АРЧ АП11 - Вынести coverage evidence contract для exact lane и завершить phase 4 агентным прогоном

llm_normalizer/data/autorun_generators/history.json

@@ -1,4 +1,37 @@
 [
+  {
+    "generation_id": "gen-ag04170808-1907fa",
+    "created_at": "2026-04-17T08:08:08+00:00",
+    "mode": "saved_user_sessions",
+    "title": "AGENT | Phase 4 coverage/evidence replay for counterparty fallback, inventory reset, and selected-object provenance",
+    "count": 5,
+    "domain": "address_phase4_coverage_evidence_mix",
+    "questions": [
+      "покажи все документы по чепурнову",
+      "что нам отгружал чепурнов, какой товар или услугу?",
+      "какие остатки на складе на март 2021",
+      "По выбранному объекту \"Столешница 600*3050*26 альмандин\": кто нам это поставил?",
+      "покажи еще раз остатки на эту же дату"
+    ],
+    "generated_by": "codex_agent",
+    "saved_case_set_file": "assistant_autogen_saved_user_sessions_20260417080808_gen-ag04170808-1907fa.json",
+    "context": {
+      "llm_provider": null,
+      "model": null,
+      "assistant_prompt_version": null,
+      "decomposition_prompt_version": null,
+      "prompt_fingerprint": null,
+      "autogen_personality_id": null,
+      "autogen_personality_prompt": null,
+      "source_session_id": null,
+      "saved_session_file": "assistant_saved_session_20260417080808_gen-ag04170808-1907fa.json",
+      "saved_case_set_kind": "agent_semantic_scenario",
+      "agent_run": true,
+      "agent_focus": "coverage/evidence contract on factual, fallback, and root-reset branches",
+      "architecture_phase": "turnaround_11_phase4",
+      "source_spec_file": "X:\\1C\\NDC_1C\\docs\\orchestration\\address_truth_harness_phase4_coverage_evidence_mix.json"
+    }
+  },
   {
     "generation_id": "gen-mo2kcds2-tlqmvng",
     "created_at": "2026-04-17T07:04:48.581Z",
@@ -546,4 +579,4 @@
       "saved_case_set_kind": null
     }
   }
-]
+]

llm_normalizer/data/autorun_generators/saved_sessions/assistant_saved_session_20260417080808_gen-ag04170808-1907fa.json

@@ -0,0 +1,83 @@
+{
+  "saved_at": "2026-04-17T08:08:08+00:00",
+  "generation_id": "gen-ag04170808-1907fa",
+  "mode": "saved_user_sessions",
+  "title": "AGENT | Phase 4 coverage/evidence replay for counterparty fallback, inventory reset, and selected-object provenance",
+  "agent_run": true,
+  "questions": [
+    "покажи все документы по чепурнову",
+    "что нам отгружал чепурнов, какой товар или услугу?",
+    "какие остатки на складе на март 2021",
+    "По выбранному объекту \"Столешница 600*3050*26 альмандин\": кто нам это поставил?",
+    "покажи еще раз остатки на эту же дату"
+  ],
+  "metadata": {
+    "assistant_prompt_version": null,
+    "decomposition_prompt_version": null,
+    "prompt_fingerprint": null,
+    "agent_focus": "coverage/evidence contract on factual, fallback, and root-reset branches",
+    "architecture_phase": "turnaround_11_phase4",
+    "source_spec_file": "X:\\1C\\NDC_1C\\docs\\orchestration\\address_truth_harness_phase4_coverage_evidence_mix.json"
+  },
+  "source_session_id": null,
+  "session": {
+    "session_id": null,
+    "mode": "agent_semantic_run",
+    "items": [
+      {
+        "message_id": "agent-user-001",
+        "role": "user",
+        "text": "покажи все документы по чепурнову",
+        "created_at": "2026-04-17T08:08:08+00:00",
+        "reply_type": null,
+        "trace_id": null,
+        "debug": null
+      },
+      {
+        "message_id": "agent-user-002",
+        "role": "user",
+        "text": "что нам отгружал чепурнов, какой товар или услугу?",
+        "created_at": "2026-04-17T08:08:08+00:00",
+        "reply_type": null,
+        "trace_id": null,
+        "debug": null
+      },
+      {
+        "message_id": "agent-user-003",
+        "role": "user",
+        "text": "какие остатки на складе на март 2021",
+        "created_at": "2026-04-17T08:08:08+00:00",
+        "reply_type": null,
+        "trace_id": null,
+        "debug": null
+      },
+      {
+        "message_id": "agent-user-004",
+        "role": "user",
+        "text": "По выбранному объекту \"Столешница 600*3050*26 альмандин\": кто нам это поставил?",
+        "created_at": "2026-04-17T08:08:08+00:00",
+        "reply_type": null,
+        "trace_id": null,
+        "debug": null
+      },
+      {
+        "message_id": "agent-user-005",
+        "role": "user",
+        "text": "покажи еще раз остатки на эту же дату",
+        "created_at": "2026-04-17T08:08:08+00:00",
+        "reply_type": null,
+        "trace_id": null,
+        "debug": null
+      }
+    ],
+    "agent_run": true,
+    "metadata": {
+      "assistant_prompt_version": null,
+      "decomposition_prompt_version": null,
+      "prompt_fingerprint": null,
+      "agent_focus": "coverage/evidence contract on factual, fallback, and root-reset branches",
+      "architecture_phase": "turnaround_11_phase4",
+      "source_spec_file": "X:\\1C\\NDC_1C\\docs\\orchestration\\address_truth_harness_phase4_coverage_evidence_mix.json"
+    }
+  }
+}

llm_normalizer/data/eval_cases/assistant_autogen_saved_user_sessions_20260417080808_gen-ag04170808-1907fa.json

@@ -0,0 +1,40 @@
+{
+  "suite_id": "assistant_saved_session_gen-ag04170808-1907fa",
+  "suite_version": "0.1.0",
+  "schema_version": "assistant_saved_session_suite_v0_1",
+  "generated_at": "2026-04-17T08:08:08+00:00",
+  "generation_id": "gen-ag04170808-1907fa",
+  "mode": "saved_user_sessions",
+  "title": "AGENT | Phase 4 coverage/evidence replay for counterparty fallback, inventory reset, and selected-object provenance",
+  "domain": "address_phase4_coverage_evidence_mix",
+  "scenario_count": 1,
+  "case_ids": [
+    "SAVED-001"
+  ],
+  "cases": [
+    {
+      "case_id": "SAVED-001",
+      "scenario_tag": "agent_saved_user_sessions",
+      "title": "AGENT | Phase 4 coverage/evidence replay for counterparty fallback, inventory reset, and selected-object provenance",
+      "question_type": "followup",
+      "broadness_level": "medium",
+      "turns": [
+        {
+          "user_message": "покажи все документы по чепурнову"
+        },
+        {
+          "user_message": "что нам отгружал чепурнов, какой товар или услугу?"
+        },
+        {
+          "user_message": "какие остатки на складе на март 2021"
+        },
+        {
+          "user_message": "По выбранному объекту \"Столешница 600*3050*26 альмандин\": кто нам это поставил?"
+        },
+        {
+          "user_message": "покажи еще раз остатки на эту же дату"
+        }
+      ]
+    }
+  ]
+}

llm_normalizer/data/eval_cases/assistant_saved_session_runtime_job-GwhfwhCDWz.json

@@ -0,0 +1,36 @@
+{
+  "suite_id": "assistant_saved_session_runtime_job-GwhfwhCDWz",
+  "suite_version": "0.1.0",
+  "schema_version": "assistant_saved_session_runtime_v0_1",
+  "title": "AGENT | Phase 4 coverage/evidence replay for counterparty fallback, inventory reset, and selected-object provenance",
+  "scenario_count": 1,
+  "case_ids": [
+    "SAVED-001"
+  ],
+  "cases": [
+    {
+      "case_id": "SAVED-001",
+      "scenario_tag": "saved_user_sessions_runtime",
+      "title": "AGENT | Phase 4 coverage/evidence replay for counterparty fallback, inventory reset, and selected-object provenance",
+      "question_type": "followup",
+      "broadness_level": "medium",
+      "turns": [
+        {
+          "user_message": "покажи все документы по чепурнову"
+        },
+        {
+          "user_message": "что нам отгружал чепурнов, какой товар или услугу?"
+        },
+        {
+          "user_message": "какие остатки на складе на март 2021"
+        },
+        {
+          "user_message": "По выбранному объекту \"Столешница 600*3050*26 альмандин\": кто нам это поставил?"
+        },
+        {
+          "user_message": "покажи еще раз остатки на эту же дату"
+        }
+      ]
+    }
+  ]
+}