Open-World: удержать бизнес-обзор от мусорных anchors

docs/ARCH/11 - architecture_turnaround/06 - phase_acceptance_matrix.md

@@ -27,7 +27,7 @@ Current reporting baseline:
 - Post-F Semantic Integrity Hardening: `99%`, operationally closed/regression gate.
 - Planner Autonomy Consolidation: `100%` for the declared phase83 slice.
 - Open-World Business Overview implementation breadth: `~99%` through Slice 25.
-- Active next pressure: `Open-World Semantic Control Gate`, accepted module progress `~93%` after manual replay `assistant-stage1-EHMOy3lNFt`.
+- Active next pressure: `Open-World Semantic Control Gate`, accepted module progress `~94%` after the first local control-gate cut.
 
 ## Archived Execution Snapshot (2026-04-17)
 

docs/ARCH/11 - architecture_turnaround/21 - current_status_canon_2026-05-01.md

@@ -17,7 +17,7 @@ It did not reopen Post-F and it did not prove that the Open-World implementation
 From this point forward:
 
 - `~99%` for Open-World means implementation breadth through `Business Overview Missing Proof Ledger`;
-- accepted module progress is `~93%` until the new `Open-World Semantic Control Gate` is fixed and rerun;
+- accepted module progress is `~94%` after the first local Semantic Control Gate cut, and remains below closure until the EHMO-derived subset is rerun;
 - the active work is control-gate hardening, not immediate expansion into more proof families.
 
 For the current execution spine, read `23 - current_execution_spine_and_semantic_control_gate_2026-05-05.md`.
@@ -55,7 +55,7 @@ For the current execution spine, read `23 - current_execution_spine_and_semantic
 - Completed active slice: `Business Overview Missing Proof Ledger`: business overview now records machine-readable hard proof gaps for accounting profit/margin, due-date debt aging, inventory reserve/liquidation quality, and vendor/procurement quality, distinguishing proxy-only evidence from reviewed routes that are not wired yet.
 - Implementation breadth: `~99% (Open-World Bounded Autonomy Breadth through Slice 25)`.
 - Next active slice: `Open-World Semantic Control Gate`, covering garbage-anchor protection, business-overview continuation, intent dominance, frame hygiene, counterparty/organization arbitration, and final-summary answer shape.
-- Active module progress: `~93% (Open-World Bounded Autonomy Breadth, active slice: Semantic Control Gate)`.
+- Active module progress: `~94% (Open-World Bounded Autonomy Breadth, active slice: Semantic Control Gate)`.
 
 ## Reporting Rule
 
@@ -63,7 +63,7 @@ Use these labels when reporting progress:
 
 - `Прогресс модуля: 99% (Post-F Semantic Integrity Hardening, operationally closed/regression gate)` when discussing the Post-F slice itself.
 - `Прогресс модуля: 100% (Planner Autonomy Consolidation, declared phase83 slice closed)` when discussing the planner-autonomy slice that was just completed.
-- `Прогресс модуля: 93% (Open-World Bounded Autonomy Breadth, active slice: Semantic Control Gate)` while discussing current module closure after the EHMO manual replay.
+- `Прогресс модуля: 94% (Open-World Bounded Autonomy Breadth, active slice: Semantic Control Gate)` while discussing current module closure after the first local Semantic Control Gate cut.
 - `Open-World Business Overview implementation breadth: ~99%, semantic acceptance gate still open` when discussing only the already wired Slice 25 breadth.
 - `Прогресс модуля: X% (Open-World Bounded Autonomy Breadth, active slice: <name>)` for later breadth work after the Semantic Control Gate is accepted.
 

docs/ARCH/11 - architecture_turnaround/22 - open_world_bounded_autonomy_breadth_2026-05-01.md

@@ -779,5 +779,27 @@ Suggested first subset:
 Current status:
 
 - implementation breadth through Slice 25: `~99%`;
-- accepted Open-World module progress after EHMO: `~93%`;
+- accepted Open-World module progress after the first local Semantic Control Gate cut: `~94%`;
 - exact P&L, real due-date debt aging, reserve/write-off/liquidation evidence, and vendor-risk engines stay queued behind this semantic gate.
+
+### Slice 26 local cut 1 - anchor hygiene and overview continuation
+
+Implemented now:
+
+- pseudo-entity candidates such as "by these data", "main supplier in", "what is confirmed", and generic proxy/audit tails are rejected before they can become scoped counterparty subjects;
+- business-overview follow-ups after `business_overview_route_template_v1` keep the organization/date frame and stay in the bounded analyst overview lane;
+- VAT-position wording inside a business-overview continuation no longer lets the generic word "position" drag the turn into inventory selected-object logic;
+- resolver-level "by these data" wording is no longer accepted as a loose counterparty anchor for document requests;
+- the older top-year company revenue resolver regression expectation was realigned with the current architecture: organization-level best-year wording belongs to business overview discovery, not the exact customer-value route.
+
+Validation:
+
+- `npm.cmd test -- assistantMcpDiscoveryTurnInputAdapter.test.ts addressIntentResolverRegression.test.ts`: passed `94` with `6` skipped.
+- `npm.cmd test -- addressCounterpartyIntentSignals.test.ts addressQueryRuntimeM23.test.ts assistantMcpDiscoveryTurnInputAdapter.test.ts addressIntentResolverRegression.test.ts`: passed `515` with `6` skipped.
+- `npm.cmd run build`: passed.
+
+Remaining before acceptance:
+
+- rerun the EHMO-derived semantic subset;
+- continue W3/W4/W5/W6 for intent dominance, frame reset, counterparty/organization arbitration, and final-summary answer lane;
+- only then rerun the fat manual GUI pack for acceptance.

docs/ARCH/11 - architecture_turnaround/23 - current_execution_spine_and_semantic_control_gate_2026-05-05.md

@@ -66,12 +66,22 @@ This gate is not a request to tune the assistant for every weird question in tha
 Current status should be reported as:
 
 - implementation breadth: `~99%` for Open-World Business Overview through Slice 25;
-- accepted module progress: `~93% (Open-World Bounded Autonomy Breadth, active slice: Semantic Control Gate)`.
+- accepted module progress: `~94% (Open-World Bounded Autonomy Breadth, active slice: Semantic Control Gate)`.
 
