Skip to content

ci: Version Packages - #2213

Open
github-actions[bot] wants to merge 1 commit into
mainfrom
changeset-release/main
Open

github-actions[bot] wants to merge 1 commit into
mainfrom
changeset-release/main

Conversation

@github-actions

@github-actions github-actions Bot commented Nov 20, 2026 •

Copy link
Copy Markdown
Contributor

This PR was opened by the Changesets release GitHub action. When you're ready to do a release, you can merge this and the packages will be published to npm automatically. If you're not ready to do a release yet, that's fine, whenever you add more changesets to main, this PR will be updated.

Releases

@tanstack/ai@1.9.0

Minor Changes

  • #2148 f25954a - Add optimization-driven, deterministic tool-result context projection.
    • @tanstack/ai gains a context field (ToolContextPolicy) on tool
      definitions plus the FieldProjection type and its combinators
      (truncateHead, truncateTail, truncateHeadTail, dropWithRef,
      aboveTokens). FieldProjection is branded, so a projection is always built
      with a combinator, never a bare object. The core reads nothing from it (same
      posture as replay); behavior lives in the new package.
    • New package @tanstack/ai-optimize: a chat() middleware that truncates only
      optimized tool-result (and optimize()-declared argument) fields in the
      model projection, never in the canonical messages, event stream, or UI.
      Deterministic strategies only, a run-scoped stash, an injected
      retrieve_context tool, and an optimize() wrapper for foreign/MCP tool
      sets. The combinators are re-exported here too.

Patch Changes

  • #2174 e5bb4d5 - The lazy tool discovery tool no longer says Unknown tool for a tool that the model can already call. Before, it knew only the lazy tools. When a model asked it for an eager tool, or for a tool that a middleware added, it returned Unknown tool, and some models then stopped using that tool. Discovery now returns the definition of each tool offered to the model in that step. An eager tool that a middleware removed still gets Unknown tool. A lazy tool that a middleware removed still returns its definition.

@tanstack/ai-cartesia@0.1.0

Minor Changes

  • #2085 5aa5808 - Add Cartesia text-to-speech and batch transcription adapters.

Patch Changes

@tanstack/ai-computer-sandbox@1.2.0

Minor Changes

  • #1982 d595931 - Add the persist.reconnect option to sandboxComputer(). It keeps the sandbox of each thread and reconnects to the same sandbox later with provider.resume, so a user who comes back to a thread gets the same desktop. A kept sandbox is not destroyed when its thread closes or goes idle.

  • #1982 d595931 - sandboxComputer() takes a persist.snapshots option. The driver saves the files of one folder, like a browser profile, when a thread closes or goes idle. It restores them into the next new sandbox of the thread, so a sign-in survives a sandbox that is gone. A kept sandbox that comes back with an empty disk gets them back too. Saves and restores of one thread run one at a time. This works with every provider. Call saveComputerSnapshot({ sandbox, threadId, snapshots }) to save right away, for example after a sign-in.

    @tanstack/ai-sandbox exports captureSandboxFiles and restoreSandboxFiles, the file capture and restore of portable snapshots.

Patch Changes

  • Updated dependencies [d595931]:
    • @tanstack/ai-sandbox@1.6.0
    • @tanstack/ai-computer-use@1.1.3

@tanstack/ai-harness@0.5.0

Minor Changes

  • #2145 ca20519 - Routed agents now remember their own tool calls, you can pass your own handoff tool, and a harnessAgent can be a root agent.

    • routing.history sets what each model call gets of the routed runs of earlier turns. With 'own' (the default), a routed agent gets its own earlier runs in full, with tool calls and results. It gets the other agents and the main model as labeled text in a user message, for example main:\n.... The main model gets the routed answers the same way, so no model reads the words of another speaker as its own. 'all' gives every speaker every routed run in full. 'text' gives routed runs as text only, as before.
    • routing.handoffTool makes the handoff tool of each speaker. It gets from, targets, allowHuman, and handoff. The tool can have any name and its own fields.
    • A harnessAgent in agents with routing keeps one child session across turns. Each turn sends it what happened in the thread since its last turn. Its model gets the handoff tool, so it can hand back.

    The default history: 'own' changes the messages that routed agents and handoff targets get. A target gets the turns of the main model as labeled text. To keep the earlier messages, and the prompt cache of the provider for a handoff target, set routing: { router, history: 'text' }.

    An app tool with the name of the handoff tool now replaces the harness tool. Before, the turn failed with a duplicate tool error.

    A handoff from the handoff tool of a root agent now adds the note messages to the thread, as a router or code handoff does. Before, the next speaker did not see that the agent handed off. On models that reject a context that ends on an assistant message (new Claude models), the main model failed after a hand-back.

Patch Changes

  • #2175 3e9a35d - A log that gives its ownership back when its sessions have no work now also clears its pending snapshot timer, so the timer no longer stays armed for a snapshot this host cannot write.

  • Updated dependencies [e5bb4d5, f25954a]:

    • @tanstack/ai@1.9.0
    • @tanstack/ai-persistence@1.1.0

@tanstack/ai-optimize@0.1.0

Minor Changes

  • #2148 f25954a - Add optimization-driven, deterministic tool-result context projection.
    • @tanstack/ai gains a context field (ToolContextPolicy) on tool
      definitions plus the FieldProjection type and its combinators
      (truncateHead, truncateTail, truncateHeadTail, dropWithRef,
      aboveTokens). FieldProjection is branded, so a projection is always built
      with a combinator, never a bare object. The core reads nothing from it (same
      posture as replay); behavior lives in the new package.
    • New package @tanstack/ai-optimize: a chat() middleware that truncates only
      optimized tool-result (and optimize()-declared argument) fields in the
      model projection, never in the canonical messages, event stream, or UI.
      Deterministic strategies only, a run-scoped stash, an injected
      retrieve_context tool, and an optimize() wrapper for foreign/MCP tool
      sets. The combinators are re-exported here too.

Patch Changes

@tanstack/ai-sandbox@1.6.0

Minor Changes

  • #1982 d595931 - sandboxComputer() takes a persist.snapshots option. The driver saves the files of one folder, like a browser profile, when a thread closes or goes idle. It restores them into the next new sandbox of the thread, so a sign-in survives a sandbox that is gone. A kept sandbox that comes back with an empty disk gets them back too. Saves and restores of one thread run one at a time. This works with every provider. Call saveComputerSnapshot({ sandbox, threadId, snapshots }) to save right away, for example after a sign-in.

    @tanstack/ai-sandbox exports captureSandboxFiles and restoreSandboxFiles, the file capture and restore of portable snapshots.

Patch Changes

  • Updated dependencies [3e9a35d, e5bb4d5, f25954a, ca20519]:
    • @tanstack/ai-harness@0.5.0
    • @tanstack/ai@1.9.0
    • @tanstack/ai-skills@1.0.4
    • @tanstack/ai-persistence@1.1.0

@tanstack/ai-acp@1.0.4

Patch Changes

@tanstack/ai-code-mode@1.1.3

Patch Changes

@tanstack/ai-computer-use@1.1.3

Patch Changes

@tanstack/ai-harness-cli@0.1.4

Patch Changes

@tanstack/ai-mcp@1.3.2

Patch Changes

  • #2150 1a23e34 - createMCPEventWebhook no longer requires the webhook-id header to equal the event's eventId. SEP-3415 says webhook-id is a per-message id that must not be derived from eventId, so the receiver returned 400 for every event from a server that follows the spec. It now accepts both a per-message id and the older webhook-id = eventId form. onEvent still gets the header as messageId, so keep deduplicating on (subscription.id, messageId).

  • Updated dependencies [3e9a35d, e5bb4d5, f25954a, ca20519]:

    • @tanstack/ai-harness@0.5.0
    • @tanstack/ai@1.9.0

@tanstack/ai-openai@1.2.1

Patch Changes

  • #2208 b8a0ce6 - openaiImage() accepts gpt-image-2.6-flare and gpt-image-2.6-sunburst. Both take sizes 1024x1024, 1536x1024, 1024x1536 and auto, and quality takes low, medium, high, xhigh, max and auto. Before, both ids threw Unknown image model before any request was sent.

  • Updated dependencies [e5bb4d5, f25954a]:

    • @tanstack/ai@1.9.0
    • @tanstack/openai-base@1.1.0

@tanstack/ai-sandbox-cloudflare@1.1.1

Patch Changes

  • #1982 d595931 - Run each exec and spawn command in a subshell. Cloudflare runs every command in one shared shell session, so a command that called exit ended the session and every later command failed. This broke the @tanstack/ai-computer-sandbox driver on Cloudflare.

  • Updated dependencies [d595931, e5bb4d5, dfbacd1, f25954a]:

    • @tanstack/ai-sandbox@1.6.0
    • @tanstack/ai@1.9.0
    • @tanstack/ai-sandbox-local-process@1.0.1

@tanstack/ai-sandbox-docker@1.1.1

Patch Changes

  • #1982 d595931 - publishPorts now publishes each port on 127.0.0.1 only, and ports.connect returns a http://127.0.0.1:<port> address. Before, Docker published the ports on every network interface, so other computers on the network could connect.

  • Updated dependencies [d595931]:

    • @tanstack/ai-sandbox@1.6.0

@tanstack/ai-sandbox-local-process@1.0.1

Patch Changes

  • #2162 dfbacd1 - exec() no longer corrupts multi-byte UTF-8 characters in stdout and stderr. A character that a pipe split across two reads used to decode as U+FFFD. Output is now decoded across chunks, like spawn() already does.

  • Updated dependencies [d595931]:

    • @tanstack/ai-sandbox@1.6.0

@tanstack/ai-skills@1.0.4

Patch Changes

@tanstack/ai-optimize-evals@0.0.1

Patch Changes

  • Updated dependencies [e5bb4d5, b8a0ce6, f25954a]:
    • @tanstack/ai@1.9.0
    • @tanstack/ai-openai@1.2.1
    • @tanstack/ai-optimize@0.1.0
    • @tanstack/ai-code-mode@1.1.3
    • @tanstack/ai-anthropic@1.2.1
    • @tanstack/ai-gemini@1.3.0

@coderabbitai

coderabbitai Bot commented Nov 20, 2026 •

Copy link
Copy Markdown
Contributor

Important

Review skipped

Bot user detected.

To trigger a single review, invoke the @coderabbitai review command.

Run configuration

  • Source mode: Auto
  • Repository: TanStack/ai
  • Branch: main
  • File: .coderabbit.yaml
  • Commit: ca20519
  • Layers: Repository YAML
  • Review profile: CHILL
  • Plan: Advanced
  • Run ID: de2c8f32-fe35-4877-acdb-d2eb48509310

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

Use the checkbox below for a quick retry:

  • Trigger review
  • Autofix · Keep fixing CodeRabbit findings and required CI, and resolving merge conflicts

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.

Share

@github-actions
github-actions Bot force-pushed the changeset-release/main branch 4 times, most recently from 6145e33 to aece3d6 Compare November 21, 2026 05:08
@github-actions
github-actions Bot force-pushed the changeset-release/main branch from aece3d6 to b0bbe24 Compare November 21, 2026 06:43
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

0 participants