ГЛОБАЛЬНЫЙ РЕФАКТОРИНГ АРХИТЕКТУРЫ - Рефакторинг этапов 2.2 - Усилена оркестрацию в deep/address гейте и follow-up binding в assistantService.ts. Починен кейс UTF-8 follow-up refinement (теперь followup_state_usage.applied=true в нужном сценарии). Убраны регрессии по assistantLivingRouter и stage3 lifecycle probe. Корректное поведение для llm canonical candidate (чтобы не уезжало в clarification_required там, где должен быть address factual).

This commit is contained in:
2026-04-11 14:56:14 +03:00
parent 19f5f19d8e
commit b5bd4fd737
46 changed files with 2471 additions and 370 deletions
@@ -0,0 +1,112 @@
{
"run_id": "eval-5S6BYeWJWv",
"timestamp": "2026-04-11T10:38:19.513Z",
"mode": "single-pass-strict",
"use_mock": true,
"prompt_version": "normalizer_v2_0_2",
"schema_version": "v2_0_2",
"dataset": {
"source": "inline_raw_questions",
"file": null,
"raw_questions_count": 2
},
"cases_total": 2,
"metrics": {
"schema_validation_pass_rate": 100,
"scope_detection_accuracy": null,
"scope_in_scope_rate": 100,
"multi_intent_detected_rate": 0,
"clarification_required_rate": 0,
"avg_fragments_per_message": 1,
"out_of_scope_fragment_rate": 0,
"routed_fragment_rate": 100,
"no_route_fragment_rate": 0,
"route_resolution_accuracy": null,
"no_route_precision": null,
"false_no_route_rate": null,
"execution_state_consistency_rate": 100,
"executable_with_soft_assumptions_rate": 100,
"soft_assumption_used_fragment_rate": 100,
"clarification_precision": null,
"clarification_recall": null,
"false_clarification_rate": null
},
"budget": {
"requests_total": 0,
"retries_used": 0
},
"clarification_eval": {
"labeled_cases": 0,
"true_positive": 0,
"false_positive": 0,
"false_negative": 0
},
"route_eval": {
"labeled_cases": 0,
"correct_cases": 0,
"expected_routed_cases": 0,
"no_route_true_positive": 0,
"no_route_false_positive": 0
},
"scope_eval": {
"labeled_cases": 0,
"correct_cases": 0
},
"execution_state_eval": {
"checks_total": 2,
"checks_passed": 2
},
"route_distribution": {
"store_feature_risk": 1,
"hybrid_store_plus_live": 1
},
"fallback_distribution": {
"none": 2
},
"results": [
{
"case_id": "BQ-001",
"raw_question": "Проверь счет 60 за июнь 2020",
"validation_passed": true,
"message_in_scope": true,
"scope_confidence": "high",
"contains_multiple_tasks": false,
"fragments_total": 1,
"in_scope_fragments": 1,
"out_of_scope_fragments": 0,
"unclear_fragments": 0,
"fallback_type": "none",
"predicted_route_status": "routed",
"expected_route_status": null,
"predicted_no_route_reason": null,
"expected_no_route_reason": null,
"predicted_clarification_required": false,
"expected_clarification_required": null,
"executable_with_soft_assumptions_fragments": 1,
"trace_id": "bi53megxPkVDpq",
"request_count_for_case": 0
},
{
"case_id": "BQ-002",
"raw_question": "Покажи риски по НДС и по закрытию",
"validation_passed": true,
"message_in_scope": true,
"scope_confidence": "high",
"contains_multiple_tasks": false,
"fragments_total": 1,
"in_scope_fragments": 1,
"out_of_scope_fragments": 0,
"unclear_fragments": 0,
"fallback_type": "none",
"predicted_route_status": "routed",
"expected_route_status": null,
"predicted_no_route_reason": null,
"expected_no_route_reason": null,
"predicted_clarification_required": false,
"expected_clarification_required": null,
"executable_with_soft_assumptions_fragments": 1,
