Version Packages

[github-actions]

This PR was opened by the Changesets release GitHub action. When you're ready to do a release, you can merge this and the packages will be published to npm automatically. If you're not ready to do a release yet, that's fine, whenever you add more changesets to main, this PR will be updated.

Releases

agents@0.22.0

Minor Changes

• #2071 9620b58 Thanks @ben-reitz! - Make durable chat recovery unconditional for AIChatAgent and Think.

  Every chat turn now runs in a recovery fiber, including WebSocket, programmatic, retry, and continuation paths. chatRecovery accepts true or a configuration object; false is no longer supported. Previously compiled JavaScript that still supplies false safely receives the default recovery configuration.

  To keep durable bookkeeping while preventing automatic inference after an interruption, return { continue: false } from onChatRecovery(). Use durable cancellation, side-effect, or spend state in that hook and tune chatRecovery budgets when retries must be bounded.

• #2133 d536067 Thanks @mattzcarey! - Vendor the required PartyServer runtime into agents/lifecycle and add a reusable Durable Object lifecycle for startup, request interception, alarms, and WebSockets. Agent now directly extends Cloudflare's DurableObject and composes the same lifecycle used by standalone objects; standalone hosts use the explicit Lifecycle.install(this) factory (or the expanded new ... plus installHandlers() form). Both Agent subclasses and standalone hosts use the existing routeAgentRequest() API and /agents URL prefix; the lifecycle entry point does not introduce a second public router.

  Lifecycle WebSockets always use Cloudflare's Hibernation API; the static options.hibernate switch and in-memory connection mode are removed. Named Durable Objects use native ctx.id.name, while a read-only __ps_name fallback migrates objects created by older releases without writing new compatibility state.

• #2058 381b9bb Thanks @ben-reitz! - Throttle chat UI updates by default in useAgentChat

  Streaming writes chat state once per chunk, and each write re-renders. When
  chunks arrive in a burst — a resumed stream replaying a long turn, for
  example — React reaches its 50-render limit and throws "Maximum update depth
  exceeded", which the AI SDK reports as a failed turn even though the server
  completed it (#1913).

  useAgentChat now coalesces those updates every 50ms, which removes about 78%
  of renders on a fast stream and matches the value the AI SDK documents. The
  first chunk of a stream is never delayed. Pass throttle: false to render
  every chunk as it arrives, or a number to change the interval. The deprecated
  experimental_throttle is still honoured. Message snapshots, functional
  updates, and streamed continuations resolve against the current chat store, so
  coalescing renders cannot roll assistant content back to an older snapshot.

• #2161 ded09c6 Thanks @mattzcarey! - Remove the published agents command-line binary. Its advertised init, dev, deploy, and mcp commands were placeholders that printed "not implemented yet" and exited successfully. Use the documented C3 starter, Vite and Wrangler commands, and MCP APIs instead.

• #1895 4ba9a37 Thanks @mattzcarey! - Make MCPClientManager a reusable Durable Object lifecycle capability. It now owns schema initialization, persisted HTTP and RPC connection restoration, and OAuth callback interception when installed with Lifecycle.use(), while preserving Agent.this.mcp and the existing Agent MCP APIs. agents/lifecycle exports the LifecycleObject host interface and canonical getCurrentAgent() accessor; Lifecycle supplies that context to host hooks while capability hooks remain self-contained.

Patch Changes

• #2027 e87ad62 Thanks @cjol! - Route asynchronous callable and streaming responses through the facet WebSocket frame that originated each RPC.

• #1978 b7c7696 Thanks @Ankcorn! - Add Agents SDK instrumentation and agent instance identity attributes to SDK-created spans.

• #2050 3b43c33 Thanks @ben-reitz! - Batch replayed chunks during stream resume so long turns do not exceed React's
  update limit and report a false error.

• #2120 b038440 Thanks @ben-reitz! - Keep Session compaction overlays scoped to their selected conversation branch and preserve deterministic ordering for overlays created in the same second.

• #2090 2f957bc Thanks @ben-reitz! - Keep sub-agent WebSocket operations routable and ordered across live and delayed contexts and before broadcasts, report routing failures, and preserve nested sub-agent broadcasts across RPC callbacks.

• #2131 bf94bb2 Thanks @ben-reitz! - Fall back to no-op tracing when an older Workers runtime exposes tracing without startActiveSpan, preventing Agent initialization from failing.

@cloudflare/ai-chat@0.11.0

Minor Changes

• #2071 9620b58 Thanks @ben-reitz! - Make durable chat recovery unconditional for AIChatAgent and Think.

  Every chat turn now runs in a recovery fiber, including WebSocket, programmatic, retry, and continuation paths. chatRecovery accepts true or a configuration object; false is no longer supported. Previously compiled JavaScript that still supplies false safely receives the default recovery configuration.

  To keep durable bookkeeping while preventing automatic inference after an interruption, return { continue: false } from onChatRecovery(). Use durable cancellation, side-effect, or spend state in that hook and tune chatRecovery budgets when retries must be bounded.

@cloudflare/channels@0.1.0

Minor Changes

• #2129 4890dc6 Thanks @cjol! - Add the experimental @cloudflare/channels package: one transport-neutral way to receive and send messages over Slack, Telegram, email, and channels of your own.

  A stateless ChannelHost authenticates and normalizes provider input, and your application decides where each event belongs and how to store it. Outbound delivery reports honest per-attempt outcomes, approvals can be rendered natively by each provider, and channel identities can be linked to your own users.

Patch Changes

• Updated dependencies [f08ee06]:
  • @cloudflare/voice@0.4.0

@cloudflare/think@0.17.0

Minor Changes

• #2071 9620b58 Thanks @ben-reitz! - Make durable chat recovery unconditional for AIChatAgent and Think.

  Every chat turn now runs in a recovery fiber, including WebSocket, programmatic, retry, and continuation paths. chatRecovery accepts true or a configuration object; false is no longer supported. Previously compiled JavaScript that still supplies false safely receives the default recovery configuration.

  To keep durable bookkeeping while preventing automatic inference after an interruption, return { continue: false } from onChatRecovery(). Use durable cancellation, side-effect, or spend state in that hook and tune chatRecovery budgets when retries must be bounded.

Patch Changes

• #2059 d5973c0 Thanks @ben-reitz! - Preserve orphaned durable execution outcomes as framework-authored notes, then project them to user context for inference so provider transcript validation cannot reject their arbitrary position. Existing outcome notes receive the same projection without rewriting stored history.

@cloudflare/voice@0.4.0

Minor Changes

• #2157 f08ee06 Thanks @cjol! - Improve voice lifecycle accuracy, diagnostics, and per-turn timing visibility.

  • Clear stale interim transcripts when calls start, end, disconnect, close, or fail during startup.
  • Emit speaking only when the first server audio chunk is sent.
  • Add structured, content-free browser diagnostics and structured Worker error logging without reading arbitrary provider response bodies.
  • Report transcriber startup and runtime failures through onFatalError, structured client errors, and reliable call cleanup.
  • Preserve model finish reasons and distinguish no-output, output-limit, content-filtered, and model-error completions.
  • Add stable typed per-turn timing summaries for speech, text, terminal outcomes, model streaming, reasoning exposed by the model stream, and overlapping TTS work through VoiceClient and the React hooks.
  • Keep the existing four-field metrics wire shape compatible while making no-audio and streamed TTS accounting consistent.
  • Update the bundled voice providers to propagate lifecycle failures and log errors consistently.

@cloudflare/voice-assemblyai@0.1.0

Minor Changes

• #2157 f08ee06 Thanks @cjol! - Improve voice lifecycle accuracy, diagnostics, and per-turn timing visibility.

  • Clear stale interim transcripts when calls start, end, disconnect, close, or fail during startup.
  • Emit speaking only when the first server audio chunk is sent.
  • Add structured, content-free browser diagnostics and structured Worker error logging without reading arbitrary provider response bodies.
  • Report transcriber startup and runtime failures through onFatalError, structured client errors, and reliable call cleanup.
  • Preserve model finish reasons and distinguish no-output, output-limit, content-filtered, and model-error completions.
  • Add stable typed per-turn timing summaries for speech, text, terminal outcomes, model streaming, reasoning exposed by the model stream, and overlapping TTS work through VoiceClient and the React hooks.
  • Keep the existing four-field metrics wire shape compatible while making no-audio and streamed TTS accounting consistent.
  • Update the bundled voice providers to propagate lifecycle failures and log errors consistently.

@cloudflare/voice-deepgram@0.1.0

Minor Changes

• #2157 f08ee06 Thanks @cjol! - Improve voice lifecycle accuracy, diagnostics, and per-turn timing visibility.

  • Clear stale interim transcripts when calls start, end, disconnect, close, or fail during startup.
  • Emit speaking only when the first server audio chunk is sent.
  • Add structured, content-free browser diagnostics and structured Worker error logging without reading arbitrary provider response bodies.
  • Report transcriber startup and runtime failures through onFatalError, structured client errors, and reliable call cleanup.
  • Preserve model finish reasons and distinguish no-output, output-limit, content-filtered, and model-error completions.
  • Add stable typed per-turn timing summaries for speech, text, terminal outcomes, model streaming, reasoning exposed by the model stream, and overlapping TTS work through VoiceClient and the React hooks.
  • Keep the existing four-field metrics wire shape compatible while making no-audio and streamed TTS accounting consistent.
  • Update the bundled voice providers to propagate lifecycle failures and log errors consistently.

@cloudflare/voice-elevenlabs@0.1.0

Minor Changes

• #2157 f08ee06 Thanks @cjol! - Improve voice lifecycle accuracy, diagnostics, and per-turn timing visibility.

  • Clear stale interim transcripts when calls start, end, disconnect, close, or fail during startup.
  • Emit speaking only when the first server audio chunk is sent.
  • Add structured, content-free browser diagnostics and structured Worker error logging without reading arbitrary provider response bodies.
  • Report transcriber startup and runtime failures through onFatalError, structured client errors, and reliable call cleanup.
  • Preserve model finish reasons and distinguish no-output, output-limit, content-filtered, and model-error completions.
  • Add stable typed per-turn timing summaries for speech, text, terminal outcomes, model streaming, reasoning exposed by the model stream, and overlapping TTS work through VoiceClient and the React hooks.
  • Keep the existing four-field metrics wire shape compatible while making no-audio and streamed TTS accounting consistent.
  • Update the bundled voice providers to propagate lifecycle failures and log errors consistently.

@cloudflare/voice-telnyx@0.1.0

Minor Changes

• #2157 f08ee06 Thanks @cjol! - Improve voice lifecycle accuracy, diagnostics, and per-turn timing visibility.

  • Clear stale interim transcripts when calls start, end, disconnect, close, or fail during startup.
  • Emit speaking only when the first server audio chunk is sent.
  • Add structured, content-free browser diagnostics and structured Worker error logging without reading arbitrary provider response bodies.
  • Report transcriber startup and runtime failures through onFatalError, structured client errors, and reliable call cleanup.
  • Preserve model finish reasons and distinguish no-output, output-limit, content-filtered, and model-error completions.
  • Add stable typed per-turn timing summaries for speech, text, terminal outcomes, model streaming, reasoning exposed by the model stream, and overlapping TTS work through VoiceClient and the React hooks.
  • Keep the existing four-field metrics wire shape compatible while making no-audio and streamed TTS accounting consistent.
  • Update the bundled voice providers to propagate lifecycle failures and log errors consistently.

@cloudflare/voice-plivo@0.1.1

Patch Changes

• #2157 f08ee06 Thanks @cjol! - Improve voice lifecycle accuracy, diagnostics, and per-turn timing visibility.

  • Clear stale interim transcripts when calls start, end, disconnect, close, or fail during startup.
  • Emit speaking only when the first server audio chunk is sent.
  • Add structured, content-free browser diagnostics and structured Worker error logging without reading arbitrary provider response bodies.
  • Report transcriber startup and runtime failures through onFatalError, structured client errors, and reliable call cleanup.
  • Preserve model finish reasons and distinguish no-output, output-limit, content-filtered, and model-error completions.
  • Add stable typed per-turn timing summaries for speech, text, terminal outcomes, model streaming, reasoning exposed by the model stream, and overlapping TTS work through VoiceClient and the React hooks.
  • Keep the existing four-field metrics wire shape compatible while making no-audio and streamed TTS accounting consistent.
  • Update the bundled voice providers to propagate lifecycle failures and log errors consistently.

@cloudflare/voice-twilio@0.0.3

Patch Changes

• #2157 f08ee06 Thanks @cjol! - Improve voice lifecycle accuracy, diagnostics, and per-turn timing visibility.

  • Clear stale interim transcripts when calls start, end, disconnect, close, or fail during startup.
  • Emit speaking only when the first server audio chunk is sent.
  • Add structured, content-free browser diagnostics and structured Worker error logging without reading arbitrary provider response bodies.
  • Report transcriber startup and runtime failures through onFatalError, structured client errors, and reliable call cleanup.
  • Preserve model finish reasons and distinguish no-output, output-limit, content-filtered, and model-error completions.
  • Add stable typed per-turn timing summaries for speech, text, terminal outcomes, model streaming, reasoning exposed by the model stream, and overlapping TTS work through VoiceClient and the React hooks.
  • Keep the existing four-field metrics wire shape compatible while making no-audio and streamed TTS accounting consistent.
  • Update the bundled voice providers to propagate lifecycle failures and log errors consistently.

@cloudflare/agent-think@0.0.7

Patch Changes

• Updated dependencies [e87ad62, d5973c0, b7c7696, 9620b58, 3b43c33, b038440, 2f957bc, d536067, bf94bb2, 381b9bb, ded09c6, 4ba9a37]:
  • agents@0.22.0
  • @cloudflare/think@0.17.0
  • @cloudflare/ai-chat@0.11.0

---

[devin-ai-integration]

✅ Devin Review: No Issues Found

Devin Review analyzed this PR and found no bugs or issues to report.

[pkg-pr-new]

Open in StackBlitz

agents

npm i https://pkg.pr.new/agents@2128

@cloudflare/ai-chat

npm i https://pkg.pr.new/@cloudflare/ai-chat@2128

@cloudflare/codemode

npm i https://pkg.pr.new/@cloudflare/codemode@2128

hono-agents

npm i https://pkg.pr.new/hono-agents@2128

@cloudflare/shell

npm i https://pkg.pr.new/@cloudflare/shell@2128

@cloudflare/think

npm i https://pkg.pr.new/@cloudflare/think@2128

@cloudflare/voice

npm i https://pkg.pr.new/@cloudflare/voice@2128

@cloudflare/worker-bundler

npm i https://pkg.pr.new/@cloudflare/worker-bundler@2128

commit: 4a82c94

[devin-ai-integration]

✅ Devin Review: No Issues Found

Devin Review analyzed this PR and found no bugs or issues to report.