Planner Autonomy: поднять inventory routes в MCP catalog

docs/ARCH/11 - architecture_turnaround/20 - planner_autonomy_consolidation_2026-05-01.md

@@ -78,6 +78,17 @@ Two arbitration seams were also hardened because they are part of the same plann
 
 These changes keep the route fabric broader without letting the planner pretend that inferred evidence is a formally proven legal fact.
 
+The following consolidation step promoted the accepted inventory-stock breadth behavior into reviewed catalog route fabric:
+
+- `inventory_stock_snapshot`
+- `inventory_supplier_overlap`
+- `inventory_purchase_provenance`
+- `inventory_sale_trace`
+
+These templates are now first-class catalog chain descriptors and can be selected by the data-need graph/planner. They reuse reviewed generic primitives (`query_movements`, `query_documents`, `aggregate_by_axis`, `drilldown_related_objects`, `probe_coverage`, `explain_evidence_basis`) and add inventory-specific axes such as `as_of_date`, `warehouse`, `supplier`, `buyer`, `quantity`, and `evidence_basis`.
+
+The live MCP pilot intentionally marks these new inventory templates as `inventory_route_template_v1` / unsupported for live generic pilot execution until the exact inventory runtime paths are explicitly bridged into the bounded MCP executor. This keeps the architecture honest: route fabric exists, but runtime execution is still gated by the existing exact inventory capabilities and future bridging work.
+
 ## Why This Matters
 
 This reduces the pressure to add one hard route per user wording.
@@ -121,13 +132,20 @@ Latest validation after the lifecycle and arbitration hardening:
 - live broad-eval to net-flow follow-up: `address_truth_harness_phase21_net_followup_after_broad_eval_planner_lifecycle_rerun2`, accepted `3/3`
 - live broad-evaluation bridge: `address_truth_harness_phase22_broad_business_evaluation_bridge_planner_lifecycle_rerun2`, accepted `3/3`
 
+Latest validation after the inventory catalog-template lift:
+
+- targeted catalog/data-need/planner/turn-input tests: passed, `139 passed`, `6 skipped`
+- full MCP-discovery suite: passed, `276 passed`, `9 skipped`
+- `npm.cmd run build`: passed
+- graphify rebuild: `5912 nodes`, `12833 edges`, `138 communities`
+
 ## Next Step
 
-The next safe step is to continue from catalog-instantiated known chain templates, first scoring rules, and lifecycle bounded inference into broader reviewed evidence templates.
+The next safe step is to continue from catalog-instantiated inventory templates into runtime bridging and broader reviewed scoring.
 
 Recommended order:
 
-1. promote repeated inventory-stock evidence behaviors into reviewed catalog templates;
+1. bridge inventory catalog templates into the bounded MCP executor only where exact inventory runtime evidence can be reused safely;
 2. broaden catalog scoring beyond explicit document/movement lane choice into unfamiliar 1C asks;
 3. grow primitive descriptors only where live replay shows a real evidence gap;
 4. keep phase19, phase21, phase22, value-flow, metadata ambiguity, and inventory-stock canaries as regression gates.

docs/ARCH/11 - architecture_turnaround/README.md

@@ -76,6 +76,7 @@ It now documents a turnaround that is already operational in code, already mater
   - lifecycle now behaves as a bounded activity-window inference chain with an explicit legal-fact boundary instead of an unqualified age answer;
   - current-turn value-flow aggregate questions can override narrower supported exact routes when the user asks for totals/net/payment amounts;
   - broad business evaluation remains in the deterministic living-chat bridge instead of being displaced by generic metadata discovery;
+  - inventory stock snapshot, supplier overlap, purchase provenance, and sale trace are now reviewed catalog chain templates, while live generic MCP pilot execution remains explicitly gated until the exact inventory runtime evidence is bridged safely;
   - live map sync: [20 - planner_autonomy_consolidation_2026-05-01.md](./20%20-%20planner_autonomy_consolidation_2026-05-01.md)
 
 Current honest status:
@@ -84,10 +85,10 @@ Current honest status:
 - exit-from-danger-zone readiness: `~97%`
 - pre-multidomain readiness: `~90%`
 - bounded-autonomy foundation readiness: `~89%`
-- open-world bounded-autonomy readiness: `~84%`
+- open-world bounded-autonomy readiness: `~85%`
 - 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: `~62%` for the declared module, with catalog-fabric, value-flow arbitration, lifecycle bounded inference, and broad-evaluation bridge validated, but broader unfamiliar 1C asks still pending
+- Planner Autonomy Consolidation progress: `~68%` for the declared module, with catalog-fabric, value-flow arbitration, lifecycle bounded inference, broad-evaluation bridge, and inventory catalog templates validated, but live inventory-template bridging and broader unfamiliar 1C asks still pending
 - graph snapshot after latest rebuild: `5912 nodes`, `12833 edges`, `138 communities`
 - current breakpoint:
   - the validated hot paths are no longer structurally broken;
@@ -128,6 +129,7 @@ Latest live proof now includes:
 - lifecycle/value-flow Planner Autonomy response gate accepted: `address_truth_harness_phase19_mcp_discovery_response_gate_planner_lifecycle_rerun4` accepted `8/8`, proving bounded lifecycle inference, current-turn value-flow aggregate arbitration, and sanitized evidence wording
 - broad-evaluation bridge continuity accepted: `address_truth_harness_phase21_net_followup_after_broad_eval_planner_lifecycle_rerun2` accepted `3/3` and `address_truth_harness_phase22_broad_business_evaluation_bridge_planner_lifecycle_rerun2` accepted `3/3`
 - latest local Planner Autonomy slice accepted: full MCP-discovery suite passed `268/268` with `9` skipped; broad MCP/living-chat/route/meaning slice passed `305/305` with `9` skipped; build passed
+- 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`
 
 Current architectural reading: