Skip to content
Source
Sign inSign up
TanStack/ai

feat: streaming structured output across openai/openrouter/grok/groq + summarize fix #527

Mergedtombeckenhammerged 33 commits intomain fromrefs/pull/527/headmerged by AlemTuzlak View on GitHub

tombeckenhamcommented

🎯 Changes

Started as openrouter-only (#526) and grew into a multi-package effort: typed streaming structured output across the four OpenAI-compatible providers, a Chat Completions sibling for OpenAI, a fix for streaming summarize, the decoupling of @tanstack/ai-openrouter from the shared OpenAI base, and a hand-testable example to exercise the whole surface.

Core — @tanstack/ai

  • New chat({ outputSchema, stream: true }) overload returning StructuredOutputStream<InferSchemaType<TSchema>>. Yields raw JSON deltas plus a terminal CUSTOM { name: 'structured-output.complete', value: { object, raw, reasoning? } } event.
  • StructuredOutputStream<T> is a discriminated union over three tagged CUSTOM variants — structured-output.complete<T>, approval-requested, and tool-input-available (new ApprovalRequestedEvent / ToolInputAvailableEvent interfaces exported from @tanstack/ai). Consumers narrow with a plain chunk.type === 'CUSTOM' && chunk.name === '<literal>' and get a fully-typed chunk.value — no helper or cast required. The bare CustomEvent (value: any) is excluded from the union on purpose to keep the narrow from collapsing to any; user-emitted events via the emitCustomEvent context API still flow at runtime as a documented residual gap.
  • Activity-layer hardening: always-finalise after the stream loop (no silent hangs on missing finishReason), typed RUN_ERROR on empty content, mid-stream provider errors terminate cleanly, schema-validation failures carry runId / model / timestamp.
  • fallbackStructuredOutputStream in the activity layer is the single source of truth for adapters that don't implement structuredOutputStream natively; BaseTextAdapter no longer ships a default.
  • ChatStreamSummarizeAdapter.summarizeStream accumulates summary text and emits a terminal CUSTOM { name: 'generation:result' } event before the final RUN_FINISHED. Fixes useSummarize never populating result over streaming connections (the client only sets result on that specific CUSTOM event).

Base — @tanstack/openai-base

  • Renamed from @tanstack/ai-openai-compatible; the old name remains published for pinned lockfiles but receives no further updates.
  • Centralised structuredOutputStream on OpenAIBaseChatCompletionsTextAdapter (uses response_format: { type: 'json_schema', strict: true } + stream: true) and OpenAIBaseResponsesTextAdapter (uses text.format: { type: 'json_schema', strict: true } + stream: true). Both call the OpenAI SDK directly post-#543's "adopt openai SDK" refactor.
  • Cross-SDK abort detection hook (isAbortError) so subclasses can map provider-specific abort errors to code: 'aborted' without owning the rest of the finalisation path.
  • Per-chunk logger.provider(...) debug logging now fires inside structuredOutputStream loops (mirroring the existing chatStream pattern) so debug mode gives end-to-end chunk introspection for the structured-output path.

Provider adapters

AdapterAPIReasoning surface
@tanstack/ai-openai openaiTextResponsesresponse.reasoning_text.delta + response.reasoning_summary_text.delta (requires reasoning.summary: 'auto')
@tanstack/ai-openai openaiChatCompletions (new)Chat Completionsreasoning emitted silently — Chat Completions has no reasoning.summary opt-in
@tanstack/ai-grok grokTextChat Completionsdelta.reasoning_content (DeepSeek convention; not typed by OpenAI SDK)
@tanstack/ai-groq groqTextChat Completionsdelta.reasoning (requires reasoning_format: 'parsed'; not typed by groq-sdk)
@tanstack/ai-openrouter openRouterTextChat Completionsdelta.reasoningDetails (camelCase)
@tanstack/ai-openrouter openRouterResponsesText (beta)Responses (beta)response.reasoning_text.delta + response.reasoning_summary_text.delta via normalizeStreamEvent

All six emit the contractual REASONING_* lifecycle (REASONING_START → REASONING_MESSAGE_START → REASONING_MESSAGE_CONTENT deltas → REASONING_MESSAGE_END → REASONING_END) and close it before TEXT_MESSAGE_START. Accumulated reasoning is also surfaced on structured-output.complete.value.reasoning for consumers that only subscribe to the terminal event. OpenRouter SDK's proprietary RequestAbortedError is mapped (alongside DOM AbortError) to code: 'aborted' in the two openrouter adapters.

@tanstack/ai-openai also exports a new OpenAIChatCompletionsTextAdapter / openaiChatCompletions / createOpenaiChatCompletions factory — a sibling to the existing Responses adapter for callers who want the older /v1/chat/completions wire format against the OpenAI SDK.

@tanstack/ai-openrouter is now decoupled from the shared OpenAI base and reads @openrouter/sdk's camelCase types natively (no more snake_case ↔ camelCase round-trips). It extends BaseTextAdapter directly; @tanstack/openai-base and openai are removed from its deps. Public OpenRouter API is unchanged.

ts-react-chat example

/generations/structured-output is now a 6-way demo of the entire feature surface:

  • Provider/API matrix: OpenAI (Responses), OpenAI (Chat Completions), Grok, Groq, OpenRouter (Chat Completions), OpenRouter (Responses beta) — each with its own model dropdown.
  • Stream toggle: off uses non-streaming chat({ outputSchema }), on uses structuredOutputStream.
  • Progressive UI rendering via parsePartialJSON — title, summary, recommendation cards (brand → name → type → price → reason), and next steps fill in field-by-field as JSON streams in, snapping to the validated payload on the terminal event.
  • Live "Thinking" strip rendering the latest reasoning sentence from REASONING_MESSAGE_CONTENT deltas.
  • Per-provider reasoning opt-ins via modelOptions (gpt-5.x/o-series → reasoning.summary: 'auto', groq gpt-oss/qwen3/kimi-k2 → reasoning_format: 'parsed', openrouter → reasoning.effort: 'medium').
  • Sidebar label cleaned up: "Structured Output (OpenRouter)" → "Structured Output" (it now spans every provider).

/generations/summarize overhauled too:

  • New model picker (gpt-4o-mini through gpt-5.2) plumbed through both API route and server-fn paths.
  • Streaming and Server-Fn modes now visibly stream — wired an onChunk handler that accumulates TEXT_MESSAGE_CONTENT deltas into local state so the summary renders token-by-token, with a "streaming…" indicator next to the heading.
  • Dropped the hard-coded maxLength: 200. On Responses-API reasoning models maxLength maps to max_output_tokens which covers reasoning + visible output combined; a 200-token cap consumed the whole budget on hidden reasoning, returning truncated responses with no summary. The concise / bullet-points / paragraph prompt instruction is enough to drive length.

E2E

testing/e2e/src/lib/feature-support.ts — structured-output-stream set expanded from ['openrouter'] to all four providers. The parameterised spec in testing/e2e/tests/structured-output-stream.spec.ts (happy path + abort) now runs across each.

✅ Checklist

  • I have followed the steps in the Contributing guide.
  • I have tested this code locally with pnpm run test:pr.

Verified during development: pnpm test:lib, pnpm test:types, pnpm test:eslint, pnpm test:build, pnpm test:knip across affected packages. Hand-tested in examples/ts-react-chat against each provider for both streaming and non-streaming. E2E (pnpm --filter @tanstack/ai-e2e test:e2e -- --grep structured-output-stream) needs to run on a host where port 4010 is free.

🚀 Release Impact

  • This change affects published code, and I have generated a changeset.
  • This change is docs/CI/dev-only (no release).

One consolidated changeset (.changeset/streaming-structured-output.md) covers the union of version bumps: minor on @tanstack/ai, @tanstack/openai-base, @tanstack/ai-openai, @tanstack/ai-grok, @tanstack/ai-groq, @tanstack/ai-openrouter; patch on @tanstack/ai-anthropic, @tanstack/ai-gemini, @tanstack/ai-ollama. The body retains the per-area sections from the originals (core, openai-base, provider adapters, openrouter decoupling, summarize subsystem) and adds the tagged-CustomEvent type design.

    1. Note

      Reviews paused

      It 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 reviews.auto_review.auto_pause_after_reviewed_commits setting.

      Use the following commands to manage reviews:

      • @coderabbitai resume to resume automatic reviews.
      • @coderabbitai review to trigger a single review.

      Use the checkboxes below for quick actions:

      • ▶️ Resume reviews
      • 🔍 Trigger review
      📝 Walkthrough

      Walkthrough

      chat({ outputSchema, stream: true }) now produces an AsyncIterable that emits JSON delta chunks plus a terminal CUSTOM event structured-output.complete with { object, raw, reasoning? }. Adapters may implement structuredOutputStream; BaseTextAdapter provides a fallback wrapping non-streaming structured output. Type and runtime plumbing added to route/validate streams.

      Changes

      Streaming Structured Output (single cohesive change DAG)

      Layer / File(s)Summary
      Type Definitions
      packages/typescript/ai/src/types.ts
      Adds StructuredOutputCompleteEvent<T>, StructuredOutputStream<T>, and isStructuredOutputCompleteEvent() to represent/identify the terminal structured-output completion event.
      Adapter Interface
      packages/typescript/ai/src/activities/chat/adapter.ts
      Adds optional structuredOutputStream(options) to TextAdapter, documenting expected AG-UI lifecycle emissions and the final CUSTOM('structured-output.complete') payload.
      Chat Types
      packages/typescript/ai/src/activities/chat/index.ts (type layer)
      Changes TStream defaults and TextActivityResult so streaming structured output is selected only when stream === true via [TStream] extends [true].
      Chat Runtime
      packages/typescript/ai/src/activities/chat/index.ts (runtime layer)
      Adds explicit outputSchema && stream === true branch, implements runStreamingStructuredOutput/runStreamingStructuredOutputImpl, wires abortController into adapter requests, and provides fallbackStructuredOutputStream that synthesizes lifecycle events from non-streaming adapters.
      Adapter Implementations
      packages/typescript/ai-openai/..., packages/typescript/ai-grok/..., packages/typescript/ai-groq/..., packages/typescript/ai-openrouter/...
      Each adapter adds structuredOutputStream async generator making a single stream: true JSON-schema request (strict), strips tools, emits AG-UI lifecycle events and TEXT_MESSAGE_CONTENT deltas, accumulates raw JSON, parses/transforms (null→undefined), emits CUSTOM('structured-output.complete') with { object, raw, reasoning? }, and emits RUN_FINISHED or RUN_ERROR for parse/empty/abort/fatal cases. OpenRouter also adjusts lifecycle finalization flags.
      Adapter Unit Tests
      packages/typescript/ai-*/tests/*
      Adds suites asserting single-request params (json_schema/strict), tools stripped, AG-UI event ordering, accumulation/parsing into CUSTOM, parse/empty/abort/failure handling, reasoning propagation, and null→undefined transform behavior.
      Core & Adapter Changesets
      .changeset/streaming-structured-output-*.md
      Adds changeset entries documenting streaming structured-output behavior across core and provider adapters.
      E2E: Features & Fixtures
      testing/e2e/src/lib/*, testing/e2e/src/lib/types.ts, testing/e2e/fixtures/structured-output-stream/*.json
      Adds 'structured-output-stream' feature, provider matrix entries, feature config, fixtures basic.json and abort.json, and README updates for fixture prefixes.
      E2E: UI & Routes
      testing/e2e/src/components/ChatUI.tsx, testing/e2e/src/routes/$provider/$feature.tsx, testing/e2e/src/routes/api.chat.ts
      Exposes hidden test attributes (data-structured-output, data-count), wires onCustomEvent/onChunk to capture structured-output.complete and delta counts, and conditions /api/chat to call chat() with outputSchema + stream: true for the feature.
      E2E Tests
      testing/e2e/tests/structured-output-stream.spec.ts
      Adds Playwright tests verifying streamed JSON delta accumulation, final structured-output.complete payload delivery, multiple deltas (>1), and mid-stream abort preventing completion.
      Examples: Structured Output UI
      examples/ts-react-chat/src/routes/*.ts*
      Adds multi-provider adapter selection, streaming SSE handling that accumulates TEXT_MESSAGE_CONTENT deltas and reasoning, progressive parse/update of partial JSON, delta counting and abort control, and UI updates for streaming state and partial/result rendering.

      Sequence Diagram

      sequenceDiagram
          participant Client
          participant ChatRoute as /api/chat
          participant ChatFn as chat()
          participant Engine as TextEngine
          participant Adapter as TextAdapter
          participant UI as ChatUI
      
          Client->>ChatRoute: POST structured-stream request
          ChatRoute->>ChatFn: chat({ outputSchema, stream: true, ... })
          ChatFn->>ChatFn: branch on outputSchema && stream === true
          ChatFn->>Engine: convert messages / run agent loop (if tools)
          Engine->>Adapter: adapter.structuredOutputStream(request)
          loop streaming
              Adapter-->>ChatFn: TEXT_MESSAGE_CONTENT chunk
              ChatFn-->>ChatRoute: forward chunk via SSE
              ChatRoute-->>UI: SSE chunk
              UI->>UI: accumulate delta
          end
          Adapter->>Adapter: parse accumulated JSON & validate schema
          Adapter-->>ChatFn: CUSTOM(structured-output.complete { object, raw, reasoning? })
          ChatFn-->>ChatRoute: forward CUSTOM event
          ChatRoute-->>UI: SSE CUSTOM event
          UI->>UI: display structured object

      Estimated code review effort

      🎯 4 (Complex) | ⏱️ ~50 minutes

      "I nibble deltas one by one, so neat, Streaming JSON rhythms, tiny feet, Parsing, validating, then complete—hooray! 🐰 A structured carrot arrives today, I hop, I stash the final JSON treat."

      🚥 Pre-merge checks | ✅ 4 | ❌ 1

      ❌ Failed checks (1 warning)

      Check nameStatusExplanationResolution
      Docstring Coverage⚠️ WarningDocstring coverage is 63.64% which is insufficient. The required threshold is 80.00%.Write docstrings for the functions missing them to satisfy the coverage threshold.
      ✅ Passed checks (4 passed)
      Check nameStatusExplanation
      Title check✅ PassedThe title 'feat: streaming structured output (chat outputSchema + stream:true)' clearly and concisely summarizes the main feature addition: streaming structured output with chat when outputSchema and stream are both true.
      Description check✅ PassedThe PR description is comprehensive and well-structured, covering changes, test results, and implementation details across all affected packages and providers.
      Linked Issues check✅ PassedCheck skipped because no linked issues were found for this pull request.
      Out of Scope Changes check✅ PassedCheck skipped because no linked issues were found for this pull request.
      ✏️ Tip: You can configure your own custom pre-merge checks in the settings.
      ✨ Finishing Touches
      🧪 Generate unit tests (beta)
      • Create PR with unit tests
      • Commit unit tests in branch `526-featai-openrouter-support-streaming-structured-output-response_format-json_schema-with-stream-true`

      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
      Comment `@coderabbitai help` to get the list of available commands and usage tips.
    2. 🚀 Changeset Version Preview

      14 package(s) bumped directly, 20 bumped as dependents.

      🟥 Major bumps

      PackageVersionReason
      @tanstack/ai-anthropic0.8.6 → 1.0.0Changeset
      @tanstack/ai-fal0.7.3 → 1.0.0Changeset
      @tanstack/ai-gemini0.10.3 → 1.0.0Changeset
      @tanstack/ai-grok0.7.3 → 1.0.0Changeset
      @tanstack/ai-groq0.1.11 → 1.0.0Changeset
      @tanstack/ai-ollama0.6.13 → 1.0.0Changeset
      @tanstack/ai-openai0.8.5 → 1.0.0Changeset
      @tanstack/ai-openrouter0.8.5 → 1.0.0Changeset
      @tanstack/ai-react0.8.2 → 1.0.0Changeset
      @tanstack/ai-solid0.7.2 → 1.0.0Changeset
      @tanstack/ai-svelte0.7.2 → 1.0.0Changeset
      @tanstack/ai-vue0.7.2 → 1.0.0Changeset
      @tanstack/openai-base0.2.1 → 1.0.0Changeset
      @tanstack/ai-code-mode0.1.10 → 1.0.0Dependent
      @tanstack/ai-code-mode-skills0.1.10 → 1.0.0Dependent
      @tanstack/ai-elevenlabs0.2.3 → 1.0.0Dependent
      @tanstack/ai-event-client0.3.0 → 1.0.0Dependent
      @tanstack/ai-isolate-node0.1.10 → 1.0.0Dependent
      @tanstack/ai-isolate-quickjs0.1.10 → 1.0.0Dependent
      @tanstack/ai-preact0.6.22 → 1.0.0Dependent
      @tanstack/ai-react-ui0.6.3 → 1.0.0Dependent
      @tanstack/ai-solid-ui0.6.3 → 1.0.0Dependent

      🟨 Minor bumps

      PackageVersionReason
      @tanstack/ai0.16.0 → 0.17.0Changeset

      🟩 Patch bumps

      PackageVersionReason
      @tanstack/ai-client0.9.1 → 0.9.2Dependent
      @tanstack/ai-code-mode-models-eval0.0.15 → 0.0.16Dependent
      @tanstack/ai-devtools-core0.3.27 → 0.3.28Dependent
      @tanstack/ai-isolate-cloudflare0.2.1 → 0.2.2Dependent
      @tanstack/ai-vue-ui0.1.33 → 0.1.34Dependent
      @tanstack/preact-ai-devtools0.1.31 → 0.1.32Dependent
      @tanstack/react-ai-devtools0.2.31 → 0.2.32Dependent
      @tanstack/solid-ai-devtools0.2.31 → 0.2.32Dependent
      ts-svelte-chat0.1.41 → 0.1.42Dependent
      ts-vue-chat0.1.41 → 0.1.42Dependent
      vanilla-chat0.0.37 → 0.0.38Dependent
    3. View your CI Pipeline Execution ↗ for commit 603cd6bc1c7dea1dd4e6969e165ebf48091e9961

      CommandStatusDurationResult
      nx run-many --targets=build --exclude=examples/**✅ Succeeded59sView ↗

      ☁️ Nx Cloud last updated this comment at 2026-05-14 13:34:23 UTC

    4. Open in StackBlitz

      @tanstack/ai

      npm i https://pkg.pr.new/@tanstack/ai@527

      @tanstack/ai-anthropic

      npm i https://pkg.pr.new/@tanstack/ai-anthropic@527

      @tanstack/ai-client

      npm i https://pkg.pr.new/@tanstack/ai-client@527

      @tanstack/ai-code-mode

      npm i https://pkg.pr.new/@tanstack/ai-code-mode@527

      @tanstack/ai-code-mode-skills

      npm i https://pkg.pr.new/@tanstack/ai-code-mode-skills@527

      @tanstack/ai-devtools-core

      npm i https://pkg.pr.new/@tanstack/ai-devtools-core@527

      @tanstack/ai-elevenlabs

      npm i https://pkg.pr.new/@tanstack/ai-elevenlabs@527

      @tanstack/ai-event-client

      npm i https://pkg.pr.new/@tanstack/ai-event-client@527

      @tanstack/ai-fal

      npm i https://pkg.pr.new/@tanstack/ai-fal@527

      @tanstack/ai-gemini

      npm i https://pkg.pr.new/@tanstack/ai-gemini@527

      @tanstack/ai-grok

      npm i https://pkg.pr.new/@tanstack/ai-grok@527

      @tanstack/ai-groq

      npm i https://pkg.pr.new/@tanstack/ai-groq@527

      @tanstack/ai-isolate-cloudflare

      npm i https://pkg.pr.new/@tanstack/ai-isolate-cloudflare@527

      @tanstack/ai-isolate-node

      npm i https://pkg.pr.new/@tanstack/ai-isolate-node@527

      @tanstack/ai-isolate-quickjs

      npm i https://pkg.pr.new/@tanstack/ai-isolate-quickjs@527

      @tanstack/ai-ollama

      npm i https://pkg.pr.new/@tanstack/ai-ollama@527

      @tanstack/ai-openai

      npm i https://pkg.pr.new/@tanstack/ai-openai@527

      @tanstack/ai-openrouter

      npm i https://pkg.pr.new/@tanstack/ai-openrouter@527

      @tanstack/ai-preact

      npm i https://pkg.pr.new/@tanstack/ai-preact@527

      @tanstack/ai-react

      npm i https://pkg.pr.new/@tanstack/ai-react@527

      @tanstack/ai-react-ui

      npm i https://pkg.pr.new/@tanstack/ai-react-ui@527

      @tanstack/ai-solid

      npm i https://pkg.pr.new/@tanstack/ai-solid@527

      @tanstack/ai-solid-ui

      npm i https://pkg.pr.new/@tanstack/ai-solid-ui@527

      @tanstack/ai-svelte

      npm i https://pkg.pr.new/@tanstack/ai-svelte@527

      @tanstack/ai-utils

      npm i https://pkg.pr.new/@tanstack/ai-utils@527

      @tanstack/ai-vue

      npm i https://pkg.pr.new/@tanstack/ai-vue@527

      @tanstack/ai-vue-ui

      npm i https://pkg.pr.new/@tanstack/ai-vue-ui@527

      @tanstack/openai-base

      npm i https://pkg.pr.new/@tanstack/openai-base@527

      @tanstack/preact-ai-devtools

      npm i https://pkg.pr.new/@tanstack/preact-ai-devtools@527

      @tanstack/react-ai-devtools

      npm i https://pkg.pr.new/@tanstack/react-ai-devtools@527

      @tanstack/solid-ai-devtools

      npm i https://pkg.pr.new/@tanstack/solid-ai-devtools@527

      commit: af1e6ef

    5. Actionable comments posted: 4

      Caution

      Some comments are outside the diff and can’t be posted inline due to platform limitations.

      ⚠️ Outside diff range comments (2)
      .changeset/streaming-structured-output-openrouter.md (1)

      1-6: ⚠️ Potential issue | 🟠 Major | ⚡ Quick win

      Missing changeset entry for @tanstack/ai.

      The changeset only bumps @tanstack/ai-openrouter, but according to the PR summary and the AI-generated diff summary, @tanstack/ai also ships public API additions in this PR:

      • StructuredOutputCompleteEvent / StructuredOutputStream types added to packages/typescript/ai/src/types.ts
      • New outputSchema && stream === true path in packages/typescript/ai/src/activities/chat/index.ts
      • BaseTextAdapter behaviour change (default structuredOutputStream removed)

      Without a corresponding entry, @tanstack/ai won't receive a version bump when the changeset is consumed.

      📦 Suggested addition to the changeset
       ---
      +'@tanstack/ai': minor
       '@tanstack/ai-openrouter': minor
       ---

      As per coding guidelines: .changeset/**/*.md — create a changeset with pnpm changeset before making changes for release management.

      🤖 Prompt for AI Agents
      Verify each finding against current code. Fix only still-valid issues, skip the
      rest with a brief reason, keep changes minimal, and validate.
      
      In @.changeset/streaming-structured-output-openrouter.md around lines 1 - 6, Add
      a new changeset markdown entry that also bumps `@tanstack/ai` (in addition to
      `@tanstack/ai-openrouter`) and documents the public API additions: include the new
      types StructuredOutputCompleteEvent and StructuredOutputStream (from
      packages/typescript/ai/src/types.ts), the new outputSchema && stream === true
      chat path (packages/typescript/ai/src/activities/chat/index.ts), and the
      BaseTextAdapter behavior change (removal/default change of
      structuredOutputStream); ensure the changeset message explains these API
      additions/behavior change so `@tanstack/ai` is versioned when the changeset is
      released.
      .changeset/streaming-structured-output-chat.md (1)

      1-6: ⚠️ Potential issue | 🟡 Minor | ⚡ Quick win

      @tanstack/ai-openrouter is missing from the changeset packages block.

      OpenRouterTextAdapter.structuredOutputStream is a new public method in packages/typescript/ai-openrouter — a user-visible feature addition. Without a corresponding entry in the changeset, the package version won't be bumped on release.

      📦 Suggested fix
       ---
       '@tanstack/ai': minor
      +'@tanstack/ai-openrouter': minor
       ---
      🤖 Prompt for AI Agents
      Verify each finding against current code. Fix only still-valid issues, skip the
      rest with a brief reason, keep changes minimal, and validate.
      
      In @.changeset/streaming-structured-output-chat.md around lines 1 - 6, The
      changeset is missing a package entry for the new public method
      OpenRouterTextAdapter.structuredOutputStream, so add the package name for the
      ai-openrouter adapter to the changeset packages block and mark it as a minor
      release (public API addition); update the same changeset that introduced
      streaming-structured-output-chat to include '@tanstack/ai-openrouter': minor so
      the package version is bumped on release and consumers get the new
      structuredOutputStream method.
      🧹 Nitpick comments (2)
      packages/typescript/ai-openrouter/src/adapters/text.ts (1)

      266-530: 🏗️ Heavy lift

      structuredOutputStream duplicates ~150 lines of stream lifecycle boilerplate from chatStream.

      The AGUIState initialization (lines 272–291), the per-chunk RUN_STARTED emission + inline error dispatch + processChoice loop (lines 324–376), and the catch block structure (lines 490–529) are near-verbatim copies of the equivalent blocks in chatStream. Any future change to stream lifecycle handling (e.g., abort signal threading, new event types, logging conventions) must be applied to both methods independently, increasing divergence risk.

      Consider extracting a shared runStreamLoop(stream, aguiState, accumulators, onFinalize) helper that takes the finalization callback as a parameter — the only materially different code between the two methods.

      🤖 Prompt for AI Agents
      Verify each finding against current code. Fix only still-valid issues, skip the
      rest with a brief reason, keep changes minimal, and validate.
      
      In `@packages/typescript/ai-openrouter/src/adapters/text.ts` around lines 266 -
      530, structuredOutputStream duplicates ~150 lines of stream lifecycle
      boilerplate from chatStream (AGUIState init, per-chunk RUN_STARTED/error
      handling, processChoice loop, and catch block); extract this shared logic into a
      new helper (e.g., runStreamLoop) that accepts the stream iterator, the
      aguiState, accumulators (accumulatedReasoning, accumulatedContent,
      toolCallBuffers), and a finalization callback (onFinalize) to run the
      method-specific wrap-up (JSON parsing, structured-output CUSTOM emission, and
      RUN_FINISHED); update structuredOutputStream to build its AGUIState and
      accumulators, call runStreamLoop(stream, aguiState, {accumulatedReasoning,
      accumulatedContent, toolCallBuffers}, onFinalize) and move processChoice usage,
      per-chunk yields, and catch handling into the shared helper so both
      structuredOutputStream and chatStream reuse the same lifecycle code.
      packages/typescript/ai/src/activities/chat/index.ts (1)

      1717-1722: 💤 Low value

      mock- ID prefixes leak into real adapter fallback runs.

      fallbackStructuredOutputStream is the production path for any adapter without a native structuredOutputStream, but the synthesized runId / threadId / messageId use a mock- prefix. That looks like test scaffolding in observability/devtools output and is inconsistent with createId('run' | 'thread' | 'msg') used elsewhere in this engine.

      ♻️ Use neutral prefixes
      -  const runId = chatOptions.runId ?? `mock-${Date.now()}`
      -  const threadId = chatOptions.threadId ?? `mock-${Date.now()}`
      -  const messageId = `mock-${Date.now()}-${Math.random().toString(36).slice(2)}`
      +  const rand = () => Math.random().toString(36).slice(2, 9)
      +  const runId = chatOptions.runId ?? `run-${Date.now()}-${rand()}`
      +  const threadId = chatOptions.threadId ?? `thread-${Date.now()}-${rand()}`
      +  const messageId = `msg-${Date.now()}-${rand()}`
      🤖 Prompt for AI Agents
      Verify each finding against current code. Fix only still-valid issues, skip the
      rest with a brief reason, keep changes minimal, and validate.
      
      In `@packages/typescript/ai/src/activities/chat/index.ts` around lines 1717 -
      1722, The current fallback ID generation in chat (variables chatOptions, runId,
      threadId, messageId) uses "mock-" prefixes which leak into production telemetry;
      replace the mock-prefixed defaults with the same neutral ID generation used
      elsewhere (e.g., call the shared createId helper with 'run' | 'thread' | 'msg'
      or use the existing engine's neutral prefix strategy) so
      runId/threadId/messageId are generated consistently when chatOptions doesn't
      supply them; update the fallback logic in the code that reads
      chatOptions.model/timestamp to use createId for runId and threadId and a
      non-mock random message id for messageId.
      🤖 Prompt for all review comments with AI agents
      Verify each finding against current code. Fix only still-valid issues, skip the
      rest with a brief reason, keep changes minimal, and validate.
      
      Inline comments:
      In @.changeset/streaming-structured-output-chat.md:
      - Line 5: The changelog line incorrectly states that BaseTextAdapter provides a
      default structuredOutputStream; update the description to say BaseTextAdapter
      does not implement structuredOutputStream and that the activity layer's
      fallbackStructuredOutputStream is the single source of truth for non-streaming
      adapters. Reference BaseTextAdapter and structuredOutputStream in
      packages/typescript/ai/src/activities/chat/adapter.ts and mention
      fallbackStructuredOutputStream in the activity layer as the fallback, and advise
      adapter authors to implement structuredOutputStream if they need native
      streaming behavior.
      
      In `@packages/typescript/ai-openrouter/src/adapters/text.ts`:
      - Around line 378-440: The finalization path for empty non-exception streams
      fails to emit RUN_STARTED if no chunks arrived; update the end-of-stream logic
      in the generator (the block after the streaming loop that currently emits
      RUN_ERROR for empty content) to check hasEmittedRunStarted and, if false, set
      hasEmittedRunStarted = true and yield the same RUN_STARTED chunk that the normal
      streaming path emits (include runId from aguiState.runId, model resolvedModel,
      and timestamp) before yielding RUN_ERROR; this mirrors the catch block behavior
      and ensures the AG-UI lifecycle (hasEmittedRunStarted, RUN_STARTED, then
      RUN_ERROR) is preserved.
      
      In `@packages/typescript/ai/src/activities/chat/index.ts`:
      - Around line 1860-1886: The loop over engine.run() can yield a RUN_ERROR chunk
      without throwing, but the code always proceeds to call engine.getMessages() and
      adapter.structuredOutputStream(...); fix by detecting an error-yield and
      short-circuiting: inside the for-await loop in runStreamingStructuredOutput (the
      block that calls engine.run()), when you yield a chunk of type 'RUN_ERROR' set a
      local flag (e.g., sawRunError) or reuse earlyTermination set by
      handleRunErrorEvent, then after the loop but before calling finalMessages =
      engine.getMessages() and adapter.structuredOutputStream(...), check that flag
      and return early (or skip the structured-output call) so no structured-output
      flow is started after an error. Ensure the check references the same symbols:
      engine.run(), handleRunErrorEvent, finalMessages, and
      adapter.structuredOutputStream.
      
      In `@testing/e2e/README.md`:
      - Line 126: Update the documented prefix list to include the undocumented prefix
      used by the abort fixture: add "[structured-stream-abort]" to the "Existing
      prefixes" line so it reflects the actual usage in
      fixtures/structured-output-stream/abort.json; ensure the exact token
      "[structured-stream-abort]" is added alongside "[structured-stream]" to prevent
      future collisions.
      
      ---
      
      Outside diff comments:
      In @.changeset/streaming-structured-output-chat.md:
      - Around line 1-6: The changeset is missing a package entry for the new public
      method OpenRouterTextAdapter.structuredOutputStream, so add the package name for
      the ai-openrouter adapter to the changeset packages block and mark it as a minor
      release (public API addition); update the same changeset that introduced
      streaming-structured-output-chat to include '@tanstack/ai-openrouter': minor so
      the package version is bumped on release and consumers get the new
      structuredOutputStream method.
      
      In @.changeset/streaming-structured-output-openrouter.md:
      - Around line 1-6: Add a new changeset markdown entry that also bumps
      `@tanstack/ai` (in addition to `@tanstack/ai-openrouter`) and documents the public
      API additions: include the new types StructuredOutputCompleteEvent and
      StructuredOutputStream (from packages/typescript/ai/src/types.ts), the new
      outputSchema && stream === true chat path
      (packages/typescript/ai/src/activities/chat/index.ts), and the BaseTextAdapter
      behavior change (removal/default change of structuredOutputStream); ensure the
      changeset message explains these API additions/behavior change so `@tanstack/ai`
      is versioned when the changeset is released.
      
      ---
      
      Nitpick comments:
      In `@packages/typescript/ai-openrouter/src/adapters/text.ts`:
      - Around line 266-530: structuredOutputStream duplicates ~150 lines of stream
      lifecycle boilerplate from chatStream (AGUIState init, per-chunk
      RUN_STARTED/error handling, processChoice loop, and catch block); extract this
      shared logic into a new helper (e.g., runStreamLoop) that accepts the stream
      iterator, the aguiState, accumulators (accumulatedReasoning, accumulatedContent,
      toolCallBuffers), and a finalization callback (onFinalize) to run the
      method-specific wrap-up (JSON parsing, structured-output CUSTOM emission, and
      RUN_FINISHED); update structuredOutputStream to build its AGUIState and
      accumulators, call runStreamLoop(stream, aguiState, {accumulatedReasoning,
      accumulatedContent, toolCallBuffers}, onFinalize) and move processChoice usage,
      per-chunk yields, and catch handling into the shared helper so both
      structuredOutputStream and chatStream reuse the same lifecycle code.
      
      In `@packages/typescript/ai/src/activities/chat/index.ts`:
      - Around line 1717-1722: The current fallback ID generation in chat (variables
      chatOptions, runId, threadId, messageId) uses "mock-" prefixes which leak into
      production telemetry; replace the mock-prefixed defaults with the same neutral
      ID generation used elsewhere (e.g., call the shared createId helper with 'run' |
      'thread' | 'msg' or use the existing engine's neutral prefix strategy) so
      runId/threadId/messageId are generated consistently when chatOptions doesn't
      supply them; update the fallback logic in the code that reads
      chatOptions.model/timestamp to use createId for runId and threadId and a
      non-mock random message id for messageId.
      🪄 Autofix (Beta)

      Fix all unresolved CodeRabbit comments on this PR:

      • Push a commit to this branch (recommended)
      • Create a new PR with the fixes

      ℹ️ Review info
      ⚙️ Run configuration

      Configuration used: defaults

      Review profile: CHILL

      Plan: Pro

      Run ID: a66ef4a2-3824-4fbc-ad8f-03cfd2e1f307

      📥 Commits

      Reviewing files that changed from the base of the PR and between ff338557d9ea54c960617f52c89c488140d60f85 and bd550bf2a61ae4f77bf0238aef7e6ea633beaa47.

      📒 Files selected for processing (17)
      • .changeset/streaming-structured-output-chat.md
      • .changeset/streaming-structured-output-openrouter.md
      • packages/typescript/ai-openrouter/src/adapters/text.ts
      • packages/typescript/ai-openrouter/tests/openrouter-adapter.test.ts
      • packages/typescript/ai/src/activities/chat/adapter.ts
      • packages/typescript/ai/src/activities/chat/index.ts
      • packages/typescript/ai/src/types.ts
      • testing/e2e/README.md
      • testing/e2e/fixtures/structured-output-stream/abort.json
      • testing/e2e/fixtures/structured-output-stream/basic.json
      • testing/e2e/src/components/ChatUI.tsx
      • testing/e2e/src/lib/feature-support.ts
      • testing/e2e/src/lib/features.ts
      • testing/e2e/src/lib/types.ts
      • testing/e2e/src/routes/$provider/$feature.tsx
      • testing/e2e/src/routes/api.chat.ts
      • testing/e2e/tests/structured-output-stream.spec.ts
      OutdatedResolvedby coderabbitai[bot](GitHub profile, opens in a new tab)
      OutdatedResolvedby coderabbitai[bot](GitHub profile, opens in a new tab)
      Resolvedby coderabbitai[bot](GitHub profile, opens in a new tab)
      OutdatedResolvedby coderabbitai[bot](GitHub profile, opens in a new tab)
    6. Actionable comments posted: 5

      🤖 Prompt for all review comments with AI agents
      Verify each finding against current code. Fix only still-valid issues, skip the
      rest with a brief reason, keep changes minimal, and validate.
      
