builder.MicrosoftAgentAIHostingOpenAIEndpointRouteBuilderExtensions.MapOpenAIResponses` |
+| 75–127 | _reserved_ | future packages | — |
+
+## Opt-out
+
+The dedicated mask-only environment variable is shared by both SDKs:
+
+- `AGENT_FRAMEWORK_FEATURE_MASK_DISABLED=true|1` — drops **only** the feature
+  mask; the base `agent-framework-<lang>/{version}` User-Agent is still sent.
+
+The dedicated flag lets a privacy-conscious user keep contributing SDK
+identity/version (useful for support and compatibility triage) while withholding
+the feature-usage signal. Python's existing
+`AGENT_FRAMEWORK_USER_AGENT_DISABLED=true|1` also suppresses its entire Agent
+Framework User-Agent contribution, mask included. Adding a matching .NET
+whole-User-Agent opt-out is outside this design.
+
+## Governance
+
+1. One index per package/feature, **numbered independently per language**, in the
+   table for that language. New indexes are added by editing this file in a reviewed
+   PR; indexes are never reused within a `(language, version)`.
+2. Each package owns a private `FeatureIndex` declaration containing only its
+   rows. Core owns the accumulator API and core indexes, but never imports
+   optional packages. Adding a new optional-package index therefore does not
+   require a core release once the marker API exists.
+3. Adding a feature: apply the [allocation tenet](#allocation-tenet), name the
+   concrete query/decision owner, add the package-local index and table row, and mark the
+   stable public entry point where actual use begins.
+4. Widening beyond 128-bit or re-partitioning bumps that language's version; old
+   decoders keep working because the version prefix disambiguates the mapping.
+5. A repository validation test gathers all package-local declarations for each
+   `(language, version)` and asserts exact table parity, complete non-reserved
+   coverage, `0..127` range, and **no duplicate/overlapping indexes**.
+
+> **No machine-readable registry file ships today.** Nothing consumes one at
+> runtime (packages own private declarations). If/when a programmatic decoder is built, this
+> table is the contract to export to JSON for it then.

dotnet/.github/skills/pull-requests/SKILL.md

@@ -0,0 +1,116 @@
+---
+name: pull-requests
+description: >
+  Guidance for creating pull requests and handling PR review comments in the
+  Agent Framework repository. Use this when writing a PR description (filling out
+  the PR template) or when responding to and resolving review comments on an
+  existing PR.
+---
+
+# Pull Request Workflow
+
+This skill covers two tasks: (1) writing a high-quality PR description, and
+(2) handling review comments on an existing PR.
+
+## 1. Writing the PR description
+
+Always follow the repository PR template at
+[`.github/pull_request_template.md`](../../../../.github/pull_request_template.md). Keep its
+exact structure and headings. Fill every section:
+
+### `### Motivation & Context`
+Explain *why* the change is needed: the problem it solves and the scenario it
+contributes to. Describe the net change relative to `main` — this is implied, so
+do **not** spell out "vs main" explicitly.
+
+### `### Description & Review Guide`
+Describe the changes, the overall approach, and the design. Answer the three
+prompts:
+- **What are the major changes?**
+- **What is the impact of these changes?**
+- **What do you want reviewers to focus on?** — This item is for **human
+  reviewers only**. Automated/AI reviewers must ignore it and review the entire
+  change rather than narrowing scope to it.
+
+### `### Related Issue`
+Link the issue the PR fixes using a GitHub closing keyword (`Fixes #123` /
+`Closes #123`) so it closes automatically on merge. A PR with no linked issue may
+be closed regardless of how valid the change is. Before opening, confirm there is
+no other open PR for the same issue; if there is, explain how this PR differs.
+
+### `### Contribution Checklist`
+Check every item that applies. For the breaking-change item:
+- Leave **"This is not a breaking change."** checked for the common case.
+- If the change **is** breaking, add the `breaking change` label **or** put
+  `[BREAKING]` in the title prefix, before or after a language prefix such as
+  `Python:` or `.NET:` — workflows keep the label and the title prefix in sync
+  automatically (see `.github/workflows/label-title-prefix.yml` and
+  `.github/workflows/label-pr.yml`).
+
+### Do not
+- Do **not** add ad-hoc sections such as "Validation" or "Tests run"; CI/CD and
+  the checklist already cover validation status.
+- Do **not** remove or reorder the template's headings.
+
+### Creating the PR
+Open new PRs as **drafts** until they are ready for review. Example:
+
+```bash
+gh pr create --repo microsoft/agent-framework --base main \
+  --head <your-fork-owner>:<branch> --draft \
+  --title "<concise title>" --body "<body following the template>"
+```
+
+## 2. Handling review comments
+
+When a PR receives review comments, follow this sequence — **do not start editing
+code before the user has reviewed the plan**:
+
+1. **Review the comments.** Read every review comment and thread on the PR,
+   including inline code comments and general review summaries.
+2. **Make a plan.** Produce a concrete plan describing how each comment will be
+   addressed (or why it should not be, with reasoning).
+3. **Let the user review the plan.** Present the plan and wait for the user's
+   approval or adjustments before implementing anything.
+4. **Implement.** Make the agreed changes.
+5. **Reply to every comment.** Add a reply to **all** comments explaining how it
+   was addressed (or the agreed outcome) — leave none unanswered.
+6. **Resolve resolved threads.** Mark a review thread as resolved only when the
+   comment has actually been addressed.
+
+### Useful commands
+
+List review comments and threads:
+
+```bash
+# Inline review comments
+gh api repos/{owner}/{repo}/pulls/{pr}/comments
+
+# Review threads with resolution state (GraphQL)
+gh api graphql -f query='
+  query($owner:String!,$repo:String!,$pr:Int!){
+    repository(owner:$owner,name:$repo){
+      pullRequest(number:$pr){
+        reviewThreads(first:100){
+          nodes{ id isResolved comments(first:50){ nodes{ id body author{login} } } }
+        }
+      }
+    }
+  }' -F owner={owner} -F repo={repo} -F pr={pr}
+```
+
+Reply to an inline review comment:
+
+```bash
+gh api repos/{owner}/{repo}/pulls/{pr}/comments/{comment_id}/replies \
+  -f body="Addressed in <commit>: <explanation>"
+```
+
+Resolve a review thread (needs the thread node id from the GraphQL query above):
+
+```bash
+gh api graphql -f query='
+  mutation($threadId:ID!){
+    resolveReviewThread(input:{threadId:$threadId}){ thread{ isResolved } }
+  }' -F threadId={thread_id}
+```

dotnet/.github/skills/verify-samples-tool/SKILL.md

@@ -1,4 +1,4 @@
----
+---
 name: verify-samples-tool
 description: How to use the verify-samples tool to run, verify, and manage sample definitions in the Agent Framework repository. Use this when adding, updating, or running sample verification.
 ---
@@ -157,7 +157,7 @@ new SampleDefinition
 new SampleDefinition
 {
     Name = "Agent_With_AzureOpenAIChatCompletion",
-    ProjectPath = "samples/02-agents/AgentProviders/Agent_With_AzureOpenAIChatCompletion",
+    ProjectPath = "samples/02-agents/AgentProviders/azure/Agent_With_AzureOpenAIChatCompletion",
     RequiredEnvironmentVariables = ["AZURE_OPENAI_ENDPOINT"],
     OptionalEnvironmentVariables = ["AZURE_OPENAI_DEPLOYMENT_NAME"],
     ExpectedOutputDescription =
@@ -173,11 +173,11 @@ new SampleDefinition
 ```csharp
 new SampleDefinition
 {
-    Name = "Workflow_Declarative_GenerateCode",
-    ProjectPath = "samples/03-workflows/Declarative/GenerateCode",
+    Name = "Workflow_Visualization",
+    ProjectPath = "samples/03-workflows/Visualization",
     IsDeterministic = true,
-    MustContain = ["WORKFLOW: Parsing", "WORKFLOW: Defined"],
-    ExpectedOutputDescription = ["The output should show a YAML workflow being parsed and C# code being generated from it."],
+    MustContain = ["Generating workflow visualization...", "Mermaid string:", "DiGraph string:"],
+    ExpectedOutputDescription = ["The output should show workflow visualization in Mermaid and DiGraph formats."],
 },
 ```
 
@@ -223,3 +223,5 @@ new SampleDefinition
     SkipReason = "Runs as an MCP stdio server that does not exit on its own.",
 },
 ```
+
+

dotnet/.gitignore

@@ -402,4 +402,11 @@ FodyWeavers.xsd
 *.msp
 
 # JetBrains Rider
-*.sln.iml
+*.sln.iml
+
+# Foundry agent CLI config (contains secrets, auto-generated)
+.foundry-agent.json
+.foundry-agent-build.log
+
+# Pre-published output for Docker builds
+out/

dotnet/AGENTS.md

@@ -10,6 +10,10 @@ See `./.github/skills/build-and-test/SKILL.md` for detailed instructions on buil
 
 See `./.github/skills/project-structure/SKILL.md` for an overview of the project structure.
 
+## Pull Requests
+
+See `./.github/skills/pull-requests/SKILL.md` for guidance on writing PR descriptions and handling/resolving PR review comments.
+
 ### Core types
 
 - `AIAgent`: The abstract base class that all agents derive from, providing common methods for interacting with an agent.

dotnet/Directory.Packages.props

@@ -11,8 +11,8 @@
   </PropertyGroup>
   <ItemGroup>
     <!-- Aspire.* -->
-    <PackageVersion Include="Anthropic" Version="12.13.0" />
-    <PackageVersion Include="Anthropic.Foundry" Version="0.5.0" />
+    <PackageVersion Include="Anthropic" Version="12.35.1" />
+    <PackageVersion Include="Anthropic.Foundry" Version="0.7.1" />
     <PackageVersion Include="Aspire.Hosting" Version="$(AspireAppHostSdkVersion)" />
     <PackageVersion Include="Aspire.Azure.AI.OpenAI" Version="13.0.0-preview.1.25560.3" />
     <PackageVersion Include="Aspire.Azure.AI.Inference" Version="13.1.0-preview.1.25616.3" />
@@ -21,12 +21,19 @@
     <PackageVersion Include="Aspire.Hosting.Azure.CognitiveServices" Version="$(AspireAppHostSdkVersion)" />
     <PackageVersion Include="Aspire.Microsoft.Azure.Cosmos" Version="$(AspireAppHostSdkVersion)" />
     <PackageVersion Include="CommunityToolkit.Aspire.OllamaSharp" Version="13.0.0" />
+    <PackageVersion Include="MessagePack" Version="3.1.7" /> <!-- Transitive dependency of Aspire pinned to newer version due to vulnerability in 2.5.192 -->
     <!-- Azure.* -->
-    <PackageVersion Include="Azure.AI.Projects" Version="2.0.0" />
+    <PackageVersion Include="Azure.AI.AgentServer.Core" Version="1.0.0-beta.26" />
+    <PackageVersion Include="Azure.AI.AgentServer.Invocations" Version="1.0.0-beta.5" />
+    <PackageVersion Include="Azure.AI.AgentServer.Responses" Version="1.0.0-beta.6" />
+    <PackageVersion Include="Azure.Search.Documents" Version="12.0.0" />
+    <PackageVersion Include="Azure.AI.Projects" Version="2.1.0-beta.4" />
     <PackageVersion Include="Azure.AI.Agents.Persistent" Version="1.2.0-beta.10" />
     <PackageVersion Include="Azure.AI.OpenAI" Version="2.9.0-beta.1" />
-    <PackageVersion Include="Azure.Identity" Version="1.20.0" />
-    <PackageVersion Include="Azure.Monitor.OpenTelemetry.Exporter" Version="1.4.0" />
+    <PackageVersion Include="Azure.Core" Version="1.60.0" />
+    <PackageVersion Include="Azure.Identity" Version="1.21.0" />
+    <PackageVersion Include="DotNetEnv" Version="3.1.1" />
+    <PackageVersion Include="Azure.Monitor.OpenTelemetry.Exporter" Version="1.5.0" />
     <!-- Google Gemini  -->
     <PackageVersion Include="Google.GenAI" Version="1.6.0" />
     <PackageVersion Include="Mscc.GenerativeAI.Microsoft" Version="2.9.3" />
@@ -35,43 +42,50 @@
     <!-- Newtonsoft.Json -->
     <PackageVersion Include="Newtonsoft.Json" Version="13.0.4" />
     <!-- System.* -->
-    <PackageVersion Include="Microsoft.Bcl.AsyncInterfaces" Version="10.0.6" />
+    <PackageVersion Include="Microsoft.Bcl.AsyncInterfaces" Version="10.0.9" />
     <PackageVersion Include="Microsoft.Bcl.HashCode" Version="6.0.0" />
-    <PackageVersion Include="Microsoft.Bcl.Memory" Version="10.0.4" />
-    <PackageVersion Include="System.ClientModel" Version="1.10.0" />
+    <PackageVersion Include="Microsoft.Bcl.Memory" Version="10.0.5" />
+    <PackageVersion Include="System.ClientModel" Version="1.14.0" />
     <PackageVersion Include="System.CodeDom" Version="10.0.0" />
     <PackageVersion Include="System.Collections.Immutable" Version="10.0.1" />
     <PackageVersion Include="System.CommandLine" Version="2.0.0-rc.2.25502.107" />
-    <PackageVersion Include="System.Diagnostics.DiagnosticSource" Version="10.0.6" />
-    <PackageVersion Include="System.Linq.AsyncEnumerable" Version="10.0.4" />
+    <PackageVersion Include="System.Diagnostics.DiagnosticSource" Version="10.0.9" />
+    <PackageVersion Include="System.Linq.AsyncEnumerable" Version="10.0.5" />
     <PackageVersion Include="System.Net.Http.Json" Version="10.0.0" />
-    <PackageVersion Include="System.Net.ServerSentEvents" Version="10.0.4" />
-    <PackageVersion Include="System.Text.Json" Version="10.0.6" />
-    <PackageVersion Include="System.Threading.Channels" Version="10.0.6" />
+    <PackageVersion Include="System.Net.ServerSentEvents" Version="10.0.8" />
+    <!-- AG-UI .NET SDK packages (published by the AG-UI team). -->
+    <PackageVersion Include="AGUI.Abstractions" Version="0.0.3" />
+    <PackageVersion Include="AGUI.Formatting" Version="0.0.3" />
+    <PackageVersion Include="AGUI.Protobuf" Version="0.0.3" />
+    <PackageVersion Include="AGUI.Client" Version="0.0.3" />
+    <PackageVersion Include="AGUI.Server" Version="0.0.3" />
+    <PackageVersion Include="System.Text.Json" Version="10.0.9" />
+    <PackageVersion Include="System.Threading.Channels" Version="10.0.9" />
     <PackageVersion Include="System.Threading.Tasks.Extensions" Version="4.6.3" />
     <PackageVersion Include="System.Net.Security" Version="4.3.2" />
     <!-- OpenTelemetry -->
-    <PackageVersion Include="OpenTelemetry" Version="1.14.0" />
-    <PackageVersion Include="OpenTelemetry.Api" Version="1.14.0" />
-    <PackageVersion Include="OpenTelemetry.Exporter.Console" Version="1.14.0" />
-    <PackageVersion Include="OpenTelemetry.Exporter.InMemory" Version="1.14.0" />
-    <PackageVersion Include="OpenTelemetry.Exporter.OpenTelemetryProtocol" Version="1.14.0" />
-    <PackageVersion Include="OpenTelemetry.Extensions.Hosting" Version="1.14.0" />
-    <PackageVersion Include="OpenTelemetry.Instrumentation.AspNetCore" Version="1.13.0" />
-    <PackageVersion Include="OpenTelemetry.Instrumentation.Http" Version="1.13.0" />
-    <PackageVersion Include="OpenTelemetry.Instrumentation.Runtime" Version="1.13.0" />
+    <PackageVersion Include="OpenTelemetry" Version="1.15.3" />
+    <PackageVersion Include="OpenTelemetry.Api" Version="1.15.3" />
+    <PackageVersion Include="OpenTelemetry.Exporter.Console" Version="1.15.3" />
+    <PackageVersion Include="OpenTelemetry.Exporter.InMemory" Version="1.15.3" />
+    <PackageVersion Include="OpenTelemetry.Exporter.OpenTelemetryProtocol" Version="1.15.3" />
+    <PackageVersion Include="OpenTelemetry.Extensions.Hosting" Version="1.15.3" />
+    <PackageVersion Include="OpenTelemetry.Instrumentation.AspNetCore" Version="1.15.2" />
+    <PackageVersion Include="OpenTelemetry.Instrumentation.Http" Version="1.15.1" />
+    <PackageVersion Include="OpenTelemetry.Instrumentation.Runtime" Version="1.15.1" />
     <!-- Microsoft.AspNetCore.* -->
     <PackageVersion Include="Microsoft.AspNetCore.Authentication.JwtBearer" Version="10.0.0" />
     <PackageVersion Include="Microsoft.AspNetCore.Authentication.OpenIdConnect" Version="10.0.0" />
-    <PackageVersion Include="Microsoft.AspNetCore.OpenApi" Version="10.0.0" />
+    <PackageVersion Include="Microsoft.AspNetCore.OpenApi" Version="10.0.9" />
+    <PackageVersion Include="Microsoft.OpenApi" Version="2.7.5" /> <!-- Pin patched OpenAPI.NET to remediate GHSA-v5pm-xwqc-g5wc -->
     <PackageVersion Include="Swashbuckle.AspNetCore.SwaggerUI" Version="10.0.0" />
     <!-- Microsoft.Extensions.* -->
-    <PackageVersion Include="Microsoft.Extensions.AI" Version="10.5.0" />
-    <PackageVersion Include="Microsoft.Extensions.AI.Abstractions" Version="10.5.0" />
-    <PackageVersion Include="Microsoft.Extensions.AI.Evaluation" Version="10.4.0" />
-    <PackageVersion Include="Microsoft.Extensions.AI.Evaluation.Quality" Version="10.4.0" />
-    <PackageVersion Include="Microsoft.Extensions.AI.Evaluation.Safety" Version="10.3.0-preview.1.26109.11" />
-    <PackageVersion Include="Microsoft.Extensions.AI.OpenAI" Version="10.5.0" />
+    <PackageVersion Include="Microsoft.Extensions.AI" Version="10.7.0" />
+    <PackageVersion Include="Microsoft.Extensions.AI.Abstractions" Version="10.7.0" />
+    <PackageVersion Include="Microsoft.Extensions.AI.Evaluation" Version="10.7.0" />
+    <PackageVersion Include="Microsoft.Extensions.AI.Evaluation.Quality" Version="10.7.0" />
+    <PackageVersion Include="Microsoft.Extensions.AI.Evaluation.Safety" Version="10.7.0" />
+    <PackageVersion Include="Microsoft.Extensions.AI.OpenAI" Version="10.6.0" />
     <PackageVersion Include="Microsoft.Extensions.Caching.Memory" Version="10.0.0" />
     <PackageVersion Include="Microsoft.Extensions.Compliance.Abstractions" Version="10.5.0" />
     <PackageVersion Include="Microsoft.Extensions.Configuration" Version="10.0.1" />
@@ -80,36 +94,41 @@
     <PackageVersion Include="Microsoft.Extensions.Configuration.Json" Version="10.0.1" />
