Copilot commented on code in PR #14488: URL: https://github.com/apache/cloudstack/pull/14488#discussion_r4359160400
########## .github/workflows/daily-issue-triage.md: ########## @@ -14,12 +14,9 @@ permissions: read-all network: defaults -# claude-sonnet-5: frontier agentic model at promotional $2/$10 per 1M tokens — -# better and cheaper than the claude-sonnet-4.6 engine default this workflow -# previously fell back to. Triage needs real judgment (duplicates, severity). engine: id: copilot - model: claude-sonnet-5 + model: claude-haiku-5.5 Review Comment: Please confirm `claude-haiku-5.5` is a valid/supported model identifier for the `copilot` engine in this repo’s gh-aw / Copilot CLI setup. If model IDs differ across environments, consider using a documented alias supported by the engine (or adding a short note/link to the canonical model list used by this repo) to avoid runtime workflow failures. ########## .github/workflows/daily-issue-triage.md: ########## @@ -14,12 +14,9 @@ permissions: read-all network: defaults -# claude-sonnet-5: frontier agentic model at promotional $2/$10 per 1M tokens — -# better and cheaper than the claude-sonnet-4.6 engine default this workflow -# previously fell back to. Triage needs real judgment (duplicates, severity). engine: id: copilot - model: claude-sonnet-5 + model: claude-haiku-5.5 Review Comment: The PR description is still the default template and doesn’t describe the behavioral change (removal of weekly reporting, model change for daily triage). Since the template explicitly notes automation relies on the description for labels/docs, please update the PR description (and select the appropriate change type checkbox) to match what this PR actually does. ########## .github/workflows/daily-issue-triage.md: ########## @@ -14,12 +14,9 @@ permissions: read-all network: defaults -# claude-sonnet-5: frontier agentic model at promotional $2/$10 per 1M tokens — -# better and cheaper than the claude-sonnet-4.6 engine default this workflow -# previously fell back to. Triage needs real judgment (duplicates, severity). engine: id: copilot Review Comment: The PR removes the prior inline documentation explaining the rationale for the model choice (cost/quality and why triage needs judgment). Please add back a brief comment describing why `claude-haiku-5.5` is the right choice for triage (and what tradeoff is being made) so future maintainers can understand/adjust this safely. -- 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]