"trace_id": "ew725J5aRLs1XU",
"request_count_for_case": 0
}
]
}
@@ -0,0 +1,112 @@
{
"run_id": "eval-D1gt1OyBqh",
"timestamp": "2026-04-11T10:35:37.557Z",
"mode": "single-pass-strict",
"use_mock": true,
"prompt_version": "normalizer_v2_0_2",
"schema_version": "v2_0_2",
"dataset": {
"source": "inline_raw_questions",
"file": null,
"raw_questions_count": 2
},
"cases_total": 2,
"metrics": {
"schema_validation_pass_rate": 100,
"scope_detection_accuracy": null,
"scope_in_scope_rate": 100,
"multi_intent_detected_rate": 0,
"clarification_required_rate": 0,
"avg_fragments_per_message": 1,
"out_of_scope_fragment_rate": 0,
"routed_fragment_rate": 100,
"no_route_fragment_rate": 0,
"route_resolution_accuracy": null,
"no_route_precision": null,
"false_no_route_rate": null,
"execution_state_consistency_rate": 100,
"executable_with_soft_assumptions_rate": 100,
"soft_assumption_used_fragment_rate": 100,
"clarification_precision": null,
"clarification_recall": null,
"false_clarification_rate": null
},
"budget": {
"requests_total": 0,
"retries_used": 0
},
"clarification_eval": {
"labeled_cases": 0,
"true_positive": 0,
"false_positive": 0,
"false_negative": 0
},
"route_eval": {
"labeled_cases": 0,
"correct_cases": 0,
"expected_routed_cases": 0,
"no_route_true_positive": 0,
"no_route_false_positive": 0
},
"scope_eval": {
"labeled_cases": 0,
"correct_cases": 0
},
"execution_state_eval": {
"checks_total": 2,
"checks_passed": 2
},
"route_distribution": {
"store_feature_risk": 1,
"hybrid_store_plus_live": 1
},
"fallback_distribution": {
"none": 2
},
"results": [
{
"case_id": "BQ-001",
"raw_question": "Проверь счет 60 за июнь 2020",
"validation_passed": true,
"message_in_scope": true,
"scope_confidence": "high",
"contains_multiple_tasks": false,
"fragments_total": 1,
"in_scope_fragments": 1,
"out_of_scope_fragments": 0,
"unclear_fragments": 0,
"fallback_type": "none",
"predicted_route_status": "routed",
"expected_route_status": null,
"predicted_no_route_reason": null,
"expected_no_route_reason": null,
"predicted_clarification_required": false,
"expected_clarification_required": null,
"executable_with_soft_assumptions_fragments": 1,
"trace_id": "0XdpLLt2DVEC8b",
"request_count_for_case": 0
},
{
"case_id": "BQ-002",
"raw_question": "Покажи риски по НДС и по закрытию",
"validation_passed": true,
"message_in_scope": true,
"scope_confidence": "high",
"contains_multiple_tasks": false,
"fragments_total": 1,
"in_scope_fragments": 1,
"out_of_scope_fragments": 0,
"unclear_fragments": 0,
"fallback_type": "none",
"predicted_route_status": "routed",
"expected_route_status": null,
"predicted_no_route_reason": null,
"expected_no_route_reason": null,
"predicted_clarification_required": false,
"expected_clarification_required": null,
"executable_with_soft_assumptions_fragments": 1,
"trace_id": "TGXTmJEIbfRfxl",
"request_count_for_case": 0
}
]
}
@@ -0,0 +1,137 @@
{
"run_id": "eval-EYDYh4k78m",
"timestamp": "2026-04-11T10:35:23.070Z",
"mode": "single-pass-strict",
"use_mock": true,
"prompt_version": "normalizer_v2_0_2",
"schema_version": "v2_0_2",
"dataset": {
"source": "inline_raw_questions",
"file": null,
"raw_questions_count": 3
},
"cases_total": 3,
"metrics": {
"schema_validation_pass_rate": 100,
"scope_detection_accuracy": null,
"scope_in_scope_rate": 33.33,
