Add debug-github-ci and debug-jenkins-ci skills

marketplaces/default.json

@@ -400,6 +400,32 @@
                 "preview",
                 "hosting"
             ]
+        },
+        {
+            "name": "debug-github-ci",
+            "source": "./debug-github-ci",
+            "description": "Debug GitHub Actions CI failures by fetching logs, identifying root causes, and suggesting fixes.",
+            "category": "debugging",
+            "keywords": [
+                "github",
+                "ci",
+                "actions",
+                "debugging",
+                "workflow"
+            ]
+        },
+        {
+            "name": "debug-jenkins-ci",
+            "source": "./debug-jenkins-ci",
+            "description": "Debug Jenkins CI/CD pipeline failures by fetching logs, identifying root causes, and suggesting fixes.",
+            "category": "debugging",
+            "keywords": [
+                "jenkins",
+                "ci",
+                "pipeline",
+                "debugging",
+                "build"
+            ]
         }
     ]
 }

plugins/debug-github-ci/README.md

@@ -0,0 +1,151 @@
+# Debug GitHub CI Plugin
+
+Automated debugging of GitHub Actions CI failures using OpenHands agents. This plugin provides GitHub workflows that automatically diagnose and suggest fixes when CI fails.
+
+## Quick Start
+
+Copy the workflow file to your repository:
+
+```bash
+mkdir -p .github/workflows
+curl -o .github/workflows/debug-ci-failure.yml \
+  https://raw.githubusercontent.com/OpenHands/extensions/main/plugins/debug-github-ci/workflows/debug-ci-failure.yml
+```
+
+Then configure the required secrets (see [Installation](#installation) below).
+
+## Features
+
+- **Automatic CI Failure Analysis**: Triggered when workflow runs fail
+- **Log Analysis**: Fetches and analyzes failed job logs to identify root causes
+- **Actionable Suggestions**: Posts comments with specific fixes and commands
+- **Error Pattern Recognition**: Identifies common CI failure patterns
+- **Context-Aware**: Considers recent commits and PR changes
+
+## Plugin Contents
+
+```
+plugins/debug-github-ci/
+├── README.md              # This file
+├── action.yml             # Composite GitHub Action
+├── skills/                # Symbolic links to debug skills
+│   └── debug-github-ci -> ../../../skills/debug-github-ci
+├── workflows/             # Example GitHub workflow files
+│   └── debug-ci-failure.yml
+└── scripts/               # Python scripts for debug execution
+    ├── agent_script.py    # Main CI debug agent script
+    └── prompt.py          # Prompt template for debugging
+```
+
+## Installation
+
+### 1. Copy the Workflow File
+
+Copy the workflow file to your repository's `.github/workflows/` directory:
+
+```bash
+mkdir -p .github/workflows
+curl -o .github/workflows/debug-ci-failure.yml \
+  https://raw.githubusercontent.com/OpenHands/extensions/main/plugins/debug-github-ci/workflows/debug-ci-failure.yml
+```
+
+### 2. Configure Secrets
+
+Add the following secrets in your repository settings (**Settings → Secrets and variables → Actions**):
+
+| Secret | Required | Description |
+|--------|----------|-------------|
+| `LLM_API_KEY` | Yes | API key for your LLM provider |
+| `GITHUB_TOKEN` | Auto | Provided automatically by GitHub Actions |
+
+### 3. Customize the Workflow (Optional)
+
+Edit the workflow file to customize:
+
+```yaml
+- name: Debug CI Failure
+  uses: OpenHands/extensions/plugins/debug-github-ci@main
+  with:
+    # LLM model to use
+    llm-model: anthropic/claude-sonnet-4-5-20250929
+
+    # Secrets
+    llm-api-key: ${{ secrets.LLM_API_KEY }}
+    github-token: ${{ secrets.GITHUB_TOKEN }}
+```
+
+## Usage
+
+### Automatic Triggers
+
+CI debugging is automatically triggered when:
+
+1. A workflow run fails on the repository
+2. The `debug-ci` label is added to a PR with failed checks
+
+### Manual Trigger
+
+You can manually trigger debugging:
+
+1. Go to **Actions** tab
+2. Select **Debug CI Failure** workflow
+3. Click **Run workflow**
+4. Enter the failed run ID
+
+## Action Inputs
+
+| Input | Required | Default | Description |
+|-------|----------|---------|-------------|
+| `llm-model` | No | `anthropic/claude-sonnet-4-5-20250929` | LLM model to use |
+| `llm-base-url` | No | `''` | Custom LLM endpoint URL |
+| `run-id` | No | Auto | Specific workflow run ID to debug |
+| `extensions-repo` | No | `OpenHands/extensions` | Extensions repository |
+| `extensions-version` | No | `main` | Git ref (tag, branch, or SHA) |
+| `llm-api-key` | Yes | - | LLM API key |
+| `github-token` | Yes | - | GitHub token for API access |
+
+## What Gets Analyzed
+
+The agent analyzes:
+
+1. **Failed job logs**: Console output from failed steps
+2. **Error messages**: Specific error patterns and stack traces
+3. **Recent commits**: Changes that may have caused the failure
+4. **Workflow configuration**: Issues in the workflow YAML
+5. **Dependencies**: Version conflicts or missing packages
+
+## Output
+
+The agent posts a comment with:
+
+- **Root Cause Analysis**: What caused the failure
+- **Suggested Fixes**: Specific commands or code changes
+- **Prevention Tips**: How to avoid similar failures
+
+## Troubleshooting
+
+### Debug Not Triggered
+
+1. Ensure the workflow file is in `.github/workflows/`
+2. Verify secrets are configured correctly
+3. Check that the workflow has `workflow_run` trigger permissions
+
+### Analysis Incomplete
+
+1. Check if logs are available (some expire after 90 days)
+2. Verify the `GITHUB_TOKEN` has read access to workflow logs
+3. Increase timeout if analysis takes too long
+
+## Security
+
+- Uses `workflow_run` event for secure access to secrets
+- Only analyzes public workflow logs
+- Does not execute any code from the failed run
+
+## Contributing
+
+See the main [extensions repository](https://github.com/OpenHands/extensions) for contribution guidelines.
+
+## License
+
+This plugin is part of the OpenHands extensions repository. See [LICENSE](../../LICENSE) for details.

