debugging-workflows（调试工作流程）

Debugging GitHub Agentic Workflows

This skill provides comprehensive guidance for debugging GitHub Agentic Workflows, including scripts to download and analyze workflow logs, audit specific runs, and understand how agentic workflows operate.

Table of Contents

• Quick Start
• Downloading Workflow Logs
• Auditing Specific Runs
• How Agentic Workflows Work
• Common Issues and Solutions
• Advanced Debugging Techniques
• Reference Commands

Quick Start

Download Logs from Recent Runs

# Download logs from the last 24 hours
gh aw logs --start-date -1d -o /tmp/workflow-logs

# Download logs for a specific workflow
gh aw logs weekly-research --start-date -1d

# Download logs with JSON output for programmatic analysis
gh aw logs --json

Audit a Specific Run

# Audit by run ID
gh aw audit 1234567890

# Audit from a GitHub Actions URL
gh aw audit https://github.com/owner/repo/actions/runs/1234567890

# Audit with JSON output
gh aw audit 1234567890 --json

Downloading Workflow Logs

The gh aw logs command downloads workflow run artifacts and logs from GitHub Actions for analysis.

Basic Usage

# Download logs for all workflows (last 10 runs)
gh aw logs

# Download logs for a specific workflow
gh aw logs <workflow-name>

# Download with custom output directory
gh aw logs -o ./my-logs

Filter Options

# Filter by date range
gh aw logs --start-date 2024-01-01 --end-date 2024-01-31
gh aw logs --start-date -1w                    # Last week
gh aw logs --start-date -1mo                   # Last month

# Filter by AI engine
gh aw logs --engine copilot
gh aw logs --engine claude
gh aw logs --engine codex

# Filter by count
gh aw logs -c 5                                # Last 5 runs

# Filter by branch/tag
gh aw logs --ref main
gh aw logs --ref feature-xyz

# Filter by run ID range
gh aw logs --after-run-id 1000 --before-run-id 2000

# Filter firewall-enabled runs
gh aw logs --firewall                          # Only firewall-enabled
gh aw logs --no-firewall                       # Only non-firewall

Output Options

# Generate JSON summary
gh aw logs --json

# Parse agent logs and generate Markdown reports
gh aw logs --parse

# Generate Mermaid tool sequence graph
gh aw logs --tool-graph

# Set download timeout
gh aw logs --timeout 300                       # 5 minute timeout

Downloaded Artifacts

When you run gh aw logs, the following artifacts are downloaded for each run:

Example: Analyze Recent Failures

# Download failed runs from last week
gh aw logs --start-date -1w -o /tmp/debug-logs

# Check the summary for patterns
cat /tmp/debug-logs/summary.json | jq '.runs[] | select(.conclusion == "failure")'

Auditing Specific Runs

The gh aw audit command investigates a single workflow run in detail, downloading artifacts, detecting errors, and generating a report.

Basic Usage

# Audit by numeric run ID
gh aw audit 1234567890

# Audit from GitHub Actions URL
gh aw audit https://github.com/owner/repo/actions/runs/1234567890

# Audit from job URL (extracts first failing step)
gh aw audit https://github.com/owner/repo/actions/runs/1234567890/job/9876543210

# Audit from job URL with specific step
gh aw audit https://github.com/owner/repo/actions/runs/1234567890/job/9876543210#step:7:1

Output Options

# JSON output for programmatic analysis
gh aw audit 1234567890 --json

# Custom output directory
gh aw audit 1234567890 -o ./audit-reports

# Parse agent logs and firewall logs
gh aw audit 1234567890 --parse

# Verbose output
gh aw audit 1234567890 -v

Audit Report Contents

The audit command provides:

• Error Detection: Errors and warnings from workflow logs
• MCP Tool Usage: Statistics on tool calls by the AI agent
• Missing Tools: Tools the agent tried to use but weren't available
• Execution Metrics: Duration, token usage, and cost information
• Safe Output Analysis: What GitHub operations were attempted

Example: Investigate a Failed Run

# Get detailed audit report
gh aw audit 1234567890 --json > audit.json

# Extract key information
cat audit.json | jq '{
  status: .status,
  conclusion: .conclusion,
  errors: .errors,
  missing_tools: .missing_tools,
  tool_usage: .tool_usage
}'

How Agentic Workflows Work

Understanding the workflow architecture helps in debugging.