      Inline comments:
      In `@examples/ts-react-chat/src/routes/api.structured-output.ts`:
      - Around line 76-80: The non-streaming branch calls chat(...) but doesn't pass
      the HTTP request abort signal, so provider work continues after client
      disconnects; modify the call to propagate the request's abort signal (e.g., pass
      req.signal or a derived AbortSignal) into chat and/or the adapter: update the
      chat invocation in the non-streaming path to include signal: req.signal (or
      create an AbortController that ties to req.signal and pass that) and ensure
      adapterFor(...) or the adapter returned accepts/forwards that signal so provider
      requests are cancelled when the client disconnects.
      - Around line 30-43: The POST body should be parsed and validated inside a
      try/catch and you must validate the provider before calling adapterFor to return
      a 400 for bad input; move the request.json() call into the try block, validate
      required fields (e.g., provider and optional model types), and if provider is
      missing or not one of the expected values return a 400 JSON error instead of
      proceeding. Also harden adapterFor by adding a default/else branch (or throw)
      when provider is unknown so it cannot return undefined (refer to adapterFor and
      its switch cases like 'openai'/'grok'/'groq'/'openrouter'); ensure any casted
      model strings are validated or fall back to safe defaults only after input
      validation.
      
      In `@packages/typescript/ai-grok/src/adapters/text.ts`:
      - Around line 447-450: The logger currently sends the raw SDK error
      (logger.errors('grok.structuredOutputStream fatal', { error, ... })) which may
      contain sensitive request/auth metadata; replace the raw error with a
      sanitized/normalized error object like the one used in
      packages/typescript/ai-openai/src/adapters/text.ts (e.g., call the same
      sanitize/normalizeOpenAIError helper from that module or replicate its behavior)
      and log only the sanitizedError (and minimal context fields) instead of the raw
      SDK error so request-level details are not leaked.
      
      In `@packages/typescript/ai-openai/src/adapters/text.ts`:
      - Around line 312-424: The loop currently only handles
      'response.output_text.delta' and drops 'response.reasoning_text.delta' and
      'response.reasoning_summary_text.delta', so add handling for those chunk.type
      values: create a separate accumulator (e.g., reasoningAccumulatedContent) and
      flags (similar to hasEmittedTextMessageStart) to collect and emit reasoning
      deltas via yield asChunk (use types analogous to TEXT_MESSAGE_START/CONTENT or a
      clear reasoning event), append deltas when chunk.delta is string|array, and
      ensure when the run completes ('response.completed' / final structured-output
      emission) you attach the accumulated reasoning to the structured-output
      completion payload (structured-output.complete.value.reasoning) so
      schema-failure post-mortems receive the model's reasoning; use existing symbols
      runId, messageId, model, timestamp, asChunk, accumulatedContent for locating
      where to add this logic.
      
      In `@testing/e2e/src/lib/feature-support.ts`:
      - Around line 83-85: Update the comment to remove the stale reference to
      BaseTextAdapter and instead mention the activity-layer
      fallbackStructuredOutputStream as the fallback handler; edit the block that
      currently references "BaseTextAdapter implementation" so it reads that other
      providers fall back to the activity-layer fallbackStructuredOutputStream (or
      similar phrasing) and keep the rest of the comment about providers with native
      streaming JSON schema support intact to avoid confusion during matrix
      maintenance.
      🪄 Autofix (Beta)

      Fix all unresolved CodeRabbit comments on this PR:

      • Push a commit to this branch (recommended)
      • Create a new PR with the fixes

      ℹ️ Review info
      ⚙️ Run configuration

      Configuration used: defaults

      Review profile: CHILL

      Plan: Pro

      Run ID: d0a46433-8d08-486d-aaac-9c40b3c58f5d

      📥 Commits

      Reviewing files that changed from the base of the PR and between bd550bf2a61ae4f77bf0238aef7e6ea633beaa47 and 0087eb9a2758292a9b39351f9d6277ee4e8ca40d.

      📒 Files selected for processing (12)
      • .changeset/streaming-structured-output-grok.md
      • .changeset/streaming-structured-output-groq.md
      • .changeset/streaming-structured-output-openai.md
      • examples/ts-react-chat/src/routes/api.structured-output.ts
      • examples/ts-react-chat/src/routes/generations.structured-output.tsx
      • packages/typescript/ai-grok/src/adapters/text.ts
      • packages/typescript/ai-grok/tests/grok-adapter.test.ts
      • packages/typescript/ai-groq/src/adapters/text.ts
      • packages/typescript/ai-groq/tests/groq-adapter.test.ts
      • packages/typescript/ai-openai/src/adapters/text.ts
      • packages/typescript/ai-openai/tests/openai-adapter.test.ts
      • testing/e2e/src/lib/feature-support.ts
      ✅ Files skipped from review due to trivial changes (3)
      • .changeset/streaming-structured-output-openai.md
      • .changeset/streaming-structured-output-grok.md
      • .changeset/streaming-structured-output-groq.md
      Resolvedby coderabbitai[bot](GitHub profile, opens in a new tab)
      Resolvedby coderabbitai[bot](GitHub profile, opens in a new tab)
      OutdatedResolvedby coderabbitai[bot](GitHub profile, opens in a new tab)
      OutdatedResolvedby coderabbitai[bot](GitHub profile, opens in a new tab)
      OutdatedResolvedby coderabbitai[bot](GitHub profile, opens in a new tab)
    7. Actionable comments posted: 5

      🤖 Prompt for all review comments with AI agents
      Verify each finding against current code. Fix only still-valid issues, skip the
      rest with a brief reason, keep changes minimal, and validate.
      
      Inline comments:
      In `@examples/ts-react-chat/src/routes/generations.structured-output.tsx`:
      - Around line 281-300: The labels "Provider", "Model" and "Prompt" are not
      linked to their form controls; add id attributes to the corresponding <select>
      and <textarea> elements (e.g., "provider-select", "model-select",
      "prompt-textarea") and set the matching htmlFor on each <label> so the label
      text is associated with the control (affects the <select value={provider}
      onChange={onProviderChange} disabled={isLoading}>, the <select value={model}
      onChange={e => setModel(e.target.value} disabled={isLoading}>, and the prompt
      <textarea>), ensuring unique ids and keeping existing props like isLoading
      intact.
      - Around line 222-229: The handler updates reasoningFull when a streamed chunk
      contains a reasoning string (setReasoningFull on chunk.value) but never
      recomputes or updates the one-line summary reasoningLine, so the “Thinking”
      strip can remain blank or stale; after calling setReasoningFull((chunk.value as
      { reasoning: string }).reasoning) also derive and call setReasoningLine with a
      compact one-line version (e.g., trim and collapse whitespace or take the first
      sentence) so that both reasoningFull and reasoningLine stay consistent when
      reasoning is sent only in the final structured-output.complete or when the final
      chunk extends earlier reasoning.
      - Around line 170-235: The reader loop currently exits on EOF without failing if
      the canonical completion signal ("structured-output.complete") never arrived;
      introduce a local boolean flag (e.g. sawFinalResult = false) and set it to true
      inside the branch that handles chunk.type === 'CUSTOM' && chunk.name ===
      'structured-output.complete' (also still call setHasFinalResult(true)). After
      the outer while (after you break on done from reader.read()), check if
      (!sawFinalResult) and throw a descriptive Error (e.g. 'Stream ended before
      structured-output.complete arrived') so the run fails on EOF when the final
      structured-output payload was not observed.
      - Around line 163-174: The stream decoding loop uses a TextDecoder with {stream:
      true} but never flushes remaining buffered bytes when the reader loop exits;
      after the while(true) loop that reads from response.body!.getReader() and
      appends decoder.decode(value, {stream: true}) into buffer, call decoder.decode()
      once more (without the stream flag) and append its result to buffer (or
      otherwise process it) before continuing with accumulated/reasoning/deltas
      handling so any partial UTF-8 sequences are correctly finalized.
      🪄 Autofix (Beta)

      Fix all unresolved CodeRabbit comments on this PR:

      • Push a commit to this branch (recommended)
      • Create a new PR with the fixes

      ℹ️ Review info
      ⚙️ Run configuration

      Configuration used: defaults

      Review profile: CHILL

      Plan: Pro

      Run ID: 49bf45f2-6618-4113-8aea-d644b0809d7c

      📥 Commits

      Reviewing files that changed from the base of the PR and between 0087eb9a2758292a9b39351f9d6277ee4e8ca40d and 0a7f31ab115e50b6888ae77cd22fde1bec5ac8a4.

      📒 Files selected for processing (7)
      • examples/ts-react-chat/src/routes/api.structured-output.ts
      • examples/ts-react-chat/src/routes/generations.structured-output.tsx
      • packages/typescript/ai-grok/src/adapters/text.ts
      • packages/typescript/ai-grok/tests/grok-adapter.test.ts
      • packages/typescript/ai-groq/src/adapters/text.ts
      • packages/typescript/ai-groq/tests/groq-adapter.test.ts
      • packages/typescript/ai-openai/src/adapters/text.ts
      🚧 Files skipped from review as they are similar to previous changes (3)
      • examples/ts-react-chat/src/routes/api.structured-output.ts
      • packages/typescript/ai-groq/src/adapters/text.ts
      • packages/typescript/ai-groq/tests/groq-adapter.test.ts
      OutdatedResolvedby coderabbitai[bot](GitHub profile, opens in a new tab)
      OutdatedResolvedby coderabbitai[bot](GitHub profile, opens in a new tab)
      Resolvedby coderabbitai[bot](GitHub profile, opens in a new tab)
      OutdatedResolvedby coderabbitai[bot](GitHub profile, opens in a new tab)
      OutdatedResolvedby coderabbitai[bot](GitHub profile, opens in a new tab)
    8. ♻️ Duplicate comments (6)
      examples/ts-react-chat/src/routes/api.structured-output.ts (2)

      97-105: ⚠️ Potential issue | 🟠 Major | ⚡ Quick win

      Validate the POST body before casting it.

      request.json() runs outside the try, and the unchecked cast lets malformed JSON or an unsupported provider fall through as a 500. Parse the body inside the try with a Zod schema and return 400 on invalid input instead of letting adapterFor() receive unchecked data.

      🤖 Prompt for AI Agents
      Verify each finding against current code. Fix only still-valid issues, skip the
      rest with a brief reason, keep changes minimal, and validate.
      
      In `@examples/ts-react-chat/src/routes/api.structured-output.ts` around lines 97 -
      105, Move parsing of the POST body into the try block and validate it with a Zod
      schema before casting so malformed JSON or invalid provider values return a 400
      instead of reaching adapterFor(); specifically, define a Zod schema for {
      prompt: string, provider?: Provider, model?: string, stream?: boolean }, call
      await request.json() inside the try, parse/validate with schema.parse or
      safeParse, and if validation fails return a 400 response; then compute
      resolvedProvider (fallback to 'openrouter') only from validated data and pass
      that safe value to adapterFor().

      127-132: ⚠️ Potential issue | 🟠 Major | ⚡ Quick win

      Propagate disconnect aborts through the non-streaming chat() call too.

      Only the streaming branch cancels provider work when request.signal aborts. The non-streaming call will keep running after the client is gone, burning tokens and tying up server capacity.

      🤖 Prompt for AI Agents
      Verify each finding against current code. Fix only still-valid issues, skip the
      rest with a brief reason, keep changes minimal, and validate.
      
      In `@examples/ts-react-chat/src/routes/api.structured-output.ts` around lines 127
      - 132, The non-streaming chat call doesn't receive the client's abort signal, so
      work continues after the client disconnects; update the chat invocation to pass
      through the abort signal (e.g., include signal: request.signal) so that
      chat(...) (and downstream adapterFor/resolvedProvider work) can cancel when the
      request is aborted; ensure the chat call's options include the signal property
      alongside adapter, modelOptions, messages, and outputSchema.
      examples/ts-react-chat/src/routes/generations.structured-output.tsx (4)

      279-299: ⚠️ Potential issue | 🟠 Major | ⚡ Quick win

      Associate the visible labels with their controls.

      Provider, Model, and Prompt are rendered as standalone labels, so the selects and textarea lose explicit accessible names and label-click focus.

      Also applies to: 326-334

      🤖 Prompt for AI Agents
      Verify each finding against current code. Fix only still-valid issues, skip the
      rest with a brief reason, keep changes minimal, and validate.
      
      In `@examples/ts-react-chat/src/routes/generations.structured-output.tsx` around
      lines 279 - 299, The labels "Provider", "Model" and "Prompt" are not associated
      with their form controls; add explicit associations by giving each
      select/textarea a unique id (e.g., providerSelect, modelSelect, promptTextarea)
      and set the corresponding label's htmlFor to that id (or wrap the control inside
      the label). Update the JSX around the provider select (value={provider},
      onChange={onProviderChange}), the model select (value={model},
      onChange={setModel}), and the prompt textarea to use those ids so clicking a
      label focuses the correct control and improves accessibility.

      220-227: ⚠️ Potential issue | 🟡 Minor | ⚡ Quick win

      Keep reasoningLine in sync with terminal reasoning.

      This branch overwrites reasoningFull but leaves the one-line strip stale. If reasoning only arrives on structured-output.complete, the “Thinking” summary stays blank or outdated.

      🤖 Prompt for AI Agents
      Verify each finding against current code. Fix only still-valid issues, skip the
      rest with a brief reason, keep changes minimal, and validate.
      
      In `@examples/ts-react-chat/src/routes/generations.structured-output.tsx` around
      lines 220 - 227, When you set reasoningFull from the chunk (inside the branch
      that checks (chunk.value as { reasoning?: string }).reasoning), also update
      reasoningLine so it stays in sync: assign reasoningFull via
      setReasoningFull((chunk.value as { reasoning: string }).reasoning) and
      immediately call setReasoningLine with a one-line/trimmed version (e.g., first
      line or trimmed slice) of the same value; update the same logic path that
      handles structured-output.complete so both state variables (reasoningFull and
      reasoningLine) are always updated from the same source.

      168-233: ⚠️ Potential issue | 🟠 Major | ⚡ Quick win

      Fail the run if EOF arrives before structured-output.complete.

      The loop currently exits successfully on EOF even when only partial deltas were received. If the connection drops before the terminal event, this page leaves a partial object rendered with no error.

      🤖 Prompt for AI Agents
      Verify each finding against current code. Fix only still-valid issues, skip the
      rest with a brief reason, keep changes minimal, and validate.
      
      In `@examples/ts-react-chat/src/routes/generations.structured-output.tsx` around
      lines 168 - 233, The reader loop currently breaks on EOF even if the terminal
      structured-output.complete was never received; add a local boolean (e.g.,
      receivedFinalResult) initialized false, set it true in the branch where you call
      setResult(...) and setHasFinalResult(true) for the
      CUSTOM/structured-output.complete chunk (the same place that currently
      setsHasFinalResult), and change the EOF handling (when done is true) to throw an
      Error (or reject) if receivedFinalResult is still false (e.g., throw new
      Error('Stream ended before structured-output.complete')). This ensures the run
      fails on premature EOF while preserving existing state updates.

      168-233: ⚠️ Potential issue | 🟠 Major | ⚡ Quick win

      Flush the TextDecoder after the read loop.

      decoder.decode(value, { stream: true }) can buffer trailing UTF-8 bytes. Without a final decoder.decode(), the last SSE frame can be truncated or dropped when a multibyte character spans reads.

      🤖 Prompt for AI Agents
      Verify each finding against current code. Fix only still-valid issues, skip the
      rest with a brief reason, keep changes minimal, and validate.
      
      In `@examples/ts-react-chat/src/routes/generations.structured-output.tsx` around
      lines 168 - 233, The TextDecoder may have buffered trailing UTF-8 bytes; after
      the read loop that uses decoder.decode(value, { stream: true }) (the while
      (true) { const { done, value } = await reader.read() ... } block) call
      decoder.decode() with no arguments to flush remaining bytes and append the
      result to buffer before continuing to parse frames, then run the same
      frame-parsing logic on the updated buffer; update references to buffer, decoder,
      and the reader loop/stream parsing code so the final partial multibyte
      characters are not dropped.
      🤖 Prompt for all review comments with AI agents
      Verify each finding against current code. Fix only still-valid issues, skip the
      rest with a brief reason, keep changes minimal, and validate.
      
      Duplicate comments:
      In `@examples/ts-react-chat/src/routes/api.structured-output.ts`:
      - Around line 97-105: Move parsing of the POST body into the try block and
      validate it with a Zod schema before casting so malformed JSON or invalid
      provider values return a 400 instead of reaching adapterFor(); specifically,
      define a Zod schema for { prompt: string, provider?: Provider, model?: string,
      stream?: boolean }, call await request.json() inside the try, parse/validate
      with schema.parse or safeParse, and if validation fails return a 400 response;
      then compute resolvedProvider (fallback to 'openrouter') only from validated
      data and pass that safe value to adapterFor().
      - Around line 127-132: The non-streaming chat call doesn't receive the client's
      abort signal, so work continues after the client disconnects; update the chat
      invocation to pass through the abort signal (e.g., include signal:
      request.signal) so that chat(...) (and downstream adapterFor/resolvedProvider
      work) can cancel when the request is aborted; ensure the chat call's options
      include the signal property alongside adapter, modelOptions, messages, and
      outputSchema.
      
      In `@examples/ts-react-chat/src/routes/generations.structured-output.tsx`:
      - Around line 279-299: The labels "Provider", "Model" and "Prompt" are not
      associated with their form controls; add explicit associations by giving each
      select/textarea a unique id (e.g., providerSelect, modelSelect, promptTextarea)
      and set the corresponding label's htmlFor to that id (or wrap the control inside
      the label). Update the JSX around the provider select (value={provider},
      onChange={onProviderChange}), the model select (value={model},
      onChange={setModel}), and the prompt textarea to use those ids so clicking a
      label focuses the correct control and improves accessibility.
      - Around line 220-227: When you set reasoningFull from the chunk (inside the
      branch that checks (chunk.value as { reasoning?: string }).reasoning), also
      update reasoningLine so it stays in sync: assign reasoningFull via
      setReasoningFull((chunk.value as { reasoning: string }).reasoning) and
      immediately call setReasoningLine with a one-line/trimmed version (e.g., first
      line or trimmed slice) of the same value; update the same logic path that
      handles structured-output.complete so both state variables (reasoningFull and
      reasoningLine) are always updated from the same source.
      - Around line 168-233: The reader loop currently breaks on EOF even if the
      terminal structured-output.complete was never received; add a local boolean
      (e.g., receivedFinalResult) initialized false, set it true in the branch where
      you call setResult(...) and setHasFinalResult(true) for the
      CUSTOM/structured-output.complete chunk (the same place that currently
      setsHasFinalResult), and change the EOF handling (when done is true) to throw an
      Error (or reject) if receivedFinalResult is still false (e.g., throw new
      Error('Stream ended before structured-output.complete')). This ensures the run
      fails on premature EOF while preserving existing state updates.
      - Around line 168-233: The TextDecoder may have buffered trailing UTF-8 bytes;
      after the read loop that uses decoder.decode(value, { stream: true }) (the while
      (true) { const { done, value } = await reader.read() ... } block) call
      decoder.decode() with no arguments to flush remaining bytes and append the
      result to buffer before continuing to parse frames, then run the same
      frame-parsing logic on the updated buffer; update references to buffer, decoder,
      and the reader loop/stream parsing code so the final partial multibyte
      characters are not dropped.

      ℹ️ Review info
      ⚙️ Run configuration

      Configuration used: defaults

      Review profile: CHILL

      Plan: Pro

      Run ID: 5087f1ff-61cd-4360-9d0e-51d3117b3ba0

      📥 Commits

      Reviewing files that changed from the base of the PR and between 0a7f31ab115e50b6888ae77cd22fde1bec5ac8a4 and b14800e8349d75b2a2cc73ec0638d943195df964.

      📒 Files selected for processing (2)
      • examples/ts-react-chat/src/routes/api.structured-output.ts
      • examples/ts-react-chat/src/routes/generations.structured-output.tsx
    9. Hi! I'm the autofix logoautofix.ci troubleshooter bot.

      It looks like you correctly set up a CI job that uses the autofix.ci GitHub Action, but the autofix.ci GitHub App has not been installed for this repository. This means that autofix.ci unfortunately does not have the permissions to fix this pull request. If you are the repository owner, please install the app and then restart the CI workflow! 😃

    10. tombeckenham changed the title

    11. AlemTuzlak reviewed

      OutdatedResolvedby tombeckenham
    12. AlemTuzlakreplied on packages/typescript/ai-openrouter/src/adapters/responses-text.ts lines 359 to 366

      okay after inspecting the previous method i don't think i know

    13. AlemTuzlak reviewed

      OutdatedResolvedby tombeckenham
    14. AlemTuzlak reviewed

      OutdatedResolvedby tombeckenham
    15. AlemTuzlak reviewed

      OutdatedResolvedby tombeckenham
    16. AlemTuzlak reviewed

      OutdatedResolvedby tombeckenham
    17. AlemTuzlak reviewed

      Resolvedby tombeckenham
    18. AlemTuzlak reviewed

      OutdatedResolvedby tombeckenham
    19. AlemTuzlak reviewed

      OutdatedResolvedby tombeckenham
    20. AlemTuzlak requested changes

      lets add an agent skill for this, also left some comments, great work!

    21. tombeckenhamreplied on packages/typescript/ai/src/activities/chat/index.ts line 1602

      packages/typescript/ai/tests/chat-result-types.test.ts:20 pins every combination with strict expectTypeOf(...).toEqualTypeOf(...)

    22. tombeckenhamreplied on packages/typescript/ai-openrouter/src/adapters/responses-text.ts lines 359 to 366

      Mirroring the order in text.ts (REASONING_START → REASONING_MESSAGE_START → STEP_STARTED) deliberately — the stream processor handles STEP_STARTED arriving after REASONING_START via consumePendingThinkingStep, so the open/close pairing is what matters, not the order within the pair.

    23. AlemTuzlak approved these changes

    24. AlemTuzlak merged this98979f7

    25. AlemTuzlak closed this

Sign in to join this conversation.