АДРЕСНЫЙ РЕЖИМ -ADDRESS:Шаг 1 - ЛЛМ ФЕРСТ + feat(address): стабилизация wave1 dynamic resolver контрагентов, follow-up carryover и актуализация docs/tests
This commit is contained in:
@@ -0,0 +1,28 @@
|
||||
# 2026-04-02_Address_Batch1_NextPack_Q6_Q7_Q28
|
||||
|
||||
Generated at: 2026-04-02T21:06:15
|
||||
Questions file: X:\1C\NDC_1C\docs\ADDRESS\question_sets\temp_batch1_next_pack_q6_q7_q28_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: 9
|
||||
- ok_200_count: 9
|
||||
- semantic_pass_count: 9
|
||||
- semantic_pass_rate: 1.0
|
||||
- route_pass_count: 9
|
||||
- route_pass_rate: 1.0
|
||||
- strict_pass_count: 9
|
||||
- strict_pass_rate: 1.0
|
||||
- factual_count: 9
|
||||
- partial_coverage_count: 0
|
||||
- clarification_required_count: 0
|
||||
- http_error_count: 0
|
||||
- llm_decomposition_applied_count: 4
|
||||
- avg_elapsed_ms: 5195.3
|
||||
|
||||
## Files
|
||||
- run_summary.json
|
||||
- full_live_results.json
|
||||
- failures_only.json
|
||||
@@ -0,0 +1 @@
|
||||
[]
|
||||
+1361
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,13 @@
|
||||
# Response Audit: 2026-04-02_Address_Batch1_NextPack_Q6_Q7_Q28
|
||||
|
||||
| id | strict | route_health | reply_type | intent | limited_reason | question | assistant_first_line |
|
||||
|---|---|---|---|---|---|---|---|
|
||||
| NXP_C006 | True | ok_or_factual | factual | counterparty_population_and_roles | None | Сколько всего уникальных контрагентов в базе? | Профиль контрагентов собран (catalog + bank-doc activity aggregate). |
|
||||
| NXP_C007 | True | ok_or_factual | factual | counterparty_population_and_roles | None | Сколько у нас заказчиков, поставщиков и смешанных контрагентов? | Профиль контрагентов собран (catalog + bank-doc activity aggregate). |
|
||||
| NXP_C008 | True | ok_or_factual | factual | contract_usage_overview | None | Сколько всего договоров заведено и сколько из них реально использовались? | Профиль договорной базы собран (catalog + usage aggregate). |
|
||||
| NXP_N006 | True | ok_or_factual | factual | counterparty_population_and_roles | None | скок уник контрагентов вообще есть | Профиль контрагентов собран (catalog + bank-doc activity aggregate). |
|
||||
| NXP_N007 | True | ok_or_factual | factual | counterparty_population_and_roles | None | разбей контров на клиентов/поставщиков/смешанных | Профиль контрагентов собран (catalog + bank-doc activity aggregate). |
|
||||
| NXP_N008 | True | ok_or_factual | factual | contract_usage_overview | None | договоров сколько всего и сколько реально юзались? | Профиль договорной базы собран (catalog + usage aggregate). |
|
||||
| NXP_F004 | True | ok_or_factual | factual | counterparty_population_and_roles | None | Сколько всего уникальных контрагентов в базе? | Профиль контрагентов собран (catalog + bank-doc activity aggregate). |
|
||||
| NXP_F005 | True | ok_or_factual | factual | counterparty_population_and_roles | None | а теперь разбей их на заказчиков и поставщиков | Профиль контрагентов собран (catalog + bank-doc activity aggregate). |
|
||||
| NXP_F006 | True | ok_or_factual | factual | contract_usage_overview | None | и сразу сколько всего договоров и сколько used | Профиль договорной базы собран (catalog + usage aggregate). |
|
||||
@@ -0,0 +1,45 @@
|
||||
{
|
||||
"run_id": "2026-04-02_Address_Batch1_NextPack_Q6_Q7_Q28",
|
||||
"generated_at": "2026-04-02T21:06:15",
|
||||
"source_questions_file": "X:\\1C\\NDC_1C\\docs\\ADDRESS\\question_sets\\temp_batch1_next_pack_q6_q7_q28_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": 9,
|
||||
"ok_200_count": 9,
|
||||
"semantic_pass_count": 9,
|
||||
"semantic_pass_rate": 1.0,
|
||||
"route_pass_count": 9,
|
||||
"route_pass_rate": 1.0,
|
||||
"strict_pass_count": 9,
|
||||
"strict_pass_rate": 1.0,
|
||||
"factual_count": 9,
|
||||
"partial_coverage_count": 0,
|
||||
"clarification_required_count": 0,
|
||||
"http_error_count": 0,
|
||||
"llm_decomposition_applied_count": 4,
|
||||
"avg_elapsed_ms": 5195.3
|
||||
},
|
||||
"distributions": {
|
||||
"reply_type": {
|
||||
"factual": 9
|
||||
},
|
||||
"actual_intent": {
|
||||
"counterparty_population_and_roles": 6,
|
||||
"contract_usage_overview": 3
|
||||
},
|
||||
"actual_mode": {
|
||||
"address_query": 9
|
||||
},
|
||||
"mcp_call_status": {
|
||||
"matched_non_empty": 9
|
||||
},
|
||||
"limited_reason_category": {},
|
||||
"route_health": {
|
||||
"ok_or_factual": 9
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,28 @@
|
||||
# 2026-04-02_Address_Batch2_Q8_Q9_Targeted
|
||||
|
||||
Generated at: 2026-04-02T21:37:06
|
||||
Questions file: X:\1C\NDC_1C\docs\ADDRESS\question_sets\temp_batch2_q8_q9_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: 6
|
||||
- ok_200_count: 6
|
||||
- semantic_pass_count: 6
|
||||
- semantic_pass_rate: 1.0
|
||||
- route_pass_count: 6
|
||||
- route_pass_rate: 1.0
|
||||
- strict_pass_count: 6
|
||||
- strict_pass_rate: 1.0
|
||||
- factual_count: 6
|
||||
- partial_coverage_count: 0
|
||||
- clarification_required_count: 0
|
||||
- http_error_count: 0
|
||||
- llm_decomposition_applied_count: 0
|
||||
- avg_elapsed_ms: 914.3
|
||||
|
||||
## Files
|
||||
- run_summary.json
|
||||
- full_live_results.json
|
||||
- failures_only.json
|
||||
@@ -0,0 +1 @@
|
||||
[]
|
||||
File diff suppressed because one or more lines are too long
@@ -0,0 +1,10 @@
|
||||
# Response Audit: 2026-04-02_Address_Batch2_Q8_Q9_Targeted
|
||||
|
||||
| id | strict | route_health | reply_type | intent | limited_reason | question | assistant_first_line |
|
||||
|---|---|---|---|---|---|---|---|
|
||||
| B2_C001 | True | ok_or_factual | factual | counterparty_activity_lifecycle | None | Какие заказчики работали с нами в 2020 году? | Собран профиль активности заказчиков (bank-doc activity aggregate). |
|
||||
| B2_C002 | True | ok_or_factual | factual | counterparty_activity_lifecycle | None | Какие заказчики работали с нами за все время? | Собран профиль активности заказчиков (bank-doc activity aggregate). |
|
||||
| B2_N001 | True | ok_or_factual | factual | counterparty_activity_lifecycle | None | какие клиенты у нас были активны в 2020? | Собран профиль активности заказчиков (bank-doc activity aggregate). |
|
||||
| B2_N002 | True | ok_or_factual | factual | counterparty_activity_lifecycle | None | выведи активных клиентов за все время | Собран профиль активности заказчиков (bank-doc activity aggregate). |
|
||||
| B2_F001 | True | ok_or_factual | factual | counterparty_activity_lifecycle | None | Какие заказчики работали с нами в 2020 году? | Собран профиль активности заказчиков (bank-doc activity aggregate). |
|
||||
| B2_F002 | True | ok_or_factual | factual | counterparty_activity_lifecycle | None | а за все время? | Собран профиль активности заказчиков (bank-doc activity aggregate). |
|
||||
@@ -0,0 +1,44 @@
|
||||
{
|
||||
"run_id": "2026-04-02_Address_Batch2_Q8_Q9_Targeted",
|
||||
"generated_at": "2026-04-02T21:37:06",
|
||||
"source_questions_file": "X:\\1C\\NDC_1C\\docs\\ADDRESS\\question_sets\\temp_batch2_q8_q9_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": 6,
|
||||
"ok_200_count": 6,
|
||||
"semantic_pass_count": 6,
|
||||
"semantic_pass_rate": 1.0,
|
||||
"route_pass_count": 6,
|
||||
"route_pass_rate": 1.0,
|
||||
"strict_pass_count": 6,
|
||||
"strict_pass_rate": 1.0,
|
||||
"factual_count": 6,
|
||||
"partial_coverage_count": 0,
|
||||
"clarification_required_count": 0,
|
||||
"http_error_count": 0,
|
||||
"llm_decomposition_applied_count": 0,
|
||||
"avg_elapsed_ms": 914.3
|
||||
},
|
||||
"distributions": {
|
||||
"reply_type": {
|
||||
"factual": 6
|
||||
},
|
||||
"actual_intent": {
|
||||
"counterparty_activity_lifecycle": 6
|
||||
},
|
||||
"actual_mode": {
|
||||
"address_query": 6
|
||||
},
|
||||
"mcp_call_status": {
|
||||
"matched_non_empty": 6
|
||||
},
|
||||
"limited_reason_category": {},
|
||||
"route_health": {
|
||||
"ok_or_factual": 6
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,28 @@
|
||||
# 2026-04-02_Address_CustomerRole_Probe
|
||||
|
||||
Generated at: 2026-04-02T21:57:59
|
||||
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: 1
|
||||
- route_pass_rate: 0.5
|
||||
- strict_pass_count: 1
|
||||
- strict_pass_rate: 0.5
|
||||
- factual_count: 1
|
||||
- partial_coverage_count: 1
|
||||
- clarification_required_count: 0
|
||||
- http_error_count: 0
|
||||
- llm_decomposition_applied_count: 1
|
||||
- avg_elapsed_ms: 5432.5
|
||||
|
||||
## Files
|
||||
- run_summary.json
|
||||
- full_live_results.json
|
||||
- failures_only.json
|
||||
@@ -0,0 +1,141 @@
|
||||
[
|
||||
{
|
||||
"index": 2,
|
||||
"id": "P002",
|
||||
"question": "кто у нас заказчики вообще",
|
||||
"session": null,
|
||||
"session_id": "asst-2026-04-02_Address_CustomerRole_Probe-p002",
|
||||
"status_code": 200,
|
||||
"ok": true,
|
||||
"elapsed_ms": 4503,
|
||||
"reply_type": "partial_coverage",
|
||||
"trace_id": "address-_VaGpRcHM0",
|
||||
"assistant_reply": "Этот запрос не подходит под address_query V1.\nПричина: intent пока не поддержан в address V1.\nЧто нужно уточнить: переформулируйте вопрос как адресный lookup по счету/контрагенту/договору.",
|
||||
"assistant_reply_first_line": "Этот запрос не подходит под address_query V1.",
|
||||
"expected_intent": null,
|
||||
"actual_intent": "unknown",
|
||||
"intent_match": true,
|
||||
"expected_mode": "address_query",
|
||||
"actual_mode": "address_query",
|
||||
"mode_match": true,
|
||||
"expected_reply_type": null,
|
||||
"reply_match": true,
|
||||
"semantic_pass": true,
|
||||
"route_pass": false,
|
||||
"route_health": "blocked_unsupported",
|
||||
"strict_policy": "factual",
|
||||
"strict_pass": false,
|
||||
"selected_recipe": null,
|
||||
"missing_required_filters": [],
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"rows_fetched": 0,
|
||||
"rows_matched": 0,
|
||||
"mcp_call_status": "skipped",
|
||||
"limited_reason_category": "unsupported",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_reason": "normalized_fragment_same",
|
||||
"fallback_rule_hit": null,
|
||||
"debug_payload": {
|
||||
"trace_id": "address-_VaGpRcHM0",
|
||||
"prompt_version": "address_query_runtime_v1",
|
||||
"schema_version": "address_query_runtime_v1",
|
||||
"fallback_type": "partial",
|
||||
"route_summary": null,
|
||||
"fragments": [],
|
||||
"requirements_extracted": [],
|
||||
"coverage_report": {
|
||||
"requirements_total": 0,
|
||||
"requirements_covered": 0,
|
||||
"requirements_uncovered": [],
|
||||
"requirements_partially_covered": [],
|
||||
"clarification_needed_for": [],
|
||||
"out_of_scope_requirements": []
|
||||
},
|
||||
"routes": [],
|
||||
"retrieval_status": [],
|
||||
"retrieval_results": [],
|
||||
"answer_grounding_check": {
|
||||
"status": "partial",
|
||||
"route_subject_match": true,
|
||||
"missing_requirements": [],
|
||||
"reasons": [
|
||||
"address_action_detected",
|
||||
"address_entity_detected",
|
||||
"shape_not_detected",
|
||||
"intent_not_supported_in_v1"
|
||||
],
|
||||
"why_included_summary": [],
|
||||
"selection_reason_summary": []
|
||||
},
|
||||
"dropped_intent_segments": [],
|
||||
"detected_mode": "address_query",
|
||||
"detected_mode_confidence": "high",
|
||||
"query_shape": "UNKNOWN",
|
||||
"query_shape_confidence": "low",
|
||||
"detected_intent": "unknown",
|
||||
"detected_intent_confidence": "low",
|
||||
"extracted_filters": {
|
||||
"sort": "period_desc",
|
||||
"limit": 20
|
||||
},
|
||||
"missing_required_filters": [],
|
||||
"selected_recipe": null,
|
||||
"mcp_call_status_legacy": "skipped",
|
||||
"account_scope_mode": "strict",
|
||||
"account_scope_fallback_applied": false,
|
||||
"anchor_type": "unknown",
|
||||
"anchor_value_raw": null,
|
||||
"anchor_value_resolved": null,
|
||||
"resolver_confidence": "low",
|
||||
"ambiguity_count": 0,
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"mcp_call_status": "skipped",
|
||||
"rows_fetched": 0,
|
||||
"raw_rows_received": 0,
|
||||
"rows_after_account_scope": 0,
|
||||
"rows_after_recipe_filter": 0,
|
||||
"rows_materialized": 0,
|
||||
"rows_matched": 0,
|
||||
"raw_row_keys_sample": [],
|
||||
"materialization_drop_reason": "none",
|
||||
"account_token_raw": null,
|
||||
"account_token_normalized": null,
|
||||
"account_scope_fields_checked": [
|
||||
"account_dt",
|
||||
"account_kt",
|
||||
"registrator",
|
||||
"analytics"
|
||||
],
|
||||
"account_scope_match_strategy": "account_code_regex_plus_alias_map_v1",
|
||||
"account_scope_drop_reason": "not_applicable",
|
||||
"runtime_readiness": "DEEP_ONLY",
|
||||
"limited_reason_category": "unsupported",
|
||||
"response_type": "LIMITED_WITH_REASON",
|
||||
"execution_lane": "address_query",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_attempted": true,
|
||||
"llm_provider_used": "local",
|
||||
"llm_decomposition_trace_id": "wDo3K7gI394XmR",
|
||||
"llm_decomposition_effective_message": "кто у нас заказчики вообще",
|
||||
"llm_decomposition_reason": "normalized_fragment_same",
|
||||
"llm_canonical_candidate_detected": true,
|
||||
"fallback_rule_hit": null,
|
||||
"sanitized_user_message": "кто у нас заказчики вообще",
|
||||
"tool_gate_decision": "run_address_lane",
|
||||
"tool_gate_reason": "address_mode_classifier_detected",
|
||||
"answer_structure_v11": null,
|
||||
"investigation_state_snapshot": null,
|
||||
"normalized": null,
|
||||
"normalizer_output": {
|
||||
"trace_id": "wDo3K7gI394XmR",
|
||||
"prompt_version": "normalizer_v2_0_2",
|
||||
"applied": false,
|
||||
"effective_message": "кто у нас заказчики вообще"
|
||||
}
|
||||
},
|
||||
"error_code": null,
|
||||
"error_message": null
|
||||
}
|
||||
]
|
||||
@@ -0,0 +1,343 @@
|
||||
{
|
||||
"run_id": "2026-04-02_Address_CustomerRole_Probe",
|
||||
"generated_at": "2026-04-02T21:57:59",
|
||||
"summary": {
|
||||
"run_id": "2026-04-02_Address_CustomerRole_Probe",
|
||||
"generated_at": "2026-04-02T21:57:59",
|
||||
"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": 1,
|
||||
"route_pass_rate": 0.5,
|
||||
"strict_pass_count": 1,
|
||||
"strict_pass_rate": 0.5,
|
||||
"factual_count": 1,
|
||||
"partial_coverage_count": 1,
|
||||
"clarification_required_count": 0,
|
||||
"http_error_count": 0,
|
||||
"llm_decomposition_applied_count": 1,
|
||||
"avg_elapsed_ms": 5432.5
|
||||
},
|
||||
"distributions": {
|
||||
"reply_type": {
|
||||
"factual": 1,
|
||||
"partial_coverage": 1
|
||||
},
|
||||
"actual_intent": {
|
||||
"counterparty_population_and_roles": 1,
|
||||
"unknown": 1
|
||||
},
|
||||
"actual_mode": {
|
||||
"address_query": 2
|
||||
},
|
||||
"mcp_call_status": {
|
||||
"matched_non_empty": 1,
|
||||
"skipped": 1
|
||||
},
|
||||
"limited_reason_category": {
|
||||
"unsupported": 1
|
||||
},
|
||||
"route_health": {
|
||||
"ok_or_factual": 1,
|
||||
"blocked_unsupported": 1
|
||||
}
|
||||
}
|
||||
},
|
||||
"rows": [
|
||||
{
|
||||
"index": 1,
|
||||
"id": "P001",
|
||||
"question": "скок клиентов",
|
||||
"session": null,
|
||||
"session_id": "asst-2026-04-02_Address_CustomerRole_Probe-p001",
|
||||
"status_code": 200,
|
||||
"ok": true,
|
||||
"elapsed_ms": 6362,
|
||||
"reply_type": "factual",
|
||||
"trace_id": "address-BlXqmGgtXZ",
|
||||
"assistant_reply": "Профиль контрагентов собран (catalog + bank-doc activity aggregate).\nСтрок агрегата: 5.\nВсего уникальных контрагентов в базе: 139.",
|
||||
"assistant_reply_first_line": "Профиль контрагентов собран (catalog + bank-doc activity aggregate).",
|
||||
"expected_intent": null,
|
||||
"actual_intent": "counterparty_population_and_roles",
|
||||
"intent_match": true,
|
||||
"expected_mode": "address_query",
|
||||
"actual_mode": "address_query",
|
||||
"mode_match": true,
|
||||
"expected_reply_type": null,
|
||||
"reply_match": true,
|
||||
"semantic_pass": true,
|
||||
"route_pass": true,
|
||||
"route_health": "ok_or_factual",
|
||||
"strict_policy": "factual",
|
||||
"strict_pass": true,
|
||||
"selected_recipe": "address_counterparty_population_roles_v1",
|
||||
"missing_required_filters": [],
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"rows_fetched": 5,
|
||||
"rows_matched": 5,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"limited_reason_category": null,
|
||||
"llm_decomposition_applied": true,
|
||||
"llm_decomposition_reason": "normalized_fragment_applied",
|
||||
"fallback_rule_hit": null,
|
||||
"debug_payload": {
|
||||
"trace_id": "address-BlXqmGgtXZ",
|
||||
"prompt_version": "address_query_runtime_v1",
|
||||
"schema_version": "address_query_runtime_v1",
|
||||
"fallback_type": "none",
|
||||
"route_summary": null,
|
||||
"fragments": [],
|
||||
"requirements_extracted": [],
|
||||
"coverage_report": {
|
||||
"requirements_total": 0,
|
||||
"requirements_covered": 0,
|
||||
"requirements_uncovered": [],
|
||||
"requirements_partially_covered": [],
|
||||
"clarification_needed_for": [],
|
||||
"out_of_scope_requirements": []
|
||||
},
|
||||
"routes": [],
|
||||
"retrieval_status": [],
|
||||
"retrieval_results": [],
|
||||
"answer_grounding_check": {
|
||||
"status": "grounded",
|
||||
"route_subject_match": true,
|
||||
"missing_requirements": [],
|
||||
"reasons": [
|
||||
"address_action_detected",
|
||||
"address_entity_detected",
|
||||
"object_signal_detected",
|
||||
"counterparty_population_and_roles_signal_detected"
|
||||
],
|
||||
"why_included_summary": [],
|
||||
"selection_reason_summary": []
|
||||
},
|
||||
"dropped_intent_segments": [],
|
||||
"detected_mode": "address_query",
|
||||
"detected_mode_confidence": "high",
|
||||
"query_shape": "OBJECT_LOOKUP",
|
||||
"query_shape_confidence": "medium",
|
||||
"detected_intent": "counterparty_population_and_roles",
|
||||
"detected_intent_confidence": "high",
|
||||
"extracted_filters": {
|
||||
"sort": "period_desc",
|
||||
"period_to": "2026-04-02"
|
||||
},
|
||||
"missing_required_filters": [],
|
||||
"selected_recipe": "address_counterparty_population_roles_v1",
|
||||
"mcp_call_status_legacy": "matched_non_empty",
|
||||
"account_scope_mode": "preferred",
|
||||
"account_scope_fallback_applied": false,
|
||||
"anchor_type": "unknown",
|
||||
"anchor_value_raw": null,
|
||||
"anchor_value_resolved": null,
|
||||
"resolver_confidence": "low",
|
||||
"ambiguity_count": 0,
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"rows_fetched": 5,
|
||||
"raw_rows_received": 5,
|
||||
"rows_after_account_scope": 5,
|
||||
"rows_after_recipe_filter": 5,
|
||||
"rows_materialized": 5,
|
||||
"rows_matched": 5,
|
||||
"raw_row_keys_sample": [
|
||||
"Период",
|
||||
"Регистратор",
|
||||
"СчетДт",
|
||||
"СчетКт",
|
||||
"Сумма",
|
||||
"Period",
|
||||
"Registrator",
|
||||
"Amount"
|
||||
],
|
||||
"materialization_drop_reason": "none",
|
||||
"account_token_raw": null,
|
||||
"account_token_normalized": null,
|
||||
"account_scope_fields_checked": [
|
||||
"account_dt",
|
||||
"account_kt",
|
||||
"registrator",
|
||||
"analytics"
|
||||
],
|
||||
"account_scope_match_strategy": "account_code_regex_plus_alias_map_v1",
|
||||
"account_scope_drop_reason": "not_applicable",
|
||||
"runtime_readiness": "LIVE_QUERYABLE_WITH_LIMITS",
|
||||
"limited_reason_category": null,
|
||||
"response_type": "FACTUAL_SUMMARY",
|
||||
"execution_lane": "address_query",
|
||||
"llm_decomposition_applied": true,
|
||||
"llm_decomposition_attempted": true,
|
||||
"llm_provider_used": "local",
|
||||
"llm_decomposition_trace_id": "kR-YwJ1dNUHCTn",
|
||||
"llm_decomposition_effective_message": "сколько контрагентов?",
|
||||
"llm_decomposition_reason": "normalized_fragment_applied",
|
||||
"llm_canonical_candidate_detected": true,
|
||||
"fallback_rule_hit": null,
|
||||
"sanitized_user_message": "скок клиентов",
|
||||
"tool_gate_decision": "run_address_lane",
|
||||
"tool_gate_reason": "address_mode_classifier_detected",
|
||||
"answer_structure_v11": null,
|
||||
"investigation_state_snapshot": null,
|
||||
"normalized": null,
|
||||
"normalizer_output": {
|
||||
"trace_id": "kR-YwJ1dNUHCTn",
|
||||
"prompt_version": "normalizer_v2_0_2",
|
||||
"applied": true,
|
||||
"effective_message": "сколько контрагентов?"
|
||||
}
|
||||
},
|
||||
"error_code": null,
|
||||
"error_message": null
|
||||
},
|
||||
{
|
||||
"index": 2,
|
||||
"id": "P002",
|
||||
"question": "кто у нас заказчики вообще",
|
||||
"session": null,
|
||||
"session_id": "asst-2026-04-02_Address_CustomerRole_Probe-p002",
|
||||
"status_code": 200,
|
||||
"ok": true,
|
||||
"elapsed_ms": 4503,
|
||||
"reply_type": "partial_coverage",
|
||||
"trace_id": "address-_VaGpRcHM0",
|
||||
"assistant_reply": "Этот запрос не подходит под address_query V1.\nПричина: intent пока не поддержан в address V1.\nЧто нужно уточнить: переформулируйте вопрос как адресный lookup по счету/контрагенту/договору.",
|
||||
"assistant_reply_first_line": "Этот запрос не подходит под address_query V1.",
|
||||
"expected_intent": null,
|
||||
"actual_intent": "unknown",
|
||||
"intent_match": true,
|
||||
"expected_mode": "address_query",
|
||||
"actual_mode": "address_query",
|
||||
"mode_match": true,
|
||||
"expected_reply_type": null,
|
||||
"reply_match": true,
|
||||
"semantic_pass": true,
|
||||
"route_pass": false,
|
||||
"route_health": "blocked_unsupported",
|
||||
"strict_policy": "factual",
|
||||
"strict_pass": false,
|
||||
"selected_recipe": null,
|
||||
"missing_required_filters": [],
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"rows_fetched": 0,
|
||||
"rows_matched": 0,
|
||||
"mcp_call_status": "skipped",
|
||||
"limited_reason_category": "unsupported",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_reason": "normalized_fragment_same",
|
||||
"fallback_rule_hit": null,
|
||||
"debug_payload": {
|
||||
"trace_id": "address-_VaGpRcHM0",
|
||||
"prompt_version": "address_query_runtime_v1",
|
||||
"schema_version": "address_query_runtime_v1",
|
||||
"fallback_type": "partial",
|
||||
"route_summary": null,
|
||||
"fragments": [],
|
||||
"requirements_extracted": [],
|
||||
"coverage_report": {
|
||||
"requirements_total": 0,
|
||||
"requirements_covered": 0,
|
||||
"requirements_uncovered": [],
|
||||
"requirements_partially_covered": [],
|
||||
"clarification_needed_for": [],
|
||||
"out_of_scope_requirements": []
|
||||
},
|
||||
"routes": [],
|
||||
"retrieval_status": [],
|
||||
"retrieval_results": [],
|
||||
"answer_grounding_check": {
|
||||
"status": "partial",
|
||||
"route_subject_match": true,
|
||||
"missing_requirements": [],
|
||||
"reasons": [
|
||||
"address_action_detected",
|
||||
"address_entity_detected",
|
||||
"shape_not_detected",
|
||||
"intent_not_supported_in_v1"
|
||||
],
|
||||
"why_included_summary": [],
|
||||
"selection_reason_summary": []
|
||||
},
|
||||
"dropped_intent_segments": [],
|
||||
"detected_mode": "address_query",
|
||||
"detected_mode_confidence": "high",
|
||||
"query_shape": "UNKNOWN",
|
||||
"query_shape_confidence": "low",
|
||||
"detected_intent": "unknown",
|
||||
"detected_intent_confidence": "low",
|
||||
"extracted_filters": {
|
||||
"sort": "period_desc",
|
||||
"limit": 20
|
||||
},
|
||||
"missing_required_filters": [],
|
||||
"selected_recipe": null,
|
||||
"mcp_call_status_legacy": "skipped",
|
||||
"account_scope_mode": "strict",
|
||||
"account_scope_fallback_applied": false,
|
||||
"anchor_type": "unknown",
|
||||
"anchor_value_raw": null,
|
||||
"anchor_value_resolved": null,
|
||||
"resolver_confidence": "low",
|
||||
"ambiguity_count": 0,
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"mcp_call_status": "skipped",
|
||||
"rows_fetched": 0,
|
||||
"raw_rows_received": 0,
|
||||
"rows_after_account_scope": 0,
|
||||
"rows_after_recipe_filter": 0,
|
||||
"rows_materialized": 0,
|
||||
"rows_matched": 0,
|
||||
"raw_row_keys_sample": [],
|
||||
"materialization_drop_reason": "none",
|
||||
"account_token_raw": null,
|
||||
"account_token_normalized": null,
|
||||
"account_scope_fields_checked": [
|
||||
"account_dt",
|
||||
"account_kt",
|
||||
"registrator",
|
||||
"analytics"
|
||||
],
|
||||
"account_scope_match_strategy": "account_code_regex_plus_alias_map_v1",
|
||||
"account_scope_drop_reason": "not_applicable",
|
||||
"runtime_readiness": "DEEP_ONLY",
|
||||
"limited_reason_category": "unsupported",
|
||||
"response_type": "LIMITED_WITH_REASON",
|
||||
"execution_lane": "address_query",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_attempted": true,
|
||||
"llm_provider_used": "local",
|
||||
"llm_decomposition_trace_id": "wDo3K7gI394XmR",
|
||||
"llm_decomposition_effective_message": "кто у нас заказчики вообще",
|
||||
"llm_decomposition_reason": "normalized_fragment_same",
|
||||
"llm_canonical_candidate_detected": true,
|
||||
"fallback_rule_hit": null,
|
||||
"sanitized_user_message": "кто у нас заказчики вообще",
|
||||
"tool_gate_decision": "run_address_lane",
|
||||
"tool_gate_reason": "address_mode_classifier_detected",
|
||||
"answer_structure_v11": null,
|
||||
"investigation_state_snapshot": null,
|
||||
"normalized": null,
|
||||
"normalizer_output": {
|
||||
"trace_id": "wDo3K7gI394XmR",
|
||||
"prompt_version": "normalizer_v2_0_2",
|
||||
"applied": false,
|
||||
"effective_message": "кто у нас заказчики вообще"
|
||||
}
|
||||
},
|
||||
"error_code": null,
|
||||
"error_message": null
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,6 @@
|
||||
# Response Audit: 2026-04-02_Address_CustomerRole_Probe
|
||||
|
||||
| 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 | False | blocked_unsupported | partial_coverage | unknown | unsupported | кто у нас заказчики вообще | Этот запрос не подходит под address_query V1. |
|
||||
@@ -0,0 +1,50 @@
|
||||
{
|
||||
"run_id": "2026-04-02_Address_CustomerRole_Probe",
|
||||
"generated_at": "2026-04-02T21:57:59",
|
||||
"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": 1,
|
||||
"route_pass_rate": 0.5,
|
||||
"strict_pass_count": 1,
|
||||
"strict_pass_rate": 0.5,
|
||||
"factual_count": 1,
|
||||
"partial_coverage_count": 1,
|
||||
"clarification_required_count": 0,
|
||||
"http_error_count": 0,
|
||||
"llm_decomposition_applied_count": 1,
|
||||
"avg_elapsed_ms": 5432.5
|
||||
},
|
||||
"distributions": {
|
||||
"reply_type": {
|
||||
"factual": 1,
|
||||
"partial_coverage": 1
|
||||
},
|
||||
"actual_intent": {
|
||||
"counterparty_population_and_roles": 1,
|
||||
"unknown": 1
|
||||
},
|
||||
"actual_mode": {
|
||||
"address_query": 2
|
||||
},
|
||||
"mcp_call_status": {
|
||||
"matched_non_empty": 1,
|
||||
"skipped": 1
|
||||
},
|
||||
"limited_reason_category": {
|
||||
"unsupported": 1
|
||||
},
|
||||
"route_health": {
|
||||
"ok_or_factual": 1,
|
||||
"blocked_unsupported": 1
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -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
|
||||
+1
@@ -0,0 +1 @@
|
||||
[]
|
||||
+348
File diff suppressed because one or more lines are too long
+6
@@ -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). |
|
||||
+45
@@ -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
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,33 @@
|
||||
# 2026-04-02_Address_GateBlock_Probe_WithMetrics
|
||||
|
||||
Generated at: 2026-04-02T22:11:14
|
||||
Questions file: X:\1C\NDC_1C\docs\ADDRESS\question_sets\temp_gate_block_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: semantic
|
||||
|
||||
## Totals
|
||||
- questions_total: 2
|
||||
- ok_200_count: 2
|
||||
- semantic_pass_count: 1
|
||||
- semantic_pass_rate: 0.5
|
||||
- route_pass_count: 1
|
||||
- route_pass_rate: 0.5
|
||||
- strict_pass_count: 1
|
||||
- strict_pass_rate: 0.5
|
||||
- factual_count: 1
|
||||
- partial_coverage_count: 0
|
||||
- clarification_required_count: 1
|
||||
- http_error_count: 0
|
||||
- llm_decomposition_attempted_count: 1
|
||||
- llm_decomposition_applied_count: 0
|
||||
- llm_fallback_count: 0
|
||||
- llm_fallback_rate: 0.0
|
||||
- tool_gate_blocked_count: 0
|
||||
- tool_gate_blocked_rate: 0.0
|
||||
- avg_elapsed_ms: 8938
|
||||
|
||||
## Files
|
||||
- run_summary.json
|
||||
- full_live_results.json
|
||||
- failures_only.json
|
||||
@@ -0,0 +1,395 @@
|
||||
[
|
||||
{
|
||||
"index": 1,
|
||||
"id": "G001",
|
||||
"question": "привет как дела",
|
||||
"session": null,
|
||||
"session_id": "asst-2026-04-02_Address_GateBlock_Probe_WithMetrics-g001",
|
||||
"status_code": 200,
|
||||
"ok": true,
|
||||
"elapsed_ms": 12732,
|
||||
"reply_type": "clarification_required",
|
||||
"trace_id": "y_xkHosQzDZRaL",
|
||||
"assistant_reply": "Коротко: Наиболее вероятный механизм проблемы подтвержден частично и требует первичной проверки. Что сломано:\n- Есть признаки проблемы, но без уточнений по периоду и объекту вывод ненадежен. Почему это похоже на проблему:\n- Сигнал проблемы есть, но механизм подтвержден не полностью. На чем это основано:\n- Опора частичная: часть требований покрыта не полностью.\n- Отдельно не подтверждено или покрыто частично: R1. Что проверить первым:\n- Уточните период проверки, чтобы подтвердить проблему без лишнего шума.\n- Проверьте связку документов и проводок по проблемному участку в указанном периоде.\n- Уточните период проверки (например, июль 2020). Ограничения:\n- Ни одно требование не получило подтвержденного покрытия.\n- Нет explainable-сигналов why_included в результатах выборки.\n- required anchors claim-bound grounding.\n- evidence.\n- Targeted evidence acquisition claim target path.",
|
||||
"assistant_reply_first_line": "Коротко: Наиболее вероятный механизм проблемы подтвержден частично и требует первичной проверки. Что сломано:",
|
||||
"expected_intent": null,
|
||||
"actual_intent": null,
|
||||
"intent_match": true,
|
||||
"expected_mode": "address_query",
|
||||
"actual_mode": null,
|
||||
"mode_match": false,
|
||||
"expected_reply_type": null,
|
||||
"reply_match": true,
|
||||
"semantic_pass": false,
|
||||
"route_pass": false,
|
||||
"route_health": "blocked_clarification",
|
||||
"strict_policy": "semantic",
|
||||
"strict_pass": false,
|
||||
"selected_recipe": null,
|
||||
"missing_required_filters": null,
|
||||
"match_failure_stage": null,
|
||||
"match_failure_reason": null,
|
||||
"rows_fetched": null,
|
||||
"rows_matched": null,
|
||||
"mcp_call_status": null,
|
||||
"limited_reason_category": null,
|
||||
"llm_decomposition_attempted": null,
|
||||
"llm_decomposition_applied": null,
|
||||
"llm_decomposition_reason": null,
|
||||
"llm_canonical_candidate_detected": null,
|
||||
"fallback_rule_hit": null,
|
||||
"tool_gate_decision": null,
|
||||
"tool_gate_reason": null,
|
||||
"predecompose_contract_intent": null,
|
||||
"predecompose_contract_aggregation_profile": null,
|
||||
"predecompose_contract_period_scope": null,
|
||||
"debug_payload": {
|
||||
"trace_id": "y_xkHosQzDZRaL",
|
||||
"prompt_version": "address_query_runtime_v1",
|
||||
"schema_version": "v1",
|
||||
"fallback_type": "clarification",
|
||||
"route_summary": null,
|
||||
"fragments": [],
|
||||
"requirements_extracted": [
|
||||
{
|
||||
"requirement_id": "R1",
|
||||
"source_fragment_id": null,
|
||||
"requirement_text": "привет как дела",
|
||||
"subject_tokens": [],
|
||||
"status": "clarification_needed",
|
||||
"route": null
|
||||
}
|
||||
],
|
||||
"coverage_report": {
|
||||
"requirements_total": 1,
|
||||
"requirements_covered": 0,
|
||||
"requirements_uncovered": [],
|
||||
"requirements_partially_covered": [],
|
||||
"clarification_needed_for": [
|
||||
"R1"
|
||||
],
|
||||
"out_of_scope_requirements": []
|
||||
},
|
||||
"routes": [],
|
||||
"retrieval_status": [],
|
||||
"retrieval_results": [],
|
||||
"answer_grounding_check": {
|
||||
"status": "no_grounded_answer",
|
||||
"route_subject_match": true,
|
||||
"missing_requirements": [
|
||||
"R1"
|
||||
],
|
||||
"reasons": [
|
||||
"Ни одно требование не получило подтвержденного покрытия.",
|
||||
"Нет explainable-сигналов why_included в результатах выборки.",
|
||||
"Недостаточно покрытия required anchors для claim-bound grounding.",
|
||||
"Недостаточно допустимого evidence для обоснованного ответа.",
|
||||
"Targeted evidence acquisition не дал допустимых попаданий по claim target path."
|
||||
],
|
||||
"why_included_summary": [],
|
||||
"selection_reason_summary": []
|
||||
},
|
||||
"dropped_intent_segments": [],
|
||||
"question_type_class": "why_breaks",
|
||||
"company_anchors": {
|
||||
"contract_numbers": [],
|
||||
"document_numbers": [],
|
||||
"dates": [],
|
||||
"amounts": [],
|
||||
"accounts": [],
|
||||
"periods": [],
|
||||
"document_types": [],
|
||||
"all": []
|
||||
},
|
||||
"business_scope_raw": [],
|
||||
"business_scope_resolved": [
|
||||
"company_specific_accounting"
|
||||
],
|
||||
"company_grounding_applied": true,
|
||||
"scope_resolution_reason": [
|
||||
"settlement_claim_company_scope_recovery"
|
||||
],
|
||||
"company_scope_resolution_reason": [
|
||||
"settlement_claim_company_scope_recovery"
|
||||
],
|
||||
"raw_time_anchor": null,
|
||||
"raw_time_scope": null,
|
||||
"resolved_time_anchor": null,
|
||||
"resolved_primary_period": null,
|
||||
"effective_primary_period": null,
|
||||
"temporal_guard_input": null,
|
||||
"temporal_alignment_status": "conflicting",
|
||||
"temporal_resolution_source": "normalized_time_scope:missing",
|
||||
"temporal_guard_basis": "none",
|
||||
"temporal_guard_applied": false,
|
||||
"temporal_guard_outcome": "passed",
|
||||
"temporal_guard": {
|
||||
"raw_time_anchor": null,
|
||||
"raw_time_scope": null,
|
||||
"resolved_time_anchor": null,
|
||||
"resolved_primary_period": null,
|
||||
"effective_primary_period": null,
|
||||
"temporal_guard_input": null,
|
||||
"temporal_alignment_status": "conflicting",
|
||||
"temporal_resolution_source": "normalized_time_scope:missing",
|
||||
"temporal_guard_basis": "none",
|
||||
"temporal_guard_applied": false,
|
||||
"temporal_guard_outcome": "passed",
|
||||
"primary_period_window": null,
|
||||
"allowed_context_window": null,
|
||||
"controlled_temporal_expansion_enabled": false,
|
||||
"context_expansion_reasons_allowed": [
|
||||
"prehistory",
|
||||
"carryover",
|
||||
"post_period_closure",
|
||||
"long_running_contract_context"
|
||||
],
|
||||
"normalized_anchor_drift_detected": false,
|
||||
"reason_codes": [
|
||||
"missing_resolved_primary_period"
|
||||
]
|
||||
},
|
||||
"raw_numeric_tokens": [],
|
||||
"classified_numeric_tokens": [],
|
||||
"rejected_as_non_accounts": [],
|
||||
"resolved_account_anchors": [],
|
||||
"domain_polarity_guard": {
|
||||
"applied": false,
|
||||
"polarity": "not_applicable",
|
||||
"outcome": "not_applicable",
|
||||
"supplier_score": 0,
|
||||
"customer_score": 0,
|
||||
"account_scope": [],
|
||||
"raw_numeric_tokens": [],
|
||||
"classified_numeric_tokens": [],
|
||||
"rejected_as_non_accounts": [],
|
||||
"resolved_account_anchors": [],
|
||||
"rejected_problem_units": 0,
|
||||
"rejected_evidence": 0,
|
||||
"critical_contradiction": false,
|
||||
"reason_codes": []
|
||||
},
|
||||
"claim_anchor_audit": {
|
||||
"claim_type": "prove_settlement_closure_state",
|
||||
"settlement_role": "unknown",
|
||||
"settlement_role_resolution_reason": [
|
||||
"settlement_role_resolved_unknown"
|
||||
],
|
||||
"polarity_resolution_status": "unknown",
|
||||
"required_anchors": [
|
||||
"period",
|
||||
"account_scope",
|
||||
"counterparty_scope_or_contract",
|
||||
"closure_signal"
|
||||
],
|
||||
"resolved_anchors": {
|
||||
"period": [],
|
||||
"account_scope": [],
|
||||
"amounts": [],
|
||||
"contract": [],
|
||||
"document_numbers": [],
|
||||
"document_types": [],
|
||||
"counterparty_scope": [],
|
||||
"advance_signal": [],
|
||||
"closure_signal": [],
|
||||
"vat_signal": [],
|
||||
"chain_signal": [],
|
||||
"close_signal": [],
|
||||
"cost_scope": [],
|
||||
"rbp_signal": [],
|
||||
"writeoff_signal": [],
|
||||
"fixed_asset_signal": [],
|
||||
"amortization_signal": [],
|
||||
"expected_fa_set": [],
|
||||
"actual_fa_set": []
|
||||
},
|
||||
"missing_anchors": [
|
||||
"period",
|
||||
"account_scope",
|
||||
"counterparty_scope_or_contract",
|
||||
"closure_signal"
|
||||
],
|
||||
"claim_anchor_resolution_rate": 0,
|
||||
"primary_period": null,
|
||||
"allowed_context_window": null,
|
||||
"context_expansion_reasons_allowed": [
|
||||
"prehistory",
|
||||
"carryover",
|
||||
"post_period_closure",
|
||||
"long_running_contract_context"
|
||||
],
|
||||
"reason_codes": [
|
||||
"claim_missing_required_anchors",
|
||||
"claim_anchor_resolution_low",
|
||||
"unresolved_supplier_customer_polarity"
|
||||
]
|
||||
},
|
||||
"settlement_role": "unknown",
|
||||
"settlement_role_resolution_reason": [
|
||||
"settlement_role_resolved_unknown"
|
||||
],
|
||||
"polarity_resolution_status": "unknown",
|
||||
"targeted_evidence_acquisition": {
|
||||
"claim_type": "prove_settlement_closure_state",
|
||||
"required_checks": [
|
||||
"payment_document_found",
|
||||
"contract_matched",
|
||||
"settlement_object_matched",
|
||||
"closing_document_found",
|
||||
"register_closure_entry_found",
|
||||
"posting_link_found"
|
||||
],
|
||||
"check_status": {
|
||||
"payment_document_found": "not_found",
|
||||
"contract_matched": "not_found",
|
||||
"settlement_object_matched": "not_found",
|
||||
"closing_document_found": "not_found",
|
||||
"register_closure_entry_found": "not_found",
|
||||
"posting_link_found": "not_found"
|
||||
},
|
||||
"targeted_item_hits": 0,
|
||||
"targeted_evidence_hits": 0,
|
||||
"targeted_evidence_hit_rate": 0,
|
||||
"targeted_evidence_source_refs": [],
|
||||
"reason_codes": [
|
||||
"targeted_evidence_not_found",
|
||||
"targeted_evidence_hit_rate_low"
|
||||
]
|
||||
},
|
||||
"evidence_admissibility_gate": {
|
||||
"candidate_evidence_total": 0,
|
||||
"admissible_evidence_count": 0,
|
||||
"rejected_evidence_count": 0,
|
||||
"rejected_item_count": 0,
|
||||
"reject_breakdown": {
|
||||
"wrong_period": 0,
|
||||
"wrong_domain": 0,
|
||||
"wrong_account_scope": 0,
|
||||
"weak_source_mapping": 0,
|
||||
"zero_live_match": 0,
|
||||
"future_dated_or_out_of_window": 0
|
||||
},
|
||||
"category_breakdown": {
|
||||
"hard_evidence": 0,
|
||||
"supporting_signal": 0,
|
||||
"inadmissible_noise": 0
|
||||
},
|
||||
"reason_codes": [
|
||||
"no_admissible_evidence_for_grounded_answer"
|
||||
]
|
||||
},
|
||||
"eligibility_time_basis": "none",
|
||||
"grounded_answer_eligibility_guard": {
|
||||
"eligible": false,
|
||||
"temporal_passed": true,
|
||||
"eligibility_time_basis": "none",
|
||||
"business_scope_passed": true,
|
||||
"polarity_passed": true,
|
||||
"claim_anchors_passed": false,
|
||||
"claim_anchor_resolution_rate": 0,
|
||||
"missing_required_anchors": 4,
|
||||
"admissible_evidence_count": 0,
|
||||
"critical_contradiction": false,
|
||||
"outcome": "limited_or_insufficient_evidence",
|
||||
"grounding_mode": "limited_or_insufficient_evidence",
|
||||
"reason_codes": [
|
||||
"claim_anchor_coverage_insufficient",
|
||||
"admissible_evidence_count_zero",
|
||||
"targeted_evidence_hit_rate_zero"
|
||||
]
|
||||
},
|
||||
"problem_centric_answer_applied": false,
|
||||
"problem_units_used_count": 0,
|
||||
"problem_answer_mode": "stage1_policy_v11",
|
||||
"answer_structure_v11": {
|
||||
"schema_version": "answer_structure_v1_1",
|
||||
"answer_summary": "Нужны уточнения: без сужения фокуса надежный вывод невозможен.",
|
||||
"direct_answer": "Есть признаки проблемы, но без уточнений по периоду и объекту вывод ненадежен.",
|
||||
"mechanism_block": {
|
||||
"status": "unresolved",
|
||||
"mechanism_notes": [],
|
||||
"limitation_reason_codes": []
|
||||
},
|
||||
"evidence_block": {
|
||||
"evidence_ids": [],
|
||||
"source_refs": [],
|
||||
"mechanism_notes": [],
|
||||
"coverage_note": "coverage_partial_or_limited"
|
||||
},
|
||||
"uncertainty_block": {
|
||||
"open_uncertainties": [
|
||||
"R1",
|
||||
"missing_anchor:period",
|
||||
"missing_anchor:account",
|
||||
"missing_anchor:document_or_object",
|
||||
"missing_anchor:counterparty"
|
||||
],
|
||||
"limitations": [
|
||||
"Ни одно требование не получило подтвержденного покрытия.",
|
||||
"Нет explainable-сигналов why_included в результатах выборки.",
|
||||
"Недостаточно покрытия required anchors для claim-bound grounding.",
|
||||
"Недостаточно допустимого evidence для обоснованного ответа.",
|
||||
"Targeted evidence acquisition не дал допустимых попаданий по claim target path."
|
||||
]
|
||||
},
|
||||
"next_step_block": {
|
||||
"recommended_actions": [
|
||||
"Дайте недостающие якоря (период/счет/объект), иначе сильный factual вывод невозможен."
|
||||
],
|
||||
"clarification_questions": [
|
||||
"Уточните период проверки (например, июль 2020).",
|
||||
"Уточните счет или группу счетов (например, 19, 60, 62).",
|
||||
"Укажите документ/GUID/конкретный объект для трассировки.",
|
||||
"Укажите контрагента или группу контрагентов.",
|
||||
"Закройте уточнения для требований: R1."
