fix(generation): preserve LLM-supplied call_id instead of overwriting with item id

[toubatbrian]

Summary

voice/generation.ts was overwriting the LLM-supplied callId with the generation's per-item UUID. Python keeps these two identifiers distinct (id = framework item id, call_id = the LLM's identifier that pairs function_call ↔ function_call_output). This change restores that separation, matching livekit-agents/.../generation.py:170-176.

// before
const toolCall = FunctionCall.create({
  callId: `${data.id}/fnc_${data.generatedToolCalls.length}`,
  name: tool.name,
  args: tool.args,
  ...
});

// after
const toolCall = FunctionCall.create({
  id: `${data.id}/fnc_${data.generatedToolCalls.length}`,
  callId: tool.callId,
  name: tool.name,
  args: tool.args,
  ...
});

Also fixes examples/src/testing/basic_task_group.test.ts > summarizeChatCtx, which was failing because its FakeLLM mock used the old pre-XML prompt format and [history summary] literal. Updated to match what ChatContext._summarize actually emits; now deterministic since fake_call_0 survives end-to-end.

Why this matters

Downstream providers (OpenAI, Anthropic, Gemini, etc.) emit their own tool_call_id that we must echo back in function_call_output so the provider can correlate the call. Overwriting it silently inverted the invariant from Python.

Test plan

• pnpm build:agents && pnpm vitest run examples/src/testing examples/src/frontdesk/test_agent.test.ts examples/src/drive-thru/test_agent.test.ts — 75/75 pass (was 74/75)
• Full pnpm test — no new regressions; remaining failures (AMD logic, plugin TTS VAD setup, missing API keys) reproduce on main

[changeset-bot]

🦋 Changeset detected

Latest commit: a6fa864

The changes in this PR will be included in the next version bump.

This PR includes changesets to release 31 packages

Name	Type
@livekit/agents	Patch
@livekit/agents-plugin-anam	Patch
@livekit/agents-plugin-assemblyai	Patch
@livekit/agents-plugin-baseten	Patch
@livekit/agents-plugin-bey	Patch
@livekit/agents-plugin-cartesia	Patch
@livekit/agents-plugin-cerebras	Patch
@livekit/agents-plugin-deepgram	Patch
@livekit/agents-plugin-elevenlabs	Patch
@livekit/agents-plugin-fishaudio	Patch
@livekit/agents-plugin-google	Patch
@livekit/agents-plugin-hedra	Patch
@livekit/agents-plugin-hume	Patch
@livekit/agents-plugin-inworld	Patch
@livekit/agents-plugin-lemonslice	Patch
@livekit/agents-plugin-liveavatar	Patch
@livekit/agents-plugin-livekit	Patch
@livekit/agents-plugin-minimax	Patch
@livekit/agents-plugin-mistral	Patch
@livekit/agents-plugin-mistralai	Patch
@livekit/agents-plugin-neuphonic	Patch
@livekit/agents-plugin-openai	Patch
@livekit/agents-plugin-phonic	Patch
@livekit/agents-plugin-resemble	Patch
@livekit/agents-plugin-rime	Patch
@livekit/agents-plugin-runway	Patch
@livekit/agents-plugin-sarvam	Patch
@livekit/agents-plugin-silero	Patch
@livekit/agents-plugins-test	Patch
@livekit/agents-plugin-trugen	Patch
@livekit/agents-plugin-xai	Patch

Not sure what this means? Click here to learn what changesets are.

Click here if you're a maintainer who wants to add another changeset to this PR

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: a6fa86460f

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

[devin-ai-integration]

✅ Devin Review: No Issues Found

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

View in Devin Review to see 2 additional findings.