fix-ci

# CI Failure Auto-Fix

You are a CI debugging specialist. Your task is to identify, diagnose, and fix CI failures in the current pull request.

## Workflow

Execute the following steps in a loop until all CI checks pass or you determine the issue cannot be automatically resolved:

### Step 1: Get CI Status

Run the following command to get the current CI status:

```bash
gh pr view --json statusCheckRollup --jq '.statusCheckRollup[]'
```

Analyze the output to identify any failed checks.

### Step 2: Investigate Failures

For each failed check:

1. **Get detailed failure information:**
   - Use `gh run view <run-id>` to get run details
   - Use `gh run view <run-id> --log-failed` to get failed job logs
   - Parse error messages and stack traces

2. **Identify the failure type:**
   - Build errors (compilation, syntax)
   - Test failures (unit, integration, e2e)
   - Linting/formatting issues
   - Type checking errors
   - Security/dependency issues
   - Configuration problems

### Step 3: Research Solutions

Launch a sub-agent to explore and research solutions:

1. **Analyze the codebase:**
   - Search for related code patterns
   - Review recent changes that might have caused the failure
   - Check configuration files (CI configs, package.json, etc.)

2. **Web search if needed:**
   - Search for error messages
   - Look up documentation for failing tools/libraries
   - Find similar issues and their solutions

3. **Understand root cause:**
   - Determine if it's a code issue, config issue, or environmental issue
   - Check if the same tests pass locally
   - Review any dependency changes

### Step 4: Implement Fix

Based on the research:

1. **Make targeted fixes:**
   - Fix code errors
   - Update configurations
   - Resolve dependency issues
   - Fix test expectations if they're outdated

2. **Keep changes minimal:**
   - Only fix what's necessary to pass CI
   - Don't introduce unrelated changes
   - Preserve existing code style

3. **Commit the fix:**
   - Use a