Build an AI Pipeline Failure Analyzer with GitHub Actions and Claude API

name: Analyze CI Failure
 
on:
  workflow_run:
    workflows: ["CI", "Build and Deploy"]   # Trigger when these fail
    types: [completed]
 
jobs:
  analyze:
    if: ${{ github.event.workflow_run.conclusion == 'failure' }}
    runs-on: ubuntu-latest
    permissions:
      actions: read
      pull-requests: write
 
    steps:
      - name: Analyze failure with Claude
        uses: actions/github-script@v7
        env:
          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
        with:
          github-token: ${{ secrets.GITHUB_TOKEN }}
          script: |
            const { analyzeFailure } = require('./scripts/analyze-failure.js');
            await analyzeFailure({ github, context });

const https = require('https');
 
async function callClaude(prompt) {
  return new Promise((resolve, reject) => {
    const body = JSON.stringify({
      model: 'claude-sonnet-5',
      max_tokens: 2000,
      messages: [{ role: 'user', content: prompt }]
    });
 
    const options = {
      hostname: 'api.anthropic.com',
      path: '/v1/messages',
      method: 'POST',
      headers: {
        'Content-Type': 'application/json',
        'x-api-key': process.env.ANTHROPIC_API_KEY,
        'anthropic-version': '2023-06-01',
        'Content-Length': Buffer.byteLength(body)
      }
    };
 
    const req = https.request(options, (res) => {
      let data = '';
      res.on('data', chunk => data += chunk);
      res.on('end', () => {
        const parsed = JSON.parse(data);
        resolve(parsed.content[0].text);
      });
    });
 
    req.on('error', reject);
    req.write(body);
    req.end();
  });
}
 
 
async function getFailedJobLogs(github, owner, repo, runId) {
  // Get list of jobs
  const jobs = await github.rest.actions.listJobsForWorkflowRun({
    owner, repo, run_id: runId
  });
 
  const failedJobs = jobs.data.jobs.filter(job => job.conclusion === 'failure');
 
  const logsPerJob = [];
  for (const job of failedJobs.slice(0, 3)) {  // Max 3 jobs
    try {
      const logs = await github.rest.actions.downloadJobLogsForWorkflowRun({
        owner, repo, job_id: job.id
      });
 
      // Extract last 200 lines — where errors usually are
      const logText = typeof logs.data === 'string'
        ? logs.data.split('\n').slice(-200).join('\n')
        : String(logs.data).slice(-8000);
 
      logsPerJob.push({
        jobName: job.name,
        conclusion: job.conclusion,
        logs: logText
      });
    } catch (e) {
      logsPerJob.push({ jobName: job.name, logs: `Could not fetch logs: ${e.message}` });
    }
  }
 
  return logsPerJob;
}
 
 
async function analyzeFailure({ github, context }) {
  const run = context.payload.workflow_run;
  const owner = context.repo.owner;
  const repo = context.repo.repo;
 
  console.log(`Analyzing failure for run ${run.id}: ${run.name}`);
 
  // Get failed job logs
  const failedJobLogs = await getFailedJobLogs(github, owner, repo, run.id);
 
  if (failedJobLogs.length === 0) {
    console.log('No failed jobs found');
    return;
  }
 
  // Build prompt for Claude
  const logsFormatted = failedJobLogs.map(job =>
    `## Job: ${job.jobName}\n\`\`\`\n${job.logs}\n\`\`\``
  ).join('\n\n');
 
  const prompt = `You are a CI/CD expert analyzing a GitHub Actions pipeline failure.
 
## Workflow Information
- Workflow: ${run.name}
- Branch: ${run.head_branch}
- Commit: ${run.head_sha.slice(0, 8)}
- Trigger: ${run.event}
 
## Failed Job Logs
${logsFormatted}
 
Analyze this failure and provide:
1. **Root Cause** (1-2 sentences): What exactly caused the failure
2. **Category**: test-failure | build-error | dependency-issue | config-error | flaky-test | infra-issue | permission-error
3. **Fix** (specific steps or code to resolve it)
4. **Confidence**: high | medium | low
5. **Estimated Fix Time**: e.g. "5 minutes", "30 minutes", "1-2 hours"
 
Format your response as a GitHub PR comment using markdown. Start with an emoji that reflects severity (🔴 critical, 🟡 flaky/infra, 🟢 easy fix).`;
 
  const analysis = await callClaude(prompt);
 
  // Find the PR associated with this workflow run
  const prs = await github.rest.pulls.list({
    owner, repo,
    head: `${owner}:${run.head_branch}`,
    state: 'open'
  });
 
  const comment = `## 🤖 AI Failure Analysis
 
**Workflow:** ${run.name} | **Job(s):** ${failedJobLogs.map(j => j.jobName).join(', ')}
 
${analysis}
 
---
*Analyzed by Claude AI · [View failed run](${run.html_url})*`;
 
  if (prs.data.length > 0) {
    // Post to the PR
    const prNumber = prs.data[0].number;
    await github.rest.issues.createComment({
      owner, repo,
      issue_number: prNumber,
      body: comment
    });
    console.log(`Posted analysis to PR #${prNumber}`);
  } else {
    // Post to commit if no PR
    await github.rest.repos.createCommitComment({
      owner, repo,
      commit_sha: run.head_sha,
      body: comment
    });
    console.log(`Posted analysis to commit ${run.head_sha.slice(0, 8)}`);
  }
}
 
module.exports = { analyzeFailure };

## 🤖 AI Failure Analysis
 
**Workflow:** CI | **Job(s):** test, build
 
🔴 **Root Cause**: The Docker build failed because the base image 
`python:3.11-slim` changed and the new version removed `libpq-dev`. 
Your requirements.txt includes `psycopg2==2.9.9` which requires PostgreSQL 
client libraries at build time.
 
**Category**: dependency-issue | **Confidence**: high | **Estimated Fix Time**: 15 minutes
 
**Fix**:
Option 1 — Install build dependency explicitly:
```dockerfile
RUN apt-get update && apt-get install -y libpq-dev gcc && rm -rf /var/lib/apt/lists/*