docs(confidence-engine): align durable context with current baseline

docs/current-project-state.md

@@ -13,7 +13,7 @@ It does not simply answer the user's question. It:
 - Builds a structured reasoning graph;
 - Selects the most useful unresolved uncertainty;
 - Asks one simple question;
-- Updates the graph from the answer;
+- Evaluates whether remaining uncertainty justifies action;
 - Repeats until action is justified or the remaining uncertainty is clear.
 
 The user may already know the answer but needs confidence to act, may need to identify who to ask, may need to find where to look, or may need to determine how to test a claim. The engine carries the complexity of reasoning so the user does not have to manage graph theory, node IDs, internal enums, schemas, prompt versions or provider details.
@@ -183,6 +183,4 @@ Since the handoff document was written, further learning has emerged from Return
 
 ### Current experimental context
 
-The project has returned to relationship-discovery experimentation following Return-to-Origin methodology work. The durable methodology principles (A1–A12 above) should be loaded before continuing experiments. RTO.21 and RTO.22 have provided initial evidence supporting the meaning-over-dictionary approach; RTO.23 apparatus is under development.
-
-For detailed current handoff state, read `docs/current-handoff.md` first.
+The durable methodology principles (A1–A12 above) should be loaded before continuing experiments. For detailed current operational state, read `docs/current-handoff.md` first.

docs/project-knowledge-inventory.md

@@ -57,7 +57,7 @@ These are the documents Claude should normally read before continuing Confidence
 - **Purpose:** Single return-to-work handoff carrying the latest stopping point in one short document. Classifies as the shortest current resume entry point.
 - **Sections to read:** All eight sections when returning after a break; specific sections only when the resuming session has partial context.
 - **Why required:** Replaces scattered current return notes with one obvious file. Does not duplicate full current-state or experiment history.
-- **Size:** short (~68 lines)
+- **Size:** medium (current operational state — loads first, then project-state and methodology)
 
 ### docs/03_Confidence_Engine_Language_Guide.md
 - **Purpose:** Exact language rules for user-facing output (voice, translations, what to avoid).

docs/task-context-packs.md

@@ -7,7 +7,7 @@
 ### Always read
 - `docs/current-working-principles.md` §0 (Axiomatic Principles A1–A12 — durable methodology baseline)
 - `docs/Confidence_Engine_Return_to_Origin_Methodology_Context_2026-08-18.md` (methodology continuity, RTO evidence)
-- `docs/current-handoff.md` (current state, Git checkpoint, experiment log)
+- `docs/current-handoff.md` (current operational state, evidence semantics, settled boundaries)
 - `.claude/architecture-guardrails.md`
 - `docs/current-implementation-verification.md`