Verify native Advanced full-plan card interactions

Replace the Basic-then-flip battle fixture with actual Advanced setup and add
five tests covering Truthtrance, Voice, ordinary Prescience, Ghola preparation,
private inspection and interrupted decisions. No runtime changes were needed.
Keep the special offer deadline and target-first ordering explicitly provisional.

Update the development maintenance policy per the user's instruction: restart
only when a change or observed server condition warrants it, preserving saves
and verifying restoration. No hourly schedule or recurring automation.

Validation: npm run check passed: types, lint and all 4,205 offline tests
(124.980 seconds). Source fingerprint:
5792403ddfed7ea7f4e0b247d367e7c000dfce6c81e1553204d9c00db376c3f6.
Private report: 20260913-full-plan-final/report.json.
Earlier build and HTTP evidence are reused for unchanged runtime code.
Independent source/test review found no actionable defect in this boundary.
Browser AZC4HGLB covers human inspection and Medium AI Ghola preparation,
desktop/phone readability and private refresh after the completed restart.
The earlier inventory seat also restored; all 64 saved room versions/hashes
remain unchanged. No mode or publication gate is opened.

Aggregate goal counters: 59,151,671 at batch start to 59,509,237 after completed
verification, or 357,566 tokens before final Git and new goal-steering overhead.
One bounded workhorse helper reused for source and independent test review;
one stable broad check. This is an audit batch, not a new gameplay capability.

docs/BASE_ADVANCED_READINESS_20260907.md

@@ -37,6 +37,18 @@ These are actual recorded implementation choices, not missing expansion componen
 
 The broad Truthtrance language creates an engineering and guidance gap even if some natural-language enforcement requires a later user interpretation. It should not be disguised as an ambiguity that excuses all knowable structured questions.
 
+## 13 September full-plan interaction follow-up
+
+The [full-plan interaction audit](ATREIDES_FULL_PLAN_TIMING.md) now verifies the
+native Voice/ordinary Prescience/Truthtrance/Ghola paths discussed above, including
+seven interruption windows, all four AI profiles, private inspection and JSON
+continuation. `tests/full-plan.test.ts` uses actual Advanced setup before staging
+the battle. No runtime change was required for those paths. The special offer's
+precise deadline and target-first ordering remain implementation choices not
+settled by the retrieved GF9 text. Keep those source limitations and all wider
+mode gates; the old statement that this particular interaction audit remains
+undone is superseded by the linked record.
+
 ## Implemented mechanisms to preserve and verify in integration
 
 | Requirement                                    | Current authoritative evidence                                                                                                                                                                                                                                                                                                                                                                    | What that evidence does and does not prove                                                                                                                                                                                                                                                                                                    |