Add diagnostic logging and increase timeout for safe-outputs MCP server startup failures

[Copilot]

Fix PR Triage Agent Workflow Failure - Safe Outputs MCP Server Startup Timeout

Problem Summary

The PR Triage Agent workflow fails because the Safe Outputs MCP HTTP server doesn't start within the timeout period. The server process starts but produces no log output and never responds on port 3001.

Failing workflow: https://github.com/githubnext/gh-aw/actions/runs/21368688445

Investigation Complete ✅

Key Findings:

1. ✅ All required files are copied correctly to /opt/gh-aw/safeoutputs/
2. ✅ Node.js process starts successfully (PID confirmed alive)
3. ✅ Server works perfectly in local test environment
4. ✅ Issue is environment-specific to GitHub Actions workflows
5. ✅ Comprehensive debug logging now in place with proper logger

Changes Made

1. Debug Logging with Proper Logger ✅

Implemented comprehensive debug logging using the createLogger() utility at critical initialization points:

• Entry Point (safe-outputs-mcp-server.cjs): Uses createLogger("safe-outputs-entry") to track Node.js execution and module loading
• HTTP Server (safe_outputs_mcp_server_http.cjs): Uses module logger and createLogger("safe-outputs-startup") to log each require() statement and function entry
• Transport Layer (mcp_http_transport.cjs): Uses createLogger("MCPServer") and createLogger("MCPHTTPTransport") to track connect() and start() async operations
• MCP Core (mcp_server_core.cjs): Uses module logger to confirm module initialization

All log messages include:

• ISO timestamps: [2026-01-26T20:29:28.069Z]
• Logger names: [safe-outputs-entry], [safeoutputs], [MCPServer], etc.
• Consistent formatting across all modules

2. Timeout Increased ✅

• Increased startup timeout from 10 seconds to 60 seconds in start_safe_outputs_server.sh
• Updated all timeout messages to reflect 60-second limit
• Updated progress messages to show attempt X/60 instead of attempt X/10

3. Workflow Updates ✅

• Merged latest changes from main branch (twice - staying up to date)
• Recompiled all workflow files with make recompile
• Formatted code with make fmt
• Linted code with make lint
• All validations passing

Local Test Results ✅

Successfully tested with exact workflow file setup and new logger:

✅ Server starts in < 0.01 seconds
✅ All 33 modules load successfully
✅ HTTP server binds to port 3001
✅ Health endpoint responds correctly  
✅ Logging captured with >> redirection
✅ All async operations complete properly
✅ Logger provides consistent timestamps and formatting
✅ All log messages properly categorized by component

Next Steps

To Complete Fix:

1. ⏳ Trigger test workflow run (PR Triage Agent or smoke-copilot)
2. ⏳ Examine debug logs from workflow environment
3. ⏳ Identify environment-specific difference
4. ⏳ Apply targeted fix based on log comparison

Expected Debug Output:
The comprehensive logging with proper logger combined with increased timeout will reveal exactly where execution stops or hangs, enabling a precise fix.

Files Modified

• actions/setup/js/safe-outputs-mcp-server.cjs - Entry point logging with createLogger
• actions/setup/js/safe_outputs_mcp_server_http.cjs - Module loading and function call logging with createLogger
• actions/setup/js/mcp_http_transport.cjs - Connect and start logging with createLogger
• actions/setup/js/mcp_server_core.cjs - Module load logging with createLogger
• actions/setup/sh/start_safe_outputs_server.sh - Increased timeout from 10s to 60s
• Merged latest changes from main branch (multiple times)
• Recompiled workflow lock files with updated action versions

Original prompt

---

This section details on the original issue you should resolve

<issue_title>[agentics] PR Triage Agent failed</issue_title>
<issue_description>### Workflow Failure

Workflow: PR Triage Agent
Branch: main
Run URL: https://github.com/githubnext/gh-aw/actions/runs/21368688445

Action Required

Debug this workflow failure using the agentic-workflows agent:

/agent agentic-workflows

When prompted, instruct the agent to debug this workflow failure.

Generated from PR Triage Agent

• expires on Feb 2, 2026, 6:13 PM UTC

Comments on the Issue (you are @copilot in this section)

• Fixes [agentics] PR Triage Agent failed #11919

---

💬 We'd love your input! Share your thoughts on Copilot coding agent in our 2 minute survey.