-This is not a regression from `99%` to `93%`. It is a metric split:
+This is not a regression from `99%` to `94%`. It is a metric split:
 
 - `99%` describes wired breadth;
-- `93%` describes closure confidence after a broad human semantic replay found control-gate defects.
+- `94%` describes closure confidence after the first local control-gate cut; the gate is still not accepted without EHMO-subset replay.
+
+## Current Local Cut
+
+Local cut 1 is implemented:
+
+- W1 starter: garbage anchors and pseudo-entity candidates are filtered before they can become counterparty subjects.
+- W2 starter: business-overview continuation wording keeps the bounded overview lane after a previous overview run.
+- W3 edge covered locally: VAT-position wording inside a business-overview continuation does not fall into inventory selected-object routing.
+
+This is local evidence only. It improves the gate but does not close it until the EHMO-derived subset and the fat manual pack are semantically reviewed again.
 
 ## Failure Classes To Fix
 
@@ -110,7 +120,7 @@ Each work unit should add focused local tests and then be validated against the
 
 ## Acceptance Gate
 
-The current module can move from `~93%` toward closure only after:
+The current module can move from `~94%` toward closure only after:
 
 - the EHMO-derived critical subset is rerun and semantically reviewed;
 - old canaries remain green: Post-F, phase83, inventory selected-object, VAT continuity, SVK document/movement chains;
@@ -148,7 +158,7 @@ Graphify snapshot at this status cut:
 
 Until the semantic control gate is accepted, use:
 
-`Прогресс модуля: 93% (Open-World Bounded Autonomy Breadth, active slice: Semantic Control Gate)`
+`Прогресс модуля: 94% (Open-World Bounded Autonomy Breadth, active slice: Semantic Control Gate)`
 
 If discussing only the already wired business-overview breadth, say:
 

docs/ARCH/11 - architecture_turnaround/README.md

@@ -144,7 +144,7 @@ Current honest status:
 - bounded-autonomy foundation readiness: `~89%`
 - open-world bounded-autonomy readiness: `~87%`
 - active Open-World Bounded Autonomy Breadth implementation breadth: `~99%`, with business-overview evidence fusion, the reviewed `business_overview` catalog/data-need/planner route-fabric slice, the fresh multi-probe runtime bridge, the explicit-period VAT/tax fact-family bridge, the explicit-period debt-position bridge, the explicit-date inventory-position bridge, the open-settlement quality bridge accepted by live semantic replay, selected-item profitability bridged by local semantic/runtime regression tests, contract-date debt age bridged locally, debt staleness-risk proxy bridged locally, debt due-date boundary arbitration bridged locally, inventory reserve/liquidation boundary arbitration bridged locally, supplier/procurement-quality boundary arbitration bridged locally, supplier concentration proxy bridged locally, document/account-section activity profile bridged locally, counterparty population/roles and contract usage profiles bridged locally, yearly operating-flow proxy bridged locally, earnings/best-year wording arbitration bridged locally, profit/margin wording boundary arbitration bridged locally, analyst synthesis added to business-overview answer drafting, company-period trading margin proxy bridged locally, inventory sales-to-stock proxy bridged locally, inventory staleness-risk proxy bridged locally, gap-specific answer shaping bridged locally, and missing proof families recorded as runtime evidence ledger; exact accounting profit/margin, true due-date debt aging/overdue, confirmed vendor-risk/procurement-quality analysis, and confirmed reserve/write-off/liquidation inventory evidence are still pending
-- active Open-World Bounded Autonomy Breadth accepted-module progress: `~93%`, because the EHMO manual GUI replay opened the `Open-World Semantic Control Gate` before closure
+- active Open-World Bounded Autonomy Breadth accepted-module progress: `~94%`, because the first local `Open-World Semantic Control Gate` cut is implemented, but EHMO-subset replay is still pending
 - Post-F semantic integrity module progress: `~99%` operationally closed, with remaining risk now treated as next-slice discovery rather than an open blocker inside the closed slice
 - active inventory-stock breadth slice progress: `100%` for the declared scenario pack, not for arbitrary inventory questions
 - Planner Autonomy Consolidation progress: `100%` for the declared module, with catalog-fabric, value-flow arbitration, lifecycle bounded inference, broad-evaluation bridge, inventory catalog templates, inventory runtime-boundary honesty, exact inventory recipe bridging, unambiguous metadata-surface lane inference, catalog chain-template scoring, structured chain-match contract exposure, runtime/debug propagation, subject-aware bidirectional comparison arbitration, structured catalog-alignment verdicts, representative alignment regression guard, catalog-alignment reason-code telemetry, explicit `alignment_status` propagation, truth-harness/acceptance-matrix surfacing, soft divergence warning, `catalog_alignment_ok` acceptance invariant, step-level expected catalog-alignment assertions, phase66 and phase32 spec alignment expectations, AGENT source-catalog surfacing, generated phase83 mixed planner-brain replay spec, checked-source user-facing error sanitation, surface-grounded catalog promotion, and guarded live phase83 acceptance validated. Broader unfamiliar 1C asks are now next-module breadth work rather than an open blocker inside this declared slice