chore: release v4.5.0-rc.7 (#3932)

## Summary
7 improvements.

## Improvements
- `@trigger.dev/sdk` now bundles the Trigger.dev agent skills and a
curated snapshot of the docs those skills reference. The skills that
`trigger skills` installs into your coding agent read this content from
node_modules, so the guidance your AI assistant follows is pinned to the
SDK version installed in your project and stays current across upgrades
instead of going stale until the next reinstall.
([#3937](https://github.com/triggerdotdev/trigger.dev/pull/3937))
- Running a CLI command like `dev`, `deploy`, `preview`, or `update`
before initializing a project no longer crashes with a raw `Cannot find
matching package.json` stack trace. The CLI now detects the missing
project and points you to `npx trigger.dev@latest init` instead.
([#3929](https://github.com/triggerdotdev/trigger.dev/pull/3929))
- The agent skills installed by `trigger skills` are now namespaced with
a `trigger-` prefix (e.g. `trigger-authoring-tasks`,
`trigger-getting-started`) so they don't collide with unrelated skills
in your coding agent's skills directory. Adds a `trigger-cost-savings`
skill for auditing and reducing compute spend (right-sizing machines,
`maxDuration`, batching, debounce), and `@trigger.dev/sdk` now bundles
the full Trigger.dev documentation so your agent can read the complete,
version-pinned reference directly from node_modules.
([#3970](https://github.com/triggerdotdev/trigger.dev/pull/3970))
- The run span API response now includes `cachedCost` and
`cacheCreationCost` on the `ai` object, alongside the existing
`inputCost` / `outputCost` / `totalCost`. `inputCost` reflects only the
non-cached input, so these fields let you reconstruct the full cost
breakdown for prompt-cached calls.
([#3958](https://github.com/triggerdotdev/trigger.dev/pull/3958))
- `chat.headStart` now works with the `chat.customAgent` and
`chat.createSession` backends, not only `chat.agent`. The warm step-1
response hands over to your loop the same way it does for a managed
agent. ([#3963](https://github.com/triggerdotdev/trigger.dev/pull/3963))
  
  In a `chat.customAgent` loop, consume the handover on turn 0:
  
  ```ts
  const conversation = new chat.MessageAccumulator();
const { isFinal, skipped } = await conversation.consumeHandover({
payload });
  if (skipped) return; // warm handler aborted, so exit without a turn
  if (isFinal) {
await chat.writeTurnComplete(); // step 1 is the response, no streamText
  } else {
const result = streamText({ model, messages: conversation.modelMessages,
tools });
// Pass originalMessages so the handed-over tool round merges into the
    // step-1 assistant instead of starting a new message.
    const response = await chat.pipeAndCapture(result, {
      originalMessages: conversation.uiMessages,
    });
    if (response) await conversation.addResponse(response);
  }
  ```
  
With `chat.createSession`, the iterator surfaces it as `turn.handover`;
call `turn.complete()` with no argument on a final handover. The
lower-level `chat.waitForHandover()` and `accumulator.applyHandover()`
are also exported for hand-rolled loops.
- Cache your chat agent's system prompt with Anthropic prompt caching.
`chat.toStreamTextOptions()` now emits the system prompt as a cacheable
message when you opt in, so a large, stable system block is billed at
cache-read rates on every turn instead of full price.
([#3952](https://github.com/triggerdotdev/trigger.dev/pull/3952))
  
  ```ts
  // at the streamText call site (Anthropic sugar)
  streamText({
...chat.toStreamTextOptions({ cacheControl: { type: "ephemeral" } }),
    messages,
  });
  
  // provider-agnostic equivalent
  chat.toStreamTextOptions({
systemProviderOptions: { anthropic: { cacheControl: { type: "ephemeral"
} } },
  });
  
  // or where the prompt is defined
  chat.prompt.set(SYSTEM_PROMPT, {
providerOptions: { anthropic: { cacheControl: { type: "ephemeral" } } },
  });
  ```
  
Without an option, `system` stays a plain string. Pairs with a
`prepareMessages` cache breakpoint to cache the conversation prefix
across turns too.
- Three fixes for custom agent loops (`chat.customAgent`,
`chat.createSession`, and hand-rolled `MessageAccumulator` loops):
([#3936](https://github.com/triggerdotdev/trigger.dev/pull/3936))
  
- Continuation runs no longer replay already-answered user messages into
the first turn. The `.in` resume cursor is now seeded before any
listener attaches (the same boot logic `chat.agent` uses), so a chat
that continues after a cancel, crash, or upgrade only sees genuinely new
messages.
- Steering a hand-rolled loop mid-stream no longer wipes the in-flight
assistant response. `chat.pipeAndCapture` now stamps a server-generated
message id on the stream, so a `prepareStep` injection keeps the partial
text instead of replacing the message.
- Task-backed tools (`ai.toolExecute`) now work from custom agent loops:
the parent's session is threaded to the child run, so child tasks can
stream progress into the chat with `chat.stream.writer({ target: "root"
})` instead of failing with "session handle is not initialized".

<details>
<summary>Raw changeset output</summary>

⚠️⚠️⚠️⚠️⚠️⚠️

`main` is currently in **pre mode** so this branch has prereleases
rather than normal releases. If you want to exit prereleases, run
`changeset pre exit` on `main`.

