shuke987 opened a new pull request, #11: URL: https://github.com/apache/doris-skills/pull/11
The review skill rejects GPT-6 Astra and Claude Fable 5.1 and always delegates an unqualified Codex task to GPT-5.6 Sol. Prefer Astra on Codex and Fable 5.1 on Claude Code, with `xhigh` as the default qualified effort. Preserve an explicitly selected qualified runtime, and use older allowlisted models only when requested or the preferred model is unavailable. Extend the exact runtime allowlist with `gpt-6-astra`, `claude-fable-5-1`, and `claude-fable-5-1[1m]`, retaining the existing model-specific effort requirements. Keep recording the actual reviewer's model and effort after delegation or fallback. Opus 4.8 and GPT-5.6 models other than Sol remain ineligible. Companion to https://github.com/apache/doris/pull/67561: merge the Doris receipt-validator support first so the new receipts can satisfy `code-review`. The hosted CI runner's Sol default is unchanged. Validation: - `./verify/repo-review/run.sh`: 38 checks passed, including the expanded runtime policy and an Astra attestation rendered into the mocked PASS comment. - Shell syntax and whitespace checks passed. - `skill-creator/scripts/quick_validate.py skills/doris-repo-review`: passed. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
