github-featured/microsoft--agent-framework

Files

T

History

Eduard van Valkenburg 6e95517659 Python: Split type checkers by target (pyright source, 5 checkers on tests/samples) (#6443 )

* Python: Split type checkers by target (pyright source, 5 checkers on tests/samples)

Rework the typing setup along the lines of the 'too many type checkers'
approach:

- Pyright (strict) is now the sole source-code type checker; mypy is
  removed from source and its [tool.mypy] block becomes a relaxed profile
  used only for tests/samples.
- Tests are checked by all five checkers (pyright relaxed, mypy, pyrefly,
  ty, zuban); samples by pyright, pyrefly, and ty. All run in a relaxed/
  basic profile so authors aren't forced into over-annotation.
- Add pyrightconfig.tests.json and bump sample pyright configs to basic.
- Unify test/sample typing onto the same parallel fan-out used by source
  pyright via run_command_items in task_runner.py.
- Make version-conditional imports symmetric: keep or drop the
  '# type: ignore' on both branches so results match across interpreter
  versions (local vs CI).
- Update SKILL.md, DEV_SETUP.md, and CODING_STANDARD.md for the five
  gating checkers and pyright on source+tests+samples.

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

* Python: Fix merge regressions from main (typing + runtime)

Merging main into the type-checker split branch surfaced regressions that
the new five-checker test suite and unit tests caught:

Runtime fixes:
- anthropic: restore the dropped `cache_read_input_token_count` mapping in
  _parse_usage_from_anthropic (lost during merge conflict resolution).
- gemini: _get_function_calling_mode test helper returned str(enum)
  ('FunctionCallingConfigMode.AUTO') instead of the enum value ('AUTO').
- openai: _response_id_from_token test helper was an infinite self-recursion;
  return token['response_id'].
- orchestrations: reset output_events per approval iteration so the terminal
  output assertion counts only the final run.
- core: drop a stale duplicate harness test whose message ('non-negative')
  contradicted the source ('positive').
- purview: import PolicyLocation/PolicyScope/ProtectionScopeActivities/
  ExecutionMode used by the processor tests.

Type-checker fixes (tests, relaxed profile):
- core: pyright/mypy/pyrefly/ty/zuban green-ups across the harness, MCP,
  observability and types tests.
- anthropic/openai: route provider-namespaced UsageDetails keys through a
  dict cast (extra_items TypedDict unsupported by mypy/ty).
- purview: typed model constructors and cache-mock casts.
- ag-ui: annotate WorkflowContext[Any, Any] so yield_output accepts test
  payloads, guard Optional forwarded_props, and ty-ignore intentional bad args.

Source pyright (sole source checker) flagged unnecessary ignores newly
introduced by merged code in core _tools.py and declarative _declarative_base.py.

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

* Python: Isolate per-package mypy cache in test-typing fan-out

The parallel test-typing fan-out runs many mypy processes concurrently,
all defaulting to a single shared ./.mypy_cache. Concurrent writes corrupt
the cache and mypy aborts with INTERNAL ERROR (intermittently, depending on
worker timing) -- which is why CI's Test Typing job failed on a shifting set
of packages while a single-package run was fine.

Give each mypy invocation an isolated cache dir keyed by its target paths so
incremental caching still works per package without races. Other checkers
(zuban/pyrefly/ty/pyright) maintain their own caches and are unaffected.

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

* Python: Make lab pyright-only on source (drop source mypy)

Lab was the last package still running mypy on its source code, requiring
mypy-only `# type: ignore` comments that pyright (the sole source checker
everywhere else) flags as unnecessary. Align lab with the rest of the
monorepo:

- Remove the lab source mypy poe tasks (mypy-gaia/lightning/tau2) and the
  now-dead strict [tool.mypy] config block.
- Drop the 'Run lab mypy' CI step; lab source is type-checked by pyright only.

Lab tests remain covered by the workspace test-typing fan-out (mypy, pyrefly,
ty, zuban, pyright over tests using the relaxed root config).

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

* Python: Fix test-typing regressions from latest main merge

A fresh merge from main brought in new test code never run under the
five-checker test-typing suite. Green up across the affected packages:

- core: narrow Optional span.attributes with 'and' guards in span filters
  and assert+cast the json.loads(...attributes[...]) reads (test_observability);
  match the existing as_agent ignore on the protocol-typed fixture (test_clients).
- openai: align new streaming tests with the established chat_options dict
  pattern (ChatOptions TypedDict isn't assignable to dict), route Optional
  .annotations[0] access through a small _first_annotation helper (mirrors the
  file's assert-not-None convention), and annotate a mapped ResponseStream.
- foundry_hosting: annotate error: dict[str, Any] = body.get(...) or {}
  (zuban needs the annotation).
- foundry: narrow ignores for the live AIProjectClient credential arg (pyrefly)
  and connections.get_default (zuban) SDK type gaps.

