Terminal
Terminal/Skill
Walks your agent through upgrading an app from AI SDK 6 to AI SDK 7 and fixing the breaking changes.
By Vercel
Works with
npx skills add vercel/ai --skill migrate-ai-sdk-v6-to-v7Use content/docs/08-migration-guides/23-migration-guide-7-0.mdx from the AI SDK repo as the source of truth. This skill is the working checklist; read the guide for exact examples or when behavior is unclear.
package.json and lockfiles to identify installed ai, @ai-sdk/*, provider, UI, MCP, and telemetry packages.@ai-sdk/otel only if the project uses OpenTelemetry spans.>=22, and AI SDK packages are ESM-only. Replace require() imports with ESM imports and add "type": "module" or use .mjs where needed.Prefer behavior-preserving changes. When v7 changes semantics, decide whether the app wants the new all-steps behavior or the previous final-step-only behavior.
experimental_customProvider -> customProvider.experimental_generateImage -> generateImage; Experimental_GenerateImageResult -> GenerateImageResult.experimental_transcribe -> transcribe; Experimental_TranscriptionResult -> TranscriptionResult.experimental_generateSpeech -> generateSpeech; Experimental_SpeechResult -> SpeechResult.experimental_output option/result -> output option/result.CallSettings -> LanguageModelCallOptions & Omit<RequestOptions, 'timeout'>; prepareCallSettings -> prepareLanguageModelCallOptions.stepCountIs -> isStepCount.system to instructions for generateText, streamText, generateObject, streamObject, and streamUI.{ role: 'system' } messages from prompt or messages into top-level instructions. Only use allowSystemInMessages: true for trusted persisted messages.experimental_prepareStep to prepareStep.prepareStep, rename returned system to instructions.experimental_repairToolCall, use { instructions } instead of { system }.prepareStep behavior: returned instructions and messages now carry forward into later steps. If code depended on one-step-only overrides, rebuild from initialInstructions, initialMessages, and responseMessages explicitly.experimental_onStart -> onStart.experimental_onStepStart -> onStepStart.onFinish -> onEnd.onStepFinish -> onStepEnd.embed, embedMany, and rerank, experimental_onFinish -> onEnd.instructions instead of system.usage.cachedInputTokens -> usage.inputTokenDetails.cacheReadTokens.usage.reasoningTokens -> usage.outputTokenDetails.reasoningTokens.ai; install @ai-sdk/otel and call registerTelemetry(new OpenTelemetry(...)) at app startup.isEnabled: true; use isEnabled: false to opt out per call.experimental_telemetry.tracer into the OpenTelemetry constructor.experimental_telemetry -> telemetry.onRerankFinish -> onRerankEnd, onEmbedFinish -> onEmbedEnd. Update tracing-channel subscribers for the same event type names.experimental_include -> include.includeRawChunks -> include.rawChunks.request.body or response.body, opt in with include.requestBody and, for generateText, include.responseBody.StreamTextResult.fullStream -> stream.streamText onChunk now receives all stream parts, including lifecycle, boundary, finish, abort, and error parts. Guard by chunk.type before assuming text/tool/raw content.step.response.messages is no longer accumulated across previous steps. Use result.responseMessages for the full response message history, or flatten result.steps.experimental_onToolCallStart -> onToolExecutionStart, experimental_onToolCallFinish -> onToolExecutionEnd.experimental_context -> context.runtimeContext for orchestration state, declare per-tool contextSchema, and pass per-tool values through toolsContext.needsApproval from tool() / dynamicTool() into per-call or agent toolApproval.experimental_activeTools -> activeTools.ToolCallOptions -> ToolExecutionOptions.isToolOrDynamicToolUIPart -> isToolUIPart.{ type: 'media' } is removed; use { type: 'file-data' }.toModelOutput image-*, file-*, file-id, and image-file-id variants to canonical { type: 'file', mediaType, data: { type: 'data' | 'url' | 'reference', ... } }.{ type: 'image', image, mediaType? } is deprecated; use { type: 'file', mediaType: 'image' | 'image/*', data }.reasoning-file content type in exhaustive switches, renderers, serializers, and validators.reasoning, remove overlapping provider-specific reasoning settings from providerOptions unless provider-specific settings intentionally take precedence.result.usage now includes all steps; result.totalUsage is deprecated. Use result.finalStep.usage for final-step-only usage.content, toolCalls, staticToolCalls, dynamicToolCalls, toolResults, staticToolResults, dynamicToolResults, files, sources, and warnings now include all steps. Use finalStep for previous final-step-only behavior.reasoning, reasoningText, request, response, and providerMetadata are deprecated for final-step data. Use result.finalStep.*; for streamText, await result.finalStep.onEnd events.The streamText result helper methods are deprecated. Replace result methods with top-level stateless helpers:
result.toUIMessageStream(...) -> toUIMessageStream({ stream: result.stream, ... }).result.toUIMessageStreamResponse(...) -> toUIMessageStream(...) plus createUIMessageStreamResponse({ stream }).result.pipeUIMessageStreamToResponse(response, ...) -> toUIMessageStream(...) plus pipeUIMessageStreamToResponse({ response, stream }).result.toTextStreamResponse() -> toTextStream({ stream: result.stream }) plus createTextStreamResponse({ stream }).result.pipeTextStreamToResponse(response) -> toTextStream({ stream: result.stream }) plus pipeTextStreamToResponse({ response, stream }).MCPTransportConfig.redirect now defaults to 'error'. Only set redirect: 'follow' for trusted MCP servers that rely on redirects.@ai-sdk/vue Chat class is deprecated. Prefer useChat, including getter/ref init for reactive chat inputs.@ai-sdk/google-vertex/anthropic: providerMetadata.anthropic.cacheCreationInputTokens was removed. Use usage.inputTokenDetails.cacheWriteTokens; raw Anthropic usage remains at finalStep.providerMetadata?.anthropic?.usage.GoogleGenerativeAI* types, classes, and functions to Google*, e.g. createGoogleGenerativeAI -> createGoogle. The google entry point is unchanged.Run the project typecheck after edits, then the smallest relevant test suite. Also smoke-test streaming, chat UI, tool execution, telemetry, and multi-step flows if the migration touched them. If type errors remain, search the migration guide for the exact removed or renamed symbol before inventing a workaround.