investigate-bug-reportlisted

# Investigate Bug Report Diagnose, don't fix. The deliverable is a root-cause finding with evidence — apply a fix only if the user then asks. ## Steps 1. **Pin down the report.** Extract from the report (ask only for what's missing and blocking): observed behavior, expected behavior, steps or input that trigger it, environment/version if relevant. - Completion criterion: you can state "given X, it does Y, but should do Z" in one sentence. 2. **Reproduce — or trace when you can't.** Prefer an actual reproduction (run the failing command, a minimal script, or an existing test tightened to the case). When reproduction isn't feasible (needs external services, prod-only data), trace the code path statically from the entry point the report implies, and say the diagnosis is trace-based. - Completion criterion: the failure is observed firsthand, or the full path from trigger to symptom is traced with `file:line` hops. 3. **Isolate the root cause.** Follow the data from symptom back to the first point where state or logic diverges from intent. Distinguish the **root cause** from where the error surfaces — they are usually different lines. Check `git log`/`git blame` on the suspect code: a recent change that introduced it is strong corroborating evidence. - Completion criterion: one specific location (`file:line`) and mechanism explains every symptom in the report. A cause that explains only some symptoms is a co-incident