Test Feedback

Spawn a background agent to parse test failures and fix them.

Arguments

The user may provide a file path to test output. Default: /tmp/output

Process

1. Determine the output path. Use whatever the user provided, or /tmp/output if not specified.

2. Verify the file exists by reading it. If it doesn't exist or is empty, ask the user where the output is. Do NOT spawn an agent without valid test output.

3. Spawn a background agent using the Agent tool with run_in_background: true. Include in the agent prompt: