Set explicit supported Copilot model for GitHub Guard Coverage Checker#7699
Conversation
There was a problem hiding this comment.
✅ Ready to approve
The change is narrowly scoped to workflow configuration, is internally consistent across source + lock, and directly addresses the reported non-transient model-selection failure.
Note: this review does not count toward required approvals for merging.
Pull request overview
This PR fixes the scheduled GitHub Guard Coverage Checker (MCP + CLI) workflow’s agent step failing due to unsupported/invalid model selection by pinning the workflow to a known supported Copilot model.
Changes:
- Updated the workflow frontmatter to use an explicit
engineobject and setmodel: gpt-5.4. - Updated the compiled lock workflow to align with the frontmatter change, including setting
GH_AW_INFO_MODELandCOPILOT_MODELtogpt-5.4and refreshing thefrontmatter_hash.
File summaries
Copilot's findings
- Files reviewed: 2/2 changed files
- Comments generated: 0
Note
Your feedback helps us improve the quality of this feature.
Please use 👍 or 👎 to tell us whether this assessment is correct.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

The scheduled GitHub Guard Coverage Checker (MCP + CLI) workflow was failing in the agent step due to an unsupported model configuration (
400 The requested model is not supported). This change pins the workflow to a supported Copilot model to prevent non-transient model-selection failures.Workflow frontmatter update
.github/workflows/github-mcp-guard-coverage-checker.md.gpt-5.4for deterministic model selection.Compiled lock alignment
.github/workflows/github-mcp-guard-coverage-checker.lock.ymlto match the source workflow change:GH_AW_INFO_MODEL: gpt-5.4COPILOT_MODEL: gpt-5.4frontmatter_hashmetadata to stay in sync with the.mdworkflow.Example of the effective source change: