docs(qa): autonomous run-to-completion mode — never stop; unblock by fixing; finish to flawless

Adds Execution-mode directive: run all passes -> fixes -> re-QA continuously to a flawless
round without checking in; fix anything that BLOCKS progress inline (stale data, crash, build
break, broken nav) to keep going; context limits = checkpoint not stop. Only a denied gated
action (prod deploy / admin write / entitlement toggle) may be surfaced, after all other work.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

ClaudeQAPlan.md

@@ -22,6 +22,26 @@ Scope decisions: **exhaustive** visual pass (all ~50 screens, both modes); **ful
 `EntitlementChecker.isPremium()` — so premium almost certainly does NOT unlock for the free partner there. Pass A
 confirms + enumerates this; the fix phase applies couple-shared everywhere.
 
+## Execution mode — run to completion (autonomous; do NOT stop)
+- **Do not stop to check in or ask for approval.** Run all five passes → the fix phase → re-QA rounds **continuously
+  until a flawless round** (zero open P0–P2, Passes D + E clean, every game fully played through, navigation/back-stack
+  verified). Don't hand control back early.
+- **Unblock yourself:** if anything **blocks progress** (a stale/blocking session, a crash, a build break, a missing
+  prerequisite state, a broken nav path that prevents reaching a screen), **fix it immediately and continue** — even
+  though passes are otherwise report-only. Blocking issues are fixed inline so the run can proceed; non-blocking
+  findings are still logged and fixed in the fix phase.
+- **"Once executed, complete it":** never declare done before the Definition of Done is met — keep cycling fix → re-QA
+  until flawless, then stop.
+- **Context limits ≠ stopping.** If a context window fills, that's a checkpoint, not a stop: make sure the run-state
+  header + MD files are current and committed; the resume command continues automatically. Keep the loop alive across
+  sessions until flawless.
+- **Don't pause for "by-design vs bug":** log the ambiguous finding and keep going (don't unilaterally rewrite
+  deliberate design — the log captures it). Never halt the run to ask.
+- **Only true stop = a gated action you cannot perform.** Production deploys, admin Firestore writes/seeds, and
+  entitlement toggles still need per-occurrence authorization (the classifier enforces this regardless of this doc).
+  If one is genuinely required to proceed and is denied, do **all** other work first, then surface only that single
+  blocker — don't halt the whole run for it.
+
 ## Methodology (every pass)
 - Devices: **5554 (QA)**, **5556 (Sam)**, paired; one **fresh throwaway account** for pre-pairing flows.
 - Drive via adb tap/swipe; resolve coords from `uiautomator dump` bounds; downscale screenshots to read;
@@ -53,7 +73,7 @@ State lives in **files**, not memory:
 ## Guardrails & efficiency
 - **Never `pm clear` / wipe app data** — breaks the App Check debug token. Pre-pairing QA: sign-out → fresh sign-up.
 - **Never run `seed/build_db.py`.** Admin seeds/writes, entitlement toggles, and any deploys are **user-authorized per occurrence**.
-- **By-design vs bug:** if a finding may be intended behavior, log it and **confirm with the user before changing it**.
+- **By-design vs bug:** if a finding may be intended behavior, **log it and keep going** (don't stop to ask; don't unilaterally rewrite deliberate design — the log captures it).
 - **Pass C parallelism:** set **5554 = Dark, 5556 = Light** to capture both themes at once.
 - Never log decrypted message/answer content.
 

ClaudeReport.md

@@ -2,6 +2,7 @@
 
 > **RUN-STATE: Round 2 (re-QA + deferred coverage) NEXT | NEXT ACTION: re-verify A-001 + E-001 fixes; **play each game ONE complete time through on both devices** (Pass B was launch-only — full playthroughs still owed); then Pass C deep/stateful screens (reveal, wheel session, dates, bucket list, auth/onboarding) in both themes + **navigation from every entry point & back-stack/double-back checks**, full live notification matrix, D3 live non-member test.**
 > Round 1 complete (all 5 passes run report-only; P0–P2 found were fixed in-line). Fixes: A-001 (e8892a9), E-001 (ce12abb). Open P3: A-003, B-001, E-002.
+> **EXECUTION MODE: autonomous run-to-completion — do NOT stop; fix anything that blocks progress and continue; keep cycling fix→re-QA until a flawless round. Only a gated action (prod deploy / admin write / entitlement toggle) that's denied may be surfaced — do all other work first.**
 > Playbook: `ClaudeQAPlan.md`. Coverage matrix: `ClaudeQACoverage.md`. Report-only during passes (no fixes until the fix phase).
 > Devices: emulator-5554 (QA=`Y05AKO`) + emulator-5556 (Sam=`imDjjO`), paired (coupleId `Xal3Kw3gjSdn0niERYKJ`). Build == HEAD `64f0a7e`.