     <PackageVersion Include="Microsoft.Extensions.Configuration.UserSecrets" Version="10.0.1" />
     <PackageVersion Include="Microsoft.Extensions.DependencyInjection" Version="10.0.1" />
-    <PackageVersion Include="Microsoft.Extensions.DependencyInjection.Abstractions" Version="10.0.6" />
+    <PackageVersion Include="Microsoft.Extensions.DependencyInjection.Abstractions" Version="10.0.9" />
+    <PackageVersion Include="Microsoft.Extensions.FileSystemGlobbing" Version="10.0.6" />
     <PackageVersion Include="Microsoft.Extensions.Hosting" Version="10.0.1" />
     <PackageVersion Include="Microsoft.Extensions.Http.Resilience" Version="10.0.0" />
     <PackageVersion Include="Microsoft.Extensions.Logging" Version="10.0.1" />
-    <PackageVersion Include="Microsoft.Extensions.Logging.Abstractions" Version="10.0.6" />
+    <PackageVersion Include="Microsoft.Extensions.Logging.Abstractions" Version="10.0.9" />
     <PackageVersion Include="Microsoft.Extensions.Logging.Console" Version="10.0.1" />
     <PackageVersion Include="Microsoft.Extensions.ServiceDiscovery" Version="10.0.0" />
-    <PackageVersion Include="Microsoft.Extensions.VectorData.Abstractions" Version="9.7.0" />
+    <PackageVersion Include="Microsoft.Extensions.VectorData.Abstractions" Version="10.7.0" />
     <!-- Vector Stores -->
-    <PackageVersion Include="Microsoft.SemanticKernel.Connectors.InMemory" Version="1.67.0-preview" />
-    <PackageVersion Include="Microsoft.SemanticKernel.Connectors.Qdrant" Version="1.67.0-preview" />
+    <PackageVersion Include="CommunityToolkit.VectorData.InMemory" Version="1.0.0" />
+    <PackageVersion Include="CommunityToolkit.VectorData.Qdrant" Version="1.0.0" />
     <!-- Agent SDKs -->
-    <PackageVersion Include="GitHub.Copilot.SDK" Version="0.1.29" />
+    <PackageVersion Include="GitHub.Copilot.SDK" Version="1.0.5" />
     <PackageVersion Include="Microsoft.Agents.CopilotStudio.Client" Version="1.3.171-beta" />
     <!-- M365 Agents SDK -->
     <PackageVersion Include="AdaptiveCards" Version="3.1.0" />
     <PackageVersion Include="Microsoft.Agents.Authentication.Msal" Version="1.3.171-beta" />
     <PackageVersion Include="Microsoft.Agents.Hosting.AspNetCore" Version="1.3.171-beta" />
     <!-- A2A -->
-    <PackageVersion Include="A2A" Version="0.3.4-preview" />
-    <PackageVersion Include="A2A.AspNetCore" Version="0.3.4-preview" />
+    <PackageVersion Include="A2A" Version="1.0.0-preview2" />
+    <PackageVersion Include="A2A.AspNetCore" Version="1.0.0-preview2" />
     <!-- MCP -->
-    <PackageVersion Include="ModelContextProtocol" Version="1.1.0" />
+    <PackageVersion Include="ModelContextProtocol" Version="1.2.0" />
+    <!-- Hyperlight -->
+    <PackageVersion Include="Hyperlight.HyperlightSandbox.Api" Version="0.4.0" />
+    <PackageVersion Include="Hyperlight.HyperlightSandbox.Guest.Python" Version="0.4.0" />
     <!-- Inference SDKs -->
+    <PackageVersion Include="Dapr.AI.Microsoft.Extensions" Version="1.18.4" />
     <PackageVersion Include="Microsoft.ML.OnnxRuntimeGenAI" Version="0.10.0" />
     <PackageVersion Include="Microsoft.ML.Tokenizers" Version="2.0.0" />
     <PackageVersion Include="OllamaSharp" Version="5.4.8" />
     <PackageVersion Include="OpenAI" Version="2.10.0" />
     <!-- Identity -->
-    <PackageVersion Include="Microsoft.Identity.Client.Extensions.Msal" Version="4.83.1" />
+    <PackageVersion Include="Microsoft.Identity.Client.Extensions.Msal" Version="4.84.2" />
     <!-- Workflows -->
     <PackageVersion Include="Microsoft.Agents.ObjectModel" Version="2026.2.4.1" />
     <PackageVersion Include="Microsoft.Agents.ObjectModel.Json" Version="2026.2.4.1" />
@@ -128,8 +147,15 @@
     <PackageVersion Include="Microsoft.Azure.Functions.Worker.Extensions.Http.AspNetCore" Version="2.1.0" />
     <PackageVersion Include="Microsoft.Azure.Functions.Worker.Extensions.Mcp" Version="1.0.0" />
     <PackageVersion Include="Microsoft.Azure.Functions.Worker.Sdk" Version="2.0.7" />
+    <!-- Valkey -->
     <!-- Redis -->
     <PackageVersion Include="StackExchange.Redis" Version="2.10.1" />
+    <!-- Valkey -->
+    <PackageVersion Include="Valkey.Glide" Version="1.1.0" />
+    <!-- Console UX -->
+    <PackageVersion Include="Spectre.Console" Version="0.49.1" />
+    <!-- AWS -->
+    <PackageVersion Include="AWSSDK.Extensions.Bedrock.MEAI" Version="4.0.6.10" />
     <!-- Test -->
     <PackageVersion Include="FluentAssertions" Version="8.8.0" />
     <PackageVersion Include="Microsoft.AspNetCore.TestHost" Condition="'$(TargetFramework)' == 'net8.0'" Version="8.0.22" />

dotnet/README.md

@@ -33,3 +33,4 @@ Console.WriteLine(await agent.RunAsync("Write a haiku about Microsoft Agent Fram
 - [Design Documents](../docs/design)
 - [Architectural Decision Records](../docs/decisions)
 - [MSFT Learn Docs](https://learn.microsoft.com/agent-framework/overview/agent-framework-overview)
+

dotnet/agent-framework-dotnet.slnx

@@ -1,12 +1,9 @@
-<Solution>
+<Solution>
   <Configurations>
     <BuildType Name="Debug" />
     <BuildType Name="Publish" />
     <BuildType Name="Release" />
   </Configurations>
-  <Folder Name="/src/Aspire.Hosting.AgentFramework.DevUI/">
-    <Project Path="src/Aspire.Hosting.AgentFramework.DevUI/Aspire.Hosting.AgentFramework.DevUI.csproj" />
-  </Folder>
   <Folder Name="/Samples/">
     <File Path="samples/AGENTS.md" />
     <File Path="samples/README.md" />
@@ -25,20 +22,21 @@
   </Folder>
   <Folder Name="/Samples/02-agents/AgentProviders/">
     <File Path="samples/02-agents/AgentProviders/README.md" />
-    <Project Path="samples/02-agents/AgentProviders/Agent_With_A2A/Agent_With_A2A.csproj" />
-    <Project Path="samples/02-agents/AgentProviders/Agent_With_Anthropic/Agent_With_Anthropic.csproj" />
-    <Project Path="samples/02-agents/AgentProviders/Agent_With_AzureAIAgentsPersistent/Agent_With_AzureAIAgentsPersistent.csproj" />
-    <Project Path="samples/02-agents/AgentProviders/Agent_With_AzureAIProject/Agent_With_AzureAIProject.csproj" />
-    <Project Path="samples/02-agents/AgentProviders/Agent_With_AzureFoundryModel/Agent_With_AzureFoundryModel.csproj" />
-    <Project Path="samples/02-agents/AgentProviders/Agent_With_AzureOpenAIChatCompletion/Agent_With_AzureOpenAIChatCompletion.csproj" />
-    <Project Path="samples/02-agents/AgentProviders/Agent_With_AzureOpenAIResponses/Agent_With_AzureOpenAIResponses.csproj" />
-    <Project Path="samples/02-agents/AgentProviders/Agent_With_CustomImplementation/Agent_With_CustomImplementation.csproj" />
-    <Project Path="samples/02-agents/AgentProviders/Agent_With_GitHubCopilot/Agent_With_GitHubCopilot.csproj" />
-    <Project Path="samples/02-agents/AgentProviders/Agent_With_GoogleGemini/Agent_With_GoogleGemini.csproj" />
-    <Project Path="samples/02-agents/AgentProviders/Agent_With_Ollama/Agent_With_Ollama.csproj" />
-    <Project Path="samples/02-agents/AgentProviders/Agent_With_ONNX/Agent_With_ONNX.csproj" />
-    <Project Path="samples/02-agents/AgentProviders/Agent_With_OpenAIChatCompletion/Agent_With_OpenAIChatCompletion.csproj" />
-    <Project Path="samples/02-agents/AgentProviders/Agent_With_OpenAIResponses/Agent_With_OpenAIResponses.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/a2a/Agent_With_A2A/Agent_With_A2A.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/anthropic/Agent_With_Anthropic/Agent_With_Anthropic.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/azure/Agent_With_AzureAIProject/Agent_With_AzureAIProject.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/azure/Agent_With_AzureFoundryModel/Agent_With_AzureFoundryModel.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/azure/Agent_With_AzureOpenAIChatCompletion/Agent_With_AzureOpenAIChatCompletion.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/azure/Agent_With_AzureOpenAIResponses/Agent_With_AzureOpenAIResponses.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/custom/Agent_With_CustomImplementation/Agent_With_CustomImplementation.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/dapr/Agent_With_Dapr/Agent_With_Dapr.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/github-copilot/Agent_With_GitHubCopilot/Agent_With_GitHubCopilot.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/github-copilot/Agent_With_GitHubCopilot_BYOK/Agent_With_GitHubCopilot_BYOK.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/google-gemini/Agent_With_GoogleGemini/Agent_With_GoogleGemini.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/ollama/Agent_With_Ollama/Agent_With_Ollama.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/onnx/Agent_With_ONNX/Agent_With_ONNX.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/openai/Agent_With_OpenAIChatCompletion/Agent_With_OpenAIChatCompletion.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/openai/Agent_With_OpenAIResponses/Agent_With_OpenAIResponses.csproj" />
