chore(deps): bump agents from 0.7.9 to 0.12.3

[dependabot]

Bumps agents from 0.7.9 to 0.12.3.

Release notes

Sourced from agents's releases.

agents@0.12.3

Patch Changes

• #1451 48b29ba Thanks @​threepointone! - Fix typed call and stub support for streaming callable methods.

agents@0.12.2

Patch Changes

• 2fffa02 Thanks @​threepointone! - Raise the minimum internal peer dependency versions for Agents chat packages so agents, @cloudflare/ai-chat, and @cloudflare/think require versions at least as recent as the current repo packages.

agents@0.12.1

Patch Changes

• #1443 e7d225b Thanks @​threepointone! - Fix sub-agent WebSockets on deployed Workers by keeping the browser WebSocket owned by the parent Agent and forwarding connect/message/close events to child facets over RPC.

  Fix resumed chat streams so a partially hydrated assistant response is rebuilt from replay chunks instead of rendering replayed text as a second assistant text part.

  Fix a resume ACK race where drill-in chat connections could miss the terminal stream frame if the helper completed between the resume notification and client acknowledgement.

agents@0.12.0

Minor Changes

• #1421 1b65ff5 Thanks @​threepointone! - Add agent tool orchestration for running Think and AIChatAgent sub-agents as retained, streaming tools from a parent agent. The new surface includes runAgentTool, agentTool, parent-side run replay and cleanup, Think and AIChatAgent child adapter support, and headless React/client event state helpers.

Patch Changes

• #1418 8de0ce3 Thanks @​threepointone! - Allow sub-agents to use alarm-backed APIs by delegating the physical Durable Object alarm to the top-level parent while executing logical work inside the owning sub-agent. This enables schedule(), scheduleEvery(), cancelSchedule(), getScheduleById(), listSchedules(), keepAlive(), keepAliveWhile(), runFiber(), and Think chat recovery inside sub-agents.

  Sub-agent schedules are scoped to the calling child, so sibling sub-agents cannot cancel each other's schedules by id. The deprecated synchronous getSchedule() and getSchedules() APIs now throw inside sub-agents; use the async alternatives instead. Destroying a sub-agent now delegates cleanup through the parent so parent-owned schedules and descendant fiber recovery leases are removed consistently.

• #1425 6471cbd Thanks @​threepointone! - Clear request, WebSocket, and email native context handles when switching Agent instances and suppress protocol broadcasts during sub-agent facet bootstrap.

agents@0.11.9

Patch Changes

• #1412 8fb7c03 Thanks @​threepointone! - Make applyChunkToParts idempotent against an existing tool part with the same toolCallId, and add isReplayChunk(parts, chunk) for stream broadcasters that want to drop provider replay chunks (#1404).

  Some providers (notably the OpenAI Responses API) re-emit a prior tool call in continuation streams. The previous tool-input-start handler unconditionally pushed a fresh tool part, which produced duplicate parts in the message; tool-input-delta and tool-input-available overwrote a fully resolved input/state if a chunk happened to arrive for an already-known toolCallId. The new behavior:

  • tool-input-start for a toolCallId that already exists in parts is a no-op (it does not push a duplicate or regress state).
  • tool-input-delta only mutates input while the existing part is still input-streaming.
  • tool-input-available only advances from input-streaming to input-available; replays against parts that have already moved past input-streaming (including approval-requested/approval-responded and any terminal state) are no-ops.

  isReplayChunk(parts, chunk) is exported from agents/chat for stream broadcasters (e.g. AIChatAgent._streamSSEReply) that want to detect "this chunk is a replay of an already-known tool call" and skip re-broadcasting it. AI SDK v6's updateToolPart on the client mutates an existing tool part in place when the toolCallId matches, so re-broadcasting these replay chunks would visibly regress an output-available part to input-streaming on connected clients. tool-output-available is not treated as a replay because its in-place update is safe when the output already matches.

  Tool calls that the model genuinely wants to re-issue always carry a new toolCallId, so an existing match is never a legitimate "start over".

... (truncated)

Changelog

Sourced from agents's changelog.

0.12.3

Patch Changes

• #1451 48b29ba Thanks @​threepointone! - Fix typed call and stub support for streaming callable methods.

0.12.2

Patch Changes

• 2fffa02 Thanks @​threepointone! - Raise the minimum internal peer dependency versions for Agents chat packages so agents, @cloudflare/ai-chat, and @cloudflare/think require versions at least as recent as the current repo packages.

0.12.1

Patch Changes

• #1443 e7d225b Thanks @​threepointone! - Fix sub-agent WebSockets on deployed Workers by keeping the browser WebSocket owned by the parent Agent and forwarding connect/message/close events to child facets over RPC.

  Fix resumed chat streams so a partially hydrated assistant response is rebuilt from replay chunks instead of rendering replayed text as a second assistant text part.

  Fix a resume ACK race where drill-in chat connections could miss the terminal stream frame if the helper completed between the resume notification and client acknowledgement.

0.12.0

Minor Changes

• #1421 1b65ff5 Thanks @​threepointone! - Add agent tool orchestration for running Think and AIChatAgent sub-agents as retained, streaming tools from a parent agent. The new surface includes runAgentTool, agentTool, parent-side run replay and cleanup, Think and AIChatAgent child adapter support, and headless React/client event state helpers.

Patch Changes

• #1418 8de0ce3 Thanks @​threepointone! - Allow sub-agents to use alarm-backed APIs by delegating the physical Durable Object alarm to the top-level parent while executing logical work inside the owning sub-agent. This enables schedule(), scheduleEvery(), cancelSchedule(), getScheduleById(), listSchedules(), keepAlive(), keepAliveWhile(), runFiber(), and Think chat recovery inside sub-agents.

  Sub-agent schedules are scoped to the calling child, so sibling sub-agents cannot cancel each other's schedules by id. The deprecated synchronous getSchedule() and getSchedules() APIs now throw inside sub-agents; use the async alternatives instead. Destroying a sub-agent now delegates cleanup through the parent so parent-owned schedules and descendant fiber recovery leases are removed consistently.

• #1425 6471cbd Thanks @​threepointone! - Clear request, WebSocket, and email native context handles when switching Agent instances and suppress protocol broadcasts during sub-agent facet bootstrap.

0.11.9

Patch Changes

• #1412 8fb7c03 Thanks @​threepointone! - Make applyChunkToParts idempotent against an existing tool part with the same toolCallId, and add isReplayChunk(parts, chunk) for stream broadcasters that want to drop provider replay chunks (#1404).

  Some providers (notably the OpenAI Responses API) re-emit a prior tool call in continuation streams. The previous tool-input-start handler unconditionally pushed a fresh tool part, which produced duplicate parts in the message; tool-input-delta and tool-input-available overwrote a fully resolved input/state if a chunk happened to arrive for an already-known toolCallId. The new behavior:

  • tool-input-start for a toolCallId that already exists in parts is a no-op (it does not push a duplicate or regress state).
  • tool-input-delta only mutates input while the existing part is still input-streaming.

... (truncated)

Commits

• b1523e8 Version Packages (#1452)
• 48b29ba Fix streaming callable client types (#1451)
• a25b535 Version Packages (#1444)
• 2fffa02 update deps
• aef678f Version Packages (#1438)
• e7d225b Fix sub-agent WebSocket forwarding (#1443)
• cdf203a Add identification check inside waitFor
• 6d67c7b Update deps, add playground demos, a11y fixes
• bde99ae Version Packages (#1419)
• 6471cbd Fix sub-agent bootstrap from WebSocket messages (#1425)
• 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]

Superseded by #27.