chore: default OpenAI model to gpt-6-luna - #97
Merged
Merged
Conversation
Codecov Report❌ Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #97 +/- ##
=======================================
Coverage 64.98% 64.99%
=======================================
Files 51 51
Lines 6983 6990 +7
=======================================
+ Hits 4538 4543 +5
- Misses 2107 2108 +1
- Partials 338 339 +1
Flags with carried forward coverage won't be shown. Click here to find out more.
🚀 New features to boost your workflow:
|
GPT-6 Luna is half the input price of gpt-5.6-luna ($0.10 vs $0.20 per 1M tokens) and ~58% cheaper on output ($0.50 vs $1.20), per the OpenAI API pricing page. Also fixes reasoning-model detection: the categorizer only treated `gpt-5*` as a reasoning model, so any `gpt-6-*` model would have been sent `temperature` instead of `reasoning_effort`. isGPT5Model is replaced by isReasoningModel, which treats GPT generation >= 5 as a reasoning model. Covered by TestIsReasoningModel and logged in docs/bug-fixes.md.
eshaffer321
force-pushed
the
chore/default-gpt-6-luna
branch
from
September 24, 2026 12:24
1d11f5b to
f296d3c
Compare
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Switches the default OpenAI categorizer model from
gpt-5.6-lunatogpt-6-luna, which is cheaper on the API:Source: OpenAI API pricing
Bug fix included
The categorizer only treated models starting with
gpt-5as reasoning models. Anygpt-6-*model fell through to the other branch and was senttemperature: 0.1instead ofreasoning_effort: "low".isGPT5Modelis replaced byisReasoningModel, which treats GPT generation 5 and later as reasoning models.TestIsReasoningModel. Its gpt-6 cases failed against the old check and pass now.docs/bug-fixes.md.Changes
config.go,categorizer.go,config.yaml,README.md,AGENTS.md, and.env.exampleOPENAI_MODELstill overrides the default, soOPENAI_MODEL=gpt-5.6-lunaswitches back.Testing
go test ./... -racepassesgo vetand golangci-lint are clean (pre-commit hook)walmart -dry-runwithgpt-6-lunamatched and categorized 2 orders end to end. The third order hasn't posted in Monarch yet.gpt-6-lunawithreasoning_effort: "low"returns valid JSON categorizations. The old request shape is rejected:'temperature' does not support 0.1 with this model, which confirms the bug.