   </Folder>
   <Folder Name="/Samples/05-end-to-end/DevUIAspireIntegration/">
     <Project Path="samples/05-end-to-end/DevUIAspireIntegration/DevUIIntegration.AppHost/DevUIIntegration.AppHost.csproj" />
@@ -67,6 +65,10 @@
     <Project Path="samples/02-agents/Agents/Agent_Step17_AdditionalAIContext/Agent_Step17_AdditionalAIContext.csproj" />
     <Project Path="samples/02-agents/Agents/Agent_Step18_CompactionPipeline/Agent_Step18_CompactionPipeline.csproj" />
     <Project Path="samples/02-agents/Agents/Agent_Step19_InFunctionLoopCheckpointing/Agent_Step19_InFunctionLoopCheckpointing.csproj" />
+    <Project Path="samples/02-agents/Agents/Agent_Step20_DynamicFunctionTools/Agent_Step20_DynamicFunctionTools.csproj" />
+    <Project Path="samples/02-agents/Agents/Agent_Step21_ShellWithEnvironment/Agent_Step21_ShellWithEnvironment.csproj" />
+    <Project Path="samples/02-agents/Agents/Agent_Step22_AgentMode/Agent_Step22_AgentMode.csproj" />
+    <Project Path="samples/02-agents/Agents/Agent_Step23_TodoList/Agent_Step23_TodoList.csproj" />
   </Folder>
   <Folder Name="/Samples/02-agents/DeclarativeAgents/">
     <Project Path="samples/02-agents/DeclarativeAgents/ChatClient/DeclarativeChatClientAgents.csproj" />
@@ -118,6 +120,23 @@
     <Project Path="samples/02-agents/AgentSkills/Agent_Step03_ClassBasedSkills/Agent_Step03_ClassBasedSkills.csproj" />
     <Project Path="samples/02-agents/AgentSkills/Agent_Step04_MixedSkills/Agent_Step04_MixedSkills.csproj" />
     <Project Path="samples/02-agents/AgentSkills/Agent_Step05_SkillsWithDI/Agent_Step05_SkillsWithDI.csproj" />
+    <Project Path="samples/02-agents/AgentSkills/Agent_Step06_McpBasedSkills/Agent_Step06_McpBasedSkills.csproj" />
+    <Project Path="samples/02-agents/AgentSkills/Agent_Step07_SkillsAutoApproval/Agent_Step07_SkillsAutoApproval.csproj" />
+  </Folder>
+  <Folder Name="/Samples/02-agents/Harness/">
+    <File Path="samples/02-agents/Harness/README.md" />
+    <Project Path="samples/02-agents/Harness/BuildYourOwnClaw/Claw_Step01_MeetYourClaw/Claw_Step01_MeetYourClaw.csproj" />
+    <Project Path="samples/02-agents/Harness/BuildYourOwnClaw/Claw_Step02_WorkingWithData/Claw_Step02_WorkingWithData.csproj" />
+    <Project Path="samples/02-agents/Harness/BuildYourOwnClaw/Claw_Step03_ScalingCapabilities/Claw_Step03_ScalingCapabilities.csproj" />
+    <Project Path="samples/02-agents/Harness/ConsoleReactiveComponents/ConsoleReactiveComponents.csproj" />
+    <Project Path="samples/02-agents/Harness/ConsoleReactiveFramework/ConsoleReactiveFramework.csproj" />
+    <Project Path="samples/02-agents/Harness/Harness_Shared_Console/Harness_Shared_Console.csproj" />
+    <Project Path="samples/02-agents/Harness/Harness_Shared_Console_OpenAI/Harness_Shared_Console_OpenAI.csproj" />
+    <Project Path="samples/02-agents/Harness/Harness_Step01_Research/Harness_Step01_Research.csproj" />
+    <Project Path="samples/02-agents/Harness/Harness_Step02_Research_WithBackgroundAgents/Harness_Step02_Research_WithBackgroundAgents.csproj" />
+    <Project Path="samples/02-agents/Harness/Harness_Step03_DataProcessing/Harness_Step03_DataProcessing.csproj" />
+    <Project Path="samples/02-agents/Harness/Harness_Step04_CodeExecution/Harness_Step04_CodeExecution.csproj" />
+    <Project Path="samples/02-agents/Harness/Harness_Step05_Loop/Harness_Step05_Loop.csproj" />
   </Folder>
   <Folder Name="/Samples/02-agents/AGUI/Step05_StateManagement/">
     <Project Path="samples/02-agents/AGUI/Step05_StateManagement/Client/Client.csproj" />
@@ -127,63 +146,74 @@
     <File Path="samples/02-agents/DevUI/README.md" />
     <Project Path="samples/02-agents/DevUI/DevUI_Step01_BasicUsage/DevUI_Step01_BasicUsage.csproj" />
   </Folder>
-  <Folder Name="/Samples/02-agents/AgentWithAnthropic/">
-    <File Path="samples/02-agents/AgentWithAnthropic/README.md" />
-    <Project Path="samples/02-agents/AgentWithAnthropic/Agent_Anthropic_Step01_Running/Agent_Anthropic_Step01_Running.csproj" />
-    <Project Path="samples/02-agents/AgentWithAnthropic/Agent_Anthropic_Step02_Reasoning/Agent_Anthropic_Step02_Reasoning.csproj" />
-    <Project Path="samples/02-agents/AgentWithAnthropic/Agent_Anthropic_Step03_UsingFunctionTools/Agent_Anthropic_Step03_UsingFunctionTools.csproj" />
-    <Project Path="samples/02-agents/AgentWithAnthropic/Agent_Anthropic_Step04_UsingSkills/Agent_Anthropic_Step04_UsingSkills.csproj" />
+  <Folder Name="/Samples/02-agents/AgentProviders/anthropic/">
+    <File Path="samples/02-agents/AgentProviders/anthropic/README.md" />
+    <Project Path="samples/02-agents/AgentProviders/anthropic/Agent_Anthropic_Step01_Running/Agent_Anthropic_Step01_Running.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/anthropic/Agent_Anthropic_Step02_Reasoning/Agent_Anthropic_Step02_Reasoning.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/anthropic/Agent_Anthropic_Step03_UsingFunctionTools/Agent_Anthropic_Step03_UsingFunctionTools.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/anthropic/Agent_Anthropic_Step04_UsingSkills/Agent_Anthropic_Step04_UsingSkills.csproj" />
   </Folder>
-  <Folder Name="/Samples/02-agents/AgentsWithFoundry/">
-    <File Path="samples/02-agents/AgentsWithFoundry/README.md" />
-    <Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step00_FoundryAgentLifecycle/Agent_Step00_FoundryAgentLifecycle.csproj" />
-    <Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step01_Basics/Agent_Step01_Basics.csproj" />
-    <Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step02.1_MultiturnConversation/Agent_Step02.1_MultiturnConversation.csproj" />
-    <Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step02.2_MultiturnWithServerConversations/Agent_Step02.2_MultiturnWithServerConversations.csproj" />
-    <Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step03_UsingFunctionTools/Agent_Step03_UsingFunctionTools.csproj" />
-    <Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step04_UsingFunctionToolsWithApprovals/Agent_Step04_UsingFunctionToolsWithApprovals.csproj" />
-    <Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step05_StructuredOutput/Agent_Step05_StructuredOutput.csproj" />
-    <Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step06_PersistedConversations/Agent_Step06_PersistedConversations.csproj" />
-    <Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step07_Observability/Agent_Step07_Observability.csproj" />
-    <Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step08_DependencyInjection/Agent_Step08_DependencyInjection.csproj" />
-    <Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step09_UsingMcpClientAsTools/Agent_Step09_UsingMcpClientAsTools.csproj" />
-    <Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step10_UsingImages/Agent_Step10_UsingImages.csproj" />
-    <Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step11_AsFunctionTool/Agent_Step11_AsFunctionTool.csproj" />
-    <Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step12_Middleware/Agent_Step12_Middleware.csproj" />
-    <Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step13_Plugins/Agent_Step13_Plugins.csproj" />
-    <Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step14_CodeInterpreter/Agent_Step14_CodeInterpreter.csproj" />
-    <Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step15_ComputerUse/Agent_Step15_ComputerUse.csproj" />
-    <Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step16_FileSearch/Agent_Step16_FileSearch.csproj" />
-    <Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step17_OpenAPITools/Agent_Step17_OpenAPITools.csproj" />
