diagnose

# /supergraph:diagnose Systematic debugging. Never guess and patch — build a feedback loop, prove the hypothesis, fix once. Announce: "🐛 /supergraph:diagnose — building feedback loop..." ## Setup **Read `.supergraph-env` for test/lint commands (if exists):** ```bash [ -f .supergraph-env ] && source .supergraph-env ``` This sets `$TEST_CMD`, `$FOCUSED_TEST_CMD`, `$LINT_CMD`. If absent, detect from project config (package.json → jest/vitest, pubspec.yaml → flutter test, etc.) same as `/supergraph:scan`. ## Phases ### Phase 1 — Build Feedback Loop Before touching any code, establish a fast, deterministic way to observe the bug. ```bash # Identify the smallest command that shows the failure $TEST_CMD --grep "<failing test name>" # focused test run # or <minimal repro command> ``` **Goal:** failure visible in < 5 seconds. If not, slim down the repro. Do NOT skip this phase. Debugging without a feedback loop is guessing. ### Phase 2 — Reproduce Cleanly - Run the feedback loop 3 times — confirm it fails consistently - Capture exact error output, stack trace, exit code - Note any flakiness → treat as separate bug before continuing - Add a failing regression test if one doesn't exist: ``` test("<bug description>", () => { ... }) // RED ``` ### Phase 3 — Hypothesize (3-5 ranked theories) List falsifiable hypotheses, ordered most-to-least likely: ``` 1. [Most likely] — [reason] — [how to falsify] 2. [Second] — [reason] — [how to falsify] 3. [Third] — [r...