feat(openai): add gpt-5.5 to model registry

[xtreme-sameer-vohra]

Summary

Adds gpt-5.5 to the OpenAI model registry so it can be selected via the livekit-plugins-openai plugin (openai.LLM(model="gpt-5.5")).

The model is also added to _supports_reasoning_effort(), matching the other bare gpt-5.x entries so reasoning_effort is passed through.

[CLAassistant]

All committers have signed the CLA.

[devin-ai-integration]

Devin Review found 1 potential issue.

View 1 additional finding in Devin Review.

[devin-ai-integration]

🟡 New gpt-5.5 model gets a different default reasoning setting than its sibling models

Enabling reasoning support for the new model ("gpt-5.5" added to _supports_reasoning_effort at livekit-plugins/livekit-plugins-openai/livekit/plugins/openai/models.py:299) without also listing it alongside its closest siblings causes it to fall into the fallback branch and default to "minimal" instead of "none" like gpt-5.4/gpt-5.2/gpt-5.1.
Impact: When someone selects the new model without explicitly choosing a reasoning setting, it silently uses a different default than the other recent models, and if that value is unsupported by the model the request can fail.

Default reasoning-effort selection excludes gpt-5.5

Once "gpt-5.5" is accepted by _supports_reasoning_effort (models.py:299), both constructors take the reasoning-default path but only assign "none" to models explicitly listed:

• livekit-plugins/livekit-plugins-openai/livekit/plugins/openai/llm.py:127 — if model in ["gpt-5.1", "gpt-5.2", "gpt-5.4", "gpt-5.4-mini"]: reasoning_effort = "none" else "minimal".
• livekit-plugins/livekit-plugins-openai/livekit/plugins/openai/responses/llm.py:189 — same list, else Reasoning(effort="minimal").

Since gpt-5.5 is absent from both lists, it defaults to minimal, diverging from the bare gpt-5.x entries (5.1/5.2/5.4) the PR intends to match. These lists likely also need "gpt-5.5".

Prompt for agents

Adding "gpt-5.5" to _supports_reasoning_effort() in models.py causes the OpenAI LLM constructors to enter the reasoning-default branch for gpt-5.5. However, in livekit-plugins/livekit-plugins-openai/livekit/plugins/openai/llm.py (around line 127) and livekit-plugins/livekit-plugins-openai/livekit/plugins/openai/responses/llm.py (around line 189), the check `if model in ["gpt-5.1", "gpt-5.2", "gpt-5.4", "gpt-5.4-mini"]` assigns reasoning effort "none", otherwise "minimal". Because gpt-5.5 is not in that list, it will default to "minimal" instead of "none" like its closest sibling gpt-5.4. Determine whether gpt-5.5 should default to "none" (matching the newer gpt-5.x family) and, if so, add "gpt-5.5" to both lists. Verify whether gpt-5.5 even supports the "minimal" reasoning effort value, since defaulting to an unsupported value would cause API request failures.

---

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