# Bug Reproduction Root Cause Hunter

## Overview

Turn loose bug reports into a repeatable debugging workflow with evidence at each step.

## Core Workflow

1. Normalize the report. Capture expected behavior, actual behavior, exact errors, inputs, and environment details.
2. Reproduce the failure. Use existing tests, app commands, logs, or a minimal repro path before theorizing.
3. Narrow the surface. Identify the smallest set of files, conditions, flags, data states, or requests needed to trigger the bug.
4. Test hypotheses. Inspect recent diffs, surrounding code, and related tests to validate likely causes.
5. Propose the fix path. Recommend the smallest safe change, the regression test to add, and any rollout concerns.

## Deliver

- Provide exact repro steps when reproduction succeeds.
- State the most likely root cause with concrete evidence.
- If reproduction fails, document what was tried, what remains plausible, and the next best experiment.
- Keep the fix plan separate from the diagnosis.

## Guardrails

- Do not claim certainty without evidence.
- Prefer recent changes and environment differences as early suspects, not automatic conclusions.
- Preserve any raw error output needed to debug further.