-    <Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step18_BingCustomSearch/Agent_Step18_BingCustomSearch.csproj" />
-    <Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step19_SharePoint/Agent_Step19_SharePoint.csproj" />
-    <Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step20_MicrosoftFabric/Agent_Step20_MicrosoftFabric.csproj" />
-    <Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step21_WebSearch/Agent_Step21_WebSearch.csproj" />
-    <Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step22_MemorySearch/Agent_Step22_MemorySearch.csproj" />
-    <Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step23_LocalMCP/Agent_Step23_LocalMCP.csproj" />
-    <Project Path="samples/02-agents/AgentsWithFoundry/Agent_Step24_CodeInterpreterFileDownload/Agent_Step24_CodeInterpreterFileDownload.csproj" />
+  <Folder Name="/Samples/02-agents/AgentProviders/foundry/">
+    <File Path="samples/02-agents/AgentProviders/foundry/README.md" />
+    <Project Path="samples/02-agents/AgentProviders/foundry/Agent_Step00_FoundryAgentLifecycle/Agent_Step00_FoundryAgentLifecycle.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/foundry/Agent_Step01_Basics/Agent_Step01_Basics.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/foundry/Agent_Step02.1_MultiturnConversation/Agent_Step02.1_MultiturnConversation.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/foundry/Agent_Step02.2_MultiturnWithServerConversations/Agent_Step02.2_MultiturnWithServerConversations.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/foundry/Agent_Step03_UsingFunctionTools/Agent_Step03_UsingFunctionTools.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/foundry/Agent_Step04_UsingFunctionToolsWithApprovals/Agent_Step04_UsingFunctionToolsWithApprovals.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/foundry/Agent_Step05_StructuredOutput/Agent_Step05_StructuredOutput.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/foundry/Agent_Step06_PersistedConversations/Agent_Step06_PersistedConversations.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/foundry/Agent_Step07_Observability/Agent_Step07_Observability.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/foundry/Agent_Step08_DependencyInjection/Agent_Step08_DependencyInjection.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/foundry/Agent_Step09_UsingMcpClientAsTools/Agent_Step09_UsingMcpClientAsTools.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/foundry/Agent_Step10_UsingImages/Agent_Step10_UsingImages.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/foundry/Agent_Step11_AsFunctionTool/Agent_Step11_AsFunctionTool.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/foundry/Agent_Step12_Middleware/Agent_Step12_Middleware.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/foundry/Agent_Step13_Plugins/Agent_Step13_Plugins.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/foundry/Agent_Step14_CodeInterpreter/Agent_Step14_CodeInterpreter.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/foundry/Agent_Step15_ComputerUse/Agent_Step15_ComputerUse.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/foundry/Agent_Step16_FileSearch/Agent_Step16_FileSearch.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/foundry/Agent_Step17_OpenAPITools/Agent_Step17_OpenAPITools.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/foundry/Agent_Step18_BingCustomSearch/Agent_Step18_BingCustomSearch.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/foundry/Agent_Step19_SharePoint/Agent_Step19_SharePoint.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/foundry/Agent_Step20_MicrosoftFabric/Agent_Step20_MicrosoftFabric.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/foundry/Agent_Step21_WebSearch/Agent_Step21_WebSearch.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/foundry/Agent_Step22_MemorySearch/Agent_Step22_MemorySearch.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/foundry/Agent_Step23_LocalMCP/Agent_Step23_LocalMCP.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/foundry/Agent_Step24_CodeInterpreterFileDownload/Agent_Step24_CodeInterpreterFileDownload.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/foundry/Agent_Step25_FoundryToolboxMcp/Agent_Step25_FoundryToolboxMcp.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/foundry/Agent_Step26_FoundryToolboxMcpSkills/Agent_Step26_FoundryToolboxMcpSkills.csproj" />
   </Folder>
   <Folder Name="/Samples/02-agents/Evaluation/">
-    <Project Path="samples/02-agents/Evaluation/Evaluation_SimpleEval/Evaluation_SimpleEval.csproj" />
     <Project Path="samples/02-agents/Evaluation/Evaluation_CustomEvals/Evaluation_CustomEvals.csproj" />
     <Project Path="samples/02-agents/Evaluation/Evaluation_ExpectedOutputs/Evaluation_ExpectedOutputs.csproj" />
     <Project Path="samples/02-agents/Evaluation/Evaluation_Multimodal/Evaluation_Multimodal.csproj" />
+    <Project Path="samples/02-agents/Evaluation/Evaluation_SimpleEval/Evaluation_SimpleEval.csproj" />
+  </Folder>
+  <Folder Name="/Samples/02-agents/AgentWithCodeAct/">
+    <File Path="samples/02-agents/AgentWithCodeAct/README.md" />
+    <Project Path="samples/02-agents/AgentWithCodeAct/AgentWithCodeAct_Step01_Interpreter/AgentWithCodeAct_Step01_Interpreter.csproj" />
+    <Project Path="samples/02-agents/AgentWithCodeAct/AgentWithCodeAct_Step02_ToolEnabled/AgentWithCodeAct_Step02_ToolEnabled.csproj" />
+    <Project Path="samples/02-agents/AgentWithCodeAct/AgentWithCodeAct_Step03_ManualWiring/AgentWithCodeAct_Step03_ManualWiring.csproj" />
   </Folder>
   <Folder Name="/Samples/02-agents/AgentWithMemory/">
     <File Path="samples/02-agents/AgentWithMemory/README.md" />
     <Project Path="samples/02-agents/AgentWithMemory/AgentWithMemory_Step01_ChatHistoryMemory/AgentWithMemory_Step01_ChatHistoryMemory.csproj" />
     <Project Path="samples/02-agents/AgentWithMemory/AgentWithMemory_Step02_MemoryUsingMem0/AgentWithMemory_Step02_MemoryUsingMem0.csproj" />
+    <Project Path="samples/02-agents/AgentWithMemory/AgentWithMemory_Step03_MemoryUsingValkey/AgentWithMemory_Step03_MemoryUsingValkey.csproj" />
+    <Project Path="samples/02-agents/AgentWithMemory/AgentWithMemory_Step03_MemoryUsingValkey_Bedrock/AgentWithMemory_Step03_MemoryUsingValkey_Bedrock.csproj" />
     <Project Path="samples/02-agents/AgentWithMemory/AgentWithMemory_Step04_MemoryUsingFoundry/AgentWithMemory_Step04_MemoryUsingFoundry.csproj" />
     <Project Path="samples/02-agents/AgentWithMemory/AgentWithMemory_Step05_BoundedChatHistory/AgentWithMemory_Step05_BoundedChatHistory.csproj" />
+    <Project Path="samples/02-agents/AgentWithMemory/AgentWithMemory_Step06_MemoryUsingAgentMemory/AgentWithMemory_Step06_MemoryUsingAgentMemory.csproj" />
   </Folder>
-  <Folder Name="/Samples/02-agents/AgentWithOpenAI/">
-    <File Path="samples/02-agents/AgentWithOpenAI/README.md" />
-    <Project Path="samples/02-agents/AgentWithOpenAI/Agent_OpenAI_Step01_Running/Agent_OpenAI_Step01_Running.csproj" />
-    <Project Path="samples/02-agents/AgentWithOpenAI/Agent_OpenAI_Step02_Reasoning/Agent_OpenAI_Step02_Reasoning.csproj" />
-    <Project Path="samples/02-agents/AgentWithOpenAI/Agent_OpenAI_Step03_CreateFromChatClient/Agent_OpenAI_Step03_CreateFromChatClient.csproj" />
-    <Project Path="samples/02-agents/AgentWithOpenAI/Agent_OpenAI_Step04_CreateFromOpenAIResponseClient/Agent_OpenAI_Step04_CreateFromOpenAIResponseClient.csproj" />
-    <Project Path="samples/02-agents/AgentWithOpenAI/Agent_OpenAI_Step05_Conversation/Agent_OpenAI_Step05_Conversation.csproj" />
-    <Project Path="samples/02-agents/AgentWithOpenAI/Agent_OpenAI_Step06_CodeInterpreterFileDownload/Agent_OpenAI_Step06_CodeInterpreterFileDownload.csproj" />
+  <Folder Name="/Samples/02-agents/AgentProviders/openai/">
+    <File Path="samples/02-agents/AgentProviders/openai/README.md" />
+    <Project Path="samples/02-agents/AgentProviders/openai/Agent_OpenAI_Step01_Running/Agent_OpenAI_Step01_Running.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/openai/Agent_OpenAI_Step02_Reasoning/Agent_OpenAI_Step02_Reasoning.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/openai/Agent_OpenAI_Step03_CreateFromChatClient/Agent_OpenAI_Step03_CreateFromChatClient.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/openai/Agent_OpenAI_Step04_CreateFromOpenAIResponseClient/Agent_OpenAI_Step04_CreateFromOpenAIResponseClient.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/openai/Agent_OpenAI_Step05_Conversation/Agent_OpenAI_Step05_Conversation.csproj" />
