feat(sdk,cli): namespace agent skills with trigger- and add cost-savings#3970
Merged
ericallam merged 4 commits intoJun 16, 2026
Conversation
🦋 Changeset detectedLatest commit: efe8dc6 The changes in this PR will be included in the next version bump. This PR includes changesets to release 25 packages
Not sure what this means? Click here to learn what changesets are. Click here if you're a maintainer who wants to add another changeset to this PR |
Contributor
|
Note Reviews pausedIt looks like this branch is under active development. To avoid overwhelming you with review comments due to an influx of new commits, CodeRabbit has automatically paused this review. You can configure this behavior by changing the Use the following commands to manage reviews:
Use the checkboxes below for quick actions:
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Repository UI Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (1)
🚧 Files skipped from review as they are similar to previous changes (1)
📜 Recent review details⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (38)
WalkthroughAll agent skills are renamed to use a 🚥 Pre-merge checks | ✅ 3 | ❌ 2❌ Failed checks (2 warnings)
✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches📝 Generate docstrings
🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![devin-ai-integration[bot]](https://avatars.githubusercontent.com/in/811515?s=60&v=4){kind=small}
This comment was marked as resolved.
This comment was marked as resolved.
Sorry, something went wrong.
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
This comment was marked as resolved.
This comment was marked as resolved.
Sorry, something went wrong.
nicktrn
approved these changes
Jun 16, 2026
d-cs
approved these changes
Jun 16, 2026
The installed skills now use a `trigger-` prefix (`trigger-authoring-tasks`, `trigger-getting-started`, and so on) so they do not collide with non-Trigger skills in a shared agent skills directory, matching the public skills repo. Adds `trigger-cost-savings`: an MCP-driven audit that right-sizes machines, flags missing `maxDuration`, and spots sequential triggers that could batch. `@trigger.dev/sdk` now bundles the entire Documentation section of the docs (not just a curated subset), so an agent has the full version-pinned reference in node_modules. The build derives the set from the docs navigation, so it stays in sync automatically.
ericallam
force-pushed
the
feature/tri-11011-bundle-all-documentation-docs-in-the-sdk-prefix-skills-with
branch
from
95db45c to
603d5e4
Compare
@trigger.dev/build
trigger.dev
@trigger.dev/core
@trigger.dev/python
@trigger.dev/react-hooks
@trigger.dev/redis-worker
@trigger.dev/rsc
@trigger.dev/schema-to-json
@trigger.dev/sdk
commit: |
Contributor
There was a problem hiding this comment.
♻️ Duplicate comments (1)
packages/trigger-sdk/skills/trigger-cost-savings/SKILL.md (1)
3-7:⚠️ Potential issue | 🟠 Major | ⚡ Quick winFrontmatter
descriptionmust be a single line (unresolved from prior review).The
description: >multiline YAML block scalar will not parse correctly. The SDK's frontmatter parser only supports single-linekey: valuepairs; it will readdescriptionas just">"instead of the intended text. Collapse the description to a single line.🐛 Proposed fix
-description: > - Analyze Trigger.dev tasks, schedules, and runs for cost optimization opportunities. Use when - asked to reduce spend, optimize costs, audit usage, right-size machines, or review task - efficiency. Combines static source analysis with live run analysis via the Trigger.dev MCP - tools (list_runs, get_run_details, get_current_worker). +description: "Analyze Trigger.dev tasks, schedules, and runs for cost optimization opportunities. Use when asked to reduce spend, optimize costs, audit usage, right-size machines, or review task efficiency. Combines static source analysis with live run analysis via the Trigger.dev MCP tools (list_runs, get_run_details, get_current_worker)."