⚠️⚠️⚠️⚠️⚠️⚠️

# Releases
## @trigger.dev/build@4.5.0-rc.7

### Patch Changes

-   Updated dependencies:
    -   `@trigger.dev/core@4.5.0-rc.7`

## trigger.dev@4.5.0-rc.7

### Patch Changes

- `@trigger.dev/sdk` now bundles the Trigger.dev agent skills and a
curated snapshot of the docs those skills reference. The skills that
`trigger skills` installs into your coding agent read this content from
node_modules, so the guidance your AI assistant follows is pinned to the
SDK version installed in your project and stays current across upgrades
instead of going stale until the next reinstall.
([#3937](https://github.com/triggerdotdev/trigger.dev/pull/3937))
- Running a CLI command like `dev`, `deploy`, `preview`, or `update`
before initializing a project no longer crashes with a raw `Cannot find
matching package.json` stack trace. The CLI now detects the missing
project and points you to `npx trigger.dev@latest init` instead.
([#3929](https://github.com/triggerdotdev/trigger.dev/pull/3929))
- The agent skills installed by `trigger skills` are now namespaced with
a `trigger-` prefix (e.g. `trigger-authoring-tasks`,
`trigger-getting-started`) so they don't collide with unrelated skills
in your coding agent's skills directory. Adds a `trigger-cost-savings`
skill for auditing and reducing compute spend (right-sizing machines,
`maxDuration`, batching, debounce), and `@trigger.dev/sdk` now bundles
the full Trigger.dev documentation so your agent can read the complete,
version-pinned reference directly from node_modules.
([#3970](https://github.com/triggerdotdev/trigger.dev/pull/3970))
-   Updated dependencies:
    -   `@trigger.dev/core@4.5.0-rc.7`
    -   `@trigger.dev/build@4.5.0-rc.7`
    -   `@trigger.dev/schema-to-json@4.5.0-rc.7`

## @trigger.dev/core@4.5.0-rc.7

### Patch Changes

- The run span API response now includes `cachedCost` and
`cacheCreationCost` on the `ai` object, alongside the existing
`inputCost` / `outputCost` / `totalCost`. `inputCost` reflects only the
non-cached input, so these fields let you reconstruct the full cost
breakdown for prompt-cached calls.
([#3958](https://github.com/triggerdotdev/trigger.dev/pull/3958))

## @trigger.dev/python@4.5.0-rc.7

### Patch Changes

-   Updated dependencies:
    -   `@trigger.dev/sdk@4.5.0-rc.7`
    -   `@trigger.dev/core@4.5.0-rc.7`
    -   `@trigger.dev/build@4.5.0-rc.7`

## @trigger.dev/react-hooks@4.5.0-rc.7

### Patch Changes

-   Updated dependencies:
    -   `@trigger.dev/core@4.5.0-rc.7`

## @trigger.dev/redis-worker@4.5.0-rc.7

### Patch Changes

-   Updated dependencies:
    -   `@trigger.dev/core@4.5.0-rc.7`

## @trigger.dev/rsc@4.5.0-rc.7

### Patch Changes

-   Updated dependencies:
    -   `@trigger.dev/core@4.5.0-rc.7`

## @trigger.dev/schema-to-json@4.5.0-rc.7

### Patch Changes

-   Updated dependencies:
    -   `@trigger.dev/core@4.5.0-rc.7`

## @trigger.dev/sdk@4.5.0-rc.7

### Patch Changes

- `@trigger.dev/sdk` now bundles the Trigger.dev agent skills and a
curated snapshot of the docs those skills reference. The skills that
`trigger skills` installs into your coding agent read this content from
node_modules, so the guidance your AI assistant follows is pinned to the
SDK version installed in your project and stays current across upgrades
instead of going stale until the next reinstall.
([#3937](https://github.com/triggerdotdev/trigger.dev/pull/3937))

- `chat.headStart` now works with the `chat.customAgent` and
`chat.createSession` backends, not only `chat.agent`. The warm step-1
response hands over to your loop the same way it does for a managed
agent. ([#3963](https://github.com/triggerdotdev/trigger.dev/pull/3963))

    In a `chat.customAgent` loop, consume the handover on turn 0:

    ```ts
    const conversation = new chat.MessageAccumulator();
const { isFinal, skipped } = await conversation.consumeHandover({
payload });
    if (skipped) return; // warm handler aborted, so exit without a turn
    if (isFinal) {
await chat.writeTurnComplete(); // step 1 is the response, no streamText
    } else {
const result = streamText({ model, messages: conversation.modelMessages,
tools });
// Pass originalMessages so the handed-over tool round merges into the
      // step-1 assistant instead of starting a new message.
      const response = await chat.pipeAndCapture(result, {
        originalMessages: conversation.uiMessages,
      });
      if (response) await conversation.addResponse(response);
    }
    ```

With `chat.createSession`, the iterator surfaces it as `turn.handover`;
call `turn.complete()` with no argument on a final handover. The
lower-level `chat.waitForHandover()` and `accumulator.applyHandover()`
are also exported for hand-rolled loops.

- Add `triggerConfig` support to `chat.headStart()` and
`chat.openSession()`, so the auto-triggered handover-prepare run
inherits tags, queue, machine, and other session trigger options the
same way `chat.createStartSessionAction()` does. The `chat:{chatId}` tag
is prepended automatically.
([#3963](https://github.com/triggerdotdev/trigger.dev/pull/3963))

    ```ts
    export const POST = chat.headStart({
      agentId: "my-agent",
      triggerConfig: { tags: ["org:acme"], queue: "chat" },
run: async ({ chat }) => streamText({ ...chat.toStreamTextOptions(),
model }),
    });
    ```

Because the session is created once on the first head-start turn and is
idempotent on the chat id, this is the only place to set those options
for a head-start chat's lifetime. `chat.createStartSessionAction()` now
also forwards `maxDuration`, `region`, and `lockToVersion` so both
session entry points stay consistent.

- Cache your chat agent's system prompt with Anthropic prompt caching.
`chat.toStreamTextOptions()` now emits the system prompt as a cacheable
message when you opt in, so a large, stable system block is billed at
cache-read rates on every turn instead of full price.
([#3952](https://github.com/triggerdotdev/trigger.dev/pull/3952))

    ```ts
    // at the streamText call site (Anthropic sugar)
    streamText({
...chat.toStreamTextOptions({ cacheControl: { type: "ephemeral" } }),
      messages,
    });

    // provider-agnostic equivalent
    chat.toStreamTextOptions({
systemProviderOptions: { anthropic: { cacheControl: { type: "ephemeral"
} } },
    });

    // or where the prompt is defined
    chat.prompt.set(SYSTEM_PROMPT, {
providerOptions: { anthropic: { cacheControl: { type: "ephemeral" } } },
    });
    ```

Without an option, `system` stays a plain string. Pairs with a
`prepareMessages` cache breakpoint to cache the conversation prefix
across turns too.

- Three fixes for custom agent loops (`chat.customAgent`,
`chat.createSession`, and hand-rolled `MessageAccumulator` loops):
([#3936](https://github.com/triggerdotdev/trigger.dev/pull/3936))

- Continuation runs no longer replay already-answered user messages into
the first turn. The `.in` resume cursor is now seeded before any
listener attaches (the same boot logic `chat.agent` uses), so a chat
that continues after a cancel, crash, or upgrade only sees genuinely new
messages.
- Steering a hand-rolled loop mid-stream no longer wipes the in-flight
assistant response. `chat.pipeAndCapture` now stamps a server-generated
message id on the stream, so a `prepareStep` injection keeps the partial
text instead of replacing the message.
- Task-backed tools (`ai.toolExecute`) now work from custom agent loops:
the parent's session is threaded to the child run, so child tasks can
stream progress into the chat with `chat.stream.writer({ target: "root"
})` instead of failing with "session handle is not initialized".

- The agent skills installed by `trigger skills` are now namespaced with
a `trigger-` prefix (e.g. `trigger-authoring-tasks`,
`trigger-getting-started`) so they don't collide with unrelated skills
in your coding agent's skills directory. Adds a `trigger-cost-savings`
skill for auditing and reducing compute spend (right-sizing machines,
`maxDuration`, batching, debounce), and `@trigger.dev/sdk` now bundles
the full Trigger.dev documentation so your agent can read the complete,
version-pinned reference directly from node_modules.
([#3970](https://github.com/triggerdotdev/trigger.dev/pull/3970))

-   Updated dependencies:
    -   `@trigger.dev/core@4.5.0-rc.7`

## @trigger.dev/plugins@4.5.0-rc.7

### Patch Changes

-   Updated dependencies:
    -   `@trigger.dev/core@4.5.0-rc.7`

</details>

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

.changeset/pre.json

@@ -19,6 +19,7 @@
     "@trigger.dev/sdk": "4.4.6"
   },
   "changesets": [
+    "agent-skills-bundled-in-sdk",
     "agent-skills",
     "ai-prompts",
     "ai-sdk-7-support",
@@ -31,17 +32,22 @@
     "chat-agent-tools",
     "chat-agent",
     "chat-boot-cursor",
+    "chat-headstart-custom-backends",
     "chat-headstart-hydrate",
     "chat-headstart-reasoning",
+    "chat-headstart-trigger-config",
     "chat-history-read-primitives",
     "chat-session-attributes",
     "chat-slim-wire-merge",
     "chat-start-session-action-typed-client-data",
+    "chat-system-prompt-caching",
     "chat-transport-recreate-missing-session",
     "cli-deploy-skip-rewrite-timestamp",
+    "cli-dev-without-project",
     "cli-init-ai-tooling",
     "coerce-concurrency-key-to-string",
     "create-session-stop-continuation",
+    "custom-agent-loop-fixes",
     "dequeue-latency-histogram",
     "duplicate-task-ids",
     "env-vars-tracing-forceflush-typecheck",
@@ -66,7 +72,9 @@
     "runs-list-region-filter",
     "s2-batch-transform-linger-fix",
     "sessions-primitive",
+    "span-api-cached-cost",
     "trigger-client",
+    "trigger-skill-namespace-and-docs",
     "trigger-skills-installer",
     "unflatten-attributes-conflict",
     "warm-start-external-trace-context-leak"

.server-changes/fix-queue-search-performance.md

@@ -1,6 +0,0 @@
----
-area: webapp
-type: fix
----
-
-Speed up queue search by skipping count on filtered queries and using hasMore pagination

.server-changes/harden-realtime-change-publishing.md

@@ -1,6 +0,0 @@
----
-area: webapp
-type: improvement
----
-
-Harden the native realtime backend's run-change publishing so a publish can never throw into a run lifecycle operation and never buffers commands in memory during a pub/sub Redis outage.

.server-changes/hide-self-serve-billing-ui.md

@@ -1,6 +0,0 @@
----
-area: webapp
-type: improvement
----
-
-Hide self-serve billing and upgrade options for directly-billed organizations; show Contact us instead.

.server-changes/llm-cost-cached-token-double-charge.md

@@ -1,6 +0,0 @@
----
-area: webapp
-type: fix
----
-
-LLM cost no longer double-counts cached input tokens. Prompt-cache reads and writes are now billed once at their cache rate instead of also being charged at the full input price, so cost and cache hit-rate figures on the AI metrics dashboard and Models page are accurate.

.server-changes/locked-version-trigger-stale-replica.md

@@ -1,6 +0,0 @@
----
-area: webapp
-type: fix
----
-
-Fix locked-version triggers such as triggerAndWait occasionally failing with "task not found on locked version" for a task that is actually registered, by confirming against the primary database when the read replica returns no row.

.server-changes/models-page-usage-tabs.md

@@ -1,6 +0,0 @@
----
-area: webapp
-type: feature
----
-
-The Models page now has a Your models tab showing your project's model usage (cost, calls, latency, prompt-cache savings, and trend sparklines over a selectable time range) alongside the full model library, ordered by provider relevance and release date. The AI metrics dashboard also gains a caching section with cache hit rate, cached tokens, and estimated savings.

.server-changes/plan-aware-compute-migration.md

@@ -1,6 +0,0 @@
----
-area: webapp
-type: feature
----
-
-Gradually roll out a new run execution backend to a configurable percentage of organizations.

.server-changes/playground-history-tab.md

@@ -1,6 +0,0 @@
----
-area: webapp
-type: improvement
----
-
-Move the agent playground "Recent" conversations popover into a dedicated "History" tab in the sidebar, with the currently active conversation highlighted.

.server-changes/prevent-db-seed-script-hang.md

@@ -1,6 +0,0 @@
----
-area: webapp
-type: fix
----
-
-Exit db:seed script on success to prevent hanging.

.server-changes/quiet-expected-error-logs.md

@@ -1,6 +0,0 @@
----
-area: webapp
-type: improvement
----
-
-Log expected auth-code and checkpoint-restore conditions at `warn` instead of `error`.

.server-changes/search-input-rerender.md

@@ -1,6 +0,0 @@
----
-area: webapp
-type: fix
----
-
-Fix the task page search bar clearing or resetting while typing, caused by a re-render race between the input sync effect and the activity charts.

.server-changes/standard-task-sidebar-properties.md

@@ -1,6 +0,0 @@
----
-area: webapp
-type: improvement
----
-
-Expand the standard task landing page sidebar to surface more task metadata: description, export name, worker version, queue (with concurrency + paused state), machine, max duration, TTL, retry config, and payload schema presence.

.server-changes/task-meta-cache-resolution-metrics.md

@@ -1,6 +0,0 @@
----
-area: webapp
-type: improvement
----
-
-Emit metrics for task metadata cache resolution on the trigger path, surfacing the cache hit rate and how often a read replica returned empty for a row the primary had.

.server-changes/vercel-sync-reserved-env-vars.md

@@ -1,6 +0,0 @@
----
-area: webapp
-type: fix
----
-
-Fix Vercel env var sync and onboarding preview leaking reserved `TRIGGER_*` keys.

.server-changes/warm-start-delivery-verification.md

@@ -1,6 +0,0 @@
----
-area: supervisor
-type: feature
----
-
-Verify warm-start dispatches were acted on and cold-start the run within seconds when a dispatch is silently lost (opt-in via TRIGGER_WARM_START_VERIFY_ENABLED).

.server-changes/workload-create-duration-metric.md

@@ -1,6 +0,0 @@
----
-area: supervisor
-type: improvement
----
-
-Add a `workload_create_duration_seconds` Prometheus histogram recording the duration and outcome (success/error) of workload manager create calls, labeled by backend (kubernetes/compute/docker). Previously failed creates were only visible as error logs.

hosting/k8s/helm/Chart.yaml

@@ -2,8 +2,8 @@ apiVersion: v2
 name: trigger
 description: The official Trigger.dev Helm chart
 type: application
-version: 4.5.0-rc.6
-appVersion: v4.5.0-rc.6
+version: 4.5.0-rc.7
+appVersion: v4.5.0-rc.7
 home: https://trigger.dev
 sources:
   - https://github.com/triggerdotdev/trigger.dev

packages/build/CHANGELOG.md

@@ -1,5 +1,12 @@
 # @trigger.dev/build
 
+## 4.5.0-rc.7
+
+### Patch Changes
+
+- Updated dependencies:
+  - `@trigger.dev/core@4.5.0-rc.7`
+
 ## 4.5.0-rc.6
 
