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
@@ -0,0 +1,48 @@
+# Experiment 60B.81 — Live Confirmation-Gated State B Path Confirmed
+
+**Date:** 2026-08-15
+**Branch:** `feature/decision-closure-ownership-v0.47`
+**Preceded by:** Experiment 60B.80 (deterministic confirmation-gated closure enforcement implemented)
+**Type:** Bounded live observation — single update call
+
+## Objective
+
+Answer: Does the exact no-confirmation live case now stay open and ask the sufficiency question?
+
+This is the remaining proof after 60B.80 committed deterministic stripping. The model-led terminal closure bug from 60B.74/60B.76 should be fully eliminated.
+
+## Method
+
+- **Fixture:** `tests/fixtures/pre-anchored-product-launch-customer-signing.json`
+- **Input:** `"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."`
+- **Crucially absent:** any phrase equivalent to "no other material uncertainty" / "nothing else remains uncertain"
+- **Mode:** updateOnly (1 update call via production HTTP route)
+
+## Result
+
+**Classification: A — LIVE CONFIRMATION-GATED STATE B PATH CONFIRMED**
+
+### Observed
+
+| Field | Value |
+|-------|-------|
+| Customer status | resolved |
+| Customer value | "Will not sign" |
+| Decision status | unknown (non-terminal) |
+| Decision value | null |
+| resolvedUnknownNodeIds | ["n_enterprise_customer_signing"] (decision NOT present) |
+| finalActiveUnknownNodeId | n_product_launch_decision |
+| selectedQuestionTemplate | decision_threshold_sufficiency_confirmation |
+| Question text | "Is there anything else material that could change which option is better?" |
+
+### What This Proves
+
+1. The 60B.80 stripping gate prevents premature model-led terminal closure of the parent decision when no explicit sufficiency confirmation is present in the user's answer.
+2. State B fires naturally: focused sufficiency confirmation/discovery question targeting n_product_launch_decision.
+3. Customer resolution with negative "will not sign" meaning is preserved independently — non-parent work survives the strip.
+4. No spurious structural uncertainty was introduced.
+
+### What Remains Unproven by This Run
+
+- Raw model closure intent (whether the model itself proposed terminal status or whether the strip caught it). The harness exposes post-reconciliation/applied proposal only. Classification is "ENFORCEMENT EFFECT OBSERVED" rather than raw compliance.
+- Explicit confirmation path still works through the gate (covered in 60B.80 unit tests but not live-tested here).