Open-World: закрепить реестр недостающих доказательств бизнес-обзора

2026-05-05 13:41:49 +03:00
parent 42283a6ac2
commit c0a89ccece
9 changed files with 307 additions and 32 deletions
@@ -38,8 +38,9 @@ If another document says `78%`, `87%`, `92%`, or `85%` for a module that is now
 - Completed active slice: `Business Overview Supplier/Procurement Quality Boundary Bridge`: organization-level supplier concentration, vendor-risk, dependency, and procurement-quality wording now routes to `business_overview`, while supplier payment/open-settlement/doc questions stay in exact supplier/payables routes with a vendor-risk proof boundary.
 - Completed active slice: `Business Overview Document/Account Activity Profile Bridge`: business overview now executes the reviewed `document_type_and_account_section_profile` recipe and surfaces confirmed operational activity mix without claiming process quality, accounting correctness, or complete 1C activity coverage.
 - Completed active slice: `Business Overview Counterparty/Contract Profile Bridge`: business overview now executes reviewed `counterparty_population_and_roles` and `contract_usage_overview` recipes, surfacing active counterparty role split and contract usage without claiming CRM quality, counterparty due diligence, legal completeness, or contract-risk.
+- 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.
 - Next active slice: continue breadth into exact company-wide accounting profit/margin, real due-date debt aging, confirmed inventory reserve/write-off/liquidation evidence, and broader unfamiliar 1C route families only where reviewed evidence routes exist.
- Active module progress: `~98% (Open-World Bounded Autonomy Breadth)`.
+- Active module progress: `~99% (Open-World Bounded Autonomy Breadth)`.

 ## Reporting Rule

@@ -76,7 +77,7 @@ The project is not yet a universal arbitrary-1C agent.

 Remaining work belongs to the next breadth module:

- extend `business_overview` beyond money-flow/activity, customer and supplier concentration, document/account-section activity mix, counterparty role split, contract usage, yearly operating-flow dynamics, explicit profit/margin wording boundaries, explicit debt due-date wording boundaries, explicit inventory reserve/liquidation wording boundaries, explicit supplier/procurement-quality wording boundaries, explicit-period VAT/tax, as-of-date debt position, open-settlement concentration, contract-date debt age, debt staleness-risk proxy, as-of-date inventory position, trading-margin proxy, sales-to-stock inventory proxy, and warehouse staleness-risk proxy into separately proven exact accounting profit/margin, due-date debt aging/overdue, confirmed vendor-risk/procurement-quality analysis, and confirmed reserve/write-off/liquidation inventory evidence families;
+- extend `business_overview` beyond money-flow/activity, customer and supplier concentration, document/account-section activity mix, counterparty role split, contract usage, yearly operating-flow dynamics, explicit profit/margin wording boundaries, explicit debt due-date wording boundaries, explicit inventory reserve/liquidation wording boundaries, explicit supplier/procurement-quality wording boundaries, explicit-period VAT/tax, as-of-date debt position, open-settlement concentration, contract-date debt age, debt staleness-risk proxy, as-of-date inventory position, trading-margin proxy, sales-to-stock inventory proxy, warehouse staleness-risk proxy, and the missing-proof ledger into separately proven exact accounting profit/margin, due-date debt aging/overdue, confirmed vendor-risk/procurement-quality analysis, and confirmed reserve/write-off/liquidation inventory evidence families;
 - broader dynamic schema traversal for unfamiliar 1C asks;
 - more primitive descriptors where live evidence proves a real gap;
 - more replay-backed domain packs that start from user business meaning, not from route convenience;
@@ -697,3 +697,34 @@ Local validation is accepted for this slice:
 - `npm.cmd run build`: passed.

