Semantic Gate: закрепить контрагентский value-flow и денежный разбор

2026-05-05 20:19:47 +03:00
parent 9be3fb29b7
commit ba23b056b8
19 changed files with 614 additions and 48 deletions
@@ -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 `~98%` after the EHMO-derived Semantic Control Gate subset accepted live at `21/21`;
+- accepted module progress is `~99%` after the EHMO-derived Semantic Control Gate subset accepted live again at `21/21` with W5/W7 hardening;
 - the active work is finishing the control-gate closure surface, not immediate expansion into more proof families.
 - full `100%` is still held back until the fat manual GUI pack is rerun/reviewed or remaining rough answers are explicitly classified outside the declared contour.

@@ -54,9 +54,10 @@ For the current execution spine, read `23 - current_execution_spine_and_semantic
 - 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.
+- Completed semantic-control slice: `W5/W7 Counterparty Value-Flow And Money-Breakdown Integrity`: bank-document/value-flow recipes now materialize explicit counterparty predicates, zero-row supplier-payment checks answer as checked negative evidence, compound money-breakdown wording stays in `business_overview`, and MCP discovery receives active organization scope only when the current turn has no explicit organization.
 - 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: `~98% (Open-World Bounded Autonomy Breadth, active slice: Semantic Control Gate)`.
+- Active module progress: `~99% (Open-World Bounded Autonomy Breadth, active slice: Semantic Control Gate)`.

 ## Reporting Rule

@@ -64,7 +65,7 @@ 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: 98% (Open-World Bounded Autonomy Breadth, active slice: Semantic Control Gate)` while discussing current module closure after the EHMO-derived critical subset accepted live.
+- `Прогресс модуля: 99% (Open-World Bounded Autonomy Breadth, active slice: Semantic Control Gate)` while discussing current module closure after the EHMO-derived critical subset accepted live again with W5/W7 hardening.
 - `Open-World Business Overview implementation breadth: ~99%, Semantic Control Gate critical subset accepted, fat GUI pack still pending` 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.

@@ -97,7 +98,7 @@ The project is not yet a universal arbitrary-1C agent.

 Remaining work belongs to the next breadth module:

- finish closure of the `Open-World Semantic Control Gate` opened by `assistant-stage1-EHMOy3lNFt`; the EHMO-derived critical subset is accepted live, but the fat GUI pack and residual answer-shape roughness still need final review;
+- finish closure of the `Open-World Semantic Control Gate` opened by `assistant-stage1-EHMOy3lNFt`; the EHMO-derived critical subset is accepted live after W5/W7 hardening, but the fat GUI pack and residual answer-shape roughness still need final review;
 - 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;
@@ -66,12 +66,12 @@ 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: `~98% (Open-World Bounded Autonomy Breadth, active slice: Semantic Control Gate)`.
+- accepted module progress: `~99% (Open-World Bounded Autonomy Breadth, active slice: Semantic Control Gate)`.

 This is not a regression from `99%` to `96%`. It is a metric split:

 - `99%` describes wired breadth;
- `98%` describes closure confidence after the EHMO-derived critical subset passed live replay; the gate is still not full module closure until the fat manual GUI pack and remaining answer-shape residuals are reviewed.
+- `99%` describes closure confidence after the EHMO-derived critical subset passed live replay again with W5/W7 hardening; the gate is still not full module closure until the fat manual GUI pack and remaining answer-shape residuals are reviewed.

 ## Current Local Cut

@@ -94,7 +94,14 @@ Local cut 3 is implemented:
 - W6: final `executive summary` / "confirmed, proxy, missing evidence, manual checks" wording is handled as deterministic conversation memory synthesis instead of generic address lookup.
 - W1/W6 hygiene: low-quality recap counterparty anchors such as standalone service prepositions are suppressed before they can appear as `«для»`-style pseudo-counterparties in the final answer.

-The EHMO-derived critical subset is now live-accepted. The remaining gate pressure is the fat manual GUI pack and known residual answer-shape roughness around selected counterparty money/document/movement follow-ups.
+The EHMO-derived critical subset is now live-accepted after the W5/W7 pass. The remaining gate pressure is the fat manual GUI pack and known residual answer-shape roughness, not an unresolved critical subset failure.
+
+Local cut 4 is implemented:
+
+- W5: bank-document/value-flow recipes now materialize explicit counterparty predicates for customer, supplier, lifecycle, and bank-document profiles instead of relying on post-filter cleanup.
+- W5: zero-row counterparty supplier-payment/value-flow checks now answer as checked negative evidence with period, organization, counterparty, and unknown-outside-boundary wording instead of looking like a generic failure.
+- W7: compound organization-level money-breakdown wording now stays in `business_overview` and receives the active organization scope inside MCP discovery when the current turn has no explicit organization.
+- W7 hygiene: pseudo predecompose counterparty anchors are filtered before they can pollute business-overview continuations.

 ## Failure Classes To Fix

@@ -128,12 +135,13 @@ The next implementation pass should be cut into these work units:
 4. `Semantic Control Gate W4 - frame reset and stale carryover policy`
 5. `Semantic Control Gate W5 - counterparty/organization arbitration after pivots`
 6. `Semantic Control Gate W6 - final-summary answer lane`
+7. `Semantic Control Gate W7 - broad money-breakdown and organization-scope discovery bridge`

 Each work unit should add focused local tests and then be validated against the EHMO-derived semantic subset.

