fix(openai): default reasoning effort for mini models

[rosetta-livekit-bot]

Ports livekit/agents#6148 to agents-js.

Summary

• Add gpt-5.4-mini to OpenAI chat model support.
• Default OpenAI chat reasoning_effort to none for gpt-5.4-mini when unset.
• Apply the same Responses API default for both HTTP and WebSocket transports.

Testing

• pnpm --filter @livekit/agents build
• pnpm --filter @livekit/agents-plugins-test build
• pnpm --filter @livekit/agents-plugin-silero build
• pnpm --filter @livekit/agents-plugin-openai build
• pnpm --filter @livekit/agents-plugin-openai lint (warnings only)
• pnpm format:check

Notes

• pnpm --filter @livekit/agents-plugin-openai api:check currently fails before validating this change because API Extractor does not support the existing export * as ___ syntax in plugins/openai/dist/index.d.ts.

---

Ported from livekit/agents#6148

Original PR description

Solves #6147

[changeset-bot]

🦋 Changeset detected

Latest commit: 7a8a791

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-plugin-openai	Patch
@livekit/agents-plugin-anam	Patch
@livekit/agents-plugin-cartesia	Patch
@livekit/agents-plugin-cerebras	Patch
@livekit/agents-plugin-elevenlabs	Patch
@livekit/agents-plugin-fishaudio	Patch
@livekit/agents-plugin-google	Patch
@livekit/agents-plugin-hume	Patch
@livekit/agents-plugin-inworld	Patch
@livekit/agents-plugin-neuphonic	Patch
@livekit/agents-plugin-perplexity	Patch
@livekit/agents-plugin-rime	Patch
@livekit/agents-plugin-sarvam	Patch
@livekit/agents-plugin-xai	Patch
@livekit/agents	Patch
@livekit/agents-plugin-assemblyai	Patch
@livekit/agents-plugin-baseten	Patch
@livekit/agents-plugin-bey	Patch
@livekit/agents-plugin-deepgram	Patch
@livekit/agents-plugin-did	Patch
@livekit/agents-plugin-hedra	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-phonic	Patch
@livekit/agents-plugin-resemble	Patch
@livekit/agents-plugin-runway	Patch
@livekit/agents-plugin-silero	Patch
@livekit/agents-plugin-soniox	Patch
@livekit/agents-plugin-tavus	Patch
@livekit/agents-plugin-trugen	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 bugs or issues to report.

[devin-ai-integration]

Devin Review found 1 new potential issue.

[devin-ai-integration]

🚩 gpt-5.4-nano missing from supportsReasoningEffort despite being in inference model types

The inference LLM types at agents/src/inference/llm.ts:23 include 'openai/gpt-5.4-nano', but supportsReasoningEffort at plugins/openai/src/models.ts:213-222 does not list gpt-5.4-nano. This means no default reasoning effort is applied for that model. This may be intentional (the model might not support reasoning), and since gpt-5.4-nano is also absent from the plugin's ChatModels type, it's not a first-class plugin model. Worth confirming this omission is deliberate.

---

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