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

* updated pyright version

* pyright fix

* Python: Fix source typing for pyright 1.1.410

Pyright 1.1.410 tightened several checks. Apply the same source fixes as
upstream PR #6275:

- anthropic: import AsyncAnthropicBedrock from anthropic.lib.bedrock and
  AsyncAnthropicVertex from anthropic.lib.vertex (no longer re-exported from
  the anthropic top-level package -> reportPrivateImportUsage).
- core _types.py: cast the transform-hook result to UpdateT (reportAssignmentType).
- core _workflows/_events.py: annotate the @contextmanager helper as
  Generator[None] instead of Iterator[None] (reportDeprecated).
- redis: build the combined filter expression with an explicit loop instead of
  reduce(and_, ...), which pyright could no longer fully type (drops the now
  unused functools.reduce / operator.and_ imports).

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

* Python: Accept plain-text body in Azure Functions workflow/run endpoint

The workflow_orchestrator already accepts plain strings as well as JSON
objects via context.get_input(), but the start_workflow_orchestration HTTP
handler only accepted JSON and returned 400 for any non-JSON body. This made
the functions integration tests that POST text/plain to /api/workflow/run
(e.g. test_09_workflow_shared_state) fail consistently with 400 != 202.

Fall back to the raw request body (decoded as UTF-8) when the body is not
JSON, rejecting only a truly empty body. The JSON path is unchanged.

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

---------

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

2026-06-18 15:06:20 +00:00

built_in_chat_clients.py

Python: update FoundryAgent for hosted agent sessions (#5447 )

2026-04-24 09:25:03 +00:00

chat_response_cancellation.py

Python: Split type checkers by target (pyright source, 5 checkers on tests/samples) (#6443 )

2026-06-18 15:06:20 +00:00

custom_chat_client.py

Python: [BREAKING] update to v1.0.0 (#5062 )

2026-04-02 15:26:30 +00:00

README.md

Python: [BREAKING] Python: move Azure AI embeddings to Foundry (#5056 )

2026-04-02 11:26:35 +00:00

require_per_service_call_history_persistence.py

Python: [BREAKING] update context provider APIs, middleware, and per-service-call history persistence (#4992 )

2026-04-01 16:13:11 +00:00

README.md

Chat Client Examples

This folder contains examples for direct chat client usage patterns.

Examples

File	Description
`built_in_chat_clients.py`	Consolidated sample for built-in chat clients. Uses `get_client()` to create the selected client and pass it to `main()`.
`chat_response_cancellation.py`	Demonstrates how to cancel chat responses during streaming, showing proper cancellation handling and cleanup.
`custom_chat_client.py`	Demonstrates how to create custom chat clients by extending the `BaseChatClient` class. Shows a `EchoingChatClient` implementation and how to integrate it with `Agent` using the `as_agent()` method.
`require_per_service_call_history_persistence.py`	Compares two otherwise identical `FoundryChatClient` agents with `store=False`; the only difference is whether `require_per_service_call_history_persistence` is enabled, and only the run without it stores the synthesized tool result when middleware terminates the loop early.

Selecting a built-in client

built_in_chat_clients.py starts with:

asyncio.run(main("openai_responses"))

Change the argument to pick a client:

openai_responses
openai_chat_completion
anthropic
ollama
bedrock
azure_openai_responses
azure_openai_chat_completion
foundry_chat

Example:

uv run samples/02-agents/chat_client/built_in_chat_clients.py

The require_per_service_call_history_persistence.py sample uses FoundryChatClient, so set the usual Foundry settings first and sign in with the Azure CLI:

export FOUNDRY_PROJECT_ENDPOINT="https://<your-project>.services.ai.azure.com/api/projects/<project-name>"
export FOUNDRY_MODEL="<your-model-deployment-name>"
az login
uv run samples/02-agents/chat_client/require_per_service_call_history_persistence.py

Environment Variables

Depending on the selected client, set the appropriate environment variables:

For Azure OpenAI clients (azure_openai_responses and azure_openai_chat_completion):

AZURE_OPENAI_ENDPOINT: Your Azure OpenAI endpoint
AZURE_OPENAI_MODEL: The Azure OpenAI deployment used by the sample
AZURE_OPENAI_API_VERSION (optional): Azure OpenAI API version override
AZURE_OPENAI_API_KEY (optional): Azure OpenAI API key if you are not using AzureCliCredential

For Foundry client (foundry_chat):

FOUNDRY_PROJECT_ENDPOINT: Your Azure AI Foundry project endpoint
FOUNDRY_MODEL: The Foundry deployment used by the sample

For OpenAI clients:

OPENAI_API_KEY: Your OpenAI API key
OPENAI_CHAT_COMPLETION_MODEL: The OpenAI model for openai_chat_completion
OPENAI_CHAT_MODEL: The OpenAI model for openai_responses

For Anthropic client (anthropic):

ANTHROPIC_API_KEY: Your Anthropic API key
ANTHROPIC_CHAT_MODEL: The Anthropic model to use (for example, claude-sonnet-4-5)

For Ollama client (ollama):

OLLAMA_HOST: Ollama server URL (defaults to http://localhost:11434 if unset)
OLLAMA_MODEL: Ollama model name (for example, mistral, qwen2.5:8b)

For Bedrock client (bedrock):

BEDROCK_CHAT_MODEL: Bedrock model ID (for example, anthropic.claude-3-5-sonnet-20240620-v1:0)
BEDROCK_REGION: AWS region (defaults to us-east-1 if unset)
AWS credentials via standard environment variables (for example, AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY)