[dependabot]

Bumps @cloudflare/ai-chat from 0.9.4 to 0.12.1.

Release notes

Sourced from @​cloudflare/ai-chat's releases.

@​cloudflare/ai-chat@​0.12.1

Patch Changes

• #2390 c55ec80 Thanks @​threepointone! - Report a failed agent-tool child as failed even when it was evicted before recording the failure. See Agent tools.

• #2384 f904999 Thanks @​threepointone! - Fix agent-tool chunks being duplicated or dropped on reconnect, child re-attach, and fiber recovery. See Agent tools.

• #2364 5e0507e Thanks @​threepointone! - Add eventDelivery: "terminal" to runAgentTool to forward only lifecycle, progress, and milestone events for a run. See Agent tools.

• #2334 7f564e7 Thanks @​threepointone! - AI Chat and Think send the terminal done frame after persisting and broadcasting the assistant reply, so later sends are not overwritten. See Chat agents.

• #2352 449ac27 Thanks @​threepointone! - Do not start an automatic continuation after an active stream finishes with a normal assistant response. See Client-side tools and auto-continuation.

• #2360 7206134 Thanks @​threepointone! - AI Chat recovers from transient response-reader errors instead of ending the turn, and respects recovery persistence choices without joining stale recovery runs. See Chat agents.

• #2391 d3fe93c Thanks @​threepointone! - Keep a tool call's input when its approval request arrives before the input finishes streaming (#1872). See Human in the loop.

• #2408 6c8f85a Thanks @​threepointone! - Require agents@>=0.25.0 so Think and AI Chat can import the chat helpers provided by that release.

• #2378 dbf170c Thanks @​threepointone! - useAgentChat gains onTurnEnd, and terminal chat frames carry outcomes and user message IDs so clients can settle sends correctly across recovery and reconnects. Replay, tool callbacks, and turn state now remain consistent through terminal delivery; see Chat agents.

• #2393 a7d0e02 Thanks @​threepointone! - Continuation turns that fail before streaming now report an error to clients and onChatResponse instead of appearing to hang (#2381). See Client tools.

• #2238 c3a4010 Thanks @​mattzcarey! - Interfaces can now be used as Props on Agent, AIChatAgent, Think, and routing helpers. See Routing.

• #2040 2afe0e0 Thanks @​AntoniTok! - Keep assistant messages and tool outputs attached to the correct turn when a provider reuses a toolCallId; resolveToolMergeId is deprecated in favour of reconcileMessages. See Chat agents.

• #2348 39361fa Thanks @​threepointone! - Fix text appearing twice when reconnecting during a tool continuation. See Resumable streaming.

• #2404 9d125c8 Thanks @​threepointone! - Add session.mirror() to keep an in-memory transcript in sync with a session's change feed. See Sessions.

• #2392 4f26402 Thanks @​threepointone! - Settle approved tool calls that never ran once the conversation moves past them, so later turns don't send unresolved tool calls (#2382). See Human in the loop.

@​cloudflare/ai-chat@​0.12.0

Minor Changes

• #2196 ec93caf Thanks @​mattzcarey! - Store AIChatAgent messages through agents/sessions while preserving the mutable messages array, destructive regeneration, retention, broadcasts, and v4 message conversion.

  Migration on first wake, no rollback. Existing cf_ai_chat_agent_messages rows are imported once into a linear Sessions chain. The old table is dropped only after every row imported; a row that fails to parse keeps the table in place so it stays recoverable, and the import retries on the next start. Once an object has migrated, rolling back to the previous release leaves it with an empty conversation. Rolling forward again is safe.

  this.messages is empty until onStart. Boot no longer loads the transcript synchronously in the constructor. The legacy lift and a single bounded hydration run in onStart, so a subclass that read this.messages in its constructor now sees []; read it from onStart or later. The array is then mirrored from the Sessions change feed.

  hydrationByteBudget (32 MiB) bounds wake-time hydration. maxPersistedMessages counts stored rows rather than the hydrated window, so retention trims the oldest stored messages even when the transcript is larger than the budget. get-messages streams its response instead of serializing the whole transcript; clients calling .json() on it are unaffected.

  There is nothing to configure about how a message is stored: a message too large for one SQLite row is split across continuation rows and reassembled on read, and a stored row is exactly what the write returned.

• #2216 dd09d44 Thanks @​mattzcarey! - feat(streams): rollover block log and an atomic stream → message cutover; no more stream-buffer sweeps.

  The Streams chunk log is now mutable rollover blocks: an append grows the open block row (an UPDATE) until it reaches 256 KB, then opens the next. Same one billed row per append as before, but a stream of thousands of chunks is a handful of rows to delete instead of thousands. Existing cf_agents_stream_chunks rows are folded into blocks lazily, one stream at a time on first touch, so startup never reads the whole legacy log; the table is dropped once it is empty.

... (truncated)

Changelog

Sourced from @​cloudflare/ai-chat's changelog.

0.12.1

Patch Changes

• #2390 c55ec80 Thanks @​threepointone! - Report a failed agent-tool child as failed even when it was evicted before recording the failure. See Agent tools.

• #2384 f904999 Thanks @​threepointone! - Fix agent-tool chunks being duplicated or dropped on reconnect, child re-attach, and fiber recovery. See Agent tools.

• #2364 5e0507e Thanks @​threepointone! - Add eventDelivery: "terminal" to runAgentTool to forward only lifecycle, progress, and milestone events for a run. See Agent tools.

• #2334 7f564e7 Thanks @​threepointone! - AI Chat and Think send the terminal done frame after persisting and broadcasting the assistant reply, so later sends are not overwritten. See Chat agents.

• #2352 449ac27 Thanks @​threepointone! - Do not start an automatic continuation after an active stream finishes with a normal assistant response. See Client-side tools and auto-continuation.

• #2360 7206134 Thanks @​threepointone! - AI Chat recovers from transient response-reader errors instead of ending the turn, and respects recovery persistence choices without joining stale recovery runs. See Chat agents.

• #2391 d3fe93c Thanks @​threepointone! - Keep a tool call's input when its approval request arrives before the input finishes streaming (#1872). See Human in the loop.

• #2408 6c8f85a Thanks @​threepointone! - Require agents@>=0.25.0 so Think and AI Chat can import the chat helpers provided by that release.

• #2378 dbf170c Thanks @​threepointone! - useAgentChat gains onTurnEnd, and terminal chat frames carry outcomes and user message IDs so clients can settle sends correctly across recovery and reconnects. Replay, tool callbacks, and turn state now remain consistent through terminal delivery; see Chat agents.

• #2393 a7d0e02 Thanks @​threepointone! - Continuation turns that fail before streaming now report an error to clients and onChatResponse instead of appearing to hang (#2381). See Client tools.

• #2238 c3a4010 Thanks @​mattzcarey! - Interfaces can now be used as Props on Agent, AIChatAgent, Think, and routing helpers. See Routing.

• #2040 2afe0e0 Thanks @​AntoniTok! - Keep assistant messages and tool outputs attached to the correct turn when a provider reuses a toolCallId; resolveToolMergeId is deprecated in favour of reconcileMessages. See Chat agents.

• #2348 39361fa Thanks @​threepointone! - Fix text appearing twice when reconnecting during a tool continuation. See Resumable streaming.

• #2404 9d125c8 Thanks @​threepointone! - Add session.mirror() to keep an in-memory transcript in sync with a session's change feed. See Sessions.

• #2392 4f26402 Thanks @​threepointone! - Settle approved tool calls that never ran once the conversation moves past them, so later turns don't send unresolved tool calls (#2382). See Human in the loop.

0.12.0

Minor Changes

• #2196 ec93caf Thanks @​mattzcarey! - Store AIChatAgent messages through agents/sessions while preserving the mutable messages array, destructive regeneration, retention, broadcasts, and v4 message conversion.

  Migration on first wake, no rollback. Existing cf_ai_chat_agent_messages rows are imported once into a linear Sessions chain. The old table is dropped only after every row imported; a row that fails to parse keeps the table in place so it stays recoverable, and the import retries on the next start. Once an object has migrated, rolling back to the previous release leaves it with an empty conversation. Rolling forward again is safe.

  this.messages is empty until onStart. Boot no longer loads the transcript synchronously in the constructor. The legacy lift and a single bounded hydration run in onStart, so a subclass that read this.messages in its constructor now sees []; read it from onStart or later. The array is then mirrored from the Sessions change feed.

  hydrationByteBudget (32 MiB) bounds wake-time hydration. maxPersistedMessages counts stored rows rather than the hydrated window, so retention trims the oldest stored messages even when the transcript is larger than the budget. get-messages streams its response instead of serializing the whole transcript; clients calling .json() on it are unaffected.

  There is nothing to configure about how a message is stored: a message too large for one SQLite row is split across continuation rows and reassembled on read, and a stored row is exactly what the write returned.

• #2216 dd09d44 Thanks @​mattzcarey! - feat(streams): rollover block log and an atomic stream → message cutover; no more stream-buffer sweeps.

... (truncated)

Commits

• 995ed8b Version Packages
• d5562e0 fix: #2013 - correctly invoke controller.error during mid-stream closure and ...
• 2afe0e0 fix(chat): reconcile reused tool-call IDs one-to-one (#2040)
• 6c8f85a fix(think,ai-chat): raise agents peer floor to >=0.25.0 (#2408)
• 9d125c8 fix(sessions): share the change-feed mirror between hosts (#2205) (#2404)
• c3a4010 fix: allow interfaces as agent props (#2238)
• a7d0e02 fix: report continuation turns that fail before streaming (#2381) (#2393)
• 4f26402 fix(agents,ai-chat,think): settle approved tool calls that never ran (#2382) ...
• d3fe93c fix: keep tool input when the approval request arrives before it (#1872) (#2391)
• c55ec80 fix(ai-chat,think): keep a child's stream error across eviction so reconcilia...
• Additional commits viewable in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

---

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

• @dependabot rebase will rebase this PR
• @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
• @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
• @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)

[dependabot]

Labels

The following labels could not be found: dependencies. Please create it before Dependabot can add it to a pull request.

Please fix the above issues or remove invalid values from dependabot.yml.

[dependabot]

Superseded by #39.