Repository navigation
Add minimal to OpenAI reasoning effort options - #9
Merged
imonlinux merged 1 commit intoNov 3, 2026
Merged
Conversation
Reasoning models such as OpenAI's gpt-5 family and Meta's Muse Spark accept reasoning_effort=minimal, which roughly halves first-text latency for short voice-assistant answers compared to low. The provider already forwards any value other than none, so only the selector options, labels and a test change. Closes imonlinux#7
3 tasks done
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Closes #7.
Adds
minimalto the OpenAI-protocol reasoning effort selector, for reasoning models that accept it (OpenAI's gpt-5 family, Meta's Muse Spark). On Muse Spark it roughly halves time to first text for short Assist answers compared withlow(timings in #7).Changes
const.py:REASONING_EFFORT_OPTIONSis now["none", "minimal", "low", "medium", "high"]. The default staysnone, so existing entries are unchanged.strings.json/translations/en.json:"minimal": "Minimal"label inselector.reasoning_effort.options.tests/providers/test_openai_chat_provider.py: newtest_build_request_reasoning_effort_minimalassertingminimalis forwarded verbatim.No provider change was needed:
build_requestalready forwards any effort other thannone.The temperature/top_p point from the issue is left for a separate change.
Validation
Full suite on Python 3.13 with
requirements_test.txt(HA 2025.8.1 tree): 134 passed, 2 skipped (was 133 passed, 2 skipped; +1 new test).Suggested changelog line, if useful: Added —
minimalreasoning effort option for OpenAI-compatible providers (#7).