ci: Version Packages - #1514
ci: Version Packages#1514
Conversation
|
Important Review skippedBot user detected. To trigger a single review, invoke the ⚙️ Run configurationConfiguration used: Repository: TanStack/ai/.coderabbit.yaml Review profile: CHILL Plan: Advanced Run ID: You can disable this status message by setting the Use the checkbox below for a quick retry:
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 |
db116a5 to
c91ac8e
Compare
c91ac8e to
c6d53e4
Compare
|
View your CI Pipeline Execution ↗ for commit c6d53e4
☁️ Nx Cloud last updated this comment at |
@tanstack/ai
@tanstack/ai-acp
@tanstack/ai-angular
@tanstack/ai-anthropic
@tanstack/ai-bedrock
@tanstack/ai-byteplus
@tanstack/ai-claude-code
@tanstack/ai-client
@tanstack/ai-cloudflare
@tanstack/ai-code-mode
@tanstack/ai-code-mode-snippets
@tanstack/ai-codex
@tanstack/ai-cohere
@tanstack/ai-compaction
@tanstack/ai-devtools-core
@tanstack/ai-durable-stream
@tanstack/ai-elevenlabs
@tanstack/ai-event-client
@tanstack/ai-fal
@tanstack/ai-gemini
@tanstack/ai-grok
@tanstack/ai-grok-build
@tanstack/ai-groq
@tanstack/ai-isolate-cloudflare
@tanstack/ai-isolate-daytona
@tanstack/ai-isolate-node
@tanstack/ai-isolate-quickjs
@tanstack/ai-isolate-quickjs-bun
@tanstack/ai-llmgateway
@tanstack/ai-lovable
@tanstack/ai-mcp
@tanstack/ai-memory
@tanstack/ai-mistral
@tanstack/ai-octane
@tanstack/ai-ollama
@tanstack/ai-openai
@tanstack/ai-opencode
@tanstack/ai-openrouter
@tanstack/ai-perplexity
@tanstack/ai-persistence
@tanstack/ai-preact
@tanstack/ai-react
@tanstack/ai-react-ui
@tanstack/ai-reactor
@tanstack/ai-remix
@tanstack/ai-sandbox
@tanstack/ai-sandbox-blaxel
@tanstack/ai-sandbox-boxd
@tanstack/ai-sandbox-cloudflare
@tanstack/ai-sandbox-daytona
@tanstack/ai-sandbox-docker
@tanstack/ai-sandbox-e2b
@tanstack/ai-sandbox-local-process
@tanstack/ai-sandbox-sprites
@tanstack/ai-sandbox-upstash-box
@tanstack/ai-sandbox-vercel
@tanstack/ai-skills
@tanstack/ai-solid
@tanstack/ai-solid-ui
@tanstack/ai-svelte
@tanstack/ai-typesafe
@tanstack/ai-utils
@tanstack/ai-vercel-gateway
@tanstack/ai-vertex
@tanstack/ai-vue
@tanstack/ai-vue-ui
@tanstack/ai-worldlabs
@tanstack/openai-base
@tanstack/preact-ai-devtools
@tanstack/react-ai-devtools
@tanstack/solid-ai-devtools
@tanstack/svelte-ai-devtools
commit: |
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@0.63.0
Minor Changes
#1509
37b2826- Add an optionalinputSchematodefineAgent. The agent's tool shows the schema to the model, so the parent model writes the child's input, such as a short brief.rungets the checked input as a typedctx.input. A bad input goes back to the model as a tool error, and the child does not start.inputSchemaneeds tool mode:chat()throws whensubagents.routermeets an agent that has one. Agents withoutinputSchemado not change.#1401
c5c1996- Preserve structured outcomes for cancelled and denied tool results. Atool-resultpart now carriesoutcome: 'cancelled' | 'denied'(newToolResultOutcometype andisToolResultOutcomeguard) across tool execution, streaming, persistence, and UI restoration, so callers can tell a user or middleware decision from an ordinary tool failure without matching error text.statestays'error'for these results. The@tanstack/ai-clientToolResultParttype (used byuseChatmessages) now has the sameoutcomefield.#1452
0eb8f0b-@tanstack/ai-mcpcan create an MCP server withcreateMCPServerandserveMCPStdio. The client package moves from@modelcontextprotocol/sdkto@modelcontextprotocol/clientand@modelcontextprotocol/server. The client tries spec 2026-07-28 first, then the 2025 handshake. When an MCP server asks for input,chat()pauses with anmcp_inputinterrupt. Answer it withresolveInterruptorcancel(), and the tool runs again with the answer inctx.inputResponse. A tool can setexecution: 'task'for a spec 2025 task handle. A tool readsrequestInputandsampleonctx.context, typed byMCPToolContext. The serverauthoption takes the MCP SDKOAuthTokenVerifiershape.jwtVerifierandintrospectionVerifiercover JWT and opaque tokens, and a tool reads the token asctx.context.authInfo.createMCPClient<typeof server>({ transport })types a remote client from acreateMCPServerserver, andcreateMCPClient({ server })calls a server in the same process.server.handle(request, { authInfo, context })takes a token your own middleware verified and values forctx.context, typed withMCPToolContext<{ db: Db }>. A tool'smetadata.titleandmetadata.annotationsreach the host as the MCP title and annotations. A tool with nooutputSchemacan return aCallToolResultas is.sessions: 'reject'turns spec 2025 sessions off for hosts with many instances.Patch Changes
#1233
8e8ee26- Preserve failed client tool results across native interrupt resumes and await asynchronous client output validation#1512
3e30cde- Keep a tool-call part atcompletewhen its result arrives before the stream ends. If a stream had noTOOL_CALL_END, the end-of-stream safety net set a finished tool-call part back toinput-complete. The final state then depended on async timing.#1528
f44b6b2-otelMiddleware({ captureContent: true })now records content on media spans (generateImage,generateVideo,generateAudio,generateSpeech,generateTranscription, and the others).gen_ai.input.messagesgets the prompt and input media.gen_ai.output.messagesgets the output URLs or the transcript text. Inline data stays a placeholder.redactandmaxContentLengthapply to each text part.#1527
d632d41-otelMiddlewarewithcaptureContent: truenow keeps multimodal parts structured ingen_ai.input.messages(OTel GenAI part shapes). URL media becomes auripart and provider file handles become afilepart, so traces show what the model looked at. Inline base64 data still records a[image]-style placeholder.@tanstack/ai-client@0.36.0
Minor Changes
c5c1996- Preserve structured outcomes for cancelled and denied tool results. Atool-resultpart now carriesoutcome: 'cancelled' | 'denied'(newToolResultOutcometype andisToolResultOutcomeguard) across tool execution, streaming, persistence, and UI restoration, so callers can tell a user or middleware decision from an ordinary tool failure without matching error text.statestays'error'for these results. The@tanstack/ai-clientToolResultParttype (used byuseChatmessages) now has the sameoutcomefield.Patch Changes
#1233
8e8ee26- Preserve failed client tool results across native interrupt resumes and await asynchronous client output validationUpdated dependencies [
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,f44b6b2,d632d41]:@tanstack/ai-mcp@0.6.0
Minor Changes
0eb8f0b-@tanstack/ai-mcpcan create an MCP server withcreateMCPServerandserveMCPStdio. The client package moves from@modelcontextprotocol/sdkto@modelcontextprotocol/clientand@modelcontextprotocol/server. The client tries spec 2026-07-28 first, then the 2025 handshake. When an MCP server asks for input,chat()pauses with anmcp_inputinterrupt. Answer it withresolveInterruptorcancel(), and the tool runs again with the answer inctx.inputResponse. A tool can setexecution: 'task'for a spec 2025 task handle. A tool readsrequestInputandsampleonctx.context, typed byMCPToolContext. The serverauthoption takes the MCP SDKOAuthTokenVerifiershape.jwtVerifierandintrospectionVerifiercover JWT and opaque tokens, and a tool reads the token asctx.context.authInfo.createMCPClient<typeof server>({ transport })types a remote client from acreateMCPServerserver, andcreateMCPClient({ server })calls a server in the same process.server.handle(request, { authInfo, context })takes a token your own middleware verified and values forctx.context, typed withMCPToolContext<{ db: Db }>. A tool'smetadata.titleandmetadata.annotationsreach the host as the MCP title and annotations. A tool with nooutputSchemacan return aCallToolResultas is.sessions: 'reject'turns spec 2025 sessions off for hosts with many instances.Patch Changes
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,f44b6b2,d632d41]:@tanstack/ai-acp@0.3.19
Patch Changes
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,f44b6b2,d632d41]:@tanstack/ai-angular@0.12.3
Patch Changes
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,f44b6b2,d632d41]:@tanstack/ai-anthropic@0.19.3
Patch Changes
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,f44b6b2,d632d41]:@tanstack/ai-bedrock@0.4.1
Patch Changes
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,bb3bf30,f44b6b2,d632d41]:@tanstack/ai-byteplus@0.5.1
Patch Changes
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,bb3bf30,f44b6b2,d632d41]:@tanstack/ai-claude-code@0.7.1
Patch Changes
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,f44b6b2,d632d41]:@tanstack/ai-cloudflare@0.2.1
Patch Changes
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,bb3bf30,f44b6b2,d632d41]:@tanstack/ai-code-mode@0.4.18
Patch Changes
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,f44b6b2,d632d41]:@tanstack/ai-code-mode-snippets@0.4.18
Patch Changes
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,f44b6b2,d632d41]:@tanstack/ai-codex@0.5.14
Patch Changes
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,f44b6b2,d632d41]:@tanstack/ai-cohere@0.4.11
Patch Changes
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,f44b6b2,d632d41]:@tanstack/ai-compaction@0.1.11
Patch Changes
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,f44b6b2,d632d41]:@tanstack/ai-devtools-core@0.5.22
Patch Changes
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,f44b6b2,d632d41]:@tanstack/ai-durable-stream@0.1.21
Patch Changes
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,f44b6b2,d632d41]:@tanstack/ai-elevenlabs@0.6.6
Patch Changes
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,f44b6b2,d632d41]:@tanstack/ai-fal@0.15.3
Patch Changes
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,f44b6b2,d632d41]:@tanstack/ai-gemini@0.34.1
Patch Changes
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,f44b6b2,d632d41]:@tanstack/ai-grok@0.20.3
Patch Changes
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,bb3bf30,f44b6b2,d632d41]:@tanstack/ai-grok-build@0.5.14
Patch Changes
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,f44b6b2,d632d41]:@tanstack/ai-groq@0.8.1
Patch Changes
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,bb3bf30,f44b6b2,d632d41]:@tanstack/ai-llmgateway@0.2.1
Patch Changes
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,bb3bf30,f44b6b2,d632d41]:@tanstack/ai-lovable@0.3.1
Patch Changes
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,bb3bf30,f44b6b2,d632d41]:@tanstack/ai-memory@0.2.8
Patch Changes
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,f44b6b2,d632d41]:@tanstack/ai-mistral@0.6.12
Patch Changes
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,f44b6b2,d632d41]:@tanstack/ai-octane@0.6.3
Patch Changes
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,f44b6b2,d632d41]:@tanstack/ai-ollama@0.11.11
Patch Changes
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,f44b6b2,d632d41]:@tanstack/ai-openai@0.25.1
Patch Changes
#1532
6b8a1c0- List the Responses provider tools ongpt-6-astra,gpt-6-sol, andgpt-6-luna. The model sync added them withtools: [], sowebSearchTool,imageGenerationTool, and the other provider tools were type errors on GPT-6. They now acceptweb_search,file_search,image_generation,code_interpreter,mcp,computer_use,shell, andapply_patch, as listed on OpenAI's model pages.#1529
24baf35-openaiImage()acceptsgpt-image-2.5-flareandgpt-image-2.5-sunburst. Both take sizes1024x1024,1536x1024,1024x1536andauto, andqualityaddsxhighandmaxtolow,medium,highandauto. Before, both ids threwUnknown image modelbefore any request was sent.Updated dependencies [
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,bb3bf30,f44b6b2,d632d41]:@tanstack/ai-opencode@0.4.14
Patch Changes
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,f44b6b2,d632d41]:@tanstack/ai-openrouter@0.20.1
Patch Changes
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,f44b6b2,d632d41]:@tanstack/ai-perplexity@0.2.19
Patch Changes
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,f44b6b2,d632d41]:@tanstack/ai-persistence@0.7.1
Patch Changes
#1233
8e8ee26- Preserve failed client tool results across native interrupt resumes and await asynchronous client output validationUpdated dependencies [
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,f44b6b2,d632d41]:@tanstack/ai-preact@0.19.3
Patch Changes
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,f44b6b2,d632d41]:@tanstack/ai-react@0.29.3
Patch Changes
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,f44b6b2,d632d41]:@tanstack/ai-reactor@0.2.9
Patch Changes
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,f44b6b2,d632d41]:@tanstack/ai-remix@0.5.3
Patch Changes
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,f44b6b2,d632d41]:@tanstack/ai-sandbox@0.5.17
Patch Changes
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,f44b6b2,d632d41]:@tanstack/ai-sandbox-cloudflare@0.4.9
Patch Changes
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,f44b6b2,d632d41]:@tanstack/ai-skills@0.1.13
Patch Changes
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,f44b6b2,d632d41]:@tanstack/ai-solid@0.25.3
Patch Changes
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,f44b6b2,d632d41]:@tanstack/ai-svelte@0.24.3
Patch Changes
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,f44b6b2,d632d41]:@tanstack/ai-typesafe@0.1.6
Patch Changes
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,f44b6b2,d632d41]:@tanstack/ai-vercel-gateway@0.3.1
Patch Changes
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,bb3bf30,f44b6b2,d632d41]:@tanstack/ai-vertex@0.2.21
Patch Changes
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,f44b6b2,d632d41]:@tanstack/ai-vue@0.25.3
Patch Changes
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,f44b6b2,d632d41]:@tanstack/ai-worldlabs@0.1.2
Patch Changes
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,f44b6b2,d632d41]:@tanstack/openai-base@0.12.1
Patch Changes
#1530
bb3bf30- Chat Completions usage now reads Moonshot (Kimi) prompt cache counts.prompt_tokens_details.cache_write_tokensmaps topromptTokensDetails.cacheWriteTokens, and acached_tokensfield at the root ofusagemaps topromptTokensDetails.cachedTokenswhenprompt_tokens_details.cached_tokensis absent.Updated dependencies [
37b2826,8e8ee26,c5c1996,3e30cde,0eb8f0b,f44b6b2,d632d41]:ag-ui@0.0.30
Patch Changes
8e8ee26,c5c1996]: