// Audit TanStack AI provider adapters for feature parity gaps and outdated model lists. Triggered as /gap-analysis <provider|feature <name>|models|--all>. Produces a dated markdown report under .agent/gap-analysis/. Maintainer tool — does not edit feature-support.ts or model-meta.ts directly.
Image, audio, video, speech (TTS), and transcription generation using activity-specific adapters: generateImage() with openaiImage/geminiImage, generateAudio() with geminiAudio/falAudio, generateVideo() with async polling, generateSpeech() with openaiSpeech, generateTranscription() with openaiTranscription. React hooks: useGenerateImage, useGenerateAudio, useGenerateSpeech, useTranscription, useGenerateVideo. TanStack Start server function integration with toServerSentEventsResponse.
Entry point for TanStack AI skills. Routes to chat-experience, tool-calling, media-generation, structured-outputs, adapter-configuration, ag-ui-protocol, middleware, custom-backend-integration, and debug-logging. Use chat() not streamText(), openaiText() not createOpenAI(), toServerSentEventsResponse() not manual SSE, middleware hooks not onEnd callbacks.
Chat lifecycle middleware hooks: onConfig, onStart, onChunk, onBeforeToolCall, onAfterToolCall, onUsage, onFinish, onAbort, onError. Use for analytics, event firing, tool caching (toolCacheMiddleware), logging, and tracing. Middleware array in chat() config, left-to-right execution order. NOT onEnd/onFinish callbacks on chat() — use middleware.
Type-safe JSON schema responses from LLMs using outputSchema on chat() and useChat(). Supports Zod, ArkType, and Valibot schemas. The adapter handles provider-specific strategies transparently — never configure structured output at the provider level. Pass stream:true alongside outputSchema for incremental JSON deltas + a terminal validated object via the `structured-output.complete` event. Every assistant turn in useChat carries its own typed `StructuredOutputPart` on `messages[i].parts`, so multi-turn structured chats preserve history automatically — partial/final derive from the latest assistant turn's part. convertSchemaToJsonSchema() for manual schema conversion.
Server-side AG-UI streaming protocol implementation: StreamChunk event types (RUN_STARTED, TEXT_MESSAGE_START/CONTENT/END, TOOL_CALL_START/ARGS/END, RUN_FINISHED, RUN_ERROR, STEP_STARTED/STEP_FINISHED, STATE_SNAPSHOT/DELTA, CUSTOM), toServerSentEventsStream() for SSE format, toHttpStream() for NDJSON format. For backends serving AG-UI events without client packages.
Pluggable, category-toggleable debug logging for TanStack AI activities. Toggle with `debug: true | false | DebugConfig` on chat(), summarize(), generateImage(), generateSpeech(), generateTranscription(), generateVideo(). Categories: request, provider, output, middleware, tools, agentLoop, config, errors. Pipe into pino/winston/etc via `debug: { logger }`. Errors log by default even when `debug` is omitted; silence with `debug: false`.
| name | gap-analysis |
| description | Audit TanStack AI provider adapters for feature parity gaps and outdated model lists. Triggered as /gap-analysis <provider|feature <name>|models|--all>. Produces a dated markdown report under .agent/gap-analysis/. Maintainer tool — does not edit feature-support.ts or model-meta.ts directly. |
You are auditing TanStack AI's provider adapters against each provider's
upstream documentation. This is a maintainer tool. Your only output is a
markdown report under .agent/gap-analysis/. Do not edit source files.
| Args | Scope |
|---|---|
<provider> (e.g. openai) | One provider — all four audit dimensions. |
feature <feature> (e.g. tts) | One feature row of the matrix across all providers. |
models | New-model diff for every provider. |
--all | Full sweep (fan out subagents, one per provider). |
| (none) | Ask the user which scope via AskUserQuestion. |
testing/e2e/src/lib/feature-support.tstesting/e2e/src/lib/types.ts (Provider + Feature unions, ALL_PROVIDERS, ALL_FEATURES)packages/typescript/ai-<provider>/src/index.tspackages/typescript/ai-<provider>/src/model-meta.tspackages/typescript/ai/src/types.ts (Modality, ContentPart, ToolCall)context7 MCP server (mcp__plugin_context7_context7__resolve-library-id
then mcp__plugin_context7_context7__query-docs).--all: launch one Explore subagent per provider, max 3
in parallel. Each subagent returns the five-dimension findings for its
provider; you synthesise into the combined report..agent/gap-analysis/YYYY-MM-DD-<scope>.md using
references/report-template.md. Date is
today's ISO date. <scope> is openai / feature-tts / models / all.feature-support.ts or any model-meta.ts. The report is
read-only — the maintainer applies changes.feature-support.ts:57) so the maintainer can jump to them.feature-support.ts (e.g., aimock format limitation). Not
actionable code-wise; surface in "Out-of-scope" section.model-meta.ts declares a capability the
model no longer has, or omits one it now has.feature-support.ts when flagging a
parity gap, so the report is self-contained.openai, anthropic, gemini, ollama, grok, groq, openrouter, fal
(media-only), elevenlabs (TTS-only). The feature matrix tracks the first
seven; fal and elevenlabs only appear in model/media audits.
Canonical list is ALL_FEATURES in testing/e2e/src/lib/types.ts — always
re-read it; this list is a snapshot:
chat, one-shot-text, reasoning, multi-turn, tool-calling,
parallel-tool-calls, tool-approval, text-tool-text, structured-output,
structured-output-stream, agentic-structured, multimodal-image,
multimodal-structured, summarize, summarize-stream, image-gen, tts,
transcription, video-gen.
Before printing the summary:
git status shows only new files under .agent/gap-analysis/ — nothing
under packages/ or testing/ should have been modified. Run git status
and confirm.