|
||||
]
|
||||
}
|
||||
},
|
||||
"investigation_state_snapshot": {
|
||||
"schema_version": "investigation_state_v1",
|
||||
"session_id": "asst-2026-04-02_Address_GateBlock_Probe_WithMetrics-g001",
|
||||
"status": "active",
|
||||
"turn_index": 1,
|
||||
"updated_at": "2026-04-02T19:11:09.280Z",
|
||||
"question_id": "msg-wm3KZbU0j2",
|
||||
"question_scope_id": "s:привет как дела",
|
||||
"scope_origin": "underspecified",
|
||||
"focus": {
|
||||
"domain": null,
|
||||
"period": null,
|
||||
"primary_accounts": [],
|
||||
"active_query_subject": "привет как дела"
|
||||
},
|
||||
"narrowing_status": "unknown",
|
||||
"evidence_refs": [],
|
||||
"open_uncertainties": [
|
||||
"clarify:R1"
|
||||
],
|
||||
"last_answer_mode": "clarification_required",
|
||||
"followup_context": {
|
||||
"previous_question_id": null,
|
||||
"last_user_message": "привет как дела",
|
||||
"referenced_requirement_ids": [
|
||||
"R1"
|
||||
],
|
||||
"active_domain": null,
|
||||
"active_requirement_ids": [
|
||||
"R1"
|
||||
],
|
||||
"uncovered_requirement_ids": [
|
||||
"R1"
|
||||
],
|
||||
"last_problem_unit_id": null,
|
||||
"settlement_next_actions": [],
|
||||
"evidence_summary": [],
|
||||
"question_scope_id": "s:привет как дела",
|
||||
"scope_origin": "underspecified"
|
||||
},
|
||||
"query_mode_hint": "investigation_candidate"
|
||||
},
|
||||
"normalized": null
|
||||
},
|
||||
"error_code": null,
|
||||
"error_message": null
|
||||
}
|
||||
]
|
||||
+672
File diff suppressed because one or more lines are too long
@@ -0,0 +1,6 @@
|
||||
# Response Audit: 2026-04-02_Address_GateBlock_Probe_WithMetrics
|
||||
|
||||
| id | strict | route_health | reply_type | intent | limited_reason | question | assistant_first_line |
|
||||
|---|---|---|---|---|---|---|---|
|
||||
| G001 | False | blocked_clarification | clarification_required | None | None | привет как дела | Коротко: Наиболее вероятный механизм проблемы подтвержден частично и требует первичной проверки. Что сломано: |
|
||||
| G002 | True | ok_or_factual | factual | counterparty_activity_lifecycle | None | выведи список заказчиков за все время | Собран профиль активности заказчиков (bank-doc activity aggregate). |
|
||||
@@ -0,0 +1,90 @@
|
||||
{
|
||||
"run_id": "2026-04-02_Address_GateBlock_Probe_WithMetrics",
|
||||
"generated_at": "2026-04-02T22:11:14",
|
||||
"source_questions_file": "X:\\1C\\NDC_1C\\docs\\ADDRESS\\question_sets\\temp_gate_block_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": "semantic",
|
||||
"totals": {
|
||||
"questions_total": 2,
|
||||
"ok_200_count": 2,
|
||||
"semantic_pass_count": 1,
|
||||
"semantic_pass_rate": 0.5,
|
||||
"route_pass_count": 1,
|
||||
"route_pass_rate": 0.5,
|
||||
"strict_pass_count": 1,
|
||||
"strict_pass_rate": 0.5,
|
||||
"factual_count": 1,
|
||||
"partial_coverage_count": 0,
|
||||
"clarification_required_count": 1,
|
||||
"http_error_count": 0,
|
||||
"llm_decomposition_attempted_count": 1,
|
||||
"llm_decomposition_applied_count": 0,
|
||||
"llm_fallback_count": 0,
|
||||
"llm_fallback_rate": 0.0,
|
||||
"tool_gate_blocked_count": 0,
|
||||
"tool_gate_blocked_rate": 0.0,
|
||||
"avg_elapsed_ms": 8938
|
||||
},
|
||||
"distributions": {
|
||||
"reply_type": {
|
||||
"clarification_required": 1,
|
||||
"factual": 1
|
||||
},
|
||||
"actual_intent": {
|
||||
"None": 1,
|
||||
"counterparty_activity_lifecycle": 1
|
||||
},
|
||||
"actual_mode": {
|
||||
"None": 1,
|
||||
"address_query": 1
|
||||
},
|
||||
"mcp_call_status": {
|
||||
"None": 1,
|
||||
"matched_non_empty": 1
|
||||
},
|
||||
"limited_reason_category": {},
|
||||
"route_health": {
|
||||
"blocked_clarification": 1,
|
||||
"ok_or_factual": 1
|
||||
},
|
||||
"tool_gate_decision": {
|
||||
"run_address_lane": 1
|
||||
},
|
||||
"tool_gate_reason": {
|
||||
"address_mode_classifier_detected": 1
|
||||
}
|
||||
},
|
||||
"address_llm_predecompose_metrics": {
|
||||
"overall": {
|
||||
"llm_attempted": 1,
|
||||
"llm_applied": 0,
|
||||
"fallback_used": 0,
|
||||
"fallback_rate": 0.0,
|
||||
"tool_gate_blocked": 0,
|
||||
"gate_block_rate": 0.0
|
||||
},
|
||||
"by_intent": {
|
||||
"unknown": {
|
||||
"total": 1,
|
||||
"llm_attempted": 0,
|
||||
"llm_applied": 0,
|
||||
"fallback_used": 0,
|
||||
"tool_gate_blocked": 0,
|
||||
"fallback_rate": 0.0,
|
||||
"gate_block_rate": 0.0
|
||||
},
|
||||
"counterparty_activity_lifecycle": {
|
||||
"total": 1,
|
||||
"llm_attempted": 1,
|
||||
"llm_applied": 0,
|
||||
"fallback_used": 0,
|
||||
"tool_gate_blocked": 0,
|
||||
"fallback_rate": 0.0,
|
||||
"gate_block_rate": 0.0
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,33 @@
|
||||
# 2026-04-02_Address_GateBlock_Probe_WithMetrics_02
|
||||
|
||||
Generated at: 2026-04-02T22:12:56
|
||||
Questions file: X:\1C\NDC_1C\docs\ADDRESS\question_sets\temp_gate_block_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: semantic
|
||||
|
||||
## Totals
|
||||
- questions_total: 2
|
||||
- ok_200_count: 2
|
||||
- semantic_pass_count: 1
|
||||
- semantic_pass_rate: 0.5
|
||||
- route_pass_count: 1
|
||||
- route_pass_rate: 0.5
|
||||
- strict_pass_count: 1
|
||||
- strict_pass_rate: 0.5
|
||||
- factual_count: 1
|
||||
- partial_coverage_count: 0
|
||||
- clarification_required_count: 1
|
||||
- http_error_count: 0
|
||||
- llm_decomposition_attempted_count: 2
|
||||
- llm_decomposition_applied_count: 0
|
||||
- llm_fallback_count: 0
|
||||
- llm_fallback_rate: 0.0
|
||||
- tool_gate_blocked_count: 1
|
||||
- tool_gate_blocked_rate: 0.5
|
||||
- avg_elapsed_ms: 9280
|
||||
|
||||
## Files
|
||||
- run_summary.json
|
||||
- full_live_results.json
|
||||
- failures_only.json
|
||||
+429
@@ -0,0 +1,429 @@
|
||||
[
|
||||
{
|
||||
"index": 1,
|
||||
"id": "G001",
|
||||
"question": "привет как дела",
|
||||
"session": null,
|
||||
"session_id": "asst-2026-04-02_Address_GateBlock_Probe_WithMetrics_02-g001",
|
||||
"status_code": 200,
|
||||
"ok": true,
|
||||
"elapsed_ms": 13029,
|
||||
"reply_type": "clarification_required",
|
||||
"trace_id": "7eMBTZk2jJHzM1",
|
||||
"assistant_reply": "Коротко: Наиболее вероятный механизм проблемы подтвержден частично и требует первичной проверки. Что сломано:\n- Есть признаки проблемы, но без уточнений по периоду и объекту вывод ненадежен. Почему это похоже на проблему:\n- Сигнал проблемы есть, но механизм подтвержден не полностью. На чем это основано:\n- Опора частичная: часть требований покрыта не полностью.\n- Отдельно не подтверждено или покрыто частично: R1. Что проверить первым:\n- Уточните период проверки, чтобы подтвердить проблему без лишнего шума.\n- Проверьте связку документов и проводок по проблемному участку в указанном периоде.\n- Уточните период проверки (например, июль 2020). Ограничения:\n- Ни одно требование не получило подтвержденного покрытия.\n- Нет explainable-сигналов why_included в результатах выборки.\n- required anchors claim-bound grounding.\n- evidence.\n- Targeted evidence acquisition claim target path.",
|
||||
"assistant_reply_first_line": "Коротко: Наиболее вероятный механизм проблемы подтвержден частично и требует первичной проверки. Что сломано:",
|
||||
"expected_intent": null,
|
||||
"actual_intent": null,
|
||||
"intent_match": true,
|
||||
"expected_mode": "address_query",
|
||||
"actual_mode": null,
|
||||
"mode_match": false,
|
||||
"expected_reply_type": null,
|
||||
"reply_match": true,
|
||||
"semantic_pass": false,
|
||||
"route_pass": false,
|
||||
"route_health": "blocked_clarification",
|
||||
"strict_policy": "semantic",
|
||||
"strict_pass": false,
|
||||
"selected_recipe": null,
|
||||
"missing_required_filters": null,
|
||||
"match_failure_stage": null,
|
||||
"match_failure_reason": null,
|
||||
"rows_fetched": null,
|
||||
"rows_matched": null,
|
||||
"mcp_call_status": null,
|
||||
"limited_reason_category": null,
|
||||
"llm_decomposition_attempted": true,
|
||||
"llm_decomposition_applied": null,
|
||||
"llm_decomposition_reason": null,
|
||||
"llm_canonical_candidate_detected": null,
|
||||
"fallback_rule_hit": null,
|
||||
"tool_gate_decision": "skip_address_lane",
|
||||
"tool_gate_reason": "no_address_signal_after_l0",
|
||||
"predecompose_contract_intent": null,
|
||||
"predecompose_contract_aggregation_profile": null,
|
||||
"predecompose_contract_period_scope": null,
|
||||
"debug_payload": {
|
||||
"trace_id": "7eMBTZk2jJHzM1",
|
||||
"prompt_version": "address_query_runtime_v1",
|
||||
"schema_version": "v1",
|
||||
"fallback_type": "clarification",
|
||||
"route_summary": null,
|
||||
"fragments": [],
|
||||
"requirements_extracted": [
|
||||
{
|
||||
"requirement_id": "R1",
|
||||
"source_fragment_id": null,
|
||||
"requirement_text": "привет как дела",
|
||||
"subject_tokens": [],
|
||||
"status": "clarification_needed",
|
||||
"route": null
|
||||
}
|
||||
],
|
||||
"coverage_report": {
|
||||
"requirements_total": 1,
|
||||
"requirements_covered": 0,
|
||||
"requirements_uncovered": [],
|
||||
"requirements_partially_covered": [],
|
||||
"clarification_needed_for": [
|
||||
"R1"
|
||||
],
|
||||
"out_of_scope_requirements": []
|
||||
},
|
||||
"routes": [],
|
||||
"retrieval_status": [],
|
||||
"retrieval_results": [],
|
||||
"answer_grounding_check": {
|
||||
"status": "no_grounded_answer",
|
||||
"route_subject_match": true,
|
||||
"missing_requirements": [
|
||||
"R1"
|
||||
],
|
||||
"reasons": [
|
||||
"Ни одно требование не получило подтвержденного покрытия.",
|
||||
"Нет explainable-сигналов why_included в результатах выборки.",
|
||||
"Недостаточно покрытия required anchors для claim-bound grounding.",
|
||||
"Недостаточно допустимого evidence для обоснованного ответа.",
|
||||
"Targeted evidence acquisition не дал допустимых попаданий по claim target path."
|
||||
],
|
||||
"why_included_summary": [],
|
||||
"selection_reason_summary": []
|
||||
},
|
||||
"dropped_intent_segments": [],
|
||||
"question_type_class": "why_breaks",
|
||||
"company_anchors": {
|
||||
"contract_numbers": [],
|
||||
"document_numbers": [],
|
||||
"dates": [],
|
||||
"amounts": [],
|
||||
"accounts": [],
|
||||
"periods": [],
|
||||
"document_types": [],
|
||||
"all": []
|
||||
},
|
||||
"business_scope_raw": [],
|
||||
"business_scope_resolved": [
|
||||
"company_specific_accounting"
|
||||
],
|
||||
"company_grounding_applied": true,
|
||||
"scope_resolution_reason": [
|
||||
"settlement_claim_company_scope_recovery"
|
||||
],
|
||||
"company_scope_resolution_reason": [
|
||||
"settlement_claim_company_scope_recovery"
|
||||
],
|
||||
"raw_time_anchor": null,
|
||||
"raw_time_scope": null,
|
||||
"resolved_time_anchor": null,
|
||||
"resolved_primary_period": null,
|
||||
"effective_primary_period": null,
|
||||
"temporal_guard_input": null,
|
||||
"temporal_alignment_status": "conflicting",
|
||||
"temporal_resolution_source": "normalized_time_scope:missing",
|
||||
"temporal_guard_basis": "none",
|
||||
"temporal_guard_applied": false,
|
||||
"temporal_guard_outcome": "passed",
|
||||
"temporal_guard": {
|
||||
"raw_time_anchor": null,
|
||||
"raw_time_scope": null,
|
||||
"resolved_time_anchor": null,
|
||||
"resolved_primary_period": null,
|
||||
"effective_primary_period": null,
|
||||
"temporal_guard_input": null,
|
||||
"temporal_alignment_status": "conflicting",
|
||||
"temporal_resolution_source": "normalized_time_scope:missing",
|
||||
"temporal_guard_basis": "none",
|
||||
"temporal_guard_applied": false,
|
||||
"temporal_guard_outcome": "passed",
|
||||
"primary_period_window": null,
|
||||
"allowed_context_window": null,
|
||||
"controlled_temporal_expansion_enabled": false,
|
||||
"context_expansion_reasons_allowed": [
|
||||
"prehistory",
|
||||
"carryover",
|
||||
"post_period_closure",
|
||||
"long_running_contract_context"
|
||||
],
|
||||
"normalized_anchor_drift_detected": false,
|
||||
"reason_codes": [
|
||||
"missing_resolved_primary_period"
|
||||
]
|
||||
},
|
||||
"raw_numeric_tokens": [],
|
||||
"classified_numeric_tokens": [],
|
||||
"rejected_as_non_accounts": [],
|
||||
"resolved_account_anchors": [],
|
||||
"domain_polarity_guard": {
|
||||
"applied": false,
|
||||
"polarity": "not_applicable",
|
||||
"outcome": "not_applicable",
|
||||
"supplier_score": 0,
|
||||
"customer_score": 0,
|
||||
"account_scope": [],
|
||||
"raw_numeric_tokens": [],
|
||||
"classified_numeric_tokens": [],
|
||||
"rejected_as_non_accounts": [],
|
||||
"resolved_account_anchors": [],
|
||||
"rejected_problem_units": 0,
|
||||
"rejected_evidence": 0,
|
||||
"critical_contradiction": false,
|
||||
"reason_codes": []
|
||||
},
|
||||
"claim_anchor_audit": {
|
||||
"claim_type": "prove_settlement_closure_state",
|
||||
"settlement_role": "unknown",
|
||||
"settlement_role_resolution_reason": [
|
||||
"settlement_role_resolved_unknown"
|
||||
],
|
||||
"polarity_resolution_status": "unknown",
|
||||
"required_anchors": [
|
||||
"period",
|
||||
"account_scope",
|
||||
"counterparty_scope_or_contract",
|
||||
"closure_signal"
|
||||
],
|
||||
"resolved_anchors": {
|
||||
"period": [],
|
||||
"account_scope": [],
|
||||
"amounts": [],
|
||||
"contract": [],
|
||||
"document_numbers": [],
|
||||
"document_types": [],
|
||||
"counterparty_scope": [],
|
||||
"advance_signal": [],
|
||||
"closure_signal": [],
|
||||
"vat_signal": [],
|
||||
"chain_signal": [],
|
||||
"close_signal": [],
|
||||
"cost_scope": [],
|
||||
"rbp_signal": [],
|
||||
"writeoff_signal": [],
|
||||
"fixed_asset_signal": [],
|
||||
"amortization_signal": [],
|
||||
"expected_fa_set": [],
|
||||
"actual_fa_set": []
|
||||
},
|
||||
"missing_anchors": [
|
||||
"period",
|
||||
"account_scope",
|
||||
"counterparty_scope_or_contract",
|
||||
"closure_signal"
|
||||
],
|
||||
"claim_anchor_resolution_rate": 0,
|
||||
"primary_period": null,
|
||||
"allowed_context_window": null,
|
||||
"context_expansion_reasons_allowed": [
|
||||
"prehistory",
|
||||
"carryover",
|
||||
"post_period_closure",
|
||||
"long_running_contract_context"
|
||||
],
|
||||
"reason_codes": [
|
||||
"claim_missing_required_anchors",
|
||||
"claim_anchor_resolution_low",
|
||||
"unresolved_supplier_customer_polarity"
|
||||
]
|
||||
},
|
||||
"settlement_role": "unknown",
|
||||
"settlement_role_resolution_reason": [
|
||||
"settlement_role_resolved_unknown"
|
||||
],
|
||||
"polarity_resolution_status": "unknown",
|
||||
"targeted_evidence_acquisition": {
|
||||
"claim_type": "prove_settlement_closure_state",
|
||||
"required_checks": [
|
||||
"payment_document_found",
|
||||
"contract_matched",
|
||||
"settlement_object_matched",
|
||||
"closing_document_found",
|
||||
"register_closure_entry_found",
|
||||
"posting_link_found"
|
||||
],
|
||||
"check_status": {
|
||||
"payment_document_found": "not_found",
|
||||
"contract_matched": "not_found",
|
||||
"settlement_object_matched": "not_found",
|
||||
"closing_document_found": "not_found",
|
||||
"register_closure_entry_found": "not_found",
|
||||
"posting_link_found": "not_found"
|
||||
},
|
||||
"targeted_item_hits": 0,
|
||||
"targeted_evidence_hits": 0,
|
||||
"targeted_evidence_hit_rate": 0,
|
||||
"targeted_evidence_source_refs": [],
|
||||
"reason_codes": [
|
||||
"targeted_evidence_not_found",
|
||||
"targeted_evidence_hit_rate_low"
|
||||
]
|
||||
},
|
||||
"evidence_admissibility_gate": {
|
||||
"candidate_evidence_total": 0,
|
||||
"admissible_evidence_count": 0,
|
||||
"rejected_evidence_count": 0,
|
||||
"rejected_item_count": 0,
|
||||
"reject_breakdown": {
|
||||
"wrong_period": 0,
|
||||
"wrong_domain": 0,
|
||||
"wrong_account_scope": 0,
|
||||
"weak_source_mapping": 0,
|
||||
"zero_live_match": 0,
|
||||
"future_dated_or_out_of_window": 0
|
||||
},
|
||||
"category_breakdown": {
|
||||
"hard_evidence": 0,
|
||||
"supporting_signal": 0,
|
||||
"inadmissible_noise": 0
|
||||
},
|
||||
"reason_codes": [
|
||||
"no_admissible_evidence_for_grounded_answer"
|
||||
]
|
||||
},
|
||||
"eligibility_time_basis": "none",
|
||||
"grounded_answer_eligibility_guard": {
|
||||
"eligible": false,
|
||||
"temporal_passed": true,
|
||||
"eligibility_time_basis": "none",
|
||||
"business_scope_passed": true,
|
||||
"polarity_passed": true,
|
||||
"claim_anchors_passed": false,
|
||||
"claim_anchor_resolution_rate": 0,
|
||||
"missing_required_anchors": 4,
|
||||
"admissible_evidence_count": 0,
|
||||
"critical_contradiction": false,
|
||||
"outcome": "limited_or_insufficient_evidence",
|
||||
"grounding_mode": "limited_or_insufficient_evidence",
|
||||
"reason_codes": [
|
||||
"claim_anchor_coverage_insufficient",
|
||||
"admissible_evidence_count_zero",
|
||||
"targeted_evidence_hit_rate_zero"
|
||||
]
|
||||
},
|
||||
"problem_centric_answer_applied": false,
|
||||
"problem_units_used_count": 0,
|
||||
"problem_answer_mode": "stage1_policy_v11",
|
||||
"address_llm_predecompose_attempted": true,
|
||||
"address_llm_predecompose_applied": false,
|
||||
"address_llm_predecompose_reason": "no_usable_fragment",
|
||||
"address_llm_predecompose_provider": "local",
|
||||
"address_fallback_rule_hit": null,
|
||||
"address_tool_gate_decision": "skip_address_lane",
|
||||
"address_tool_gate_reason": "no_address_signal_after_l0",
|
||||
"address_llm_predecompose_contract": {
|
||||
"schema_version": "address_llm_predecompose_contract_v1",
|
||||
"source_message": "привет как дела",
|
||||
"canonical_message": "привет как дела",
|
||||
"mode": "unsupported",
|
||||
"mode_confidence": "low",
|
||||
"query_shape": "UNKNOWN",
|
||||
"query_shape_confidence": "low",
|
||||
"intent": "unknown",
|
||||
"intent_confidence": "low",
|
||||
"entities": {
|
||||
"account": null,
|
||||
"counterparty": null,
|
||||
"contract": null,
|
||||
"document_type": null,
|
||||
"document_ref": null,
|
||||
"organization": null
|
||||
},
|
||||
"period": {
|
||||
"scope": "unspecified",
|
||||
"period_from": null,
|
||||
"period_to": null,
|
||||
"as_of_date": null,
|
||||
"has_explicit_period": false
|
||||
},
|
||||
"aggregation_profile": "unknown"
|
||||
},
|
||||
"answer_structure_v11": {
|
||||
"schema_version": "answer_structure_v1_1",
|
||||
"answer_summary": "Нужны уточнения: без сужения фокуса надежный вывод невозможен.",
|
||||
"direct_answer": "Есть признаки проблемы, но без уточнений по периоду и объекту вывод ненадежен.",
|
||||
"mechanism_block": {
|
||||
"status": "unresolved",
|
||||
"mechanism_notes": [],
|
||||
"limitation_reason_codes": []
|
||||
},
|
||||
"evidence_block": {
|
||||
"evidence_ids": [],
|
||||
"source_refs": [],
|
||||
"mechanism_notes": [],
|
||||
"coverage_note": "coverage_partial_or_limited"
|
||||
},
|
||||
"uncertainty_block": {
|
||||
"open_uncertainties": [
|
||||
"R1",
|
||||
"missing_anchor:period",
|
||||
"missing_anchor:account",
|
||||
"missing_anchor:document_or_object",
|
||||
"missing_anchor:counterparty"
|
||||
],
|
||||
"limitations": [
|
||||
"Ни одно требование не получило подтвержденного покрытия.",
|
||||
"Нет explainable-сигналов why_included в результатах выборки.",
|
||||
"Недостаточно покрытия required anchors для claim-bound grounding.",
|
||||
"Недостаточно допустимого evidence для обоснованного ответа.",
|
||||
"Targeted evidence acquisition не дал допустимых попаданий по claim target path."
|
||||
]
|
||||
},
|
||||
"next_step_block": {
|
||||
"recommended_actions": [
|
||||
"Дайте недостающие якоря (период/счет/объект), иначе сильный factual вывод невозможен."
|
||||
],
|
||||
"clarification_questions": [
|
||||
"Уточните период проверки (например, июль 2020).",
|
||||
"Уточните счет или группу счетов (например, 19, 60, 62).",
|
||||
"Укажите документ/GUID/конкретный объект для трассировки.",
|
||||
"Укажите контрагента или группу контрагентов.",
|
||||
"Закройте уточнения для требований: R1."
|
||||
]
|
||||
}
|
||||
},
|
||||
"investigation_state_snapshot": {
|
||||
"schema_version": "investigation_state_v1",
|
||||
"session_id": "asst-2026-04-02_Address_GateBlock_Probe_WithMetrics_02-g001",
|
||||
"status": "active",
|
||||
"turn_index": 1,
|
||||
"updated_at": "2026-04-02T19:12:50.522Z",
|
||||
"question_id": "msg-v7LY-ucCiX",
|
||||
"question_scope_id": "s:привет как дела",
|
||||
"scope_origin": "underspecified",
|
||||
"focus": {
|
||||
"domain": null,
|
||||
"period": null,
|
||||
"primary_accounts": [],
|
||||
"active_query_subject": "привет как дела"
|
||||
},
|
||||
"narrowing_status": "unknown",
|
||||
"evidence_refs": [],
|
||||
"open_uncertainties": [
|
||||
"clarify:R1"
|
||||
],
|
||||
"last_answer_mode": "clarification_required",
|
||||
"followup_context": {
|
||||
"previous_question_id": null,
|
||||
"last_user_message": "привет как дела",
|
||||
"referenced_requirement_ids": [
|
||||
"R1"
|
||||
],
|
||||
"active_domain": null,
|
||||
"active_requirement_ids": [
|
||||
"R1"
|
||||
],
|
||||
"uncovered_requirement_ids": [
|
||||
"R1"
|
||||
],
|
||||
"last_problem_unit_id": null,
|
||||
"settlement_next_actions": [],
|
||||
"evidence_summary": [],
|
||||
"question_scope_id": "s:привет как дела",
|
||||
"scope_origin": "underspecified"
|
||||
},
|
||||
"query_mode_hint": "investigation_candidate"
|
||||
},
|
||||
"normalized": null
|
||||
},
|
||||
"error_code": null,
|
||||
"error_message": null
|
||||
}
|
||||
]
|
||||
+708
File diff suppressed because one or more lines are too long
@@ -0,0 +1,6 @@
|
||||
# Response Audit: 2026-04-02_Address_GateBlock_Probe_WithMetrics_02
|
||||
|
||||
| id | strict | route_health | reply_type | intent | limited_reason | question | assistant_first_line |
|
||||
|---|---|---|---|---|---|---|---|
|
||||
| G001 | False | blocked_clarification | clarification_required | None | None | привет как дела | Коротко: Наиболее вероятный механизм проблемы подтвержден частично и требует первичной проверки. Что сломано: |
|
||||
| G002 | True | ok_or_factual | factual | counterparty_activity_lifecycle | None | выведи список заказчиков за все время | Собран профиль активности заказчиков (bank-doc activity aggregate). |
|
||||
@@ -0,0 +1,92 @@
|
||||
{
|
||||
"run_id": "2026-04-02_Address_GateBlock_Probe_WithMetrics_02",
|
||||
"generated_at": "2026-04-02T22:12:56",
|
||||
"source_questions_file": "X:\\1C\\NDC_1C\\docs\\ADDRESS\\question_sets\\temp_gate_block_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": "semantic",
|
||||
"totals": {
|
||||
"questions_total": 2,
|
||||
"ok_200_count": 2,
|
||||
"semantic_pass_count": 1,
|
||||
"semantic_pass_rate": 0.5,
|
||||
"route_pass_count": 1,
|
||||
"route_pass_rate": 0.5,
|
||||
"strict_pass_count": 1,
|
||||
"strict_pass_rate": 0.5,
|
||||
"factual_count": 1,
|
||||
"partial_coverage_count": 0,
|
||||
"clarification_required_count": 1,
|
||||
"http_error_count": 0,
|
||||
"llm_decomposition_attempted_count": 2,
|
||||
"llm_decomposition_applied_count": 0,
|
||||
"llm_fallback_count": 0,
|
||||
"llm_fallback_rate": 0.0,
|
||||
"tool_gate_blocked_count": 1,
|
||||
"tool_gate_blocked_rate": 0.5,
|
||||
"avg_elapsed_ms": 9280
|
||||
},
|
||||
"distributions": {
|
||||
"reply_type": {
|
||||
"clarification_required": 1,
|
||||
"factual": 1
|
||||
},
|
||||
"actual_intent": {
|
||||
"None": 1,
|
||||
"counterparty_activity_lifecycle": 1
|
||||
},
|
||||
"actual_mode": {
|
||||
"None": 1,
|
||||
"address_query": 1
|
||||
},
|
||||
"mcp_call_status": {
|
||||
"None": 1,
|
||||
"matched_non_empty": 1
|
||||
},
|
||||
"limited_reason_category": {},
|
||||
"route_health": {
|
||||
"blocked_clarification": 1,
|
||||
"ok_or_factual": 1
|
||||
},
|
||||
"tool_gate_decision": {
|
||||
"skip_address_lane": 1,
|
||||
"run_address_lane": 1
|
||||
},
|
||||
"tool_gate_reason": {
|
||||
"no_address_signal_after_l0": 1,
|
||||
"address_mode_classifier_detected": 1
|
||||
}
|
||||
},
|
||||
"address_llm_predecompose_metrics": {
|
||||
"overall": {
|
||||
"llm_attempted": 2,
|
||||
"llm_applied": 0,
|
||||
"fallback_used": 0,
|
||||
"fallback_rate": 0.0,
|
||||
"tool_gate_blocked": 1,
|
||||
"gate_block_rate": 0.5
|
||||
},
|
||||
"by_intent": {
|
||||
"unknown": {
|
||||
"total": 1,
|
||||
"llm_attempted": 1,
|
||||
"llm_applied": 0,
|
||||
"fallback_used": 0,
|
||||
"tool_gate_blocked": 1,
|
||||
"fallback_rate": 0.0,
|
||||
"gate_block_rate": 1.0
|
||||
},
|
||||
"counterparty_activity_lifecycle": {
|
||||
"total": 1,
|
||||
"llm_attempted": 1,
|
||||
"llm_applied": 0,
|
||||
"fallback_used": 0,
|
||||
"tool_gate_blocked": 0,
|
||||
"fallback_rate": 0.0,
|
||||
"gate_block_rate": 0.0
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,28 @@
|
||||
# 2026-04-02_Address_General5_Live_Check_AfterFix_01
|
||||
|
||||
Generated at: 2026-04-02T19:27:58
|
||||
Questions file: X:\1C\NDC_1C\docs\ADDRESS\question_sets\temp_general5_live_check_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: route
|
||||
|
||||
## Totals
|
||||
- questions_total: 5
|
||||
- ok_200_count: 5
|
||||
- semantic_pass_count: 5
|
||||
- semantic_pass_rate: 1.0
|
||||
- route_pass_count: 0
|
||||
- route_pass_rate: 0.0
|
||||
- strict_pass_count: 0
|
||||
- strict_pass_rate: 0.0
|
||||
- factual_count: 0
|
||||
- partial_coverage_count: 5
|
||||
- clarification_required_count: 0
|
||||
- http_error_count: 0
|
||||
- llm_decomposition_applied_count: 0
|
||||
- avg_elapsed_ms: 2632
|
||||
|
||||
## Files
|
||||
- run_summary.json
|
||||
- full_live_results.json
|
||||
- failures_only.json
|
||||
+673
@@ -0,0 +1,673 @@
|
||||
[
|
||||
{
|
||||
"index": 1,
|
||||
"id": "Q1",
|
||||
"question": "За какие годы в базе есть данные?",
|
||||
"session": null,
|
||||
"session_id": "asst-2026-04-02_Address_General5_Live_Check_AfterFix_01-q1",
|
||||
"status_code": 200,
|
||||
"ok": true,
|
||||
"elapsed_ms": 962,
|
||||
"reply_type": "partial_coverage",
|
||||
"trace_id": "address-eW6Yb7i_tq",
|
||||
"assistant_reply": "Не удалось выполнить адресный live-запрос в V1.\nПричина: live MCP вызов завершился ошибкой.\nЧто нужно уточнить: {ВнешняяОбработка.MCPToolkit.Форма.Форма.Форма(1989)}: Ошибка при вызове метода контекста (Выполнить): {(10, 24)}: Синтаксическая ошибка\nДвижения.Период <= <<?>>ТЕКУЩАЯДАТА().",
|
||||
"assistant_reply_first_line": "Не удалось выполнить адресный live-запрос в V1.",
|
||||
"expected_intent": "period_coverage_profile",
|
||||
"actual_intent": "period_coverage_profile",
|
||||
"intent_match": true,
|
||||
"expected_mode": "address_query",
|
||||
"actual_mode": "address_query",
|
||||
"mode_match": true,
|
||||
"expected_reply_type": null,
|
||||
"reply_match": true,
|
||||
"semantic_pass": true,
|
||||
"route_pass": false,
|
||||
"route_health": "blocked_execution_error",
|
||||
"strict_policy": "route",
|
||||
"strict_pass": false,
|
||||
"selected_recipe": "address_period_coverage_profile_v1",
|
||||
"missing_required_filters": [],
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"rows_fetched": 0,
|
||||
"rows_matched": 0,
|
||||
"mcp_call_status": "error",
|
||||
"limited_reason_category": "execution_error",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_reason": "not_address_like",
|
||||
"fallback_rule_hit": null,
|
||||
"debug_payload": {
|
||||
"trace_id": "address-eW6Yb7i_tq",
|
||||
"prompt_version": "address_query_runtime_v1",
|
||||
"schema_version": "address_query_runtime_v1",
|
||||
"fallback_type": "partial",
|
||||
"route_summary": null,
|
||||
"fragments": [],
|
||||
"requirements_extracted": [],
|
||||
"coverage_report": {
|
||||
"requirements_total": 0,
|
||||
"requirements_covered": 0,
|
||||
"requirements_uncovered": [],
|
||||
"requirements_partially_covered": [],
|
||||
"clarification_needed_for": [],
|
||||
"out_of_scope_requirements": []
|
||||
},
|
||||
"routes": [],
|
||||
"retrieval_status": [],
|
||||
"retrieval_results": [],
|
||||
"answer_grounding_check": {
|
||||
"status": "partial",
|
||||
"route_subject_match": true,
|
||||
"missing_requirements": [],
|
||||
"reasons": [
|
||||
"management_profile_signal_detected",
|
||||
"shape_not_detected",
|
||||
"period_coverage_profile_signal_detected",
|
||||
"{ВнешняяОбработка.MCPToolkit.Форма.Форма.Форма(1989)}: Ошибка при вызове метода контекста (Выполнить): {(10, 24)}: Синтаксическая ошибка\nДвижения.Период <= <<?>>ТЕКУЩАЯДАТА()"
|
||||
],
|
||||
"why_included_summary": [],
|
||||
"selection_reason_summary": []
|
||||
},
|
||||
"dropped_intent_segments": [],
|
||||
"detected_mode": "address_query",
|
||||
"detected_mode_confidence": "medium",
|
||||
"query_shape": "UNKNOWN",
|
||||
"query_shape_confidence": "low",
|
||||
"detected_intent": "period_coverage_profile",
|
||||
"detected_intent_confidence": "high",
|
||||
"extracted_filters": {
|
||||
"sort": "period_desc"
|
||||
},
|
||||
"missing_required_filters": [],
|
||||
"selected_recipe": "address_period_coverage_profile_v1",
|
||||
"mcp_call_status_legacy": "error",
|
||||
"account_scope_mode": "preferred",
|
||||
"account_scope_fallback_applied": false,
|
||||
"anchor_type": "unknown",
|
||||
"anchor_value_raw": null,
|
||||
"anchor_value_resolved": null,
|
||||
"resolver_confidence": "low",
|
||||
"ambiguity_count": 0,
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"mcp_call_status": "error",
|
||||
"rows_fetched": 0,
|
||||
"raw_rows_received": 0,
|
||||
"rows_after_account_scope": 0,
|
||||
"rows_after_recipe_filter": 0,
|
||||
"rows_materialized": 0,
|
||||
"rows_matched": 0,
|
||||
"raw_row_keys_sample": [],
|
||||
"materialization_drop_reason": "none",
|
||||
"account_token_raw": null,
|
||||
"account_token_normalized": null,
|
||||
"account_scope_fields_checked": [
|
||||
"account_dt",
|
||||
"account_kt",
|
||||
"registrator",
|
||||
"analytics"
|
||||
],
|
||||
"account_scope_match_strategy": "account_code_regex_plus_alias_map_v1",
|
||||
"account_scope_drop_reason": "not_applicable",
|
||||
"runtime_readiness": "UNKNOWN",
|
||||
"limited_reason_category": "execution_error",
|
||||
"response_type": "LIMITED_WITH_REASON",
|
||||
"execution_lane": "address_query",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_attempted": false,
|
||||
"llm_provider_used": "local",
|
||||
"llm_decomposition_trace_id": null,
|
||||
"llm_decomposition_effective_message": "За какие годы в базе есть данные?",
|
||||
"llm_decomposition_reason": "not_address_like",
|
||||
"fallback_rule_hit": null,
|
||||
"sanitized_user_message": "за какие годы в базе есть данные?",
|
||||
"tool_gate_decision": "run_address_lane",
|
||||
"tool_gate_reason": "address_mode_classifier_detected",
|
||||
"answer_structure_v11": null,
|
||||
"investigation_state_snapshot": null,
|
||||
"normalized": null,
|
||||
"normalizer_output": null
|
||||
},
|
||||
"error_code": null,
|
||||
"error_message": null
|
||||
},
|
||||
{
|
||||
"index": 2,
|
||||
"id": "Q2",
|
||||
"question": "Какой год самый активный по количеству документов?",
|
||||
"session": null,
|
||||
"session_id": "asst-2026-04-02_Address_General5_Live_Check_AfterFix_01-q2",
|
||||
"status_code": 200,
|
||||
"ok": true,
|
||||
"elapsed_ms": 5072,
|
||||
"reply_type": "partial_coverage",
|
||||
"trace_id": "address-BKVNDThPUd",
|
||||
"assistant_reply": "Не удалось выполнить адресный live-запрос в V1.\nПричина: live MCP вызов завершился ошибкой.\nЧто нужно уточнить: {ВнешняяОбработка.MCPToolkit.Форма.Форма.Форма(1989)}: Ошибка при вызове метода контекста (Выполнить): {(10, 24)}: Синтаксическая ошибка\nДвижения.Период <= <<?>>ТЕКУЩАЯДАТА().",
|
||||
"assistant_reply_first_line": "Не удалось выполнить адресный live-запрос в V1.",
|
||||
"expected_intent": "period_coverage_profile",
|
||||
"actual_intent": "period_coverage_profile",
|
||||
"intent_match": true,
|
||||
"expected_mode": "address_query",
|
||||
"actual_mode": "address_query",
|
||||
"mode_match": true,
|
||||
"expected_reply_type": null,
|
||||
"reply_match": true,
|
||||
"semantic_pass": true,
|
||||
"route_pass": false,
|
||||
"route_health": "blocked_execution_error",
|
||||
"strict_policy": "route",
|
||||
"strict_pass": false,
|
||||
"selected_recipe": "address_period_coverage_profile_v1",
|
||||
"missing_required_filters": [],
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"rows_fetched": 0,
|
||||
"rows_matched": 0,
|
||||
"mcp_call_status": "error",
|
||||
"limited_reason_category": "execution_error",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_reason": "normalized_fragment_rejected_intent_conflict",
|
||||
"fallback_rule_hit": null,
|
||||
"debug_payload": {
|
||||
"trace_id": "address-BKVNDThPUd",
|
||||
"prompt_version": "address_query_runtime_v1",
|
||||
"schema_version": "address_query_runtime_v1",
|
||||
"fallback_type": "partial",
|
||||
"route_summary": null,
|
||||
"fragments": [],
|
||||
"requirements_extracted": [],
|
||||
"coverage_report": {
|
||||
"requirements_total": 0,
|
||||
"requirements_covered": 0,
|
||||
"requirements_uncovered": [],
|
||||
"requirements_partially_covered": [],
|
||||
"clarification_needed_for": [],
|
||||
"out_of_scope_requirements": []
|
||||
},
|
||||
"routes": [],
|
||||
"retrieval_status": [],
|
||||
"retrieval_results": [],
|
||||
"answer_grounding_check": {
|
||||
"status": "partial",
|
||||
"route_subject_match": true,
|
||||
"missing_requirements": [],
|
||||
"reasons": [
|
||||
"management_profile_signal_detected",
|
||||
"document_list_signal_detected",
|
||||
"period_coverage_profile_signal_detected",
|
||||
"{ВнешняяОбработка.MCPToolkit.Форма.Форма.Форма(1989)}: Ошибка при вызове метода контекста (Выполнить): {(10, 24)}: Синтаксическая ошибка\nДвижения.Период <= <<?>>ТЕКУЩАЯДАТА()"
|
||||
],
|
||||
"why_included_summary": [],
|
||||
"selection_reason_summary": []
|
||||
},
|
||||
"dropped_intent_segments": [],
|
||||
"detected_mode": "address_query",
|
||||
"detected_mode_confidence": "medium",
|
||||
"query_shape": "DOCUMENT_LIST",
|
||||
"query_shape_confidence": "medium",
|
||||
"detected_intent": "period_coverage_profile",
|
||||
"detected_intent_confidence": "high",
|
||||
"extracted_filters": {
|
||||
"sort": "period_desc"
|
||||
},
|
||||
"missing_required_filters": [],
|
||||
"selected_recipe": "address_period_coverage_profile_v1",
|
||||
"mcp_call_status_legacy": "error",
|
||||
"account_scope_mode": "preferred",
|
||||
"account_scope_fallback_applied": false,
|
||||
"anchor_type": "unknown",
|
||||
"anchor_value_raw": null,
|
||||
"anchor_value_resolved": null,
|
||||
"resolver_confidence": "low",
|
||||
"ambiguity_count": 0,
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"mcp_call_status": "error",
|
||||
"rows_fetched": 0,
|
||||
"raw_rows_received": 0,
|
||||
"rows_after_account_scope": 0,
|
||||
"rows_after_recipe_filter": 0,
|
||||
"rows_materialized": 0,
|
||||
"rows_matched": 0,
|
||||
"raw_row_keys_sample": [],
|
||||
"materialization_drop_reason": "none",
|
||||
"account_token_raw": null,
|
||||
"account_token_normalized": null,
|
||||
"account_scope_fields_checked": [
|
||||
"account_dt",
|
||||
"account_kt",
|
||||
"registrator",
|
||||
"analytics"
|
||||
],
|
||||
"account_scope_match_strategy": "account_code_regex_plus_alias_map_v1",
|
||||
"account_scope_drop_reason": "not_applicable",
|
||||
"runtime_readiness": "UNKNOWN",
|
||||
"limited_reason_category": "execution_error",
|
||||
"response_type": "LIMITED_WITH_REASON",
|
||||
"execution_lane": "address_query",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_attempted": true,
|
||||
"llm_provider_used": "local",
|
||||
"llm_decomposition_trace_id": "bgFD0eUh97bbae",
|
||||
"llm_decomposition_effective_message": "Какой год самый активный по количеству документов?",
|
||||
"llm_decomposition_reason": "normalized_fragment_rejected_intent_conflict",
|
||||
"fallback_rule_hit": null,
|
||||
"sanitized_user_message": "какой год самый активный по количеству документов?",
|
||||
"tool_gate_decision": "run_address_lane",
|
||||
"tool_gate_reason": "address_mode_classifier_detected",
|
||||
"answer_structure_v11": null,
|
||||
"investigation_state_snapshot": null,
|
||||
"normalized": null,
|
||||
"normalizer_output": {
|
||||
"trace_id": "bgFD0eUh97bbae",
|
||||
"prompt_version": "normalizer_v2_0_2",
|
||||
"applied": false,
|
||||
"effective_message": "Какой год самый активный по количеству документов?"
|
||||
}
|
||||
},
|
||||
"error_code": null,
|
||||
"error_message": null
|
||||
},
|
||||
{
|
||||
"index": 3,
|
||||
"id": "Q3",
|
||||
"question": "Какой месяц самый активный по количеству операций?",
|
||||
"session": null,
|
||||
"session_id": "asst-2026-04-02_Address_General5_Live_Check_AfterFix_01-q3",
|
||||
"status_code": 200,
|
||||
"ok": true,
|
||||
"elapsed_ms": 1066,
|
||||
"reply_type": "partial_coverage",
|
||||
"trace_id": "address-lxBpVpL9YV",
|
||||
"assistant_reply": "Не удалось выполнить адресный live-запрос в V1.\nПричина: live MCP вызов завершился ошибкой.\nЧто нужно уточнить: {ВнешняяОбработка.MCPToolkit.Форма.Форма.Форма(1989)}: Ошибка при вызове метода контекста (Выполнить): {(10, 24)}: Синтаксическая ошибка\nДвижения.Период <= <<?>>ТЕКУЩАЯДАТА().",
|
||||
"assistant_reply_first_line": "Не удалось выполнить адресный live-запрос в V1.",
|
||||
"expected_intent": "period_coverage_profile",
|
||||
"actual_intent": "period_coverage_profile",
|
||||
"intent_match": true,
|
||||
"expected_mode": "address_query",
|
||||
"actual_mode": "address_query",
|
||||
"mode_match": true,
|
||||
"expected_reply_type": null,
|
||||
"reply_match": true,
|
||||
"semantic_pass": true,
|
||||
"route_pass": false,
|
||||
"route_health": "blocked_execution_error",
|
||||
"strict_policy": "route",
|
||||
"strict_pass": false,
|
||||
"selected_recipe": "address_period_coverage_profile_v1",
|
||||
"missing_required_filters": [],
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"rows_fetched": 0,
|
||||
"rows_matched": 0,
|
||||
"mcp_call_status": "error",
|
||||
"limited_reason_category": "execution_error",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_reason": "not_address_like",
|
||||
"fallback_rule_hit": null,
|
||||
"debug_payload": {
|
||||
"trace_id": "address-lxBpVpL9YV",
|
||||
"prompt_version": "address_query_runtime_v1",
|
||||
"schema_version": "address_query_runtime_v1",
|
||||
"fallback_type": "partial",
|
||||
"route_summary": null,
|
||||
"fragments": [],
|
||||
"requirements_extracted": [],
|
||||
"coverage_report": {
|
||||
"requirements_total": 0,
|
||||
"requirements_covered": 0,
|
||||
"requirements_uncovered": [],
|
||||
"requirements_partially_covered": [],
|
||||
"clarification_needed_for": [],
|
||||
"out_of_scope_requirements": []
|
||||
},
|
||||
"routes": [],
|
||||
"retrieval_status": [],
|
||||
"retrieval_results": [],
|
||||
"answer_grounding_check": {
|
||||
"status": "partial",
|
||||
"route_subject_match": true,
|
||||
"missing_requirements": [],
|
||||
"reasons": [
|
||||
"management_profile_signal_detected",
|
||||
"shape_not_detected",
|
||||
"period_coverage_profile_signal_detected",
|
||||
"{ВнешняяОбработка.MCPToolkit.Форма.Форма.Форма(1989)}: Ошибка при вызове метода контекста (Выполнить): {(10, 24)}: Синтаксическая ошибка\nДвижения.Период <= <<?>>ТЕКУЩАЯДАТА()"
|
||||
],
|
||||
"why_included_summary": [],
|
||||
"selection_reason_summary": []
|
||||
},
|
||||
"dropped_intent_segments": [],
|
||||
"detected_mode": "address_query",
|
||||
"detected_mode_confidence": "medium",
|
||||
"query_shape": "UNKNOWN",
|
||||
"query_shape_confidence": "low",
|
||||
"detected_intent": "period_coverage_profile",
|
||||
"detected_intent_confidence": "high",
|
||||
"extracted_filters": {
|
||||
"sort": "period_desc"
|
||||
},
|
||||
"missing_required_filters": [],
|
||||
"selected_recipe": "address_period_coverage_profile_v1",
|
||||
"mcp_call_status_legacy": "error",
|
||||
"account_scope_mode": "preferred",
|
||||
"account_scope_fallback_applied": false,
|
||||
"anchor_type": "unknown",
|
||||
"anchor_value_raw": null,
|
||||
"anchor_value_resolved": null,
|
||||
"resolver_confidence": "low",
|
||||
"ambiguity_count": 0,
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"mcp_call_status": "error",
|
||||
"rows_fetched": 0,
|
||||
"raw_rows_received": 0,
|
||||
"rows_after_account_scope": 0,
|
||||
"rows_after_recipe_filter": 0,
|
||||
"rows_materialized": 0,
|
||||
"rows_matched": 0,
|
||||
"raw_row_keys_sample": [],
|
||||
"materialization_drop_reason": "none",
|
||||
"account_token_raw": null,
|
||||
"account_token_normalized": null,
|
||||
"account_scope_fields_checked": [
|
||||
"account_dt",
|
||||
"account_kt",
|
||||
"registrator",
|
||||
"analytics"
|
||||
],
|
||||
"account_scope_match_strategy": "account_code_regex_plus_alias_map_v1",
|
||||
"account_scope_drop_reason": "not_applicable",
|
||||
"runtime_readiness": "UNKNOWN",
|
||||
"limited_reason_category": "execution_error",
|
||||
"response_type": "LIMITED_WITH_REASON",
|
||||
"execution_lane": "address_query",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_attempted": false,
|
||||
"llm_provider_used": "local",
|
||||
"llm_decomposition_trace_id": null,
|
||||
"llm_decomposition_effective_message": "Какой месяц самый активный по количеству операций?",
|
||||
"llm_decomposition_reason": "not_address_like",
|
||||
"fallback_rule_hit": null,
|
||||
"sanitized_user_message": "какой месяц самый активный по количеству операций?",
|
||||
"tool_gate_decision": "run_address_lane",
|
||||
"tool_gate_reason": "address_mode_classifier_detected",
|
||||
"answer_structure_v11": null,
|
||||
"investigation_state_snapshot": null,
|
||||
"normalized": null,
|
||||
"normalizer_output": null
|
||||
},
|
||||
"error_code": null,
|
||||
"error_message": null
|
||||
},
|
||||
{
|
||||
"index": 4,
|
||||
"id": "Q4",
|
||||
"question": "Какие типы документов используются чаще всего в базе?",
|
||||
"session": null,
|
||||
"session_id": "asst-2026-04-02_Address_General5_Live_Check_AfterFix_01-q4",
|
||||
"status_code": 200,
|
||||
"ok": true,
|
||||
"elapsed_ms": 5058,
|
||||
"reply_type": "partial_coverage",
|
||||
"trace_id": "address-0_1nOMvz1f",
|
||||
"assistant_reply": "Не удалось выполнить адресный live-запрос в V1.\nПричина: live MCP вызов завершился ошибкой.\nЧто нужно уточнить: {ВнешняяОбработка.MCPToolkit.Форма.Форма.Форма(1989)}: Ошибка при вызове метода контекста (Выполнить): {(10, 24)}: Синтаксическая ошибка\nДвижения.Период <= <<?>>ТЕКУЩАЯДАТА().",
|
||||
"assistant_reply_first_line": "Не удалось выполнить адресный live-запрос в V1.",
|
||||
"expected_intent": "document_type_and_account_section_profile",
|
||||
"actual_intent": "document_type_and_account_section_profile",
|
||||
"intent_match": true,
|
||||
"expected_mode": "address_query",
|
||||
"actual_mode": "address_query",
|
||||
"mode_match": true,
|
||||
"expected_reply_type": null,
|
||||
"reply_match": true,
|
||||
"semantic_pass": true,
|
||||
"route_pass": false,
|
||||
"route_health": "blocked_execution_error",
|
||||
"strict_policy": "route",
|
||||
"strict_pass": false,
|
||||
"selected_recipe": "address_document_type_and_account_section_profile_v1",
|
||||
"missing_required_filters": [],
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"rows_fetched": 0,
|
||||
"rows_matched": 0,
|
||||
"mcp_call_status": "error",
|
||||
"limited_reason_category": "execution_error",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_reason": "normalized_fragment_same",
|
||||
"fallback_rule_hit": null,
|
||||
"debug_payload": {
|
||||
"trace_id": "address-0_1nOMvz1f",
|
||||
"prompt_version": "address_query_runtime_v1",
|
||||
"schema_version": "address_query_runtime_v1",
|
||||
"fallback_type": "partial",
|
||||
"route_summary": null,
|
||||
"fragments": [],
|
||||
"requirements_extracted": [],
|
||||
"coverage_report": {
|
||||
"requirements_total": 0,
|
||||
"requirements_covered": 0,
|
||||
"requirements_uncovered": [],
|
||||
"requirements_partially_covered": [],
|
||||
"clarification_needed_for": [],
|
||||
"out_of_scope_requirements": []
|
||||
},
|
||||
"routes": [],
|
||||
"retrieval_status": [],
|
||||
"retrieval_results": [],
|
||||
"answer_grounding_check": {
|
||||
"status": "partial",
|
||||
"route_subject_match": true,
|
||||
"missing_requirements": [],
|
||||
"reasons": [
|
||||
"address_action_detected",
|
||||
"address_entity_detected",
|
||||
"document_list_signal_detected",
|
||||
"document_type_and_account_section_profile_signal_detected",
|
||||
"{ВнешняяОбработка.MCPToolkit.Форма.Форма.Форма(1989)}: Ошибка при вызове метода контекста (Выполнить): {(10, 24)}: Синтаксическая ошибка\nДвижения.Период <= <<?>>ТЕКУЩАЯДАТА()"
|
||||
],
|
||||
"why_included_summary": [],
|
||||
"selection_reason_summary": []
|
||||
},
|
||||
"dropped_intent_segments": [],
|
||||
"detected_mode": "address_query",
|
||||
"detected_mode_confidence": "high",
|
||||
"query_shape": "DOCUMENT_LIST",
|
||||
"query_shape_confidence": "medium",
|
||||
"detected_intent": "document_type_and_account_section_profile",
|
||||
"detected_intent_confidence": "high",
|
||||
"extracted_filters": {
|
||||
"sort": "period_desc"
|
||||
},
|
||||
"missing_required_filters": [],
|
||||
"selected_recipe": "address_document_type_and_account_section_profile_v1",
|
||||
"mcp_call_status_legacy": "error",
|
||||
"account_scope_mode": "preferred",
|
||||
"account_scope_fallback_applied": false,
|
||||
"anchor_type": "unknown",
|
||||
"anchor_value_raw": null,
|
||||
"anchor_value_resolved": null,
|
||||
"resolver_confidence": "low",
|
||||
"ambiguity_count": 0,
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"mcp_call_status": "error",
|
||||
"rows_fetched": 0,
|
||||
"raw_rows_received": 0,
|
||||
"rows_after_account_scope": 0,
|
||||
"rows_after_recipe_filter": 0,
|
||||
"rows_materialized": 0,
|
||||
"rows_matched": 0,
|
||||
"raw_row_keys_sample": [],
|
||||
"materialization_drop_reason": "none",
|
||||
"account_token_raw": null,
|
||||
"account_token_normalized": null,
|
||||
"account_scope_fields_checked": [
|
||||
"account_dt",
|
||||
"account_kt",
|
||||
"registrator",
|
||||
"analytics"
|
||||
],
|
||||
"account_scope_match_strategy": "account_code_regex_plus_alias_map_v1",
|
||||
"account_scope_drop_reason": "not_applicable",
|
||||
"runtime_readiness": "UNKNOWN",
|
||||
"limited_reason_category": "execution_error",
|
||||
"response_type": "LIMITED_WITH_REASON",
|
||||
"execution_lane": "address_query",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_attempted": true,
|
||||
"llm_provider_used": "local",
|
||||
"llm_decomposition_trace_id": "KAAw7U8orkHpRG",
|
||||
"llm_decomposition_effective_message": "Какие типы документов используются чаще всего в базе?",
|
||||
"llm_decomposition_reason": "normalized_fragment_same",
|
||||
"fallback_rule_hit": null,
|
||||
"sanitized_user_message": "какие типы документов используются чаще всего в базе?",
|
||||
"tool_gate_decision": "run_address_lane",
|
||||
"tool_gate_reason": "address_mode_classifier_detected",
|
||||
"answer_structure_v11": null,
|
||||
"investigation_state_snapshot": null,
|
||||
"normalized": null,
|
||||
"normalizer_output": {
|
||||
"trace_id": "KAAw7U8orkHpRG",
|
||||
"prompt_version": "normalizer_v2_0_2",
|
||||
"applied": false,
|
||||
"effective_message": "Какие типы документов используются чаще всего в базе?"
