Open-World: добавить концентрацию поставщиков в бизнес-обзор

This commit is contained in:
2026-05-04 11:36:33 +03:00
parent cd22164f33
commit 027e9b373e
9 changed files with 136 additions and 8 deletions
@@ -29,8 +29,9 @@ If another document says `78%`, `87%`, `92%`, or `85%` for a module that is now
- Completed active slice: `Business Overview Inventory Staleness Risk Proxy Bridge`: when current-turn stock aging and sales-to-stock evidence are both present, business overview can include a bounded warehouse staleness-risk proxy while confirmed obsolete stock, reserves, write-offs, and liquidation value remain unclaimed.
- Completed active slice: `Business Overview Gap-Specific Headline And Next-Step Precision`: broad company-analysis answers now name the remaining unchecked families from `missing_signal_families` instead of using stale generic profit/debt/VAT/warehouse wording after partial proxies are proven.
- Completed active slice: `Business Overview Debt Staleness Risk Proxy Bridge`: when current-turn open-settlement concentration and contract-date age are both present, business overview can include a bounded debt staleness-risk proxy while contractual delinquency, credit risk, and due-date aging remain unclaimed.
- Completed active slice: `Business Overview Supplier Concentration Proxy Bridge`: business overview now derives top suppliers/recipients from confirmed outgoing payment rows and surfaces procurement concentration without claiming vendor risk, procurement quality, or full expense structure.
- 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: `~86% (Open-World Bounded Autonomy Breadth)`.
- Active module progress: `~88% (Open-World Bounded Autonomy Breadth)`.
## Reporting Rule
@@ -67,7 +68,7 @@ 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, 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, and confirmed reserve/write-off/liquidation inventory evidence families;
- extend `business_overview` beyond money-flow/activity, customer and supplier concentration, 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, 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;
@@ -376,8 +376,6 @@ Business-overview inventory sales velocity proxy validation:
- `npm.cmd test -- addressQueryRuntimeM23.test.ts`: passed `412`.
- `npm.cmd run build`: passed.
Graphify rebuild after Slice 15 code/doc sync: `6040 nodes`, `13158 edges`, `135 communities`.
Graphify rebuild after Slice 12 code/doc sync: `6030 nodes`, `13136 edges`, `137 communities`.
## Slice 12 - Business Overview Inventory Sales Velocity Proxy Bridge
@@ -480,3 +478,29 @@ 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 `412`.
- `npm.cmd run build`: passed.
Graphify rebuild after Slice 15 code/doc sync: `6040 nodes`, `13158 edges`, `135 communities`.
## Slice 16 - Business Overview Supplier Concentration Proxy Bridge
This slice fills a low-risk but important analyst gap in the broad company overview.
Before this slice, `business_overview` could name the largest confirmed customer from incoming payment rows, but the outgoing side only showed total supplier payout. That made company analysis asymmetrical: the assistant could discuss customer concentration but could not say whether outgoing payments were concentrated on one supplier/recipient.
Implemented now:
- the pilot reuses the reviewed `deriveRankedValueFlow` aggregation on the outgoing supplier-payout result;
- `derived_business_overview.top_suppliers` now carries the top confirmed outgoing counterparties from the current-turn rows;
- evidence and answer drafting surface the largest confirmed supplier/recipient and the share of checked outgoing payment flow;
- the wording is explicitly bounded as `procurement concentration proxy`, not vendor risk, procurement quality, or full expense structure;
- reason codes now expose both pilot-side and answer-side supplier concentration signals for replay review.
This is intentionally not a new due-diligence domain. It is a management concentration signal derived from rows already fetched by the existing business-overview runtime bridge.
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 `412`.
- `npm.cmd run build`: passed.
Graphify rebuild after Slice 16 code/doc sync: `6041 nodes`, `13162 edges`, `136 communities`.
@@ -64,6 +64,7 @@ Status canon for planning:
- The current completed breadth slice is `Business Overview Inventory Staleness Risk Proxy Bridge`: when current-turn stock aging and sales-to-stock evidence are both present, company analysis can include a bounded staleness-risk proxy while confirmed obsolete stock, reserves, write-offs, and liquidation value remain unclaimed.
- The current completed breadth slice is `Business Overview Gap-Specific Headline And Next-Step Precision`: business-overview answers now name remaining unchecked families from `missing_signal_families` instead of falling back to stale generic gap wording.
- The current completed breadth slice is `Business Overview Debt Staleness Risk Proxy Bridge`: when current-turn open-settlement concentration and contract-date age are both present, company analysis can include a bounded debt staleness-risk proxy while confirmed overdue debt, contractual delinquency, credit risk, and due-date aging remain unclaimed.
- The current completed breadth slice is `Business Overview Supplier Concentration Proxy Bridge`: company analysis now ranks confirmed outgoing payment counterparties and surfaces supplier/procurement concentration as a bounded proxy, not as vendor risk or full expense structure.
- 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).
@@ -129,11 +130,11 @@ 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: `~86%`, 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, 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, and confirmed reserve/write-off/liquidation inventory evidence are still pending
- active Open-World Bounded Autonomy Breadth progress: `~88%`, 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, supplier concentration proxy 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
- 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: `6040 nodes`, `13158 edges`, `135 communities`
- graph snapshot after latest rebuild: `6041 nodes`, `13162 edges`, `136 communities`
- current regression-gate breakpoint:
- the validated hot paths are no longer structurally broken;
- flagship continuity collapse is no longer the primary risk;
@@ -185,6 +186,7 @@ Latest live proof now includes:
- business-overview inventory 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 `6034 nodes`, `13145 edges`, `136 communities`; the proxy combines stock aging and sales-to-stock ratio while confirmed obsolete stock, reserves, write-offs, and liquidation value remain unclaimed
- business-overview gap-specific answer shaping accepted locally: answer-adapter slice passed `34/34` with `1` skipped; build passed; graphify rebuilt to `6036 nodes`, `13149 edges`, `134 communities`; headline and next-step wording now follow `missing_signal_families` instead of stale generic gap labels
- 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
- 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`
- inventory exact-runtime bridge accepted locally: runtime-bridge/answer-adapter/pilot-executor slice passed `70/70` with `1` skipped; full MCP-discovery slice passed `279/279` with `9` skipped; build passed; graphify rebuilt to `5930 nodes`, `12884 edges`, `135 communities`