chore: update model catalog from bot issues#833
Merged
Erin McNulty (erin2722) merged 4 commits intoJun 22, 2026
Conversation
github-actions
Bot
requested review from
Alex Z (CLowbrow),
aswink,
Caitlin Pinn (cpinn),
Erin McNulty (erin2722) and
Ken Jiang (knjiang)
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
Contributor
Author
|
Codex (@codex) review |
|
Codex Review: Didn't find any major issues. You're on a roll. Reviewed commit: ℹ️ About Codex in GitHubCodex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
If Codex has suggestions, it will comment; otherwise it will react with 👍. When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "Codex (@codex) address that feedback". |
Contributor
Author
|
Codex review found no issues ("Didn't find any major issues"). No changes were made to repository files. |
This was referenced Jun 19, 2026
Closed
Closed
The bot batch raised max_input_tokens 272000->400000 for the gpt-5.4-mini, gpt-5.4-nano and gpt-5.3-codex aliases. 400000 is the GPT-5 family's TOTAL context window (272000 input + 128000 output); 272000 is the input-token cap (OpenAI returns "Input tokens exceed the configured limit of 272,000 tokens"). max_input_tokens must be the input cap. The dated snapshots these aliases resolve to (gpt-5.4-mini-2026-03-17, gpt-5.4-nano-2026-03-17) and every other mini/nano/codex entry in the family already use 272000; reverting restores consistency. Same regression class as #780/#776. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
…rmat to converse
Both model-sync workflows have a 'Respond to Codex review with Claude Code'
step that auto-applies Codex's suggestions to the catalog. When the index.ts
Bedrock mappings for openai.gpt-5.5 / openai.gpt-5.4 / xai.grok-4.3 are present,
Codex posts a P1 ('openai format on a Bedrock model fails') because the TS
proxy's fetchOpenAI rejects Bedrock secrets, and the auto-apply step 'fixes' it
by flipping format openai->converse. That is wrong: these are Bedrock Mantle
models served only via the OpenAI-compatible bedrock-mantle endpoint, which does
not support the Converse API or InvokeModel, so converse breaks invocation at
AWS. This recurred across #834/#836/#840/#843 (all reverting the validated #822
openai fix). The LiteLLM field sync never touches format (no checkAndUpdateFormat),
so this guardrail on the codex-response prompt is the correct lever.
Adds a 'Bedrock Mantle exception' instruction to the codex-response prompt in
both sync-models.yaml and fix-missing-model-bot-issues.yaml: keep format=openai
for bedrock-only openai-format models and explain in the summary that this is an
intentional Mantle case to be handled proxy-side, not a catalog change.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Erin McNulty (erin2722)
approved these changes
Jun 22, 2026
The bot batch wrote the new/updated endpoint entries (chatgpt-4o-latest, gpt-5.3-codex, gpt-5.4-mini, gpt-5.4-nano, codex-mini-latest) as ["openai","azure"] without the space after the comma that the .prettierrc (trailingComma: all) style requires. Run prettier to restore ["openai", "azure"], fixing the lint job. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.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.
Automated daily batch of model catalog updates from bot issues.
Included issues
Summary
qwen/qwen3.6-27bqwen/qwen3.6-27b2
Qwen/Qwen3.7-PlusQwen/Qwen3.7-Plusgpt-5.4-minigpt-5.4-nanogpt-5.4-minigpt-5.4-nano2
3
gpt-5.3-codexgpt-5.3-codex2
magistral-medium-2509magistral-small-2509devstral-2512magistral-medium-2509magistral-small-2509devstral-25122
open-mistral-nemoopen-mistral-nemo-2407open-mistral-nemoopen-mistral-nemo-24072
chatgpt-4o-latestcodex-mini-latestchatgpt-4o-latestcodex-mini-latest2
Verified metadata
#824: [BOT ISSUE] Groq: add missing qwen/qwen3.6-27b model
Verification notes
No LLM verification step ran; model metadata was already complete in the issue.
sync_models vs proposed update
sync_models cross-check found differences. Official provider verification was used for the applied values, and sync_models discrepancies are listed below for review.
#825: [BOT ISSUE] Together: add missing Qwen/Qwen3.7-Plus model
Verification notes
No LLM verification step ran; model metadata was already complete in the issue.
sync_models vs proposed update
sync_models cross-check found differences. Official provider verification was used for the applied values, and sync_models discrepancies are listed below for review.
#826: [BOT ISSUE] OpenAI: update gpt-5.4-mini and gpt-5.4-nano max_input_tokens from 272K to 400K
Verification notes
No LLM verification step ran; model metadata was already complete in the issue.
sync_models vs proposed update
sync_models cross-check found differences. Official provider verification was used for the applied values, and sync_models discrepancies are listed below for review.
#827: [BOT ISSUE] OpenAI: update gpt-5.3-codex max_input_tokens from 272K to 400K
Verification notes
No LLM verification step ran; model metadata was already complete in the issue.
sync_models vs proposed update
sync_models cross-check found differences. Official provider verification was used for the applied values, and sync_models discrepancies are listed below for review.
#828: [BOT ISSUE] Mistral: add deprecation markers for magistral-medium-2509, magistral-small-2509, devstral-2512
Verification notes
Verification
sync_models vs proposed update
sync_models cross-check found differences. Official provider verification was used for the applied values, and sync_models discrepancies are listed below for review.
#829: [BOT ISSUE] Mistral: add deprecation markers for open-mistral-nemo and open-mistral-nemo-2407
Verification notes
Verification
sync_models vs proposed update
sync_models cross-check found differences. Official provider verification was used for the applied values, and sync_models discrepancies are listed below for review.
#830: [BOT ISSUE] OpenAI: mark chatgpt-4o-latest and codex-mini-latest as deprecated (already shut down)
Verification notes
Verification
sync_models vs proposed update
sync_models cross-check found no pricing/token discrepancies for the changed models.
No sync_models discrepancies were noted.