 ## Acceptance Gate

-The current module can move from `~98%` toward closure only after:
+The current module can move from `~99%` toward closure only after:

 - the EHMO-derived critical subset remains accepted after future nearby edits;
 - old canaries remain green: Post-F, phase83, inventory selected-object, VAT continuity, SVK document/movement chains;
@@ -164,21 +172,19 @@ Manual runtime run reviewed as the gate opener:
 Live EHMO-derived critical subset proof:

 - spec: `docs/orchestration/address_truth_harness_phase89_open_world_semantic_control_gate_ehmo_subset.json`
- run: `artifacts/domain_runs/address_truth_harness_phase89_open_world_semantic_control_gate_ehmo_subset_live_fix4_20260505`
+- run: `artifacts/domain_runs/address_truth_harness_phase89_open_world_semantic_control_gate_ehmo_subset_live_fix8b_20260505`
 - result: `accepted`, `21/21`, `0` warnings, MCP live-readiness `ready`
- key covered repairs: business-audit synthesis no longer falls into capability help; final executive summary uses confirmed/proxy/missing/manual-check sections and filters pseudo-counterparty garbage.
+- key covered repairs: business-audit synthesis no longer falls into capability help; money-breakdown continuations use grounded business-overview evidence; SVK outgoing zero-row value-flow is rendered as checked negative evidence; final executive summary uses confirmed/proxy/missing/manual-check sections and filters pseudo-counterparty garbage.

 Graphify snapshot at this status cut:

- `6081 nodes`
- `13263 edges`
- `140 communities`
+- see `graphify-out/GRAPH_REPORT.md`

 ## Reporting Rule

 Until the fat manual GUI pack is reviewed or residuals are explicitly classified, use:

-`Прогресс модуля: 98% (Open-World Bounded Autonomy Breadth, active slice: Semantic Control Gate)`
+`Прогресс модуля: 99% (Open-World Bounded Autonomy Breadth, active slice: Semantic Control Gate)`

 If discussing only the already wired business-overview breadth, say:

@@ -144,11 +144,11 @@ 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: `~98%`, because the EHMO-derived `Open-World Semantic Control Gate` critical subset now accepts live at `21/21`; full closure is still held back for the fat manual GUI pack and remaining answer-shape residual review
+- active Open-World Bounded Autonomy Breadth accepted-module progress: `~99%`, because the EHMO-derived `Open-World Semantic Control Gate` critical subset accepts live at `21/21` after W5/W7 hardening; full closure is still held back for the fat manual GUI pack and remaining answer-shape residual review
 - 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: `6081 nodes`, `13263 edges`, `140 communities`
+- graph snapshot after latest rebuild: see `graphify-out/GRAPH_REPORT.md`
 - current regression-gate breakpoint:
  - the validated hot paths are no longer structurally broken;
  - flagship continuity collapse is no longer the primary risk;
@@ -177,7 +177,7 @@ Latest live proof now includes:
 - `address_truth_harness_phase82_human_mixed_integrity_status_dialog_post_f_account_injection_guard_clean_scope` accepted `19/19`, with the `Жуковке 51` numeric counterparty suffix kept as counterparty scope instead of leaking as account `51`
 - `address_truth_harness_post_f_cross_stage_canary_agent_20260424_live7` accepted `24/24`, proving a saved cross-stage AGENT canary across VAT metadata, metadata-scoped organization/document pivots, numeric counterparty suffixes, open-organization value-flow clarification, ranked value-flow year switches, and SVK grounded reset; the saved autorun is `AGENT | Post-F cross-stage semantic integrity canary` (`gen-ag04241406-abe4d8`)
 - `address_truth_harness_post_f_manual_failures_20260424_live3` accepted `11/11`, proving the manual failure slice from `assistant-stage1-9liEOh-7JP`: VAT purchase-date, VAT February 2017, highest-value customer, and Chepurnov item-flow after stale inventory context; the saved autorun is `AGENT | Post-F ручные провалы VAT revenue item-flow live3` (`gen-ag04241710-bdb248`)
- `address_truth_harness_phase89_open_world_semantic_control_gate_ehmo_subset_live_fix4_20260505` accepted `21/21`, proving the EHMO-derived Semantic Control Gate subset after business-audit lane repair, final executive-summary memory synthesis, and pseudo-counterparty recap filtering
+- `address_truth_harness_phase89_open_world_semantic_control_gate_ehmo_subset_live_fix8b_20260505` accepted `21/21`, proving the EHMO-derived Semantic Control Gate subset after business-audit lane repair, money-breakdown business-overview recovery, SVK zero-row value-flow answer shaping, final executive-summary memory synthesis, and pseudo-counterparty recap filtering
 - `address_truth_harness_phase11_manual_followup_meta_quality_live_rerun_vatfix` accepted `10/10`
 - `address_truth_harness_phase20_continuity_stabilization_live_rerun_vatfix` accepted `6/6`
 - `addressQueryRuntimeM23.test.ts` full semantic/runtime slice accepted `403/403` after Post-F VAT/date-basis, scope-recovery, open value-flow organization clarification, document-vs-bank arbitration, and reply-shape hardening
@@ -204,7 +204,7 @@ Latest live proof now includes:
 - 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
- semantic control gate critical subset accepted live: focused W2/W3/W6 regressions passed `54/54`; broader living/router semantic slice passed `90/90`; build passed; EHMO-derived replay `address_truth_harness_phase89_open_world_semantic_control_gate_ehmo_subset_live_fix4_20260505` accepted `21/21` with `0` warnings; graphify rebuilt to `6081 nodes`, `13263 edges`, `140 communities`; fat manual GUI pack remains the closure check
+- semantic control gate critical subset accepted live: W5/W7 focused regression plus focused W2/W3/W6 and broader living/router semantic slices passed locally; build passed; EHMO-derived replay `address_truth_harness_phase89_open_world_semantic_control_gate_ehmo_subset_live_fix8b_20260505` accepted `21/21` with `0` warnings; graphify rebuilt after this cut; fat manual GUI pack remains the closure check
 - 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`