Workflow Structure

Agentic workflows use a markdown + YAML frontmatter format:

---
on:
  issues:
    types: [opened]
permissions:
  issues: write
timeout-minutes: 10
engine: copilot
tools:
  github:
    mode: remote
    toolsets: [default]
safe-outputs:
  create-issue:
    labels: [ai-generated]
---

# Workflow Title

Natural language instructions for the AI agent.

Use GitHub context like ${{ github.event.issue.number }}.

Execution Flow

1. Trigger Event (issue opened, PR created, schedule, etc.)
     ↓
2. Activation Job
   - Validates permissions
   - Processes mcp-scripts
   - Sanitizes context
     ↓
3. AI Agent Job
   - Loads MCP servers and tools
   - Executes AI agent with prompt
   - Agent makes tool calls
   - Agent produces output
     ↓
4. Safe Outputs Job
   - Processes agent output
   - Creates GitHub resources (issues, PRs, etc.)
   - Applies labels, comments
     ↓
5. Completion
   - Workflow summary generated
   - Artifacts uploaded

Key Components

Compilation Process

# Compile workflow to GitHub Actions YAML
gh aw compile <workflow-name>

# Result: .github/workflows/<name>.md → .github/workflows/<name>.lock.yml

The .lock.yml file is the actual GitHub Actions workflow that runs.

Common Issues and Solutions

Missing Tool Errors

Symptoms:

• Error: "Tool 'github:read_issue' not found"
• Agent cannot access GitHub APIs

Solution: Add GitHub MCP server configuration:

tools:
  github:
    mode: remote
    toolsets: [default]

Permission Errors

Symptoms:

• HTTP 403 (Forbidden) errors
• "Resource not accessible" errors

Solution: Add required permissions:

permissions:
  contents: read
  issues: write
  pull-requests: write

Safe-Input Errors

Symptoms:

• "missing tool configuration for mcpscripts-gh"
• Environment variable not available

Solution: Configure mcp-scripts:

mcp-scripts:
  issue:
    script: |
      return { title: process.env.ISSUE_TITLE, body: process.env.ISSUE_BODY };
    env:
      ISSUE_TITLE: ${{ github.event.issue.title }}
      ISSUE_BODY: ${{ github.event.issue.body }}

Safe-Output Errors

Symptoms:

• Agent tries to create resources but fails
• "Safe output not enabled" errors

Solution: Enable safe-outputs:

safe-outputs:
  staged: false  # Set to false to actually create resources
  create-issue:
    labels: [ai-generated]

Network Access Errors

Symptoms:

• Firewall denials
• URLs appearing as "(redacted)"

Solution: Configure network access:

network:
  allowed:
    - defaults
    - python    # For PyPI
    - node      # For npm
    - "api.example.com"  # Custom domains

Timeout Errors

Symptoms:

• Workflow exceeds time limit
• Agent loops or hangs

Solution: Increase timeout or optimize prompt:

timeout-minutes: 30  # Increase from default

Advanced Debugging Techniques

Polling In-Progress Runs

When a run is still executing:

# Poll until completion
while true; do
  output=$(gh aw audit <run-id> --json 2>&1)
  if echo "$output" | grep -q '"status":.*"\(completed\|failure\|cancelled\)"'; then
    echo "$output"
    break
  fi
  echo "⏳ Run still in progress. Waiting 45 seconds..."
  sleep 45
done

Inspecting MCP Configuration

# Inspect MCP servers for a workflow
gh aw mcp inspect <workflow-name>

# List all workflows with MCP servers
gh aw mcp list

Checking Workflow Status

# Show status of all agentic workflows
gh aw status

Downloading Specific Artifacts

# Download only the agent log artifact
GH_REPO=owner/repo gh run download <run-id> -n agent-stdio.log

Inspecting Job Logs

# View specific job logs
gh run view <run-id>
gh run view --job <job-id> --log

Analyzing Firewall Logs

# Parse firewall logs for network issues
gh aw logs --parse

# Check firewall-enabled runs
gh aw logs --firewall

Debug Mode Compilation

# Compile with verbose output
gh aw compile --verbose

# Compile with strict security checks
gh aw compile --strict

# Run security scanners
gh aw compile --actionlint --zizmor --poutine

Reference Commands

Log Analysis Commands

Audit Commands

MCP Commands

Status Commands

Workflow Execution Commands

Additional Resources

• Workflow Health Monitoring Runbook - Step-by-step investigation procedures
• Common Issues Reference - Frequently encountered issues
• Error Reference - Error codes and solutions
• GitHub MCP Server Documentation - Tool configuration reference