АДРЕСНЫЙ РЕЖИМ -ADDRESS:Шаг 1 - ЛЛМ ФЕРСТ + feat(address): стабилизация wave1 dynamic resolver контрагентов, follow-up carryover и актуализация docs/tests

2026-04-02 23:11:49 +03:00
parent 53716e548e
commit 88094c09f8
243 changed files with 94296 additions and 181 deletions
@@ -0,0 +1,28 @@
+# 2026-04-02_Address_CustomerRole_Probe_AfterRosterFix
+
+Generated at: 2026-04-02T22:00:04
+Questions file: X:\1C\NDC_1C\docs\ADDRESS\question_sets\temp_customer_role_probe_2026-04-02.json
+Backend URL: http://127.0.0.1:8787/api/assistant/message
+LLM: local / qwen2.5-14b-instruct-1m @ http://127.0.0.1:1234
+Strict policy: factual
+
+## Totals
+- questions_total: 2
+- ok_200_count: 2
+- semantic_pass_count: 2
+- semantic_pass_rate: 1.0
+- route_pass_count: 2
+- route_pass_rate: 1.0
+- strict_pass_count: 2
+- strict_pass_rate: 1.0
+- factual_count: 2
+- partial_coverage_count: 0
+- clarification_required_count: 0
+- http_error_count: 0
+- llm_decomposition_applied_count: 1
+- avg_elapsed_ms: 5649
+
+## Files
+- run_summary.json
+- full_live_results.json
+- failures_only.json
@@ -0,0 +1 @@
+[]
@@ -0,0 +1,6 @@
+# Response Audit: 2026-04-02_Address_CustomerRole_Probe_AfterRosterFix
+
+| id | strict | route_health | reply_type | intent | limited_reason | question | assistant_first_line |
+|---|---|---|---|---|---|---|---|
+| P001 | True | ok_or_factual | factual | counterparty_population_and_roles | None | скок клиентов | Профиль контрагентов собран (catalog + bank-doc activity aggregate). |
+| P002 | True | ok_or_factual | factual | counterparty_activity_lifecycle | None | кто у нас заказчики вообще | Собран профиль активности заказчиков (bank-doc activity aggregate). |
@@ -0,0 +1,45 @@
+{
+  "run_id": "2026-04-02_Address_CustomerRole_Probe_AfterRosterFix",
+  "generated_at": "2026-04-02T22:00:04",
+  "source_questions_file": "X:\\1C\\NDC_1C\\docs\\ADDRESS\\question_sets\\temp_customer_role_probe_2026-04-02.json",
+  "backend_url": "http://127.0.0.1:8787/api/assistant/message",
+  "llm_provider": "local",
+  "llm_model": "qwen2.5-14b-instruct-1m",
+  "llm_base_url": "http://127.0.0.1:1234",
+  "strict_policy": "factual",
+  "totals": {
+    "questions_total": 2,
+    "ok_200_count": 2,
+    "semantic_pass_count": 2,
+    "semantic_pass_rate": 1.0,
+    "route_pass_count": 2,
+    "route_pass_rate": 1.0,
+    "strict_pass_count": 2,
+    "strict_pass_rate": 1.0,
+    "factual_count": 2,
+    "partial_coverage_count": 0,
+    "clarification_required_count": 0,
+    "http_error_count": 0,
+    "llm_decomposition_applied_count": 1,
+    "avg_elapsed_ms": 5649
+  },
+  "distributions": {
+    "reply_type": {
+      "factual": 2
+    },
+    "actual_intent": {
+      "counterparty_population_and_roles": 1,
+      "counterparty_activity_lifecycle": 1
+    },
+    "actual_mode": {
+      "address_query": 2
+    },
+    "mcp_call_status": {
+      "matched_non_empty": 2
+    },
+    "limited_reason_category": {},
+    "route_health": {
+      "ok_or_factual": 2
+    }
+  }
+}