+    <Project Path="samples/02-agents/AgentProviders/openai/Agent_OpenAI_Step06_CodeInterpreterFileDownload/Agent_OpenAI_Step06_CodeInterpreterFileDownload.csproj" />
   </Folder>
   <Folder Name="/Samples/02-agents/AgentWithRAG/">
     <File Path="samples/02-agents/AgentWithRAG/README.md" />
@@ -195,6 +225,8 @@
   </Folder>
   <Folder Name="/Samples/02-agents/ModelContextProtocol/">
     <File Path="samples/02-agents/ModelContextProtocol/README.md" />
+    <Project Path="samples/02-agents/ModelContextProtocol/Agent_MCP_LongRunningTask_Client/Agent_MCP_LongRunningTask_Client.csproj" />
+    <Project Path="samples/02-agents/ModelContextProtocol/Agent_MCP_PerRun_AuthHeaders/Agent_MCP_PerRun_AuthHeaders.csproj" />
     <Project Path="samples/02-agents/ModelContextProtocol/Agent_MCP_Server/Agent_MCP_Server.csproj" />
     <Project Path="samples/02-agents/ModelContextProtocol/Agent_MCP_Server_Auth/Agent_MCP_Server_Auth.csproj" />
     <Project Path="samples/02-agents/ModelContextProtocol/FoundryAgent_Hosted_MCP/FoundryAgent_Hosted_MCP.csproj" />
@@ -217,16 +249,17 @@
   </Folder>
   <Folder Name="/Samples/03-workflows/Declarative/">
     <File Path="samples/03-workflows/Declarative/README.md" />
+    <Project Path="samples/03-workflows/Declarative/AotCheckpointing/AotCheckpointing.csproj" />
     <Project Path="samples/03-workflows/Declarative/ConfirmInput/ConfirmInput.csproj" />
     <Project Path="samples/03-workflows/Declarative/CustomerSupport/CustomerSupport.csproj" />
     <Project Path="samples/03-workflows/Declarative/DeepResearch/DeepResearch.csproj" />
-    <Project Path="samples/03-workflows/Declarative/ExecuteCode/ExecuteCode.csproj" />
     <Project Path="samples/03-workflows/Declarative/ExecuteWorkflow/ExecuteWorkflow.csproj" />
     <Project Path="samples/03-workflows/Declarative/FunctionTools/FunctionTools.csproj" />
-    <Project Path="samples/03-workflows/Declarative/GenerateCode/GenerateCode.csproj" />
     <Project Path="samples/03-workflows/Declarative/HostedWorkflow/HostedWorkflow.csproj" />
     <Project Path="samples/03-workflows/Declarative/InputArguments/InputArguments.csproj" />
+    <Project Path="samples/03-workflows/Declarative/InvokeFoundryToolboxMcp/InvokeFoundryToolboxMcp.csproj" />
     <Project Path="samples/03-workflows/Declarative/InvokeFunctionTool/InvokeFunctionTool.csproj" />
+    <Project Path="samples/03-workflows/Declarative/InvokeHttpRequest/InvokeHttpRequest.csproj" />
     <Project Path="samples/03-workflows/Declarative/InvokeMcpTool/InvokeMcpTool.csproj" />
     <Project Path="samples/03-workflows/Declarative/Marketing/Marketing.csproj" />
     <Project Path="samples/03-workflows/Declarative/StudentTeacher/StudentTeacher.csproj" />
@@ -262,6 +295,7 @@
   </Folder>
   <Folder Name="/Samples/03-workflows/Orchestration/">
     <Project Path="samples/03-workflows/Orchestration/Handoff/Handoff.csproj" />
+    <Project Path="samples/03-workflows/Orchestration/Magentic/Magentic.csproj" />
   </Folder>
   <Folder Name="/Samples/03-workflows/Observability/">
     <Project Path="samples/03-workflows/Observability/ApplicationInsights/ApplicationInsights.csproj" />
@@ -282,8 +316,90 @@
   </Folder>
   <Folder Name="/Samples/03-workflows/Evaluation/">
     <Project Path="samples/03-workflows/Evaluation/Evaluation_WorkflowEval/Evaluation_WorkflowEval.csproj" />
+    <Project Path="samples/03-workflows/Evaluation/Evaluation_WorkflowExpectedOutputs/Evaluation_WorkflowExpectedOutputs.csproj" />
   </Folder>
   <Folder Name="/Samples/04-hosting/" />
+  <Folder Name="/Samples/04-hosting/af-hosting/">
+    <File Path="samples/04-hosting/af-hosting/README.md" />
+  </Folder>
+  <Folder Name="/Samples/04-hosting/af-hosting/local_responses/">
+    <File Path="samples/04-hosting/af-hosting/local_responses/README.md" />
+    <Project Path="samples/04-hosting/af-hosting/local_responses/Server/Server.csproj" />
+    <Project Path="samples/04-hosting/af-hosting/local_responses/Client/Client.csproj" />
+  </Folder>
+  <Folder Name="/Samples/04-hosting/af-hosting/local_responses_workflow/">
+    <File Path="samples/04-hosting/af-hosting/local_responses_workflow/README.md" />
+    <Project Path="samples/04-hosting/af-hosting/local_responses_workflow/Server/Server.csproj" />
+    <Project Path="samples/04-hosting/af-hosting/local_responses_workflow/Client/Client.csproj" />
+  </Folder>
+  <Folder Name="/Samples/04-hosting/FoundryHostedAgents/" />
+  <Folder Name="/Samples/04-hosting/FoundryHostedAgents/invocations/" />
+  <Folder Name="/Samples/04-hosting/FoundryHostedAgents/invocations/Hosted-Invocations-EchoAgent/">
+    <Project Path="samples/04-hosting/FoundryHostedAgents/invocations/Hosted-Invocations-EchoAgent/Hosted-Invocations-EchoAgent.csproj" />
+  </Folder>
+  <Folder Name="/Samples/04-hosting/FoundryHostedAgents/invocations/Using-Samples/">
+    <Project Path="samples/04-hosting/FoundryHostedAgents/invocations/Using-Samples/SimpleInvocationsAgent/SimpleInvocationsAgent.csproj" />
+  </Folder>
+  <Folder Name="/Samples/04-hosting/FoundryHostedAgents/responses/" />
+  <Folder Name="/Samples/04-hosting/FoundryHostedAgents/responses/Hosted-ChatClientAgent/">
+    <Project Path="samples/04-hosting/FoundryHostedAgents/responses/Hosted-ChatClientAgent/HostedChatClientAgent.csproj" />
+  </Folder>
+  <Folder Name="/Samples/04-hosting/FoundryHostedAgents/responses/Hosted-ChatClientAgent-Dockerfile/">
+    <Project Path="samples/04-hosting/FoundryHostedAgents/responses/Hosted-ChatClientAgent-Dockerfile/HostedChatClientAgentDocker.csproj" />
+  </Folder>
+  <Folder Name="/Samples/04-hosting/FoundryHostedAgents/responses/Hosted-FoundryAgent/">
+    <Project Path="samples/04-hosting/FoundryHostedAgents/responses/Hosted-FoundryAgent/HostedFoundryAgent.csproj" />
+  </Folder>
+  <Folder Name="/Samples/04-hosting/FoundryHostedAgents/responses/Hosted-Files/">
+    <Project Path="samples/04-hosting/FoundryHostedAgents/responses/Hosted-Files/HostedFiles.csproj" />
+  </Folder>
+  <Folder Name="/Samples/04-hosting/FoundryHostedAgents/responses/Hosted-LocalTools/">
+    <Project Path="samples/04-hosting/FoundryHostedAgents/responses/Hosted-LocalTools/HostedLocalTools.csproj" />
+  </Folder>
+  <Folder Name="/Samples/04-hosting/FoundryHostedAgents/responses/Hosted-LocalCodeAct/">
+    <Project Path="samples/04-hosting/FoundryHostedAgents/responses/Hosted-LocalCodeAct/HostedLocalCodeAct.csproj" />
+  </Folder>
+  <Folder Name="/Samples/04-hosting/FoundryHostedAgents/responses/Hosted-McpTools/">
+    <Project Path="samples/04-hosting/FoundryHostedAgents/responses/Hosted-McpTools/HostedMcpTools.csproj" />
+  </Folder>
+  <Folder Name="/Samples/04-hosting/FoundryHostedAgents/responses/Hosted-MemoryAgent/">
+    <Project Path="samples/04-hosting/FoundryHostedAgents/responses/Hosted-MemoryAgent/HostedMemoryAgent.csproj" />
+  </Folder>
+  <Folder Name="/Samples/04-hosting/FoundryHostedAgents/responses/Hosted-Observability/">
+    <Project Path="samples/04-hosting/FoundryHostedAgents/responses/Hosted-Observability/HostedObservability.csproj" />
+  </Folder>
+  <Folder Name="/Samples/04-hosting/FoundryHostedAgents/responses/Hosted_Shared_Contributor_Setup/">
+    <Project Path="samples/04-hosting/FoundryHostedAgents/responses/Hosted_Shared_Contributor_Setup/Hosted_Shared_Contributor_Setup.csproj" />
+  </Folder>
+  <Folder Name="/Samples/04-hosting/FoundryHostedAgents/responses/Hosted-Toolbox/">
+    <Project Path="samples/04-hosting/FoundryHostedAgents/responses/Hosted-Toolbox/HostedToolbox.csproj" />
+  </Folder>
+  <Folder Name="/Samples/04-hosting/FoundryHostedAgents/responses/Hosted-Toolbox-AuthPaths/">
+    <Project Path="samples/04-hosting/FoundryHostedAgents/responses/Hosted-Toolbox-AuthPaths/Hosted-Toolbox-AuthPaths.csproj" />
+  </Folder>
+  <Folder Name="/Samples/04-hosting/FoundryHostedAgents/responses/Hosted-ToolboxMcpSkills/">
