Repository navigation
fix(llm): treat GPT-6 as an OpenAI reasoning model - #1131
Draft
sosidudku1 wants to merge 2 commits into
Draft
sosidudku1 wants to merge 2 commits into
sosidudku1 wants to merge 2 commits into
Conversation
The reasoning rule only knew o1-o9 and gpt-5, so gpt-6 ids (Sol, Terra, Luna, Astra) went out with temperature and max_tokens, the two fields OpenAI's reasoning models refuse. Every GPT generation from 5 on now gets no temperature and max_completion_tokens.
The two-digit branch of the generation match also caught gpt-35-turbo, which takes temperature and max_tokens. The generation is one digit.
This branch has not been deployed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What
model-params.tsrecognised OpenAI's reasoning models aso1…o9andgpt-5only. GPT-6 ids (gpt-6.1-sol,gpt-6.2-sol,gpt-6-terra,gpt-6-astra, with or without theopenai/prefix) fell through to the default body:temperature: 0.2andmax_tokens, the two fields this family refuses on a direct OpenAI key. The rule now covers every GPT generation from 5 on, so these ids get notemperatureandmax_completion_tokens. GPT-4.x is unchanged.Why
A direct OpenAI key with a GPT-6 model would get a 400 on the first turn, the same failure the file documents for
gpt-5. Linear: ATO-1339.Out of scope: whether some GPT-6 models need the Responses API for tool calls. The agent only speaks
/chat/completions; that needs a real key to confirm and would be its own change.How it was verified
model-params.test.ts: GPT-6 ids added to the reasoning-model cases,gpt-4.1-minito the free cases.Not yet checked on the second Mac.