fix(agents): stop forwarding frame processor info

[rosetta-livekit-bot]

Summary

• Port Move frame processor url/token/stream info to client sdk agents#5867 behavior to agents-js room input handling
• Stop manually forwarding frame processor stream info and LiveKit credentials from agents room I/O
• Remove token refresh listener registration tied to those manual credential updates

Testing

• pnpm exec tsc -p agents/tsconfig.json --noEmit
• pnpm test agents/src/voice/room_io/room_io.test.ts

---

Ported from livekit/agents#5867

Original PR description

Delegate sending stream info to the frame processor to the client sdk AudioStream instead of doing it all at the agents sdk level.

Depends on livekit/python-sdks#679 - all the FrameProcessor-related code removed in here has been moved into the underlying python sdk.

TODO

• Be sure Fully configure frame processors when they are used directly on an audio stream python-sdks#679 is merged before eventually merging this one
• Bump version of python-sdks to the ^ above, which will fix the ci build error
• Run this through the full battery of tests (just did a happy path test for now)

[changeset-bot]

🦋 Changeset detected

Latest commit: 61bff05

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

This PR includes changesets to release 35 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-did	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-perplexity	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-plugin-soniox	Patch
@livekit/agents-plugin-tavus	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

[1egoman]

Duplicate of #1881, closing.

[devin-ai-integration]

Devin Review found 1 potential issue.

[devin-ai-integration]

🚩 FrameProcessor no longer receives stream context or credentials after track subscription

The removed code at agents/src/voice/room_io/_input.ts:155-164 (old lines) forwarded participant identity, room name, publication SID, token, and server URL to the FrameProcessor whenever a new track was subscribed, and refreshed credentials on token refresh. After this PR, the FrameProcessor still receives audio frames via AudioStream (agents/src/voice/room_io/_input.ts:159-164), but it no longer has access to the stream metadata or LiveKit credentials. If any FrameProcessor implementation (e.g., a cloud-based noise cancellation service) relies on these callbacks to authenticate or route audio, it would silently stop working. The changeset description explicitly states this is intentional, so this is likely coordinated with an update in @livekit/rtc-node where AudioStream now handles this internally. Worth confirming with the rtc-node team that the FrameProcessor contract no longer requires these calls.

---

Was this helpful? React with 👍 or 👎 to provide feedback.