fishaudio: reuse streaming websocket and prebuffer initial chunks

[rosetta-livekit-bot]

Summary

Port livekit-plugins-fishaudio pooled websocket reuse and initial audio prebuffering from livekit/agents#6368.

• Reuse /v1/tts/live websocket connections through the existing JS ConnectionPool.
• Add TTS.prewarm() and close pooled sockets from TTS.close().
• Invalidate the pool when model changes because FishAudio sends model as a websocket handshake header.
• Prebuffer the first two audio chunks before feeding the byte stream, flushing held audio on short utterance finish.

Source diff coverage

Coverage

Source file	Classification	Target handling
livekit-plugins/livekit-plugins-fishaudio/livekit/plugins/fishaudio/tts.py	Ported/adapted	Ported to plugins/fishaudio/src/tts.ts. The pooled /v1/tts/live websocket behavior maps to the existing JS ConnectionPool; prewarm(), pool close, model-change invalidation, and first-N chunk prebuffering were implemented. Adaptations are TypeScript/Node ws API differences, millisecond duration units (300_000 ms), and the target stream/frame queue conventions.

Verification

• pnpm --filter @livekit/agents-plugin-fishaudio... build
• pnpm --filter @livekit/agents-plugin-fishaudio build
• pnpm --filter @livekit/agents-plugin-fishaudio lint
• pnpm test -- plugins/fishaudio (FishAudio test skipped because FISH_API_KEY/OPENAI_API_KEY are not set)
• pnpm build
• pnpm lint (passes with pre-existing warnings in unrelated packages)
• cue-cli text-mode run against built warm-transfer example: asserted conversation_item_added(.item.message.role="ASSISTANT"); FishAudio provider was not exercised because FISH_API_KEY is not set in this environment.

Notes

• Target already had the needed ConnectionPool infrastructure, so no infrastructure gap was left unported.
• pnpm --filter @livekit/agents-plugin-fishaudio api:check still fails due existing package API report/release-tag warnings (plugins/fishaudio/etc API report is absent); this PR does not introduce that gap.

---

Ported from livekit/agents#6368

Original PR description

two changes to the fish plugin:

1. reuse/pre-warm the /v1/tts/live websocket via utils.ConnectionPool (same
   pattern as cartesia/rime). the plugin used to open a fresh WSS per utterance,
   paying ~330ms of TLS+WS handshake on every reply. now one socket is reused per
   session and pre-warmed via prewarm(), so the first reply skips the handshake.
   general latency win, independent of the crackle fix.

2. prebuffer the first two audio chunks before starting playout. fish streams a
   small first chunk (~460ms) then, ~250ms later, a much larger second chunk.
   starting webrtc's real-time playout at the first chunk leaves only ~190ms of
   buffer headroom; app/network jitter tips it into an underrun the receiver
   conceals as an audible click/gap ~0.5s into the first utterance (repro'd ~1 in
   5). waiting for the second chunk starts playout with ~1.3s buffered and
   eliminates it.

the prebuffer is an internal constant (_PREBUFFER_CHUNKS = 2), not a public
option. it costs a little TTFB and is a stopgap for fish's cold-start chunk
pacing; once the inference side streams the opening chunks smoothly we'll drop it
to 1 to start on the first chunk. working with the fish inference team on that now.

verified no crackles on livekit-demo-web.onrender.com; chunk-2 headroom measured
before/after and the negative tail is gone.

[changeset-bot]

🦋 Changeset detected

Latest commit: 363246c

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

This PR includes changesets to release 36 packages

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

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

[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 1 additional finding.