fix(elevenlabs): send keyterms on the realtime STT WebSocket

[rosetta-livekit-bot]

Ports livekit/agents#6746 to the ElevenLabs JavaScript plugin.

Realtime Scribe v2 connections now send repeated, percent-encoded keyterms query parameters. Updating keyterms on either the STT instance or an active speech stream triggers a reconnect so the new biasing takes effect.

Adds a patch changeset for @livekit/agents-plugin-elevenlabs.

Verification

• pnpm test plugins/elevenlabs (24 passed, 2 credential-gated integration tests skipped)
• pnpm build (40/40 packages passed)
• pnpm lint (40/40 packages passed; existing warnings only)
• pnpm exec prettier --check plugins/elevenlabs/src/stt.ts plugins/elevenlabs/src/stt.test.ts .changeset/elevenlabs-realtime-keyterms.md

Source diff coverage

Authoritative source: livekit/agents#6746

• Adapted: livekit-plugins/livekit-plugins-elevenlabs/livekit/plugins/elevenlabs/stt.py -> plugins/elevenlabs/src/stt.ts. Ported constructor option documentation, repeated percent-encoded realtime WebSocket keyterms, STT-to-stream option forwarding, and reconnect-on-keyterm-update behavior. JavaScript encodeURIComponent replaces Python urllib.parse.quote.
• Adapted: tests/test_plugin_elevenlabs_stt.py -> plugins/elevenlabs/src/stt.test.ts. Ported all five source tests for inclusion, query-delimiter escaping and URL round trips, omission when unspecified, STT-level forwarding, and stream-level reconnects. The target tests observe URLs through its local WebSocket test server because TypeScript private fields and methods are inaccessible.
• Not applicable: none. Every source diff file has a target counterpart and is covered.

---

Ported from livekit/agents#6746

Original PR description

Problem

keyterms is accepted by elevenlabs.STT(...) but only ever sent on the batch
request. It is dropped on the realtime WebSocket path, so scribe_v2_realtime
sessions get no keyterm biasing even when the caller passes them.

ElevenLabs does support it there, as repeated keyterms query params on the connect URL:

• Realtime STT API reference lists keyterms — "List of keyterms the model is biased towards."
• Keyterm prompting guide — "also available for the realtime Speech to Text WebSocket API." Batch allows 1000 keyterms × 50 chars, realtime 50 × 20.

The docstring claims the opposite. It was accurate when written, before ElevenLabs
shipped realtime keyterms — no_verbatim, released alongside them, was wired into
_connect_ws, but keyterms was missed and the docstring never updated.

Changes

• _connect_ws appends repeated keyterms= query params, percent-encoded.
• SpeechStream.update_options accepts keyterms and triggers a reconnect, mirroring
  no_verbatim. STT.update_options forwards them to active streams.
• Docstring corrected with the real per-mode limits.
• 5 tests, following the existing enable_logging / no_verbatim patterns.

Keyterms are free-form text, unlike the other params in that URL (model ids, enums,
numbers, language codes), so they need encoding: verified against yarl.URL — the parser
aiohttp.ws_connect uses — an unescaped & splits Smith & Sons into keyterms='Smith '
plus a bogus ' Sons' param, and # truncates C# to C.
test_connect_ws_escapes_query_delimiters_in_keyterms pins this via
URL(...).query.getall("keyterms").

Verification

make check clean (ruff, mypy over 629 files). pytest tests/test_plugin_elevenlabs_stt.py — 25 passed.

Those mock the socket, so they only prove the URL is built correctly. Checked separately
against the live endpoint: one TTS-synthesized clip per term, transcribed twice over
scribe_v2_realtime — identical audio bytes in both arms, so any difference isolates
the keyterm.

term	without keyterms	with keyterms
Sonic3000	Sonic 3000	Sonic3000
GPT4o	GPT-4o	GPT4o
K2Turbo	K2 Turbo	K2Turbo
nova-3	Nova 3	nova-3
scribe-v2	Scribe V2	scribe-v2

[changeset-bot]

🦋 Changeset detected

Latest commit: 99217fd

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

This PR includes changesets to release 39 packages

Name	Type
@livekit/agents-plugin-elevenlabs	Patch
@livekit/agents	Patch
@livekit/agents-plugin-anam	Patch
@livekit/agents-plugin-anthropic	Patch
@livekit/agents-plugin-assemblyai	Patch
@livekit/agents-plugin-azure	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-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-krisp	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-protoface	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-plugin-trugen	Patch
@livekit/agents-plugin-xai	Patch
@livekit/agents-plugins-test	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

[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.