ℹ️ Review info
⚙️ Run configuration
Configuration used: Repository UI
Review profile: CHILL
Plan: Pro
Run ID: 7f96d702-97d9-4db6-90b3-61789b9be626
📒 Files selected for processing (16)
.changeset/trigger-skill-namespace-and-docs.mddocs/mcp-agent-rules.mdxdocs/skills.mdxpackages/cli-v3/skills/trigger-authoring-chat-agent/SKILL.mdpackages/cli-v3/skills/trigger-authoring-tasks/SKILL.mdpackages/cli-v3/skills/trigger-chat-agent-advanced/SKILL.mdpackages/cli-v3/skills/trigger-cost-savings/SKILL.mdpackages/cli-v3/skills/trigger-getting-started/SKILL.mdpackages/cli-v3/skills/trigger-realtime-and-frontend/SKILL.mdpackages/cli-v3/src/commands/init.tspackages/trigger-sdk/skills/trigger-authoring-chat-agent/SKILL.mdpackages/trigger-sdk/skills/trigger-authoring-tasks/SKILL.mdpackages/trigger-sdk/skills/trigger-chat-agent-advanced/SKILL.mdpackages/trigger-sdk/skills/trigger-cost-savings/SKILL.mdpackages/trigger-sdk/skills/trigger-realtime-and-frontend/SKILL.mdscripts/bundleSdkDocs.ts
✅ Files skipped from review due to trivial changes (10)
- packages/trigger-sdk/skills/trigger-authoring-tasks/SKILL.md
- packages/cli-v3/skills/trigger-cost-savings/SKILL.md
- packages/cli-v3/src/commands/init.ts
- docs/mcp-agent-rules.mdx
- packages/cli-v3/skills/trigger-authoring-tasks/SKILL.md
- packages/cli-v3/skills/trigger-getting-started/SKILL.md
- packages/cli-v3/skills/trigger-chat-agent-advanced/SKILL.md
- packages/cli-v3/skills/trigger-authoring-chat-agent/SKILL.md
- packages/trigger-sdk/skills/trigger-authoring-chat-agent/SKILL.md
- packages/trigger-sdk/skills/trigger-chat-agent-advanced/SKILL.md
🚧 Files skipped from review as they are similar to previous changes (2)
- .changeset/trigger-skill-namespace-and-docs.md
- scripts/bundleSdkDocs.ts
📜 Review details
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (39)
- GitHub Check: internal / 🧪 Unit Tests: Internal (10, 12)
- GitHub Check: internal / 🧪 Unit Tests: Internal (5, 12)
- GitHub Check: internal / 🧪 Unit Tests: Internal (6, 12)
- GitHub Check: internal / 🧪 Unit Tests: Internal (7, 12)
- GitHub Check: internal / 🧪 Unit Tests: Internal (11, 12)
- GitHub Check: internal / 🧪 Unit Tests: Internal (1, 12)
- GitHub Check: internal / 🧪 Unit Tests: Internal (8, 12)
- GitHub Check: internal / 🧪 Unit Tests: Internal (4, 12)
- GitHub Check: internal / 🧪 Unit Tests: Internal (9, 12)
- GitHub Check: internal / 🧪 Unit Tests: Internal (2, 12)
- GitHub Check: internal / 🧪 Unit Tests: Internal (12, 12)
- GitHub Check: webapp / 🧪 Unit Tests: Webapp (7, 10)
- GitHub Check: webapp / 🧪 Unit Tests: Webapp (9, 10)
- GitHub Check: webapp / 🧪 Unit Tests: Webapp (3, 10)
- GitHub Check: webapp / 🧪 Unit Tests: Webapp (5, 10)
- GitHub Check: e2e / 🧪 CLI v3 tests (ubuntu-latest - pnpm)
- GitHub Check: internal / 🧪 Unit Tests: Internal (3, 12)
- GitHub Check: webapp / 🧪 Unit Tests: Webapp (8, 10)
- GitHub Check: webapp / 🧪 Unit Tests: Webapp (4, 10)
- GitHub Check: webapp / 🧪 Unit Tests: Webapp (10, 10)
- GitHub Check: webapp / 🧪 Unit Tests: Webapp (6, 10)
- GitHub Check: sdk-compat / Node.js 22.12 (ubuntu-latest)
- GitHub Check: webapp / 🧪 Unit Tests: Webapp (1, 10)
- GitHub Check: webapp / 🧪 Unit Tests: Webapp (2, 10)
- GitHub Check: packages / 🧪 Unit Tests: Packages (3, 3)
