Repository navigation
fix(review): correct OpenAI advisor model ID - #10835
Merged
Merged
Conversation
Signed-off-by: Carlos Villela <cvillela@nvidia.com>
Contributor
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: CHILL Plan: Enterprise Run ID: 📒 Files selected for processing (2)
Included review availability: Your plan provides up to 12 included reviews per hour; 11 remain after this review. 📝 WalkthroughWalkthroughThe default specialist matrix and its test now use ChangesModel identifier correction
Estimated code review effort: 1 (Trivial) | ~2 minutes Merge Risk: ⚪ Minimal · up to The OpenAI advisor matrix now uses the corrected model identifier while preserving the Azure configuration, so no actionable merge-blocking risk remains beyond normal checks and review. Suggested reviewers: 🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
Full details: Docstring CoverageExplanation No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check. Docstring coverage is scoped to functions touched by this diff. Analyzed 0 functions across 2 files. ✨ Finishing Touches 💡 1🛠️ Fix failing CI checks 💡
📝 Generate docstrings
🧪 Generate unit tests (beta)
Comment |
Contributor
cv
added a commit
that referenced
this pull request
Sep 2, 2026
<!-- markdownlint-disable MD041 --> ## Outcome Both PR Review Advisor model lanes use their complete upstream model IDs and configure successfully in the embedded advisor registry. ## Reason OpenShell forwards the configured model ID verbatim and requires `openai/openai/gpt-5.6-terra`. The embedded Pi registry previously registered only the Azure default, so the complete OpenAI ID failed local lookup. Shortening that ID passed local lookup only after changing the matrix, but OpenShell then rejected it with HTTP 403 because the key was not authorized for `openai/gpt-5.6-terra`. ## Changes - Restore the complete `openai/openai/gpt-5.6-terra` matrix identifier. - Register the selected runtime model ID in the embedded advisor provider configuration. - Pass the selected ID through advisor configuration setup. - Cover selected-model registration and the restored matrix value. ## Verification - Local validation intentionally skipped at maintainer direction for this follow-up. - Runtime evidence: post-#10835 run 33577784873 reached OpenShell with the shortened ID and received `key_model_access_denied` for `openai/gpt-5.6-terra`; Azure specialists succeeded. - Secrets review: The diff contains no secrets, API keys, or credentials. --- Signed-off-by: Carlos Villela <cvillela@nvidia.com> Signed-off-by: Carlos Villela <cvillela@nvidia.com>
wscurran
added
the
area: ci
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.
Outcome
OpenAI-routed PR Review Advisor specialists configure successfully while the inference service continues to receive
openai/openai/gpt-5.6-terra.Reason
The Pi registry prepends its local
openaiprovider name to the configured model ID. Supplyingopenai/openai/gpt-5.6-terratherefore attempted to resolveopenai/openai/openai/gpt-5.6-terraand caused half of each advisor matrix to fail before inference.Changes
openai/gpt-5.6-terra.Verification
Signed-off-by: Carlos Villela cvillela@nvidia.com
Summary by CodeRabbit