feat: make gpt-5.6-luna the default OpenAI model - #2007
Merged
Conversation
gpt-5.6-luna is cheaper than gpt-5.4-mini and carries a much larger context, but chat completions rejects function tools while reasoning is active, and the model rejects a non-default temperature while reasoning is on. Lumen sends a temperature on every request and uses function tools for structured output, so the id swap alone fails on every call. Rather than hardcode which models need which workaround, adapt from the API's own 400: it names the offending parameter, so OpenAI.run_client records the fix per model and retries. New models need no code change, and providers that accept the parameters are never touched. Fixes #2002
Codecov Report❌ Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #2007 +/- ##
==========================================
+ Coverage 72.98% 73.06% +0.07%
==========================================
Files 205 205
Lines 36865 36967 +102
==========================================
+ Hits 26907 27011 +104
+ Misses 9958 9956 -2 ☔ View full report in Codecov by Harness. 🚀 New features to boost your workflow:
|
ahuang11
approved these changes
Aug 13, 2026
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Makes
gpt-5.6-lunathe default OpenAI model, adapting from the API's own 400 rather than hardcoding which models rejecttemperatureorreasoning_effort.gpt-5.6-lunagpt-5.4-mini3.5x cheaper on the same question.
Fixes #2002