|
||||
}
|
||||
},
|
||||
"error_code": null,
|
||||
"error_message": null
|
||||
},
|
||||
{
|
||||
"index": 5,
|
||||
"id": "Q5",
|
||||
"question": "Какие разделы учета наиболее заполнены и какие почти не используются?",
|
||||
"session": null,
|
||||
"session_id": "asst-2026-04-02_Address_General5_Live_Check_AfterFix_01-q5",
|
||||
"status_code": 200,
|
||||
"ok": true,
|
||||
"elapsed_ms": 1002,
|
||||
"reply_type": "partial_coverage",
|
||||
"trace_id": "address-0XdEJQTykP",
|
||||
"assistant_reply": "Не удалось выполнить адресный live-запрос в V1.\nПричина: live MCP вызов завершился ошибкой.\nЧто нужно уточнить: {ВнешняяОбработка.MCPToolkit.Форма.Форма.Форма(1989)}: Ошибка при вызове метода контекста (Выполнить): {(10, 24)}: Синтаксическая ошибка\nДвижения.Период <= <<?>>ТЕКУЩАЯДАТА().",
|
||||
"assistant_reply_first_line": "Не удалось выполнить адресный live-запрос в V1.",
|
||||
"expected_intent": "document_type_and_account_section_profile",
|
||||
"actual_intent": "document_type_and_account_section_profile",
|
||||
"intent_match": true,
|
||||
"expected_mode": "address_query",
|
||||
"actual_mode": "address_query",
|
||||
"mode_match": true,
|
||||
"expected_reply_type": null,
|
||||
"reply_match": true,
|
||||
"semantic_pass": true,
|
||||
"route_pass": false,
|
||||
"route_health": "blocked_execution_error",
|
||||
"strict_policy": "route",
|
||||
"strict_pass": false,
|
||||
"selected_recipe": "address_document_type_and_account_section_profile_v1",
|
||||
"missing_required_filters": [],
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"rows_fetched": 0,
|
||||
"rows_matched": 0,
|
||||
"mcp_call_status": "error",
|
||||
"limited_reason_category": "execution_error",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_reason": "not_address_like",
|
||||
"fallback_rule_hit": null,
|
||||
"debug_payload": {
|
||||
"trace_id": "address-0XdEJQTykP",
|
||||
"prompt_version": "address_query_runtime_v1",
|
||||
"schema_version": "address_query_runtime_v1",
|
||||
"fallback_type": "partial",
|
||||
"route_summary": null,
|
||||
"fragments": [],
|
||||
"requirements_extracted": [],
|
||||
"coverage_report": {
|
||||
"requirements_total": 0,
|
||||
"requirements_covered": 0,
|
||||
"requirements_uncovered": [],
|
||||
"requirements_partially_covered": [],
|
||||
"clarification_needed_for": [],
|
||||
"out_of_scope_requirements": []
|
||||
},
|
||||
"routes": [],
|
||||
"retrieval_status": [],
|
||||
"retrieval_results": [],
|
||||
"answer_grounding_check": {
|
||||
"status": "partial",
|
||||
"route_subject_match": true,
|
||||
"missing_requirements": [],
|
||||
"reasons": [
|
||||
"management_profile_signal_detected",
|
||||
"shape_not_detected",
|
||||
"document_type_and_account_section_profile_signal_detected",
|
||||
"{ВнешняяОбработка.MCPToolkit.Форма.Форма.Форма(1989)}: Ошибка при вызове метода контекста (Выполнить): {(10, 24)}: Синтаксическая ошибка\nДвижения.Период <= <<?>>ТЕКУЩАЯДАТА()"
|
||||
],
|
||||
"why_included_summary": [],
|
||||
"selection_reason_summary": []
|
||||
},
|
||||
"dropped_intent_segments": [],
|
||||
"detected_mode": "address_query",
|
||||
"detected_mode_confidence": "medium",
|
||||
"query_shape": "UNKNOWN",
|
||||
"query_shape_confidence": "low",
|
||||
"detected_intent": "document_type_and_account_section_profile",
|
||||
"detected_intent_confidence": "high",
|
||||
"extracted_filters": {
|
||||
"sort": "period_desc"
|
||||
},
|
||||
"missing_required_filters": [],
|
||||
"selected_recipe": "address_document_type_and_account_section_profile_v1",
|
||||
"mcp_call_status_legacy": "error",
|
||||
"account_scope_mode": "preferred",
|
||||
"account_scope_fallback_applied": false,
|
||||
"anchor_type": "unknown",
|
||||
"anchor_value_raw": null,
|
||||
"anchor_value_resolved": null,
|
||||
"resolver_confidence": "low",
|
||||
"ambiguity_count": 0,
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"mcp_call_status": "error",
|
||||
"rows_fetched": 0,
|
||||
"raw_rows_received": 0,
|
||||
"rows_after_account_scope": 0,
|
||||
"rows_after_recipe_filter": 0,
|
||||
"rows_materialized": 0,
|
||||
"rows_matched": 0,
|
||||
"raw_row_keys_sample": [],
|
||||
"materialization_drop_reason": "none",
|
||||
"account_token_raw": null,
|
||||
"account_token_normalized": null,
|
||||
"account_scope_fields_checked": [
|
||||
"account_dt",
|
||||
"account_kt",
|
||||
"registrator",
|
||||
"analytics"
|
||||
],
|
||||
"account_scope_match_strategy": "account_code_regex_plus_alias_map_v1",
|
||||
"account_scope_drop_reason": "not_applicable",
|
||||
"runtime_readiness": "UNKNOWN",
|
||||
"limited_reason_category": "execution_error",
|
||||
"response_type": "LIMITED_WITH_REASON",
|
||||
"execution_lane": "address_query",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_attempted": false,
|
||||
"llm_provider_used": "local",
|
||||
"llm_decomposition_trace_id": null,
|
||||
"llm_decomposition_effective_message": "Какие разделы учета наиболее заполнены и какие почти не используются?",
|
||||
"llm_decomposition_reason": "not_address_like",
|
||||
"fallback_rule_hit": null,
|
||||
"sanitized_user_message": "какие разделы учета наиболее заполнены и какие почти не используются?",
|
||||
"tool_gate_decision": "run_address_lane",
|
||||
"tool_gate_reason": "address_mode_classifier_detected",
|
||||
"answer_structure_v11": null,
|
||||
"investigation_state_snapshot": null,
|
||||
"normalized": null,
|
||||
"normalizer_output": null
|
||||
},
|
||||
"error_code": null,
|
||||
"error_message": null
|
||||
}
|
||||
]
|
||||
+724
@@ -0,0 +1,724 @@
|
||||
{
|
||||
"run_id": "2026-04-02_Address_General5_Live_Check_AfterFix_01",
|
||||
"generated_at": "2026-04-02T19:27:58",
|
||||
"summary": {
|
||||
"run_id": "2026-04-02_Address_General5_Live_Check_AfterFix_01",
|
||||
"generated_at": "2026-04-02T19:27:58",
|
||||
"source_questions_file": "X:\\1C\\NDC_1C\\docs\\ADDRESS\\question_sets\\temp_general5_live_check_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": "route",
|
||||
"totals": {
|
||||
"questions_total": 5,
|
||||
"ok_200_count": 5,
|
||||
"semantic_pass_count": 5,
|
||||
"semantic_pass_rate": 1.0,
|
||||
"route_pass_count": 0,
|
||||
"route_pass_rate": 0.0,
|
||||
"strict_pass_count": 0,
|
||||
"strict_pass_rate": 0.0,
|
||||
"factual_count": 0,
|
||||
"partial_coverage_count": 5,
|
||||
"clarification_required_count": 0,
|
||||
"http_error_count": 0,
|
||||
"llm_decomposition_applied_count": 0,
|
||||
"avg_elapsed_ms": 2632
|
||||
},
|
||||
"distributions": {
|
||||
"reply_type": {
|
||||
"partial_coverage": 5
|
||||
},
|
||||
"actual_intent": {
|
||||
"period_coverage_profile": 3,
|
||||
"document_type_and_account_section_profile": 2
|
||||
},
|
||||
"actual_mode": {
|
||||
"address_query": 5
|
||||
},
|
||||
"mcp_call_status": {
|
||||
"error": 5
|
||||
},
|
||||
"limited_reason_category": {
|
||||
"execution_error": 5
|
||||
},
|
||||
"route_health": {
|
||||
"blocked_execution_error": 5
|
||||
}
|
||||
}
|
||||
},
|
||||
"rows": [
|
||||
{
|
||||
"index": 1,
|
||||
"id": "Q1",
|
||||
"question": "За какие годы в базе есть данные?",
|
||||
"session": null,
|
||||
"session_id": "asst-2026-04-02_Address_General5_Live_Check_AfterFix_01-q1",
|
||||
"status_code": 200,
|
||||
"ok": true,
|
||||
"elapsed_ms": 962,
|
||||
"reply_type": "partial_coverage",
|
||||
"trace_id": "address-eW6Yb7i_tq",
|
||||
"assistant_reply": "Не удалось выполнить адресный live-запрос в V1.\nПричина: live MCP вызов завершился ошибкой.\nЧто нужно уточнить: {ВнешняяОбработка.MCPToolkit.Форма.Форма.Форма(1989)}: Ошибка при вызове метода контекста (Выполнить): {(10, 24)}: Синтаксическая ошибка\nДвижения.Период <= <<?>>ТЕКУЩАЯДАТА().",
|
||||
"assistant_reply_first_line": "Не удалось выполнить адресный live-запрос в V1.",
|
||||
"expected_intent": "period_coverage_profile",
|
||||
"actual_intent": "period_coverage_profile",
|
||||
"intent_match": true,
|
||||
"expected_mode": "address_query",
|
||||
"actual_mode": "address_query",
|
||||
"mode_match": true,
|
||||
"expected_reply_type": null,
|
||||
"reply_match": true,
|
||||
"semantic_pass": true,
|
||||
"route_pass": false,
|
||||
"route_health": "blocked_execution_error",
|
||||
"strict_policy": "route",
|
||||
"strict_pass": false,
|
||||
"selected_recipe": "address_period_coverage_profile_v1",
|
||||
"missing_required_filters": [],
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"rows_fetched": 0,
|
||||
"rows_matched": 0,
|
||||
"mcp_call_status": "error",
|
||||
"limited_reason_category": "execution_error",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_reason": "not_address_like",
|
||||
"fallback_rule_hit": null,
|
||||
"debug_payload": {
|
||||
"trace_id": "address-eW6Yb7i_tq",
|
||||
"prompt_version": "address_query_runtime_v1",
|
||||
"schema_version": "address_query_runtime_v1",
|
||||
"fallback_type": "partial",
|
||||
"route_summary": null,
|
||||
"fragments": [],
|
||||
"requirements_extracted": [],
|
||||
"coverage_report": {
|
||||
"requirements_total": 0,
|
||||
"requirements_covered": 0,
|
||||
"requirements_uncovered": [],
|
||||
"requirements_partially_covered": [],
|
||||
"clarification_needed_for": [],
|
||||
"out_of_scope_requirements": []
|
||||
},
|
||||
"routes": [],
|
||||
"retrieval_status": [],
|
||||
"retrieval_results": [],
|
||||
"answer_grounding_check": {
|
||||
"status": "partial",
|
||||
"route_subject_match": true,
|
||||
"missing_requirements": [],
|
||||
"reasons": [
|
||||
"management_profile_signal_detected",
|
||||
"shape_not_detected",
|
||||
"period_coverage_profile_signal_detected",
|
||||
"{ВнешняяОбработка.MCPToolkit.Форма.Форма.Форма(1989)}: Ошибка при вызове метода контекста (Выполнить): {(10, 24)}: Синтаксическая ошибка\nДвижения.Период <= <<?>>ТЕКУЩАЯДАТА()"
|
||||
],
|
||||
"why_included_summary": [],
|
||||
"selection_reason_summary": []
|
||||
},
|
||||
"dropped_intent_segments": [],
|
||||
"detected_mode": "address_query",
|
||||
"detected_mode_confidence": "medium",
|
||||
"query_shape": "UNKNOWN",
|
||||
"query_shape_confidence": "low",
|
||||
"detected_intent": "period_coverage_profile",
|
||||
"detected_intent_confidence": "high",
|
||||
"extracted_filters": {
|
||||
"sort": "period_desc"
|
||||
},
|
||||
"missing_required_filters": [],
|
||||
"selected_recipe": "address_period_coverage_profile_v1",
|
||||
"mcp_call_status_legacy": "error",
|
||||
"account_scope_mode": "preferred",
|
||||
"account_scope_fallback_applied": false,
|
||||
"anchor_type": "unknown",
|
||||
"anchor_value_raw": null,
|
||||
"anchor_value_resolved": null,
|
||||
"resolver_confidence": "low",
|
||||
"ambiguity_count": 0,
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"mcp_call_status": "error",
|
||||
"rows_fetched": 0,
|
||||
"raw_rows_received": 0,
|
||||
"rows_after_account_scope": 0,
|
||||
"rows_after_recipe_filter": 0,
|
||||
"rows_materialized": 0,
|
||||
"rows_matched": 0,
|
||||
"raw_row_keys_sample": [],
|
||||
"materialization_drop_reason": "none",
|
||||
"account_token_raw": null,
|
||||
"account_token_normalized": null,
|
||||
"account_scope_fields_checked": [
|
||||
"account_dt",
|
||||
"account_kt",
|
||||
"registrator",
|
||||
"analytics"
|
||||
],
|
||||
"account_scope_match_strategy": "account_code_regex_plus_alias_map_v1",
|
||||
"account_scope_drop_reason": "not_applicable",
|
||||
"runtime_readiness": "UNKNOWN",
|
||||
"limited_reason_category": "execution_error",
|
||||
"response_type": "LIMITED_WITH_REASON",
|
||||
"execution_lane": "address_query",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_attempted": false,
|
||||
"llm_provider_used": "local",
|
||||
"llm_decomposition_trace_id": null,
|
||||
"llm_decomposition_effective_message": "За какие годы в базе есть данные?",
|
||||
"llm_decomposition_reason": "not_address_like",
|
||||
"fallback_rule_hit": null,
|
||||
"sanitized_user_message": "за какие годы в базе есть данные?",
|
||||
"tool_gate_decision": "run_address_lane",
|
||||
"tool_gate_reason": "address_mode_classifier_detected",
|
||||
"answer_structure_v11": null,
|
||||
"investigation_state_snapshot": null,
|
||||
"normalized": null,
|
||||
"normalizer_output": null
|
||||
},
|
||||
"error_code": null,
|
||||
"error_message": null
|
||||
},
|
||||
{
|
||||
"index": 2,
|
||||
"id": "Q2",
|
||||
"question": "Какой год самый активный по количеству документов?",
|
||||
"session": null,
|
||||
"session_id": "asst-2026-04-02_Address_General5_Live_Check_AfterFix_01-q2",
|
||||
"status_code": 200,
|
||||
"ok": true,
|
||||
"elapsed_ms": 5072,
|
||||
"reply_type": "partial_coverage",
|
||||
"trace_id": "address-BKVNDThPUd",
|
||||
"assistant_reply": "Не удалось выполнить адресный live-запрос в V1.\nПричина: live MCP вызов завершился ошибкой.\nЧто нужно уточнить: {ВнешняяОбработка.MCPToolkit.Форма.Форма.Форма(1989)}: Ошибка при вызове метода контекста (Выполнить): {(10, 24)}: Синтаксическая ошибка\nДвижения.Период <= <<?>>ТЕКУЩАЯДАТА().",
|
||||
"assistant_reply_first_line": "Не удалось выполнить адресный live-запрос в V1.",
|
||||
"expected_intent": "period_coverage_profile",
|
||||
"actual_intent": "period_coverage_profile",
|
||||
"intent_match": true,
|
||||
"expected_mode": "address_query",
|
||||
"actual_mode": "address_query",
|
||||
"mode_match": true,
|
||||
"expected_reply_type": null,
|
||||
"reply_match": true,
|
||||
"semantic_pass": true,
|
||||
"route_pass": false,
|
||||
"route_health": "blocked_execution_error",
|
||||
"strict_policy": "route",
|
||||
"strict_pass": false,
|
||||
"selected_recipe": "address_period_coverage_profile_v1",
|
||||
"missing_required_filters": [],
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"rows_fetched": 0,
|
||||
"rows_matched": 0,
|
||||
"mcp_call_status": "error",
|
||||
"limited_reason_category": "execution_error",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_reason": "normalized_fragment_rejected_intent_conflict",
|
||||
"fallback_rule_hit": null,
|
||||
"debug_payload": {
|
||||
"trace_id": "address-BKVNDThPUd",
|
||||
"prompt_version": "address_query_runtime_v1",
|
||||
"schema_version": "address_query_runtime_v1",
|
||||
"fallback_type": "partial",
|
||||
"route_summary": null,
|
||||
"fragments": [],
|
||||
"requirements_extracted": [],
|
||||
"coverage_report": {
|
||||
"requirements_total": 0,
|
||||
"requirements_covered": 0,
|
||||
"requirements_uncovered": [],
|
||||
"requirements_partially_covered": [],
|
||||
"clarification_needed_for": [],
|
||||
"out_of_scope_requirements": []
|
||||
},
|
||||
"routes": [],
|
||||
"retrieval_status": [],
|
||||
"retrieval_results": [],
|
||||
"answer_grounding_check": {
|
||||
"status": "partial",
|
||||
"route_subject_match": true,
|
||||
"missing_requirements": [],
|
||||
"reasons": [
|
||||
"management_profile_signal_detected",
|
||||
"document_list_signal_detected",
|
||||
"period_coverage_profile_signal_detected",
|
||||
"{ВнешняяОбработка.MCPToolkit.Форма.Форма.Форма(1989)}: Ошибка при вызове метода контекста (Выполнить): {(10, 24)}: Синтаксическая ошибка\nДвижения.Период <= <<?>>ТЕКУЩАЯДАТА()"
|
||||
],
|
||||
"why_included_summary": [],
|
||||
"selection_reason_summary": []
|
||||
},
|
||||
"dropped_intent_segments": [],
|
||||
"detected_mode": "address_query",
|
||||
"detected_mode_confidence": "medium",
|
||||
"query_shape": "DOCUMENT_LIST",
|
||||
"query_shape_confidence": "medium",
|
||||
"detected_intent": "period_coverage_profile",
|
||||
"detected_intent_confidence": "high",
|
||||
"extracted_filters": {
|
||||
"sort": "period_desc"
|
||||
},
|
||||
"missing_required_filters": [],
|
||||
"selected_recipe": "address_period_coverage_profile_v1",
|
||||
"mcp_call_status_legacy": "error",
|
||||
"account_scope_mode": "preferred",
|
||||
"account_scope_fallback_applied": false,
|
||||
"anchor_type": "unknown",
|
||||
"anchor_value_raw": null,
|
||||
"anchor_value_resolved": null,
|
||||
"resolver_confidence": "low",
|
||||
"ambiguity_count": 0,
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"mcp_call_status": "error",
|
||||
"rows_fetched": 0,
|
||||
"raw_rows_received": 0,
|
||||
"rows_after_account_scope": 0,
|
||||
"rows_after_recipe_filter": 0,
|
||||
"rows_materialized": 0,
|
||||
"rows_matched": 0,
|
||||
"raw_row_keys_sample": [],
|
||||
"materialization_drop_reason": "none",
|
||||
"account_token_raw": null,
|
||||
"account_token_normalized": null,
|
||||
"account_scope_fields_checked": [
|
||||
"account_dt",
|
||||
"account_kt",
|
||||
"registrator",
|
||||
"analytics"
|
||||
],
|
||||
"account_scope_match_strategy": "account_code_regex_plus_alias_map_v1",
|
||||
"account_scope_drop_reason": "not_applicable",
|
||||
"runtime_readiness": "UNKNOWN",
|
||||
"limited_reason_category": "execution_error",
|
||||
"response_type": "LIMITED_WITH_REASON",
|
||||
"execution_lane": "address_query",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_attempted": true,
|
||||
"llm_provider_used": "local",
|
||||
"llm_decomposition_trace_id": "bgFD0eUh97bbae",
|
||||
"llm_decomposition_effective_message": "Какой год самый активный по количеству документов?",
|
||||
"llm_decomposition_reason": "normalized_fragment_rejected_intent_conflict",
|
||||
"fallback_rule_hit": null,
|
||||
"sanitized_user_message": "какой год самый активный по количеству документов?",
|
||||
"tool_gate_decision": "run_address_lane",
|
||||
"tool_gate_reason": "address_mode_classifier_detected",
|
||||
"answer_structure_v11": null,
|
||||
"investigation_state_snapshot": null,
|
||||
"normalized": null,
|
||||
"normalizer_output": {
|
||||
"trace_id": "bgFD0eUh97bbae",
|
||||
"prompt_version": "normalizer_v2_0_2",
|
||||
"applied": false,
|
||||
"effective_message": "Какой год самый активный по количеству документов?"
|
||||
}
|
||||
},
|
||||
"error_code": null,
|
||||
"error_message": null
|
||||
},
|
||||
{
|
||||
"index": 3,
|
||||
"id": "Q3",
|
||||
"question": "Какой месяц самый активный по количеству операций?",
|
||||
"session": null,
|
||||
"session_id": "asst-2026-04-02_Address_General5_Live_Check_AfterFix_01-q3",
|
||||
"status_code": 200,
|
||||
"ok": true,
|
||||
"elapsed_ms": 1066,
|
||||
"reply_type": "partial_coverage",
|
||||
"trace_id": "address-lxBpVpL9YV",
|
||||
"assistant_reply": "Не удалось выполнить адресный live-запрос в V1.\nПричина: live MCP вызов завершился ошибкой.\nЧто нужно уточнить: {ВнешняяОбработка.MCPToolkit.Форма.Форма.Форма(1989)}: Ошибка при вызове метода контекста (Выполнить): {(10, 24)}: Синтаксическая ошибка\nДвижения.Период <= <<?>>ТЕКУЩАЯДАТА().",
|
||||
"assistant_reply_first_line": "Не удалось выполнить адресный live-запрос в V1.",
|
||||
"expected_intent": "period_coverage_profile",
|
||||
"actual_intent": "period_coverage_profile",
|
||||
"intent_match": true,
|
||||
"expected_mode": "address_query",
|
||||
"actual_mode": "address_query",
|
||||
"mode_match": true,
|
||||
"expected_reply_type": null,
|
||||
"reply_match": true,
|
||||
"semantic_pass": true,
|
||||
"route_pass": false,
|
||||
"route_health": "blocked_execution_error",
|
||||
"strict_policy": "route",
|
||||
"strict_pass": false,
|
||||
"selected_recipe": "address_period_coverage_profile_v1",
|
||||
"missing_required_filters": [],
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"rows_fetched": 0,
|
||||
"rows_matched": 0,
|
||||
"mcp_call_status": "error",
|
||||
"limited_reason_category": "execution_error",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_reason": "not_address_like",
|
||||
"fallback_rule_hit": null,
|
||||
"debug_payload": {
|
||||
"trace_id": "address-lxBpVpL9YV",
|
||||
"prompt_version": "address_query_runtime_v1",
|
||||
"schema_version": "address_query_runtime_v1",
|
||||
"fallback_type": "partial",
|
||||
"route_summary": null,
|
||||
"fragments": [],
|
||||
"requirements_extracted": [],
|
||||
"coverage_report": {
|
||||
"requirements_total": 0,
|
||||
"requirements_covered": 0,
|
||||
"requirements_uncovered": [],
|
||||
"requirements_partially_covered": [],
|
||||
"clarification_needed_for": [],
|
||||
"out_of_scope_requirements": []
|
||||
},
|
||||
"routes": [],
|
||||
"retrieval_status": [],
|
||||
"retrieval_results": [],
|
||||
"answer_grounding_check": {
|
||||
"status": "partial",
|
||||
"route_subject_match": true,
|
||||
"missing_requirements": [],
|
||||
"reasons": [
|
||||
"management_profile_signal_detected",
|
||||
"shape_not_detected",
|
||||
"period_coverage_profile_signal_detected",
|
||||
"{ВнешняяОбработка.MCPToolkit.Форма.Форма.Форма(1989)}: Ошибка при вызове метода контекста (Выполнить): {(10, 24)}: Синтаксическая ошибка\nДвижения.Период <= <<?>>ТЕКУЩАЯДАТА()"
|
||||
],
|
||||
"why_included_summary": [],
|
||||
"selection_reason_summary": []
|
||||
},
|
||||
"dropped_intent_segments": [],
|
||||
"detected_mode": "address_query",
|
||||
"detected_mode_confidence": "medium",
|
||||
"query_shape": "UNKNOWN",
|
||||
"query_shape_confidence": "low",
|
||||
"detected_intent": "period_coverage_profile",
|
||||
"detected_intent_confidence": "high",
|
||||
"extracted_filters": {
|
||||
"sort": "period_desc"
|
||||
},
|
||||
"missing_required_filters": [],
|
||||
"selected_recipe": "address_period_coverage_profile_v1",
|
||||
"mcp_call_status_legacy": "error",
|
||||
"account_scope_mode": "preferred",
|
||||
"account_scope_fallback_applied": false,
|
||||
"anchor_type": "unknown",
|
||||
"anchor_value_raw": null,
|
||||
"anchor_value_resolved": null,
|
||||
"resolver_confidence": "low",
|
||||
"ambiguity_count": 0,
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"mcp_call_status": "error",
|
||||
"rows_fetched": 0,
|
||||
"raw_rows_received": 0,
|
||||
"rows_after_account_scope": 0,
|
||||
"rows_after_recipe_filter": 0,
|
||||
"rows_materialized": 0,
|
||||
"rows_matched": 0,
|
||||
"raw_row_keys_sample": [],
|
||||
"materialization_drop_reason": "none",
|
||||
"account_token_raw": null,
|
||||
"account_token_normalized": null,
|
||||
"account_scope_fields_checked": [
|
||||
"account_dt",
|
||||
"account_kt",
|
||||
"registrator",
|
||||
"analytics"
|
||||
],
|
||||
"account_scope_match_strategy": "account_code_regex_plus_alias_map_v1",
|
||||
"account_scope_drop_reason": "not_applicable",
|
||||
"runtime_readiness": "UNKNOWN",
|
||||
"limited_reason_category": "execution_error",
|
||||
"response_type": "LIMITED_WITH_REASON",
|
||||
"execution_lane": "address_query",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_attempted": false,
|
||||
"llm_provider_used": "local",
|
||||
"llm_decomposition_trace_id": null,
|
||||
"llm_decomposition_effective_message": "Какой месяц самый активный по количеству операций?",
|
||||
"llm_decomposition_reason": "not_address_like",
|
||||
"fallback_rule_hit": null,
|
||||
"sanitized_user_message": "какой месяц самый активный по количеству операций?",
|
||||
"tool_gate_decision": "run_address_lane",
|
||||
"tool_gate_reason": "address_mode_classifier_detected",
|
||||
"answer_structure_v11": null,
|
||||
"investigation_state_snapshot": null,
|
||||
"normalized": null,
|
||||
"normalizer_output": null
|
||||
},
|
||||
"error_code": null,
|
||||
"error_message": null
|
||||
},
|
||||
{
|
||||
"index": 4,
|
||||
"id": "Q4",
|
||||
"question": "Какие типы документов используются чаще всего в базе?",
|
||||
"session": null,
|
||||
"session_id": "asst-2026-04-02_Address_General5_Live_Check_AfterFix_01-q4",
|
||||
"status_code": 200,
|
||||
"ok": true,
|
||||
"elapsed_ms": 5058,
|
||||
"reply_type": "partial_coverage",
|
||||
"trace_id": "address-0_1nOMvz1f",
|
||||
"assistant_reply": "Не удалось выполнить адресный live-запрос в V1.\nПричина: live MCP вызов завершился ошибкой.\nЧто нужно уточнить: {ВнешняяОбработка.MCPToolkit.Форма.Форма.Форма(1989)}: Ошибка при вызове метода контекста (Выполнить): {(10, 24)}: Синтаксическая ошибка\nДвижения.Период <= <<?>>ТЕКУЩАЯДАТА().",
|
||||
"assistant_reply_first_line": "Не удалось выполнить адресный live-запрос в V1.",
|
||||
"expected_intent": "document_type_and_account_section_profile",
|
||||
"actual_intent": "document_type_and_account_section_profile",
|
||||
"intent_match": true,
|
||||
"expected_mode": "address_query",
|
||||
"actual_mode": "address_query",
|
||||
"mode_match": true,
|
||||
"expected_reply_type": null,
|
||||
"reply_match": true,
|
||||
"semantic_pass": true,
|
||||
"route_pass": false,
|
||||
"route_health": "blocked_execution_error",
|
||||
"strict_policy": "route",
|
||||
"strict_pass": false,
|
||||
"selected_recipe": "address_document_type_and_account_section_profile_v1",
|
||||
"missing_required_filters": [],
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"rows_fetched": 0,
|
||||
"rows_matched": 0,
|
||||
"mcp_call_status": "error",
|
||||
"limited_reason_category": "execution_error",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_reason": "normalized_fragment_same",
|
||||
"fallback_rule_hit": null,
|
||||
"debug_payload": {
|
||||
"trace_id": "address-0_1nOMvz1f",
|
||||
"prompt_version": "address_query_runtime_v1",
|
||||
"schema_version": "address_query_runtime_v1",
|
||||
"fallback_type": "partial",
|
||||
"route_summary": null,
|
||||
"fragments": [],
|
||||
"requirements_extracted": [],
|
||||
"coverage_report": {
|
||||
"requirements_total": 0,
|
||||
"requirements_covered": 0,
|
||||
"requirements_uncovered": [],
|
||||
"requirements_partially_covered": [],
|
||||
"clarification_needed_for": [],
|
||||
"out_of_scope_requirements": []
|
||||
},
|
||||
"routes": [],
|
||||
"retrieval_status": [],
|
||||
"retrieval_results": [],
|
||||
"answer_grounding_check": {
|
||||
"status": "partial",
|
||||
"route_subject_match": true,
|
||||
"missing_requirements": [],
|
||||
"reasons": [
|
||||
"address_action_detected",
|
||||
"address_entity_detected",
|
||||
"document_list_signal_detected",
|
||||
"document_type_and_account_section_profile_signal_detected",
|
||||
"{ВнешняяОбработка.MCPToolkit.Форма.Форма.Форма(1989)}: Ошибка при вызове метода контекста (Выполнить): {(10, 24)}: Синтаксическая ошибка\nДвижения.Период <= <<?>>ТЕКУЩАЯДАТА()"
|
||||
],
|
||||
"why_included_summary": [],
|
||||
"selection_reason_summary": []
|
||||
},
|
||||
"dropped_intent_segments": [],
|
||||
"detected_mode": "address_query",
|
||||
"detected_mode_confidence": "high",
|
||||
"query_shape": "DOCUMENT_LIST",
|
||||
"query_shape_confidence": "medium",
|
||||
"detected_intent": "document_type_and_account_section_profile",
|
||||
"detected_intent_confidence": "high",
|
||||
"extracted_filters": {
|
||||
"sort": "period_desc"
|
||||
},
|
||||
"missing_required_filters": [],
|
||||
"selected_recipe": "address_document_type_and_account_section_profile_v1",
|
||||
"mcp_call_status_legacy": "error",
|
||||
"account_scope_mode": "preferred",
|
||||
"account_scope_fallback_applied": false,
|
||||
"anchor_type": "unknown",
|
||||
"anchor_value_raw": null,
|
||||
"anchor_value_resolved": null,
|
||||
"resolver_confidence": "low",
|
||||
"ambiguity_count": 0,
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"mcp_call_status": "error",
|
||||
"rows_fetched": 0,
|
||||
"raw_rows_received": 0,
|
||||
"rows_after_account_scope": 0,
|
||||
"rows_after_recipe_filter": 0,
|
||||
"rows_materialized": 0,
|
||||
"rows_matched": 0,
|
||||
"raw_row_keys_sample": [],
|
||||
"materialization_drop_reason": "none",
|
||||
"account_token_raw": null,
|
||||
"account_token_normalized": null,
|
||||
"account_scope_fields_checked": [
|
||||
"account_dt",
|
||||
"account_kt",
|
||||
"registrator",
|
||||
"analytics"
|
||||
],
|
||||
"account_scope_match_strategy": "account_code_regex_plus_alias_map_v1",
|
||||
"account_scope_drop_reason": "not_applicable",
|
||||
"runtime_readiness": "UNKNOWN",
|
||||
"limited_reason_category": "execution_error",
|
||||
"response_type": "LIMITED_WITH_REASON",
|
||||
"execution_lane": "address_query",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_attempted": true,
|
||||
"llm_provider_used": "local",
|
||||
"llm_decomposition_trace_id": "KAAw7U8orkHpRG",
|
||||
"llm_decomposition_effective_message": "Какие типы документов используются чаще всего в базе?",
|
||||
"llm_decomposition_reason": "normalized_fragment_same",
|
||||
"fallback_rule_hit": null,
|
||||
"sanitized_user_message": "какие типы документов используются чаще всего в базе?",
|
||||
"tool_gate_decision": "run_address_lane",
|
||||
"tool_gate_reason": "address_mode_classifier_detected",
|
||||
"answer_structure_v11": null,
|
||||
"investigation_state_snapshot": null,
|
||||
"normalized": null,
|
||||
"normalizer_output": {
|
||||
"trace_id": "KAAw7U8orkHpRG",
|
||||
"prompt_version": "normalizer_v2_0_2",
|
||||
"applied": false,
|
||||
"effective_message": "Какие типы документов используются чаще всего в базе?"
|
||||
}
|
||||
},
|
||||
"error_code": null,
|
||||
"error_message": null
|
||||
},
|
||||
{
|
||||
"index": 5,
|
||||
"id": "Q5",
|
||||
"question": "Какие разделы учета наиболее заполнены и какие почти не используются?",
|
||||
"session": null,
|
||||
"session_id": "asst-2026-04-02_Address_General5_Live_Check_AfterFix_01-q5",
|
||||
"status_code": 200,
|
||||
"ok": true,
|
||||
"elapsed_ms": 1002,
|
||||
"reply_type": "partial_coverage",
|
||||
"trace_id": "address-0XdEJQTykP",
|
||||
"assistant_reply": "Не удалось выполнить адресный live-запрос в V1.\nПричина: live MCP вызов завершился ошибкой.\nЧто нужно уточнить: {ВнешняяОбработка.MCPToolkit.Форма.Форма.Форма(1989)}: Ошибка при вызове метода контекста (Выполнить): {(10, 24)}: Синтаксическая ошибка\nДвижения.Период <= <<?>>ТЕКУЩАЯДАТА().",
|
||||
"assistant_reply_first_line": "Не удалось выполнить адресный live-запрос в V1.",
|
||||
"expected_intent": "document_type_and_account_section_profile",
|
||||
"actual_intent": "document_type_and_account_section_profile",
|
||||
"intent_match": true,
|
||||
"expected_mode": "address_query",
|
||||
"actual_mode": "address_query",
|
||||
"mode_match": true,
|
||||
"expected_reply_type": null,
|
||||
"reply_match": true,
|
||||
"semantic_pass": true,
|
||||
"route_pass": false,
|
||||
"route_health": "blocked_execution_error",
|
||||
"strict_policy": "route",
|
||||
"strict_pass": false,
|
||||
"selected_recipe": "address_document_type_and_account_section_profile_v1",
|
||||
"missing_required_filters": [],
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"rows_fetched": 0,
|
||||
"rows_matched": 0,
|
||||
"mcp_call_status": "error",
|
||||
"limited_reason_category": "execution_error",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_reason": "not_address_like",
|
||||
"fallback_rule_hit": null,
|
||||
"debug_payload": {
|
||||
"trace_id": "address-0XdEJQTykP",
|
||||
"prompt_version": "address_query_runtime_v1",
|
||||
"schema_version": "address_query_runtime_v1",
|
||||
"fallback_type": "partial",
|
||||
"route_summary": null,
|
||||
"fragments": [],
|
||||
"requirements_extracted": [],
|
||||
"coverage_report": {
|
||||
"requirements_total": 0,
|
||||
"requirements_covered": 0,
|
||||
"requirements_uncovered": [],
|
||||
"requirements_partially_covered": [],
|
||||
"clarification_needed_for": [],
|
||||
"out_of_scope_requirements": []
|
||||
},
|
||||
"routes": [],
|
||||
"retrieval_status": [],
|
||||
"retrieval_results": [],
|
||||
"answer_grounding_check": {
|
||||
"status": "partial",
|
||||
"route_subject_match": true,
|
||||
"missing_requirements": [],
|
||||
"reasons": [
|
||||
"management_profile_signal_detected",
|
||||
"shape_not_detected",
|
||||
"document_type_and_account_section_profile_signal_detected",
|
||||
"{ВнешняяОбработка.MCPToolkit.Форма.Форма.Форма(1989)}: Ошибка при вызове метода контекста (Выполнить): {(10, 24)}: Синтаксическая ошибка\nДвижения.Период <= <<?>>ТЕКУЩАЯДАТА()"
|
||||
],
|
||||
"why_included_summary": [],
|
||||
"selection_reason_summary": []
|
||||
},
|
||||
"dropped_intent_segments": [],
|
||||
"detected_mode": "address_query",
|
||||
"detected_mode_confidence": "medium",
|
||||
"query_shape": "UNKNOWN",
|
||||
"query_shape_confidence": "low",
|
||||
"detected_intent": "document_type_and_account_section_profile",
|
||||
"detected_intent_confidence": "high",
|
||||
"extracted_filters": {
|
||||
"sort": "period_desc"
|
||||
},
|
||||
"missing_required_filters": [],
|
||||
"selected_recipe": "address_document_type_and_account_section_profile_v1",
|
||||
"mcp_call_status_legacy": "error",
|
||||
"account_scope_mode": "preferred",
|
||||
"account_scope_fallback_applied": false,
|
||||
"anchor_type": "unknown",
|
||||
"anchor_value_raw": null,
|
||||
"anchor_value_resolved": null,
|
||||
"resolver_confidence": "low",
|
||||
"ambiguity_count": 0,
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"mcp_call_status": "error",
|
||||
"rows_fetched": 0,
|
||||
"raw_rows_received": 0,
|
||||
"rows_after_account_scope": 0,
|
||||
"rows_after_recipe_filter": 0,
|
||||
"rows_materialized": 0,
|
||||
"rows_matched": 0,
|
||||
"raw_row_keys_sample": [],
|
||||
"materialization_drop_reason": "none",
|
||||
"account_token_raw": null,
|
||||
"account_token_normalized": null,
|
||||
"account_scope_fields_checked": [
|
||||
"account_dt",
|
||||
"account_kt",
|
||||
"registrator",
|
||||
"analytics"
|
||||
],
|
||||
"account_scope_match_strategy": "account_code_regex_plus_alias_map_v1",
|
||||
"account_scope_drop_reason": "not_applicable",
|
||||
"runtime_readiness": "UNKNOWN",
|
||||
"limited_reason_category": "execution_error",
|
||||
"response_type": "LIMITED_WITH_REASON",
|
||||
"execution_lane": "address_query",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_attempted": false,
|
||||
"llm_provider_used": "local",
|
||||
"llm_decomposition_trace_id": null,
|
||||
"llm_decomposition_effective_message": "Какие разделы учета наиболее заполнены и какие почти не используются?",
|
||||
"llm_decomposition_reason": "not_address_like",
|
||||
"fallback_rule_hit": null,
|
||||
"sanitized_user_message": "какие разделы учета наиболее заполнены и какие почти не используются?",
|
||||
"tool_gate_decision": "run_address_lane",
|
||||
"tool_gate_reason": "address_mode_classifier_detected",
|
||||
"answer_structure_v11": null,
|
||||
"investigation_state_snapshot": null,
|
||||
"normalized": null,
|
||||
"normalizer_output": null
|
||||
},
|
||||
"error_code": null,
|
||||
"error_message": null
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,9 @@
|
||||
# Response Audit: 2026-04-02_Address_General5_Live_Check_AfterFix_01
|
||||
|
||||
| id | strict | route_health | reply_type | intent | limited_reason | question | assistant_first_line |
|
||||
|---|---|---|---|---|---|---|---|
|
||||
| Q1 | False | blocked_execution_error | partial_coverage | period_coverage_profile | execution_error | За какие годы в базе есть данные? | Не удалось выполнить адресный live-запрос в V1. |
|
||||
| Q2 | False | blocked_execution_error | partial_coverage | period_coverage_profile | execution_error | Какой год самый активный по количеству документов? | Не удалось выполнить адресный live-запрос в V1. |
|
||||
| Q3 | False | blocked_execution_error | partial_coverage | period_coverage_profile | execution_error | Какой месяц самый активный по количеству операций? | Не удалось выполнить адресный live-запрос в V1. |
|
||||
| Q4 | False | blocked_execution_error | partial_coverage | document_type_and_account_section_profile | execution_error | Какие типы документов используются чаще всего в базе? | Не удалось выполнить адресный live-запрос в V1. |
|
||||
| Q5 | False | blocked_execution_error | partial_coverage | document_type_and_account_section_profile | execution_error | Какие разделы учета наиболее заполнены и какие почти не используются? | Не удалось выполнить адресный live-запрос в V1. |
|
||||
@@ -0,0 +1,47 @@
|
||||
{
|
||||
"run_id": "2026-04-02_Address_General5_Live_Check_AfterFix_01",
|
||||
"generated_at": "2026-04-02T19:27:58",
|
||||
"source_questions_file": "X:\\1C\\NDC_1C\\docs\\ADDRESS\\question_sets\\temp_general5_live_check_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": "route",
|
||||
"totals": {
|
||||
"questions_total": 5,
|
||||
"ok_200_count": 5,
|
||||
"semantic_pass_count": 5,
|
||||
"semantic_pass_rate": 1.0,
|
||||
"route_pass_count": 0,
|
||||
"route_pass_rate": 0.0,
|
||||
"strict_pass_count": 0,
|
||||
"strict_pass_rate": 0.0,
|
||||
"factual_count": 0,
|
||||
"partial_coverage_count": 5,
|
||||
"clarification_required_count": 0,
|
||||
"http_error_count": 0,
|
||||
"llm_decomposition_applied_count": 0,
|
||||
"avg_elapsed_ms": 2632
|
||||
},
|
||||
"distributions": {
|
||||
"reply_type": {
|
||||
"partial_coverage": 5
|
||||
},
|
||||
"actual_intent": {
|
||||
"period_coverage_profile": 3,
|
||||
"document_type_and_account_section_profile": 2
|
||||
},
|
||||
"actual_mode": {
|
||||
"address_query": 5
|
||||
},
|
||||
"mcp_call_status": {
|
||||
"error": 5
|
||||
},
|
||||
"limited_reason_category": {
|
||||
"execution_error": 5
|
||||
},
|
||||
"route_health": {
|
||||
"blocked_execution_error": 5
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,28 @@
|
||||
# 2026-04-02_Address_General5_Live_Check_AfterFix_02
|
||||
|
||||
Generated at: 2026-04-02T19:29:40
|
||||
Questions file: X:\1C\NDC_1C\docs\ADDRESS\question_sets\temp_general5_live_check_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: route
|
||||
|
||||
## Totals
|
||||
- questions_total: 5
|
||||
- ok_200_count: 5
|
||||
- semantic_pass_count: 5
|
||||
- semantic_pass_rate: 1.0
|
||||
- route_pass_count: 5
|
||||
- route_pass_rate: 1.0
|
||||
- strict_pass_count: 5
|
||||
- strict_pass_rate: 1.0
|
||||
- factual_count: 5
|
||||
- partial_coverage_count: 0
|
||||
- clarification_required_count: 0
|
||||
- http_error_count: 0
|
||||
- llm_decomposition_applied_count: 0
|
||||
- avg_elapsed_ms: 3100.6
|
||||
|
||||
## Files
|
||||
- run_summary.json
|
||||
- full_live_results.json
|
||||
- failures_only.json
|
||||
+1
@@ -0,0 +1 @@
|
||||
[]
|
||||
+769
@@ -0,0 +1,769 @@
|
||||
{
|
||||
"run_id": "2026-04-02_Address_General5_Live_Check_AfterFix_02",
|
||||
"generated_at": "2026-04-02T19:29:40",
|
||||
"summary": {
|
||||
"run_id": "2026-04-02_Address_General5_Live_Check_AfterFix_02",
|
||||
"generated_at": "2026-04-02T19:29:40",
|
||||
"source_questions_file": "X:\\1C\\NDC_1C\\docs\\ADDRESS\\question_sets\\temp_general5_live_check_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": "route",
|
||||
"totals": {
|
||||
"questions_total": 5,
|
||||
"ok_200_count": 5,
|
||||
"semantic_pass_count": 5,
|
||||
"semantic_pass_rate": 1.0,
|
||||
"route_pass_count": 5,
|
||||
"route_pass_rate": 1.0,
|
||||
"strict_pass_count": 5,
|
||||
"strict_pass_rate": 1.0,
|
||||
"factual_count": 5,
|
||||
"partial_coverage_count": 0,
|
||||
"clarification_required_count": 0,
|
||||
"http_error_count": 0,
|
||||
"llm_decomposition_applied_count": 0,
|
||||
"avg_elapsed_ms": 3100.6
|
||||
},
|
||||
"distributions": {
|
||||
"reply_type": {
|
||||
"factual": 5
|
||||
},
|
||||
"actual_intent": {
|
||||
"period_coverage_profile": 3,
|
||||
"document_type_and_account_section_profile": 2
|
||||
},
|
||||
"actual_mode": {
|
||||
"address_query": 5
|
||||
},
|
||||
"mcp_call_status": {
|
||||
"matched_non_empty": 5
|
||||
},
|
||||
"limited_reason_category": {},
|
||||
"route_health": {
|
||||
"ok_or_factual": 5
|
||||
}
|
||||
}
|
||||
},
|
||||
"rows": [
|
||||
{
|
||||
"index": 1,
|
||||
"id": "Q1",
|
||||
"question": "За какие годы в базе есть данные?",
|
||||
"session": null,
|
||||
"session_id": "asst-2026-04-02_Address_General5_Live_Check_AfterFix_02-q1",
|
||||
"status_code": 200,
|
||||
"ok": true,
|
||||
"elapsed_ms": 1185,
|
||||
"reply_type": "factual",
|
||||
"trace_id": "address-HfTGzxvrUv",
|
||||
"assistant_reply": "Профиль периодов базы собран (movement-based aggregate).\nСтрок агрегата: 134.\nПокрытие по датам: 2014-05-27T12:00:00Z.. 2026-03-31T00:00:00Z.\nГоды с данными: 2014..2026 (уникальных: 12).\nСамый активный год по документам: 2019 (1004).\nСамый активный месяц по операциям: 2015-02 (1249).\nТоп годов по документам:\n1. 2019: 1004\n2. 2018: 703\n3. 2015: 671\n4. 2016: 577\n5. 2020: 536\nТоп месяцев по операциям:\n1. 2015-02: 1249\n2. 2015-01: 924\n3. 2018-08: 854\n4. 2019-05: 536\n5. 2017-12: 503",
|
||||
"assistant_reply_first_line": "Профиль периодов базы собран (movement-based aggregate).",
|
||||
"expected_intent": "period_coverage_profile",
|
||||
"actual_intent": "period_coverage_profile",
|
||||
"intent_match": true,
|
||||
"expected_mode": "address_query",
|
||||
"actual_mode": "address_query",
|
||||
"mode_match": true,
|
||||
"expected_reply_type": null,
|
||||
"reply_match": true,
|
||||
"semantic_pass": true,
|
||||
"route_pass": true,
|
||||
"route_health": "ok_or_factual",
|
||||
"strict_policy": "route",
|
||||
"strict_pass": true,
|
||||
"selected_recipe": "address_period_coverage_profile_v1",
|
||||
"missing_required_filters": [],
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"rows_fetched": 134,
|
||||
"rows_matched": 134,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"limited_reason_category": null,
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_reason": "not_address_like",
|
||||
"fallback_rule_hit": null,
|
||||
"debug_payload": {
|
||||
"trace_id": "address-HfTGzxvrUv",
|
||||
"prompt_version": "address_query_runtime_v1",
|
||||
"schema_version": "address_query_runtime_v1",
|
||||
"fallback_type": "none",
|
||||
"route_summary": null,
|
||||
"fragments": [],
|
||||
"requirements_extracted": [],
|
||||
"coverage_report": {
|
||||
"requirements_total": 0,
|
||||
"requirements_covered": 0,
|
||||
"requirements_uncovered": [],
|
||||
"requirements_partially_covered": [],
|
||||
"clarification_needed_for": [],
|
||||
"out_of_scope_requirements": []
|
||||
},
|
||||
"routes": [],
|
||||
"retrieval_status": [],
|
||||
"retrieval_results": [],
|
||||
"answer_grounding_check": {
|
||||
"status": "grounded",
|
||||
"route_subject_match": true,
|
||||
"missing_requirements": [],
|
||||
"reasons": [
|
||||
"management_profile_signal_detected",
|
||||
"shape_not_detected",
|
||||
"period_coverage_profile_signal_detected"
|
||||
],
|
||||
"why_included_summary": [],
|
||||
"selection_reason_summary": []
|
||||
},
|
||||
"dropped_intent_segments": [],
|
||||
"detected_mode": "address_query",
|
||||
"detected_mode_confidence": "medium",
|
||||
"query_shape": "UNKNOWN",
|
||||
"query_shape_confidence": "low",
|
||||
"detected_intent": "period_coverage_profile",
|
||||
"detected_intent_confidence": "high",
|
||||
"extracted_filters": {
|
||||
"sort": "period_desc",
|
||||
"period_to": "2026-04-02"
|
||||
},
|
||||
"missing_required_filters": [],
|
||||
"selected_recipe": "address_period_coverage_profile_v1",
|
||||
"mcp_call_status_legacy": "matched_non_empty",
|
||||
"account_scope_mode": "preferred",
|
||||
"account_scope_fallback_applied": false,
|
||||
"anchor_type": "unknown",
|
||||
"anchor_value_raw": null,
|
||||
"anchor_value_resolved": null,
|
||||
"resolver_confidence": "low",
|
||||
"ambiguity_count": 0,
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"rows_fetched": 134,
|
||||
"raw_rows_received": 134,
|
||||
"rows_after_account_scope": 134,
|
||||
"rows_after_recipe_filter": 134,
|
||||
"rows_materialized": 134,
|
||||
"rows_matched": 134,
|
||||
"raw_row_keys_sample": [
|
||||
"Период",
|
||||
"Регистратор",
|
||||
"СчетДт",
|
||||
"СчетКт",
|
||||
"Сумма",
|
||||
"Period",
|
||||
"Registrator",
|
||||
"Amount"
|
||||
],
|
||||
"materialization_drop_reason": "none",
|
||||
"account_token_raw": null,
|
||||
"account_token_normalized": null,
|
||||
"account_scope_fields_checked": [
|
||||
"account_dt",
|
||||
"account_kt",
|
||||
"registrator",
|
||||
"analytics"
|
||||
],
|
||||
"account_scope_match_strategy": "account_code_regex_plus_alias_map_v1",
|
||||
"account_scope_drop_reason": "not_applicable",
|
||||
"runtime_readiness": "LIVE_QUERYABLE_WITH_LIMITS",
|
||||
"limited_reason_category": null,
|
||||
"response_type": "FACTUAL_SUMMARY",
|
||||
"execution_lane": "address_query",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_attempted": false,
|
||||
"llm_provider_used": "local",
|
||||
"llm_decomposition_trace_id": null,
|
||||
"llm_decomposition_effective_message": "За какие годы в базе есть данные?",
|
||||
"llm_decomposition_reason": "not_address_like",
|
||||
"fallback_rule_hit": null,
|
||||
"sanitized_user_message": "за какие годы в базе есть данные?",
|
||||
"tool_gate_decision": "run_address_lane",
|
||||
"tool_gate_reason": "address_mode_classifier_detected",
|
||||
"answer_structure_v11": null,
|
||||
"investigation_state_snapshot": null,
|
||||
"normalized": null,
|
||||
"normalizer_output": null
|
||||
},
|
||||
"error_code": null,
|
||||
"error_message": null
|
||||
},
|
||||
{
|
||||
"index": 2,
|
||||
"id": "Q2",
|
||||
"question": "Какой год самый активный по количеству документов?",
|
||||
"session": null,
|
||||
"session_id": "asst-2026-04-02_Address_General5_Live_Check_AfterFix_02-q2",
|
||||
"status_code": 200,
|
||||
"ok": true,
|
||||
"elapsed_ms": 6159,
|
||||
"reply_type": "factual",
|
||||
"trace_id": "address-AL_CR3C1wQ",
|
||||
"assistant_reply": "Профиль периодов базы собран (movement-based aggregate).\nСтрок агрегата: 134.\nПокрытие по датам: 2014-05-27T12:00:00Z.. 2026-03-31T00:00:00Z.\nГоды с данными: 2014..2026 (уникальных: 12).\nСамый активный год по документам: 2019 (1004).\nСамый активный месяц по операциям: 2015-02 (1249).\nТоп годов по документам:\n1. 2019: 1004\n2. 2018: 703\n3. 2015: 671\n4. 2016: 577\n5. 2020: 536\nТоп месяцев по операциям:\n1. 2015-02: 1249\n2. 2015-01: 924\n3. 2018-08: 854\n4. 2019-05: 536\n5. 2017-12: 503",
|
||||
"assistant_reply_first_line": "Профиль периодов базы собран (movement-based aggregate).",
|
||||
"expected_intent": "period_coverage_profile",
|
||||
"actual_intent": "period_coverage_profile",
|
||||
"intent_match": true,
|
||||
"expected_mode": "address_query",
|
||||
"actual_mode": "address_query",
|
||||
"mode_match": true,
|
||||
"expected_reply_type": null,
|
||||
"reply_match": true,
|
||||
"semantic_pass": true,
|
||||
"route_pass": true,
|
||||
"route_health": "ok_or_factual",
|
||||
"strict_policy": "route",
|
||||
"strict_pass": true,
|
||||
"selected_recipe": "address_period_coverage_profile_v1",
|
||||
"missing_required_filters": [],
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"rows_fetched": 134,
|
||||
"rows_matched": 134,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"limited_reason_category": null,
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_reason": "normalized_fragment_rejected_intent_conflict",
|
||||
"fallback_rule_hit": null,
|
||||
"debug_payload": {
|
||||
"trace_id": "address-AL_CR3C1wQ",
|
||||
"prompt_version": "address_query_runtime_v1",
|
||||
"schema_version": "address_query_runtime_v1",
|
||||
"fallback_type": "none",
|
||||
"route_summary": null,
|
||||
"fragments": [],
|
||||
"requirements_extracted": [],
|
||||
"coverage_report": {
|
||||
"requirements_total": 0,
|
||||
"requirements_covered": 0,
|
||||
"requirements_uncovered": [],
|
||||
"requirements_partially_covered": [],
|
||||
"clarification_needed_for": [],
|
||||
"out_of_scope_requirements": []
|
||||
},
|
||||
"routes": [],
|
||||
"retrieval_status": [],
|
||||
"retrieval_results": [],
|
||||
"answer_grounding_check": {
|
||||
"status": "grounded",
|
||||
"route_subject_match": true,
|
||||
"missing_requirements": [],
|
||||
"reasons": [
|
||||
"management_profile_signal_detected",
|
||||
"document_list_signal_detected",
|
||||
"period_coverage_profile_signal_detected"
|
||||
],
|
||||
"why_included_summary": [],
|
||||
"selection_reason_summary": []
|
||||
},
|
||||
"dropped_intent_segments": [],
|
||||
"detected_mode": "address_query",
|
||||
"detected_mode_confidence": "medium",
|
||||
"query_shape": "DOCUMENT_LIST",
|
||||
"query_shape_confidence": "medium",
|
||||
"detected_intent": "period_coverage_profile",
|
||||
"detected_intent_confidence": "high",
|
||||
"extracted_filters": {
|
||||
"sort": "period_desc",
|
||||
"period_to": "2026-04-02"
|
||||
},
|
||||
"missing_required_filters": [],
|
||||
"selected_recipe": "address_period_coverage_profile_v1",
|
||||
"mcp_call_status_legacy": "matched_non_empty",
|
||||
"account_scope_mode": "preferred",
|
||||
"account_scope_fallback_applied": false,
|
||||
"anchor_type": "unknown",
|
||||
"anchor_value_raw": null,
|
||||
"anchor_value_resolved": null,
|
||||
"resolver_confidence": "low",
|
||||
"ambiguity_count": 0,
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"rows_fetched": 134,
|
||||
"raw_rows_received": 134,
|
||||
"rows_after_account_scope": 134,
|
||||
"rows_after_recipe_filter": 134,
|
||||
"rows_materialized": 134,
|
||||
"rows_matched": 134,
|
||||
"raw_row_keys_sample": [
|
||||
"Период",
|
||||
"Регистратор",
|
||||
"СчетДт",
|
||||
"СчетКт",
|
||||
"Сумма",
|
||||
"Period",
|
||||
"Registrator",
|
||||
"Amount"
|
||||
],
|
||||
"materialization_drop_reason": "none",
|
||||
"account_token_raw": null,
|
||||
"account_token_normalized": null,
|
||||
"account_scope_fields_checked": [
|
||||
"account_dt",
|
||||
"account_kt",
|
||||
"registrator",
|
||||
"analytics"
|
||||
],
|
||||
"account_scope_match_strategy": "account_code_regex_plus_alias_map_v1",
|
||||
"account_scope_drop_reason": "not_applicable",
|
||||
"runtime_readiness": "LIVE_QUERYABLE_WITH_LIMITS",
|
||||
"limited_reason_category": null,
|
||||
"response_type": "FACTUAL_SUMMARY",
|
||||
"execution_lane": "address_query",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_attempted": true,
|
||||
"llm_provider_used": "local",
|
||||
"llm_decomposition_trace_id": "rAUqIM9N9BsIJV",
|
||||
"llm_decomposition_effective_message": "Какой год самый активный по количеству документов?",
|
||||
"llm_decomposition_reason": "normalized_fragment_rejected_intent_conflict",
|
||||
"fallback_rule_hit": null,
|
||||
"sanitized_user_message": "какой год самый активный по количеству документов?",
|
||||
"tool_gate_decision": "run_address_lane",
|
||||
"tool_gate_reason": "address_mode_classifier_detected",
|
||||
"answer_structure_v11": null,
|
||||
"investigation_state_snapshot": null,
|
||||
"normalized": null,
|
||||
"normalizer_output": {
|
||||
"trace_id": "rAUqIM9N9BsIJV",
|
||||
"prompt_version": "normalizer_v2_0_2",
|
||||
"applied": false,
|
||||
"effective_message": "Какой год самый активный по количеству документов?"
|
||||
}
|
||||
},
|
||||
"error_code": null,
|
||||
"error_message": null
|
||||
},
|
||||
{
|
||||
"index": 3,
|
||||
"id": "Q3",
|
||||
"question": "Какой месяц самый активный по количеству операций?",
|
||||
"session": null,
|
||||
"session_id": "asst-2026-04-02_Address_General5_Live_Check_AfterFix_02-q3",
|
||||
"status_code": 200,
|
||||
"ok": true,
|
||||
"elapsed_ms": 980,
|
||||
"reply_type": "factual",
|
||||
"trace_id": "address-s1bNIMxNTL",
|
||||
"assistant_reply": "Профиль периодов базы собран (movement-based aggregate).\nСтрок агрегата: 134.\nПокрытие по датам: 2014-05-27T12:00:00Z.. 2026-03-31T00:00:00Z.\nГоды с данными: 2014..2026 (уникальных: 12).\nСамый активный год по документам: 2019 (1004).\nСамый активный месяц по операциям: 2015-02 (1249).\nТоп годов по документам:\n1. 2019: 1004\n2. 2018: 703\n3. 2015: 671\n4. 2016: 577\n5. 2020: 536\nТоп месяцев по операциям:\n1. 2015-02: 1249\n2. 2015-01: 924\n3. 2018-08: 854\n4. 2019-05: 536\n5. 2017-12: 503",
|
||||
"assistant_reply_first_line": "Профиль периодов базы собран (movement-based aggregate).",
|
||||
"expected_intent": "period_coverage_profile",
|
||||
"actual_intent": "period_coverage_profile",
|
||||
"intent_match": true,
|
||||
"expected_mode": "address_query",
|
||||
"actual_mode": "address_query",
|
||||
"mode_match": true,
|
||||
"expected_reply_type": null,
|
||||
"reply_match": true,
|
||||
"semantic_pass": true,
|
||||
"route_pass": true,
|
||||
"route_health": "ok_or_factual",
|
||||
"strict_policy": "route",
|
||||
"strict_pass": true,
|
||||
"selected_recipe": "address_period_coverage_profile_v1",
|
||||
"missing_required_filters": [],
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"rows_fetched": 134,
|
||||
"rows_matched": 134,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"limited_reason_category": null,
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_reason": "not_address_like",
|
||||
"fallback_rule_hit": null,
|
||||
"debug_payload": {
|
||||
"trace_id": "address-s1bNIMxNTL",
|
||||
"prompt_version": "address_query_runtime_v1",
|
||||
"schema_version": "address_query_runtime_v1",
|
||||
"fallback_type": "none",
|
||||
"route_summary": null,
|
||||
"fragments": [],
|
||||
"requirements_extracted": [],
|
||||
"coverage_report": {
|
||||
"requirements_total": 0,
|
||||
"requirements_covered": 0,
|
||||
"requirements_uncovered": [],
|
||||
"requirements_partially_covered": [],
|
||||
"clarification_needed_for": [],
|
||||
"out_of_scope_requirements": []
|
||||
},
|
||||
"routes": [],
|
||||
"retrieval_status": [],
|
||||
"retrieval_results": [],
|
||||
"answer_grounding_check": {
|
||||
"status": "grounded",
|
||||
"route_subject_match": true,
|
||||
"missing_requirements": [],
|
||||
"reasons": [
|
||||
"management_profile_signal_detected",
|
||||
"shape_not_detected",
|
||||
"period_coverage_profile_signal_detected"
|
||||
],
|
||||
"why_included_summary": [],
|
||||
"selection_reason_summary": []
|
||||
},
|
||||
"dropped_intent_segments": [],
|
||||
"detected_mode": "address_query",
|
||||
"detected_mode_confidence": "medium",
|
||||
"query_shape": "UNKNOWN",
|
||||
"query_shape_confidence": "low",
|
||||
"detected_intent": "period_coverage_profile",
|
||||
"detected_intent_confidence": "high",
|
||||
"extracted_filters": {
|
||||
"sort": "period_desc",
|
||||
"period_to": "2026-04-02"
|
||||
},
|
||||
"missing_required_filters": [],
|
||||
"selected_recipe": "address_period_coverage_profile_v1",
|
||||
"mcp_call_status_legacy": "matched_non_empty",
|
||||
"account_scope_mode": "preferred",
|
||||
"account_scope_fallback_applied": false,
|
||||
"anchor_type": "unknown",
|
||||
"anchor_value_raw": null,
|
||||
"anchor_value_resolved": null,
|
||||
"resolver_confidence": "low",
|
||||
"ambiguity_count": 0,
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"rows_fetched": 134,
|
||||
"raw_rows_received": 134,
|
||||
"rows_after_account_scope": 134,
|
||||
"rows_after_recipe_filter": 134,
|
||||
"rows_materialized": 134,
|
||||
"rows_matched": 134,
|
||||
"raw_row_keys_sample": [
|
||||
"Период",
|
||||
"Регистратор",
|
||||
"СчетДт",
|
||||
"СчетКт",
|
||||
"Сумма",
|
||||
"Period",
|
||||
"Registrator",
|
||||
"Amount"
|
||||
],
|
||||
"materialization_drop_reason": "none",
|
||||
"account_token_raw": null,
|
||||
"account_token_normalized": null,
|
||||
"account_scope_fields_checked": [
|
||||
"account_dt",
|
||||
"account_kt",
|
||||
"registrator",
|
||||
"analytics"
|
||||
],
|
||||
"account_scope_match_strategy": "account_code_regex_plus_alias_map_v1",
|
||||
"account_scope_drop_reason": "not_applicable",
|
||||
"runtime_readiness": "LIVE_QUERYABLE_WITH_LIMITS",
|
||||
"limited_reason_category": null,
|
||||
"response_type": "FACTUAL_SUMMARY",
|
||||
"execution_lane": "address_query",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_attempted": false,
|
||||
"llm_provider_used": "local",
|
||||
"llm_decomposition_trace_id": null,
|
||||
"llm_decomposition_effective_message": "Какой месяц самый активный по количеству операций?",
|
||||
"llm_decomposition_reason": "not_address_like",
|
||||
"fallback_rule_hit": null,
|
||||
"sanitized_user_message": "какой месяц самый активный по количеству операций?",
|
||||
"tool_gate_decision": "run_address_lane",
|
||||
"tool_gate_reason": "address_mode_classifier_detected",
|
||||
"answer_structure_v11": null,
|
||||
"investigation_state_snapshot": null,
|
||||
"normalized": null,
|
||||
"normalizer_output": null
|
||||
},
|
||||
"error_code": null,
|
||||
"error_message": null
|
||||
},
|
||||
{
|
||||
"index": 4,
|
||||
"id": "Q4",
|
||||
"question": "Какие типы документов используются чаще всего в базе?",
|
||||
"session": null,
|
||||
"session_id": "asst-2026-04-02_Address_General5_Live_Check_AfterFix_02-q4",
|
||||
"status_code": 200,
|
||||
"ok": true,
|
||||
"elapsed_ms": 6282,
|
||||
"reply_type": "factual",
|
||||
"trace_id": "address-UVGdY-3_VN",
|
||||
"assistant_reply": "Профиль типов документов и разделов учета собран (movement-based aggregate).\nСтрок агрегата: 147.\nТоп типов документов (по числу уникальных регистраторов):\n1. Списание с расчетного счета: 2352 (52.6%)\n2. Поступление товаров и услуг: 486 (10.9%)\n3. Регламентная операция: 414 (9.3%)\n4. Поступление на расчетный счет: 323 (7.2%)\n5. Счет-фактура полученный: 261 (5.8%)\n6. Операция (бухгалтерский и налоговый учет): 147 (3.3%)\n7. Реализация товаров и услуг: 123 (2.8%)\n8. Отражение зарплаты в регламентированном учете: 87 (1.9%)\n9. Приходный кассовый ордер: 76 (1.7%)\n10. Расходный кассовый ордер: 73 (1.6%)\nНаиболее заполненные разделы учета (по операциям Дт+Кт):\n1. 90 (Продажи): 2973 (12.1%)\n2. 51 (Расчетные счета): 2967 (12.1%)\n3. 60 (Расчеты с поставщиками и подрядчиками): 2793 (11.4%)\n4. 44 (Расходы на продажу): 2422 (9.9%)\n5. 68 (Расчеты по налогам и сборам): 1553 (6.3%)\n6. 10 (Материалы): 1494 (6.1%)\n7. 19 (НДС по приобретенным ценностям): 1489 (6.1%)\n8. 91 (Прочие доходы и расходы): 1324 (5.4%)\n9. 41 (Товары): 1312 (5.3%)\n10. 76 (Расчеты с разными дебиторами и кредиторами): 1240 (5.0%)\nРазделы с минимальной активностью (среди использованных):\n1. 58 (Финансовые вложения): 2\n2. 81 (Собственные акции (доли)): 2\n3. 80 (Уставный капитал): 5\n4. 03: 6\n5. 04 (Нематериальные активы): 6\n6. 75 (Расчеты с учредителями): 16\n7. 55 (Специальные счета в банках): 18\n8. 84 (Нераспределенная прибыль (непокрытый убыток)): 20\n9. 26 (Общехозяйственные расходы): 51\n10. 71 (Расчеты с подотчетными лицами): 76",
|
||||
"assistant_reply_first_line": "Профиль типов документов и разделов учета собран (movement-based aggregate).",
|
||||
"expected_intent": "document_type_and_account_section_profile",
|
||||
"actual_intent": "document_type_and_account_section_profile",
|
||||
"intent_match": true,
|
||||
"expected_mode": "address_query",
|
||||
"actual_mode": "address_query",
|
||||
"mode_match": true,
|
||||
"expected_reply_type": null,
|
||||
"reply_match": true,
|
||||
"semantic_pass": true,
|
||||
"route_pass": true,
|
||||
"route_health": "ok_or_factual",
|
||||
"strict_policy": "route",
|
||||
"strict_pass": true,
|
||||
"selected_recipe": "address_document_type_and_account_section_profile_v1",
|
||||
"missing_required_filters": [],
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"rows_fetched": 147,
|
||||
"rows_matched": 147,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"limited_reason_category": null,
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_reason": "normalized_fragment_same",
|
||||
"fallback_rule_hit": null,
|
||||
"debug_payload": {
|
||||
"trace_id": "address-UVGdY-3_VN",
|
||||
"prompt_version": "address_query_runtime_v1",
|
||||
"schema_version": "address_query_runtime_v1",
|
||||
"fallback_type": "none",
|
||||
"route_summary": null,
|
||||
"fragments": [],
|
||||
"requirements_extracted": [],
|
||||
"coverage_report": {
|
||||
"requirements_total": 0,
|
||||
"requirements_covered": 0,
|
||||
"requirements_uncovered": [],
|
||||
"requirements_partially_covered": [],
|
||||
"clarification_needed_for": [],
|
||||
"out_of_scope_requirements": []
|
||||
},
|
||||
"routes": [],
|
||||
"retrieval_status": [],
|
||||
"retrieval_results": [],
|
||||
"answer_grounding_check": {
|
||||
"status": "grounded",
|
||||
"route_subject_match": true,
|
||||
"missing_requirements": [],
|
||||
"reasons": [
|
||||
"address_action_detected",
|
||||
"address_entity_detected",
|
||||
"document_list_signal_detected",
|
||||
"document_type_and_account_section_profile_signal_detected"
|
||||
],
|
||||
"why_included_summary": [],
|
||||
"selection_reason_summary": []
|
||||
},
|
||||
"dropped_intent_segments": [],
|
||||
"detected_mode": "address_query",
|
||||
"detected_mode_confidence": "high",
|
||||
"query_shape": "DOCUMENT_LIST",
|
||||
"query_shape_confidence": "medium",
|
||||
"detected_intent": "document_type_and_account_section_profile",
|
||||
"detected_intent_confidence": "high",
|
||||
"extracted_filters": {
|
||||
"sort": "period_desc",
|
||||
"period_to": "2026-04-02"
|
||||
},
|
||||
"missing_required_filters": [],
|
||||
"selected_recipe": "address_document_type_and_account_section_profile_v1",
|
||||
"mcp_call_status_legacy": "matched_non_empty",
|
||||
"account_scope_mode": "preferred",
|
||||
"account_scope_fallback_applied": false,
|
||||
"anchor_type": "unknown",
|
||||
"anchor_value_raw": null,
|
||||
"anchor_value_resolved": null,
|
||||
"resolver_confidence": "low",
|
||||
"ambiguity_count": 0,
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"rows_fetched": 147,
|
||||
"raw_rows_received": 147,
|
||||
"rows_after_account_scope": 147,
|
||||
"rows_after_recipe_filter": 147,
|
||||
"rows_materialized": 147,
|
||||
"rows_matched": 147,
|
||||
"raw_row_keys_sample": [
|
||||
"Период",
|
||||
"Регистратор",
|
||||
"СчетДт",
|
||||
"СчетКт",
|
||||
"Сумма",
|
||||
"Period",
|
||||
"Registrator",
|
||||
"AccountDt",
|
||||
"Amount"
|
||||
],
|
||||
"materialization_drop_reason": "none",
|
||||
"account_token_raw": null,
|
||||
"account_token_normalized": null,
|
||||
"account_scope_fields_checked": [
|
||||
"account_dt",
|
||||
"account_kt",
|
||||
"registrator",
|
||||
"analytics"
|
||||
],
|
||||
"account_scope_match_strategy": "account_code_regex_plus_alias_map_v1",
|
||||
"account_scope_drop_reason": "not_applicable",
|
||||
"runtime_readiness": "LIVE_QUERYABLE_WITH_LIMITS",
|
||||
"limited_reason_category": null,
|
||||
"response_type": "FACTUAL_SUMMARY",
|
||||
"execution_lane": "address_query",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_attempted": true,
|
||||
"llm_provider_used": "local",
|
||||
"llm_decomposition_trace_id": "jQJYufBVkLJJHx",
|
||||
"llm_decomposition_effective_message": "Какие типы документов используются чаще всего в базе?",
|
||||
"llm_decomposition_reason": "normalized_fragment_same",
|
||||
"fallback_rule_hit": null,
|
||||
"sanitized_user_message": "какие типы документов используются чаще всего в базе?",
|
||||
"tool_gate_decision": "run_address_lane",
|
||||
"tool_gate_reason": "address_mode_classifier_detected",
|
||||
"answer_structure_v11": null,
|
||||
"investigation_state_snapshot": null,
|
||||
"normalized": null,
|
||||
"normalizer_output": {
|
||||
"trace_id": "jQJYufBVkLJJHx",
|
||||
"prompt_version": "normalizer_v2_0_2",
|
||||
"applied": false,
|
||||
"effective_message": "Какие типы документов используются чаще всего в базе?"
|
||||
}
|
||||
},
|
||||
"error_code": null,
|
||||
"error_message": null
|
||||
},
|
||||
{
|
||||
"index": 5,
|
||||
"id": "Q5",
|
||||
"question": "Какие разделы учета наиболее заполнены и какие почти не используются?",
|
||||
"session": null,
|
||||
"session_id": "asst-2026-04-02_Address_General5_Live_Check_AfterFix_02-q5",
|
||||
"status_code": 200,
|
||||
"ok": true,
|
||||
"elapsed_ms": 897,
|
||||
"reply_type": "factual",
|
||||
"trace_id": "address--3Oc-f_Szc",
|
||||
"assistant_reply": "Профиль типов документов и разделов учета собран (movement-based aggregate).\nСтрок агрегата: 147.\nТоп типов документов (по числу уникальных регистраторов):\n1. Списание с расчетного счета: 2352 (52.6%)\n2. Поступление товаров и услуг: 486 (10.9%)\n3. Регламентная операция: 414 (9.3%)\n4. Поступление на расчетный счет: 323 (7.2%)\n5. Счет-фактура полученный: 261 (5.8%)\n6. Операция (бухгалтерский и налоговый учет): 147 (3.3%)\n7. Реализация товаров и услуг: 123 (2.8%)\n8. Отражение зарплаты в регламентированном учете: 87 (1.9%)\n9. Приходный кассовый ордер: 76 (1.7%)\n10. Расходный кассовый ордер: 73 (1.6%)\nНаиболее заполненные разделы учета (по операциям Дт+Кт):\n1. 90 (Продажи): 2973 (12.1%)\n2. 51 (Расчетные счета): 2967 (12.1%)\n3. 60 (Расчеты с поставщиками и подрядчиками): 2793 (11.4%)\n4. 44 (Расходы на продажу): 2422 (9.9%)\n5. 68 (Расчеты по налогам и сборам): 1553 (6.3%)\n6. 10 (Материалы): 1494 (6.1%)\n7. 19 (НДС по приобретенным ценностям): 1489 (6.1%)\n8. 91 (Прочие доходы и расходы): 1324 (5.4%)\n9. 41 (Товары): 1312 (5.3%)\n10. 76 (Расчеты с разными дебиторами и кредиторами): 1240 (5.0%)\nРазделы с минимальной активностью (среди использованных):\n1. 58 (Финансовые вложения): 2\n2. 81 (Собственные акции (доли)): 2\n3. 80 (Уставный капитал): 5\n4. 03: 6\n5. 04 (Нематериальные активы): 6\n6. 75 (Расчеты с учредителями): 16\n7. 55 (Специальные счета в банках): 18\n8. 84 (Нераспределенная прибыль (непокрытый убыток)): 20\n9. 26 (Общехозяйственные расходы): 51\n10. 71 (Расчеты с подотчетными лицами): 76",
|
||||
"assistant_reply_first_line": "Профиль типов документов и разделов учета собран (movement-based aggregate).",
|
||||
"expected_intent": "document_type_and_account_section_profile",
|
||||
"actual_intent": "document_type_and_account_section_profile",
|
||||
"intent_match": true,
|
||||
"expected_mode": "address_query",
|
||||
"actual_mode": "address_query",
|
||||
"mode_match": true,
|
||||
"expected_reply_type": null,
|
||||
"reply_match": true,
|
||||
"semantic_pass": true,
|
||||
"route_pass": true,
|
||||
"route_health": "ok_or_factual",
|
||||
"strict_policy": "route",
|
||||
"strict_pass": true,
|
||||
"selected_recipe": "address_document_type_and_account_section_profile_v1",
|
||||
"missing_required_filters": [],
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"rows_fetched": 147,
|
||||
"rows_matched": 147,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"limited_reason_category": null,
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_reason": "not_address_like",
|
||||
"fallback_rule_hit": null,
|
||||
"debug_payload": {
|
||||
"trace_id": "address--3Oc-f_Szc",
|
||||
"prompt_version": "address_query_runtime_v1",
|
||||
"schema_version": "address_query_runtime_v1",
|
||||
"fallback_type": "none",
|
||||
"route_summary": null,
|
||||
"fragments": [],
|
||||
"requirements_extracted": [],
|
||||
"coverage_report": {
|
||||
"requirements_total": 0,
|
||||
"requirements_covered": 0,
|
||||
"requirements_uncovered": [],
|
||||
"requirements_partially_covered": [],
|
||||
"clarification_needed_for": [],
|
||||
"out_of_scope_requirements": []
|
||||
},
|
||||
"routes": [],
|
||||
"retrieval_status": [],
|
||||
"retrieval_results": [],
|
||||
"answer_grounding_check": {
|
||||
"status": "grounded",
|
||||
"route_subject_match": true,
|
||||
"missing_requirements": [],
|
||||
"reasons": [
|
||||
"management_profile_signal_detected",
|
||||
"shape_not_detected",
|
||||
"document_type_and_account_section_profile_signal_detected"
|
||||
],
|
||||
"why_included_summary": [],
|
||||
"selection_reason_summary": []
|
||||
},
|
||||
"dropped_intent_segments": [],
|
||||
"detected_mode": "address_query",
|
||||
"detected_mode_confidence": "medium",
|
||||
"query_shape": "UNKNOWN",
|
||||
"query_shape_confidence": "low",
|
||||
"detected_intent": "document_type_and_account_section_profile",
|
||||
"detected_intent_confidence": "high",
|
||||
"extracted_filters": {
|
||||
"sort": "period_desc",
|
||||
"period_to": "2026-04-02"
|
||||
},
|
||||
"missing_required_filters": [],
|
||||
"selected_recipe": "address_document_type_and_account_section_profile_v1",
|
||||
"mcp_call_status_legacy": "matched_non_empty",
|
||||
"account_scope_mode": "preferred",
|
||||
"account_scope_fallback_applied": false,
|
||||
"anchor_type": "unknown",
|
||||
"anchor_value_raw": null,
|
||||
"anchor_value_resolved": null,
|
||||
"resolver_confidence": "low",
|
||||
"ambiguity_count": 0,
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"rows_fetched": 147,
|
||||
"raw_rows_received": 147,
|
||||
"rows_after_account_scope": 147,
|
||||
"rows_after_recipe_filter": 147,
|
||||
"rows_materialized": 147,
|
||||
"rows_matched": 147,
|
||||
"raw_row_keys_sample": [
|
||||
"Период",
|
||||
"Регистратор",
|
||||
"СчетДт",
|
||||
"СчетКт",
|
||||
"Сумма",
|
||||
"Period",
|
||||
"Registrator",
|
||||
"AccountDt",
|
||||
"Amount"
|
||||
],
|
||||
"materialization_drop_reason": "none",
|
||||
"account_token_raw": null,
|
||||
"account_token_normalized": null,
|
||||
"account_scope_fields_checked": [
|
||||
"account_dt",
|
||||
"account_kt",
|
||||
"registrator",
|
||||
"analytics"
|
||||
],
|
||||
"account_scope_match_strategy": "account_code_regex_plus_alias_map_v1",
|
||||
"account_scope_drop_reason": "not_applicable",
|
||||
"runtime_readiness": "LIVE_QUERYABLE_WITH_LIMITS",
|
||||
"limited_reason_category": null,
|
||||
"response_type": "FACTUAL_SUMMARY",
|
||||
"execution_lane": "address_query",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_attempted": false,
|
||||
"llm_provider_used": "local",
|
||||
"llm_decomposition_trace_id": null,
|
||||
"llm_decomposition_effective_message": "Какие разделы учета наиболее заполнены и какие почти не используются?",
|
||||
"llm_decomposition_reason": "not_address_like",
|
||||
"fallback_rule_hit": null,
|
||||
"sanitized_user_message": "какие разделы учета наиболее заполнены и какие почти не используются?",
|
||||
"tool_gate_decision": "run_address_lane",
|
||||
"tool_gate_reason": "address_mode_classifier_detected",
|
||||
"answer_structure_v11": null,
|
||||
"investigation_state_snapshot": null,
|
||||
"normalized": null,
|
||||
"normalizer_output": null
|
||||
},
|
||||
"error_code": null,
|
||||
"error_message": null
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,9 @@
|
||||
# Response Audit: 2026-04-02_Address_General5_Live_Check_AfterFix_02
|
||||
|
||||
| id | strict | route_health | reply_type | intent | limited_reason | question | assistant_first_line |
|
||||
|---|---|---|---|---|---|---|---|
|
||||
| Q1 | True | ok_or_factual | factual | period_coverage_profile | None | За какие годы в базе есть данные? | Профиль периодов базы собран (movement-based aggregate). |
|
||||
| Q2 | True | ok_or_factual | factual | period_coverage_profile | None | Какой год самый активный по количеству документов? | Профиль периодов базы собран (movement-based aggregate). |
|
||||
| Q3 | True | ok_or_factual | factual | period_coverage_profile | None | Какой месяц самый активный по количеству операций? | Профиль периодов базы собран (movement-based aggregate). |
|
||||
| Q4 | True | ok_or_factual | factual | document_type_and_account_section_profile | None | Какие типы документов используются чаще всего в базе? | Профиль типов документов и разделов учета собран (movement-based aggregate). |
|
||||
| Q5 | True | ok_or_factual | factual | document_type_and_account_section_profile | None | Какие разделы учета наиболее заполнены и какие почти не используются? | Профиль типов документов и разделов учета собран (movement-based aggregate). |
|
||||
@@ -0,0 +1,45 @@
|
||||
{
|
||||
"run_id": "2026-04-02_Address_General5_Live_Check_AfterFix_02",
|
||||
"generated_at": "2026-04-02T19:29:40",
|
||||
"source_questions_file": "X:\\1C\\NDC_1C\\docs\\ADDRESS\\question_sets\\temp_general5_live_check_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": "route",
|
||||
"totals": {
|
||||
"questions_total": 5,
|
||||
"ok_200_count": 5,
|
||||
"semantic_pass_count": 5,
|
||||
"semantic_pass_rate": 1.0,
|
||||
"route_pass_count": 5,
|
||||
"route_pass_rate": 1.0,
|
||||
"strict_pass_count": 5,
|
||||
"strict_pass_rate": 1.0,
|
||||
"factual_count": 5,
|
||||
"partial_coverage_count": 0,
|
||||
"clarification_required_count": 0,
|
||||
"http_error_count": 0,
|
||||
"llm_decomposition_applied_count": 0,
|
||||
"avg_elapsed_ms": 3100.6
|
||||
},
|
||||
"distributions": {
|
||||
"reply_type": {
|
||||
"factual": 5
|
||||
},
|
||||
"actual_intent": {
|
||||
"period_coverage_profile": 3,
|
||||
"document_type_and_account_section_profile": 2
|
||||
},
|
||||
"actual_mode": {
|
||||
"address_query": 5
|
||||
},
|
||||
"mcp_call_status": {
|
||||
"matched_non_empty": 5
|
||||
},
|
||||
"limited_reason_category": {},
|
||||
"route_health": {
|
||||
"ok_or_factual": 5
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,28 @@
|
||||
# 2026-04-02_Address_General5_Live_Check_AfterFix_03
|
||||
|
||||
Generated at: 2026-04-02T19:45:20
|
||||
Questions file: X:\1C\NDC_1C\docs\ADDRESS\question_sets\temp_general5_live_check_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: route
|
||||
|
||||
## Totals
|
||||
- questions_total: 5
|
||||
- ok_200_count: 5
|
||||
- semantic_pass_count: 5
|
||||
- semantic_pass_rate: 1.0
|
||||
- route_pass_count: 5
|
||||
- route_pass_rate: 1.0
|
||||
- strict_pass_count: 5
|
||||
- strict_pass_rate: 1.0
|
||||
- factual_count: 5
|
||||
- partial_coverage_count: 0
|
||||
- clarification_required_count: 0
|
||||
- http_error_count: 0
|
||||
- llm_decomposition_applied_count: 0
|
||||
- avg_elapsed_ms: 2805.8
|
||||
|
||||
## Files
|
||||
- run_summary.json
|
||||
- full_live_results.json
|
||||
- failures_only.json
|
||||
+1
@@ -0,0 +1 @@
|
||||
[]
|
||||
+769
@@ -0,0 +1,769 @@
|
||||
{
|
||||
"run_id": "2026-04-02_Address_General5_Live_Check_AfterFix_03",
|
||||
"generated_at": "2026-04-02T19:45:20",
|
||||
"summary": {
|
||||
"run_id": "2026-04-02_Address_General5_Live_Check_AfterFix_03",
|
||||
"generated_at": "2026-04-02T19:45:20",
|
||||
"source_questions_file": "X:\\1C\\NDC_1C\\docs\\ADDRESS\\question_sets\\temp_general5_live_check_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": "route",
|
||||
"totals": {
|
||||
"questions_total": 5,
|
||||
"ok_200_count": 5,
|
||||
"semantic_pass_count": 5,
|
||||
"semantic_pass_rate": 1.0,
|
||||
"route_pass_count": 5,
|
||||
"route_pass_rate": 1.0,
|
||||
"strict_pass_count": 5,
|
||||
"strict_pass_rate": 1.0,
|
||||
"factual_count": 5,
|
||||
"partial_coverage_count": 0,
|
||||
"clarification_required_count": 0,
|
||||
"http_error_count": 0,
|
||||
"llm_decomposition_applied_count": 0,
|
||||
"avg_elapsed_ms": 2805.8
|
||||
},
|
||||
"distributions": {
|
||||
"reply_type": {
|
||||
"factual": 5
|
||||
},
|
||||
"actual_intent": {
|
||||
"period_coverage_profile": 3,
|
||||
"document_type_and_account_section_profile": 2
|
||||
},
|
||||
"actual_mode": {
|
||||
"address_query": 5
|
||||
},
|
||||
"mcp_call_status": {
|
||||
"matched_non_empty": 5
|
||||
},
|
||||
"limited_reason_category": {},
|
||||
"route_health": {
|
||||
"ok_or_factual": 5
|
||||
}
|
||||
}
|
||||
},
|
||||
"rows": [
|
||||
{
|
||||
"index": 1,
|
||||
"id": "Q1",
|
||||
"question": "За какие годы в базе есть данные?",
|
||||
"session": null,
|
||||
"session_id": "asst-2026-04-02_Address_General5_Live_Check_AfterFix_03-q1",
|
||||
"status_code": 200,
|
||||
"ok": true,
|
||||
"elapsed_ms": 780,
|
||||
"reply_type": "factual",
|
||||
"trace_id": "address--IzaA87urN",
|
||||
"assistant_reply": "Профиль периодов базы собран (movement-based aggregate).\nСтрок агрегата: 134.\nПокрытие по датам: 2014-05-27T12:00:00Z.. 2026-03-31T00:00:00Z.\nГоды с данными: 2014..2026 (уникальных: 12).\nСамый активный год по документам: 2019 (1004).\nСамый активный месяц по операциям: 2015-02 (1249).\nТоп годов по документам:\n1. 2019: 1004\n2. 2018: 703\n3. 2015: 671\n4. 2016: 577\n5. 2020: 536\nТоп месяцев по операциям:\n1. 2015-02: 1249\n2. 2015-01: 924\n3. 2018-08: 854\n4. 2019-05: 536\n5. 2017-12: 503",
|
||||
"assistant_reply_first_line": "Профиль периодов базы собран (movement-based aggregate).",
|
||||
"expected_intent": "period_coverage_profile",
|
||||
"actual_intent": "period_coverage_profile",
|
||||
"intent_match": true,
|
||||
"expected_mode": "address_query",
|
||||
"actual_mode": "address_query",
|
||||
"mode_match": true,
|
||||
"expected_reply_type": null,
|
||||
"reply_match": true,
|
||||
"semantic_pass": true,
|
||||
"route_pass": true,
|
||||
"route_health": "ok_or_factual",
|
||||
"strict_policy": "route",
|
||||
"strict_pass": true,
|
||||
"selected_recipe": "address_period_coverage_profile_v1",
|
||||
"missing_required_filters": [],
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"rows_fetched": 134,
|
||||
"rows_matched": 134,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"limited_reason_category": null,
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_reason": "not_address_like",
|
||||
"fallback_rule_hit": null,
|
||||
"debug_payload": {
|
||||
"trace_id": "address--IzaA87urN",
|
||||
"prompt_version": "address_query_runtime_v1",
|
||||
"schema_version": "address_query_runtime_v1",
|
||||
"fallback_type": "none",
|
||||
"route_summary": null,
|
||||
"fragments": [],
|
||||
"requirements_extracted": [],
|
||||
"coverage_report": {
|
||||
"requirements_total": 0,
|
||||
"requirements_covered": 0,
|
||||
"requirements_uncovered": [],
|
||||
"requirements_partially_covered": [],
|
||||
"clarification_needed_for": [],
|
||||
"out_of_scope_requirements": []
|
||||
},
|
||||
"routes": [],
|
||||
"retrieval_status": [],
|
||||
"retrieval_results": [],
|
||||
"answer_grounding_check": {
|
||||
"status": "grounded",
|
||||
"route_subject_match": true,
|
||||
"missing_requirements": [],
|
||||
"reasons": [
|
||||
"management_profile_signal_detected",
|
||||
"shape_not_detected",
|
||||
"period_coverage_profile_signal_detected"
|
||||
],
|
||||
"why_included_summary": [],
|
||||
"selection_reason_summary": []
|
||||
},
|
||||
"dropped_intent_segments": [],
|
||||
"detected_mode": "address_query",
|
||||
"detected_mode_confidence": "medium",
|
||||
"query_shape": "UNKNOWN",
|
||||
"query_shape_confidence": "low",
|
||||
"detected_intent": "period_coverage_profile",
|
||||
"detected_intent_confidence": "high",
|
||||
"extracted_filters": {
|
||||
"sort": "period_desc",
|
||||
"period_to": "2026-04-02"
|
||||
},
|
||||
"missing_required_filters": [],
|
||||
"selected_recipe": "address_period_coverage_profile_v1",
|
||||
"mcp_call_status_legacy": "matched_non_empty",
|
||||
"account_scope_mode": "preferred",
|
||||
"account_scope_fallback_applied": false,
|
||||
"anchor_type": "unknown",
|
||||
"anchor_value_raw": null,
|
||||
"anchor_value_resolved": null,
|
||||
"resolver_confidence": "low",
|
||||
"ambiguity_count": 0,
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"rows_fetched": 134,
|
||||
"raw_rows_received": 134,
|
||||
"rows_after_account_scope": 134,
|
||||
"rows_after_recipe_filter": 134,
|
||||
"rows_materialized": 134,
|
||||
"rows_matched": 134,
|
||||
"raw_row_keys_sample": [
|
||||
"Период",
|
||||
"Регистратор",
|
||||
"СчетДт",
|
||||
"СчетКт",
|
||||
"Сумма",
|
||||
"Period",
|
||||
"Registrator",
|
||||
"Amount"
|
||||
],
|
||||
"materialization_drop_reason": "none",
|
||||
"account_token_raw": null,
|
||||
"account_token_normalized": null,
|
||||
"account_scope_fields_checked": [
|
||||
"account_dt",
|
||||
"account_kt",
|
||||
"registrator",
|
||||
"analytics"
|
||||
],
|
||||
"account_scope_match_strategy": "account_code_regex_plus_alias_map_v1",
|
||||
"account_scope_drop_reason": "not_applicable",
|
||||
"runtime_readiness": "LIVE_QUERYABLE_WITH_LIMITS",
|
||||
"limited_reason_category": null,
|
||||
"response_type": "FACTUAL_SUMMARY",
|
||||
"execution_lane": "address_query",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_attempted": false,
|
||||
"llm_provider_used": "local",
|
||||
"llm_decomposition_trace_id": null,
|
||||
"llm_decomposition_effective_message": "За какие годы в базе есть данные?",
|
||||
"llm_decomposition_reason": "not_address_like",
|
||||
"fallback_rule_hit": null,
|
||||
"sanitized_user_message": "за какие годы в базе есть данные?",
|
||||
"tool_gate_decision": "run_address_lane",
|
||||
"tool_gate_reason": "address_mode_classifier_detected",
|
||||
"answer_structure_v11": null,
|
||||
"investigation_state_snapshot": null,
|
||||
"normalized": null,
|
||||
"normalizer_output": null
|
||||
},
|
||||
"error_code": null,
|
||||
"error_message": null
|
||||
},
|
||||
{
|
||||
"index": 2,
|
||||
"id": "Q2",
|
||||
"question": "Какой год самый активный по количеству документов?",
|
||||
"session": null,
|
||||
"session_id": "asst-2026-04-02_Address_General5_Live_Check_AfterFix_03-q2",
|
||||
"status_code": 200,
|
||||
"ok": true,
|
||||
"elapsed_ms": 6137,
|
||||
"reply_type": "factual",
|
||||
"trace_id": "address-4r8q6DoYyz",
|
||||
"assistant_reply": "Профиль периодов базы собран (movement-based aggregate).\nСтрок агрегата: 134.\nПокрытие по датам: 2014-05-27T12:00:00Z.. 2026-03-31T00:00:00Z.\nГоды с данными: 2014..2026 (уникальных: 12).\nСамый активный год по документам: 2019 (1004).\nСамый активный месяц по операциям: 2015-02 (1249).\nТоп годов по документам:\n1. 2019: 1004\n2. 2018: 703\n3. 2015: 671\n4. 2016: 577\n5. 2020: 536\nТоп месяцев по операциям:\n1. 2015-02: 1249\n2. 2015-01: 924\n3. 2018-08: 854\n4. 2019-05: 536\n5. 2017-12: 503",
|
||||
"assistant_reply_first_line": "Профиль периодов базы собран (movement-based aggregate).",
|
||||
"expected_intent": "period_coverage_profile",
|
||||
"actual_intent": "period_coverage_profile",
|
||||
"intent_match": true,
|
||||
"expected_mode": "address_query",
|
||||
"actual_mode": "address_query",
|
||||
"mode_match": true,
|
||||
"expected_reply_type": null,
|
||||
"reply_match": true,
|
||||
"semantic_pass": true,
|
||||
"route_pass": true,
|
||||
"route_health": "ok_or_factual",
|
||||
"strict_policy": "route",
|
||||
"strict_pass": true,
|
||||
"selected_recipe": "address_period_coverage_profile_v1",
|
||||
"missing_required_filters": [],
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"rows_fetched": 134,
|
||||
"rows_matched": 134,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"limited_reason_category": null,
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_reason": "normalized_fragment_rejected_intent_conflict",
|
||||
"fallback_rule_hit": null,
|
||||
"debug_payload": {
|
||||
"trace_id": "address-4r8q6DoYyz",
|
||||
"prompt_version": "address_query_runtime_v1",
|
||||
"schema_version": "address_query_runtime_v1",
|
||||
"fallback_type": "none",
|
||||
"route_summary": null,
|
||||
"fragments": [],
|
||||
"requirements_extracted": [],
|
||||
"coverage_report": {
|
||||
"requirements_total": 0,
|
||||
"requirements_covered": 0,
|
||||
"requirements_uncovered": [],
|
||||
"requirements_partially_covered": [],
|
||||
"clarification_needed_for": [],
|
||||
"out_of_scope_requirements": []
|
||||
},
|
||||
"routes": [],
|
||||
"retrieval_status": [],
|
||||
"retrieval_results": [],
|
||||
"answer_grounding_check": {
|
||||
"status": "grounded",
|
||||
"route_subject_match": true,
|
||||
"missing_requirements": [],
|
||||
"reasons": [
|
||||
"management_profile_signal_detected",
|
||||
"document_list_signal_detected",
|
||||
"period_coverage_profile_signal_detected"
|
||||
],
|
||||
"why_included_summary": [],
|
||||
"selection_reason_summary": []
|
||||
},
|
||||
"dropped_intent_segments": [],
|
||||
"detected_mode": "address_query",
|
||||
"detected_mode_confidence": "medium",
|
||||
"query_shape": "DOCUMENT_LIST",
|
||||
"query_shape_confidence": "medium",
|
||||
"detected_intent": "period_coverage_profile",
|
||||
"detected_intent_confidence": "high",
|
||||
"extracted_filters": {
|
||||
"sort": "period_desc",
|
||||
"period_to": "2026-04-02"
|
||||
},
|
||||
"missing_required_filters": [],
|
||||
"selected_recipe": "address_period_coverage_profile_v1",
|
||||
"mcp_call_status_legacy": "matched_non_empty",
|
||||
"account_scope_mode": "preferred",
|
||||
"account_scope_fallback_applied": false,
|
||||
"anchor_type": "unknown",
|
||||
"anchor_value_raw": null,
|
||||
"anchor_value_resolved": null,
|
||||
"resolver_confidence": "low",
|
||||
"ambiguity_count": 0,
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"rows_fetched": 134,
|
||||
"raw_rows_received": 134,
|
||||
"rows_after_account_scope": 134,
|
||||
"rows_after_recipe_filter": 134,
|
||||
"rows_materialized": 134,
|
||||
"rows_matched": 134,
|
||||
"raw_row_keys_sample": [
|
||||
"Период",
|
||||
"Регистратор",
|
||||
"СчетДт",
|
||||
"СчетКт",
|
||||
"Сумма",
|
||||
"Period",
|
||||
"Registrator",
|
||||
"Amount"
|
||||
],
|
||||
"materialization_drop_reason": "none",
|
||||
"account_token_raw": null,
|
||||
"account_token_normalized": null,
|
||||
"account_scope_fields_checked": [
|
||||
"account_dt",
|
||||
"account_kt",
|
||||
"registrator",
|
||||
"analytics"
|
||||
],
|
||||
"account_scope_match_strategy": "account_code_regex_plus_alias_map_v1",
|
||||
"account_scope_drop_reason": "not_applicable",
|
||||
"runtime_readiness": "LIVE_QUERYABLE_WITH_LIMITS",
|
||||
"limited_reason_category": null,
|
||||
"response_type": "FACTUAL_SUMMARY",
|
||||
"execution_lane": "address_query",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_attempted": true,
|
||||
"llm_provider_used": "local",
|
||||
"llm_decomposition_trace_id": "JZJaNxdo2sfwwX",
|
||||
"llm_decomposition_effective_message": "Какой год самый активный по количеству документов?",
|
||||
"llm_decomposition_reason": "normalized_fragment_rejected_intent_conflict",
|
||||
"fallback_rule_hit": null,
|
||||
"sanitized_user_message": "какой год самый активный по количеству документов?",
|
||||
"tool_gate_decision": "run_address_lane",
|
||||
"tool_gate_reason": "address_mode_classifier_detected",
|
||||
"answer_structure_v11": null,
|
||||
"investigation_state_snapshot": null,
|
||||
"normalized": null,
|
||||
"normalizer_output": {
|
||||
"trace_id": "JZJaNxdo2sfwwX",
|
||||
"prompt_version": "normalizer_v2_0_2",
|
||||
"applied": false,
|
||||
"effective_message": "Какой год самый активный по количеству документов?"
|
||||
}
|
||||
},
|
||||
"error_code": null,
|
||||
"error_message": null
|
||||
},
|
||||
{
|
||||
"index": 3,
|
||||
"id": "Q3",
|
||||
"question": "Какой месяц самый активный по количеству операций?",
|
||||
"session": null,
|
||||
"session_id": "asst-2026-04-02_Address_General5_Live_Check_AfterFix_03-q3",
|
||||
"status_code": 200,
|
||||
"ok": true,
|
||||
"elapsed_ms": 951,
|
||||
"reply_type": "factual",
|
||||
"trace_id": "address-8M9cIXeAaF",
|
||||
"assistant_reply": "Профиль периодов базы собран (movement-based aggregate).\nСтрок агрегата: 134.\nПокрытие по датам: 2014-05-27T12:00:00Z.. 2026-03-31T00:00:00Z.\nГоды с данными: 2014..2026 (уникальных: 12).\nСамый активный год по документам: 2019 (1004).\nСамый активный месяц по операциям: 2015-02 (1249).\nТоп годов по документам:\n1. 2019: 1004\n2. 2018: 703\n3. 2015: 671\n4. 2016: 577\n5. 2020: 536\nТоп месяцев по операциям:\n1. 2015-02: 1249\n2. 2015-01: 924\n3. 2018-08: 854\n4. 2019-05: 536\n5. 2017-12: 503",
|
||||
"assistant_reply_first_line": "Профиль периодов базы собран (movement-based aggregate).",
|
||||
"expected_intent": "period_coverage_profile",
|
||||
"actual_intent": "period_coverage_profile",
|
||||
"intent_match": true,
|
||||
"expected_mode": "address_query",
|
||||
"actual_mode": "address_query",
|
||||
"mode_match": true,
|
||||
"expected_reply_type": null,
|
||||
"reply_match": true,
|
||||
"semantic_pass": true,
|
||||
"route_pass": true,
|
||||
"route_health": "ok_or_factual",
|
||||
"strict_policy": "route",
|
||||
"strict_pass": true,
|
||||
"selected_recipe": "address_period_coverage_profile_v1",
|
||||
"missing_required_filters": [],
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"rows_fetched": 134,
|
||||
"rows_matched": 134,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"limited_reason_category": null,
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_reason": "not_address_like",
|
||||
"fallback_rule_hit": null,
|
||||
"debug_payload": {
|
||||
"trace_id": "address-8M9cIXeAaF",
|
||||
"prompt_version": "address_query_runtime_v1",
|
||||
"schema_version": "address_query_runtime_v1",
|
||||
"fallback_type": "none",
|
||||
"route_summary": null,
|
||||
"fragments": [],
|
||||
"requirements_extracted": [],
|
||||
"coverage_report": {
|
||||
"requirements_total": 0,
|
||||
"requirements_covered": 0,
|
||||
"requirements_uncovered": [],
|
||||
"requirements_partially_covered": [],
|
||||
"clarification_needed_for": [],
|
||||
"out_of_scope_requirements": []
|
||||
},
|
||||
"routes": [],
|
||||
"retrieval_status": [],
|
||||
"retrieval_results": [],
|
||||
"answer_grounding_check": {
|
||||
"status": "grounded",
|
||||
"route_subject_match": true,
|
||||
"missing_requirements": [],
|
||||
"reasons": [
|
||||
"management_profile_signal_detected",
|
||||
"shape_not_detected",
|
||||
"period_coverage_profile_signal_detected"
|
||||
],
|
||||
"why_included_summary": [],
|
||||
"selection_reason_summary": []
|
||||
},
|
||||
"dropped_intent_segments": [],
|
||||
"detected_mode": "address_query",
|
||||
"detected_mode_confidence": "medium",
|
||||
"query_shape": "UNKNOWN",
|
||||
"query_shape_confidence": "low",
|
||||
"detected_intent": "period_coverage_profile",
|
||||
"detected_intent_confidence": "high",
|
||||
"extracted_filters": {
|
||||
"sort": "period_desc",
|
||||
"period_to": "2026-04-02"
|
||||
},
|
||||
"missing_required_filters": [],
|
||||
"selected_recipe": "address_period_coverage_profile_v1",
|
||||
"mcp_call_status_legacy": "matched_non_empty",
|
||||
"account_scope_mode": "preferred",
|
||||
"account_scope_fallback_applied": false,
|
||||
"anchor_type": "unknown",
|
||||
"anchor_value_raw": null,
|
||||
"anchor_value_resolved": null,
|
||||
"resolver_confidence": "low",
|
||||
"ambiguity_count": 0,
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"rows_fetched": 134,
|
||||
"raw_rows_received": 134,
|
||||
"rows_after_account_scope": 134,
|
||||
"rows_after_recipe_filter": 134,
|
||||
"rows_materialized": 134,
|
||||
"rows_matched": 134,
|
||||
"raw_row_keys_sample": [
|
||||
"Период",
|
||||
"Регистратор",
|
||||
"СчетДт",
|
||||
"СчетКт",
|
||||
"Сумма",
|
||||
"Period",
|
||||
"Registrator",
|
||||
"Amount"
|
||||
],
|
||||
"materialization_drop_reason": "none",
|
||||
"account_token_raw": null,
|
||||
"account_token_normalized": null,
|
||||
"account_scope_fields_checked": [
|
||||
"account_dt",
|
||||
"account_kt",
|
||||
"registrator",
|
||||
"analytics"
|
||||
],
|
||||
"account_scope_match_strategy": "account_code_regex_plus_alias_map_v1",
|
||||
"account_scope_drop_reason": "not_applicable",
|
||||
"runtime_readiness": "LIVE_QUERYABLE_WITH_LIMITS",
|
||||
"limited_reason_category": null,
|
||||
"response_type": "FACTUAL_SUMMARY",
|
||||
"execution_lane": "address_query",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_attempted": false,
|
||||
"llm_provider_used": "local",
|
||||
"llm_decomposition_trace_id": null,
|
||||
"llm_decomposition_effective_message": "Какой месяц самый активный по количеству операций?",
|
||||
"llm_decomposition_reason": "not_address_like",
|
||||
"fallback_rule_hit": null,
|
||||
"sanitized_user_message": "какой месяц самый активный по количеству операций?",
|
||||
"tool_gate_decision": "run_address_lane",
|
||||
"tool_gate_reason": "address_mode_classifier_detected",
|
||||
"answer_structure_v11": null,
|
||||
"investigation_state_snapshot": null,
|
||||
"normalized": null,
|
||||
"normalizer_output": null
|
||||
},
|
||||
"error_code": null,
|
||||
"error_message": null
|
||||
},
|
||||
{
|
||||
"index": 4,
|
||||
"id": "Q4",
|
||||
"question": "Какие типы документов используются чаще всего в базе?",
|
||||
"session": null,
|
||||
"session_id": "asst-2026-04-02_Address_General5_Live_Check_AfterFix_03-q4",
|
||||
"status_code": 200,
|
||||
"ok": true,
|
||||
"elapsed_ms": 5156,
|
||||
"reply_type": "factual",
|
||||
"trace_id": "address-QVkxNBqT0e",
|
||||
"assistant_reply": "Профиль типов документов и разделов учета собран (movement-based aggregate).\nСтрок агрегата: 147.\nТоп типов документов (по числу уникальных регистраторов):\n1. Списание с расчетного счета: 2352 (52.6%)\n2. Поступление товаров и услуг: 486 (10.9%)\n3. Регламентная операция: 414 (9.3%)\n4. Поступление на расчетный счет: 323 (7.2%)\n5. Счет-фактура полученный: 261 (5.8%)\n6. Операция (бухгалтерский и налоговый учет): 147 (3.3%)\n7. Реализация товаров и услуг: 123 (2.8%)\n8. Отражение зарплаты в регламентированном учете: 87 (1.9%)\n9. Приходный кассовый ордер: 76 (1.7%)\n10. Расходный кассовый ордер: 73 (1.6%)\nНаиболее заполненные разделы учета (по операциям Дт+Кт):\n1. 90 (Продажи): 2973 (12.1%)\n2. 51 (Расчетные счета): 2967 (12.1%)\n3. 60 (Расчеты с поставщиками и подрядчиками): 2793 (11.4%)\n4. 44 (Расходы на продажу): 2422 (9.9%)\n5. 68 (Расчеты по налогам и сборам): 1553 (6.3%)\n6. 10 (Материалы): 1494 (6.1%)\n7. 19 (НДС по приобретенным ценностям): 1489 (6.1%)\n8. 91 (Прочие доходы и расходы): 1324 (5.4%)\n9. 41 (Товары): 1312 (5.3%)\n10. 76 (Расчеты с разными дебиторами и кредиторами): 1240 (5.0%)\nРазделы с минимальной активностью (среди использованных):\n1. 58 (Финансовые вложения): 2\n2. 81 (Собственные акции (доли)): 2\n3. 80 (Уставный капитал): 5\n4. 03: 6\n5. 04 (Нематериальные активы): 6\n6. 75 (Расчеты с учредителями): 16\n7. 55 (Специальные счета в банках): 18\n8. 84 (Нераспределенная прибыль (непокрытый убыток)): 20\n9. 26 (Общехозяйственные расходы): 51\n10. 71 (Расчеты с подотчетными лицами): 76",
|
||||
"assistant_reply_first_line": "Профиль типов документов и разделов учета собран (movement-based aggregate).",
|
||||
"expected_intent": "document_type_and_account_section_profile",
|
||||
"actual_intent": "document_type_and_account_section_profile",
|
||||
"intent_match": true,
|
||||
"expected_mode": "address_query",
|
||||
"actual_mode": "address_query",
|
||||
"mode_match": true,
|
||||
"expected_reply_type": null,
|
||||
"reply_match": true,
|
||||
"semantic_pass": true,
|
||||
"route_pass": true,
|
||||
"route_health": "ok_or_factual",
|
||||
"strict_policy": "route",
|
||||
"strict_pass": true,
|
||||
"selected_recipe": "address_document_type_and_account_section_profile_v1",
|
||||
"missing_required_filters": [],
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"rows_fetched": 147,
|
||||
"rows_matched": 147,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"limited_reason_category": null,
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_reason": "normalized_fragment_same",
|
||||
"fallback_rule_hit": null,
|
||||
"debug_payload": {
|
||||
"trace_id": "address-QVkxNBqT0e",
|
||||
"prompt_version": "address_query_runtime_v1",
|
||||
"schema_version": "address_query_runtime_v1",
|
||||
"fallback_type": "none",
|
||||
"route_summary": null,
|
||||
"fragments": [],
|
||||
"requirements_extracted": [],
|
||||
"coverage_report": {
|
||||
"requirements_total": 0,
|
||||
"requirements_covered": 0,
|
||||
"requirements_uncovered": [],
|
||||
"requirements_partially_covered": [],
|
||||
"clarification_needed_for": [],
|
||||
"out_of_scope_requirements": []
|
||||
},
|
||||
"routes": [],
|
||||
"retrieval_status": [],
|
||||
"retrieval_results": [],
|
||||
"answer_grounding_check": {
|
||||
"status": "grounded",
|
||||
"route_subject_match": true,
|
||||
"missing_requirements": [],
|
||||
"reasons": [
|
||||
"address_action_detected",
|
||||
"address_entity_detected",
|
||||
"document_list_signal_detected",
|
||||
"document_type_and_account_section_profile_signal_detected"
|
||||
],
|
||||
"why_included_summary": [],
|
||||
"selection_reason_summary": []
|
||||
},
|
||||
"dropped_intent_segments": [],
|
||||
"detected_mode": "address_query",
|
||||
"detected_mode_confidence": "high",
|
||||
"query_shape": "DOCUMENT_LIST",
|
||||
"query_shape_confidence": "medium",
|
||||
"detected_intent": "document_type_and_account_section_profile",
|
||||
"detected_intent_confidence": "high",
|
||||
"extracted_filters": {
|
||||
"sort": "period_desc",
|
||||
"period_to": "2026-04-02"
|
||||
},
|
||||
"missing_required_filters": [],
|
||||
"selected_recipe": "address_document_type_and_account_section_profile_v1",
|
||||
"mcp_call_status_legacy": "matched_non_empty",
|
||||
"account_scope_mode": "preferred",
|
||||
"account_scope_fallback_applied": false,
|
||||
"anchor_type": "unknown",
|
||||
"anchor_value_raw": null,
|
||||
"anchor_value_resolved": null,
|
||||
"resolver_confidence": "low",
|
||||
"ambiguity_count": 0,
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"rows_fetched": 147,
|
||||
"raw_rows_received": 147,
|
||||
"rows_after_account_scope": 147,
|
||||
"rows_after_recipe_filter": 147,
|
||||
"rows_materialized": 147,
|
||||
"rows_matched": 147,
|
||||
"raw_row_keys_sample": [
|
||||
"Период",
|
||||
"Регистратор",
|
||||
"СчетДт",
|
||||
"СчетКт",
|
||||
"Сумма",
|
||||
"Period",
|
||||
"Registrator",
|
||||
"AccountDt",
|
||||
"Amount"
|
||||
],
|
||||
"materialization_drop_reason": "none",
|
||||
"account_token_raw": null,
|
||||
"account_token_normalized": null,
|
||||
"account_scope_fields_checked": [
|
||||
"account_dt",
|
||||
"account_kt",
|
||||
"registrator",
|
||||
"analytics"
|
||||
],
|
||||
"account_scope_match_strategy": "account_code_regex_plus_alias_map_v1",
|
||||
"account_scope_drop_reason": "not_applicable",
|
||||
"runtime_readiness": "LIVE_QUERYABLE_WITH_LIMITS",
|
||||
"limited_reason_category": null,
|
||||
"response_type": "FACTUAL_SUMMARY",
|
||||
"execution_lane": "address_query",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_attempted": true,
|
||||
"llm_provider_used": "local",
|
||||
"llm_decomposition_trace_id": "3zbySabYai6x29",
|
||||
"llm_decomposition_effective_message": "Какие типы документов используются чаще всего в базе?",
|
||||
"llm_decomposition_reason": "normalized_fragment_same",
|
||||
"fallback_rule_hit": null,
|
||||
"sanitized_user_message": "какие типы документов используются чаще всего в базе?",
|
||||
"tool_gate_decision": "run_address_lane",
|
||||
"tool_gate_reason": "address_mode_classifier_detected",
|
||||
"answer_structure_v11": null,
|
||||
"investigation_state_snapshot": null,
|
||||
"normalized": null,
|
||||
"normalizer_output": {
|
||||
"trace_id": "3zbySabYai6x29",
|
||||
"prompt_version": "normalizer_v2_0_2",
|
||||
"applied": false,
|
||||
"effective_message": "Какие типы документов используются чаще всего в базе?"
|
||||
}
|
||||
},
|
||||
"error_code": null,
|
||||
"error_message": null
|
||||
},
|
||||
{
|
||||
"index": 5,
|
||||
"id": "Q5",
|
||||
"question": "Какие разделы учета наиболее заполнены и какие почти не используются?",
|
||||
"session": null,
|
||||
"session_id": "asst-2026-04-02_Address_General5_Live_Check_AfterFix_03-q5",
|
||||
"status_code": 200,
|
||||
"ok": true,
|
||||
"elapsed_ms": 1005,
|
||||
"reply_type": "factual",
|
||||
"trace_id": "address-wpbdV5Mkcd",
|
||||
"assistant_reply": "Профиль типов документов и разделов учета собран (movement-based aggregate).\nСтрок агрегата: 147.\nТоп типов документов (по числу уникальных регистраторов):\n1. Списание с расчетного счета: 2352 (52.6%)\n2. Поступление товаров и услуг: 486 (10.9%)\n3. Регламентная операция: 414 (9.3%)\n4. Поступление на расчетный счет: 323 (7.2%)\n5. Счет-фактура полученный: 261 (5.8%)\n6. Операция (бухгалтерский и налоговый учет): 147 (3.3%)\n7. Реализация товаров и услуг: 123 (2.8%)\n8. Отражение зарплаты в регламентированном учете: 87 (1.9%)\n9. Приходный кассовый ордер: 76 (1.7%)\n10. Расходный кассовый ордер: 73 (1.6%)\nНаиболее заполненные разделы учета (по операциям Дт+Кт):\n1. 90 (Продажи): 2973 (12.1%)\n2. 51 (Расчетные счета): 2967 (12.1%)\n3. 60 (Расчеты с поставщиками и подрядчиками): 2793 (11.4%)\n4. 44 (Расходы на продажу): 2422 (9.9%)\n5. 68 (Расчеты по налогам и сборам): 1553 (6.3%)\n6. 10 (Материалы): 1494 (6.1%)\n7. 19 (НДС по приобретенным ценностям): 1489 (6.1%)\n8. 91 (Прочие доходы и расходы): 1324 (5.4%)\n9. 41 (Товары): 1312 (5.3%)\n10. 76 (Расчеты с разными дебиторами и кредиторами): 1240 (5.0%)\nРазделы с минимальной активностью (среди использованных):\n1. 58 (Финансовые вложения): 2\n2. 81 (Собственные акции (доли)): 2\n3. 80 (Уставный капитал): 5\n4. 03: 6\n5. 04 (Нематериальные активы): 6\n6. 75 (Расчеты с учредителями): 16\n7. 55 (Специальные счета в банках): 18\n8. 84 (Нераспределенная прибыль (непокрытый убыток)): 20\n9. 26 (Общехозяйственные расходы): 51\n10. 71 (Расчеты с подотчетными лицами): 76",
|
||||
"assistant_reply_first_line": "Профиль типов документов и разделов учета собран (movement-based aggregate).",
|
||||
"expected_intent": "document_type_and_account_section_profile",
|
||||
"actual_intent": "document_type_and_account_section_profile",
|
||||
"intent_match": true,
|
||||
"expected_mode": "address_query",
|
||||
"actual_mode": "address_query",
|
||||
"mode_match": true,
|
||||
"expected_reply_type": null,
|
||||
"reply_match": true,
|
||||
"semantic_pass": true,
|
||||
"route_pass": true,
|
||||
"route_health": "ok_or_factual",
|
||||
"strict_policy": "route",
|
||||
"strict_pass": true,
|
||||
"selected_recipe": "address_document_type_and_account_section_profile_v1",
|
||||
"missing_required_filters": [],
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"rows_fetched": 147,
|
||||
"rows_matched": 147,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"limited_reason_category": null,
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_reason": "not_address_like",
|
||||
"fallback_rule_hit": null,
|
||||
"debug_payload": {
|
||||
"trace_id": "address-wpbdV5Mkcd",
|
||||
"prompt_version": "address_query_runtime_v1",
|
||||
"schema_version": "address_query_runtime_v1",
|
||||
"fallback_type": "none",
|
||||
"route_summary": null,
|
||||
"fragments": [],
|
||||
"requirements_extracted": [],
|
||||
"coverage_report": {
|
||||
"requirements_total": 0,
|
||||
"requirements_covered": 0,
|
||||
"requirements_uncovered": [],
|
||||
"requirements_partially_covered": [],
|
||||
"clarification_needed_for": [],
|
||||
"out_of_scope_requirements": []
|
||||
},
|
||||
"routes": [],
|
||||
"retrieval_status": [],
|
||||
"retrieval_results": [],
|
||||
"answer_grounding_check": {
|
||||
"status": "grounded",
|
||||
"route_subject_match": true,
|
||||
"missing_requirements": [],
|
||||
"reasons": [
|
||||
"management_profile_signal_detected",
|
||||
"shape_not_detected",
|
||||
"document_type_and_account_section_profile_signal_detected"
|
||||
],
|
||||
"why_included_summary": [],
|
||||
"selection_reason_summary": []
|
||||
},
|
||||
"dropped_intent_segments": [],
|
||||
"detected_mode": "address_query",
|
||||
"detected_mode_confidence": "medium",
|
||||
"query_shape": "UNKNOWN",
|
||||
"query_shape_confidence": "low",
|
||||
"detected_intent": "document_type_and_account_section_profile",
|
||||
"detected_intent_confidence": "high",
|
||||
"extracted_filters": {
|
||||
"sort": "period_desc",
|
||||
"period_to": "2026-04-02"
|
||||
},
|
||||
"missing_required_filters": [],
|
||||
"selected_recipe": "address_document_type_and_account_section_profile_v1",
|
||||
"mcp_call_status_legacy": "matched_non_empty",
|
||||
"account_scope_mode": "preferred",
|
||||
"account_scope_fallback_applied": false,
|
||||
"anchor_type": "unknown",
|
||||
"anchor_value_raw": null,
|
||||
"anchor_value_resolved": null,
|
||||
"resolver_confidence": "low",
|
||||
"ambiguity_count": 0,
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"rows_fetched": 147,
|
||||
"raw_rows_received": 147,
|
||||
"rows_after_account_scope": 147,
|
||||
"rows_after_recipe_filter": 147,
|
||||
"rows_materialized": 147,
|
||||
"rows_matched": 147,
|
||||
"raw_row_keys_sample": [
|
||||
"Период",
|
||||
"Регистратор",
|
||||
"СчетДт",
|
||||
"СчетКт",
|
||||
"Сумма",
|
||||
"Period",
|
||||
"Registrator",
|
||||
"AccountDt",
|
||||
"Amount"
|
||||
],
|
||||
"materialization_drop_reason": "none",
|
||||
"account_token_raw": null,
|
||||
"account_token_normalized": null,
|
||||
"account_scope_fields_checked": [
|
||||
"account_dt",
|
||||
"account_kt",
|
||||
"registrator",
|
||||
"analytics"
|
||||
],
|
||||
"account_scope_match_strategy": "account_code_regex_plus_alias_map_v1",
|
||||
"account_scope_drop_reason": "not_applicable",
|
||||
"runtime_readiness": "LIVE_QUERYABLE_WITH_LIMITS",
|
||||
"limited_reason_category": null,
|
||||
"response_type": "FACTUAL_SUMMARY",
|
||||
"execution_lane": "address_query",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_attempted": false,
|
||||
"llm_provider_used": "local",
|
||||
"llm_decomposition_trace_id": null,
|
||||
"llm_decomposition_effective_message": "Какие разделы учета наиболее заполнены и какие почти не используются?",
|
||||
"llm_decomposition_reason": "not_address_like",
|
||||
"fallback_rule_hit": null,
|
||||
"sanitized_user_message": "какие разделы учета наиболее заполнены и какие почти не используются?",
|
||||
"tool_gate_decision": "run_address_lane",
|
||||
"tool_gate_reason": "address_mode_classifier_detected",
|
||||
"answer_structure_v11": null,
|
||||
"investigation_state_snapshot": null,
|
||||
"normalized": null,
|
||||
"normalizer_output": null
|
||||
},
|
||||
"error_code": null,
|
||||
"error_message": null
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,9 @@
|
||||
# Response Audit: 2026-04-02_Address_General5_Live_Check_AfterFix_03
|
||||
|
||||
| id | strict | route_health | reply_type | intent | limited_reason | question | assistant_first_line |
|
||||
|---|---|---|---|---|---|---|---|
|
||||
| Q1 | True | ok_or_factual | factual | period_coverage_profile | None | За какие годы в базе есть данные? | Профиль периодов базы собран (movement-based aggregate). |
|
||||
| Q2 | True | ok_or_factual | factual | period_coverage_profile | None | Какой год самый активный по количеству документов? | Профиль периодов базы собран (movement-based aggregate). |
|
||||
| Q3 | True | ok_or_factual | factual | period_coverage_profile | None | Какой месяц самый активный по количеству операций? | Профиль периодов базы собран (movement-based aggregate). |
|
||||
| Q4 | True | ok_or_factual | factual | document_type_and_account_section_profile | None | Какие типы документов используются чаще всего в базе? | Профиль типов документов и разделов учета собран (movement-based aggregate). |
|
||||
| Q5 | True | ok_or_factual | factual | document_type_and_account_section_profile | None | Какие разделы учета наиболее заполнены и какие почти не используются? | Профиль типов документов и разделов учета собран (movement-based aggregate). |
|
||||
@@ -0,0 +1,45 @@
|
||||
{
|
||||
"run_id": "2026-04-02_Address_General5_Live_Check_AfterFix_03",
|
||||
"generated_at": "2026-04-02T19:45:20",
|
||||
"source_questions_file": "X:\\1C\\NDC_1C\\docs\\ADDRESS\\question_sets\\temp_general5_live_check_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": "route",
|
||||
"totals": {
|
||||
"questions_total": 5,
|
||||
"ok_200_count": 5,
|
||||
"semantic_pass_count": 5,
|
||||
"semantic_pass_rate": 1.0,
|
||||
"route_pass_count": 5,
|
||||
"route_pass_rate": 1.0,
|
||||
"strict_pass_count": 5,
|
||||
"strict_pass_rate": 1.0,
|
||||
"factual_count": 5,
|
||||
"partial_coverage_count": 0,
|
||||
"clarification_required_count": 0,
|
||||
"http_error_count": 0,
|
||||
"llm_decomposition_applied_count": 0,
|
||||
"avg_elapsed_ms": 2805.8
|
||||
},
|
||||
"distributions": {
|
||||
"reply_type": {
|
||||
"factual": 5
|
||||
},
|
||||
"actual_intent": {
|
||||
"period_coverage_profile": 3,
|
||||
"document_type_and_account_section_profile": 2
|
||||
},
|
||||
"actual_mode": {
|
||||
"address_query": 5
|
||||
},
|
||||
"mcp_call_status": {
|
||||
"matched_non_empty": 5
|
||||
},
|
||||
"limited_reason_category": {},
|
||||
"route_health": {
|
||||
"ok_or_factual": 5
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,28 @@
|
||||
# 2026-04-02_Address_General5_Live_Check_AfterFocusFix_04
|
||||
|
||||
Generated at: 2026-04-02T20:11:30
|
||||
Questions file: X:\1C\NDC_1C\docs\ADDRESS\question_sets\temp_general5_live_check_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: route
|
||||
|
||||
## Totals
|
||||
- questions_total: 5
|
||||
- ok_200_count: 5
|
||||
- semantic_pass_count: 5
|
||||
- semantic_pass_rate: 1.0
|
||||
- route_pass_count: 5
|
||||
- route_pass_rate: 1.0
|
||||
- strict_pass_count: 5
|
||||
- strict_pass_rate: 1.0
|
||||
- factual_count: 5
|
||||
- partial_coverage_count: 0
|
||||
- clarification_required_count: 0
|
||||
- http_error_count: 0
|
||||
- llm_decomposition_applied_count: 0
|
||||
- avg_elapsed_ms: 2712.4
|
||||
|
||||
## Files
|
||||
- run_summary.json
|
||||
- full_live_results.json
|
||||
- failures_only.json
|
||||
+1
@@ -0,0 +1 @@
|
||||
[]
|
||||
+769
@@ -0,0 +1,769 @@
|
||||
{
|
||||
"run_id": "2026-04-02_Address_General5_Live_Check_AfterFocusFix_04",
|
||||
"generated_at": "2026-04-02T20:11:30",
|
||||
"summary": {
|
||||
"run_id": "2026-04-02_Address_General5_Live_Check_AfterFocusFix_04",
|
||||
"generated_at": "2026-04-02T20:11:30",
|
||||
"source_questions_file": "X:\\1C\\NDC_1C\\docs\\ADDRESS\\question_sets\\temp_general5_live_check_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": "route",
|
||||
"totals": {
|
||||
"questions_total": 5,
|
||||
"ok_200_count": 5,
|
||||
"semantic_pass_count": 5,
|
||||
"semantic_pass_rate": 1.0,
|
||||
"route_pass_count": 5,
|
||||
"route_pass_rate": 1.0,
|
||||
"strict_pass_count": 5,
|
||||
"strict_pass_rate": 1.0,
|
||||
"factual_count": 5,
|
||||
"partial_coverage_count": 0,
|
||||
"clarification_required_count": 0,
|
||||
"http_error_count": 0,
|
||||
"llm_decomposition_applied_count": 0,
|
||||
"avg_elapsed_ms": 2712.4
|
||||
},
|
||||
"distributions": {
|
||||
"reply_type": {
|
||||
"factual": 5
|
||||
},
|
||||
"actual_intent": {
|
||||
"period_coverage_profile": 3,
|
||||
"document_type_and_account_section_profile": 2
|
||||
},
|
||||
"actual_mode": {
|
||||
"address_query": 5
|
||||
},
|
||||
"mcp_call_status": {
|
||||
"matched_non_empty": 5
|
||||
},
|
||||
"limited_reason_category": {},
|
||||
"route_health": {
|
||||
"ok_or_factual": 5
|
||||
}
|
||||
}
|
||||
},
|
||||
"rows": [
|
||||
{
|
||||
"index": 1,
|
||||
"id": "Q1",
|
||||
"question": "За какие годы в базе есть данные?",
|
||||
"session": null,
|
||||
"session_id": "asst-2026-04-02_Address_General5_Live_Check_AfterFocusFix_04-q1",
|
||||
"status_code": 200,
|
||||
"ok": true,
|
||||
"elapsed_ms": 347,
|
||||
"reply_type": "factual",
|
||||
"trace_id": "address-YQkPAhS48Z",
|
||||
"assistant_reply": "Профиль периодов базы собран (movement-based aggregate).\nСтрок агрегата: 134.\nОперационный период с выраженной активностью: 2014..2022.\nНизкоактивный хвост (единичные записи): 2023, 2025, 2026.\nПолный технический диапазон дат: 2014-05-27T12:00:00Z.. 2026-03-31T00:00:00Z.",
|
||||
"assistant_reply_first_line": "Профиль периодов базы собран (movement-based aggregate).",
|
||||
"expected_intent": "period_coverage_profile",
|
||||
"actual_intent": "period_coverage_profile",
|
||||
"intent_match": true,
|
||||
"expected_mode": "address_query",
|
||||
"actual_mode": "address_query",
|
||||
"mode_match": true,
|
||||
"expected_reply_type": null,
|
||||
"reply_match": true,
|
||||
"semantic_pass": true,
|
||||
"route_pass": true,
|
||||
"route_health": "ok_or_factual",
|
||||
"strict_policy": "route",
|
||||
"strict_pass": true,
|
||||
"selected_recipe": "address_period_coverage_profile_v1",
|
||||
"missing_required_filters": [],
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"rows_fetched": 134,
|
||||
"rows_matched": 134,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"limited_reason_category": null,
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_reason": "not_address_like",
|
||||
"fallback_rule_hit": null,
|
||||
"debug_payload": {
|
||||
"trace_id": "address-YQkPAhS48Z",
|
||||
"prompt_version": "address_query_runtime_v1",
|
||||
"schema_version": "address_query_runtime_v1",
|
||||
"fallback_type": "none",
|
||||
"route_summary": null,
|
||||
"fragments": [],
|
||||
"requirements_extracted": [],
|
||||
"coverage_report": {
|
||||
"requirements_total": 0,
|
||||
"requirements_covered": 0,
|
||||
"requirements_uncovered": [],
|
||||
"requirements_partially_covered": [],
|
||||
"clarification_needed_for": [],
|
||||
"out_of_scope_requirements": []
|
||||
},
|
||||
"routes": [],
|
||||
"retrieval_status": [],
|
||||
"retrieval_results": [],
|
||||
"answer_grounding_check": {
|
||||
"status": "grounded",
|
||||
"route_subject_match": true,
|
||||
"missing_requirements": [],
|
||||
"reasons": [
|
||||
"management_profile_signal_detected",
|
||||
"shape_not_detected",
|
||||
"period_coverage_profile_signal_detected"
|
||||
],
|
||||
"why_included_summary": [],
|
||||
"selection_reason_summary": []
|
||||
},
|
||||
"dropped_intent_segments": [],
|
||||
"detected_mode": "address_query",
|
||||
"detected_mode_confidence": "medium",
|
||||
"query_shape": "UNKNOWN",
|
||||
"query_shape_confidence": "low",
|
||||
"detected_intent": "period_coverage_profile",
|
||||
"detected_intent_confidence": "high",
|
||||
"extracted_filters": {
|
||||
"sort": "period_desc",
|
||||
"period_to": "2026-04-02"
|
||||
},
|
||||
"missing_required_filters": [],
|
||||
"selected_recipe": "address_period_coverage_profile_v1",
|
||||
"mcp_call_status_legacy": "matched_non_empty",
|
||||
"account_scope_mode": "preferred",
|
||||
"account_scope_fallback_applied": false,
|
||||
"anchor_type": "unknown",
|
||||
"anchor_value_raw": null,
|
||||
"anchor_value_resolved": null,
|
||||
"resolver_confidence": "low",
|
||||
"ambiguity_count": 0,
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"rows_fetched": 134,
|
||||
"raw_rows_received": 134,
|
||||
"rows_after_account_scope": 134,
|
||||
"rows_after_recipe_filter": 134,
|
||||
"rows_materialized": 134,
|
||||
"rows_matched": 134,
|
||||
"raw_row_keys_sample": [
|
||||
"Период",
|
||||
"Регистратор",
|
||||
"СчетДт",
|
||||
"СчетКт",
|
||||
"Сумма",
|
||||
"Period",
|
||||
"Registrator",
|
||||
"Amount"
|
||||
],
|
||||
"materialization_drop_reason": "none",
|
||||
"account_token_raw": null,
|
||||
"account_token_normalized": null,
|
||||
"account_scope_fields_checked": [
|
||||
"account_dt",
|
||||
"account_kt",
|
||||
"registrator",
|
||||
"analytics"
|
||||
],
|
||||
"account_scope_match_strategy": "account_code_regex_plus_alias_map_v1",
|
||||
"account_scope_drop_reason": "not_applicable",
|
||||
"runtime_readiness": "LIVE_QUERYABLE_WITH_LIMITS",
|
||||
"limited_reason_category": null,
|
||||
"response_type": "FACTUAL_SUMMARY",
|
||||
"execution_lane": "address_query",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_attempted": false,
|
||||
"llm_provider_used": "local",
|
||||
"llm_decomposition_trace_id": null,
|
||||
"llm_decomposition_effective_message": "За какие годы в базе есть данные?",
|
||||
"llm_decomposition_reason": "not_address_like",
|
||||
"fallback_rule_hit": null,
|
||||
"sanitized_user_message": "за какие годы в базе есть данные?",
|
||||
"tool_gate_decision": "run_address_lane",
|
||||
"tool_gate_reason": "address_mode_classifier_detected",
|
||||
"answer_structure_v11": null,
|
||||
"investigation_state_snapshot": null,
|
||||
"normalized": null,
|
||||
"normalizer_output": null
|
||||
},
|
||||
"error_code": null,
|
||||
"error_message": null
|
||||
},
|
||||
{
|
||||
"index": 2,
|
||||
"id": "Q2",
|
||||
"question": "Какой год самый активный по количеству документов?",
|
||||
"session": null,
|
||||
"session_id": "asst-2026-04-02_Address_General5_Live_Check_AfterFocusFix_04-q2",
|
||||
"status_code": 200,
|
||||
"ok": true,
|
||||
"elapsed_ms": 6067,
|
||||
"reply_type": "factual",
|
||||
"trace_id": "address-_kFbMGKC0d",
|
||||
"assistant_reply": "Профиль периодов базы собран (movement-based aggregate).\nСтрок агрегата: 134.\nСамый активный год по документам: 2019 (1004).\n1. 2019: 1004\n2. 2018: 703\n3. 2015: 671\n4. 2016: 577\n5. 2020: 536",
|
||||
"assistant_reply_first_line": "Профиль периодов базы собран (movement-based aggregate).",
|
||||
"expected_intent": "period_coverage_profile",
|
||||
"actual_intent": "period_coverage_profile",
|
||||
"intent_match": true,
|
||||
"expected_mode": "address_query",
|
||||
"actual_mode": "address_query",
|
||||
"mode_match": true,
|
||||
"expected_reply_type": null,
|
||||
"reply_match": true,
|
||||
"semantic_pass": true,
|
||||
"route_pass": true,
|
||||
"route_health": "ok_or_factual",
|
||||
"strict_policy": "route",
|
||||
"strict_pass": true,
|
||||
"selected_recipe": "address_period_coverage_profile_v1",
|
||||
"missing_required_filters": [],
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"rows_fetched": 134,
|
||||
"rows_matched": 134,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"limited_reason_category": null,
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_reason": "normalized_fragment_rejected_intent_conflict",
|
||||
"fallback_rule_hit": null,
|
||||
"debug_payload": {
|
||||
"trace_id": "address-_kFbMGKC0d",
|
||||
"prompt_version": "address_query_runtime_v1",
|
||||
"schema_version": "address_query_runtime_v1",
|
||||
"fallback_type": "none",
|
||||
"route_summary": null,
|
||||
"fragments": [],
|
||||
"requirements_extracted": [],
|
||||
"coverage_report": {
|
||||
"requirements_total": 0,
|
||||
"requirements_covered": 0,
|
||||
"requirements_uncovered": [],
|
||||
"requirements_partially_covered": [],
|
||||
"clarification_needed_for": [],
|
||||
"out_of_scope_requirements": []
|
||||
},
|
||||
"routes": [],
|
||||
"retrieval_status": [],
|
||||
"retrieval_results": [],
|
||||
"answer_grounding_check": {
|
||||
"status": "grounded",
|
||||
"route_subject_match": true,
|
||||
"missing_requirements": [],
|
||||
"reasons": [
|
||||
"management_profile_signal_detected",
|
||||
"document_list_signal_detected",
|
||||
"period_coverage_profile_signal_detected"
|
||||
],
|
||||
"why_included_summary": [],
|
||||
"selection_reason_summary": []
|
||||
},
|
||||
"dropped_intent_segments": [],
|
||||
"detected_mode": "address_query",
|
||||
"detected_mode_confidence": "medium",
|
||||
"query_shape": "DOCUMENT_LIST",
|
||||
"query_shape_confidence": "medium",
|
||||
"detected_intent": "period_coverage_profile",
|
||||
"detected_intent_confidence": "high",
|
||||
"extracted_filters": {
|
||||
"sort": "period_desc",
|
||||
"period_to": "2026-04-02"
|
||||
},
|
||||
"missing_required_filters": [],
|
||||
"selected_recipe": "address_period_coverage_profile_v1",
|
||||
"mcp_call_status_legacy": "matched_non_empty",
|
||||
"account_scope_mode": "preferred",
|
||||
"account_scope_fallback_applied": false,
|
||||
"anchor_type": "unknown",
|
||||
"anchor_value_raw": null,
|
||||
"anchor_value_resolved": null,
|
||||
"resolver_confidence": "low",
|
||||
"ambiguity_count": 0,
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"rows_fetched": 134,
|
||||
"raw_rows_received": 134,
|
||||
"rows_after_account_scope": 134,
|
||||
"rows_after_recipe_filter": 134,
|
||||
"rows_materialized": 134,
|
||||
"rows_matched": 134,
|
||||
"raw_row_keys_sample": [
|
||||
"Период",
|
||||
"Регистратор",
|
||||
"СчетДт",
|
||||
"СчетКт",
|
||||
"Сумма",
|
||||
"Period",
|
||||
"Registrator",
|
||||
"Amount"
|
||||
],
|
||||
"materialization_drop_reason": "none",
|
||||
"account_token_raw": null,
|
||||
"account_token_normalized": null,
|
||||
"account_scope_fields_checked": [
|
||||
"account_dt",
|
||||
"account_kt",
|
||||
"registrator",
|
||||
"analytics"
|
||||
],
|
||||
"account_scope_match_strategy": "account_code_regex_plus_alias_map_v1",
|
||||
"account_scope_drop_reason": "not_applicable",
|
||||
"runtime_readiness": "LIVE_QUERYABLE_WITH_LIMITS",
|
||||
"limited_reason_category": null,
|
||||
"response_type": "FACTUAL_SUMMARY",
|
||||
"execution_lane": "address_query",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_attempted": true,
|
||||
"llm_provider_used": "local",
|
||||
"llm_decomposition_trace_id": "2M199yWCsRuVEl",
|
||||
"llm_decomposition_effective_message": "Какой год самый активный по количеству документов?",
|
||||
"llm_decomposition_reason": "normalized_fragment_rejected_intent_conflict",
|
||||
"fallback_rule_hit": null,
|
||||
"sanitized_user_message": "какой год самый активный по количеству документов?",
|
||||
"tool_gate_decision": "run_address_lane",
|
||||
"tool_gate_reason": "address_mode_classifier_detected",
|
||||
"answer_structure_v11": null,
|
||||
"investigation_state_snapshot": null,
|
||||
"normalized": null,
|
||||
"normalizer_output": {
|
||||
"trace_id": "2M199yWCsRuVEl",
|
||||
"prompt_version": "normalizer_v2_0_2",
|
||||
"applied": false,
|
||||
"effective_message": "Какой год самый активный по количеству документов?"
|
||||
}
|
||||
},
|
||||
"error_code": null,
|
||||
"error_message": null
|
||||
},
|
||||
{
|
||||
"index": 3,
|
||||
"id": "Q3",
|
||||
"question": "Какой месяц самый активный по количеству операций?",
|
||||
"session": null,
|
||||
"session_id": "asst-2026-04-02_Address_General5_Live_Check_AfterFocusFix_04-q3",
|
||||
"status_code": 200,
|
||||
"ok": true,
|
||||
"elapsed_ms": 1035,
|
||||
"reply_type": "factual",
|
||||
"trace_id": "address-Yko0r2wuQx",
|
||||
"assistant_reply": "Профиль периодов базы собран (movement-based aggregate).\nСтрок агрегата: 134.\nСамый активный месяц по операциям: 2015-02 (1249).\n1. 2015-02: 1249\n2. 2015-01: 924\n3. 2018-08: 854\n4. 2019-05: 536\n5. 2017-12: 503",
|
||||
"assistant_reply_first_line": "Профиль периодов базы собран (movement-based aggregate).",
|
||||
"expected_intent": "period_coverage_profile",
|
||||
"actual_intent": "period_coverage_profile",
|
||||
"intent_match": true,
|
||||
"expected_mode": "address_query",
|
||||
"actual_mode": "address_query",
|
||||
"mode_match": true,
|
||||
"expected_reply_type": null,
|
||||
"reply_match": true,
|
||||
"semantic_pass": true,
|
||||
"route_pass": true,
|
||||
"route_health": "ok_or_factual",
|
||||
"strict_policy": "route",
|
||||
"strict_pass": true,
|
||||
"selected_recipe": "address_period_coverage_profile_v1",
|
||||
"missing_required_filters": [],
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"rows_fetched": 134,
|
||||
"rows_matched": 134,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"limited_reason_category": null,
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_reason": "not_address_like",
|
||||
"fallback_rule_hit": null,
|
||||
"debug_payload": {
|
||||
"trace_id": "address-Yko0r2wuQx",
|
||||
"prompt_version": "address_query_runtime_v1",
|
||||
"schema_version": "address_query_runtime_v1",
|
||||
"fallback_type": "none",
|
||||
"route_summary": null,
|
||||
"fragments": [],
|
||||
"requirements_extracted": [],
|
||||
"coverage_report": {
|
||||
"requirements_total": 0,
|
||||
"requirements_covered": 0,
|
||||
"requirements_uncovered": [],
|
||||
"requirements_partially_covered": [],
|
||||
"clarification_needed_for": [],
|
||||
"out_of_scope_requirements": []
|
||||
},
|
||||
"routes": [],
|
||||
"retrieval_status": [],
|
||||
"retrieval_results": [],
|
||||
"answer_grounding_check": {
|
||||
"status": "grounded",
|
||||
"route_subject_match": true,
|
||||
"missing_requirements": [],
|
||||
"reasons": [
|
||||
"management_profile_signal_detected",
|
||||
"shape_not_detected",
|
||||
"period_coverage_profile_signal_detected"
|
||||
],
|
||||
"why_included_summary": [],
|
||||
"selection_reason_summary": []
|
||||
},
|
||||
"dropped_intent_segments": [],
|
||||
"detected_mode": "address_query",
|
||||
"detected_mode_confidence": "medium",
|
||||
"query_shape": "UNKNOWN",
|
||||
"query_shape_confidence": "low",
|
||||
"detected_intent": "period_coverage_profile",
|
||||
"detected_intent_confidence": "high",
|
||||
"extracted_filters": {
|
||||
"sort": "period_desc",
|
||||
"period_to": "2026-04-02"
|
||||
},
|
||||
"missing_required_filters": [],
|
||||
"selected_recipe": "address_period_coverage_profile_v1",
|
||||
"mcp_call_status_legacy": "matched_non_empty",
|
||||
"account_scope_mode": "preferred",
|
||||
"account_scope_fallback_applied": false,
|
||||
"anchor_type": "unknown",
|
||||
"anchor_value_raw": null,
|
||||
"anchor_value_resolved": null,
|
||||
"resolver_confidence": "low",
|
||||
"ambiguity_count": 0,
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"rows_fetched": 134,
|
||||
"raw_rows_received": 134,
|
||||
"rows_after_account_scope": 134,
|
||||
"rows_after_recipe_filter": 134,
|
||||
"rows_materialized": 134,
|
||||
"rows_matched": 134,
|
||||
"raw_row_keys_sample": [
|
||||
"Период",
|
||||
"Регистратор",
|
||||
"СчетДт",
|
||||
"СчетКт",
|
||||
"Сумма",
|
||||
"Period",
|
||||
"Registrator",
|
||||
"Amount"
|
||||
],
|
||||
"materialization_drop_reason": "none",
|
||||
"account_token_raw": null,
|
||||
"account_token_normalized": null,
|
||||
"account_scope_fields_checked": [
|
||||
"account_dt",
|
||||
"account_kt",
|
||||
"registrator",
|
||||
"analytics"
|
||||
],
|
||||
"account_scope_match_strategy": "account_code_regex_plus_alias_map_v1",
|
||||
"account_scope_drop_reason": "not_applicable",
|
||||
"runtime_readiness": "LIVE_QUERYABLE_WITH_LIMITS",
|
||||
"limited_reason_category": null,
|
||||
"response_type": "FACTUAL_SUMMARY",
|
||||
"execution_lane": "address_query",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_attempted": false,
|
||||
"llm_provider_used": "local",
|
||||
"llm_decomposition_trace_id": null,
|
||||
"llm_decomposition_effective_message": "Какой месяц самый активный по количеству операций?",
|
||||
"llm_decomposition_reason": "not_address_like",
|
||||
"fallback_rule_hit": null,
|
||||
"sanitized_user_message": "какой месяц самый активный по количеству операций?",
|
||||
"tool_gate_decision": "run_address_lane",
|
||||
"tool_gate_reason": "address_mode_classifier_detected",
|
||||
"answer_structure_v11": null,
|
||||
"investigation_state_snapshot": null,
|
||||
"normalized": null,
|
||||
"normalizer_output": null
|
||||
},
|
||||
"error_code": null,
|
||||
"error_message": null
|
||||
},
|
||||
{
|
||||
"index": 4,
|
||||
"id": "Q4",
|
||||
"question": "Какие типы документов используются чаще всего в базе?",
|
||||
"session": null,
|
||||
"session_id": "asst-2026-04-02_Address_General5_Live_Check_AfterFocusFix_04-q4",
|
||||
"status_code": 200,
|
||||
"ok": true,
|
||||
"elapsed_ms": 5138,
|
||||
"reply_type": "factual",
|
||||
"trace_id": "address-ABN02IDAER",
|
||||
"assistant_reply": "Профиль типов документов и разделов учета собран (movement-based aggregate).\nСтрок агрегата: 147.\nТоп типов документов (по числу уникальных регистраторов):\n1. Списание с расчетного счета: 2352 (52.6%)\n2. Поступление товаров и услуг: 486 (10.9%)\n3. Регламентная операция: 414 (9.3%)\n4. Поступление на расчетный счет: 323 (7.2%)\n5. Счет-фактура полученный: 261 (5.8%)\n6. Операция (бухгалтерский и налоговый учет): 147 (3.3%)\n7. Реализация товаров и услуг: 123 (2.8%)\n8. Отражение зарплаты в регламентированном учете: 87 (1.9%)\n9. Приходный кассовый ордер: 76 (1.7%)\n10. Расходный кассовый ордер: 73 (1.6%)",
|
||||
"assistant_reply_first_line": "Профиль типов документов и разделов учета собран (movement-based aggregate).",
|
||||
"expected_intent": "document_type_and_account_section_profile",
|
||||
"actual_intent": "document_type_and_account_section_profile",
|
||||
"intent_match": true,
|
||||
"expected_mode": "address_query",
|
||||
"actual_mode": "address_query",
|
||||
"mode_match": true,
|
||||
"expected_reply_type": null,
|
||||
"reply_match": true,
|
||||
"semantic_pass": true,
|
||||
"route_pass": true,
|
||||
"route_health": "ok_or_factual",
|
||||
"strict_policy": "route",
|
||||
"strict_pass": true,
|
||||
"selected_recipe": "address_document_type_and_account_section_profile_v1",
|
||||
"missing_required_filters": [],
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"rows_fetched": 147,
|
||||
"rows_matched": 147,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"limited_reason_category": null,
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_reason": "normalized_fragment_same",
|
||||
"fallback_rule_hit": null,
|
||||
"debug_payload": {
|
||||
"trace_id": "address-ABN02IDAER",
|
||||
"prompt_version": "address_query_runtime_v1",
|
||||
"schema_version": "address_query_runtime_v1",
|
||||
"fallback_type": "none",
|
||||
"route_summary": null,
|
||||
"fragments": [],
|
||||
"requirements_extracted": [],
|
||||
"coverage_report": {
|
||||
"requirements_total": 0,
|
||||
"requirements_covered": 0,
|
||||
"requirements_uncovered": [],
|
||||
"requirements_partially_covered": [],
|
||||
"clarification_needed_for": [],
|
||||
"out_of_scope_requirements": []
|
||||
},
|
||||
"routes": [],
|
||||
"retrieval_status": [],
|
||||
"retrieval_results": [],
|
||||
"answer_grounding_check": {
|
||||
"status": "grounded",
|
||||
"route_subject_match": true,
|
||||
"missing_requirements": [],
|
||||
"reasons": [
|
||||
"address_action_detected",
|
||||
"address_entity_detected",
|
||||
"document_list_signal_detected",
|
||||
"document_type_and_account_section_profile_signal_detected"
|
||||
],
|
||||
"why_included_summary": [],
|
||||
"selection_reason_summary": []
|
||||
},
|
||||
"dropped_intent_segments": [],
|
||||
"detected_mode": "address_query",
|
||||
"detected_mode_confidence": "high",
|
||||
"query_shape": "DOCUMENT_LIST",
|
||||
"query_shape_confidence": "medium",
|
||||
"detected_intent": "document_type_and_account_section_profile",
|
||||
"detected_intent_confidence": "high",
|
||||
"extracted_filters": {
|
||||
"sort": "period_desc",
|
||||
"period_to": "2026-04-02"
|
||||
},
|
||||
"missing_required_filters": [],
|
||||
"selected_recipe": "address_document_type_and_account_section_profile_v1",
|
||||
"mcp_call_status_legacy": "matched_non_empty",
|
||||
"account_scope_mode": "preferred",
|
||||
"account_scope_fallback_applied": false,
|
||||
"anchor_type": "unknown",
|
||||
"anchor_value_raw": null,
|
||||
"anchor_value_resolved": null,
|
||||
"resolver_confidence": "low",
|
||||
"ambiguity_count": 0,
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"rows_fetched": 147,
|
||||
"raw_rows_received": 147,
|
||||
"rows_after_account_scope": 147,
|
||||
"rows_after_recipe_filter": 147,
|
||||
"rows_materialized": 147,
|
||||
"rows_matched": 147,
|
||||
"raw_row_keys_sample": [
|
||||
"Период",
|
||||
"Регистратор",
|
||||
"СчетДт",
|
||||
"СчетКт",
|
||||
"Сумма",
|
||||
"Period",
|
||||
"Registrator",
|
||||
"AccountDt",
|
||||
"Amount"
|
||||
],
|
||||
"materialization_drop_reason": "none",
|
||||
"account_token_raw": null,
|
||||
"account_token_normalized": null,
|
||||
"account_scope_fields_checked": [
|
||||
"account_dt",
|
||||
"account_kt",
|
||||
"registrator",
|
||||
"analytics"
|
||||
],
|
||||
"account_scope_match_strategy": "account_code_regex_plus_alias_map_v1",
|
||||
"account_scope_drop_reason": "not_applicable",
|
||||
"runtime_readiness": "LIVE_QUERYABLE_WITH_LIMITS",
|
||||
"limited_reason_category": null,
|
||||
"response_type": "FACTUAL_SUMMARY",
|
||||
"execution_lane": "address_query",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_attempted": true,
|
||||
"llm_provider_used": "local",
|
||||
"llm_decomposition_trace_id": "Wr7ac2wuNb5EXA",
|
||||
"llm_decomposition_effective_message": "Какие типы документов используются чаще всего в базе?",
|
||||
"llm_decomposition_reason": "normalized_fragment_same",
|
||||
"fallback_rule_hit": null,
|
||||
"sanitized_user_message": "какие типы документов используются чаще всего в базе?",
|
||||
"tool_gate_decision": "run_address_lane",
|
||||
"tool_gate_reason": "address_mode_classifier_detected",
|
||||
"answer_structure_v11": null,
|
||||
"investigation_state_snapshot": null,
|
||||
"normalized": null,
|
||||
"normalizer_output": {
|
||||
"trace_id": "Wr7ac2wuNb5EXA",
|
||||
"prompt_version": "normalizer_v2_0_2",
|
||||
"applied": false,
|
||||
"effective_message": "Какие типы документов используются чаще всего в базе?"
|
||||
}
|
||||
},
|
||||
"error_code": null,
|
||||
"error_message": null
|
||||
},
|
||||
{
|
||||
"index": 5,
|
||||
"id": "Q5",
|
||||
"question": "Какие разделы учета наиболее заполнены и какие почти не используются?",
|
||||
"session": null,
|
||||
"session_id": "asst-2026-04-02_Address_General5_Live_Check_AfterFocusFix_04-q5",
|
||||
"status_code": 200,
|
||||
"ok": true,
|
||||
"elapsed_ms": 975,
|
||||
"reply_type": "factual",
|
||||
"trace_id": "address-9KxpfWz3qt",
|
||||
"assistant_reply": "Профиль типов документов и разделов учета собран (movement-based aggregate).\nСтрок агрегата: 147.\nНаиболее заполненные разделы учета (по операциям Дт+Кт):\n1. 90 (Продажи): 2973 (12.1%)\n2. 51 (Расчетные счета): 2967 (12.1%)\n3. 60 (Расчеты с поставщиками и подрядчиками): 2793 (11.4%)\n4. 44 (Расходы на продажу): 2422 (9.9%)\n5. 68 (Расчеты по налогам и сборам): 1553 (6.3%)\n6. 10 (Материалы): 1494 (6.1%)\n7. 19 (НДС по приобретенным ценностям): 1489 (6.1%)\n8. 91 (Прочие доходы и расходы): 1324 (5.4%)\n9. 41 (Товары): 1312 (5.3%)\n10. 76 (Расчеты с разными дебиторами и кредиторами): 1240 (5.0%)\nРазделы с минимальной активностью (среди использованных):\n1. 58 (Финансовые вложения): 2\n2. 81 (Собственные акции (доли)): 2\n3. 80 (Уставный капитал): 5\n4. 03: 6\n5. 04 (Нематериальные активы): 6\n6. 75 (Расчеты с учредителями): 16\n7. 55 (Специальные счета в банках): 18\n8. 84 (Нераспределенная прибыль (непокрытый убыток)): 20\n9. 26 (Общехозяйственные расходы): 51\n10. 71 (Расчеты с подотчетными лицами): 76",
|
||||
"assistant_reply_first_line": "Профиль типов документов и разделов учета собран (movement-based aggregate).",
|
||||
"expected_intent": "document_type_and_account_section_profile",
|
||||
"actual_intent": "document_type_and_account_section_profile",
|
||||
"intent_match": true,
|
||||
"expected_mode": "address_query",
|
||||
"actual_mode": "address_query",
|
||||
"mode_match": true,
|
||||
"expected_reply_type": null,
|
||||
"reply_match": true,
|
||||
"semantic_pass": true,
|
||||
"route_pass": true,
|
||||
"route_health": "ok_or_factual",
|
||||
"strict_policy": "route",
|
||||
"strict_pass": true,
|
||||
"selected_recipe": "address_document_type_and_account_section_profile_v1",
|
||||
"missing_required_filters": [],
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"rows_fetched": 147,
|
||||
"rows_matched": 147,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"limited_reason_category": null,
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_reason": "not_address_like",
|
||||
"fallback_rule_hit": null,
|
||||
"debug_payload": {
|
||||
"trace_id": "address-9KxpfWz3qt",
|
||||
"prompt_version": "address_query_runtime_v1",
|
||||
"schema_version": "address_query_runtime_v1",
|
||||
"fallback_type": "none",
|
||||
"route_summary": null,
|
||||
"fragments": [],
|
||||
"requirements_extracted": [],
|
||||
"coverage_report": {
|
||||
"requirements_total": 0,
|
||||
"requirements_covered": 0,
|
||||
"requirements_uncovered": [],
|
||||
"requirements_partially_covered": [],
|
||||
"clarification_needed_for": [],
|
||||
"out_of_scope_requirements": []
|
||||
},
|
||||
"routes": [],
|
||||
"retrieval_status": [],
|
||||
"retrieval_results": [],
|
||||
"answer_grounding_check": {
|
||||
"status": "grounded",
|
||||
"route_subject_match": true,
|
||||
"missing_requirements": [],
|
||||
"reasons": [
|
||||
"management_profile_signal_detected",
|
||||
"shape_not_detected",
|
||||
"document_type_and_account_section_profile_signal_detected"
|
||||
],
|
||||
"why_included_summary": [],
|
||||
"selection_reason_summary": []
|
||||
},
|
||||
"dropped_intent_segments": [],
|
||||
"detected_mode": "address_query",
|
||||
"detected_mode_confidence": "medium",
|
||||
"query_shape": "UNKNOWN",
|
||||
"query_shape_confidence": "low",
|
||||
"detected_intent": "document_type_and_account_section_profile",
|
||||
"detected_intent_confidence": "high",
|
||||
"extracted_filters": {
|
||||
"sort": "period_desc",
|
||||
"period_to": "2026-04-02"
|
||||
},
|
||||
"missing_required_filters": [],
|
||||
"selected_recipe": "address_document_type_and_account_section_profile_v1",
|
||||
"mcp_call_status_legacy": "matched_non_empty",
|
||||
"account_scope_mode": "preferred",
|
||||
"account_scope_fallback_applied": false,
|
||||
"anchor_type": "unknown",
|
||||
"anchor_value_raw": null,
|
||||
"anchor_value_resolved": null,
|
||||
"resolver_confidence": "low",
|
||||
"ambiguity_count": 0,
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"rows_fetched": 147,
|
||||
"raw_rows_received": 147,
|
||||
"rows_after_account_scope": 147,
|
||||
"rows_after_recipe_filter": 147,
|
||||
"rows_materialized": 147,
|
||||
"rows_matched": 147,
|
||||
"raw_row_keys_sample": [
|
||||
"Период",
|
||||
"Регистратор",
|
||||
"СчетДт",
|
||||
"СчетКт",
|
||||
"Сумма",
|
||||
"Period",
|
||||
"Registrator",
|
||||
"AccountDt",
|
||||
"Amount"
|
||||
],
|
||||
"materialization_drop_reason": "none",
|
||||
"account_token_raw": null,
|
||||
"account_token_normalized": null,
|
||||
"account_scope_fields_checked": [
|
||||
"account_dt",
|
||||
"account_kt",
|
||||
"registrator",
|
||||
"analytics"
|
||||
],
|
||||
"account_scope_match_strategy": "account_code_regex_plus_alias_map_v1",
|
||||
"account_scope_drop_reason": "not_applicable",
|
||||
"runtime_readiness": "LIVE_QUERYABLE_WITH_LIMITS",
|
||||
"limited_reason_category": null,
|
||||
"response_type": "FACTUAL_SUMMARY",
|
||||
"execution_lane": "address_query",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_attempted": false,
|
||||
"llm_provider_used": "local",
|
||||
"llm_decomposition_trace_id": null,
|
||||
"llm_decomposition_effective_message": "Какие разделы учета наиболее заполнены и какие почти не используются?",
|
||||
"llm_decomposition_reason": "not_address_like",
|
||||
"fallback_rule_hit": null,
|
||||
"sanitized_user_message": "какие разделы учета наиболее заполнены и какие почти не используются?",
|
||||
"tool_gate_decision": "run_address_lane",
|
||||
"tool_gate_reason": "address_mode_classifier_detected",
|
||||
"answer_structure_v11": null,
|
||||
"investigation_state_snapshot": null,
|
||||
"normalized": null,
|
||||
"normalizer_output": null
|
||||
},
|
||||
"error_code": null,
|
||||
"error_message": null
|
||||
}
|
||||
]
|
||||
}
|
||||
+9
@@ -0,0 +1,9 @@
|
||||
# Response Audit: 2026-04-02_Address_General5_Live_Check_AfterFocusFix_04
|
||||
|
||||
| id | strict | route_health | reply_type | intent | limited_reason | question | assistant_first_line |
|
||||
|---|---|---|---|---|---|---|---|
|
||||
| Q1 | True | ok_or_factual | factual | period_coverage_profile | None | За какие годы в базе есть данные? | Профиль периодов базы собран (movement-based aggregate). |
|
||||
| Q2 | True | ok_or_factual | factual | period_coverage_profile | None | Какой год самый активный по количеству документов? | Профиль периодов базы собран (movement-based aggregate). |
|
||||
| Q3 | True | ok_or_factual | factual | period_coverage_profile | None | Какой месяц самый активный по количеству операций? | Профиль периодов базы собран (movement-based aggregate). |
|
||||
| Q4 | True | ok_or_factual | factual | document_type_and_account_section_profile | None | Какие типы документов используются чаще всего в базе? | Профиль типов документов и разделов учета собран (movement-based aggregate). |
|
||||
| Q5 | True | ok_or_factual | factual | document_type_and_account_section_profile | None | Какие разделы учета наиболее заполнены и какие почти не используются? | Профиль типов документов и разделов учета собран (movement-based aggregate). |
|
||||
+45
@@ -0,0 +1,45 @@
|
||||
{
|
||||
"run_id": "2026-04-02_Address_General5_Live_Check_AfterFocusFix_04",
|
||||
"generated_at": "2026-04-02T20:11:30",
|
||||
"source_questions_file": "X:\\1C\\NDC_1C\\docs\\ADDRESS\\question_sets\\temp_general5_live_check_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": "route",
|
||||
"totals": {
|
||||
"questions_total": 5,
|
||||
"ok_200_count": 5,
|
||||
"semantic_pass_count": 5,
|
||||
"semantic_pass_rate": 1.0,
|
||||
"route_pass_count": 5,
|
||||
"route_pass_rate": 1.0,
|
||||
"strict_pass_count": 5,
|
||||
"strict_pass_rate": 1.0,
|
||||
"factual_count": 5,
|
||||
"partial_coverage_count": 0,
|
||||
"clarification_required_count": 0,
|
||||
"http_error_count": 0,
|
||||
"llm_decomposition_applied_count": 0,
|
||||
"avg_elapsed_ms": 2712.4
|
||||
},
|
||||
"distributions": {
|
||||
"reply_type": {
|
||||
"factual": 5
|
||||
},
|
||||
"actual_intent": {
|
||||
"period_coverage_profile": 3,
|
||||
"document_type_and_account_section_profile": 2
|
||||
},
|
||||
"actual_mode": {
|
||||
"address_query": 5
|
||||
},
|
||||
"mcp_call_status": {
|
||||
"matched_non_empty": 5
|
||||
},
|
||||
"limited_reason_category": {},
|
||||
"route_health": {
|
||||
"ok_or_factual": 5
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,28 @@
|
||||
# 2026-04-02_Address_General5_Live_Check_AfterNextPack
|
||||
|
||||
Generated at: 2026-04-02T21:06:53
|
||||
Questions file: X:\1C\NDC_1C\docs\ADDRESS\question_sets\temp_general5_live_check_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: 5
|
||||
- ok_200_count: 5
|
||||
- semantic_pass_count: 5
|
||||
- semantic_pass_rate: 1.0
|
||||
- route_pass_count: 5
|
||||
- route_pass_rate: 1.0
|
||||
- strict_pass_count: 5
|
||||
- strict_pass_rate: 1.0
|
||||
- factual_count: 5
|
||||
- partial_coverage_count: 0
|
||||
- clarification_required_count: 0
|
||||
- http_error_count: 0
|
||||
- llm_decomposition_applied_count: 0
|
||||
- avg_elapsed_ms: 3653.8
|
||||
|
||||
## Files
|
||||
- run_summary.json
|
||||
- full_live_results.json
|
||||
- failures_only.json
|
||||
+1
@@ -0,0 +1 @@
|
||||
[]
|
||||
+769
@@ -0,0 +1,769 @@
|
||||
{
|
||||
"run_id": "2026-04-02_Address_General5_Live_Check_AfterNextPack",
|
||||
"generated_at": "2026-04-02T21:06:53",
|
||||
"summary": {
|
||||
"run_id": "2026-04-02_Address_General5_Live_Check_AfterNextPack",
|
||||
"generated_at": "2026-04-02T21:06:53",
|
||||
"source_questions_file": "X:\\1C\\NDC_1C\\docs\\ADDRESS\\question_sets\\temp_general5_live_check_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": 5,
|
||||
"ok_200_count": 5,
|
||||
"semantic_pass_count": 5,
|
||||
"semantic_pass_rate": 1.0,
|
||||
"route_pass_count": 5,
|
||||
"route_pass_rate": 1.0,
|
||||
"strict_pass_count": 5,
|
||||
"strict_pass_rate": 1.0,
|
||||
"factual_count": 5,
|
||||
"partial_coverage_count": 0,
|
||||
"clarification_required_count": 0,
|
||||
"http_error_count": 0,
|
||||
"llm_decomposition_applied_count": 0,
|
||||
"avg_elapsed_ms": 3653.8
|
||||
},
|
||||
"distributions": {
|
||||
"reply_type": {
|
||||
"factual": 5
|
||||
},
|
||||
"actual_intent": {
|
||||
"period_coverage_profile": 3,
|
||||
"document_type_and_account_section_profile": 2
|
||||
},
|
||||
"actual_mode": {
|
||||
"address_query": 5
|
||||
},
|
||||
"mcp_call_status": {
|
||||
"matched_non_empty": 5
|
||||
},
|
||||
"limited_reason_category": {},
|
||||
"route_health": {
|
||||
"ok_or_factual": 5
|
||||
}
|
||||
}
|
||||
},
|
||||
"rows": [
|
||||
{
|
||||
"index": 1,
|
||||
"id": "Q1",
|
||||
"question": "За какие годы в базе есть данные?",
|
||||
"session": null,
|
||||
"session_id": "asst-2026-04-02_Address_General5_Live_Check_AfterNextPack-q1",
|
||||
"status_code": 200,
|
||||
"ok": true,
|
||||
"elapsed_ms": 905,
|
||||
"reply_type": "factual",
|
||||
"trace_id": "address-8J2hUefXpX",
|
||||
"assistant_reply": "Профиль периодов базы собран (movement-based aggregate).\nСтрок агрегата: 134.\nОперационный период с выраженной активностью: 2014..2022.\nНизкоактивный хвост (единичные записи): 2023, 2025, 2026.\nПолный технический диапазон дат: 2014-05-27T12:00:00Z.. 2026-03-31T00:00:00Z.",
|
||||
"assistant_reply_first_line": "Профиль периодов базы собран (movement-based aggregate).",
|
||||
"expected_intent": "period_coverage_profile",
|
||||
"actual_intent": "period_coverage_profile",
|
||||
"intent_match": true,
|
||||
"expected_mode": "address_query",
|
||||
"actual_mode": "address_query",
|
||||
"mode_match": true,
|
||||
"expected_reply_type": null,
|
||||
"reply_match": true,
|
||||
"semantic_pass": true,
|
||||
"route_pass": true,
|
||||
"route_health": "ok_or_factual",
|
||||
"strict_policy": "factual",
|
||||
"strict_pass": true,
|
||||
"selected_recipe": "address_period_coverage_profile_v1",
|
||||
"missing_required_filters": [],
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"rows_fetched": 134,
|
||||
"rows_matched": 134,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"limited_reason_category": null,
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_reason": "not_address_like",
|
||||
"fallback_rule_hit": null,
|
||||
"debug_payload": {
|
||||
"trace_id": "address-8J2hUefXpX",
|
||||
"prompt_version": "address_query_runtime_v1",
|
||||
"schema_version": "address_query_runtime_v1",
|
||||
"fallback_type": "none",
|
||||
"route_summary": null,
|
||||
"fragments": [],
|
||||
"requirements_extracted": [],
|
||||
"coverage_report": {
|
||||
"requirements_total": 0,
|
||||
"requirements_covered": 0,
|
||||
"requirements_uncovered": [],
|
||||
"requirements_partially_covered": [],
|
||||
"clarification_needed_for": [],
|
||||
"out_of_scope_requirements": []
|
||||
},
|
||||
"routes": [],
|
||||
"retrieval_status": [],
|
||||
"retrieval_results": [],
|
||||
"answer_grounding_check": {
|
||||
"status": "grounded",
|
||||
"route_subject_match": true,
|
||||
"missing_requirements": [],
|
||||
"reasons": [
|
||||
"management_profile_signal_detected",
|
||||
"shape_not_detected",
|
||||
"period_coverage_profile_signal_detected"
|
||||
],
|
||||
"why_included_summary": [],
|
||||
"selection_reason_summary": []
|
||||
},
|
||||
"dropped_intent_segments": [],
|
||||
"detected_mode": "address_query",
|
||||
"detected_mode_confidence": "medium",
|
||||
"query_shape": "UNKNOWN",
|
||||
"query_shape_confidence": "low",
|
||||
"detected_intent": "period_coverage_profile",
|
||||
"detected_intent_confidence": "high",
|
||||
"extracted_filters": {
|
||||
"sort": "period_desc",
|
||||
"period_to": "2026-04-02"
|
||||
},
|
||||
"missing_required_filters": [],
|
||||
"selected_recipe": "address_period_coverage_profile_v1",
|
||||
"mcp_call_status_legacy": "matched_non_empty",
|
||||
"account_scope_mode": "preferred",
|
||||
"account_scope_fallback_applied": false,
|
||||
"anchor_type": "unknown",
|
||||
"anchor_value_raw": null,
|
||||
"anchor_value_resolved": null,
|
||||
"resolver_confidence": "low",
|
||||
"ambiguity_count": 0,
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"rows_fetched": 134,
|
||||
"raw_rows_received": 134,
|
||||
"rows_after_account_scope": 134,
|
||||
"rows_after_recipe_filter": 134,
|
||||
"rows_materialized": 134,
|
||||
"rows_matched": 134,
|
||||
"raw_row_keys_sample": [
|
||||
"Период",
|
||||
"Регистратор",
|
||||
"СчетДт",
|
||||
"СчетКт",
|
||||
"Сумма",
|
||||
"Period",
|
||||
"Registrator",
|
||||
"Amount"
|
||||
],
|
||||
"materialization_drop_reason": "none",
|
||||
"account_token_raw": null,
|
||||
"account_token_normalized": null,
|
||||
"account_scope_fields_checked": [
|
||||
"account_dt",
|
||||
"account_kt",
|
||||
"registrator",
|
||||
"analytics"
|
||||
],
|
||||
"account_scope_match_strategy": "account_code_regex_plus_alias_map_v1",
|
||||
"account_scope_drop_reason": "not_applicable",
|
||||
"runtime_readiness": "LIVE_QUERYABLE_WITH_LIMITS",
|
||||
"limited_reason_category": null,
|
||||
"response_type": "FACTUAL_SUMMARY",
|
||||
"execution_lane": "address_query",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_attempted": false,
|
||||
"llm_provider_used": "local",
|
||||
"llm_decomposition_trace_id": null,
|
||||
"llm_decomposition_effective_message": "За какие годы в базе есть данные?",
|
||||
"llm_decomposition_reason": "not_address_like",
|
||||
"fallback_rule_hit": null,
|
||||
"sanitized_user_message": "за какие годы в базе есть данные?",
|
||||
"tool_gate_decision": "run_address_lane",
|
||||
"tool_gate_reason": "address_mode_classifier_detected",
|
||||
"answer_structure_v11": null,
|
||||
"investigation_state_snapshot": null,
|
||||
"normalized": null,
|
||||
"normalizer_output": null
|
||||
},
|
||||
"error_code": null,
|
||||
"error_message": null
|
||||
},
|
||||
{
|
||||
"index": 2,
|
||||
"id": "Q2",
|
||||
"question": "Какой год самый активный по количеству документов?",
|
||||
"session": null,
|
||||
"session_id": "asst-2026-04-02_Address_General5_Live_Check_AfterNextPack-q2",
|
||||
"status_code": 200,
|
||||
"ok": true,
|
||||
"elapsed_ms": 7055,
|
||||
"reply_type": "factual",
|
||||
"trace_id": "address-B_bb26I1tB",
|
||||
"assistant_reply": "Профиль периодов базы собран (movement-based aggregate).\nСтрок агрегата: 134.\nСамый активный год по документам: 2019 (1004).\n1. 2019: 1004\n2. 2018: 703\n3. 2015: 671\n4. 2016: 577\n5. 2020: 536",
|
||||
"assistant_reply_first_line": "Профиль периодов базы собран (movement-based aggregate).",
|
||||
"expected_intent": "period_coverage_profile",
|
||||
"actual_intent": "period_coverage_profile",
|
||||
"intent_match": true,
|
||||
"expected_mode": "address_query",
|
||||
"actual_mode": "address_query",
|
||||
"mode_match": true,
|
||||
"expected_reply_type": null,
|
||||
"reply_match": true,
|
||||
"semantic_pass": true,
|
||||
"route_pass": true,
|
||||
"route_health": "ok_or_factual",
|
||||
"strict_policy": "factual",
|
||||
"strict_pass": true,
|
||||
"selected_recipe": "address_period_coverage_profile_v1",
|
||||
"missing_required_filters": [],
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"rows_fetched": 134,
|
||||
"rows_matched": 134,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"limited_reason_category": null,
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_reason": "normalized_fragment_rejected_intent_conflict",
|
||||
"fallback_rule_hit": null,
|
||||
"debug_payload": {
|
||||
"trace_id": "address-B_bb26I1tB",
|
||||
"prompt_version": "address_query_runtime_v1",
|
||||
"schema_version": "address_query_runtime_v1",
|
||||
"fallback_type": "none",
|
||||
"route_summary": null,
|
||||
"fragments": [],
|
||||
"requirements_extracted": [],
|
||||
"coverage_report": {
|
||||
"requirements_total": 0,
|
||||
"requirements_covered": 0,
|
||||
"requirements_uncovered": [],
|
||||
"requirements_partially_covered": [],
|
||||
"clarification_needed_for": [],
|
||||
"out_of_scope_requirements": []
|
||||
},
|
||||
"routes": [],
|
||||
"retrieval_status": [],
|
||||
"retrieval_results": [],
|
||||
"answer_grounding_check": {
|
||||
"status": "grounded",
|
||||
"route_subject_match": true,
|
||||
"missing_requirements": [],
|
||||
"reasons": [
|
||||
"management_profile_signal_detected",
|
||||
"document_list_signal_detected",
|
||||
"period_coverage_profile_signal_detected"
|
||||
],
|
||||
"why_included_summary": [],
|
||||
"selection_reason_summary": []
|
||||
},
|
||||
"dropped_intent_segments": [],
|
||||
"detected_mode": "address_query",
|
||||
"detected_mode_confidence": "medium",
|
||||
"query_shape": "DOCUMENT_LIST",
|
||||
"query_shape_confidence": "medium",
|
||||
"detected_intent": "period_coverage_profile",
|
||||
"detected_intent_confidence": "high",
|
||||
"extracted_filters": {
|
||||
"sort": "period_desc",
|
||||
"period_to": "2026-04-02"
|
||||
},
|
||||
"missing_required_filters": [],
|
||||
"selected_recipe": "address_period_coverage_profile_v1",
|
||||
"mcp_call_status_legacy": "matched_non_empty",
|
||||
"account_scope_mode": "preferred",
|
||||
"account_scope_fallback_applied": false,
|
||||
"anchor_type": "unknown",
|
||||
"anchor_value_raw": null,
|
||||
"anchor_value_resolved": null,
|
||||
"resolver_confidence": "low",
|
||||
"ambiguity_count": 0,
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"rows_fetched": 134,
|
||||
"raw_rows_received": 134,
|
||||
"rows_after_account_scope": 134,
|
||||
"rows_after_recipe_filter": 134,
|
||||
"rows_materialized": 134,
|
||||
"rows_matched": 134,
|
||||
"raw_row_keys_sample": [
|
||||
"Период",
|
||||
"Регистратор",
|
||||
"СчетДт",
|
||||
"СчетКт",
|
||||
"Сумма",
|
||||
"Period",
|
||||
"Registrator",
|
||||
"Amount"
|
||||
],
|
||||
"materialization_drop_reason": "none",
|
||||
"account_token_raw": null,
|
||||
"account_token_normalized": null,
|
||||
"account_scope_fields_checked": [
|
||||
"account_dt",
|
||||
"account_kt",
|
||||
"registrator",
|
||||
"analytics"
|
||||
],
|
||||
"account_scope_match_strategy": "account_code_regex_plus_alias_map_v1",
|
||||
"account_scope_drop_reason": "not_applicable",
|
||||
"runtime_readiness": "LIVE_QUERYABLE_WITH_LIMITS",
|
||||
"limited_reason_category": null,
|
||||
"response_type": "FACTUAL_SUMMARY",
|
||||
"execution_lane": "address_query",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_attempted": true,
|
||||
"llm_provider_used": "local",
|
||||
"llm_decomposition_trace_id": "yaGqRP2q_a36DM",
|
||||
"llm_decomposition_effective_message": "Какой год самый активный по количеству документов?",
|
||||
"llm_decomposition_reason": "normalized_fragment_rejected_intent_conflict",
|
||||
"fallback_rule_hit": null,
|
||||
"sanitized_user_message": "какой год самый активный по количеству документов?",
|
||||
"tool_gate_decision": "run_address_lane",
|
||||
"tool_gate_reason": "address_mode_classifier_detected",
|
||||
"answer_structure_v11": null,
|
||||
"investigation_state_snapshot": null,
|
||||
"normalized": null,
|
||||
"normalizer_output": {
|
||||
"trace_id": "yaGqRP2q_a36DM",
|
||||
"prompt_version": "normalizer_v2_0_2",
|
||||
"applied": false,
|
||||
"effective_message": "Какой год самый активный по количеству документов?"
|
||||
}
|
||||
},
|
||||
"error_code": null,
|
||||
"error_message": null
|
||||
},
|
||||
{
|
||||
"index": 3,
|
||||
"id": "Q3",
|
||||
"question": "Какой месяц самый активный по количеству операций?",
|
||||
"session": null,
|
||||
"session_id": "asst-2026-04-02_Address_General5_Live_Check_AfterNextPack-q3",
|
||||
"status_code": 200,
|
||||
"ok": true,
|
||||
"elapsed_ms": 1998,
|
||||
"reply_type": "factual",
|
||||
"trace_id": "address-2qu73I71yI",
|
||||
"assistant_reply": "Профиль периодов базы собран (movement-based aggregate).\nСтрок агрегата: 134.\nСамый активный месяц по операциям: 2015-02 (1249).\n1. 2015-02: 1249\n2. 2015-01: 924\n3. 2018-08: 854\n4. 2019-05: 536\n5. 2017-12: 503",
|
||||
"assistant_reply_first_line": "Профиль периодов базы собран (movement-based aggregate).",
|
||||
"expected_intent": "period_coverage_profile",
|
||||
"actual_intent": "period_coverage_profile",
|
||||
"intent_match": true,
|
||||
"expected_mode": "address_query",
|
||||
"actual_mode": "address_query",
|
||||
"mode_match": true,
|
||||
"expected_reply_type": null,
|
||||
"reply_match": true,
|
||||
"semantic_pass": true,
|
||||
"route_pass": true,
|
||||
"route_health": "ok_or_factual",
|
||||
"strict_policy": "factual",
|
||||
"strict_pass": true,
|
||||
"selected_recipe": "address_period_coverage_profile_v1",
|
||||
"missing_required_filters": [],
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"rows_fetched": 134,
|
||||
"rows_matched": 134,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"limited_reason_category": null,
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_reason": "not_address_like",
|
||||
"fallback_rule_hit": null,
|
||||
"debug_payload": {
|
||||
"trace_id": "address-2qu73I71yI",
|
||||
"prompt_version": "address_query_runtime_v1",
|
||||
"schema_version": "address_query_runtime_v1",
|
||||
"fallback_type": "none",
|
||||
"route_summary": null,
|
||||
"fragments": [],
|
||||
"requirements_extracted": [],
|
||||
"coverage_report": {
|
||||
"requirements_total": 0,
|
||||
"requirements_covered": 0,
|
||||
"requirements_uncovered": [],
|
||||
"requirements_partially_covered": [],
|
||||
"clarification_needed_for": [],
|
||||
"out_of_scope_requirements": []
|
||||
},
|
||||
"routes": [],
|
||||
"retrieval_status": [],
|
||||
"retrieval_results": [],
|
||||
"answer_grounding_check": {
|
||||
"status": "grounded",
|
||||
"route_subject_match": true,
|
||||
"missing_requirements": [],
|
||||
"reasons": [
|
||||
"management_profile_signal_detected",
|
||||
"shape_not_detected",
|
||||
"period_coverage_profile_signal_detected"
|
||||
],
|
||||
"why_included_summary": [],
|
||||
"selection_reason_summary": []
|
||||
},
|
||||
"dropped_intent_segments": [],
|
||||
"detected_mode": "address_query",
|
||||
"detected_mode_confidence": "medium",
|
||||
"query_shape": "UNKNOWN",
|
||||
"query_shape_confidence": "low",
|
||||
"detected_intent": "period_coverage_profile",
|
||||
"detected_intent_confidence": "high",
|
||||
"extracted_filters": {
|
||||
"sort": "period_desc",
|
||||
"period_to": "2026-04-02"
|
||||
},
|
||||
"missing_required_filters": [],
|
||||
"selected_recipe": "address_period_coverage_profile_v1",
|
||||
"mcp_call_status_legacy": "matched_non_empty",
|
||||
"account_scope_mode": "preferred",
|
||||
"account_scope_fallback_applied": false,
|
||||
"anchor_type": "unknown",
|
||||
"anchor_value_raw": null,
|
||||
"anchor_value_resolved": null,
|
||||
"resolver_confidence": "low",
|
||||
"ambiguity_count": 0,
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"rows_fetched": 134,
|
||||
"raw_rows_received": 134,
|
||||
"rows_after_account_scope": 134,
|
||||
"rows_after_recipe_filter": 134,
|
||||
"rows_materialized": 134,
|
||||
"rows_matched": 134,
|
||||
"raw_row_keys_sample": [
|
||||
"Период",
|
||||
"Регистратор",
|
||||
"СчетДт",
|
||||
"СчетКт",
|
||||
"Сумма",
|
||||
"Period",
|
||||
"Registrator",
|
||||
"Amount"
|
||||
],
|
||||
"materialization_drop_reason": "none",
|
||||
"account_token_raw": null,
|
||||
"account_token_normalized": null,
|
||||
"account_scope_fields_checked": [
|
||||
"account_dt",
|
||||
"account_kt",
|
||||
"registrator",
|
||||
"analytics"
|
||||
],
|
||||
"account_scope_match_strategy": "account_code_regex_plus_alias_map_v1",
|
||||
"account_scope_drop_reason": "not_applicable",
|
||||
"runtime_readiness": "LIVE_QUERYABLE_WITH_LIMITS",
|
||||
"limited_reason_category": null,
|
||||
"response_type": "FACTUAL_SUMMARY",
|
||||
"execution_lane": "address_query",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_attempted": false,
|
||||
"llm_provider_used": "local",
|
||||
"llm_decomposition_trace_id": null,
|
||||
"llm_decomposition_effective_message": "Какой месяц самый активный по количеству операций?",
|
||||
"llm_decomposition_reason": "not_address_like",
|
||||
"fallback_rule_hit": null,
|
||||
"sanitized_user_message": "какой месяц самый активный по количеству операций?",
|
||||
"tool_gate_decision": "run_address_lane",
|
||||
"tool_gate_reason": "address_mode_classifier_detected",
|
||||
"answer_structure_v11": null,
|
||||
"investigation_state_snapshot": null,
|
||||
"normalized": null,
|
||||
"normalizer_output": null
|
||||
},
|
||||
"error_code": null,
|
||||
"error_message": null
|
||||
},
|
||||
{
|
||||
"index": 4,
|
||||
"id": "Q4",
|
||||
"question": "Какие типы документов используются чаще всего в базе?",
|
||||
"session": null,
|
||||
"session_id": "asst-2026-04-02_Address_General5_Live_Check_AfterNextPack-q4",
|
||||
"status_code": 200,
|
||||
"ok": true,
|
||||
"elapsed_ms": 7349,
|
||||
"reply_type": "factual",
|
||||
"trace_id": "address-7Vm8W8ioP-",
|
||||
"assistant_reply": "Профиль типов документов и разделов учета собран (movement-based aggregate).\nСтрок агрегата: 147.\nТоп типов документов (по числу уникальных регистраторов):\n1. Списание с расчетного счета: 2352 (52.6%)\n2. Поступление товаров и услуг: 486 (10.9%)\n3. Регламентная операция: 414 (9.3%)\n4. Поступление на расчетный счет: 323 (7.2%)\n5. Счет-фактура полученный: 261 (5.8%)\n6. Операция (бухгалтерский и налоговый учет): 147 (3.3%)\n7. Реализация товаров и услуг: 123 (2.8%)\n8. Отражение зарплаты в регламентированном учете: 87 (1.9%)\n9. Приходный кассовый ордер: 76 (1.7%)\n10. Расходный кассовый ордер: 73 (1.6%)",
|
||||
"assistant_reply_first_line": "Профиль типов документов и разделов учета собран (movement-based aggregate).",
|
||||
"expected_intent": "document_type_and_account_section_profile",
|
||||
"actual_intent": "document_type_and_account_section_profile",
|
||||
"intent_match": true,
|
||||
"expected_mode": "address_query",
|
||||
"actual_mode": "address_query",
|
||||
"mode_match": true,
|
||||
"expected_reply_type": null,
|
||||
"reply_match": true,
|
||||
"semantic_pass": true,
|
||||
"route_pass": true,
|
||||
"route_health": "ok_or_factual",
|
||||
"strict_policy": "factual",
|
||||
"strict_pass": true,
|
||||
"selected_recipe": "address_document_type_and_account_section_profile_v1",
|
||||
"missing_required_filters": [],
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"rows_fetched": 147,
|
||||
"rows_matched": 147,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"limited_reason_category": null,
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_reason": "normalized_fragment_same",
|
||||
"fallback_rule_hit": null,
|
||||
"debug_payload": {
|
||||
"trace_id": "address-7Vm8W8ioP-",
|
||||
"prompt_version": "address_query_runtime_v1",
|
||||
"schema_version": "address_query_runtime_v1",
|
||||
"fallback_type": "none",
|
||||
"route_summary": null,
|
||||
"fragments": [],
|
||||
"requirements_extracted": [],
|
||||
"coverage_report": {
|
||||
"requirements_total": 0,
|
||||
"requirements_covered": 0,
|
||||
"requirements_uncovered": [],
|
||||
"requirements_partially_covered": [],
|
||||
"clarification_needed_for": [],
|
||||
"out_of_scope_requirements": []
|
||||
},
|
||||
"routes": [],
|
||||
"retrieval_status": [],
|
||||
"retrieval_results": [],
|
||||
"answer_grounding_check": {
|
||||
"status": "grounded",
|
||||
"route_subject_match": true,
|
||||
"missing_requirements": [],
|
||||
"reasons": [
|
||||
"address_action_detected",
|
||||
"address_entity_detected",
|
||||
"document_list_signal_detected",
|
||||
"document_type_and_account_section_profile_signal_detected"
|
||||
],
|
||||
"why_included_summary": [],
|
||||
"selection_reason_summary": []
|
||||
},
|
||||
"dropped_intent_segments": [],
|
||||
"detected_mode": "address_query",
|
||||
"detected_mode_confidence": "high",
|
||||
"query_shape": "DOCUMENT_LIST",
|
||||
"query_shape_confidence": "medium",
|
||||
"detected_intent": "document_type_and_account_section_profile",
|
||||
"detected_intent_confidence": "high",
|
||||
"extracted_filters": {
|
||||
"sort": "period_desc",
|
||||
"period_to": "2026-04-02"
|
||||
},
|
||||
"missing_required_filters": [],
|
||||
"selected_recipe": "address_document_type_and_account_section_profile_v1",
|
||||
"mcp_call_status_legacy": "matched_non_empty",
|
||||
"account_scope_mode": "preferred",
|
||||
"account_scope_fallback_applied": false,
|
||||
"anchor_type": "unknown",
|
||||
"anchor_value_raw": null,
|
||||
"anchor_value_resolved": null,
|
||||
"resolver_confidence": "low",
|
||||
"ambiguity_count": 0,
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"rows_fetched": 147,
|
||||
"raw_rows_received": 147,
|
||||
"rows_after_account_scope": 147,
|
||||
"rows_after_recipe_filter": 147,
|
||||
"rows_materialized": 147,
|
||||
"rows_matched": 147,
|
||||
"raw_row_keys_sample": [
|
||||
"Период",
|
||||
"Регистратор",
|
||||
"СчетДт",
|
||||
"СчетКт",
|
||||
"Сумма",
|
||||
"Period",
|
||||
"Registrator",
|
||||
"AccountDt",
|
||||
"Amount"
|
||||
],
|
||||
"materialization_drop_reason": "none",
|
||||
"account_token_raw": null,
|
||||
"account_token_normalized": null,
|
||||
"account_scope_fields_checked": [
|
||||
"account_dt",
|
||||
"account_kt",
|
||||
"registrator",
|
||||
"analytics"
|
||||
],
|
||||
"account_scope_match_strategy": "account_code_regex_plus_alias_map_v1",
|
||||
"account_scope_drop_reason": "not_applicable",
|
||||
"runtime_readiness": "LIVE_QUERYABLE_WITH_LIMITS",
|
||||
"limited_reason_category": null,
|
||||
"response_type": "FACTUAL_SUMMARY",
|
||||
"execution_lane": "address_query",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_attempted": true,
|
||||
"llm_provider_used": "local",
|
||||
"llm_decomposition_trace_id": "HD-Gzx7qj5iYfQ",
|
||||
"llm_decomposition_effective_message": "Какие типы документов используются чаще всего в базе?",
|
||||
"llm_decomposition_reason": "normalized_fragment_same",
|
||||
"fallback_rule_hit": null,
|
||||
"sanitized_user_message": "какие типы документов используются чаще всего в базе?",
|
||||
"tool_gate_decision": "run_address_lane",
|
||||
"tool_gate_reason": "address_mode_classifier_detected",
|
||||
"answer_structure_v11": null,
|
||||
"investigation_state_snapshot": null,
|
||||
"normalized": null,
|
||||
"normalizer_output": {
|
||||
"trace_id": "HD-Gzx7qj5iYfQ",
|
||||
"prompt_version": "normalizer_v2_0_2",
|
||||
"applied": false,
|
||||
"effective_message": "Какие типы документов используются чаще всего в базе?"
|
||||
}
|
||||
},
|
||||
"error_code": null,
|
||||
"error_message": null
|
||||
},
|
||||
{
|
||||
"index": 5,
|
||||
"id": "Q5",
|
||||
"question": "Какие разделы учета наиболее заполнены и какие почти не используются?",
|
||||
"session": null,
|
||||
"session_id": "asst-2026-04-02_Address_General5_Live_Check_AfterNextPack-q5",
|
||||
"status_code": 200,
|
||||
"ok": true,
|
||||
"elapsed_ms": 962,
|
||||
"reply_type": "factual",
|
||||
"trace_id": "address-TbMJKjcLPN",
|
||||
"assistant_reply": "Профиль типов документов и разделов учета собран (movement-based aggregate).\nСтрок агрегата: 147.\nНаиболее заполненные разделы учета (по операциям Дт+Кт):\n1. 90 (Продажи): 2973 (12.1%)\n2. 51 (Расчетные счета): 2967 (12.1%)\n3. 60 (Расчеты с поставщиками и подрядчиками): 2793 (11.4%)\n4. 44 (Расходы на продажу): 2422 (9.9%)\n5. 68 (Расчеты по налогам и сборам): 1553 (6.3%)\n6. 10 (Материалы): 1494 (6.1%)\n7. 19 (НДС по приобретенным ценностям): 1489 (6.1%)\n8. 91 (Прочие доходы и расходы): 1324 (5.4%)\n9. 41 (Товары): 1312 (5.3%)\n10. 76 (Расчеты с разными дебиторами и кредиторами): 1240 (5.0%)\nРазделы с минимальной активностью (среди использованных):\n1. 58 (Финансовые вложения): 2\n2. 81 (Собственные акции (доли)): 2\n3. 80 (Уставный капитал): 5\n4. 03: 6\n5. 04 (Нематериальные активы): 6\n6. 75 (Расчеты с учредителями): 16\n7. 55 (Специальные счета в банках): 18\n8. 84 (Нераспределенная прибыль (непокрытый убыток)): 20\n9. 26 (Общехозяйственные расходы): 51\n10. 71 (Расчеты с подотчетными лицами): 76",
|
||||
"assistant_reply_first_line": "Профиль типов документов и разделов учета собран (movement-based aggregate).",
|
||||
"expected_intent": "document_type_and_account_section_profile",
|
||||
"actual_intent": "document_type_and_account_section_profile",
|
||||
"intent_match": true,
|
||||
"expected_mode": "address_query",
|
||||
"actual_mode": "address_query",
|
||||
"mode_match": true,
|
||||
"expected_reply_type": null,
|
||||
"reply_match": true,
|
||||
"semantic_pass": true,
|
||||
"route_pass": true,
|
||||
"route_health": "ok_or_factual",
|
||||
"strict_policy": "factual",
|
||||
"strict_pass": true,
|
||||
"selected_recipe": "address_document_type_and_account_section_profile_v1",
|
||||
"missing_required_filters": [],
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"rows_fetched": 147,
|
||||
"rows_matched": 147,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"limited_reason_category": null,
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_reason": "not_address_like",
|
||||
"fallback_rule_hit": null,
|
||||
"debug_payload": {
|
||||
"trace_id": "address-TbMJKjcLPN",
|
||||
"prompt_version": "address_query_runtime_v1",
|
||||
"schema_version": "address_query_runtime_v1",
|
||||
"fallback_type": "none",
|
||||
"route_summary": null,
|
||||
"fragments": [],
|
||||
"requirements_extracted": [],
|
||||
"coverage_report": {
|
||||
"requirements_total": 0,
|
||||
"requirements_covered": 0,
|
||||
"requirements_uncovered": [],
|
||||
"requirements_partially_covered": [],
|
||||
"clarification_needed_for": [],
|
||||
"out_of_scope_requirements": []
|
||||
},
|
||||
"routes": [],
|
||||
"retrieval_status": [],
|
||||
"retrieval_results": [],
|
||||
"answer_grounding_check": {
|
||||
"status": "grounded",
|
||||
"route_subject_match": true,
|
||||
"missing_requirements": [],
|
||||
"reasons": [
|
||||
"management_profile_signal_detected",
|
||||
"shape_not_detected",
|
||||
"document_type_and_account_section_profile_signal_detected"
|
||||
],
|
||||
"why_included_summary": [],
|
||||
"selection_reason_summary": []
|
||||
},
|
||||
"dropped_intent_segments": [],
|
||||
"detected_mode": "address_query",
|
||||
"detected_mode_confidence": "medium",
|
||||
"query_shape": "UNKNOWN",
|
||||
"query_shape_confidence": "low",
|
||||
"detected_intent": "document_type_and_account_section_profile",
|
||||
"detected_intent_confidence": "high",
|
||||
"extracted_filters": {
|
||||
"sort": "period_desc",
|
||||
"period_to": "2026-04-02"
|
||||
},
|
||||
"missing_required_filters": [],
|
||||
"selected_recipe": "address_document_type_and_account_section_profile_v1",
|
||||
"mcp_call_status_legacy": "matched_non_empty",
|
||||
"account_scope_mode": "preferred",
|
||||
"account_scope_fallback_applied": false,
|
||||
"anchor_type": "unknown",
|
||||
"anchor_value_raw": null,
|
||||
"anchor_value_resolved": null,
|
||||
"resolver_confidence": "low",
|
||||
"ambiguity_count": 0,
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"rows_fetched": 147,
|
||||
"raw_rows_received": 147,
|
||||
"rows_after_account_scope": 147,
|
||||
"rows_after_recipe_filter": 147,
|
||||
"rows_materialized": 147,
|
||||
"rows_matched": 147,
|
||||
"raw_row_keys_sample": [
|
||||
"Период",
|
||||
"Регистратор",
|
||||
"СчетДт",
|
||||
"СчетКт",
|
||||
"Сумма",
|
||||
"Period",
|
||||
"Registrator",
|
||||
"AccountDt",
|
||||
"Amount"
|
||||
],
|
||||
"materialization_drop_reason": "none",
|
||||
"account_token_raw": null,
|
||||
"account_token_normalized": null,
|
||||
"account_scope_fields_checked": [
|
||||
"account_dt",
|
||||
"account_kt",
|
||||
"registrator",
|
||||
"analytics"
|
||||
],
|
||||
"account_scope_match_strategy": "account_code_regex_plus_alias_map_v1",
|
||||
"account_scope_drop_reason": "not_applicable",
|
||||
"runtime_readiness": "LIVE_QUERYABLE_WITH_LIMITS",
|
||||
"limited_reason_category": null,
|
||||
"response_type": "FACTUAL_SUMMARY",
|
||||
"execution_lane": "address_query",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_attempted": false,
|
||||
"llm_provider_used": "local",
|
||||
"llm_decomposition_trace_id": null,
|
||||
"llm_decomposition_effective_message": "Какие разделы учета наиболее заполнены и какие почти не используются?",
|
||||
"llm_decomposition_reason": "not_address_like",
|
||||
"fallback_rule_hit": null,
|
||||
"sanitized_user_message": "какие разделы учета наиболее заполнены и какие почти не используются?",
|
||||
"tool_gate_decision": "run_address_lane",
|
||||
"tool_gate_reason": "address_mode_classifier_detected",
|
||||
"answer_structure_v11": null,
|
||||
"investigation_state_snapshot": null,
|
||||
"normalized": null,
|
||||
"normalizer_output": null
|
||||
},
|
||||
"error_code": null,
|
||||
"error_message": null
|
||||
}
|
||||
]
|
||||
}
|
||||
+9
@@ -0,0 +1,9 @@
|
||||
# Response Audit: 2026-04-02_Address_General5_Live_Check_AfterNextPack
|
||||
|
||||
| id | strict | route_health | reply_type | intent | limited_reason | question | assistant_first_line |
|
||||
|---|---|---|---|---|---|---|---|
|
||||
| Q1 | True | ok_or_factual | factual | period_coverage_profile | None | За какие годы в базе есть данные? | Профиль периодов базы собран (movement-based aggregate). |
|
||||
| Q2 | True | ok_or_factual | factual | period_coverage_profile | None | Какой год самый активный по количеству документов? | Профиль периодов базы собран (movement-based aggregate). |
|
||||
| Q3 | True | ok_or_factual | factual | period_coverage_profile | None | Какой месяц самый активный по количеству операций? | Профиль периодов базы собран (movement-based aggregate). |
|
||||
| Q4 | True | ok_or_factual | factual | document_type_and_account_section_profile | None | Какие типы документов используются чаще всего в базе? | Профиль типов документов и разделов учета собран (movement-based aggregate). |
|
||||
| Q5 | True | ok_or_factual | factual | document_type_and_account_section_profile | None | Какие разделы учета наиболее заполнены и какие почти не используются? | Профиль типов документов и разделов учета собран (movement-based aggregate). |
|
||||
+45
@@ -0,0 +1,45 @@
|
||||
{
|
||||
"run_id": "2026-04-02_Address_General5_Live_Check_AfterNextPack",
|
||||
"generated_at": "2026-04-02T21:06:53",
|
||||
"source_questions_file": "X:\\1C\\NDC_1C\\docs\\ADDRESS\\question_sets\\temp_general5_live_check_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": 5,
|
||||
"ok_200_count": 5,
|
||||
"semantic_pass_count": 5,
|
||||
"semantic_pass_rate": 1.0,
|
||||
"route_pass_count": 5,
|
||||
"route_pass_rate": 1.0,
|
||||
"strict_pass_count": 5,
|
||||
"strict_pass_rate": 1.0,
|
||||
"factual_count": 5,
|
||||
"partial_coverage_count": 0,
|
||||
"clarification_required_count": 0,
|
||||
"http_error_count": 0,
|
||||
"llm_decomposition_applied_count": 0,
|
||||
"avg_elapsed_ms": 3653.8
|
||||
},
|
||||
"distributions": {
|
||||
"reply_type": {
|
||||
"factual": 5
|
||||
},
|
||||
"actual_intent": {
|
||||
"period_coverage_profile": 3,
|
||||
"document_type_and_account_section_profile": 2
|
||||
},
|
||||
"actual_mode": {
|
||||
"address_query": 5
|
||||
},
|
||||
"mcp_call_status": {
|
||||
"matched_non_empty": 5
|
||||
},
|
||||
"limited_reason_category": {},
|
||||
"route_health": {
|
||||
"ok_or_factual": 5
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,28 @@
|
||||
# 2026-04-02_Address_General5_Live_Check_AfterReverseFix
|
||||
|
||||
Generated at: 2026-04-02T20:52:16
|
||||
Questions file: X:\1C\NDC_1C\docs\ADDRESS\question_sets\temp_general5_live_check_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: 5
|
||||
- ok_200_count: 5
|
||||
- semantic_pass_count: 5
|
||||
- semantic_pass_rate: 1.0
|
||||
- route_pass_count: 5
|
||||
- route_pass_rate: 1.0
|
||||
- strict_pass_count: 5
|
||||
- strict_pass_rate: 1.0
|
||||
- factual_count: 5
|
||||
- partial_coverage_count: 0
|
||||
- clarification_required_count: 0
|
||||
- http_error_count: 0
|
||||
- llm_decomposition_applied_count: 0
|
||||
- avg_elapsed_ms: 2670.4
|
||||
|
||||
## Files
|
||||
- run_summary.json
|
||||
- full_live_results.json
|
||||
- failures_only.json
|
||||
+1
@@ -0,0 +1 @@
|
||||
[]
|
||||
+769
@@ -0,0 +1,769 @@
|
||||
{
|
||||
"run_id": "2026-04-02_Address_General5_Live_Check_AfterReverseFix",
|
||||
"generated_at": "2026-04-02T20:52:16",
|
||||
"summary": {
|
||||
"run_id": "2026-04-02_Address_General5_Live_Check_AfterReverseFix",
|
||||
"generated_at": "2026-04-02T20:52:16",
|
||||
"source_questions_file": "X:\\1C\\NDC_1C\\docs\\ADDRESS\\question_sets\\temp_general5_live_check_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": 5,
|
||||
"ok_200_count": 5,
|
||||
"semantic_pass_count": 5,
|
||||
"semantic_pass_rate": 1.0,
|
||||
"route_pass_count": 5,
|
||||
"route_pass_rate": 1.0,
|
||||
"strict_pass_count": 5,
|
||||
"strict_pass_rate": 1.0,
|
||||
"factual_count": 5,
|
||||
"partial_coverage_count": 0,
|
||||
"clarification_required_count": 0,
|
||||
"http_error_count": 0,
|
||||
"llm_decomposition_applied_count": 0,
|
||||
"avg_elapsed_ms": 2670.4
|
||||
},
|
||||
"distributions": {
|
||||
"reply_type": {
|
||||
"factual": 5
|
||||
},
|
||||
"actual_intent": {
|
||||
"period_coverage_profile": 3,
|
||||
"document_type_and_account_section_profile": 2
|
||||
},
|
||||
"actual_mode": {
|
||||
"address_query": 5
|
||||
},
|
||||
"mcp_call_status": {
|
||||
"matched_non_empty": 5
|
||||
},
|
||||
"limited_reason_category": {},
|
||||
"route_health": {
|
||||
"ok_or_factual": 5
|
||||
}
|
||||
}
|
||||
},
|
||||
"rows": [
|
||||
{
|
||||
"index": 1,
|
||||
"id": "Q1",
|
||||
"question": "За какие годы в базе есть данные?",
|
||||
"session": null,
|
||||
"session_id": "asst-2026-04-02_Address_General5_Live_Check_AfterReverseFix-q1",
|
||||
"status_code": 200,
|
||||
"ok": true,
|
||||
"elapsed_ms": 1112,
|
||||
"reply_type": "factual",
|
||||
"trace_id": "address-gt4_phWphT",
|
||||
"assistant_reply": "Профиль периодов базы собран (movement-based aggregate).\nСтрок агрегата: 134.\nОперационный период с выраженной активностью: 2014..2022.\nНизкоактивный хвост (единичные записи): 2023, 2025, 2026.\nПолный технический диапазон дат: 2014-05-27T12:00:00Z.. 2026-03-31T00:00:00Z.",
|
||||
"assistant_reply_first_line": "Профиль периодов базы собран (movement-based aggregate).",
|
||||
"expected_intent": "period_coverage_profile",
|
||||
"actual_intent": "period_coverage_profile",
|
||||
"intent_match": true,
|
||||
"expected_mode": "address_query",
|
||||
"actual_mode": "address_query",
|
||||
"mode_match": true,
|
||||
"expected_reply_type": null,
|
||||
"reply_match": true,
|
||||
"semantic_pass": true,
|
||||
"route_pass": true,
|
||||
"route_health": "ok_or_factual",
|
||||
"strict_policy": "factual",
|
||||
"strict_pass": true,
|
||||
"selected_recipe": "address_period_coverage_profile_v1",
|
||||
"missing_required_filters": [],
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"rows_fetched": 134,
|
||||
"rows_matched": 134,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"limited_reason_category": null,
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_reason": "not_address_like",
|
||||
"fallback_rule_hit": null,
|
||||
"debug_payload": {
|
||||
"trace_id": "address-gt4_phWphT",
|
||||
"prompt_version": "address_query_runtime_v1",
|
||||
"schema_version": "address_query_runtime_v1",
|
||||
"fallback_type": "none",
|
||||
"route_summary": null,
|
||||
"fragments": [],
|
||||
"requirements_extracted": [],
|
||||
"coverage_report": {
|
||||
"requirements_total": 0,
|
||||
"requirements_covered": 0,
|
||||
"requirements_uncovered": [],
|
||||
"requirements_partially_covered": [],
|
||||
"clarification_needed_for": [],
|
||||
"out_of_scope_requirements": []
|
||||
},
|
||||
"routes": [],
|
||||
"retrieval_status": [],
|
||||
"retrieval_results": [],
|
||||
"answer_grounding_check": {
|
||||
"status": "grounded",
|
||||
"route_subject_match": true,
|
||||
"missing_requirements": [],
|
||||
"reasons": [
|
||||
"management_profile_signal_detected",
|
||||
"shape_not_detected",
|
||||
"period_coverage_profile_signal_detected"
|
||||
],
|
||||
"why_included_summary": [],
|
||||
"selection_reason_summary": []
|
||||
},
|
||||
"dropped_intent_segments": [],
|
||||
"detected_mode": "address_query",
|
||||
"detected_mode_confidence": "medium",
|
||||
"query_shape": "UNKNOWN",
|
||||
"query_shape_confidence": "low",
|
||||
"detected_intent": "period_coverage_profile",
|
||||
"detected_intent_confidence": "high",
|
||||
"extracted_filters": {
|
||||
"sort": "period_desc",
|
||||
"period_to": "2026-04-02"
|
||||
},
|
||||
"missing_required_filters": [],
|
||||
"selected_recipe": "address_period_coverage_profile_v1",
|
||||
"mcp_call_status_legacy": "matched_non_empty",
|
||||
"account_scope_mode": "preferred",
|
||||
"account_scope_fallback_applied": false,
|
||||
"anchor_type": "unknown",
|
||||
"anchor_value_raw": null,
|
||||
"anchor_value_resolved": null,
|
||||
"resolver_confidence": "low",
|
||||
"ambiguity_count": 0,
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"rows_fetched": 134,
|
||||
"raw_rows_received": 134,
|
||||
"rows_after_account_scope": 134,
|
||||
"rows_after_recipe_filter": 134,
|
||||
"rows_materialized": 134,
|
||||
"rows_matched": 134,
|
||||
"raw_row_keys_sample": [
|
||||
"Период",
|
||||
"Регистратор",
|
||||
"СчетДт",
|
||||
"СчетКт",
|
||||
"Сумма",
|
||||
"Period",
|
||||
"Registrator",
|
||||
"Amount"
|
||||
],
|
||||
"materialization_drop_reason": "none",
|
||||
"account_token_raw": null,
|
||||
"account_token_normalized": null,
|
||||
"account_scope_fields_checked": [
|
||||
"account_dt",
|
||||
"account_kt",
|
||||
"registrator",
|
||||
"analytics"
|
||||
],
|
||||
"account_scope_match_strategy": "account_code_regex_plus_alias_map_v1",
|
||||
"account_scope_drop_reason": "not_applicable",
|
||||
"runtime_readiness": "LIVE_QUERYABLE_WITH_LIMITS",
|
||||
"limited_reason_category": null,
|
||||
"response_type": "FACTUAL_SUMMARY",
|
||||
"execution_lane": "address_query",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_attempted": false,
|
||||
"llm_provider_used": "local",
|
||||
"llm_decomposition_trace_id": null,
|
||||
"llm_decomposition_effective_message": "За какие годы в базе есть данные?",
|
||||
"llm_decomposition_reason": "not_address_like",
|
||||
"fallback_rule_hit": null,
|
||||
"sanitized_user_message": "за какие годы в базе есть данные?",
|
||||
"tool_gate_decision": "run_address_lane",
|
||||
"tool_gate_reason": "address_mode_classifier_detected",
|
||||
"answer_structure_v11": null,
|
||||
"investigation_state_snapshot": null,
|
||||
"normalized": null,
|
||||
"normalizer_output": null
|
||||
},
|
||||
"error_code": null,
|
||||
"error_message": null
|
||||
},
|
||||
{
|
||||
"index": 2,
|
||||
"id": "Q2",
|
||||
"question": "Какой год самый активный по количеству документов?",
|
||||
"session": null,
|
||||
"session_id": "asst-2026-04-02_Address_General5_Live_Check_AfterReverseFix-q2",
|
||||
"status_code": 200,
|
||||
"ok": true,
|
||||
"elapsed_ms": 5044,
|
||||
"reply_type": "factual",
|
||||
"trace_id": "address-VdsAJmYHgW",
|
||||
"assistant_reply": "Профиль периодов базы собран (movement-based aggregate).\nСтрок агрегата: 134.\nСамый активный год по документам: 2019 (1004).\n1. 2019: 1004\n2. 2018: 703\n3. 2015: 671\n4. 2016: 577\n5. 2020: 536",
|
||||
"assistant_reply_first_line": "Профиль периодов базы собран (movement-based aggregate).",
|
||||
"expected_intent": "period_coverage_profile",
|
||||
"actual_intent": "period_coverage_profile",
|
||||
"intent_match": true,
|
||||
"expected_mode": "address_query",
|
||||
"actual_mode": "address_query",
|
||||
"mode_match": true,
|
||||
"expected_reply_type": null,
|
||||
"reply_match": true,
|
||||
"semantic_pass": true,
|
||||
"route_pass": true,
|
||||
"route_health": "ok_or_factual",
|
||||
"strict_policy": "factual",
|
||||
"strict_pass": true,
|
||||
"selected_recipe": "address_period_coverage_profile_v1",
|
||||
"missing_required_filters": [],
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"rows_fetched": 134,
|
||||
"rows_matched": 134,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"limited_reason_category": null,
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_reason": "normalized_fragment_rejected_intent_conflict",
|
||||
"fallback_rule_hit": null,
|
||||
"debug_payload": {
|
||||
"trace_id": "address-VdsAJmYHgW",
|
||||
"prompt_version": "address_query_runtime_v1",
|
||||
"schema_version": "address_query_runtime_v1",
|
||||
"fallback_type": "none",
|
||||
"route_summary": null,
|
||||
"fragments": [],
|
||||
"requirements_extracted": [],
|
||||
"coverage_report": {
|
||||
"requirements_total": 0,
|
||||
"requirements_covered": 0,
|
||||
"requirements_uncovered": [],
|
||||
"requirements_partially_covered": [],
|
||||
"clarification_needed_for": [],
|
||||
"out_of_scope_requirements": []
|
||||
},
|
||||
"routes": [],
|
||||
"retrieval_status": [],
|
||||
"retrieval_results": [],
|
||||
"answer_grounding_check": {
|
||||
"status": "grounded",
|
||||
"route_subject_match": true,
|
||||
"missing_requirements": [],
|
||||
"reasons": [
|
||||
"management_profile_signal_detected",
|
||||
"document_list_signal_detected",
|
||||
"period_coverage_profile_signal_detected"
|
||||
],
|
||||
"why_included_summary": [],
|
||||
"selection_reason_summary": []
|
||||
},
|
||||
"dropped_intent_segments": [],
|
||||
"detected_mode": "address_query",
|
||||
"detected_mode_confidence": "medium",
|
||||
"query_shape": "DOCUMENT_LIST",
|
||||
"query_shape_confidence": "medium",
|
||||
"detected_intent": "period_coverage_profile",
|
||||
"detected_intent_confidence": "high",
|
||||
"extracted_filters": {
|
||||
"sort": "period_desc",
|
||||
"period_to": "2026-04-02"
|
||||
},
|
||||
"missing_required_filters": [],
|
||||
"selected_recipe": "address_period_coverage_profile_v1",
|
||||
"mcp_call_status_legacy": "matched_non_empty",
|
||||
"account_scope_mode": "preferred",
|
||||
"account_scope_fallback_applied": false,
|
||||
"anchor_type": "unknown",
|
||||
"anchor_value_raw": null,
|
||||
"anchor_value_resolved": null,
|
||||
"resolver_confidence": "low",
|
||||
"ambiguity_count": 0,
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"rows_fetched": 134,
|
||||
"raw_rows_received": 134,
|
||||
"rows_after_account_scope": 134,
|
||||
"rows_after_recipe_filter": 134,
|
||||
"rows_materialized": 134,
|
||||
"rows_matched": 134,
|
||||
"raw_row_keys_sample": [
|
||||
"Период",
|
||||
"Регистратор",
|
||||
"СчетДт",
|
||||
"СчетКт",
|
||||
"Сумма",
|
||||
"Period",
|
||||
"Registrator",
|
||||
"Amount"
|
||||
],
|
||||
"materialization_drop_reason": "none",
|
||||
"account_token_raw": null,
|
||||
"account_token_normalized": null,
|
||||
"account_scope_fields_checked": [
|
||||
"account_dt",
|
||||
"account_kt",
|
||||
"registrator",
|
||||
"analytics"
|
||||
],
|
||||
"account_scope_match_strategy": "account_code_regex_plus_alias_map_v1",
|
||||
"account_scope_drop_reason": "not_applicable",
|
||||
"runtime_readiness": "LIVE_QUERYABLE_WITH_LIMITS",
|
||||
"limited_reason_category": null,
|
||||
"response_type": "FACTUAL_SUMMARY",
|
||||
"execution_lane": "address_query",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_attempted": true,
|
||||
"llm_provider_used": "local",
|
||||
"llm_decomposition_trace_id": "XjOmBTjLbXP2n7",
|
||||
"llm_decomposition_effective_message": "Какой год самый активный по количеству документов?",
|
||||
"llm_decomposition_reason": "normalized_fragment_rejected_intent_conflict",
|
||||
"fallback_rule_hit": null,
|
||||
"sanitized_user_message": "какой год самый активный по количеству документов?",
|
||||
"tool_gate_decision": "run_address_lane",
|
||||
"tool_gate_reason": "address_mode_classifier_detected",
|
||||
"answer_structure_v11": null,
|
||||
"investigation_state_snapshot": null,
|
||||
"normalized": null,
|
||||
"normalizer_output": {
|
||||
"trace_id": "XjOmBTjLbXP2n7",
|
||||
"prompt_version": "normalizer_v2_0_2",
|
||||
"applied": false,
|
||||
"effective_message": "Какой год самый активный по количеству документов?"
|
||||
}
|
||||
},
|
||||
"error_code": null,
|
||||
"error_message": null
|
||||
},
|
||||
{
|
||||
"index": 3,
|
||||
"id": "Q3",
|
||||
"question": "Какой месяц самый активный по количеству операций?",
|
||||
"session": null,
|
||||
"session_id": "asst-2026-04-02_Address_General5_Live_Check_AfterReverseFix-q3",
|
||||
"status_code": 200,
|
||||
"ok": true,
|
||||
"elapsed_ms": 1018,
|
||||
"reply_type": "factual",
|
||||
"trace_id": "address-gq-TeIhTfe",
|
||||
"assistant_reply": "Профиль периодов базы собран (movement-based aggregate).\nСтрок агрегата: 134.\nСамый активный месяц по операциям: 2015-02 (1249).\n1. 2015-02: 1249\n2. 2015-01: 924\n3. 2018-08: 854\n4. 2019-05: 536\n5. 2017-12: 503",
|
||||
"assistant_reply_first_line": "Профиль периодов базы собран (movement-based aggregate).",
|
||||
"expected_intent": "period_coverage_profile",
|
||||
"actual_intent": "period_coverage_profile",
|
||||
"intent_match": true,
|
||||
"expected_mode": "address_query",
|
||||
"actual_mode": "address_query",
|
||||
"mode_match": true,
|
||||
"expected_reply_type": null,
|
||||
"reply_match": true,
|
||||
"semantic_pass": true,
|
||||
"route_pass": true,
|
||||
"route_health": "ok_or_factual",
|
||||
"strict_policy": "factual",
|
||||
"strict_pass": true,
|
||||
"selected_recipe": "address_period_coverage_profile_v1",
|
||||
"missing_required_filters": [],
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"rows_fetched": 134,
|
||||
"rows_matched": 134,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"limited_reason_category": null,
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_reason": "not_address_like",
|
||||
"fallback_rule_hit": null,
|
||||
"debug_payload": {
|
||||
"trace_id": "address-gq-TeIhTfe",
|
||||
"prompt_version": "address_query_runtime_v1",
|
||||
"schema_version": "address_query_runtime_v1",
|
||||
"fallback_type": "none",
|
||||
"route_summary": null,
|
||||
"fragments": [],
|
||||
"requirements_extracted": [],
|
||||
"coverage_report": {
|
||||
"requirements_total": 0,
|
||||
"requirements_covered": 0,
|
||||
"requirements_uncovered": [],
|
||||
"requirements_partially_covered": [],
|
||||
"clarification_needed_for": [],
|
||||
"out_of_scope_requirements": []
|
||||
},
|
||||
"routes": [],
|
||||
"retrieval_status": [],
|
||||
"retrieval_results": [],
|
||||
"answer_grounding_check": {
|
||||
"status": "grounded",
|
||||
"route_subject_match": true,
|
||||
"missing_requirements": [],
|
||||
"reasons": [
|
||||
"management_profile_signal_detected",
|
||||
"shape_not_detected",
|
||||
"period_coverage_profile_signal_detected"
|
||||
],
|
||||
"why_included_summary": [],
|
||||
"selection_reason_summary": []
|
||||
},
|
||||
"dropped_intent_segments": [],
|
||||
"detected_mode": "address_query",
|
||||
"detected_mode_confidence": "medium",
|
||||
"query_shape": "UNKNOWN",
|
||||
"query_shape_confidence": "low",
|
||||
"detected_intent": "period_coverage_profile",
|
||||
"detected_intent_confidence": "high",
|
||||
"extracted_filters": {
|
||||
"sort": "period_desc",
|
||||
"period_to": "2026-04-02"
|
||||
},
|
||||
"missing_required_filters": [],
|
||||
"selected_recipe": "address_period_coverage_profile_v1",
|
||||
"mcp_call_status_legacy": "matched_non_empty",
|
||||
"account_scope_mode": "preferred",
|
||||
"account_scope_fallback_applied": false,
|
||||
"anchor_type": "unknown",
|
||||
"anchor_value_raw": null,
|
||||
"anchor_value_resolved": null,
|
||||
"resolver_confidence": "low",
|
||||
"ambiguity_count": 0,
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"rows_fetched": 134,
|
||||
"raw_rows_received": 134,
|
||||
"rows_after_account_scope": 134,
|
||||
"rows_after_recipe_filter": 134,
|
||||
"rows_materialized": 134,
|
||||
"rows_matched": 134,
|
||||
"raw_row_keys_sample": [
|
||||
"Период",
|
||||
"Регистратор",
|
||||
"СчетДт",
|
||||
"СчетКт",
|
||||
"Сумма",
|
||||
"Period",
|
||||
"Registrator",
|
||||
"Amount"
|
||||
],
|
||||
"materialization_drop_reason": "none",
|
||||
"account_token_raw": null,
|
||||
"account_token_normalized": null,
|
||||
"account_scope_fields_checked": [
|
||||
"account_dt",
|
||||
"account_kt",
|
||||
"registrator",
|
||||
"analytics"
|
||||
],
|
||||
"account_scope_match_strategy": "account_code_regex_plus_alias_map_v1",
|
||||
"account_scope_drop_reason": "not_applicable",
|
||||
"runtime_readiness": "LIVE_QUERYABLE_WITH_LIMITS",
|
||||
"limited_reason_category": null,
|
||||
"response_type": "FACTUAL_SUMMARY",
|
||||
"execution_lane": "address_query",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_attempted": false,
|
||||
"llm_provider_used": "local",
|
||||
"llm_decomposition_trace_id": null,
|
||||
"llm_decomposition_effective_message": "Какой месяц самый активный по количеству операций?",
|
||||
"llm_decomposition_reason": "not_address_like",
|
||||
"fallback_rule_hit": null,
|
||||
"sanitized_user_message": "какой месяц самый активный по количеству операций?",
|
||||
"tool_gate_decision": "run_address_lane",
|
||||
"tool_gate_reason": "address_mode_classifier_detected",
|
||||
"answer_structure_v11": null,
|
||||
"investigation_state_snapshot": null,
|
||||
"normalized": null,
|
||||
"normalizer_output": null
|
||||
},
|
||||
"error_code": null,
|
||||
"error_message": null
|
||||
},
|
||||
{
|
||||
"index": 4,
|
||||
"id": "Q4",
|
||||
"question": "Какие типы документов используются чаще всего в базе?",
|
||||
"session": null,
|
||||
"session_id": "asst-2026-04-02_Address_General5_Live_Check_AfterReverseFix-q4",
|
||||
"status_code": 200,
|
||||
"ok": true,
|
||||
"elapsed_ms": 5177,
|
||||
"reply_type": "factual",
|
||||
"trace_id": "address-JVeZqbkygd",
|
||||
"assistant_reply": "Профиль типов документов и разделов учета собран (movement-based aggregate).\nСтрок агрегата: 147.\nТоп типов документов (по числу уникальных регистраторов):\n1. Списание с расчетного счета: 2352 (52.6%)\n2. Поступление товаров и услуг: 486 (10.9%)\n3. Регламентная операция: 414 (9.3%)\n4. Поступление на расчетный счет: 323 (7.2%)\n5. Счет-фактура полученный: 261 (5.8%)\n6. Операция (бухгалтерский и налоговый учет): 147 (3.3%)\n7. Реализация товаров и услуг: 123 (2.8%)\n8. Отражение зарплаты в регламентированном учете: 87 (1.9%)\n9. Приходный кассовый ордер: 76 (1.7%)\n10. Расходный кассовый ордер: 73 (1.6%)",
|
||||
"assistant_reply_first_line": "Профиль типов документов и разделов учета собран (movement-based aggregate).",
|
||||
"expected_intent": "document_type_and_account_section_profile",
|
||||
"actual_intent": "document_type_and_account_section_profile",
|
||||
"intent_match": true,
|
||||
"expected_mode": "address_query",
|
||||
"actual_mode": "address_query",
|
||||
"mode_match": true,
|
||||
"expected_reply_type": null,
|
||||
"reply_match": true,
|
||||
"semantic_pass": true,
|
||||
"route_pass": true,
|
||||
"route_health": "ok_or_factual",
|
||||
"strict_policy": "factual",
|
||||
"strict_pass": true,
|
||||
"selected_recipe": "address_document_type_and_account_section_profile_v1",
|
||||
"missing_required_filters": [],
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"rows_fetched": 147,
|
||||
"rows_matched": 147,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"limited_reason_category": null,
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_reason": "normalized_fragment_same",
|
||||
"fallback_rule_hit": null,
|
||||
"debug_payload": {
|
||||
"trace_id": "address-JVeZqbkygd",
|
||||
"prompt_version": "address_query_runtime_v1",
|
||||
"schema_version": "address_query_runtime_v1",
|
||||
"fallback_type": "none",
|
||||
"route_summary": null,
|
||||
"fragments": [],
|
||||
"requirements_extracted": [],
|
||||
"coverage_report": {
|
||||
"requirements_total": 0,
|
||||
"requirements_covered": 0,
|
||||
"requirements_uncovered": [],
|
||||
"requirements_partially_covered": [],
|
||||
"clarification_needed_for": [],
|
||||
"out_of_scope_requirements": []
|
||||
},
|
||||
"routes": [],
|
||||
"retrieval_status": [],
|
||||
"retrieval_results": [],
|
||||
"answer_grounding_check": {
|
||||
"status": "grounded",
|
||||
"route_subject_match": true,
|
||||
"missing_requirements": [],
|
||||
"reasons": [
|
||||
"address_action_detected",
|
||||
"address_entity_detected",
|
||||
"document_list_signal_detected",
|
||||
"document_type_and_account_section_profile_signal_detected"
|
||||
],
|
||||
"why_included_summary": [],
|
||||
"selection_reason_summary": []
|
||||
},
|
||||
"dropped_intent_segments": [],
|
||||
"detected_mode": "address_query",
|
||||
"detected_mode_confidence": "high",
|
||||
"query_shape": "DOCUMENT_LIST",
|
||||
"query_shape_confidence": "medium",
|
||||
"detected_intent": "document_type_and_account_section_profile",
|
||||
"detected_intent_confidence": "high",
|
||||
"extracted_filters": {
|
||||
"sort": "period_desc",
|
||||
"period_to": "2026-04-02"
|
||||
},
|
||||
"missing_required_filters": [],
|
||||
"selected_recipe": "address_document_type_and_account_section_profile_v1",
|
||||
"mcp_call_status_legacy": "matched_non_empty",
|
||||
"account_scope_mode": "preferred",
|
||||
"account_scope_fallback_applied": false,
|
||||
"anchor_type": "unknown",
|
||||
"anchor_value_raw": null,
|
||||
"anchor_value_resolved": null,
|
||||
"resolver_confidence": "low",
|
||||
"ambiguity_count": 0,
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"rows_fetched": 147,
|
||||
"raw_rows_received": 147,
|
||||
"rows_after_account_scope": 147,
|
||||
"rows_after_recipe_filter": 147,
|
||||
"rows_materialized": 147,
|
||||
"rows_matched": 147,
|
||||
"raw_row_keys_sample": [
|
||||
"Период",
|
||||
"Регистратор",
|
||||
"СчетДт",
|
||||
"СчетКт",
|
||||
"Сумма",
|
||||
"Period",
|
||||
"Registrator",
|
||||
"AccountDt",
|
||||
"Amount"
|
||||
],
|
||||
"materialization_drop_reason": "none",
|
||||
"account_token_raw": null,
|
||||
"account_token_normalized": null,
|
||||
"account_scope_fields_checked": [
|
||||
"account_dt",
|
||||
"account_kt",
|
||||
"registrator",
|
||||
"analytics"
|
||||
],
|
||||
"account_scope_match_strategy": "account_code_regex_plus_alias_map_v1",
|
||||
"account_scope_drop_reason": "not_applicable",
|
||||
"runtime_readiness": "LIVE_QUERYABLE_WITH_LIMITS",
|
||||
"limited_reason_category": null,
|
||||
"response_type": "FACTUAL_SUMMARY",
|
||||
"execution_lane": "address_query",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_attempted": true,
|
||||
"llm_provider_used": "local",
|
||||
"llm_decomposition_trace_id": "9kh3MZnV3-IXQJ",
|
||||
"llm_decomposition_effective_message": "Какие типы документов используются чаще всего в базе?",
|
||||
"llm_decomposition_reason": "normalized_fragment_same",
|
||||
"fallback_rule_hit": null,
|
||||
"sanitized_user_message": "какие типы документов используются чаще всего в базе?",
|
||||
"tool_gate_decision": "run_address_lane",
|
||||
"tool_gate_reason": "address_mode_classifier_detected",
|
||||
"answer_structure_v11": null,
|
||||
"investigation_state_snapshot": null,
|
||||
"normalized": null,
|
||||
"normalizer_output": {
|
||||
"trace_id": "9kh3MZnV3-IXQJ",
|
||||
"prompt_version": "normalizer_v2_0_2",
|
||||
"applied": false,
|
||||
"effective_message": "Какие типы документов используются чаще всего в базе?"
|
||||
}
|
||||
},
|
||||
"error_code": null,
|
||||
"error_message": null
|
||||
},
|
||||
{
|
||||
"index": 5,
|
||||
"id": "Q5",
|
||||
"question": "Какие разделы учета наиболее заполнены и какие почти не используются?",
|
||||
"session": null,
|
||||
"session_id": "asst-2026-04-02_Address_General5_Live_Check_AfterReverseFix-q5",
|
||||
"status_code": 200,
|
||||
"ok": true,
|
||||
"elapsed_ms": 1001,
|
||||
"reply_type": "factual",
|
||||
"trace_id": "address-L4Ak23OiJH",
|
||||
"assistant_reply": "Профиль типов документов и разделов учета собран (movement-based aggregate).\nСтрок агрегата: 147.\nНаиболее заполненные разделы учета (по операциям Дт+Кт):\n1. 90 (Продажи): 2973 (12.1%)\n2. 51 (Расчетные счета): 2967 (12.1%)\n3. 60 (Расчеты с поставщиками и подрядчиками): 2793 (11.4%)\n4. 44 (Расходы на продажу): 2422 (9.9%)\n5. 68 (Расчеты по налогам и сборам): 1553 (6.3%)\n6. 10 (Материалы): 1494 (6.1%)\n7. 19 (НДС по приобретенным ценностям): 1489 (6.1%)\n8. 91 (Прочие доходы и расходы): 1324 (5.4%)\n9. 41 (Товары): 1312 (5.3%)\n10. 76 (Расчеты с разными дебиторами и кредиторами): 1240 (5.0%)\nРазделы с минимальной активностью (среди использованных):\n1. 58 (Финансовые вложения): 2\n2. 81 (Собственные акции (доли)): 2\n3. 80 (Уставный капитал): 5\n4. 03: 6\n5. 04 (Нематериальные активы): 6\n6. 75 (Расчеты с учредителями): 16\n7. 55 (Специальные счета в банках): 18\n8. 84 (Нераспределенная прибыль (непокрытый убыток)): 20\n9. 26 (Общехозяйственные расходы): 51\n10. 71 (Расчеты с подотчетными лицами): 76",
|
||||
"assistant_reply_first_line": "Профиль типов документов и разделов учета собран (movement-based aggregate).",
|
||||
"expected_intent": "document_type_and_account_section_profile",
|
||||
"actual_intent": "document_type_and_account_section_profile",
|
||||
"intent_match": true,
|
||||
"expected_mode": "address_query",
|
||||
"actual_mode": "address_query",
|
||||
"mode_match": true,
|
||||
"expected_reply_type": null,
|
||||
"reply_match": true,
|
||||
"semantic_pass": true,
|
||||
"route_pass": true,
|
||||
"route_health": "ok_or_factual",
|
||||
"strict_policy": "factual",
|
||||
"strict_pass": true,
|
||||
"selected_recipe": "address_document_type_and_account_section_profile_v1",
|
||||
"missing_required_filters": [],
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"rows_fetched": 147,
|
||||
"rows_matched": 147,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"limited_reason_category": null,
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_reason": "not_address_like",
|
||||
"fallback_rule_hit": null,
|
||||
"debug_payload": {
|
||||
"trace_id": "address-L4Ak23OiJH",
|
||||
"prompt_version": "address_query_runtime_v1",
|
||||
"schema_version": "address_query_runtime_v1",
|
||||
"fallback_type": "none",
|
||||
"route_summary": null,
|
||||
"fragments": [],
|
||||
"requirements_extracted": [],
|
||||
"coverage_report": {
|
||||
"requirements_total": 0,
|
||||
"requirements_covered": 0,
|
||||
"requirements_uncovered": [],
|
||||
"requirements_partially_covered": [],
|
||||
"clarification_needed_for": [],
|
||||
"out_of_scope_requirements": []
|
||||
},
|
||||
"routes": [],
|
||||
"retrieval_status": [],
|
||||
"retrieval_results": [],
|
||||
"answer_grounding_check": {
|
||||
"status": "grounded",
|
||||
"route_subject_match": true,
|
||||
"missing_requirements": [],
|
||||
"reasons": [
|
||||
"management_profile_signal_detected",
|
||||
"shape_not_detected",
|
||||
"document_type_and_account_section_profile_signal_detected"
|
||||
],
|
||||
"why_included_summary": [],
|
||||
"selection_reason_summary": []
|
||||
},
|
||||
"dropped_intent_segments": [],
|
||||
"detected_mode": "address_query",
|
||||
"detected_mode_confidence": "medium",
|
||||
"query_shape": "UNKNOWN",
|
||||
"query_shape_confidence": "low",
|
||||
"detected_intent": "document_type_and_account_section_profile",
|
||||
"detected_intent_confidence": "high",
|
||||
"extracted_filters": {
|
||||
"sort": "period_desc",
|
||||
"period_to": "2026-04-02"
|
||||
},
|
||||
"missing_required_filters": [],
|
||||
"selected_recipe": "address_document_type_and_account_section_profile_v1",
|
||||
"mcp_call_status_legacy": "matched_non_empty",
|
||||
"account_scope_mode": "preferred",
|
||||
"account_scope_fallback_applied": false,
|
||||
"anchor_type": "unknown",
|
||||
"anchor_value_raw": null,
|
||||
"anchor_value_resolved": null,
|
||||
"resolver_confidence": "low",
|
||||
"ambiguity_count": 0,
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"mcp_call_status": "matched_non_empty",
|
||||
"rows_fetched": 147,
|
||||
"raw_rows_received": 147,
|
||||
"rows_after_account_scope": 147,
|
||||
"rows_after_recipe_filter": 147,
|
||||
"rows_materialized": 147,
|
||||
"rows_matched": 147,
|
||||
"raw_row_keys_sample": [
|
||||
"Период",
|
||||
"Регистратор",
|
||||
"СчетДт",
|
||||
"СчетКт",
|
||||
"Сумма",
|
||||
"Period",
|
||||
"Registrator",
|
||||
"AccountDt",
|
||||
"Amount"
|
||||
],
|
||||
"materialization_drop_reason": "none",
|
||||
"account_token_raw": null,
|
||||
"account_token_normalized": null,
|
||||
"account_scope_fields_checked": [
|
||||
"account_dt",
|
||||
"account_kt",
|
||||
"registrator",
|
||||
"analytics"
|
||||
],
|
||||
"account_scope_match_strategy": "account_code_regex_plus_alias_map_v1",
|
||||
"account_scope_drop_reason": "not_applicable",
|
||||
"runtime_readiness": "LIVE_QUERYABLE_WITH_LIMITS",
|
||||
"limited_reason_category": null,
|
||||
"response_type": "FACTUAL_SUMMARY",
|
||||
"execution_lane": "address_query",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_attempted": false,
|
||||
"llm_provider_used": "local",
|
||||
"llm_decomposition_trace_id": null,
|
||||
"llm_decomposition_effective_message": "Какие разделы учета наиболее заполнены и какие почти не используются?",
|
||||
"llm_decomposition_reason": "not_address_like",
|
||||
"fallback_rule_hit": null,
|
||||
"sanitized_user_message": "какие разделы учета наиболее заполнены и какие почти не используются?",
|
||||
"tool_gate_decision": "run_address_lane",
|
||||
"tool_gate_reason": "address_mode_classifier_detected",
|
||||
"answer_structure_v11": null,
|
||||
"investigation_state_snapshot": null,
|
||||
"normalized": null,
|
||||
"normalizer_output": null
|
||||
},
|
||||
"error_code": null,
|
||||
"error_message": null
|
||||
}
|
||||
]
|
||||
}
|
||||
+9
@@ -0,0 +1,9 @@
|
||||
# Response Audit: 2026-04-02_Address_General5_Live_Check_AfterReverseFix
|
||||
|
||||
| id | strict | route_health | reply_type | intent | limited_reason | question | assistant_first_line |
|
||||
|---|---|---|---|---|---|---|---|
|
||||
| Q1 | True | ok_or_factual | factual | period_coverage_profile | None | За какие годы в базе есть данные? | Профиль периодов базы собран (movement-based aggregate). |
|
||||
| Q2 | True | ok_or_factual | factual | period_coverage_profile | None | Какой год самый активный по количеству документов? | Профиль периодов базы собран (movement-based aggregate). |
|
||||
| Q3 | True | ok_or_factual | factual | period_coverage_profile | None | Какой месяц самый активный по количеству операций? | Профиль периодов базы собран (movement-based aggregate). |
|
||||
| Q4 | True | ok_or_factual | factual | document_type_and_account_section_profile | None | Какие типы документов используются чаще всего в базе? | Профиль типов документов и разделов учета собран (movement-based aggregate). |
|
||||
| Q5 | True | ok_or_factual | factual | document_type_and_account_section_profile | None | Какие разделы учета наиболее заполнены и какие почти не используются? | Профиль типов документов и разделов учета собран (movement-based aggregate). |
|
||||
+45
@@ -0,0 +1,45 @@
|
||||
{
|
||||
"run_id": "2026-04-02_Address_General5_Live_Check_AfterReverseFix",
|
||||
"generated_at": "2026-04-02T20:52:16",
|
||||
"source_questions_file": "X:\\1C\\NDC_1C\\docs\\ADDRESS\\question_sets\\temp_general5_live_check_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": 5,
|
||||
"ok_200_count": 5,
|
||||
"semantic_pass_count": 5,
|
||||
"semantic_pass_rate": 1.0,
|
||||
"route_pass_count": 5,
|
||||
"route_pass_rate": 1.0,
|
||||
"strict_pass_count": 5,
|
||||
"strict_pass_rate": 1.0,
|
||||
"factual_count": 5,
|
||||
"partial_coverage_count": 0,
|
||||
"clarification_required_count": 0,
|
||||
"http_error_count": 0,
|
||||
"llm_decomposition_applied_count": 0,
|
||||
"avg_elapsed_ms": 2670.4
|
||||
},
|
||||
"distributions": {
|
||||
"reply_type": {
|
||||
"factual": 5
|
||||
},
|
||||
"actual_intent": {
|
||||
"period_coverage_profile": 3,
|
||||
"document_type_and_account_section_profile": 2
|
||||
},
|
||||
"actual_mode": {
|
||||
"address_query": 5
|
||||
},
|
||||
"mcp_call_status": {
|
||||
"matched_non_empty": 5
|
||||
},
|
||||
"limited_reason_category": {},
|
||||
"route_health": {
|
||||
"ok_or_factual": 5
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,28 @@
|
||||
# 2026-04-02_Address_LLM_First_Gate_Probe
|
||||
|
||||
Generated at: 2026-04-02T21:57:17
|
||||
Questions file: X:\1C\NDC_1C\docs\ADDRESS\question_sets\temp_llm_first_gate_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: 4
|
||||
- ok_200_count: 4
|
||||
- semantic_pass_count: 4
|
||||
- semantic_pass_rate: 1.0
|
||||
- route_pass_count: 3
|
||||
- route_pass_rate: 0.75
|
||||
- strict_pass_count: 3
|
||||
- strict_pass_rate: 0.75
|
||||
- factual_count: 3
|
||||
- partial_coverage_count: 1
|
||||
- clarification_required_count: 0
|
||||
- http_error_count: 0
|
||||
- llm_decomposition_applied_count: 2
|
||||
- avg_elapsed_ms: 6017.5
|
||||
|
||||
## Files
|
||||
- run_summary.json
|
||||
- full_live_results.json
|
||||
- failures_only.json
|
||||
@@ -0,0 +1,141 @@
|
||||
[
|
||||
{
|
||||
"index": 4,
|
||||
"id": "L004",
|
||||
"question": "кто у нас заказчики вообще",
|
||||
"session": null,
|
||||
"session_id": "asst-2026-04-02_Address_LLM_First_Gate_Probe-l004",
|
||||
"status_code": 200,
|
||||
"ok": true,
|
||||
"elapsed_ms": 4493,
|
||||
"reply_type": "partial_coverage",
|
||||
"trace_id": "address-414GMyc_O7",
|
||||
"assistant_reply": "Этот запрос не подходит под address_query V1.\nПричина: intent пока не поддержан в address V1.\nЧто нужно уточнить: переформулируйте вопрос как адресный lookup по счету/контрагенту/договору.",
|
||||
"assistant_reply_first_line": "Этот запрос не подходит под address_query V1.",
|
||||
"expected_intent": null,
|
||||
"actual_intent": "unknown",
|
||||
"intent_match": true,
|
||||
"expected_mode": "address_query",
|
||||
"actual_mode": "address_query",
|
||||
"mode_match": true,
|
||||
"expected_reply_type": null,
|
||||
"reply_match": true,
|
||||
"semantic_pass": true,
|
||||
"route_pass": false,
|
||||
"route_health": "blocked_unsupported",
|
||||
"strict_policy": "factual",
|
||||
"strict_pass": false,
|
||||
"selected_recipe": null,
|
||||
"missing_required_filters": [],
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"rows_fetched": 0,
|
||||
"rows_matched": 0,
|
||||
"mcp_call_status": "skipped",
|
||||
"limited_reason_category": "unsupported",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_reason": "normalized_fragment_same",
|
||||
"fallback_rule_hit": null,
|
||||
"debug_payload": {
|
||||
"trace_id": "address-414GMyc_O7",
|
||||
"prompt_version": "address_query_runtime_v1",
|
||||
"schema_version": "address_query_runtime_v1",
|
||||
"fallback_type": "partial",
|
||||
"route_summary": null,
|
||||
"fragments": [],
|
||||
"requirements_extracted": [],
|
||||
"coverage_report": {
|
||||
"requirements_total": 0,
|
||||
"requirements_covered": 0,
|
||||
"requirements_uncovered": [],
|
||||
"requirements_partially_covered": [],
|
||||
"clarification_needed_for": [],
|
||||
"out_of_scope_requirements": []
|
||||
},
|
||||
"routes": [],
|
||||
"retrieval_status": [],
|
||||
"retrieval_results": [],
|
||||
"answer_grounding_check": {
|
||||
"status": "partial",
|
||||
"route_subject_match": true,
|
||||
"missing_requirements": [],
|
||||
"reasons": [
|
||||
"address_action_detected",
|
||||
"address_entity_detected",
|
||||
"shape_not_detected",
|
||||
"intent_not_supported_in_v1"
|
||||
],
|
||||
"why_included_summary": [],
|
||||
"selection_reason_summary": []
|
||||
},
|
||||
"dropped_intent_segments": [],
|
||||
"detected_mode": "address_query",
|
||||
"detected_mode_confidence": "high",
|
||||
"query_shape": "UNKNOWN",
|
||||
"query_shape_confidence": "low",
|
||||
"detected_intent": "unknown",
|
||||
"detected_intent_confidence": "low",
|
||||
"extracted_filters": {
|
||||
"sort": "period_desc",
|
||||
"limit": 20
|
||||
},
|
||||
"missing_required_filters": [],
|
||||
"selected_recipe": null,
|
||||
"mcp_call_status_legacy": "skipped",
|
||||
"account_scope_mode": "strict",
|
||||
"account_scope_fallback_applied": false,
|
||||
"anchor_type": "unknown",
|
||||
"anchor_value_raw": null,
|
||||
"anchor_value_resolved": null,
|
||||
"resolver_confidence": "low",
|
||||
"ambiguity_count": 0,
|
||||
"match_failure_stage": "none",
|
||||
"match_failure_reason": null,
|
||||
"mcp_call_status": "skipped",
|
||||
"rows_fetched": 0,
|
||||
"raw_rows_received": 0,
|
||||
"rows_after_account_scope": 0,
|
||||
"rows_after_recipe_filter": 0,
|
||||
"rows_materialized": 0,
|
||||
"rows_matched": 0,
|
||||
"raw_row_keys_sample": [],
|
||||
"materialization_drop_reason": "none",
|
||||
"account_token_raw": null,
|
||||
"account_token_normalized": null,
|
||||
"account_scope_fields_checked": [
|
||||
"account_dt",
|
||||
"account_kt",
|
||||
"registrator",
|
||||
"analytics"
|
||||
],
|
||||
"account_scope_match_strategy": "account_code_regex_plus_alias_map_v1",
|
||||
"account_scope_drop_reason": "not_applicable",
|
||||
"runtime_readiness": "DEEP_ONLY",
|
||||
"limited_reason_category": "unsupported",
|
||||
"response_type": "LIMITED_WITH_REASON",
|
||||
"execution_lane": "address_query",
|
||||
"llm_decomposition_applied": false,
|
||||
"llm_decomposition_attempted": true,
|
||||
"llm_provider_used": "local",
|
||||
"llm_decomposition_trace_id": "wrWnx-j7j-vZsF",
|
||||
"llm_decomposition_effective_message": "кто у нас заказчики вообще",
|
||||
"llm_decomposition_reason": "normalized_fragment_same",
|
||||
"llm_canonical_candidate_detected": true,
|
||||
"fallback_rule_hit": null,
|
||||
"sanitized_user_message": "кто у нас заказчики вообще",
|
||||
"tool_gate_decision": "run_address_lane",
|
||||
"tool_gate_reason": "address_mode_classifier_detected",
|
||||
"answer_structure_v11": null,
|
||||
"investigation_state_snapshot": null,
|
||||
"normalized": null,
|
||||
"normalizer_output": {
|
||||
"trace_id": "wrWnx-j7j-vZsF",
|
||||
"prompt_version": "normalizer_v2_0_2",
|
||||
"applied": false,
|
||||
"effective_message": "кто у нас заказчики вообще"
|
||||
}
|
||||
},
|
||||
"error_code": null,
|
||||
"error_message": null
|
||||
}
|
||||
]
|
||||
File diff suppressed because one or more lines are too long
@@ -0,0 +1,8 @@
|
||||
# Response Audit: 2026-04-02_Address_LLM_First_Gate_Probe
|
||||
|
||||
| id | strict | route_health | reply_type | intent | limited_reason | question | assistant_first_line |
|
||||
|---|---|---|---|---|---|---|---|
|
||||
| L001 | True | ok_or_factual | factual | counterparty_activity_lifecycle | None | выведи список заказчиков за все время | Собран профиль активности заказчиков (bank-doc activity aggregate). |
|
||||
| L002 | True | ok_or_factual | factual | counterparty_activity_lifecycle | None | покажи список заказчиков за 20год | Собран профиль активности заказчиков (bank-doc activity aggregate). |
|
||||
| L003 | True | ok_or_factual | factual | counterparty_activity_lifecycle | None | zakazchiki za 20 god spisok | Собран профиль активности заказчиков (bank-doc activity aggregate). |
|
||||
| L004 | False | blocked_unsupported | partial_coverage | unknown | unsupported | кто у нас заказчики вообще | Этот запрос не подходит под address_query V1. |
|
||||
@@ -0,0 +1,50 @@
|
||||
{
|
||||
"run_id": "2026-04-02_Address_LLM_First_Gate_Probe",
|
||||
"generated_at": "2026-04-02T21:57:17",
|
||||
"source_questions_file": "X:\\1C\\NDC_1C\\docs\\ADDRESS\\question_sets\\temp_llm_first_gate_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": 4,
|
||||
"ok_200_count": 4,
|
||||
"semantic_pass_count": 4,
|
||||
"semantic_pass_rate": 1.0,
|
||||
"route_pass_count": 3,
|
||||
"route_pass_rate": 0.75,
|
||||
"strict_pass_count": 3,
|
||||
"strict_pass_rate": 0.75,
|
||||
"factual_count": 3,
|
||||
"partial_coverage_count": 1,
|
||||
"clarification_required_count": 0,
|
||||
"http_error_count": 0,
|
||||
"llm_decomposition_applied_count": 2,
|
||||
"avg_elapsed_ms": 6017.5
|
||||
},
|
||||
"distributions": {
|
||||
"reply_type": {
|
||||
"factual": 3,
|
||||
"partial_coverage": 1
|
||||
},
|
||||
"actual_intent": {
|
||||
"counterparty_activity_lifecycle": 3,
|
||||
"unknown": 1
|
||||
},
|
||||
"actual_mode": {
|
||||
"address_query": 4
|
||||
},
|
||||
"mcp_call_status": {
|
||||
"matched_non_empty": 3,
|
||||
"skipped": 1
|
||||
},
|
||||
"limited_reason_category": {
|
||||
"unsupported": 1
|
||||
},
|
||||
"route_health": {
|
||||
"ok_or_factual": 3,
|
||||
"blocked_unsupported": 1
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,28 @@
|
||||
# 2026-04-02_Address_LLM_First_Gate_Probe_AfterRosterFix
|
||||
|
||||
Generated at: 2026-04-02T22:00:35
|
||||
Questions file: X:\1C\NDC_1C\docs\ADDRESS\question_sets\temp_llm_first_gate_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: 4
|
||||
- ok_200_count: 4
|
||||
- semantic_pass_count: 4
|
||||
- semantic_pass_rate: 1.0
|
||||
- route_pass_count: 4
|
||||
- route_pass_rate: 1.0
|
||||
- strict_pass_count: 4
|
||||
- strict_pass_rate: 1.0
|
||||
- factual_count: 4
|
||||
- partial_coverage_count: 0
|
||||
- clarification_required_count: 0
|
||||
- http_error_count: 0
|
||||
- llm_decomposition_applied_count: 2
|
||||
- avg_elapsed_ms: 6061.8
|
||||
|
||||
## Files
|
||||
- run_summary.json
|
||||
- full_live_results.json
|
||||
- failures_only.json
|
||||
+1
@@ -0,0 +1 @@
|
||||
[]
|
||||
+648
File diff suppressed because one or more lines are too long
+8
@@ -0,0 +1,8 @@
|
||||
# Response Audit: 2026-04-02_Address_LLM_First_Gate_Probe_AfterRosterFix
|
||||
|
||||
| id | strict | route_health | reply_type | intent | limited_reason | question | assistant_first_line |
|
||||
|---|---|---|---|---|---|---|---|
|
||||
| L001 | True | ok_or_factual | factual | counterparty_activity_lifecycle | None | выведи список заказчиков за все время | Собран профиль активности заказчиков (bank-doc activity aggregate). |
|
||||
| L002 | True | ok_or_factual | factual | counterparty_activity_lifecycle | None | покажи список заказчиков за 20год | Собран профиль активности заказчиков (bank-doc activity aggregate). |
|
||||
| L003 | True | ok_or_factual | factual | counterparty_activity_lifecycle | None | zakazchiki za 20 god spisok | Собран профиль активности заказчиков (bank-doc activity aggregate). |
|
||||
| L004 | True | ok_or_factual | factual | counterparty_activity_lifecycle | None | кто у нас заказчики вообще | Собран профиль активности заказчиков (bank-doc activity aggregate). |
|
||||
+44
@@ -0,0 +1,44 @@
|
||||
{
|
||||
"run_id": "2026-04-02_Address_LLM_First_Gate_Probe_AfterRosterFix",
|
||||
"generated_at": "2026-04-02T22:00:35",
|
||||
"source_questions_file": "X:\\1C\\NDC_1C\\docs\\ADDRESS\\question_sets\\temp_llm_first_gate_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": 4,
|
||||
"ok_200_count": 4,
|
||||
"semantic_pass_count": 4,
|
||||
"semantic_pass_rate": 1.0,
|
||||
"route_pass_count": 4,
|
||||
"route_pass_rate": 1.0,
|
||||
"strict_pass_count": 4,
|
||||
"strict_pass_rate": 1.0,
|
||||
"factual_count": 4,
|
||||
"partial_coverage_count": 0,
|
||||
"clarification_required_count": 0,
|
||||
"http_error_count": 0,
|
||||
"llm_decomposition_applied_count": 2,
|
||||
"avg_elapsed_ms": 6061.8
|
||||
},
|
||||
"distributions": {
|
||||
"reply_type": {
|
||||
"factual": 4
|
||||
},
|
||||
"actual_intent": {
|
||||
"counterparty_activity_lifecycle": 4
|
||||
},
|
||||
"actual_mode": {
|
||||
"address_query": 4
|
||||
},
|
||||
"mcp_call_status": {
|
||||
"matched_non_empty": 4
|
||||
},
|
||||
"limited_reason_category": {},
|
||||
"route_health": {
|
||||
"ok_or_factual": 4
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,33 @@
|
||||
# 2026-04-02_Address_LLM_First_Gate_Probe_WithMetrics
|
||||
|
||||
Generated at: 2026-04-02T22:10:35
|
||||
Questions file: X:\1C\NDC_1C\docs\ADDRESS\question_sets\temp_llm_first_gate_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: 4
|
||||
- ok_200_count: 4
|
||||
- semantic_pass_count: 4
|
||||
- semantic_pass_rate: 1.0
|
||||
- route_pass_count: 4
|
||||
- route_pass_rate: 1.0
|
||||
- strict_pass_count: 4
|
||||
- strict_pass_rate: 1.0
|
||||
- factual_count: 4
|
||||
- partial_coverage_count: 0
|
||||
- clarification_required_count: 0
|
||||
- http_error_count: 0
|
||||
- llm_decomposition_attempted_count: 4
|
||||
- llm_decomposition_applied_count: 2
|
||||
- llm_fallback_count: 0
|
||||
- llm_fallback_rate: 0.0
|
||||
- tool_gate_blocked_count: 0
|
||||
- tool_gate_blocked_rate: 0.0
|
||||
- avg_elapsed_ms: 6098.5
|
||||
|
||||
## Files
|
||||
- run_summary.json
|
||||
- full_live_results.json
|
||||
- failures_only.json
|
||||
+1
@@ -0,0 +1 @@
|
||||
[]
|
||||
+816
File diff suppressed because one or more lines are too long
+8
@@ -0,0 +1,8 @@
|
||||
# Response Audit: 2026-04-02_Address_LLM_First_Gate_Probe_WithMetrics
|
||||
|
||||
| id | strict | route_health | reply_type | intent | limited_reason | question | assistant_first_line |
|
||||
|---|---|---|---|---|---|---|---|
|
||||
| L001 | True | ok_or_factual | factual | counterparty_activity_lifecycle | None | выведи список заказчиков за все время | Собран профиль активности заказчиков (bank-doc activity aggregate). |
|
||||
| L002 | True | ok_or_factual | factual | counterparty_activity_lifecycle | None | покажи список заказчиков за 20год | Собран профиль активности заказчиков (bank-doc activity aggregate). |
|
||||
| L003 | True | ok_or_factual | factual | counterparty_activity_lifecycle | None | zakazchiki za 20 god spisok | Собран профиль активности заказчиков (bank-doc activity aggregate). |
|
||||
| L004 | True | ok_or_factual | factual | counterparty_activity_lifecycle | None | кто у нас заказчики вообще | Собран профиль активности заказчиков (bank-doc activity aggregate). |
|
||||
+76
@@ -0,0 +1,76 @@
|
||||
{
|
||||
"run_id": "2026-04-02_Address_LLM_First_Gate_Probe_WithMetrics",
|
||||
"generated_at": "2026-04-02T22:10:35",
|
||||
"source_questions_file": "X:\\1C\\NDC_1C\\docs\\ADDRESS\\question_sets\\temp_llm_first_gate_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": 4,
|
||||
"ok_200_count": 4,
|
||||
"semantic_pass_count": 4,
|
||||
"semantic_pass_rate": 1.0,
|
||||
"route_pass_count": 4,
|
||||
"route_pass_rate": 1.0,
|
||||
"strict_pass_count": 4,
|
||||
"strict_pass_rate": 1.0,
|
||||
"factual_count": 4,
|
||||
"partial_coverage_count": 0,
|
||||
"clarification_required_count": 0,
|
||||
"http_error_count": 0,
|
||||
"llm_decomposition_attempted_count": 4,
|
||||
"llm_decomposition_applied_count": 2,
|
||||
"llm_fallback_count": 0,
|
||||
"llm_fallback_rate": 0.0,
|
||||
"tool_gate_blocked_count": 0,
|
||||
"tool_gate_blocked_rate": 0.0,
|
||||
"avg_elapsed_ms": 6098.5
|
||||
},
|
||||
"distributions": {
|
||||
"reply_type": {
|
||||
"factual": 4
|
||||
},
|
||||
"actual_intent": {
|
||||
"counterparty_activity_lifecycle": 4
|
||||
},
|
||||
"actual_mode": {
|
||||
"address_query": 4
|
||||
},
|
||||
"mcp_call_status": {
|
||||
"matched_non_empty": 4
|
||||
},
|
||||
"limited_reason_category": {},
|
||||
"route_health": {
|
||||
"ok_or_factual": 4
|
||||
},
|
||||
"tool_gate_decision": {
|
||||
"run_address_lane": 4
|
||||
},
|
||||
"tool_gate_reason": {
|
||||
"address_mode_classifier_detected": 4
|
||||
}
|
||||
},
|
||||
"address_llm_predecompose_metrics": {
|
||||
"overall": {
|
||||
"llm_attempted": 4,
|
||||
"llm_applied": 2,
|
||||
"fallback_used": 0,
|
||||
"fallback_rate": 0.0,
|
||||
"tool_gate_blocked": 0,
|
||||
"gate_block_rate": 0.0
|
||||
},
|
||||
"by_intent": {
|
||||
"counterparty_activity_lifecycle": {
|
||||
"total": 4,
|
||||
"llm_attempted": 4,
|
||||
"llm_applied": 2,
|
||||
"fallback_used": 0,
|
||||
"tool_gate_blocked": 0,
|
||||
"fallback_rate": 0.0,
|
||||
"gate_block_rate": 0.0
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
+28
@@ -0,0 +1,28 @@
|
||||
# 2026-04-02_Address_Nightly_followup_25_20-23-18
|
||||
|
||||
Generated at: 2026-04-02T20:25:42
|
||||
Questions file: X:\1C\NDC_1C\docs\ADDRESS\question_sets\address_followup_context_chains_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: route
|
||||
|
||||
## Totals
|
||||
- questions_total: 25
|
||||
- ok_200_count: 25
|
||||
- semantic_pass_count: 25
|
||||
- semantic_pass_rate: 1.0
|
||||
- route_pass_count: 25
|
||||
- route_pass_rate: 1.0
|
||||
- strict_pass_count: 25
|
||||
- strict_pass_rate: 1.0
|
||||
- factual_count: 23
|
||||
- partial_coverage_count: 2
|
||||
- clarification_required_count: 0
|
||||
- http_error_count: 0
|
||||
- llm_decomposition_applied_count: 14
|
||||
- avg_elapsed_ms: 5770.4
|
||||
|
||||
## Files
|
||||
- run_summary.json
|
||||
- full_live_results.json
|
||||
- failures_only.json
|
||||
+1
@@ -0,0 +1 @@
|
||||
[]
|
||||
+3832
File diff suppressed because one or more lines are too long
+29
@@ -0,0 +1,29 @@
|
||||
# Response Audit: 2026-04-02_Address_Nightly_followup_25_20-23-18
|
||||
|
||||
| id | strict | route_health | reply_type | intent | limited_reason | question | assistant_first_line |
|
||||
|---|---|---|---|---|---|---|---|
|
||||
| F001 | True | ok_or_factual | factual | list_documents_by_counterparty | None | Покажи документы по СВК за 2020 | Собран список документов по контрагенту (live address lane). |
|
||||
| F002 | True | ok_or_factual | factual | list_documents_by_counterparty | None | а теперь только за май 2020 | По окну 2020-05-01..2020-05-31 строк не найдено; показаны ближайшие доступные данные 2020-07-27..2021-11-10. |
|
||||
| F003 | True | ok_or_factual | factual | account_balance_snapshot | None | а по счету 60.01 на ту же дату | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| F004 | True | ok_or_factual | factual | account_balance_snapshot | None | а на ту же дату по 62.01 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| F005 | True | ok_or_factual | factual | documents_forming_balance | None | раскрой остаток по 62.01 документами на ту же дату | Собран drilldown документов, формирующих остаток по счету на указанную дату. |
|
||||
| F006 | True | ok_or_factual | factual | bank_operations_by_counterparty | None | Покажи банковские операции по СВК за 2020 | Точный якорь не подтвердился в текущем окне live-данных; показаны ближайшие доступные документы/операции по выбранному типу. |
|
||||
| F007 | True | ok_or_factual | factual | bank_operations_by_counterparty | None | а теперь только ноябрь 2020 | Точный якорь не подтвердился в текущем окне live-данных; показаны ближайшие доступные документы/операции по выбранному типу. |
|
||||
| F008 | True | ok_or_factual | factual | list_documents_by_counterparty | None | а теперь документы по нему | Точный якорь не подтвердился в текущем окне live-данных; показаны ближайшие доступные документы/операции по выбранному типу. |
|
||||
| F009 | True | ok_or_factual | factual | account_balance_snapshot | None | и остаток по 51 на ту же дату | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| F010 | True | ok_or_factual | factual | account_balance_snapshot | None | а теперь только май 2020 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| F011 | True | partial_non_blocking | partial_coverage | account_balance_snapshot | empty_match | Покажи сальдо по счету 60 на 2020-12-31 | В live-данных по текущему фильтру записи не найдены. |
|
||||
| F012 | True | ok_or_factual | factual | account_balance_snapshot | None | а теперь только май 2020 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| F013 | True | ok_or_factual | factual | account_balance_snapshot | None | а на ту же дату по 62 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| F014 | True | ok_or_factual | factual | documents_forming_balance | None | раскрой 62 документами на ту же дату | Собран drilldown документов, формирующих остаток по счету на указанную дату. |
|
||||
| F015 | True | partial_non_blocking | partial_coverage | account_balance_snapshot | empty_match | вернись на 2020-12-31 по 60 | В live-данных по текущему фильтру записи не найдены. |
|
||||
| F016 | True | ok_or_factual | factual | list_documents_by_contract | None | Покажи документы по договору 19/15 за 2020 | Период сохранен. Глубина live-выборки автоматически расширена до 1000 строк. |
|
||||
| F017 | True | ok_or_factual | factual | bank_operations_by_contract | None | а теперь банковские операции | Период сохранен. Глубина live-выборки автоматически расширена до 1000 строк. |
|
||||
| F018 | True | ok_or_factual | factual | bank_operations_by_contract | None | а теперь только за 2020 | Период сохранен. Глубина live-выборки автоматически расширена до 1000 строк. |
|
||||
| F019 | True | ok_or_factual | factual | open_items_by_counterparty_or_contract | None | есть ли открытые позиции по договору 19/15 на 2020-12-31 | Период сохранен. Глубина live-выборки автоматически расширена до 1000 строк. |
|
||||
| F020 | True | ok_or_factual | factual | list_documents_by_contract | None | покажи документы по этому же договору | Собран список документов по договору (live address lane). |
|
||||
| F021 | True | ok_or_factual | factual | bank_operations_by_contract | None | Покажи банковские операции по договору 19/15 | Собран список банковских операций по договору (live address lane). |
|
||||
| F022 | True | ok_or_factual | factual | open_items_by_counterparty_or_contract | None | а теперь открытые позиции по нему | Период сохранен. Глубина live-выборки автоматически расширена до 1000 строк. |
|
||||
| F023 | True | ok_or_factual | factual | open_items_by_counterparty_or_contract | None | а теперь на 2020-12-31 | Период сохранен. Глубина live-выборки автоматически расширена до 1000 строк. |
|
||||
| F024 | True | ok_or_factual | factual | account_balance_snapshot | None | а по счету 51 на ту же дату | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| F025 | True | ok_or_factual | factual | list_documents_by_contract | None | а документы по этому же договору за тот же период | Точный якорь не подтвердился в текущем окне live-данных; показаны ближайшие доступные документы/операции по выбранному типу. |
|
||||
+55
@@ -0,0 +1,55 @@
|
||||
{
|
||||
"run_id": "2026-04-02_Address_Nightly_followup_25_20-23-18",
|
||||
"generated_at": "2026-04-02T20:25:42",
|
||||
"source_questions_file": "X:\\1C\\NDC_1C\\docs\\ADDRESS\\question_sets\\address_followup_context_chains_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": "route",
|
||||
"totals": {
|
||||
"questions_total": 25,
|
||||
"ok_200_count": 25,
|
||||
"semantic_pass_count": 25,
|
||||
"semantic_pass_rate": 1.0,
|
||||
"route_pass_count": 25,
|
||||
"route_pass_rate": 1.0,
|
||||
"strict_pass_count": 25,
|
||||
"strict_pass_rate": 1.0,
|
||||
"factual_count": 23,
|
||||
"partial_coverage_count": 2,
|
||||
"clarification_required_count": 0,
|
||||
"http_error_count": 0,
|
||||
"llm_decomposition_applied_count": 14,
|
||||
"avg_elapsed_ms": 5770.4
|
||||
},
|
||||
"distributions": {
|
||||
"reply_type": {
|
||||
"factual": 23,
|
||||
"partial_coverage": 2
|
||||
},
|
||||
"actual_intent": {
|
||||
"list_documents_by_counterparty": 3,
|
||||
"account_balance_snapshot": 9,
|
||||
"documents_forming_balance": 2,
|
||||
"bank_operations_by_counterparty": 2,
|
||||
"list_documents_by_contract": 3,
|
||||
"bank_operations_by_contract": 3,
|
||||
"open_items_by_counterparty_or_contract": 3
|
||||
},
|
||||
"actual_mode": {
|
||||
"address_query": 25
|
||||
},
|
||||
"mcp_call_status": {
|
||||
"matched_non_empty": 23,
|
||||
"no_raw_rows": 2
|
||||
},
|
||||
"limited_reason_category": {
|
||||
"empty_match": 2
|
||||
},
|
||||
"route_health": {
|
||||
"ok_or_factual": 23,
|
||||
"partial_non_blocking": 2
|
||||
}
|
||||
}
|
||||
}
|
||||
+23
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"generated_at": "2026-04-02T20:25:42",
|
||||
"total": 1,
|
||||
"passed": 1,
|
||||
"failed": 0,
|
||||
"results": [
|
||||
{
|
||||
"run_dir": "X:\\1C\\NDC_1C\\docs\\ADDRESS\\runs\\2026-04-02_Address_Nightly_Regression_AfterFocusFix\\2026-04-02_Address_Nightly_followup_25_20-23-18",
|
||||
"valid": true,
|
||||
"errors": [],
|
||||
"warnings": [],
|
||||
"metrics": {
|
||||
"run_id": "2026-04-02_Address_Nightly_followup_25_20-23-18",
|
||||
"questions_total": 25,
|
||||
"route_pass_rate": 1.0,
|
||||
"strict_pass_rate": 1.0,
|
||||
"http_error_count": 0,
|
||||
"rows_count": 25,
|
||||
"failures_count": 0
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
+28
@@ -0,0 +1,28 @@
|
||||
# 2026-04-02_Address_Nightly_followup_25_20-27-52
|
||||
|
||||
Generated at: 2026-04-02T20:29:57
|
||||
Questions file: X:\1C\NDC_1C\docs\ADDRESS\question_sets\address_followup_context_chains_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: route
|
||||
|
||||
## Totals
|
||||
- questions_total: 25
|
||||
- ok_200_count: 25
|
||||
- semantic_pass_count: 25
|
||||
- semantic_pass_rate: 1.0
|
||||
- route_pass_count: 25
|
||||
- route_pass_rate: 1.0
|
||||
- strict_pass_count: 25
|
||||
- strict_pass_rate: 1.0
|
||||
- factual_count: 23
|
||||
- partial_coverage_count: 2
|
||||
- clarification_required_count: 0
|
||||
- http_error_count: 0
|
||||
- llm_decomposition_applied_count: 14
|
||||
- avg_elapsed_ms: 4961.4
|
||||
|
||||
## Files
|
||||
- run_summary.json
|
||||
- full_live_results.json
|
||||
- failures_only.json
|
||||
+1
@@ -0,0 +1 @@
|
||||
[]
|
||||
+3837
File diff suppressed because one or more lines are too long
+29
@@ -0,0 +1,29 @@
|
||||
# Response Audit: 2026-04-02_Address_Nightly_followup_25_20-27-52
|
||||
|
||||
| id | strict | route_health | reply_type | intent | limited_reason | question | assistant_first_line |
|
||||
|---|---|---|---|---|---|---|---|
|
||||
| F001 | True | ok_or_factual | factual | list_documents_by_counterparty | None | Покажи документы по СВК за 2020 | Собран список документов по контрагенту (live address lane). |
|
||||
| F002 | True | ok_or_factual | factual | list_documents_by_counterparty | None | а теперь только за май 2020 | По окну 2020-05-01..2020-05-31 строк не найдено; показаны ближайшие доступные данные 2020-07-27..2021-11-10. |
|
||||
| F003 | True | ok_or_factual | factual | account_balance_snapshot | None | а по счету 60.01 на ту же дату | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| F004 | True | ok_or_factual | factual | account_balance_snapshot | None | а на ту же дату по 62.01 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| F005 | True | ok_or_factual | factual | documents_forming_balance | None | раскрой остаток по 62.01 документами на ту же дату | Собран drilldown документов, формирующих остаток по счету на указанную дату. |
|
||||
| F006 | True | ok_or_factual | factual | bank_operations_by_counterparty | None | Покажи банковские операции по СВК за 2020 | Точный якорь не подтвердился в текущем окне live-данных; показаны ближайшие доступные документы/операции по выбранному типу. |
|
||||
| F007 | True | ok_or_factual | factual | bank_operations_by_counterparty | None | а теперь только ноябрь 2020 | Точный якорь не подтвердился в текущем окне live-данных; показаны ближайшие доступные документы/операции по выбранному типу. |
|
||||
| F008 | True | ok_or_factual | factual | list_documents_by_counterparty | None | а теперь документы по нему | Точный якорь не подтвердился в текущем окне live-данных; показаны ближайшие доступные документы/операции по выбранному типу. |
|
||||
| F009 | True | ok_or_factual | factual | account_balance_snapshot | None | и остаток по 51 на ту же дату | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| F010 | True | ok_or_factual | factual | account_balance_snapshot | None | а теперь только май 2020 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| F011 | True | partial_non_blocking | partial_coverage | account_balance_snapshot | empty_match | Покажи сальдо по счету 60 на 2020-12-31 | В live-данных по текущему фильтру записи не найдены. |
|
||||
| F012 | True | ok_or_factual | factual | account_balance_snapshot | None | а теперь только май 2020 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| F013 | True | ok_or_factual | factual | account_balance_snapshot | None | а на ту же дату по 62 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| F014 | True | ok_or_factual | factual | documents_forming_balance | None | раскрой 62 документами на ту же дату | Собран drilldown документов, формирующих остаток по счету на указанную дату. |
|
||||
| F015 | True | partial_non_blocking | partial_coverage | account_balance_snapshot | empty_match | вернись на 2020-12-31 по 60 | В live-данных по текущему фильтру записи не найдены. |
|
||||
| F016 | True | ok_or_factual | factual | list_documents_by_contract | None | Покажи документы по договору 19/15 за 2020 | Период сохранен. Глубина live-выборки автоматически расширена до 1000 строк. |
|
||||
| F017 | True | ok_or_factual | factual | bank_operations_by_contract | None | а теперь банковские операции | Период сохранен. Глубина live-выборки автоматически расширена до 1000 строк. |
|
||||
| F018 | True | ok_or_factual | factual | bank_operations_by_contract | None | а теперь только за 2020 | Период сохранен. Глубина live-выборки автоматически расширена до 1000 строк. |
|
||||
| F019 | True | ok_or_factual | factual | open_items_by_counterparty_or_contract | None | есть ли открытые позиции по договору 19/15 на 2020-12-31 | Период сохранен. Глубина live-выборки автоматически расширена до 1000 строк. |
|
||||
| F020 | True | ok_or_factual | factual | list_documents_by_contract | None | покажи документы по этому же договору | Собран список документов по договору (live address lane). |
|
||||
| F021 | True | ok_or_factual | factual | bank_operations_by_contract | None | Покажи банковские операции по договору 19/15 | Собран список банковских операций по договору (live address lane). |
|
||||
| F022 | True | ok_or_factual | factual | open_items_by_counterparty_or_contract | None | а теперь открытые позиции по нему | Период сохранен. Глубина live-выборки автоматически расширена до 1000 строк. |
|
||||
| F023 | True | ok_or_factual | factual | open_items_by_counterparty_or_contract | None | а теперь на 2020-12-31 | Период сохранен. Глубина live-выборки автоматически расширена до 1000 строк. |
|
||||
| F024 | True | ok_or_factual | factual | account_balance_snapshot | None | а по счету 51 на ту же дату | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| F025 | True | ok_or_factual | factual | list_documents_by_contract | None | а документы по этому же договору за тот же период | Точный якорь не подтвердился в текущем окне live-данных; показаны ближайшие доступные документы/операции по выбранному типу. |
|
||||
+55
@@ -0,0 +1,55 @@
|
||||
{
|
||||
"run_id": "2026-04-02_Address_Nightly_followup_25_20-27-52",
|
||||
"generated_at": "2026-04-02T20:29:57",
|
||||
"source_questions_file": "X:\\1C\\NDC_1C\\docs\\ADDRESS\\question_sets\\address_followup_context_chains_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": "route",
|
||||
"totals": {
|
||||
"questions_total": 25,
|
||||
"ok_200_count": 25,
|
||||
"semantic_pass_count": 25,
|
||||
"semantic_pass_rate": 1.0,
|
||||
"route_pass_count": 25,
|
||||
"route_pass_rate": 1.0,
|
||||
"strict_pass_count": 25,
|
||||
"strict_pass_rate": 1.0,
|
||||
"factual_count": 23,
|
||||
"partial_coverage_count": 2,
|
||||
"clarification_required_count": 0,
|
||||
"http_error_count": 0,
|
||||
"llm_decomposition_applied_count": 14,
|
||||
"avg_elapsed_ms": 4961.4
|
||||
},
|
||||
"distributions": {
|
||||
"reply_type": {
|
||||
"factual": 23,
|
||||
"partial_coverage": 2
|
||||
},
|
||||
"actual_intent": {
|
||||
"list_documents_by_counterparty": 3,
|
||||
"account_balance_snapshot": 9,
|
||||
"documents_forming_balance": 2,
|
||||
"bank_operations_by_counterparty": 2,
|
||||
"list_documents_by_contract": 3,
|
||||
"bank_operations_by_contract": 3,
|
||||
"open_items_by_counterparty_or_contract": 3
|
||||
},
|
||||
"actual_mode": {
|
||||
"address_query": 25
|
||||
},
|
||||
"mcp_call_status": {
|
||||
"matched_non_empty": 23,
|
||||
"no_raw_rows": 2
|
||||
},
|
||||
"limited_reason_category": {
|
||||
"empty_match": 2
|
||||
},
|
||||
"route_health": {
|
||||
"ok_or_factual": 23,
|
||||
"partial_non_blocking": 2
|
||||
}
|
||||
}
|
||||
}
|
||||
+67
@@ -0,0 +1,67 @@
|
||||
{
|
||||
"generated_at": "2026-04-02T20:29:57",
|
||||
"overall_pass": true,
|
||||
"baseline": {
|
||||
"summary_path": "X:\\1C\\NDC_1C\\docs\\ADDRESS\\runs\\2026-04-02_Address_Followup_Context_Chains_2026-04-02_19-15-Run5\\run_summary.json",
|
||||
"run_id": "2026-04-02_Address_Followup_Context_Chains_2026-04-02_19-15-Run5",
|
||||
"questions_total": 25,
|
||||
"strict_pass_rate": 1.0,
|
||||
"route_pass_rate": 1.0,
|
||||
"execution_error_count": 0,
|
||||
"false_factual_rate": 0.0,
|
||||
"notes": [
|
||||
"execution_error_count derived as http_error_count + limited_reason_category.execution_error",
|
||||
"false_factual_rate derived from false_factual_count/questions_total"
|
||||
]
|
||||
},
|
||||
"candidate": {
|
||||
"summary_path": "X:\\1C\\NDC_1C\\docs\\ADDRESS\\runs\\2026-04-02_Address_Nightly_Regression_AfterFocusFix\\2026-04-02_Address_Nightly_followup_25_20-27-52\\run_summary.json",
|
||||
"run_id": "2026-04-02_Address_Nightly_followup_25_20-27-52",
|
||||
"questions_total": 25,
|
||||
"strict_pass_rate": 1.0,
|
||||
"route_pass_rate": 1.0,
|
||||
"execution_error_count": 0,
|
||||
"false_factual_rate": 0.0,
|
||||
"notes": [
|
||||
"execution_error_count derived as http_error_count + limited_reason_category.execution_error",
|
||||
"false_factual_rate derived from false_factual_count/questions_total"
|
||||
]
|
||||
},
|
||||
"checks": [
|
||||
{
|
||||
"metric": "strict_pass_rate",
|
||||
"passed": true,
|
||||
"baseline": 1.0,
|
||||
"candidate": 1.0,
|
||||
"rule": "candidate >= baseline"
|
||||
},
|
||||
{
|
||||
"metric": "route_pass_rate",
|
||||
"passed": true,
|
||||
"baseline": 1.0,
|
||||
"candidate": 1.0,
|
||||
"rule": "candidate >= baseline"
|
||||
},
|
||||
{
|
||||
"metric": "execution_error_count",
|
||||
"passed": true,
|
||||
"baseline": 0,
|
||||
"candidate": 0,
|
||||
"rule": "candidate <= baseline"
|
||||
},
|
||||
{
|
||||
"metric": "false_factual_rate",
|
||||
"passed": true,
|
||||
"baseline": 0.0,
|
||||
"candidate": 0.0,
|
||||
"rule": "candidate <= baseline"
|
||||
},
|
||||
{
|
||||
"metric": "questions_total_match",
|
||||
"passed": true,
|
||||
"baseline": 25,
|
||||
"candidate": 25,
|
||||
"rule": "candidate == baseline"
|
||||
}
|
||||
]
|
||||
}
|
||||
+23
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"generated_at": "2026-04-02T20:29:57",
|
||||
"total": 1,
|
||||
"passed": 1,
|
||||
"failed": 0,
|
||||
"results": [
|
||||
{
|
||||
"run_dir": "X:\\1C\\NDC_1C\\docs\\ADDRESS\\runs\\2026-04-02_Address_Nightly_Regression_AfterFocusFix\\2026-04-02_Address_Nightly_followup_25_20-27-52",
|
||||
"valid": true,
|
||||
"errors": [],
|
||||
"warnings": [],
|
||||
"metrics": {
|
||||
"run_id": "2026-04-02_Address_Nightly_followup_25_20-27-52",
|
||||
"questions_total": 25,
|
||||
"route_pass_rate": 1.0,
|
||||
"strict_pass_rate": 1.0,
|
||||
"http_error_count": 0,
|
||||
"rows_count": 25,
|
||||
"failures_count": 0
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
+28
@@ -0,0 +1,28 @@
|
||||
# 2026-04-02_Address_Nightly_stress_102_20-11-51
|
||||
|
||||
Generated at: 2026-04-02T20:23:18
|
||||
Questions file: X:\1C\NDC_1C\docs\ADDRESS\question_sets\address_slang_stress_full_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: route
|
||||
|
||||
## Totals
|
||||
- questions_total: 102
|
||||
- ok_200_count: 102
|
||||
- semantic_pass_count: 102
|
||||
- semantic_pass_rate: 1.0
|
||||
- route_pass_count: 102
|
||||
- route_pass_rate: 1.0
|
||||
- strict_pass_count: 102
|
||||
- strict_pass_rate: 1.0
|
||||
- factual_count: 96
|
||||
- partial_coverage_count: 6
|
||||
- clarification_required_count: 0
|
||||
- http_error_count: 0
|
||||
- llm_decomposition_applied_count: 81
|
||||
- avg_elapsed_ms: 6736.3
|
||||
|
||||
## Files
|
||||
- run_summary.json
|
||||
- full_live_results.json
|
||||
- failures_only.json
|
||||
+1
@@ -0,0 +1 @@
|
||||
[]
|
||||
+15391
File diff suppressed because one or more lines are too long
+106
@@ -0,0 +1,106 @@
|
||||
# Response Audit: 2026-04-02_Address_Nightly_stress_102_20-11-51
|
||||
|
||||
| id | strict | route_health | reply_type | intent | limited_reason | question | assistant_first_line |
|
||||
|---|---|---|---|---|---|---|---|
|
||||
| S001 | True | ok_or_factual | factual | list_documents_by_counterparty | None | свк доки за 2020 покаж пж | Точный якорь не подтвердился в текущем окне live-данных; показаны ближайшие доступные документы/операции по выбранному типу. |
|
||||
| S002 | True | ok_or_factual | factual | list_documents_by_counterparty | None | покеж все доки по свк за 20 год | Собран список документов по контрагенту (live address lane). |
|
||||
| S003 | True | ok_or_factual | factual | list_documents_by_counterparty | None | дай список документов по свк за 2020 | Собран список документов по контрагенту (live address lane). |
|
||||
| S004 | True | ok_or_factual | factual | list_documents_by_counterparty | None | какие у свк есть доки за 2020? | Точный якорь не подтвердился в текущем окне live-данных; показаны ближайшие доступные документы/операции по выбранному типу. |
|
||||
| S005 | True | ok_or_factual | factual | list_documents_by_counterparty | None | че по свк по докам за 2020 год | Собран список документов по контрагенту (live address lane). |
|
||||
| S006 | True | ok_or_factual | factual | list_documents_by_counterparty | None | ёпт покажи доки по свк за 2020 | Собран список документов по контрагенту (live address lane). |
|
||||
| S007 | True | ok_or_factual | factual | list_documents_by_counterparty | None | бля, доки свк 2020 вывали | Собран список документов по контрагенту (live address lane). |
|
||||
| S008 | True | ok_or_factual | factual | list_documents_by_counterparty | None | svk docs for 2020 please | Собран список документов по контрагенту (live address lane). |
|
||||
| S009 | True | ok_or_factual | factual | list_documents_by_counterparty | None | docs by counterparty svk year 2020 | Точный якорь не подтвердился в текущем окне live-данных; показаны ближайшие доступные документы/операции по выбранному типу. |
|
||||
| S010 | True | ok_or_factual | factual | list_documents_by_counterparty | None | по контрагенту свк покаж документы за 2020 | Собран список документов по контрагенту (live address lane). |
|
||||
| S011 | True | ok_or_factual | factual | list_documents_by_counterparty | None | плс доки по свк 2020 | Точный якорь не подтвердился в текущем окне live-данных; показаны ближайшие доступные документы/операции по выбранному типу. |
|
||||
| S012 | True | ok_or_factual | factual | list_documents_by_counterparty | None | свк док за 2020 гони | Собран список документов по контрагенту (live address lane). |
|
||||
| S013 | True | ok_or_factual | factual | bank_operations_by_counterparty | None | по свк банковские операции за 2020 покаж | Собран список банковских операций по контрагенту (live address lane). |
|
||||
| S014 | True | ok_or_factual | factual | bank_operations_by_counterparty | None | свк выписка банка 2020 | Собран список банковских операций по контрагенту (live address lane). |
|
||||
| S015 | True | ok_or_factual | factual | bank_operations_by_counterparty | None | платежи по свк за 2020 выведи | Собран список банковских операций по контрагенту (live address lane). |
|
||||
| S016 | True | ok_or_factual | factual | bank_operations_by_counterparty | None | оплаты по свк за 2020 | Собран список банковских операций по контрагенту (live address lane). |
|
||||
| S017 | True | ok_or_factual | factual | bank_operations_by_counterparty | None | свк банк опер за 2020 | Точный якорь не подтвердился в текущем окне live-данных; показаны ближайшие доступные документы/операции по выбранному типу. |
|
||||
| S018 | True | ok_or_factual | factual | bank_operations_by_counterparty | None | че у свк по банку за 2020 | Точный якорь не подтвердился в текущем окне live-данных; показаны ближайшие доступные документы/операции по выбранному типу. |
|
||||
| S019 | True | ok_or_factual | factual | bank_operations_by_counterparty | None | свк списания/поступления за 2020 | Точный якорь не подтвердился в текущем окне live-данных; показаны ближайшие доступные документы/операции по выбранному типу. |
|
||||
| S020 | True | ok_or_factual | factual | bank_operations_by_counterparty | None | bank ops by svk for 2020 | Собран список банковских операций по контрагенту (live address lane). |
|
||||
| S021 | True | ok_or_factual | factual | bank_operations_by_counterparty | None | transactions by counterparty svk 2020 | Собран список банковских операций по контрагенту (live address lane). |
|
||||
| S022 | True | ok_or_factual | factual | bank_operations_by_counterparty | None | бля, по свк банковские платежки 2020 | Собран список банковских операций по контрагенту (live address lane). |
|
||||
| S023 | True | ok_or_factual | factual | account_balance_snapshot | None | сальдо по счету 60.01 на дату 2020-07-31 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| S024 | True | ok_or_factual | factual | account_balance_snapshot | None | остаток по счету 60.01 на 2020.05 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| S025 | True | ok_or_factual | factual | account_balance_snapshot | None | покажи остаток по 60.01 за май 2020 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| S026 | True | ok_or_factual | factual | account_balance_snapshot | None | счет 60 остаток на май 2020 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| S027 | True | ok_or_factual | factual | account_balance_snapshot | None | баланс account 60.01 as of 2020-07-31 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| S028 | True | ok_or_factual | factual | account_balance_snapshot | None | 60.01 saldo на 31.07.2020 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| S029 | True | ok_or_factual | factual | account_balance_snapshot | None | сколько на счете 60 на конец 2020-05 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| S030 | True | partial_non_blocking | partial_coverage | account_balance_snapshot | empty_match | дай остаток 60.02 на 2020-12-31 | В live-данных по текущему фильтру записи не найдены. |
|
||||
| S031 | True | partial_non_blocking | partial_coverage | account_balance_snapshot | empty_match | епт, сальдо по счету 62.01 на 2020-12-31 | В live-данных по текущему фильтру записи не найдены. |
|
||||
| S032 | True | ok_or_factual | factual | account_balance_snapshot | None | плс остаток по счету 51 на 2020-06-30 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| S033 | True | ok_or_factual | factual | account_balance_snapshot | None | как там по счету 60.01 на 2020.07? | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| S034 | True | ok_or_factual | factual | account_balance_snapshot | None | сальдо 60 на 2020 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| S035 | True | ok_or_factual | factual | documents_forming_balance | None | какие документы формируют остаток по счету 60.01 на 2020-07-31 | Собран drilldown документов, формирующих остаток по счету на указанную дату. |
|
||||
| S036 | True | ok_or_factual | factual | documents_forming_balance | None | из чего состоит остаток по счету 60 на 2020.05 | Собран drilldown документов, формирующих остаток по счету на указанную дату. |
|
||||
| S037 | True | ok_or_factual | factual | documents_forming_balance | None | раскрой остаток 60.01 по документам на конец июля 2020 | Собран drilldown документов, формирующих остаток по счету на указанную дату. |
|
||||
| S038 | True | ok_or_factual | factual | documents_forming_balance | None | доки под остатком 60.01 на 2020-07-31 | Собран drilldown документов, формирующих остаток по счету на указанную дату. |
|
||||
| S039 | True | ok_or_factual | factual | documents_forming_balance | None | documents forming balance for account 60.01 as of 2020-07-31 | Собран drilldown документов, формирующих остаток по счету на указанную дату. |
|
||||
| S040 | True | ok_or_factual | factual | documents_forming_balance | None | бля, какие доки формируют остаток 60.01 на 2020-05-31 | Собран drilldown документов, формирующих остаток по счету на указанную дату. |
|
||||
| S041 | True | partial_non_blocking | partial_coverage | documents_forming_balance | empty_match | по счету 62.01 раскрой остаток документами на 2020-12-31 | В live-данных по текущему фильтру записи не найдены. |
|
||||
| S042 | True | ok_or_factual | factual | documents_forming_balance | None | из чего остаток по счету 51 на 2020-06-30 | Собран drilldown документов, формирующих остаток по счету на указанную дату. |
|
||||
| S043 | True | ok_or_factual | factual | list_documents_by_contract | None | покажи документы по договору 19/15 за 2020 | Период сохранен. Глубина live-выборки автоматически расширена до 1000 строк. |
|
||||
| S044 | True | ok_or_factual | factual | list_documents_by_contract | None | доки по дог. 19/15 за 2020 | Период сохранен. Глубина live-выборки автоматически расширена до 1000 строк. |
|
||||
| S045 | True | ok_or_factual | factual | list_documents_by_contract | None | какие документы по контракту 19/15 | Собран список документов по договору (live address lane). |
|
||||
| S046 | True | ok_or_factual | factual | list_documents_by_contract | None | docs by contract 19/15 year 2020 | Период сохранен. Глубина live-выборки автоматически расширена до 1000 строк. |
|
||||
| S047 | True | ok_or_factual | factual | list_documents_by_contract | None | бля, покажи по договору 19/15 доки | Собран список документов по договору (live address lane). |
|
||||
| S048 | True | ok_or_factual | factual | list_documents_by_contract | None | договор 19/15 документы | Собран список документов по договору (live address lane). |
|
||||
| S049 | True | ok_or_factual | factual | list_documents_by_contract | None | плс документы договор №19/15 | Собран список документов по договору (live address lane). |
|
||||
| S050 | True | ok_or_factual | factual | list_documents_by_contract | None | покеж документы по 19/15 | Собран список документов по договору (live address lane). |
|
||||
| S051 | True | ok_or_factual | factual | bank_operations_by_contract | None | банковские операции по договору 19/15 | Собран список банковских операций по договору (live address lane). |
|
||||
| S052 | True | ok_or_factual | factual | bank_operations_by_contract | None | платежи по договору 19/15 | Собран список банковских операций по договору (live address lane). |
|
||||
| S053 | True | ok_or_factual | factual | bank_operations_by_contract | None | выписка по договору 19/15 | Собран список банковских операций по договору (live address lane). |
|
||||
| S054 | True | ok_or_factual | factual | bank_operations_by_contract | None | bank ops by contract 19/15 | Точный якорь не подтвердился в текущем окне live-данных; показаны ближайшие доступные документы/операции по выбранному типу. |
|
||||
| S055 | True | ok_or_factual | factual | bank_operations_by_contract | None | ёпт, покажи банк операции по дог 19/15 | Собран список банковских операций по договору (live address lane). |
|
||||
| S056 | True | ok_or_factual | factual | bank_operations_by_contract | None | по контракту 19/15 платежки | Собран список банковских операций по договору (live address lane). |
|
||||
| S057 | True | ok_or_factual | factual | account_balance_snapshot | None | покажи сальдо по счету 60 за 2020 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| S058 | True | ok_or_factual | factual | account_balance_snapshot | None | а теперь только май 2020 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| S059 | True | ok_or_factual | factual | account_balance_snapshot | None | ок, теперь 2020.05 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| S060 | True | ok_or_factual | factual | account_balance_snapshot | None | теперь на 2020-07-31 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| X001 | True | ok_or_factual | factual | list_documents_by_counterparty | None | свк доки кинь за 2020 | Точный якорь не подтвердился в текущем окне live-данных; показаны ближайшие доступные документы/операции по выбранному типу. |
|
||||
| X002 | True | ok_or_factual | factual | list_documents_by_counterparty | None | по свк все документы за 20й год | Собран список документов по контрагенту (live address lane). |
|
||||
| X003 | True | ok_or_factual | factual | list_documents_by_counterparty | None | пж вывали доки контрагент свк 2020 | Собран список документов по контрагенту (live address lane). |
|
||||
| X004 | True | ok_or_factual | factual | list_documents_by_counterparty | None | svk poka docy za 2020 | Собран список документов по контрагенту (live address lane). |
|
||||
| X005 | True | ok_or_factual | factual | list_documents_by_counterparty | None | какие доки по компании свк за 2020 | Собран список документов по контрагенту (live address lane). |
|
||||
| X006 | True | ok_or_factual | factual | list_documents_by_counterparty | None | бля покаж свк документы 2020 | Точный якорь не подтвердился в текущем окне live-данных; показаны ближайшие доступные документы/операции по выбранному типу. |
|
||||
| X007 | True | ok_or_factual | factual | bank_operations_by_counterparty | None | свк банк операции за 2020 | Точный якорь не подтвердился в текущем окне live-данных; показаны ближайшие доступные документы/операции по выбранному типу. |
|
||||
| X008 | True | ok_or_factual | factual | bank_operations_by_counterparty | None | по свк выписку банка за 2020 выведи | Собран список банковских операций по контрагенту (live address lane). |
|
||||
| X009 | True | ok_or_factual | factual | bank_operations_by_counterparty | None | свк платежки за 2020 | Точный якорь не подтвердился в текущем окне live-данных; показаны ближайшие доступные документы/операции по выбранному типу. |
|
||||
| X010 | True | ok_or_factual | factual | bank_operations_by_counterparty | None | bank ops svk 2020 | Собран список банковских операций по контрагенту (live address lane). |
|
||||
| X011 | True | ok_or_factual | factual | bank_operations_by_counterparty | None | транзакции по свк за 2020 | Собран список банковских операций по контрагенту (live address lane). |
|
||||
| X012 | True | ok_or_factual | factual | bank_operations_by_counterparty | None | ёпт по свк че по банку 2020 | Точный якорь не подтвердился в текущем окне live-данных; показаны ближайшие доступные документы/операции по выбранному типу. |
|
||||
| X013 | True | ok_or_factual | factual | account_balance_snapshot | None | остаток по 60.01 на 2020-07-31 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| X014 | True | ok_or_factual | factual | account_balance_snapshot | None | сальдо 60.01 на 31.07.2020 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| X015 | True | ok_or_factual | factual | account_balance_snapshot | None | что на счете 60 на 2020.05 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| X016 | True | ok_or_factual | factual | account_balance_snapshot | None | дай остаток 62.01 на 2020 май | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| X017 | True | partial_non_blocking | partial_coverage | account_balance_snapshot | empty_match | saldo account 60 as of 2020-12-31 | В live-данных по текущему фильтру записи не найдены. |
|
||||
| X018 | True | ok_or_factual | factual | account_balance_snapshot | None | плиз остаток по счету 51 на 2020-06-30 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| X019 | True | partial_non_blocking | partial_coverage | account_balance_snapshot | empty_match | скока по 60.02 на конец 2020-12 | В live-данных по текущему фильтру записи не найдены. |
|
||||
| X020 | True | ok_or_factual | factual | account_balance_snapshot | None | бля сальдо 60.01 на 2020-05-31 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| X021 | True | ok_or_factual | factual | documents_forming_balance | None | раскрой остаток 60.01 по документам на конец июля 2020 | Собран drilldown документов, формирующих остаток по счету на указанную дату. |
|
||||
| X022 | True | ok_or_factual | factual | documents_forming_balance | None | доки под остатком 60.01 на 2020-07-31 | Собран drilldown документов, формирующих остаток по счету на указанную дату. |
|
||||
| X023 | True | ok_or_factual | factual | documents_forming_balance | None | из чего остаток 60.01 на 2020-07-31 | Собран drilldown документов, формирующих остаток по счету на указанную дату. |
|
||||
| X024 | True | ok_or_factual | factual | documents_forming_balance | None | какие документы формируют остаток по 60.01 на 2020-07-31 | Собран drilldown документов, формирующих остаток по счету на указанную дату. |
|
||||
| X025 | True | ok_or_factual | factual | documents_forming_balance | None | docs forming balance 60.01 as of 2020-07-31 | Собран drilldown документов, формирующих остаток по счету на указанную дату. |
|
||||
| X026 | True | partial_non_blocking | partial_coverage | documents_forming_balance | empty_match | раскидай остаток 62.01 по докам на 2020-12-31 | В live-данных по текущему фильтру записи не найдены. |
|
||||
| X027 | True | ok_or_factual | factual | documents_forming_balance | None | по счету 51 раскрой остаток документами на 2020-06-30 | Собран drilldown документов, формирующих остаток по счету на указанную дату. |
|
||||
| X028 | True | ok_or_factual | factual | documents_forming_balance | None | бля из чего состоит остаток по 60.01 на 2020-05-31 | Собран drilldown документов, формирующих остаток по счету на указанную дату. |
|
||||
| X029 | True | ok_or_factual | factual | list_documents_by_contract | None | доки по договору 19/15 за 2020 | Период сохранен. Глубина live-выборки автоматически расширена до 1000 строк. |
|
||||
| X030 | True | ok_or_factual | factual | list_documents_by_contract | None | покажи документы контракт 19/15 | Собран список документов по договору (live address lane). |
|
||||
| X031 | True | ok_or_factual | factual | list_documents_by_contract | None | docs by contract 19/15 2020 | Период сохранен. Глубина live-выборки автоматически расширена до 1000 строк. |
|
||||
| X032 | True | ok_or_factual | factual | list_documents_by_contract | None | по дог 19/15 какие документы | Собран список документов по договору (live address lane). |
|
||||
| X033 | True | ok_or_factual | factual | list_documents_by_contract | None | договор 19/15 выведи доки | Точный якорь не подтвердился в текущем окне live-данных; показаны ближайшие доступные документы/операции по выбранному типу. |
|
||||
| X034 | True | ok_or_factual | factual | list_documents_by_contract | None | нах покажи документы по 19/15 | Собран список документов по договору (live address lane). |
|
||||
| X035 | True | ok_or_factual | factual | bank_operations_by_contract | None | банк операции по договору 19/15 | Собран список банковских операций по договору (live address lane). |
|
||||
| X036 | True | ok_or_factual | factual | bank_operations_by_contract | None | платежки по дог 19/15 | Собран список банковских операций по договору (live address lane). |
|
||||
| X037 | True | ok_or_factual | factual | bank_operations_by_contract | None | выписка по контракту 19/15 | Собран список банковских операций по договору (live address lane). |
|
||||
| X038 | True | ok_or_factual | factual | bank_operations_by_contract | None | bank ops by contract 19/15 | Точный якорь не подтвердился в текущем окне live-данных; показаны ближайшие доступные документы/операции по выбранному типу. |
|
||||
| X039 | True | ok_or_factual | factual | bank_operations_by_contract | None | покажи банк опер по дог 19/15 пж | Собран список банковских операций по договору (live address lane). |
|
||||
| X040 | True | ok_or_factual | factual | bank_operations_by_contract | None | епт транзакции договор 19/15 | Собран список банковских операций по договору (live address lane). |
|
||||
| X041 | True | ok_or_factual | factual | account_balance_snapshot | None | покажи сальдо по счету 60 за 2020 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| X042 | True | ok_or_factual | factual | account_balance_snapshot | None | а теперь только май 2020 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
+54
@@ -0,0 +1,54 @@
|
||||
{
|
||||
"run_id": "2026-04-02_Address_Nightly_stress_102_20-11-51",
|
||||
"generated_at": "2026-04-02T20:23:18",
|
||||
"source_questions_file": "X:\\1C\\NDC_1C\\docs\\ADDRESS\\question_sets\\address_slang_stress_full_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": "route",
|
||||
"totals": {
|
||||
"questions_total": 102,
|
||||
"ok_200_count": 102,
|
||||
"semantic_pass_count": 102,
|
||||
"semantic_pass_rate": 1.0,
|
||||
"route_pass_count": 102,
|
||||
"route_pass_rate": 1.0,
|
||||
"strict_pass_count": 102,
|
||||
"strict_pass_rate": 1.0,
|
||||
"factual_count": 96,
|
||||
"partial_coverage_count": 6,
|
||||
"clarification_required_count": 0,
|
||||
"http_error_count": 0,
|
||||
"llm_decomposition_applied_count": 81,
|
||||
"avg_elapsed_ms": 6736.3
|
||||
},
|
||||
"distributions": {
|
||||
"reply_type": {
|
||||
"factual": 96,
|
||||
"partial_coverage": 6
|
||||
},
|
||||
"actual_intent": {
|
||||
"list_documents_by_counterparty": 18,
|
||||
"bank_operations_by_counterparty": 16,
|
||||
"account_balance_snapshot": 26,
|
||||
"documents_forming_balance": 16,
|
||||
"list_documents_by_contract": 14,
|
||||
"bank_operations_by_contract": 12
|
||||
},
|
||||
"actual_mode": {
|
||||
"address_query": 102
|
||||
},
|
||||
"mcp_call_status": {
|
||||
"matched_non_empty": 96,
|
||||
"no_raw_rows": 6
|
||||
},
|
||||
"limited_reason_category": {
|
||||
"empty_match": 6
|
||||
},
|
||||
"route_health": {
|
||||
"ok_or_factual": 96,
|
||||
"partial_non_blocking": 6
|
||||
}
|
||||
}
|
||||
}
|
||||
+67
@@ -0,0 +1,67 @@
|
||||
{
|
||||
"generated_at": "2026-04-02T20:23:18",
|
||||
"overall_pass": true,
|
||||
"baseline": {
|
||||
"summary_path": "X:\\1C\\NDC_1C\\docs\\ADDRESS\\runs\\2026-04-02_Address_Slang_Live_Stress_2026-04-02_12-57-27\\run_summary.json",
|
||||
"run_id": "2026-04-02_Address_Slang_Live_Stress_2026-04-02_12-57-27",
|
||||
"questions_total": 102,
|
||||
"strict_pass_rate": 1.0,
|
||||
"route_pass_rate": 1.0,
|
||||
"execution_error_count": 0,
|
||||
"false_factual_rate": 0.0,
|
||||
"notes": [
|
||||
"execution_error_count derived as http_error_count + limited_reason_category.execution_error",
|
||||
"false_factual_rate derived from false_factual_count/questions_total"
|
||||
]
|
||||
},
|
||||
"candidate": {
|
||||
"summary_path": "X:\\1C\\NDC_1C\\docs\\ADDRESS\\runs\\2026-04-02_Address_Nightly_Regression_AfterFocusFix\\2026-04-02_Address_Nightly_stress_102_20-11-51\\run_summary.json",
|
||||
"run_id": "2026-04-02_Address_Nightly_stress_102_20-11-51",
|
||||
"questions_total": 102,
|
||||
"strict_pass_rate": 1.0,
|
||||
"route_pass_rate": 1.0,
|
||||
"execution_error_count": 0,
|
||||
"false_factual_rate": 0.0,
|
||||
"notes": [
|
||||
"execution_error_count derived as http_error_count + limited_reason_category.execution_error",
|
||||
"false_factual_rate derived from false_factual_count/questions_total"
|
||||
]
|
||||
},
|
||||
"checks": [
|
||||
{
|
||||
"metric": "strict_pass_rate",
|
||||
"passed": true,
|
||||
"baseline": 1.0,
|
||||
"candidate": 1.0,
|
||||
"rule": "candidate >= baseline"
|
||||
},
|
||||
{
|
||||
"metric": "route_pass_rate",
|
||||
"passed": true,
|
||||
"baseline": 1.0,
|
||||
"candidate": 1.0,
|
||||
"rule": "candidate >= baseline"
|
||||
},
|
||||
{
|
||||
"metric": "execution_error_count",
|
||||
"passed": true,
|
||||
"baseline": 0,
|
||||
"candidate": 0,
|
||||
"rule": "candidate <= baseline"
|
||||
},
|
||||
{
|
||||
"metric": "false_factual_rate",
|
||||
"passed": true,
|
||||
"baseline": 0.0,
|
||||
"candidate": 0.0,
|
||||
"rule": "candidate <= baseline"
|
||||
},
|
||||
{
|
||||
"metric": "questions_total_match",
|
||||
"passed": true,
|
||||
"baseline": 102,
|
||||
"candidate": 102,
|
||||
"rule": "candidate == baseline"
|
||||
}
|
||||
]
|
||||
}
|
||||
+23
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"generated_at": "2026-04-02T20:23:18",
|
||||
"total": 1,
|
||||
"passed": 1,
|
||||
"failed": 0,
|
||||
"results": [
|
||||
{
|
||||
"run_dir": "X:\\1C\\NDC_1C\\docs\\ADDRESS\\runs\\2026-04-02_Address_Nightly_Regression_AfterFocusFix\\2026-04-02_Address_Nightly_stress_102_20-11-51",
|
||||
"valid": true,
|
||||
"errors": [],
|
||||
"warnings": [],
|
||||
"metrics": {
|
||||
"run_id": "2026-04-02_Address_Nightly_stress_102_20-11-51",
|
||||
"questions_total": 102,
|
||||
"route_pass_rate": 1.0,
|
||||
"strict_pass_rate": 1.0,
|
||||
"http_error_count": 0,
|
||||
"rows_count": 102,
|
||||
"failures_count": 0
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
+28
@@ -0,0 +1,28 @@
|
||||
# 2026-04-02_Address_Nightly_stress_102_20-16-06
|
||||
|
||||
Generated at: 2026-04-02T20:27:52
|
||||
Questions file: X:\1C\NDC_1C\docs\ADDRESS\question_sets\address_slang_stress_full_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: route
|
||||
|
||||
## Totals
|
||||
- questions_total: 102
|
||||
- ok_200_count: 102
|
||||
- semantic_pass_count: 102
|
||||
- semantic_pass_rate: 1.0
|
||||
- route_pass_count: 102
|
||||
- route_pass_rate: 1.0
|
||||
- strict_pass_count: 102
|
||||
- strict_pass_rate: 1.0
|
||||
- factual_count: 96
|
||||
- partial_coverage_count: 6
|
||||
- clarification_required_count: 0
|
||||
- http_error_count: 0
|
||||
- llm_decomposition_applied_count: 81
|
||||
- avg_elapsed_ms: 6920.5
|
||||
|
||||
## Files
|
||||
- run_summary.json
|
||||
- full_live_results.json
|
||||
- failures_only.json
|
||||
+1
@@ -0,0 +1 @@
|
||||
[]
|
||||
+15394
File diff suppressed because one or more lines are too long
+106
@@ -0,0 +1,106 @@
|
||||
# Response Audit: 2026-04-02_Address_Nightly_stress_102_20-16-06
|
||||
|
||||
| id | strict | route_health | reply_type | intent | limited_reason | question | assistant_first_line |
|
||||
|---|---|---|---|---|---|---|---|
|
||||
| S001 | True | ok_or_factual | factual | list_documents_by_counterparty | None | свк доки за 2020 покаж пж | Точный якорь не подтвердился в текущем окне live-данных; показаны ближайшие доступные документы/операции по выбранному типу. |
|
||||
| S002 | True | ok_or_factual | factual | list_documents_by_counterparty | None | покеж все доки по свк за 20 год | Собран список документов по контрагенту (live address lane). |
|
||||
| S003 | True | ok_or_factual | factual | list_documents_by_counterparty | None | дай список документов по свк за 2020 | Собран список документов по контрагенту (live address lane). |
|
||||
| S004 | True | ok_or_factual | factual | list_documents_by_counterparty | None | какие у свк есть доки за 2020? | Точный якорь не подтвердился в текущем окне live-данных; показаны ближайшие доступные документы/операции по выбранному типу. |
|
||||
| S005 | True | ok_or_factual | factual | list_documents_by_counterparty | None | че по свк по докам за 2020 год | Собран список документов по контрагенту (live address lane). |
|
||||
| S006 | True | ok_or_factual | factual | list_documents_by_counterparty | None | ёпт покажи доки по свк за 2020 | Собран список документов по контрагенту (live address lane). |
|
||||
| S007 | True | ok_or_factual | factual | list_documents_by_counterparty | None | бля, доки свк 2020 вывали | Собран список документов по контрагенту (live address lane). |
|
||||
| S008 | True | ok_or_factual | factual | list_documents_by_counterparty | None | svk docs for 2020 please | Собран список документов по контрагенту (live address lane). |
|
||||
| S009 | True | ok_or_factual | factual | list_documents_by_counterparty | None | docs by counterparty svk year 2020 | Точный якорь не подтвердился в текущем окне live-данных; показаны ближайшие доступные документы/операции по выбранному типу. |
|
||||
| S010 | True | ok_or_factual | factual | list_documents_by_counterparty | None | по контрагенту свк покаж документы за 2020 | Собран список документов по контрагенту (live address lane). |
|
||||
| S011 | True | ok_or_factual | factual | list_documents_by_counterparty | None | плс доки по свк 2020 | Точный якорь не подтвердился в текущем окне live-данных; показаны ближайшие доступные документы/операции по выбранному типу. |
|
||||
| S012 | True | ok_or_factual | factual | list_documents_by_counterparty | None | свк док за 2020 гони | Собран список документов по контрагенту (live address lane). |
|
||||
| S013 | True | ok_or_factual | factual | bank_operations_by_counterparty | None | по свк банковские операции за 2020 покаж | Собран список банковских операций по контрагенту (live address lane). |
|
||||
| S014 | True | ok_or_factual | factual | bank_operations_by_counterparty | None | свк выписка банка 2020 | Собран список банковских операций по контрагенту (live address lane). |
|
||||
| S015 | True | ok_or_factual | factual | bank_operations_by_counterparty | None | платежи по свк за 2020 выведи | Собран список банковских операций по контрагенту (live address lane). |
|
||||
| S016 | True | ok_or_factual | factual | bank_operations_by_counterparty | None | оплаты по свк за 2020 | Собран список банковских операций по контрагенту (live address lane). |
|
||||
| S017 | True | ok_or_factual | factual | bank_operations_by_counterparty | None | свк банк опер за 2020 | Точный якорь не подтвердился в текущем окне live-данных; показаны ближайшие доступные документы/операции по выбранному типу. |
|
||||
| S018 | True | ok_or_factual | factual | bank_operations_by_counterparty | None | че у свк по банку за 2020 | Точный якорь не подтвердился в текущем окне live-данных; показаны ближайшие доступные документы/операции по выбранному типу. |
|
||||
| S019 | True | ok_or_factual | factual | bank_operations_by_counterparty | None | свк списания/поступления за 2020 | Точный якорь не подтвердился в текущем окне live-данных; показаны ближайшие доступные документы/операции по выбранному типу. |
|
||||
| S020 | True | ok_or_factual | factual | bank_operations_by_counterparty | None | bank ops by svk for 2020 | Собран список банковских операций по контрагенту (live address lane). |
|
||||
| S021 | True | ok_or_factual | factual | bank_operations_by_counterparty | None | transactions by counterparty svk 2020 | Собран список банковских операций по контрагенту (live address lane). |
|
||||
| S022 | True | ok_or_factual | factual | bank_operations_by_counterparty | None | бля, по свк банковские платежки 2020 | Собран список банковских операций по контрагенту (live address lane). |
|
||||
| S023 | True | ok_or_factual | factual | account_balance_snapshot | None | сальдо по счету 60.01 на дату 2020-07-31 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| S024 | True | ok_or_factual | factual | account_balance_snapshot | None | остаток по счету 60.01 на 2020.05 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| S025 | True | ok_or_factual | factual | account_balance_snapshot | None | покажи остаток по 60.01 за май 2020 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| S026 | True | ok_or_factual | factual | account_balance_snapshot | None | счет 60 остаток на май 2020 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| S027 | True | ok_or_factual | factual | account_balance_snapshot | None | баланс account 60.01 as of 2020-07-31 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| S028 | True | ok_or_factual | factual | account_balance_snapshot | None | 60.01 saldo на 31.07.2020 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| S029 | True | ok_or_factual | factual | account_balance_snapshot | None | сколько на счете 60 на конец 2020-05 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| S030 | True | partial_non_blocking | partial_coverage | account_balance_snapshot | empty_match | дай остаток 60.02 на 2020-12-31 | В live-данных по текущему фильтру записи не найдены. |
|
||||
| S031 | True | partial_non_blocking | partial_coverage | account_balance_snapshot | empty_match | епт, сальдо по счету 62.01 на 2020-12-31 | В live-данных по текущему фильтру записи не найдены. |
|
||||
| S032 | True | ok_or_factual | factual | account_balance_snapshot | None | плс остаток по счету 51 на 2020-06-30 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| S033 | True | ok_or_factual | factual | account_balance_snapshot | None | как там по счету 60.01 на 2020.07? | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| S034 | True | ok_or_factual | factual | account_balance_snapshot | None | сальдо 60 на 2020 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| S035 | True | ok_or_factual | factual | documents_forming_balance | None | какие документы формируют остаток по счету 60.01 на 2020-07-31 | Собран drilldown документов, формирующих остаток по счету на указанную дату. |
|
||||
| S036 | True | ok_or_factual | factual | documents_forming_balance | None | из чего состоит остаток по счету 60 на 2020.05 | Собран drilldown документов, формирующих остаток по счету на указанную дату. |
|
||||
| S037 | True | ok_or_factual | factual | documents_forming_balance | None | раскрой остаток 60.01 по документам на конец июля 2020 | Собран drilldown документов, формирующих остаток по счету на указанную дату. |
|
||||
| S038 | True | ok_or_factual | factual | documents_forming_balance | None | доки под остатком 60.01 на 2020-07-31 | Собран drilldown документов, формирующих остаток по счету на указанную дату. |
|
||||
| S039 | True | ok_or_factual | factual | documents_forming_balance | None | documents forming balance for account 60.01 as of 2020-07-31 | Собран drilldown документов, формирующих остаток по счету на указанную дату. |
|
||||
| S040 | True | ok_or_factual | factual | documents_forming_balance | None | бля, какие доки формируют остаток 60.01 на 2020-05-31 | Собран drilldown документов, формирующих остаток по счету на указанную дату. |
|
||||
| S041 | True | partial_non_blocking | partial_coverage | documents_forming_balance | empty_match | по счету 62.01 раскрой остаток документами на 2020-12-31 | В live-данных по текущему фильтру записи не найдены. |
|
||||
| S042 | True | ok_or_factual | factual | documents_forming_balance | None | из чего остаток по счету 51 на 2020-06-30 | Собран drilldown документов, формирующих остаток по счету на указанную дату. |
|
||||
| S043 | True | ok_or_factual | factual | list_documents_by_contract | None | покажи документы по договору 19/15 за 2020 | Период сохранен. Глубина live-выборки автоматически расширена до 1000 строк. |
|
||||
| S044 | True | ok_or_factual | factual | list_documents_by_contract | None | доки по дог. 19/15 за 2020 | Период сохранен. Глубина live-выборки автоматически расширена до 1000 строк. |
|
||||
| S045 | True | ok_or_factual | factual | list_documents_by_contract | None | какие документы по контракту 19/15 | Собран список документов по договору (live address lane). |
|
||||
| S046 | True | ok_or_factual | factual | list_documents_by_contract | None | docs by contract 19/15 year 2020 | Период сохранен. Глубина live-выборки автоматически расширена до 1000 строк. |
|
||||
| S047 | True | ok_or_factual | factual | list_documents_by_contract | None | бля, покажи по договору 19/15 доки | Собран список документов по договору (live address lane). |
|
||||
| S048 | True | ok_or_factual | factual | list_documents_by_contract | None | договор 19/15 документы | Собран список документов по договору (live address lane). |
|
||||
| S049 | True | ok_or_factual | factual | list_documents_by_contract | None | плс документы договор №19/15 | Точный якорь не подтвердился в текущем окне live-данных; показаны ближайшие доступные документы/операции по выбранному типу. |
|
||||
| S050 | True | ok_or_factual | factual | list_documents_by_contract | None | покеж документы по 19/15 | Собран список документов по договору (live address lane). |
|
||||
| S051 | True | ok_or_factual | factual | bank_operations_by_contract | None | банковские операции по договору 19/15 | Собран список банковских операций по договору (live address lane). |
|
||||
| S052 | True | ok_or_factual | factual | bank_operations_by_contract | None | платежи по договору 19/15 | Собран список банковских операций по договору (live address lane). |
|
||||
| S053 | True | ok_or_factual | factual | bank_operations_by_contract | None | выписка по договору 19/15 | Собран список банковских операций по договору (live address lane). |
|
||||
| S054 | True | ok_or_factual | factual | bank_operations_by_contract | None | bank ops by contract 19/15 | Точный якорь не подтвердился в текущем окне live-данных; показаны ближайшие доступные документы/операции по выбранному типу. |
|
||||
| S055 | True | ok_or_factual | factual | bank_operations_by_contract | None | ёпт, покажи банк операции по дог 19/15 | Собран список банковских операций по договору (live address lane). |
|
||||
| S056 | True | ok_or_factual | factual | bank_operations_by_contract | None | по контракту 19/15 платежки | Собран список банковских операций по договору (live address lane). |
|
||||
| S057 | True | ok_or_factual | factual | account_balance_snapshot | None | покажи сальдо по счету 60 за 2020 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| S058 | True | ok_or_factual | factual | account_balance_snapshot | None | а теперь только май 2020 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| S059 | True | ok_or_factual | factual | account_balance_snapshot | None | ок, теперь 2020.05 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| S060 | True | ok_or_factual | factual | account_balance_snapshot | None | теперь на 2020-07-31 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| X001 | True | ok_or_factual | factual | list_documents_by_counterparty | None | свк доки кинь за 2020 | Точный якорь не подтвердился в текущем окне live-данных; показаны ближайшие доступные документы/операции по выбранному типу. |
|
||||
| X002 | True | ok_or_factual | factual | list_documents_by_counterparty | None | по свк все документы за 20й год | Собран список документов по контрагенту (live address lane). |
|
||||
| X003 | True | ok_or_factual | factual | list_documents_by_counterparty | None | пж вывали доки контрагент свк 2020 | Собран список документов по контрагенту (live address lane). |
|
||||
| X004 | True | ok_or_factual | factual | list_documents_by_counterparty | None | svk poka docy za 2020 | Собран список документов по контрагенту (live address lane). |
|
||||
| X005 | True | ok_or_factual | factual | list_documents_by_counterparty | None | какие доки по компании свк за 2020 | Собран список документов по контрагенту (live address lane). |
|
||||
| X006 | True | ok_or_factual | factual | list_documents_by_counterparty | None | бля покаж свк документы 2020 | Точный якорь не подтвердился в текущем окне live-данных; показаны ближайшие доступные документы/операции по выбранному типу. |
|
||||
| X007 | True | ok_or_factual | factual | bank_operations_by_counterparty | None | свк банк операции за 2020 | Собран список банковских операций по контрагенту (live address lane). |
|
||||
| X008 | True | ok_or_factual | factual | bank_operations_by_counterparty | None | по свк выписку банка за 2020 выведи | Собран список банковских операций по контрагенту (live address lane). |
|
||||
| X009 | True | ok_or_factual | factual | bank_operations_by_counterparty | None | свк платежки за 2020 | Точный якорь не подтвердился в текущем окне live-данных; показаны ближайшие доступные документы/операции по выбранному типу. |
|
||||
| X010 | True | ok_or_factual | factual | bank_operations_by_counterparty | None | bank ops svk 2020 | Собран список банковских операций по контрагенту (live address lane). |
|
||||
| X011 | True | ok_or_factual | factual | bank_operations_by_counterparty | None | транзакции по свк за 2020 | Собран список банковских операций по контрагенту (live address lane). |
|
||||
| X012 | True | ok_or_factual | factual | bank_operations_by_counterparty | None | ёпт по свк че по банку 2020 | Точный якорь не подтвердился в текущем окне live-данных; показаны ближайшие доступные документы/операции по выбранному типу. |
|
||||
| X013 | True | ok_or_factual | factual | account_balance_snapshot | None | остаток по 60.01 на 2020-07-31 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| X014 | True | ok_or_factual | factual | account_balance_snapshot | None | сальдо 60.01 на 31.07.2020 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| X015 | True | ok_or_factual | factual | account_balance_snapshot | None | что на счете 60 на 2020.05 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| X016 | True | ok_or_factual | factual | account_balance_snapshot | None | дай остаток 62.01 на 2020 май | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| X017 | True | partial_non_blocking | partial_coverage | account_balance_snapshot | empty_match | saldo account 60 as of 2020-12-31 | В live-данных по текущему фильтру записи не найдены. |
|
||||
| X018 | True | ok_or_factual | factual | account_balance_snapshot | None | плиз остаток по счету 51 на 2020-06-30 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| X019 | True | partial_non_blocking | partial_coverage | account_balance_snapshot | empty_match | скока по 60.02 на конец 2020-12 | В live-данных по текущему фильтру записи не найдены. |
|
||||
| X020 | True | ok_or_factual | factual | account_balance_snapshot | None | бля сальдо 60.01 на 2020-05-31 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| X021 | True | ok_or_factual | factual | documents_forming_balance | None | раскрой остаток 60.01 по документам на конец июля 2020 | Собран drilldown документов, формирующих остаток по счету на указанную дату. |
|
||||
| X022 | True | ok_or_factual | factual | documents_forming_balance | None | доки под остатком 60.01 на 2020-07-31 | Собран drilldown документов, формирующих остаток по счету на указанную дату. |
|
||||
| X023 | True | ok_or_factual | factual | documents_forming_balance | None | из чего остаток 60.01 на 2020-07-31 | Собран drilldown документов, формирующих остаток по счету на указанную дату. |
|
||||
| X024 | True | ok_or_factual | factual | documents_forming_balance | None | какие документы формируют остаток по 60.01 на 2020-07-31 | Собран drilldown документов, формирующих остаток по счету на указанную дату. |
|
||||
| X025 | True | ok_or_factual | factual | documents_forming_balance | None | docs forming balance 60.01 as of 2020-07-31 | Собран drilldown документов, формирующих остаток по счету на указанную дату. |
|
||||
| X026 | True | partial_non_blocking | partial_coverage | documents_forming_balance | empty_match | раскидай остаток 62.01 по докам на 2020-12-31 | В live-данных по текущему фильтру записи не найдены. |
|
||||
| X027 | True | ok_or_factual | factual | documents_forming_balance | None | по счету 51 раскрой остаток документами на 2020-06-30 | Собран drilldown документов, формирующих остаток по счету на указанную дату. |
|
||||
| X028 | True | ok_or_factual | factual | documents_forming_balance | None | бля из чего состоит остаток по 60.01 на 2020-05-31 | Собран drilldown документов, формирующих остаток по счету на указанную дату. |
|
||||
| X029 | True | ok_or_factual | factual | list_documents_by_contract | None | доки по договору 19/15 за 2020 | Период сохранен. Глубина live-выборки автоматически расширена до 1000 строк. |
|
||||
| X030 | True | ok_or_factual | factual | list_documents_by_contract | None | покажи документы контракт 19/15 | Собран список документов по договору (live address lane). |
|
||||
| X031 | True | ok_or_factual | factual | list_documents_by_contract | None | docs by contract 19/15 2020 | Период сохранен. Глубина live-выборки автоматически расширена до 1000 строк. |
|
||||
| X032 | True | ok_or_factual | factual | list_documents_by_contract | None | по дог 19/15 какие документы | Собран список документов по договору (live address lane). |
|
||||
| X033 | True | ok_or_factual | factual | list_documents_by_contract | None | договор 19/15 выведи доки | Точный якорь не подтвердился в текущем окне live-данных; показаны ближайшие доступные документы/операции по выбранному типу. |
|
||||
| X034 | True | ok_or_factual | factual | list_documents_by_contract | None | нах покажи документы по 19/15 | Собран список документов по договору (live address lane). |
|
||||
| X035 | True | ok_or_factual | factual | bank_operations_by_contract | None | банк операции по договору 19/15 | Собран список банковских операций по договору (live address lane). |
|
||||
| X036 | True | ok_or_factual | factual | bank_operations_by_contract | None | платежки по дог 19/15 | Собран список банковских операций по договору (live address lane). |
|
||||
| X037 | True | ok_or_factual | factual | bank_operations_by_contract | None | выписка по контракту 19/15 | Собран список банковских операций по договору (live address lane). |
|
||||
| X038 | True | ok_or_factual | factual | bank_operations_by_contract | None | bank ops by contract 19/15 | Точный якорь не подтвердился в текущем окне live-данных; показаны ближайшие доступные документы/операции по выбранному типу. |
|
||||
| X039 | True | ok_or_factual | factual | bank_operations_by_contract | None | покажи банк опер по дог 19/15 пж | Собран список банковских операций по договору (live address lane). |
|
||||
| X040 | True | ok_or_factual | factual | bank_operations_by_contract | None | епт транзакции договор 19/15 | Собран список банковских операций по договору (live address lane). |
|
||||
| X041 | True | ok_or_factual | factual | account_balance_snapshot | None | покажи сальдо по счету 60 за 2020 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
| X042 | True | ok_or_factual | factual | account_balance_snapshot | None | а теперь только май 2020 | Адресный срез по счету собран (по движениям live MCP). |
|
||||
+54
@@ -0,0 +1,54 @@
|
||||
{
|
||||
"run_id": "2026-04-02_Address_Nightly_stress_102_20-16-06",
|
||||
"generated_at": "2026-04-02T20:27:52",
|
||||
"source_questions_file": "X:\\1C\\NDC_1C\\docs\\ADDRESS\\question_sets\\address_slang_stress_full_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": "route",
|
||||
"totals": {
|
||||
"questions_total": 102,
|
||||
"ok_200_count": 102,
|
||||
"semantic_pass_count": 102,
|
||||
"semantic_pass_rate": 1.0,
|
||||
"route_pass_count": 102,
|
||||
"route_pass_rate": 1.0,
|
||||
"strict_pass_count": 102,
|
||||
"strict_pass_rate": 1.0,
|
||||
"factual_count": 96,
|
||||
"partial_coverage_count": 6,
|
||||
"clarification_required_count": 0,
|
||||
"http_error_count": 0,
|
||||
"llm_decomposition_applied_count": 81,
|
||||
"avg_elapsed_ms": 6920.5
|
||||
},
|
||||
"distributions": {
|
||||
"reply_type": {
|
||||
"factual": 96,
|
||||
"partial_coverage": 6
|
||||
},
|
||||
"actual_intent": {
|
||||
"list_documents_by_counterparty": 18,
|
||||
"bank_operations_by_counterparty": 16,
|
||||
"account_balance_snapshot": 26,
|
||||
"documents_forming_balance": 16,
|
||||
"list_documents_by_contract": 14,
|
||||
"bank_operations_by_contract": 12
|
||||
},
|
||||
"actual_mode": {
|
||||
"address_query": 102
|
||||
},
|
||||
"mcp_call_status": {
|
||||
"matched_non_empty": 96,
|
||||
"no_raw_rows": 6
|
||||
},
|
||||
"limited_reason_category": {
|
||||
"empty_match": 6
|
||||
},
|
||||
"route_health": {
|
||||
"ok_or_factual": 96,
|
||||
"partial_non_blocking": 6
|
||||
}
|
||||
}
|
||||
}
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user