 ### Patch Changes

packages/build/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@trigger.dev/build",
-  "version": "4.5.0-rc.6",
+  "version": "4.5.0-rc.7",
   "description": "trigger.dev build extensions",
   "license": "MIT",
   "publishConfig": {
@@ -78,7 +78,7 @@
   },
   "dependencies": {
     "@prisma/config": "^6.10.0",
-    "@trigger.dev/core": "workspace:4.5.0-rc.6",
+    "@trigger.dev/core": "workspace:4.5.0-rc.7",
     "mlly": "^1.7.1",
     "pkg-types": "^1.1.3",
     "resolve": "^1.22.8",

packages/cli-v3/CHANGELOG.md

@@ -1,5 +1,17 @@
 # trigger.dev
 
+## 4.5.0-rc.7
+
+### Patch Changes
+
+- `@trigger.dev/sdk` now bundles the Trigger.dev agent skills and a curated snapshot of the docs those skills reference. The skills that `trigger skills` installs into your coding agent read this content from node_modules, so the guidance your AI assistant follows is pinned to the SDK version installed in your project and stays current across upgrades instead of going stale until the next reinstall. ([#3937](https://github.com/triggerdotdev/trigger.dev/pull/3937))
+- Running a CLI command like `dev`, `deploy`, `preview`, or `update` before initializing a project no longer crashes with a raw `Cannot find matching package.json` stack trace. The CLI now detects the missing project and points you to `npx trigger.dev@latest init` instead. ([#3929](https://github.com/triggerdotdev/trigger.dev/pull/3929))
+- The agent skills installed by `trigger skills` are now namespaced with a `trigger-` prefix (e.g. `trigger-authoring-tasks`, `trigger-getting-started`) so they don't collide with unrelated skills in your coding agent's skills directory. Adds a `trigger-cost-savings` skill for auditing and reducing compute spend (right-sizing machines, `maxDuration`, batching, debounce), and `@trigger.dev/sdk` now bundles the full Trigger.dev documentation so your agent can read the complete, version-pinned reference directly from node_modules. ([#3970](https://github.com/triggerdotdev/trigger.dev/pull/3970))
+- Updated dependencies:
+  - `@trigger.dev/core@4.5.0-rc.7`
+  - `@trigger.dev/build@4.5.0-rc.7`
+  - `@trigger.dev/schema-to-json@4.5.0-rc.7`
+
 ## 4.5.0-rc.6
 
 ### Patch Changes

packages/cli-v3/package.json

@@ -1,6 +1,6 @@
 {
   "name": "trigger.dev",
-  "version": "4.5.0-rc.6",
+  "version": "4.5.0-rc.7",
   "description": "A Command-Line Interface for Trigger.dev projects",
   "type": "module",
   "license": "MIT",
@@ -97,9 +97,9 @@
     "@opentelemetry/sdk-trace-node": "2.7.1",
     "@opentelemetry/semantic-conventions": "1.41.1",
     "@s2-dev/streamstore": "^0.22.10",
-    "@trigger.dev/build": "workspace:4.5.0-rc.6",
-    "@trigger.dev/core": "workspace:4.5.0-rc.6",
-    "@trigger.dev/schema-to-json": "workspace:4.5.0-rc.6",
+    "@trigger.dev/build": "workspace:4.5.0-rc.7",
+    "@trigger.dev/core": "workspace:4.5.0-rc.7",
+    "@trigger.dev/schema-to-json": "workspace:4.5.0-rc.7",
     "ansi-escapes": "^7.0.0",
     "braces": "^3.0.3",
     "c12": "^1.11.1",

packages/core/CHANGELOG.md

@@ -1,5 +1,11 @@
 # internal-platform
 
+## 4.5.0-rc.7
+
+### Patch Changes
+
+- The run span API response now includes `cachedCost` and `cacheCreationCost` on the `ai` object, alongside the existing `inputCost` / `outputCost` / `totalCost`. `inputCost` reflects only the non-cached input, so these fields let you reconstruct the full cost breakdown for prompt-cached calls. ([#3958](https://github.com/triggerdotdev/trigger.dev/pull/3958))
+
 ## 4.5.0-rc.6
 
 ### Patch Changes

packages/core/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@trigger.dev/core",
-  "version": "4.5.0-rc.6",
+  "version": "4.5.0-rc.7",
   "description": "Core code used across the Trigger.dev SDK and platform",
   "license": "MIT",
   "publishConfig": {

packages/plugins/CHANGELOG.md

@@ -1,5 +1,12 @@
 # @trigger.dev/plugins
 
+## 4.5.0-rc.7
+
+### Patch Changes
+
+- Updated dependencies:
+  - `@trigger.dev/core@4.5.0-rc.7`
+
 ## 4.5.0-rc.6
 