+    <Project Path="samples/04-hosting/FoundryHostedAgents/responses/Hosted-ToolboxMcpSkills/HostedToolboxMcpSkills.csproj" />
+  </Folder>
+  <Folder Name="/Samples/04-hosting/FoundryHostedAgents/responses/Hosted-AzureSearchRag/">
+    <Project Path="samples/04-hosting/FoundryHostedAgents/responses/Hosted-AzureSearchRag/HostedAzureSearchRag.csproj" />
+  </Folder>
+  <Folder Name="/Samples/04-hosting/FoundryHostedAgents/responses/Hosted-TextRag/">
+    <Project Path="samples/04-hosting/FoundryHostedAgents/responses/Hosted-TextRag/HostedTextRag.csproj" />
+  </Folder>
+  <Folder Name="/Samples/04-hosting/FoundryHostedAgents/responses/Hosted-Workflow-Simple/">
+    <Project Path="samples/04-hosting/FoundryHostedAgents/responses/Hosted-Workflow-Simple/HostedWorkflowSimple.csproj" />
+  </Folder>
+  <Folder Name="/Samples/04-hosting/FoundryHostedAgents/responses/Using-Samples/">
+    <Project Path="samples/04-hosting/FoundryHostedAgents/responses/Using-Samples/Hosted-Toolbox-AuthPaths-Client/Hosted-Toolbox-AuthPaths-Client.csproj" />
+    <Project Path="samples/04-hosting/FoundryHostedAgents/responses/Using-Samples/SessionFilesClient/SessionFilesClient.csproj" />
+    <Project Path="samples/04-hosting/FoundryHostedAgents/responses/Using-Samples/SimpleAgent/SimpleAgent.csproj" />
+  </Folder>
+  <Folder Name="/Samples/04-hosting/FoundryHostedAgents/responses/Hosted-Workflow-Handoff/">
+    <Project Path="samples/04-hosting/FoundryHostedAgents/responses/Hosted-Workflow-Handoff/HostedWorkflowHandoff.csproj" />
+  </Folder>
+  <Folder Name="/Samples/04-hosting/FoundryHostedAgents/responses/Hosted-AgentSkills/">
+    <Project Path="samples/04-hosting/FoundryHostedAgents/responses/Hosted-AgentSkills/HostedAgentSkills.csproj" />
+  </Folder>
   <Folder Name="/Samples/04-hosting/DurableAgents/" />
   <Folder Name="/Samples/04-hosting/DurableAgents/AzureFunctions/">
     <File Path="samples/04-hosting/DurableAgents/AzureFunctions/.editorconfig" />
@@ -307,19 +423,22 @@
     <Project Path="samples/04-hosting/DurableAgents/ConsoleApps/06_LongRunningTools/06_LongRunningTools.csproj" />
     <Project Path="samples/04-hosting/DurableAgents/ConsoleApps/07_ReliableStreaming/07_ReliableStreaming.csproj" />
   </Folder>
-  <Folder Name="/Samples/04-hosting/A2A/">
-    <File Path="samples/04-hosting/A2A/README.md" />
-    <Project Path="samples/04-hosting/A2A/A2AAgent_AsFunctionTools/A2AAgent_AsFunctionTools.csproj" />
-    <Project Path="samples/04-hosting/A2A/A2AAgent_PollingForTaskCompletion/A2AAgent_PollingForTaskCompletion.csproj" />
+  <Folder Name="/Samples/02-agents/A2A/">
+    <File Path="samples/02-agents/A2A/README.md" />
+    <Project Path="samples/02-agents/A2A/A2AAgent_AsFunctionTools/A2AAgent_AsFunctionTools.csproj" />
+    <Project Path="samples/02-agents/A2A/A2AAgent_PollingForTaskCompletion/A2AAgent_PollingForTaskCompletion.csproj" />
+    <Project Path="samples/02-agents/A2A/A2AAgent_ProtocolSelection/A2AAgent_ProtocolSelection.csproj" />
+    <Project Path="samples/02-agents/A2A/A2AAgent_StreamReconnection/A2AAgent_StreamReconnection.csproj" />
   </Folder>
   <Folder Name="/Samples/05-end-to-end/">
     <Project Path="samples/05-end-to-end/AgentWithPurview/AgentWithPurview.csproj" />
     <Project Path="samples/05-end-to-end/M365Agent/M365Agent.csproj" />
   </Folder>
   <Folder Name="/Samples/05-end-to-end/Evaluation/">
-    <Project Path="samples/05-end-to-end/Evaluation/Evaluation_FoundryQuality/Evaluation_FoundryQuality.csproj" />
-    <Project Path="samples/05-end-to-end/Evaluation/Evaluation_MixedProviders/Evaluation_MixedProviders.csproj" />
     <Project Path="samples/05-end-to-end/Evaluation/Evaluation_ConversationSplits/Evaluation_ConversationSplits.csproj" />
+    <Project Path="samples/05-end-to-end/Evaluation/Evaluation_FoundryQuality/Evaluation_FoundryQuality.csproj" />
+    <Project Path="samples/05-end-to-end/Evaluation/Evaluation_FoundryRubric/Evaluation_FoundryRubric.csproj" />
+    <Project Path="samples/05-end-to-end/Evaluation/Evaluation_MixedProviders/Evaluation_MixedProviders.csproj" />
   </Folder>
   <Folder Name="/Samples/05-end-to-end/A2AClientServer/">
     <File Path="samples/05-end-to-end/A2AClientServer/README.md" />
@@ -338,15 +457,6 @@
     <Project Path="samples/05-end-to-end/AGUIClientServer/AGUIDojoServer/AGUIDojoServer.csproj" />
     <Project Path="samples/05-end-to-end/AGUIClientServer/AGUIServer/AGUIServer.csproj" />
   </Folder>
-  <Folder Name="/Samples/05-end-to-end/HostedAgents/">
-    <Project Path="samples/05-end-to-end/HostedAgents/AgentsInWorkflows/AgentsInWorkflows.csproj" />
-    <Project Path="samples/05-end-to-end/HostedAgents/AgentThreadAndHITL/AgentThreadAndHITL.csproj" />
-    <Project Path="samples/05-end-to-end/HostedAgents/AgentWithHostedMCP/AgentWithHostedMCP.csproj" />
-    <Project Path="samples/05-end-to-end/HostedAgents/AgentWithLocalTools/AgentWithLocalTools.csproj" />
-    <Project Path="samples/05-end-to-end/HostedAgents/AgentWithTextSearchRag/AgentWithTextSearchRag.csproj" />
-    <Project Path="samples/05-end-to-end/HostedAgents/FoundryMultiAgent/FoundryMultiAgent.csproj" />
-    <Project Path="samples/05-end-to-end/HostedAgents/FoundrySingleAgent/FoundrySingleAgent.csproj" />
-  </Folder>
   <Folder Name="/Samples/05-end-to-end/AspNetAgentAuthorization/">
     <File Path="samples/05-end-to-end/AspNetAgentAuthorization/docker-compose.yml" />
     <File Path="samples/05-end-to-end/AspNetAgentAuthorization/README.md" />
@@ -498,33 +608,50 @@
   <Folder Name="/Solution Items/src/Shared/StructuredOutput/">
     <File Path="src/Shared/StructuredOutput/StructuredOutputSchemaUtilities.cs" />
   </Folder>
+  <Folder Name="/Solution Items/src/Shared/Workflows/" />
+  <Folder Name="/Solution Items/src/Shared/Workflows/Execution/">
+    <File Path="src/Shared/Workflows/Execution/README.md" />
+    <File Path="src/Shared/Workflows/Execution/WorkflowFactory.cs" />
+    <File Path="src/Shared/Workflows/Execution/WorkflowRunner.cs" />
+  </Folder>
+  <Folder Name="/Solution Items/src/Shared/Workflows/Settings/">
+    <File Path="src/Shared/Workflows/Settings/Application.cs" />
+    <File Path="src/Shared/Workflows/Settings/README.md" />
+  </Folder>
   <Folder Name="/Solution Items/tests/">
     <File Path="tests/.editorconfig" />
     <File Path="tests/Directory.Build.props" />
   </Folder>
   <Folder Name="/src/">
+    <Project Path="src/Aspire.Hosting.AgentFramework.DevUI/Aspire.Hosting.AgentFramework.DevUI.csproj" />
     <Project Path="src/Microsoft.Agents.AI.A2A/Microsoft.Agents.AI.A2A.csproj" />
     <Project Path="src/Microsoft.Agents.AI.Abstractions/Microsoft.Agents.AI.Abstractions.csproj" />
-    <Project Path="src/Microsoft.Agents.AI.AGUI/Microsoft.Agents.AI.AGUI.csproj" />
     <Project Path="src/Microsoft.Agents.AI.Anthropic/Microsoft.Agents.AI.Anthropic.csproj" />
     <Project Path="src/Microsoft.Agents.AI.AzureAI.Persistent/Microsoft.Agents.AI.AzureAI.Persistent.csproj" />
-    <Project Path="src/Microsoft.Agents.AI.Foundry/Microsoft.Agents.AI.Foundry.csproj" />
     <Project Path="src/Microsoft.Agents.AI.CopilotStudio/Microsoft.Agents.AI.CopilotStudio.csproj" />
     <Project Path="src/Microsoft.Agents.AI.CosmosNoSql/Microsoft.Agents.AI.CosmosNoSql.csproj" />
     <Project Path="src/Microsoft.Agents.AI.Declarative/Microsoft.Agents.AI.Declarative.csproj" />
     <Project Path="src/Microsoft.Agents.AI.DevUI/Microsoft.Agents.AI.DevUI.csproj" />
     <Project Path="src/Microsoft.Agents.AI.DurableTask/Microsoft.Agents.AI.DurableTask.csproj" />
-
+    <Project Path="src/Microsoft.Agents.AI.Foundry.Hosting/Microsoft.Agents.AI.Foundry.Hosting.csproj" />
+    <Project Path="src/Microsoft.Agents.AI.Foundry/Microsoft.Agents.AI.Foundry.csproj" />
     <Project Path="src/Microsoft.Agents.AI.GitHub.Copilot/Microsoft.Agents.AI.GitHub.Copilot.csproj" />
+    <Project Path="src/Microsoft.Agents.AI.Harness/Microsoft.Agents.AI.Harness.csproj" />
     <Project Path="src/Microsoft.Agents.AI.Hosting.A2A.AspNetCore/Microsoft.Agents.AI.Hosting.A2A.AspNetCore.csproj" />
     <Project Path="src/Microsoft.Agents.AI.Hosting.A2A/Microsoft.Agents.AI.Hosting.A2A.csproj" />
     <Project Path="src/Microsoft.Agents.AI.Hosting.AGUI.AspNetCore/Microsoft.Agents.AI.Hosting.AGUI.AspNetCore.csproj" />