- GitHub Check: sdk-compat / Cloudflare Workers
- GitHub Check: packages / 🧪 Unit Tests: Packages (1, 3)
- GitHub Check: e2e / 🧪 CLI v3 tests (ubuntu-latest - npm)
- GitHub Check: sdk-compat / Deno Runtime
- GitHub Check: sdk-compat / Node.js 20.20 (ubuntu-latest)
- GitHub Check: packages / 🧪 Unit Tests: Packages (2, 3)
- GitHub Check: e2e / 🧪 CLI v3 tests (windows-latest - npm)
- GitHub Check: sdk-compat / Bun Runtime
- GitHub Check: e2e / 🧪 CLI v3 tests (windows-latest - pnpm)
- GitHub Check: e2e-webapp / 🧪 E2E Tests: Webapp
- GitHub Check: typecheck / typecheck
- GitHub Check: Build and publish previews
- GitHub Check: audit
- GitHub Check: Analyze (javascript-typescript)
🧰 Additional context used
📓 Path-based instructions (2)
docs/**/*.mdx
📄 CodeRabbit inference engine (docs/CLAUDE.md)
docs/**/*.mdx: MDX documentation pages must include frontmatter with title (required), description (required), and sidebarTitle (optional) in YAML format
Use Mintlify components for structured content: , , , , , , /, /
Always import from@trigger.dev/sdkin code examples (never from@trigger.dev/sdk/v3)
Code examples must be complete and runnable where possible
Use language tags in code fences:typescript,bash,json
Files:
docs/skills.mdx
**/*.{js,ts,tsx,jsx,css,json,md}
📄 CodeRabbit inference engine (AGENTS.md)
Use Prettier for code formatting and run
pnpm run formatbefore committing
Files:
packages/cli-v3/skills/trigger-realtime-and-frontend/SKILL.mdpackages/trigger-sdk/skills/trigger-cost-savings/SKILL.mdpackages/trigger-sdk/skills/trigger-realtime-and-frontend/SKILL.md
🧠 Learnings (2)
📚 Learning: 2026-03-10T12:44:14.176Z
Learnt from: nicktrn
Repo: triggerdotdev/trigger.dev PR: 3200
File: docs/config/config-file.mdx:353-368
Timestamp: 2026-03-10T12:44:14.176Z
Learning: In the trigger.dev repo, docs PRs are often companions to implementation PRs. When reviewing docs PRs (MDX files under docs/), check the PR description for any companion/related PR references and verify that the documented features exist in those companion PRs before flagging missing implementations. This ensures docs stay in sync with code changes across related PRs.
Applied to files:
docs/skills.mdx
📚 Learning: 2026-04-30T20:30:29.458Z
Learnt from: ericallam
Repo: triggerdotdev/trigger.dev PR: 3226
File: docs/ai-chat/quick-start.mdx:13-13
Timestamp: 2026-04-30T20:30:29.458Z
Learning: In this repo’s documentation MDX files (`docs/**/*.mdx`), use `ts` and `tsx` (not `typescript`) as the code-fence language tags for TypeScript/TSX snippets. Do not flag `ts`/`tsx` code-fence language tags as incorrect in any docs MDX file, since this is the site-wide Mintlify-compatible convention.
Applied to files:
docs/skills.mdx
🪛 LanguageTool
docs/skills.mdx
[uncategorized] ~27-~27: The official name of this software platform is spelled with a capital “H”.
Context: ... (.claude/skills/, .cursor/skills/, .github/skills/, .agents/skills/). It also a...
(GITHUB)
packages/trigger-sdk/skills/trigger-cost-savings/SKILL.md
[uncategorized] ~116-~116: If this is a compound adjective that modifies the following noun, use a hyphen.
Context: ... (see the adjacent package.json). The full cost documentation ships alongside it under ...