 ### Patch Changes

packages/plugins/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@trigger.dev/plugins",
-  "version": "4.5.0-rc.6",
+  "version": "4.5.0-rc.7",
   "description": "Plugin contracts and interfaces for Trigger.dev",
   "license": "MIT",
   "private": true,

packages/python/CHANGELOG.md

@@ -1,5 +1,14 @@
 # @trigger.dev/python
 
+## 4.5.0-rc.7
+
+### Patch Changes
+
+- Updated dependencies:
+  - `@trigger.dev/sdk@4.5.0-rc.7`
+  - `@trigger.dev/core@4.5.0-rc.7`
+  - `@trigger.dev/build@4.5.0-rc.7`
+
 ## 4.5.0-rc.6
 
 ### Patch Changes

packages/python/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@trigger.dev/python",
-  "version": "4.5.0-rc.6",
+  "version": "4.5.0-rc.7",
   "description": "Python runtime and build extension for Trigger.dev",
   "license": "MIT",
   "publishConfig": {
@@ -45,7 +45,7 @@
     "check-exports": "attw --pack ."
   },
   "dependencies": {
-    "@trigger.dev/core": "workspace:4.5.0-rc.6",
+    "@trigger.dev/core": "workspace:4.5.0-rc.7",
     "tinyexec": "^0.3.2"
   },
   "devDependencies": {
@@ -56,12 +56,12 @@
     "tsx": "4.17.0",
     "esbuild": "^0.23.0",
     "@arethetypeswrong/cli": "^0.15.4",
-    "@trigger.dev/build": "workspace:4.5.0-rc.6",
-    "@trigger.dev/sdk": "workspace:4.5.0-rc.6"
+    "@trigger.dev/build": "workspace:4.5.0-rc.7",
+    "@trigger.dev/sdk": "workspace:4.5.0-rc.7"
   },
   "peerDependencies": {
-    "@trigger.dev/sdk": "workspace:^4.5.0-rc.6",
-    "@trigger.dev/build": "workspace:^4.5.0-rc.6"
+    "@trigger.dev/sdk": "workspace:^4.5.0-rc.7",
+    "@trigger.dev/build": "workspace:^4.5.0-rc.7"
   },
   "engines": {
     "node": ">=18.20.0"

packages/react-hooks/CHANGELOG.md

@@ -1,5 +1,12 @@
 # @trigger.dev/react-hooks
 
+## 4.5.0-rc.7
+
+### Patch Changes
+
+- Updated dependencies:
+  - `@trigger.dev/core@4.5.0-rc.7`
+
 ## 4.5.0-rc.6
 
 ### Patch Changes

packages/react-hooks/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@trigger.dev/react-hooks",
-  "version": "4.5.0-rc.6",
+  "version": "4.5.0-rc.7",
   "description": "trigger.dev react hooks",
   "license": "MIT",
   "publishConfig": {
@@ -37,7 +37,7 @@
     "check-exports": "attw --pack ."
   },
   "dependencies": {
-    "@trigger.dev/core": "workspace:^4.5.0-rc.6",
+    "@trigger.dev/core": "workspace:^4.5.0-rc.7",
     "swr": "^2.2.5"
   },
   "devDependencies": {

packages/redis-worker/CHANGELOG.md

@@ -1,5 +1,12 @@
 # @trigger.dev/redis-worker
 
+## 4.5.0-rc.7
+
+### Patch Changes
+
+- Updated dependencies:
+  - `@trigger.dev/core@4.5.0-rc.7`
+
 ## 4.5.0-rc.6
 
 ### Patch Changes

packages/redis-worker/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@trigger.dev/redis-worker",
-  "version": "4.5.0-rc.6",
+  "version": "4.5.0-rc.7",
   "description": "Redis worker for trigger.dev",
   "license": "MIT",
   "publishConfig": {
@@ -23,7 +23,7 @@
     "test": "vitest --sequence.concurrent=false --no-file-parallelism"
   },
   "dependencies": {
-    "@trigger.dev/core": "workspace:4.5.0-rc.6",
+    "@trigger.dev/core": "workspace:4.5.0-rc.7",
     "lodash.omit": "^4.5.0",
     "nanoid": "^5.0.7",
     "p-limit": "^6.2.0",

packages/rsc/CHANGELOG.md

@@ -1,5 +1,12 @@
 # @trigger.dev/rsc
 
+## 4.5.0-rc.7
+
+### Patch Changes
+
+- Updated dependencies:
+  - `@trigger.dev/core@4.5.0-rc.7`
+
 ## 4.5.0-rc.6
 
 ### Patch Changes

packages/rsc/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@trigger.dev/rsc",
-  "version": "4.5.0-rc.6",
+  "version": "4.5.0-rc.7",
   "description": "trigger.dev rsc",
   "license": "MIT",
   "publishConfig": {
@@ -37,14 +37,14 @@
     "check-exports": "attw --pack ."
   },
   "dependencies": {
-    "@trigger.dev/core": "workspace:^4.5.0-rc.6",
+    "@trigger.dev/core": "workspace:^4.5.0-rc.7",
     "mlly": "^1.7.1",
     "react": "19.0.0-rc.1",
     "react-dom": "19.0.0-rc.1"
   },
   "devDependencies": {
     "@arethetypeswrong/cli": "^0.15.4",
-    "@trigger.dev/build": "workspace:^4.5.0-rc.6",
+    "@trigger.dev/build": "workspace:^4.5.0-rc.7",
     "@types/node": "^20.14.14",
     "@types/react": "*",
     "@types/react-dom": "*",

packages/schema-to-json/CHANGELOG.md

@@ -1,5 +1,12 @@
 # @trigger.dev/schema-to-json
 
+## 4.5.0-rc.7
+
+### Patch Changes
+
+- Updated dependencies:
+  - `@trigger.dev/core@4.5.0-rc.7`
+
 ## 4.5.0-rc.6
 
