experiment: confirm live confirmation-gated state b path

2026-08-15 12:27:08 +01:00
parent 357be25de5
commit abc01b181f
2 changed files with 71 additions and 0 deletions
@@ -4349,3 +4349,26 @@ Why:
 One unresolved question: Boundary B (dedicated pre-validation function) vs Boundary D (extend existing gate). Boundary D is more tightly coupled but less architecturally clean. **Recommendation: Boundary B** — `reconcileDecisionClosureOwnership(graph, proposal, answer)` between reconciliation (line 3549) and validation (line 3552).

 Smallest implementation boundary: One new function + one prompt rule change. No schema changes.
+
+---
+
+### Experiment 60B.81 — Live Confirmation-Gated State B Path Confirmed (2026-08-15)
+
+**Type:** Bounded live observation (1 update call, production route)
+
+**Input:** No-confirmation answer: *"The enterprise customer has now confirmed in writing that they will not sign if we launch this year, so the £700,000 of expected annual revenue from them will not be received."*
+
+**Classification: A — LIVE CONFIRMATION-GATED STATE B PATH CONFIRMED**
+
+Observed:
+- Customer resolved ("Will not sign")
+- Decision remains non-terminal (status=unknown, value=null)
+- Decision remains active target (finalActiveUnknownNodeId = n_product_launch_decision)
+- Focused sufficiency question fires: *"Is there anything else material that could change which option is better?"*
+- decision_threshold_sufficiency_confirmation template selected
+- No spurious uncertainty introduced
+- Enforces the confirmation-gated closure boundary from 60B.80 in live production code
+
+What this proves: The deterministic stripping gate from 60B.80 prevents premature model-led terminal closure of parent decisions when no explicit sufficiency confirmation is present, and allows State B to fire naturally through the existing questioning path.
+
+**Doc:** docs/experiment-60b81.md