"multi_intent_detected_rate": 0,
"clarification_required_rate": 0,
"avg_fragments_per_message": 1,
"out_of_scope_fragment_rate": 33.33,
"routed_fragment_rate": 66.67,
"no_route_fragment_rate": 33.33,
"route_resolution_accuracy": null,
"no_route_precision": null,
"false_no_route_rate": null,
"execution_state_consistency_rate": 66.67,
"executable_with_soft_assumptions_rate": 100,
"soft_assumption_used_fragment_rate": 100,
"clarification_precision": null,
"clarification_recall": null,
"false_clarification_rate": null
},
"budget": {
"requests_total": 0,
"retries_used": 0
},
"clarification_eval": {
"labeled_cases": 0,
"true_positive": 0,
"false_positive": 0,
"false_negative": 0
},
"route_eval": {
"labeled_cases": 0,
"correct_cases": 0,
"expected_routed_cases": 0,
"no_route_true_positive": 0,
"no_route_false_positive": 0
},
"scope_eval": {
"labeled_cases": 0,
"correct_cases": 0
},
"execution_state_eval": {
"checks_total": 3,
"checks_passed": 2
},
"route_distribution": {
"hybrid_store_plus_live": 1,
"no_route": 1,
"batch_refresh_then_store": 1
},
"fallback_distribution": {
"none": 1,
"out_of_scope": 1,
"clarification": 1
},
"results": [
{
"case_id": "BQ-001",
"raw_question": "Проверь хвосты по поставщикам и разложи цепочку",
"validation_passed": true,
"message_in_scope": true,
"scope_confidence": "high",
"contains_multiple_tasks": false,
"fragments_total": 1,
"in_scope_fragments": 1,
"out_of_scope_fragments": 0,
"unclear_fragments": 0,
"fallback_type": "none",
"predicted_route_status": "routed",
"expected_route_status": null,
"predicted_no_route_reason": null,
"expected_no_route_reason": null,
"predicted_clarification_required": false,
"expected_clarification_required": null,
"executable_with_soft_assumptions_fragments": 1,
"trace_id": "XkM4LP-bXu4rf9",
"request_count_for_case": 0
},
{
"case_id": "BQ-002",
"raw_question": "Как вообще по ФСБУ",
"validation_passed": true,
"message_in_scope": false,
"scope_confidence": "low",
"contains_multiple_tasks": false,
"fragments_total": 1,
"in_scope_fragments": 0,
"out_of_scope_fragments": 1,
"unclear_fragments": 0,
"fallback_type": "out_of_scope",
"predicted_route_status": "no_route",
"expected_route_status": null,
"predicted_no_route_reason": "out_of_scope",
"expected_no_route_reason": null,
"predicted_clarification_required": false,
"expected_clarification_required": null,
"executable_with_soft_assumptions_fragments": 0,
"trace_id": "eDF6_4JOsguyhk",
"request_count_for_case": 0
},
{
"case_id": "BQ-003",
"raw_question": "Покажи топ рисков за июнь 2020",
"validation_passed": true,
"message_in_scope": false,
"scope_confidence": "low",
"contains_multiple_tasks": false,
"fragments_total": 1,
"in_scope_fragments": 0,
"out_of_scope_fragments": 0,
"unclear_fragments": 1,
"fallback_type": "clarification",
"predicted_route_status": "routed",
"expected_route_status": null,
"predicted_no_route_reason": null,
"expected_no_route_reason": null,
"predicted_clarification_required": false,
"expected_clarification_required": null,
"executable_with_soft_assumptions_fragments": 0,
"trace_id": "dsCVkLkLYqwqHr",
"request_count_for_case": 0
}
]
}
@@ -0,0 +1,112 @@
{
"run_id": "eval-NeqPDTflc7",
"timestamp": "2026-04-11T10:16:53.909Z",
"mode": "single-pass-strict",
"use_mock": true,
"prompt_version": "normalizer_v2_0_2",
"schema_version": "v2_0_2",