(EN_COMPOUND_ADJECTIVE_INTERNAL)
🪛 SkillSpector (2.1.1)
packages/cli-v3/skills/trigger-realtime-and-frontend/SKILL.md
[error] 29: [PE3] Credential Access: Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
Remediation: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
(Privilege Escalation (PE3))
[error] 29: [PE3] Credential Access: Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
Remediation: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
(Privilege Escalation (PE3))
[error] 29: [PE3] Credential Access: Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
Remediation: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
(Privilege Escalation (PE3))
[error] 29: [PE3] Credential Access: Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
Remediation: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
(Privilege Escalation (PE3))
packages/trigger-sdk/skills/trigger-realtime-and-frontend/SKILL.md
[error] 235: [PE3] Credential Access: Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
Remediation: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
(Privilege Escalation (PE3))
[error] 235: [PE3] Credential Access: Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
Remediation: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
(Privilege Escalation (PE3))
[error] 235: [PE3] Credential Access: Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
Remediation: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
(Privilege Escalation (PE3))
🔇 Additional comments (6)
docs/skills.mdx (1)
1-51: LGTM!packages/cli-v3/skills/trigger-realtime-and-frontend/SKILL.md (1)
2-2: LGTM!Also applies to: 13-13, 22-22, 58-58
packages/trigger-sdk/skills/trigger-cost-savings/SKILL.md (2)
25-46: LGTM! Documentation paths, MCP prerequisites, workflow, and principles are clear and complete.
91-116: LGTM! Cost table, principles, and versioning info are well-structured and accurate.packages/trigger-sdk/skills/trigger-realtime-and-frontend/SKILL.md (2)
2-2: LGTM!Also applies to: 13-13, 265-266
30-276: LGTM! Code examples are complete, runnable, and properly tagged withts/tsxlanguage identifiers. Documentation structure and sibling-skill references are correct and consistent.
The getting-started reference in the skills.mdx lightweight-skills paragraph (merged separately) was the last bare skill name; prefix it to trigger-getting-started.
Validate each docs.json nav path before joining (reject `..`/absolute so a fat-fingered entry cannot copy files from outside docs/), and fail the build if zero docs were copied rather than shipping an empty docs bundle.
This comment was marked as resolved.
This comment was marked as resolved.
Sorry, something went wrong.
POSIX normalization misses backslash traversal, so a Windows-style path could escape docs/ on a Windows build. Reject backslashes and both POSIX and Windows absolute forms, keeping the normalized `..` traversal check.
ericallam
deleted the
feature/tri-11011-bundle-all-documentation-docs-in-the-sdk-prefix-skills-with
branch
ericallam
pushed a commit
that referenced
this pull request
Jun 17, 2026
## 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](#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](#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](#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](#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](#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](#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](#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](#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](#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](#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](#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](#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](#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](#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](#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](#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](#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>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Three improvements to the SDK-bundled agent skills (follow-up to the skills installer):
trigger-namespace. The installed skills (authoring-tasks,getting-started, …) had generic names that collide with unrelated skills in a shared agent skills directory. They're now prefixed —trigger-authoring-tasks,trigger-getting-started, etc. — matching the convention the public skills repo already uses.trigger-cost-savingsskill. An MCP-driven cost audit: right-sizes machines, flags missingmaxDuration, spots sequential triggers that could batch, and reviews schedule frequency, usinglist_runs/get_run_detailsfor live analysis.@trigger.dev/sdknow bundles the entire "Documentation" section of the docs (157 pages) instead of a curated 55-page subset, so an agent has the complete, version-pinned reference innode_modules.How the bundling works
scripts/bundleSdkDocs.tsnow readsdocs/docs.json, walks the "Documentation" dropdown, and copies every page under it into the SDK. The set tracks the docs navigation automatically — add a page to the nav and it ships, no skill edits needed. The API reference and Guides & examples dropdowns are intentionally excluded. A skill'ssources:frontmatter is now informational only.The dropped idea of a dedicated
trigger-configskill is replaced by references to the bundled build-extension docs (config/extensions/*) from thetrigger-authoring-tasksconfig section and the chat-agent skills.