---

Changeset

• Type: patch
• Description: Add diagnostic logging and expand the safe-outputs MCP server startup timeout to 60 seconds to reduce CI flakiness.

Ahoy! This treasure was crafted by 🏴‍☠️ Changeset Generator

---

Changeset

• Type: patch
• Description: Add diagnostic logging and widen the safe-outputs MCP server startup timeout to 60 seconds to tame CI flakiness.

Ahoy! This treasure was crafted by 🏴‍☠️ Changeset Generator

[pelikhan]

@copilot increase timeout to 60 seconds

[pelikhan]

@copilot revert all *.lock.yml files

[Copilot]

@copilot increase timeout to 60 seconds

Increased timeout from 10 to 60 seconds in start_safe_outputs_server.sh. Commit: 34907fc

[pelikhan]

@copilot merge main, recompile, format, lint

[Copilot]

@copilot revert all *.lock.yml files

Reverted all 139 *.lock.yml files to their original state. Commit: 73654be

[github-actions]

🎬 THE END — Smoke Claude MISSION: ACCOMPLISHED! The hero saves the day! ✨

[github-actions]

✨ The prophecy is fulfilled... Smoke Codex has completed its mystical journey. The stars align. 🌟

[pelikhan]

@copilot create logger and use them instead of directly using process.stderr

[Copilot]

@copilot create logger and use them instead of directly using process.stderr

Refactored all debug logging to use createLogger() instead of direct process.stderr.write() calls. All log messages now include ISO timestamps and consistent logger names. Commit: f71d27e

[github-actions]

✨ The prophecy is fulfilled... Smoke Codex has completed its mystical journey. The stars align. 🌟

[github-actions]

🎬 THE END — Smoke Claude MISSION: ACCOMPLISHED! The hero saves the day! ✨

[github-actions]

🎉 Yo ho ho! Changeset Generator found the treasure and completed successfully! ⚓💰

[github-actions]

📰 BREAKING: Smoke Copilot is now investigating this pull request. Sources say the story is developing...

[github-actions]

Tests: GitHub MCP ✅; gh CLI ✅; Serena ✅; Playwright ✅; Tavily ✅; File ✅; Bash ✅; Discussion ✅
Overall: PASS
Update workflows to actions/checkout v6
[instructions] Sync github-agentic-workflows.md with latest schema features
Add copilot-setup.md prompt for automated repository configuration
Update CLI versions: Copilot 0.0.395, GitHub MCP v0.30.1, Playwright 0.0.60, Gateway v0.0.80

AI generated by Smoke Codex

[github-actions]

Smoke Test Results

PRs Tested:

• Update workflows to actions/checkout v6 #11935: Update workflows to actions/checkout v6
• [instructions] Sync github-agentic-workflows.md with latest schema features #11939: Sync github-agentic-workflows.md with latest schema features

Status:

• ✅ GitHub MCP
• ✅ Safe Inputs GH CLI
• ✅ Serena MCP
• ✅ Playwright
• ✅ File Writing
• ✅ Bash Tool
• ✅ Discussion Interaction

Overall: ✅ PASS

@pelikhan @Copilot

AI generated by Smoke Copilot

[github-actions]

📰 VERDICT: Smoke Copilot has concluded. All systems operational. This is a developing story. 🎤

[github-actions]

Smoke Test Results - Claude Engine

Status: ✅ PASS (9/9 tests)

Merged PRs Reviewed:

• Update workflows to actions/checkout v6 #11935 - Update workflows to actions/checkout v6
• [instructions] Sync github-agentic-workflows.md with latest schema features #11939 - Sync github-agentic-workflows.md with latest schema features

Tests:
✅ GitHub MCP
✅ Safe Inputs GH CLI
✅ Serena MCP
✅ Make Build
✅ Playwright
✅ Tavily Search
✅ File Writing
✅ Bash Tool
✅ Discussion Interaction

Run: §21373219714

AI generated by Smoke Claude

[pelikhan]

@copilot merge main and recompile

[Copilot]

@copilot merge main and recompile

Merged main and recompiled workflows. Resolved conflicts by accepting main branch changes. Commit: 32a004c