feat: support both AI SDK v6 and v7 in Think and its dependencies#1940
Merged
Conversation
|
| Name | Type |
|---|---|
| agents | Minor |
| @cloudflare/ai-chat | Minor |
| @cloudflare/codemode | Minor |
| @cloudflare/think | Minor |
| @cloudflare/agent-think | Patch |
Click here to learn what changesets are, and how to add one.
Click here if you're a maintainer who wants to add a changeset to this PR
cjol
force-pushed
the
fix/think-ai-sdk-v6-v7-compat
branch
2 times, most recently
from
July 14, 2026 15:23
455de86 to
93144a0
Compare
Widen the "ai" peer range to "^6 || ^7" (and "@ai-sdk/react" to "^3 || ^4") across agents, @cloudflare/ai-chat, @cloudflare/codemode, and @cloudflare/think, so consumers can upgrade these packages without being forced onto AI SDK v7. Think now calls the AI SDK through the option names present in both majors (stepCountIs, system, experimental_telemetry, onStepFinish, experimental_onToolCallFinish) and normalizes the genuine divergences at the boundary: - normalizeToolFinishEvent collapses the v6 and v7 tool-execution-finished event shapes into one ToolCallResultContext. - The UI message stream uses the result's toUIMessageStream() method (present in both majors) instead of the v7-only standalone helper + result.stream. - The workspace read tool emits the "file-data" model output content part, which both majors accept (v7's newer "file" shape does not exist in v6). Also fix a v7-migration test regression: a test helper called getReader() on toUIMessageStream()'s result, which became a pure async iterable when readableStreamToAsyncIterable was introduced, masking the intended error and failing 17 error-handling tests. It now consumes the async iterator. Drop the v7-only telemetry test that froze telemetry.integrations behavior (v6 has no such API). Add an ai@6 / ai@7 CI matrix (.github/workflows/ai-sdk-compat.yml + scripts/use-ai-sdk-major.mjs) that type-checks and runs Think's workers tests under each major. Verified: 0 typecheck errors and full workers suite passing on both. Generated with [Devin](https://devin.ai) Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>
cjol
force-pushed
the
fix/think-ai-sdk-v6-v7-compat
branch
from
July 14, 2026 15:36
93144a0 to
4c92b98
Compare
agents
@cloudflare/ai-chat
@cloudflare/codemode
create-think
hono-agents
@cloudflare/shell
@cloudflare/think
@cloudflare/voice
@cloudflare/worker-bundler
commit: |
cjol
marked this pull request as ready for review
July 21, 2026 21:16
![devin-ai-integration[bot]](https://avatars.githubusercontent.com/in/811515?s=60&v=4){kind=small}
cjol
added a commit
that referenced
this pull request
Jul 23, 2026
* feat: update AI SDK to v7 This PR updates the repo from AI SDK v6 to v7 across the published packages, examples, guides, experiments, and starters. It migrates the current implementations only: new optimisations or improvements made available by the v7 SDK are intentionally out of scope for this change. ## Why - Consumers need the Agents SDK packages to work with AI SDK v7 and the matching @ai-sdk/* package majors. - A version-only bump was not enough because v7 renamed prompt, stop-condition, lifecycle callback, telemetry, and tool execution APIs used throughout the repo. - We could have renamed the Think-facing API to match v7 directly, but that would add a second API migration on top of the dependency migration. This keeps Think's existing caller-facing names where practical and translates at the AI SDK boundary. - We could have adopted v7-only follow-up improvements like stateless UI message stream helpers, final-step result audits, or media part cleanup here, but those are behaviour and design choices rather than required compatibility fixes. ## Public API Surface | Symbol | Kind | Notes | | ------ | ---- | ----- | | package peer dependencies | Breaking | Published packages now require ai@7 and @ai-sdk/react@4 where applicable. | | @cloudflare/think TurnConfig.experimental_telemetry | Changed | Still accepted, but now typed against the v7 telemetry option. v6 metadata is no longer supported by AI SDK v7. | | @cloudflare/think TurnConfig.telemetry | Additive | Accepted as the v7 option name and forwarded ahead of experimental_telemetry when present. | | @cloudflare/think StepContext | Changed | Still exported under the same name, now derived from GenerateTextOnStepFinishCallback. | | @cloudflare/ai-chat AIChatAgent.onChatMessage | Changed | The onFinish callback type now uses GenerateTextOnFinishCallback. | - Think still exposes system, onStepFinish, and experimental_telemetry as current top-level API names where callers already use them. - Think adapts v7 onToolExecutionEnd events back into the existing ToolCallResultContext shape for afterToolCall hooks and extensions. - ToolCallResultContext.stepNumber is now undefined for tool completion callbacks because AI SDK v7 no longer provides that value on the tool execution end event. ## Code Changes - Dependency ranges move from ai@6 and @ai-sdk/*@3 to ai@7 and @ai-sdk/*@4 across packages, examples, experiments, starters, and the lockfile. - AI SDK call sites use v7 names: instructions instead of system, isStepCount instead of stepCountIs, telemetry instead of experimental_telemetry at the SDK boundary, and onStepEnd or onToolExecutionEnd instead of the old lifecycle callback names. - Think keeps its public turn configuration and hook names stable while translating them into v7 streamText options internally. - Tool schema adapters in agents, codemode, and browser tooling normalize function-valued tool descriptions because downstream connectors still expect string descriptions. - agent-think drops telemetry metadata and uses functionId because AI SDK v7 removed TelemetryOptions.metadata. - forever-chat uses includeRawChunks directly for raw OpenAI response chunk handling. ## Compatibility - Consumers of published packages must install ai@7 and @ai-sdk/*@4-compatible peers. - Code that passed TelemetryOptions.metadata through Think's experimental_telemetry must move that identity into supported v7 telemetry fields or an integration. - Code that relied on stepNumber inside Think tool completion callbacks should treat it as unavailable for v7-backed executions. - This change does not migrate callers to new v7 capabilities beyond what is needed to keep the current implementations working. * chore: add AI SDK v7 changeset * fix: add AI SDK v7 migration aliases * chore(agent-think): adopt AI SDK v7 via workers-ai-provider preview agent-think uses workers-ai-provider's createClientFallbackModel, which had no AI SDK v7 (LanguageModelV4) release on npm (latest 3.3.1 is v6/LanguageModelV3). Pinning agent-think to v6 instead caused a dual ai instance in the monorepo (agent-think on ai@6 vs the workspace think/agents packages on their own ai@7 devDeps), which does not type-check. Point workers-ai-provider at the v7 preview build from cloudflare/ai#601 (https://pkg.pr.new/cloudflare/ai/workers-ai-provider@601) and put agent-think fully on v7 (ai@7, @ai-sdk/*@4). This yields a single ai@7 instance across the workspace and type-checks cleanly. TODO: swap the pkg.pr.new URL for the published workers-ai-provider v7 release once cloudflare/ai#601 lands. * fix(think): consume toUIMessageStream result as async iterable in test helper The AI SDK v7 migration wrapped StreamableResult.toUIMessageStream() in readableStreamToAsyncIterable, changing its return from a ReadableStream to a pure async generator. A test helper in tests/agents/think-session.ts still called getReader() on it, throwing "getReader is not a function" mid-stream. That throw masked the intended simulated error and failed 17 error-handling tests. Consume the stream via its async iterator (next / return) instead, matching the documented AsyncIterable contract. * fix(think): pin CLI augment ai range to v7 to match the basic starter * feat: support both AI SDK v6 and v7 in Think and its dependencies Widen the "ai" peer range to "^6 || ^7" (and "@ai-sdk/react" to "^3 || ^4") across agents, @cloudflare/ai-chat, @cloudflare/codemode, and @cloudflare/think, so consumers can upgrade these packages without being forced onto AI SDK v7. Think now calls the AI SDK through the option names present in both majors (stepCountIs, system, experimental_telemetry, onStepFinish, experimental_onToolCallFinish) and normalizes the genuine divergences at the boundary: - normalizeToolFinishEvent collapses the v6 and v7 tool-execution-finished event shapes into one ToolCallResultContext. - The UI message stream uses the result's toUIMessageStream() method (present in both majors) instead of the v7-only standalone helper + result.stream. - The workspace read tool emits the "file-data" model output content part, which both majors accept (v7's newer "file" shape does not exist in v6). Also fix a v7-migration test regression: a test helper called getReader() on toUIMessageStream()'s result, which became a pure async iterable when readableStreamToAsyncIterable was introduced, masking the intended error and failing 17 error-handling tests. It now consumes the async iterator. Drop the v7-only telemetry test that froze telemetry.integrations behavior (v6 has no such API). Add an ai@6 / ai@7 CI matrix (.github/workflows/ai-sdk-compat.yml + scripts/use-ai-sdk-major.mjs) that type-checks and runs Think's workers tests under each major. Verified: 0 typecheck errors and full workers suite passing on both. Generated with [Devin](https://devin.ai) Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com> * feat: support both AI SDK v6 and v7 in Think and its dependencies (#1940) Widen the "ai" peer range to "^6 || ^7" (and "@ai-sdk/react" to "^3 || ^4") across agents, @cloudflare/ai-chat, @cloudflare/codemode, and @cloudflare/think, so consumers can upgrade these packages without being forced onto AI SDK v7. Think now calls the AI SDK through the option names present in both majors (stepCountIs, system, experimental_telemetry, onStepFinish, experimental_onToolCallFinish) and normalizes the genuine divergences at the boundary: - normalizeToolFinishEvent collapses the v6 and v7 tool-execution-finished event shapes into one ToolCallResultContext. - The UI message stream uses the result's toUIMessageStream() method (present in both majors) instead of the v7-only standalone helper + result.stream. - The workspace read tool emits the "file-data" model output content part, which both majors accept (v7's newer "file" shape does not exist in v6). Also fix a v7-migration test regression: a test helper called getReader() on toUIMessageStream()'s result, which became a pure async iterable when readableStreamToAsyncIterable was introduced, masking the intended error and failing 17 error-handling tests. It now consumes the async iterator. Drop the v7-only telemetry test that froze telemetry.integrations behavior (v6 has no such API). Add an ai@6 / ai@7 CI matrix (.github/workflows/ai-sdk-compat.yml + scripts/use-ai-sdk-major.mjs) that type-checks and runs Think's workers tests under each major. Verified: 0 typecheck errors and full workers suite passing on both. Generated with [Devin](https://devin.ai) Co-authored-by: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix: update Workers AI provider for AI SDK v7 --------- Co-authored-by: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com> Co-authored-by: agent-think[bot] <agent-think[bot]@users.noreply.github.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Warning
Do not merge until cloudflare/ai#601 (
workers-ai-providerAI SDK v7 support) is released.agent-thinkdepends on apkg.pr.newpreview build ofworkers-ai-provider(inherited from the base branchfix/jul9-ai-sdk-v7). Thepkg.pr.newURL must be replaced with the publishedworkers-ai-providerrelease before this reachesmain.This PR makes
@cloudflare/think,agents,@cloudflare/ai-chat, and@cloudflare/codemodesupport both AI SDK v6 and v7, rather than the v7-only cutover in #1922. It stacks on #1922 (base branchfix/jul9-ai-sdk-v7) and is offered as an alternative: take #1922 for a clean v7-only move, or this PR to keep v6 working too.Why
aiand@ai-sdk/*majors in lockstep.@cloudflare/ai-chatand@cloudflare/thinkdeclareaias a required peer, so on npm 7+ a consumer staying on v6 hits anERESOLVEinstall failure, not a warning.system,stepCountIs,experimental_telemetry,onStepFinish,experimental_onToolCallFinish), so calling the SDK through the shared names lets one code path serve both majors without a compile-time fork..d.tsis compiled against one major; consumers get correct types for whicheveraithey install, and the runtime is correct for both.Public API Surface
aipeer range^7.0.0to^6.0.0 || ^7.0.0onagents,@cloudflare/ai-chat,@cloudflare/codemode,@cloudflare/think. Additive: v7 consumers unaffected.@ai-sdk/reactpeer range^4.0.0to^3.0.0 || ^4.0.0onagents,@cloudflare/ai-chat,@cloudflare/think.No exported symbols are added or removed. The change is to peer acceptance ranges only.
Code Changes
@cloudflare/thinkcallsstreamTextthrough the names present in both majors:system,stepCountIs,experimental_telemetry,onStepFinish, andexperimental_onToolCallFinish. In v7 the last resolves internally toonToolExecutionEndand fires once, so there is no double dispatch.normalizeToolFinishEventcollapses the two tool-execution-finished event shapes ({ success, output, error, durationMs, stepNumber }in v6,{ toolOutput, toolExecutionMs }in v7) into oneToolCallResultContextsoafterToolCalland extensions are version-agnostic.toUIMessageStream()method, which exists in both majors. The standalonetoUIMessageStream({ stream })helper andresult.streamare v7-only.file-datamodel-output content part, accepted by both majors. v7's newer{ type: "file", data: { type: "data", data } }shape does not exist in v6..getReader()ontoUIMessageStream()'s result, which became a pure async iterable whenreadableStreamToAsyncIterablewas introduced in the v7 migration. The resulting throw masked the intended error and failed 17 error-handling tests. It now consumes the async iterator.telemetry.integrationscallback API, which does not exist in v6, to avoid freezing v7-only behaviour..github/workflows/ai-sdk-compat.ymlandscripts/use-ai-sdk-major.mjs: a matrix that installs eachaimajor and runs@cloudflare/think's typecheck and workers tests under both.Compatibility
ai@6/@ai-sdk/*@3or move toai@7/@ai-sdk/*@4. Bumping these packages no longer forces an AI SDK major upgrade.workers-ai-provider(Think's default model provider) has no v7 release yet, so a consumer onai@6who relies on Think's built-in default model may hit a provider-version mismatch. Passing an explicitLanguageModelavoids this.agent-think(private, not published) uses theworkers-ai-providerv7 preview from Add support for AI SDK 7 ai#601 and must be repointed at the release before merge, per the warning above.