"dataset": {
"source": "inline_raw_questions",
"file": null,
"raw_questions_count": 2
},
"cases_total": 2,
"metrics": {
"schema_validation_pass_rate": 100,
"scope_detection_accuracy": null,
"scope_in_scope_rate": 100,
"multi_intent_detected_rate": 0,
"clarification_required_rate": 0,
"avg_fragments_per_message": 1,
"out_of_scope_fragment_rate": 0,
"routed_fragment_rate": 100,
"no_route_fragment_rate": 0,
"route_resolution_accuracy": null,
"no_route_precision": null,
"false_no_route_rate": null,
"execution_state_consistency_rate": 100,
"executable_with_soft_assumptions_rate": 100,
"soft_assumption_used_fragment_rate": 100,
"clarification_precision": null,
"clarification_recall": null,
"false_clarification_rate": null
},
"budget": {
"requests_total": 0,
"retries_used": 0
},
"clarification_eval": {
"labeled_cases": 0,
"true_positive": 0,
"false_positive": 0,
"false_negative": 0
},
"route_eval": {
"labeled_cases": 0,
"correct_cases": 0,
"expected_routed_cases": 0,
"no_route_true_positive": 0,
"no_route_false_positive": 0
},
"scope_eval": {
"labeled_cases": 0,
"correct_cases": 0
},
"execution_state_eval": {
"checks_total": 2,
"checks_passed": 2
},
"route_distribution": {
"store_feature_risk": 1,
"hybrid_store_plus_live": 1
},
"fallback_distribution": {
"none": 2
},
"results": [
{
"case_id": "BQ-001",
"raw_question": "Проверь счет 60 за июнь 2020",
"validation_passed": true,
"message_in_scope": true,
"scope_confidence": "high",
"contains_multiple_tasks": false,
"fragments_total": 1,
"in_scope_fragments": 1,
"out_of_scope_fragments": 0,
"unclear_fragments": 0,
"fallback_type": "none",
"predicted_route_status": "routed",
"expected_route_status": null,
"predicted_no_route_reason": null,
"expected_no_route_reason": null,
"predicted_clarification_required": false,
"expected_clarification_required": null,
"executable_with_soft_assumptions_fragments": 1,
"trace_id": "ynDJfmhtaBS6Jh",
"request_count_for_case": 0
},
{
"case_id": "BQ-002",
"raw_question": "Покажи риски по счету 97",
"validation_passed": true,
"message_in_scope": true,
"scope_confidence": "high",
"contains_multiple_tasks": false,
"fragments_total": 1,
"in_scope_fragments": 1,
"out_of_scope_fragments": 0,
"unclear_fragments": 0,
"fallback_type": "none",
"predicted_route_status": "routed",
"expected_route_status": null,
"predicted_no_route_reason": null,
"expected_no_route_reason": null,
"predicted_clarification_required": false,
"expected_clarification_required": null,
"executable_with_soft_assumptions_fragments": 1,
"trace_id": "BhT9NfO-40oigp",
"request_count_for_case": 0
}
]
}
@@ -0,0 +1,137 @@
{
"run_id": "eval-OSNnoiu9KQ",
"timestamp": "2026-04-11T10:16:34.741Z",
"mode": "single-pass-strict",
"use_mock": true,
"prompt_version": "normalizer_v2_0_2",
"schema_version": "v2_0_2",
"dataset": {
"source": "inline_raw_questions",
"file": null,
"raw_questions_count": 3
},
"cases_total": 3,
"metrics": {
"schema_validation_pass_rate": 100,
"scope_detection_accuracy": null,
"scope_in_scope_rate": 33.33,
"multi_intent_detected_rate": 0,
"clarification_required_rate": 0,
"avg_fragments_per_message": 1,
"out_of_scope_fragment_rate": 33.33,
"routed_fragment_rate": 66.67,
"no_route_fragment_rate": 33.33,
"route_resolution_accuracy": null,
"no_route_precision": null,
"false_no_route_rate": null,
"execution_state_consistency_rate": 66.67,
"executable_with_soft_assumptions_rate": 100,
"soft_assumption_used_fragment_rate": 100,
"clarification_precision": null,
"clarification_recall": null,
"false_clarification_rate": null
},
"budget": {
"requests_total": 0,
"retries_used": 0
},
"clarification_eval": {
"labeled_cases": 0,
"true_positive": 0,
"false_positive": 0,
"false_negative": 0
},
"route_eval": {
"labeled_cases": 0,
"correct_cases": 0,
"expected_routed_cases": 0,
"no_route_true_positive": 0,
"no_route_false_positive": 0
},
"scope_eval": {
"labeled_cases": 0,
"correct_cases": 0
},
"execution_state_eval": {
"checks_total": 3,
"checks_passed": 2
},
"route_distribution": {
"hybrid_store_plus_live": 1,
"no_route": 1,
"batch_refresh_then_store": 1
},
"fallback_distribution": {
"none": 1,
"out_of_scope": 1,
"clarification": 1
},
"results": [
{
"case_id": "BQ-001",
"raw_question": "Проверь хвосты по поставщикам и разложи цепочку",
"validation_passed": true,
"message_in_scope": true,
"scope_confidence": "high",
"contains_multiple_tasks": false,
"fragments_total": 1,
"in_scope_fragments": 1,
"out_of_scope_fragments": 0,
"unclear_fragments": 0,
"fallback_type": "none",
"predicted_route_status": "routed",
"expected_route_status": null,
"predicted_no_route_reason": null,
"expected_no_route_reason": null,
"predicted_clarification_required": false,
"expected_clarification_required": null,
"executable_with_soft_assumptions_fragments": 1,
"trace_id": "YPmWhiLGA674vn",
"request_count_for_case": 0
},
{
"case_id": "BQ-002",
"raw_question": "Как вообще по ФСБУ",
"validation_passed": true,
"message_in_scope": false,
"scope_confidence": "low",
"contains_multiple_tasks": false,
"fragments_total": 1,
"in_scope_fragments": 0,
"out_of_scope_fragments": 1,
"unclear_fragments": 0,
"fallback_type": "out_of_scope",
"predicted_route_status": "no_route",
"expected_route_status": null,
"predicted_no_route_reason": "out_of_scope",
"expected_no_route_reason": null,
"predicted_clarification_required": false,
"expected_clarification_required": null,
"executable_with_soft_assumptions_fragments": 0,
"trace_id": "JAbihOWvYs9bYR",
"request_count_for_case": 0
},
{
"case_id": "BQ-003",
"raw_question": "Покажи топ рисков за июнь 2020",
"validation_passed": true,
"message_in_scope": false,
"scope_confidence": "low",
"contains_multiple_tasks": false,
"fragments_total": 1,
"in_scope_fragments": 0,
"out_of_scope_fragments": 0,
"unclear_fragments": 1,
"fallback_type": "clarification",
"predicted_route_status": "routed",
"expected_route_status": null,
"predicted_no_route_reason": null,
"expected_no_route_reason": null,
"predicted_clarification_required": false,
"expected_clarification_required": null,
"executable_with_soft_assumptions_fragments": 0,
"trace_id": "WuI3XbextvaDxw",
"request_count_for_case": 0
}
]
}
@@ -0,0 +1,112 @@
{
"run_id": "eval-RVeDpGREWm",
"timestamp": "2026-04-11T10:14:44.794Z",
"mode": "single-pass-strict",
"use_mock": true,
"prompt_version": "normalizer_v2_0_2",
"schema_version": "v2_0_2",
"dataset": {
"source": "inline_raw_questions",
"file": null,
"raw_questions_count": 2
},
"cases_total": 2,
"metrics": {
"schema_validation_pass_rate": 100,
"scope_detection_accuracy": null,
"scope_in_scope_rate": 100,
"multi_intent_detected_rate": 0,
"clarification_required_rate": 0,