+    <Project Path="src/Microsoft.Agents.AI.Hosting.AspNetCore/Microsoft.Agents.AI.Hosting.AspNetCore.csproj" />
     <Project Path="src/Microsoft.Agents.AI.Hosting.AzureFunctions/Microsoft.Agents.AI.Hosting.AzureFunctions.csproj" />
     <Project Path="src/Microsoft.Agents.AI.Hosting.OpenAI/Microsoft.Agents.AI.Hosting.OpenAI.csproj" />
     <Project Path="src/Microsoft.Agents.AI.Hosting/Microsoft.Agents.AI.Hosting.csproj" />
+    <Project Path="src/Microsoft.Agents.AI.Hyperlight/Microsoft.Agents.AI.Hyperlight.csproj" />
+    <Project Path="src/Microsoft.Agents.AI.LocalCodeAct/Microsoft.Agents.AI.LocalCodeAct.csproj" />
+    <Project Path="src/Microsoft.Agents.AI.Mcp/Microsoft.Agents.AI.Mcp.csproj" />
     <Project Path="src/Microsoft.Agents.AI.Mem0/Microsoft.Agents.AI.Mem0.csproj" />
     <Project Path="src/Microsoft.Agents.AI.OpenAI/Microsoft.Agents.AI.OpenAI.csproj" />
     <Project Path="src/Microsoft.Agents.AI.Purview/Microsoft.Agents.AI.Purview.csproj" />
+    <Project Path="src/Microsoft.Agents.AI.Tools.Shell/Microsoft.Agents.AI.Tools.Shell.csproj" />
+    <Project Path="src/Microsoft.Agents.AI.Valkey/Microsoft.Agents.AI.Valkey.csproj" />
     <Project Path="src/Microsoft.Agents.AI.Workflows.Declarative.Foundry/Microsoft.Agents.AI.Workflows.Declarative.Foundry.csproj" />
     <Project Path="src/Microsoft.Agents.AI.Workflows.Declarative.Mcp/Microsoft.Agents.AI.Workflows.Declarative.Mcp.csproj" />
     <Project Path="src/Microsoft.Agents.AI.Workflows.Declarative/Microsoft.Agents.AI.Workflows.Declarative.csproj" />
@@ -532,19 +659,24 @@
     <Project Path="src/Microsoft.Agents.AI.Workflows/Microsoft.Agents.AI.Workflows.csproj" />
     <Project Path="src/Microsoft.Agents.AI/Microsoft.Agents.AI.csproj" />
   </Folder>
-  <Folder Name="/Tests/" />
+  <Folder Name="/Tests/">
+    <Project Path="tests/Microsoft.Agents.AI.Hosting.OpenAI.IntegrationTests/Microsoft.Agents.AI.Hosting.OpenAI.IntegrationTests.csproj" />
+  </Folder>
   <Folder Name="/Tests/IntegrationTests/">
     <Project Path="tests/AgentConformance.IntegrationTests/AgentConformance.IntegrationTests.csproj" />
     <Project Path="tests/AnthropicChatCompletion.IntegrationTests/AnthropicChatCompletion.IntegrationTests.csproj" />
-    <Project Path="tests/Foundry.IntegrationTests/Foundry.IntegrationTests.csproj" />
     <Project Path="tests/AzureAIAgentsPersistent.IntegrationTests/AzureAIAgentsPersistent.IntegrationTests.csproj" />
     <Project Path="tests/CopilotStudio.IntegrationTests/CopilotStudio.IntegrationTests.csproj" />
+    <Project Path="tests/Foundry.Hosting.IntegrationTests.TestContainer/Foundry.Hosting.IntegrationTests.TestContainer.csproj" />
+    <Project Path="tests/Foundry.Hosting.IntegrationTests/Foundry.Hosting.IntegrationTests.csproj" />
+    <Project Path="tests/Foundry.IntegrationTests/Foundry.IntegrationTests.csproj" />
     <Project Path="tests/Microsoft.Agents.AI.DurableTask.IntegrationTests/Microsoft.Agents.AI.DurableTask.IntegrationTests.csproj" />
-
     <Project Path="tests/Microsoft.Agents.AI.GitHub.Copilot.IntegrationTests/Microsoft.Agents.AI.GitHub.Copilot.IntegrationTests.csproj" />
     <Project Path="tests/Microsoft.Agents.AI.Hosting.AGUI.AspNetCore.IntegrationTests/Microsoft.Agents.AI.Hosting.AGUI.AspNetCore.IntegrationTests.csproj" />
     <Project Path="tests/Microsoft.Agents.AI.Hosting.AzureFunctions.IntegrationTests/Microsoft.Agents.AI.Hosting.AzureFunctions.IntegrationTests.csproj" />
+    <Project Path="tests/Microsoft.Agents.AI.Hyperlight.IntegrationTests/Microsoft.Agents.AI.Hyperlight.IntegrationTests.csproj" />
     <Project Path="tests/Microsoft.Agents.AI.Mem0.IntegrationTests/Microsoft.Agents.AI.Mem0.IntegrationTests.csproj" />
+    <Project Path="tests/Microsoft.Agents.AI.Tools.Shell.IntegrationTests/Microsoft.Agents.AI.Tools.Shell.IntegrationTests.csproj" />
     <Project Path="tests/Microsoft.Agents.AI.Workflows.Declarative.IntegrationTests/Microsoft.Agents.AI.Workflows.Declarative.IntegrationTests.csproj" />
     <Project Path="tests/OpenAIAssistant.IntegrationTests/OpenAIAssistant.IntegrationTests.csproj" />
     <Project Path="tests/OpenAIChatCompletion.IntegrationTests/OpenAIChatCompletion.IntegrationTests.csproj" />
@@ -554,28 +686,35 @@
     <Project Path="tests/Aspire.Hosting.AgentFramework.DevUI.UnitTests/Aspire.Hosting.AgentFramework.DevUI.UnitTests.csproj" />
     <Project Path="tests/Microsoft.Agents.AI.A2A.UnitTests/Microsoft.Agents.AI.A2A.UnitTests.csproj" />
     <Project Path="tests/Microsoft.Agents.AI.Abstractions.UnitTests/Microsoft.Agents.AI.Abstractions.UnitTests.csproj" />
-    <Project Path="tests/Microsoft.Agents.AI.AGUI.UnitTests/Microsoft.Agents.AI.AGUI.UnitTests.csproj" />
     <Project Path="tests/Microsoft.Agents.AI.Anthropic.UnitTests/Microsoft.Agents.AI.Anthropic.UnitTests.csproj" />
     <Project Path="tests/Microsoft.Agents.AI.AzureAI.Persistent.UnitTests/Microsoft.Agents.AI.AzureAI.Persistent.UnitTests.csproj" />
-    <Project Path="tests/Microsoft.Agents.AI.Foundry.UnitTests/Microsoft.Agents.AI.Foundry.UnitTests.csproj" />
     <Project Path="tests/Microsoft.Agents.AI.CosmosNoSql.UnitTests/Microsoft.Agents.AI.CosmosNoSql.UnitTests.csproj" />
     <Project Path="tests/Microsoft.Agents.AI.Declarative.UnitTests/Microsoft.Agents.AI.Declarative.UnitTests.csproj" />
     <Project Path="tests/Microsoft.Agents.AI.DevUI.UnitTests/Microsoft.Agents.AI.DevUI.UnitTests.csproj" />
     <Project Path="tests/Microsoft.Agents.AI.DurableTask.UnitTests/Microsoft.Agents.AI.DurableTask.UnitTests.csproj" />
-
+    <Project Path="tests/Microsoft.Agents.AI.Foundry.Hosting.UnitTests/Microsoft.Agents.AI.Foundry.Hosting.UnitTests.csproj" />
+    <Project Path="tests/Microsoft.Agents.AI.Foundry.UnitTests/Microsoft.Agents.AI.Foundry.UnitTests.csproj" />
     <Project Path="tests/Microsoft.Agents.AI.GitHub.Copilot.UnitTests/Microsoft.Agents.AI.GitHub.Copilot.UnitTests.csproj" />
+    <Project Path="tests/Microsoft.Agents.AI.Harness.UnitTests/Microsoft.Agents.AI.Harness.UnitTests.csproj" />
     <Project Path="tests/Microsoft.Agents.AI.Hosting.A2A.UnitTests/Microsoft.Agents.AI.Hosting.A2A.UnitTests.csproj" />
     <Project Path="tests/Microsoft.Agents.AI.Hosting.AGUI.AspNetCore.UnitTests/Microsoft.Agents.AI.Hosting.AGUI.AspNetCore.UnitTests.csproj" />
     <Project Path="tests/Microsoft.Agents.AI.Hosting.AzureFunctions.UnitTests/Microsoft.Agents.AI.Hosting.AzureFunctions.UnitTests.csproj" />
     <Project Path="tests/Microsoft.Agents.AI.Hosting.OpenAI.UnitTests/Microsoft.Agents.AI.Hosting.OpenAI.UnitTests.csproj" />
     <Project Path="tests/Microsoft.Agents.AI.Hosting.UnitTests/Microsoft.Agents.AI.Hosting.UnitTests.csproj" />
+    <Project Path="tests/Microsoft.Agents.AI.Hyperlight.UnitTests/Microsoft.Agents.AI.Hyperlight.UnitTests.csproj" />
+    <Project Path="tests/Microsoft.Agents.AI.LocalCodeAct.UnitTests/Microsoft.Agents.AI.LocalCodeAct.UnitTests.csproj" />
+    <Project Path="tests/Microsoft.Agents.AI.Mcp.UnitTests/Microsoft.Agents.AI.Mcp.UnitTests.csproj" />
     <Project Path="tests/Microsoft.Agents.AI.Mem0.UnitTests/Microsoft.Agents.AI.Mem0.UnitTests.csproj" />
     <Project Path="tests/Microsoft.Agents.AI.OpenAI.UnitTests/Microsoft.Agents.AI.OpenAI.UnitTests.csproj" />
     <Project Path="tests/Microsoft.Agents.AI.Purview.UnitTests/Microsoft.Agents.AI.Purview.UnitTests.csproj" />
+    <Project Path="tests/Microsoft.Agents.AI.Tools.Shell.UnitTests/Microsoft.Agents.AI.Tools.Shell.UnitTests.csproj" />
     <Project Path="tests/Microsoft.Agents.AI.UnitTests/Microsoft.Agents.AI.UnitTests.csproj" />
+    <Project Path="tests/Microsoft.Agents.AI.Valkey.UnitTests/Microsoft.Agents.AI.Valkey.UnitTests.csproj" />
     <Project Path="tests/Microsoft.Agents.AI.Workflows.Declarative.Mcp.UnitTests/Microsoft.Agents.AI.Workflows.Declarative.Mcp.UnitTests.csproj" />
     <Project Path="tests/Microsoft.Agents.AI.Workflows.Declarative.UnitTests/Microsoft.Agents.AI.Workflows.Declarative.UnitTests.csproj" />
     <Project Path="tests/Microsoft.Agents.AI.Workflows.Generators.UnitTests/Microsoft.Agents.AI.Workflows.Generators.UnitTests.csproj" />
     <Project Path="tests/Microsoft.Agents.AI.Workflows.UnitTests/Microsoft.Agents.AI.Workflows.UnitTests.csproj" />
   </Folder>
 </Solution>
+
+