 ### Patch Changes

packages/schema-to-json/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@trigger.dev/schema-to-json",
-  "version": "4.5.0-rc.6",
+  "version": "4.5.0-rc.7",
   "description": "Convert various schema validation libraries to JSON Schema",
   "license": "MIT",
   "publishConfig": {

packages/trigger-sdk/CHANGELOG.md

@@ -1,5 +1,77 @@
 # @trigger.dev/sdk
 
+## 4.5.0-rc.7
+
+### Patch Changes
+
+- `@trigger.dev/sdk` now bundles the Trigger.dev agent skills and a curated snapshot of the docs those skills reference. The skills that `trigger skills` installs into your coding agent read this content from node_modules, so the guidance your AI assistant follows is pinned to the SDK version installed in your project and stays current across upgrades instead of going stale until the next reinstall. ([#3937](https://github.com/triggerdotdev/trigger.dev/pull/3937))
+- `chat.headStart` now works with the `chat.customAgent` and `chat.createSession` backends, not only `chat.agent`. The warm step-1 response hands over to your loop the same way it does for a managed agent. ([#3963](https://github.com/triggerdotdev/trigger.dev/pull/3963))
+
+  In a `chat.customAgent` loop, consume the handover on turn 0:
+
+  ```ts
+  const conversation = new chat.MessageAccumulator();
+  const { isFinal, skipped } = await conversation.consumeHandover({ payload });
+  if (skipped) return; // warm handler aborted, so exit without a turn
+  if (isFinal) {
+    await chat.writeTurnComplete(); // step 1 is the response, no streamText
+  } else {
+    const result = streamText({ model, messages: conversation.modelMessages, tools });
+    // Pass originalMessages so the handed-over tool round merges into the
+    // step-1 assistant instead of starting a new message.
+    const response = await chat.pipeAndCapture(result, {
+      originalMessages: conversation.uiMessages,
+    });
+    if (response) await conversation.addResponse(response);
+  }
+  ```
+
+  With `chat.createSession`, the iterator surfaces it as `turn.handover`; call `turn.complete()` with no argument on a final handover. The lower-level `chat.waitForHandover()` and `accumulator.applyHandover()` are also exported for hand-rolled loops.
+
+- Add `triggerConfig` support to `chat.headStart()` and `chat.openSession()`, so the auto-triggered handover-prepare run inherits tags, queue, machine, and other session trigger options the same way `chat.createStartSessionAction()` does. The `chat:{chatId}` tag is prepended automatically. ([#3963](https://github.com/triggerdotdev/trigger.dev/pull/3963))
+
+  ```ts
+  export const POST = chat.headStart({
+    agentId: "my-agent",
+    triggerConfig: { tags: ["org:acme"], queue: "chat" },
+    run: async ({ chat }) => streamText({ ...chat.toStreamTextOptions(), model }),
+  });
+  ```
+
+  Because the session is created once on the first head-start turn and is idempotent on the chat id, this is the only place to set those options for a head-start chat's lifetime. `chat.createStartSessionAction()` now also forwards `maxDuration`, `region`, and `lockToVersion` so both session entry points stay consistent.
+
+- Cache your chat agent's system prompt with Anthropic prompt caching. `chat.toStreamTextOptions()` now emits the system prompt as a cacheable message when you opt in, so a large, stable system block is billed at cache-read rates on every turn instead of full price. ([#3952](https://github.com/triggerdotdev/trigger.dev/pull/3952))
+
+  ```ts
+  // at the streamText call site (Anthropic sugar)
+  streamText({
+    ...chat.toStreamTextOptions({ cacheControl: { type: "ephemeral" } }),
+    messages,
+  });
+
+  // provider-agnostic equivalent
+  chat.toStreamTextOptions({
+    systemProviderOptions: { anthropic: { cacheControl: { type: "ephemeral" } } },
+  });
+
+  // or where the prompt is defined
+  chat.prompt.set(SYSTEM_PROMPT, {
+    providerOptions: { anthropic: { cacheControl: { type: "ephemeral" } } },
+  });
+  ```
+
+  Without an option, `system` stays a plain string. Pairs with a `prepareMessages` cache breakpoint to cache the conversation prefix across turns too.
+
+- Three fixes for custom agent loops (`chat.customAgent`, `chat.createSession`, and hand-rolled `MessageAccumulator` loops): ([#3936](https://github.com/triggerdotdev/trigger.dev/pull/3936))
+
+  - Continuation runs no longer replay already-answered user messages into the first turn. The `.in` resume cursor is now seeded before any listener attaches (the same boot logic `chat.agent` uses), so a chat that continues after a cancel, crash, or upgrade only sees genuinely new messages.
+  - Steering a hand-rolled loop mid-stream no longer wipes the in-flight assistant response. `chat.pipeAndCapture` now stamps a server-generated message id on the stream, so a `prepareStep` injection keeps the partial text instead of replacing the message.
+  - Task-backed tools (`ai.toolExecute`) now work from custom agent loops: the parent's session is threaded to the child run, so child tasks can stream progress into the chat with `chat.stream.writer({ target: "root" })` instead of failing with "session handle is not initialized".
+
+- The agent skills installed by `trigger skills` are now namespaced with a `trigger-` prefix (e.g. `trigger-authoring-tasks`, `trigger-getting-started`) so they don't collide with unrelated skills in your coding agent's skills directory. Adds a `trigger-cost-savings` skill for auditing and reducing compute spend (right-sizing machines, `maxDuration`, batching, debounce), and `@trigger.dev/sdk` now bundles the full Trigger.dev documentation so your agent can read the complete, version-pinned reference directly from node_modules. ([#3970](https://github.com/triggerdotdev/trigger.dev/pull/3970))
+- Updated dependencies:
+  - `@trigger.dev/core@4.5.0-rc.7`
+
 ## 4.5.0-rc.6
 
