Repository navigation
fix(autoreview): default to Astra with Sol access fallback - #19
Merged
Merged
Conversation
Contributor
There was a problem hiding this comment.
🟡 Changes recommended
Minor but user-facing documentation/help inconsistencies remain in the updated guidance around the Astra fallback and standard/default mode examples.
Once you've addressed the issues Copilot identified, you can request another Copilot review.
Pull request overview
Updates the autoreview skill + bundled helper so Codex reviews default to gpt-6-astra (high reasoning) with a single access-only fallback retry to gpt-5.6-sol, while preserving explicit model selections (explicit Sol remains pinned).
Changes:
- Switched Codex default model from Sol to Astra and updated the access-fallback behavior to Astra → Sol.
- Updated skill documentation/examples and CLI help text to reflect the new defaults and standard-mode guidance.
- Updated regression/self-tests and added validation around “explicit Sol stays pinned” behavior.
File summaries
| File | Description |
|---|---|
| skills/autoreview/SKILL.md | Updates skill contract/docs/examples for Astra default + Sol access fallback; adds standard-mode guidance. |
| skills/autoreview/scripts/autoreview_test.py | Adjusts regression tests to validate Astra→Sol access-only fallback and non-fallback cases. |
| skills/autoreview/scripts/autoreview | Updates helper defaults + self-tests; refreshes CLI help strings for new model defaults. |
| CHANGELOG.md | Records the Astra default change for autoreview. |
Review details
- Files reviewed: 4/4 changed files
- Comments generated: 2
- Review effort level: Lite
💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.
| Run the bundled structured review helper as a closeout check. This is code review, not Guardian `auto_review` approval routing. | ||
|
|
||
| Codex review is the default when no engine is set. It uses `gpt-5.6-sol` with `high` reasoning by default, then retries once with `gpt-5.6-terra` only when the account cannot access Sol. Claude review is optional and uses `claude-fable-5` by default. | ||
| Codex review is the default when no engine is set. It uses `gpt-6-astra` with `high` reasoning by default, then retries once with `gpt-5.6-sol` only when the account cannot access Astra. Claude review is optional and uses `claude-fable-5` by default. Use standard mode for Codex reviews (`--codex-speed default`); never use fast mode. |
Comment on lines
+11121
to
11122
| help="Model for all reviewers or engine=model. Repeatable. Defaults: codex=gpt-6-astra with an access-only gpt-5.6-sol retry, claude=claude-fable-5.", | ||
| ) |
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.
Autoreview now defaults to
gpt-6-astraat high reasoning. If Astra is unavailable to the account, it retries once withgpt-5.6-sol; capacity, rate-limit, and unrelated failures do not trigger a model switch. Explicit model selections remain supported, and explicit Sol stays pinned without a fallback.Updated the bundled helper, CLI help, skill instructions, examples, regression tests, and changelog. The skill requires standard mode and no longer recommends fast-mode commands. No shell configuration changes are included.
Validation:
git diff --checkpassed.Local CLI diagnosis: Homebrew's installed CLI 0.144.1 rejects Astra with an explicit newer-version requirement. The app-bundled CLI 0.153.1 successfully ran Astra and completed the review. Updating the standalone CLI is separate from this skill change.