fix: drop invalid "none" from GPT-5.6 reasoning.summary#1
Merged
guillaumegay13 merged 1 commit intoJul 14, 2026
Conversation
The subscription entries for gpt-5.6-luna/sol/terra declared reasoning.summary values [auto, concise, detailed, none], but the real OpenAI subscription API (verified live via the Manifest gateway) rejects `none` with a 400 for all three models. Valid values are [auto, concise, detailed]; default `auto` is unchanged. Regenerated package data. Co-Authored-By: paolodc95 <paolo.dc95@gmail.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Follow-up to mnfst#103 (targets its branch so it folds in before merge).
What
Removes the
nonevalue fromreasoning.summaryon the three GPT-5.6 subscription entries (gpt-5.6-luna/sol/terra). Valid values become[auto, concise, detailed]; defaultautois unchanged. Regenerated package data (data.ts,params-by-id.ts).Why
noneis not a validreasoning.summaryvalue for these models. Verified live against the real OpenAI subscription API (via the Manifest gatewayopenai/gpt-5.6-*-subscriptionendpoints):For reference, the rest of the PR checks out against the live API:
reasoning.effortacceptsnone/low/medium/high/xhigh/maxand correctly 400s onminimal(5.6 dropped it);text.verbosityacceptslow/medium/highand 400s on out-of-enum values.Validation
validate(214 models),typecheck,guard:params, lint, prettier, and 125 root + 37 package tests all pass. Codegen is idempotent.Note: the same
nonevalue likely exists in the oldergpt-5.x-subscriptionentries (where this block was copied from) — worth a separate cleanup pass.