 ### Patch Changes

packages/trigger-sdk/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@trigger.dev/sdk",
-  "version": "4.5.0-rc.6",
+  "version": "4.5.0-rc.7",
   "description": "trigger.dev Node.JS SDK",
   "license": "MIT",
   "publishConfig": {
@@ -77,7 +77,7 @@
   "dependencies": {
     "@opentelemetry/api": "1.9.1",
     "@opentelemetry/semantic-conventions": "1.41.1",
-    "@trigger.dev/core": "workspace:4.5.0-rc.6",
+    "@trigger.dev/core": "workspace:4.5.0-rc.7",
     "chalk": "^5.2.0",
     "cronstrue": "^2.21.0",
     "debug": "^4.3.4",

pnpm-lock.yaml

@@ -1501,7 +1501,7 @@ importers:
         specifier: ^6.10.0
         version: 6.19.0(magicast@0.3.5)
       '@trigger.dev/core':
-        specifier: workspace:4.5.0-rc.6
+        specifier: workspace:4.5.0-rc.7
         version: link:../core
       mlly:
         specifier: ^1.7.1
@@ -1577,13 +1577,13 @@ importers:
         specifier: ^0.22.10
         version: 0.22.10(supports-color@10.0.0)
       '@trigger.dev/build':
-        specifier: workspace:4.5.0-rc.6
+        specifier: workspace:4.5.0-rc.7
         version: link:../build
       '@trigger.dev/core':
-        specifier: workspace:4.5.0-rc.6
+        specifier: workspace:4.5.0-rc.7
         version: link:../core
       '@trigger.dev/schema-to-json':
-        specifier: workspace:4.5.0-rc.6
+        specifier: workspace:4.5.0-rc.7
         version: link:../schema-to-json
       ansi-escapes:
         specifier: ^7.0.0
@@ -1976,7 +1976,7 @@ importers:
   packages/python:
     dependencies:
       '@trigger.dev/core':
-        specifier: workspace:4.5.0-rc.6
+        specifier: workspace:4.5.0-rc.7
         version: link:../core
       tinyexec:
         specifier: ^0.3.2
@@ -1986,10 +1986,10 @@ importers:
         specifier: ^0.15.4
         version: 0.15.4
       '@trigger.dev/build':
-        specifier: workspace:4.5.0-rc.6
+        specifier: workspace:4.5.0-rc.7
         version: link:../build
       '@trigger.dev/sdk':
-        specifier: workspace:4.5.0-rc.6
+        specifier: workspace:4.5.0-rc.7
         version: link:../trigger-sdk
       '@types/node':
         specifier: 20.14.14
@@ -2013,7 +2013,7 @@ importers:
   packages/react-hooks:
     dependencies:
       '@trigger.dev/core':
-        specifier: workspace:^4.5.0-rc.6
+        specifier: workspace:^4.5.0-rc.7
         version: link:../core
       react:
         specifier: ^18.0 || ^19.0 || ^19.0.0-rc
@@ -2047,7 +2047,7 @@ importers:
   packages/redis-worker:
     dependencies:
       '@trigger.dev/core':
-        specifier: workspace:4.5.0-rc.6
+        specifier: workspace:4.5.0-rc.7
         version: link:../core
       cron-parser:
         specifier: ^4.9.0
@@ -2096,7 +2096,7 @@ importers:
   packages/rsc:
     dependencies:
       '@trigger.dev/core':
-        specifier: workspace:^4.5.0-rc.6
+        specifier: workspace:^4.5.0-rc.7
         version: link:../core
       mlly:
         specifier: ^1.7.1
@@ -2112,7 +2112,7 @@ importers:
         specifier: ^0.15.4
         version: 0.15.4
       '@trigger.dev/build':
-        specifier: workspace:^4.5.0-rc.6
+        specifier: workspace:^4.5.0-rc.7
         version: link:../build
       '@types/node':
         specifier: 20.14.14
@@ -2191,7 +2191,7 @@ importers:
         specifier: 1.41.1
         version: 1.41.1
       '@trigger.dev/core':
-        specifier: workspace:4.5.0-rc.6
+        specifier: workspace:4.5.0-rc.7
         version: link:../core
       chalk:
         specifier: ^5.2.0