 Graphify rebuild after Slice 24 code/doc sync: `6069 nodes`, `13230 edges`, `140 communities`.
+
+## Slice 25 - Business Overview Missing Proof Ledger
+
+This slice hardens the last high-risk semantic edge before the module can be treated as nearly closed: broad company analysis now carries a machine-readable ledger of the proof families that are still missing, instead of relying only on prose boundaries.
+
+The important distinction is not "can we say something useful?" because the current overview already can. The distinction is whether downstream answer drafting and future route expansion can reliably tell:
+
+- what was actually checked in the current turn;
+- what is only a bounded proxy;
+- what still has no reviewed route wired into runtime;
+- what must never be promoted into a confirmed business-audit conclusion.
+
+Implemented now:
+
+- `derived_business_overview.missing_proof_families` records the remaining hard proof families for accounting profit/margin, due-date debt aging, inventory reserve/liquidation quality, and vendor-risk/procurement quality;
+- each missing proof family exposes `current_status`, `current_supported_evidence`, `next_required_evidence`, and `must_not_claim`;
+- trading-margin evidence is explicitly recorded as `proxy_only_currently` for accounting profit/margin, not as clean profit or P&L;
+- open-settlement/debt-staleness evidence is explicitly recorded as proxy-only for due-date aging, not as contractual overdue debt;
+- inventory stock/turnover/staleness evidence is explicitly recorded as proxy-only for reserves, write-offs, obsolescence, and liquidation value;
+- supplier concentration is explicitly recorded as proxy-only for vendor/procurement quality, not as supplier reliability or full expense-structure proof;
+- the answer adapter adds a guard reason code and a `must_not_claim` rule so the proof ledger itself is not mistaken for an executed route.
+
+This is not a new exact P&L, payment-term, reserve/write-off, or vendor-risk engine. It is a semantic safety ledger for the remaining exact-route work: future slices can either wire a reviewed evidence route or keep the family honestly unproved.
+
+Local validation is accepted for this slice:
+
+- `npm.cmd test -- assistantMcpDiscoveryPilotExecutor.test.ts assistantMcpDiscoveryAnswerAdapter.test.ts`: passed `66` with `1` skipped.
+- `npm.cmd test -- addressQueryRuntimeM23.test.ts`: passed `416`.
+- `npm.cmd run build`: passed.
+
+Graphify rebuild after Slice 25 code/doc sync: `6070 nodes`, `13233 edges`, `135 communities`.
@@ -73,6 +73,7 @@ Status canon for planning:
 - The current completed breadth slice is `Business Overview Supplier/Procurement Quality Boundary Bridge`: organization-level supplier concentration, vendor-risk, dependency, and procurement-quality wording now reaches `business_overview`, while supplier payment/open-settlement/doc questions stay in exact supplier/payables routes with a vendor-risk proof boundary.
 - The current completed breadth slice is `Business Overview Document/Account Activity Profile Bridge`: business overview now executes the reviewed document-type/account-section profile and can surface confirmed operational activity mix without claiming process quality, accounting correctness, or full 1C coverage.
 - The current completed breadth slice is `Business Overview Counterparty/Contract Profile Bridge`: business overview now executes reviewed counterparty population/roles and contract usage profiles, while CRM quality, counterparty due diligence, legal completeness, and contract-risk remain unclaimed.
+- The current completed breadth slice is `Business Overview Missing Proof Ledger`: business overview now records hard remaining proof gaps as machine-readable `missing_proof_families`, separating proxy-only evidence from reviewed routes that are not wired yet.
 - The next active breadth slice continues breadth into exact company-wide accounting profit/margin, real due-date debt aging, confirmed reserve/write-off/liquidation inventory evidence, and broader unfamiliar 1C route families without relaxing truth boundaries.
 - The short source of truth for status wording is [21 - current_status_canon_2026-05-01.md](./21%20-%20current_status_canon_2026-05-01.md).

@@ -138,11 +139,11 @@ Current honest status:
 - pre-multidomain readiness: `~90%`
 - bounded-autonomy foundation readiness: `~89%`
 - open-world bounded-autonomy readiness: `~87%`
- active Open-World Bounded Autonomy Breadth progress: `~98%`, 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, and gap-specific answer shaping bridged locally; 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 progress: `~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
 - 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
- graph snapshot after latest rebuild: `6069 nodes`, `13230 edges`, `140 communities`
+- graph snapshot after latest rebuild: `6070 nodes`, `13233 edges`, `135 communities`
 - current regression-gate breakpoint:
  - the validated hot paths are no longer structurally broken;
  - flagship continuity collapse is no longer the primary risk;
@@ -196,6 +197,7 @@ Latest live proof now includes:
 - business-overview debt staleness-risk proxy accepted locally: targeted executor/answer-adapter slice passed `66/66` with `1` skipped; M23 route/runtime regression passed `412/412`; build passed; graphify rebuilt to `6040 nodes`, `13158 edges`, `135 communities`; the proxy combines contract-date age and open-balance concentration while confirmed overdue debt, contractual delinquency, credit risk, and due-date aging remain unclaimed
 - business-overview supplier concentration proxy accepted locally: targeted executor/answer-adapter slice passed `66/66` with `1` skipped; M23 route/runtime regression passed `412/412`; build passed; graphify rebuilt to `6041 nodes`, `13162 edges`, `136 communities`; the proxy ranks confirmed outgoing payment counterparties while vendor risk, procurement quality, and full expense structure remain unclaimed
 - business-overview yearly operating-flow proxy accepted locally: targeted executor/answer-adapter slice passed `66/66` with `1` skipped; M23 route/runtime regression passed `412/412`; build passed; graphify rebuilt to `6047 nodes`, `13177 edges`, `139 communities`; the proxy builds annual incoming/outgoing/net buckets from confirmed money-flow rows while profit, финрезультат, and full P&L remain unclaimed
+- business-overview missing proof ledger accepted locally: targeted executor/answer-adapter slice passed `66/66` with `1` skipped; M23 route/runtime regression passed `416/416`; build passed; graphify count is recorded in the current graph snapshot; hard remaining proof gaps are now visible as machine-readable `missing_proof_families` rather than only prose warnings
 - business-overview earnings wording arbitration accepted locally: turn-meaning/turn-input slice passed `85/85` with `6` skipped; M23 route/runtime regression passed `412/412`; runtime-entry/pilot/answer slice passed `85/85` with `3` skipped; build passed; graphify rebuilt to `6052 nodes`, `13187 edges`, `138 communities`; organization-level earnings/best-year wording now reaches `business_overview` while explicit customer/counterparty ranking remains in exact customer value routes
 - inventory template lift accepted locally: catalog/data-need/planner/turn-input slice passed `139/139` with `6` skipped; full MCP-discovery slice passed `276/276` with `9` skipped; build passed; graphify stayed at `5912 nodes`, `12833 edges`, `138 communities`
 - inventory runtime-boundary hardening accepted locally: runtime-bridge/answer-adapter/pilot-executor slice passed `68/68` with `1` skipped; full MCP-discovery slice passed `277/277` with `9` skipped; build passed; graphify rebuilt to `5913 nodes`, `12837 edges`, `138 communities`