plugins/debug-github-ci/action.yml

@@ -0,0 +1,122 @@
+---
+name: OpenHands Debug GitHub CI
+description: Automated CI failure debugging using OpenHands agent
+author: OpenHands
+
+branding:
+    icon: alert-circle
+    color: red
+
+inputs:
+    llm-model:
+        description: LLM model to use for debugging
+        required: false
+        default: anthropic/claude-sonnet-4-5-20250929
+    llm-base-url:
+        description: LLM base URL (optional, for custom LLM endpoints)
+        required: false
+        default: ''
+    run-id:
+        description: Specific workflow run ID to debug (auto-detected if not provided)
+        required: false
+        default: ''
+    extensions-repo:
+        description: GitHub repository for extensions (owner/repo)
+        required: false
+        default: OpenHands/extensions
+    extensions-version:
+        description: Git ref to use for extensions (tag, branch, or commit SHA)
+        required: false
+        default: main
+    llm-api-key:
+        description: LLM API key (required)
+        required: true
+    github-token:
+        description: GitHub token for API access (required)
+        required: true
+
+runs:
+    using: composite
+    steps:
+        - name: Checkout extensions repository
+          uses: actions/checkout@v4
+          with:
+              repository: ${{ inputs.extensions-repo }}
+              ref: ${{ inputs.extensions-version }}
+              path: extensions
+
+        - name: Set up Python
+          uses: actions/setup-python@v5
+          with:
+              python-version: '3.12'
+
+        - name: Install uv
+          uses: astral-sh/setup-uv@v6
+          with:
+              enable-cache: true
+
+        - name: Install GitHub CLI
+          shell: bash
+          run: |
+              sudo apt-get update
+              sudo apt-get install -y gh
+
+        - name: Determine run ID
+          id: get-run-id
+          shell: bash
+          env:
+              GITHUB_TOKEN: ${{ inputs.github-token }}
+              INPUT_RUN_ID: ${{ inputs.run-id }}
+          run: |
+              if [ -n "$INPUT_RUN_ID" ]; then
+                echo "run_id=$INPUT_RUN_ID" >> $GITHUB_OUTPUT
+              elif [ -n "${{ github.event.workflow_run.id }}" ]; then
+                echo "run_id=${{ github.event.workflow_run.id }}" >> $GITHUB_OUTPUT
+              else
+                # Get the most recent failed run
+                RUN_ID=$(gh run list --status failure --limit 1 --json databaseId --jq '.[0].databaseId')
+                echo "run_id=$RUN_ID" >> $GITHUB_OUTPUT
+              fi
+
+        - name: Check required configuration
+          shell: bash
+          env:
+              LLM_API_KEY: ${{ inputs.llm-api-key }}
+              GITHUB_TOKEN: ${{ inputs.github-token }}
+          run: |
+              if [ -z "$LLM_API_KEY" ]; then
+                echo "Error: llm-api-key is required."
+                exit 1
+              fi
+
+              if [ -z "$GITHUB_TOKEN" ]; then
+                echo "Error: github-token is required."
+                exit 1
+              fi
+
+              echo "Run ID to debug: ${{ steps.get-run-id.outputs.run_id }}"
+              echo "Repository: ${{ github.repository }}"
+              echo "LLM model: ${{ inputs.llm-model }}"
+
+        - name: Run CI debug analysis
+          shell: bash
+          env:
+              LLM_MODEL: ${{ inputs.llm-model }}
+              LLM_BASE_URL: ${{ inputs.llm-base-url }}
+              LLM_API_KEY: ${{ inputs.llm-api-key }}
+              GITHUB_TOKEN: ${{ inputs.github-token }}
+              RUN_ID: ${{ steps.get-run-id.outputs.run_id }}
+              REPO_NAME: ${{ github.repository }}
+          run: |
+              uv run --with openhands-sdk --with openhands-tools \
+                python extensions/plugins/debug-github-ci/scripts/agent_script.py
+
+        - name: Upload logs as artifact
+          uses: actions/upload-artifact@v4
+          if: always()
+          with:
+              name: openhands-ci-debug-logs
+              path: |
+                  *.log
+                  output/
+              retention-days: 7