remove shortcut inference STT model name

[longcw]

Summary by CodeRabbit

Release Notes

• Breaking Changes
  • STT model selection now requires specifying exact model versions (e.g., "deepgram/nova-3" instead of "deepgram"). Update your agent configurations accordingly.

_{✏️ Tip: You can customize this high-level summary in your review settings.}

[coderabbitai]

📝 Walkthrough

Walkthrough

The pull request removes generic provider names ("deepgram", "cartesia", "assemblyai") from STT model type aliases, requiring explicit model specifications instead. The example configuration is updated to use specific model identifiers like "deepgram/nova-3" and "cartesia/ink-whisper".

Changes

Cohort / File(s)	Summary
STT Model Type Definitions livekit-agents/livekit/agents/inference/stt.py	Removed generic provider options from public type aliases: removed "deepgram" from DeepgramModels, consolidated CartesiaModels from 2 entries to 1 ("cartesia/ink-whisper"), consolidated AssemblyAIModels from 2 entries to 1 ("assemblyai/universal-streaming"). Forces explicit model specification.
Example Configuration examples/voice_agents/langfuse_trace.py	Updated STT model selections in Kelly agent initialization: "deepgram" → "deepgram/nova-3", "cartesia" → "cartesia/ink-whisper" to align with new type definitions.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~10 minutes

Suggested reviewers

• davidzhao

Poem

🐰 Generic names hop away,
Specific models here to stay!
From "deepgram" to "nova-3" bright,
Each STT now gets it right.
Clarity whispers through the code,
On the specificity road! 🎙️

🚥 Pre-merge checks | ✅ 2 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Docstring Coverage	⚠️ Warning	Docstring coverage is 0.00% which is insufficient. The required threshold is 80.00%.	Write docstrings for the functions missing them to satisfy the coverage threshold.

✅ Passed checks (2 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title 'remove shortcut inference STT model name' accurately describes the main change: removing shortcut model names (like 'deepgram', 'cartesia', 'assemblyai') and requiring explicit sub-model specifications (e.g., 'deepgram/nova-3').

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing touches

• 📝 Generate docstrings

---

📜 Recent review details

Configuration used: Organization UI

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 47ce504 and 35014d8.

📒 Files selected for processing (2)

• examples/voice_agents/langfuse_trace.py
• livekit-agents/livekit/agents/inference/stt.py

🧰 Additional context used

📓 Path-based instructions (1)

**/*.py

📄 CodeRabbit inference engine (AGENTS.md)

**/*.py: Format code with ruff
Run ruff linter and auto-fix issues
Run mypy type checker in strict mode
Maintain line length of 100 characters maximum
Ensure Python 3.9+ compatibility
Use Google-style docstrings

Files:

• examples/voice_agents/langfuse_trace.py
• livekit-agents/livekit/agents/inference/stt.py

🧠 Learnings (3)

📓 Common learnings

Learnt from: CR
Repo: livekit/agents PR: 0
File: AGENTS.md:0-0
Timestamp: 2026-01-16T07:44:56.353Z
Learning: Implement Model Interface Pattern for STT, TTS, LLM, and Realtime models with provider-agnostic interfaces, fallback adapters for resilience, and stream adapters for different streaming patterns

📚 Learning: 2026-01-16T07:44:56.353Z

Learnt from: CR
Repo: livekit/agents PR: 0
File: AGENTS.md:0-0
Timestamp: 2026-01-16T07:44:56.353Z
Learning: Implement Model Interface Pattern for STT, TTS, LLM, and Realtime models with provider-agnostic interfaces, fallback adapters for resilience, and stream adapters for different streaming patterns

Applied to files:

• examples/voice_agents/langfuse_trace.py
• livekit-agents/livekit/agents/inference/stt.py

📚 Learning: 2026-01-22T03:28:16.289Z

Learnt from: longcw
Repo: livekit/agents PR: 4563
File: livekit-agents/livekit/agents/beta/tools/end_call.py:65-65
Timestamp: 2026-01-22T03:28:16.289Z
Learning: In code paths that check capabilities or behavior of the LLM processing the current interaction, prefer using the activity's LLM obtained via ctx.session.current_agent._get_activity_or_raise().llm instead of ctx.session.llm. The session-level LLM may be a fallback and not reflect the actual agent handling the interaction. Use the activity LLM to determine capabilities and to make capability checks or feature toggles relevant to the current processing agent.

Applied to files:

• livekit-agents/livekit/agents/inference/stt.py

🧬 Code graph analysis (1)

examples/voice_agents/langfuse_trace.py (4)

livekit-agents/livekit/agents/voice/agent_session.py (1)

• stt (1256-1257)

livekit-agents/livekit/agents/voice/agent_activity.py (1)

• stt (2778-2779)

livekit-agents/livekit/agents/voice/agent.py (1)

• stt (508-518)

livekit-agents/livekit/agents/inference/stt.py (1)

• STT (143-372)

⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (6)

• GitHub Check: type-check (3.13)
• GitHub Check: type-check (3.9)
• GitHub Check: livekit-plugins-openai
• GitHub Check: livekit-plugins-cartesia
• GitHub Check: livekit-plugins-deepgram
• GitHub Check: unit-tests

🔇 Additional comments (2)

livekit-agents/livekit/agents/inference/stt.py (1)

39-40: Explicit model literals look good.

Tightening the model literals to explicit provider/model strings aligns with the stated objective and improves type clarity.

examples/voice_agents/langfuse_trace.py (1)

86-91: Example updated consistently with new STT model naming.

The explicit model identifiers match the updated STT literals and keep the example valid.

_{✏️ Tip: You can disable this entire section by setting review_details to false in your review settings.}

---

_{Comment @coderabbitai help to get the list of available commands and usage tips.}