Breaking change

Proposed change

gpt-6-luna supports the none reasoning effort, but the configuration flow uses the general GPT-6 list, which does not include it. This means users cannot select none when configuring the model.

This change adds a gpt-6-luna entry before the general gpt-6 entry. It allows none in both Conversation and AI Task subentries and keeps low as the default.

The supported effort levels are listed in the OpenAI model documentation.

How to reproduce

1. Reconfigure an OpenAI Conversation or AI Task subentry.
2. Disable recommended settings and set the model to gpt-6-luna.
3. Check the reasoning effort selector. Before this change, none is missing.

Tests

The tests cover the effort list, saving none and low for both subentry types, and the Responses API arguments for both settings.

• Before the fix, three regression cases failed. After the fix, all 17 focused tests passed.
• The full OpenAI integration suite passed: 262 tests and 56 snapshots. Coverage was 98% for the integration and 100% for config_flow.py.
• Ruff, mypy and pylint passed for the changed code. All applicable prek hooks passed for the four changed files.
• I also checked both settings against the Responses API with a simulated function. Both returned the requested function call. With none, the API also accepted temperature=0.5 and top_p=0.9. These checks used no Home Assistant device data or actions.

Integration test command:

uv run --no-sync pytest -q tests/components/openai_conversation --cov=homeassistant.components.openai_conversation --cov-report=term-missing

Local validation limits

I used Python 3.14.5 and the dependencies pinned by Core, including the test requirements and OpenAI SDK.

The full script/setup stopped while building DTLSSocket because autoconf was unavailable. I installed the dependencies needed for the integration and ran the tests and checks above.

The repository-wide prek run --all-files was stopped when pylint exhausted the available memory. Running the remaining hooks reported a duplicate-module conflict for signal_type.py/.pyi in mypy and a missing infrared_protocols dependency in hassfest. The checks on the changed files passed, but I could not complete all repository-wide checks locally.

This PR adds no dependencies or configuration keys. The model-switch effort reset discussed in #182222 is outside its scope.

Type of change

• Dependency upgrade
• Bugfix (non-breaking change which fixes an issue)
• New integration (thank you!)
• New feature (which adds functionality to an existing integration)
• Deprecation (breaking change to happen in the future)
• Breaking change (fix/feature causing existing functionality to break)
• Code quality improvements to existing code or addition of tests

Additional information

• This PR fixes or closes issue: N/A
• This PR is related to issue: Add GPT-6 Astra support #181693, Fix effort level when configuring a different OpenAI model #182222
• Link to documentation pull request:
• Link to developer documentation pull request:
• Link to frontend pull request:

Checklist

• I understand the code I am submitting and can explain how it works.
• The code change is tested and works locally.
• Local tests pass. Your PR cannot be merged unless tests pass
• There is no commented out code in this PR.
• I have followed the development checklist
• I have followed the perfect PR recommendations
• The code has been formatted using Ruff (ruff format homeassistant tests)
• Tests have been added to verify that the new code works.
• Any generated code has been carefully reviewed for correctness and compliance with project standards.

If user exposed functionality or configuration variables are added/changed:

• Documentation added/updated for www.home-assistant.io

If the code communicates with devices, web services, or third-party tools:

• The manifest file has all fields filled out correctly.
  Updated and included derived files by running: python3 -m script.hassfest.
• New or updated dependencies have been added to requirements_all.txt.
  Updated by running python3 -m script.gen_requirements_all.
• For the updated dependencies a diff between library versions and ideally a link to the changelog/release notes is added to the PR description.

To help with the load of incoming pull requests:

• I have reviewed two other open pull requests in this repository.