fix(workflow): set engine.mcp.tool-timeout on daily-safe-output-optimizer

[Copilot]

The daily-safe-output-optimizer workflow was consistently failing because the MCP gateway enforces a default 60 s per-tool RPC deadline. Every invocation of the agenticworkflows logs tool timed out at ~60 s regardless of the timeout parameter passed—that parameter only governs the subprocess deadline, not the gateway-level one.

Changes

• daily-safe-output-optimizer.md: Expanded engine: claude to the full block and added engine.mcp.tool-timeout: 10m, matching the existing pattern in safe-output-health.md, audit-workflows.md, api-consumption-report.md, and detection-analysis-report.md.

# before
engine: claude

# after
engine:
  id: claude
  mcp:
    tool-timeout: 10m

The compiled lock file now emits "toolTimeout": 600 in the gateway config section, giving the logs tool enough headroom to download 24 h of workflow run artifacts before the gateway closes the connection.

• Fixes [aw] Daily Safe Output Tool Optimizer reported incomplete result #48982

[github-actions]

Triage: fix(workflow): set engine.mcp.tool-timeout

• Category: chore | Risk: low | Score: 47/100 (Impact 20, Urgency 15, Quality 12)
• Recommendation: defer — draft, CI pending. Small config fix (2 files, +8/-4). Un-draft and confirm CI once gateway timeout applies, then fast-track.

Generated by 🔧 PR Triage Agent · aut00 · 52.7 AIC · ⌖ 9.26 AIC · ⊞ 7.9K · ◷

[github-actions]

Warning

threat detection engine error
The threat detection engine encountered an error and could not complete analysis. This is a tooling failure, not a security finding.

Details

The threat detection engine failed to produce results.

Review the workflow run logs for details.

🎯 Great work fixing the timeout issue! This PR addresses the root cause identified in #48982 where the MCP gateway's 60-second RPC deadline was preventing the agenticworkflows logs tool from completing its 24-hour artifact downloads.

What looks good:

• ✅ Focused change — expands the engine config to include the MCP tool-timeout setting, matching the established pattern in safe-output-health.md, audit-workflows.md, and other workflows
• ✅ Clear explanation — the PR body clearly describes the problem, the solution, and references the related issue
• ✅ Follows conventions — uses the same YAML structure as existing workflows
• ✅ Low risk — configuration-only change with a single, specific fix

On test coverage: For infrastructure/workflow configuration changes like this, manual verification that the workflow runs successfully (without timeout) is the appropriate validation, which can be observed once this merges and the workflow runs again.

This PR is ready for review!

Warning

Firewall blocked 1 domain

The following domain was blocked by the firewall during workflow execution:

• patchdiff.githubusercontent.com

To allow these domains, add them to the network.allowed list in your workflow frontmatter:

network:
  allowed:
    - defaults
    - "patchdiff.githubusercontent.com"

See Network Configuration for more information.

Generated by ✅ Contribution Check · aut00 · 61.8 AIC · ⊞ 8.7K · ◷

[Copilot]

Pull request overview

Configures a 10-minute MCP gateway tool deadline so log analysis can complete without the previous 60-second timeout.

Changes:

• Adds engine.mcp.tool-timeout: 10m.
• Regenerates the compiled workflow with toolTimeout: 600.

Show a summary per file

File	Description
.github/workflows/daily-safe-output-optimizer.md	Configures the longer MCP tool timeout.
.github/workflows/daily-safe-output-optimizer.lock.yml	Applies the timeout to the generated gateway configuration.

Review details

Tip

Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

• Files reviewed: 2/2 changed files
• Comments generated: 0
• Review effort level: Medium