ai

LLM-generated TypeScript execution in sandboxed environments: createCodeModeTool() with isolate drivers (createNodeIsolateDriver, createQuickJSIsolateDriver, createCloudflareIsolateDriver), codeModeWithSkills() for persistent skill libraries, trust strategies, skill storage (FileSystem, LocalStorage, InMemory, Mongo), client-side execution progress via code_mode:* custom events in useChat.

Provider adapter selection and configuration: openaiText, anthropicText, geminiText, ollamaText, grokText, groqText, openRouterText. Per-model type safety with modelOptions, reasoning/thinking configuration, runtime adapter switching, extendAdapter() for custom models, createModel(). API key env vars: OPENAI_API_KEY, ANTHROPIC_API_KEY, GOOGLE_API_KEY/GEMINI_API_KEY, XAI_API_KEY, GROQ_API_KEY, OPENROUTER_API_KEY, OLLAMA_HOST.

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.

End-to-end chat implementation: server endpoint with chat() and toServerSentEventsResponse(), client-side useChat hook with fetchServerSentEvents(), message rendering with UIMessage parts, multimodal content, thinking/reasoning display. Covers streaming states, connection adapters, and message format conversions. NOT Vercel AI SDK — uses chat() not streamText().

Image, video, speech (TTS), and transcription generation using activity-specific adapters: generateImage() with openaiImage/geminiImage, generateVideo() with async polling, generateSpeech() with openaiSpeech, generateTranscription() with openaiTranscription. React hooks: useGenerateImage, useGenerateSpeech, useTranscription, useGenerateVideo. TanStack Start server function integration with toServerSentEventsResponse.

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.

Entry point for TanStack AI skills. Routes to chat-experience, tool-calling, media-generation, structured-outputs, adapter-configuration, ag-ui-protocol, middleware, and custom-backend-integration. Use chat() not streamText(), openaiText() not createOpenAI(), toServerSentEventsResponse() not manual SSE, middleware hooks not onEnd callbacks.

Type-safe JSON schema responses from LLMs using outputSchema on chat(). Supports Zod, ArkType, and Valibot schemas. The adapter handles provider-specific strategies transparently — never configure structured output at the provider level. convertSchemaToJsonSchema() for manual schema conversion.

Isomorphic tool system: toolDefinition() with Zod schemas, .server() and .client() implementations, passing tools to both chat() on server and useChat/clientTools on client, tool approval flows with needsApproval and addToolApprovalResponse(), lazy tool discovery with lazy:true, rendering ToolCallPart and ToolResultPart in UI.