fix(dependabot): use openai/gpt-4.1 for the AI gate (gpt-5 unavailable on Models)#7
Merged
Conversation
…e on Models) The GitHub Models inference endpoint returns `unavailable_model` for the gpt-5 family (they are in the catalog but not servable), which made the gate fail every call and silently fall back to manual review. Switch to `openai/gpt-4.1`, the strongest model actually available for GitHub Models inference. Verified locally against real + fixture changelogs via GitHub Models: - docker/metadata-action v4->v6 (real PR #2226) -> auto / low - synthetic breaking changelog (removed/required inputs, changed defaults) -> human / high - benign Node-runtime-only bump -> auto / low Ref RealRate-Private#2229. 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
While validating the gate before enforcement, I found
openai/gpt-5(set in #6) returnsunavailable_modelfrom the GitHub Models inference endpoint — the gpt-5 family is in the catalog but not servable. That made every verdict fail and fall back to manual review (safe, but the gate would never actually work).Fix: switch
MODEL_IDtoopenai/gpt-4.1, the strongest model actually available for GitHub Models inference (probed live: gpt-4o, gpt-4o-mini, gpt-4.1, gpt-4.1-mini work; gpt-5* do not).Validated locally against real GitHub Models with
gpt-4.1:auto/ low ✅human/ high ✅auto/ low ✅Still dry-run. Next: recreate a real major github-actions Dependabot PR (#2223, actions/checkout v4→v7) to observe the verdict in CI, then flip
AIGATE_DRY_RUN.🤖 Generated with Claude Code