docs: record sufficiency confirmation question

docs/current-handoff.md

@@ -3507,3 +3507,45 @@ The no-confirmation guard works live post-refactor. Parent decision stays open w
 Inverses the question-target problem of 60B.71: when the guard correctly keeps the decision open, the next question should be a sufficiency-confirmation question — not a generic decision_threshold continuation. Currently it cannot distinguish "need to confirm no remaining factors" from "need to investigate an unresolved factor."
 
 **Status:** pending Rob's review. Full analysis in docs/experiment-60b72.md.
+
+
+---
+
+---
+
+---
+
+### Experiment 60B.73 — Missing Sufficiency Confirmation Question (IMPLEMENTATION)
+
+**Date:** 2026-08-14
+**Branch:** `feature/sufficiency-confirmation-question-v0.45`
+**Parent:** 60B.72 (diagnosis ready for implementation)
+**Type:** Bounded implementation + focused verification
+
+#### What Changed
+
+Added State B detection in `formulateQuestion()` — before strategy selection — that detects:
+```text
+unresolved decision target
+AND zero remaining material factors
+AND no explicit sufficiency confirmation in resolvedValues
+```
+
+Produces template `decision_threshold_sufficiency_confirmation` with question:
+"Is there anything else material that could change which option is better?"
+
+#### Key Design Decisions
+
+- **Detection:** Transient, from existing state (node kind/status + hasRemainingMaterialFactors + resolvedValues check)
+- **Template:** New key in existing family `decision_threshold` — no new question family
+- **Plumbing:** Uses existing `context.resolvedValues[]` — no new parameters or schema changes
+- **Scope:** Single early-return branch before selectInvestigationStrategy
+
+#### Focused Verification
+
+8 new tests (60B.73 Tests 1-8) all pass. All 50 question-formulator tests pass.
+
+Pre-existing apply-proposal failures (4) confirmed unrelated via git stash/re-run.
+
+#### Status
+COMPLETE — production + tests committed, documentation recorded.