"avg_fragments_per_message": 1,
"out_of_scope_fragment_rate": 0,
"routed_fragment_rate": 100,
"no_route_fragment_rate": 0,
"route_resolution_accuracy": null,
"no_route_precision": null,
"false_no_route_rate": null,
"execution_state_consistency_rate": 100,
"executable_with_soft_assumptions_rate": 100,
"soft_assumption_used_fragment_rate": 100,
"clarification_precision": null,
"clarification_recall": null,
"false_clarification_rate": null
},
"budget": {
"requests_total": 0,
"retries_used": 0
},
"clarification_eval": {
"labeled_cases": 0,
"true_positive": 0,
"false_positive": 0,
"false_negative": 0
},
"route_eval": {
"labeled_cases": 0,
"correct_cases": 0,
"expected_routed_cases": 0,
"no_route_true_positive": 0,
"no_route_false_positive": 0
},
"scope_eval": {
"labeled_cases": 0,
"correct_cases": 0
},
"execution_state_eval": {
"checks_total": 2,
"checks_passed": 2
},
"route_distribution": {
"store_feature_risk": 1,
"hybrid_store_plus_live": 1
},
"fallback_distribution": {
"none": 2
},
"results": [
{
"case_id": "BQ-001",
"raw_question": "Проверь счет 60 за июнь 2020",
"validation_passed": true,
"message_in_scope": true,
"scope_confidence": "high",
"contains_multiple_tasks": false,
"fragments_total": 1,
"in_scope_fragments": 1,
"out_of_scope_fragments": 0,
"unclear_fragments": 0,
"fallback_type": "none",
"predicted_route_status": "routed",
"expected_route_status": null,
"predicted_no_route_reason": null,
"expected_no_route_reason": null,
"predicted_clarification_required": false,
"expected_clarification_required": null,
"executable_with_soft_assumptions_fragments": 1,
"trace_id": "9WDoQo0uvKHsFh",
"request_count_for_case": 0
},
{
"case_id": "BQ-002",
"raw_question": "Покажи риски по НДС и по закрытию",
"validation_passed": true,
"message_in_scope": true,
"scope_confidence": "high",
"contains_multiple_tasks": false,
"fragments_total": 1,
"in_scope_fragments": 1,
"out_of_scope_fragments": 0,
"unclear_fragments": 0,
"fallback_type": "none",
"predicted_route_status": "routed",
"expected_route_status": null,
"predicted_no_route_reason": null,
"expected_no_route_reason": null,
"predicted_clarification_required": false,
"expected_clarification_required": null,
"executable_with_soft_assumptions_fragments": 1,
"trace_id": "YJ7f6z9_SS7ZgW",
"request_count_for_case": 0
}
]
}
@@ -0,0 +1,137 @@
{
"run_id": "eval-hhXvDmFzGJ",
"timestamp": "2026-04-11T10:14:25.501Z",
"mode": "single-pass-strict",
"use_mock": true,
"prompt_version": "normalizer_v2_0_2",
"schema_version": "v2_0_2",
"dataset": {
"source": "inline_raw_questions",
"file": null,
"raw_questions_count": 3
},
"cases_total": 3,
"metrics": {
"schema_validation_pass_rate": 100,
"scope_detection_accuracy": null,
"scope_in_scope_rate": 33.33,
"multi_intent_detected_rate": 0,
"clarification_required_rate": 0,
"avg_fragments_per_message": 1,
"out_of_scope_fragment_rate": 33.33,
"routed_fragment_rate": 66.67,
"no_route_fragment_rate": 33.33,
"route_resolution_accuracy": null,
"no_route_precision": null,
"false_no_route_rate": null,
"execution_state_consistency_rate": 66.67,
"executable_with_soft_assumptions_rate": 100,
"soft_assumption_used_fragment_rate": 100,
"clarification_precision": null,
"clarification_recall": null,
"false_clarification_rate": null
},
"budget": {
"requests_total": 0,
"retries_used": 0
},
"clarification_eval": {
"labeled_cases": 0,
"true_positive": 0,
"false_positive": 0,
"false_negative": 0
},
"route_eval": {
"labeled_cases": 0,
"correct_cases": 0,
"expected_routed_cases": 0,
"no_route_true_positive": 0,
"no_route_false_positive": 0
},
"scope_eval": {
"labeled_cases": 0,
"correct_cases": 0
},
"execution_state_eval": {
"checks_total": 3,
"checks_passed": 2
},
"route_distribution": {
"hybrid_store_plus_live": 1,
"no_route": 1,
"batch_refresh_then_store": 1
},
"fallback_distribution": {
"none": 1,
"out_of_scope": 1,
"clarification": 1
},
"results": [
{
"case_id": "BQ-001",
"raw_question": "Проверь хвосты по поставщикам и разложи цепочку",
"validation_passed": true,
"message_in_scope": true,
"scope_confidence": "high",
"contains_multiple_tasks": false,
"fragments_total": 1,
"in_scope_fragments": 1,
"out_of_scope_fragments": 0,
"unclear_fragments": 0,
"fallback_type": "none",
"predicted_route_status": "routed",
"expected_route_status": null,
"predicted_no_route_reason": null,
"expected_no_route_reason": null,
"predicted_clarification_required": false,
"expected_clarification_required": null,
"executable_with_soft_assumptions_fragments": 1,
"trace_id": "5-MShsMwdLMm1O",
"request_count_for_case": 0
},
{
"case_id": "BQ-002",
"raw_question": "Как вообще по ФСБУ",
"validation_passed": true,
"message_in_scope": false,
"scope_confidence": "low",
"contains_multiple_tasks": false,
"fragments_total": 1,
"in_scope_fragments": 0,
"out_of_scope_fragments": 1,
"unclear_fragments": 0,
"fallback_type": "out_of_scope",
"predicted_route_status": "no_route",
"expected_route_status": null,
"predicted_no_route_reason": "out_of_scope",
"expected_no_route_reason": null,
"predicted_clarification_required": false,
"expected_clarification_required": null,
"executable_with_soft_assumptions_fragments": 0,
"trace_id": "pv-o-6Cock8Ve2",
"request_count_for_case": 0
},
{
"case_id": "BQ-003",
"raw_question": "Покажи топ рисков за июнь 2020",
"validation_passed": true,
"message_in_scope": false,
"scope_confidence": "low",
"contains_multiple_tasks": false,
"fragments_total": 1,
"in_scope_fragments": 0,
"out_of_scope_fragments": 0,
"unclear_fragments": 1,
"fallback_type": "clarification",
"predicted_route_status": "routed",
"expected_route_status": null,
"predicted_no_route_reason": null,
"expected_no_route_reason": null,
"predicted_clarification_required": false,
"expected_clarification_required": null,
"executable_with_soft_assumptions_fragments": 0,
"trace_id": "K0zAFkzMAu2BqF",
"request_count_for_case": 0
}
]
}
@@ -0,0 +1,112 @@
{
"run_id": "eval-kBTYkPR4wq",
"timestamp": "2026-04-11T10:16:53.895Z",
"mode": "single-pass-strict",
"use_mock": true,
"prompt_version": "normalizer_v2_0_2",
"schema_version": "v2_0_2",
"dataset": {
"source": "inline_raw_questions",
"file": null,
"raw_questions_count": 2
},
"cases_total": 2,
"metrics": {
"schema_validation_pass_rate": 100,
"scope_detection_accuracy": null,
"scope_in_scope_rate": 100,
"multi_intent_detected_rate": 0,
"clarification_required_rate": 0,
"avg_fragments_per_message": 1,
"out_of_scope_fragment_rate": 0,
"routed_fragment_rate": 100,
"no_route_fragment_rate": 0,
"route_resolution_accuracy": null,
"no_route_precision": null,
"false_no_route_rate": null,
"execution_state_consistency_rate": 100,
"executable_with_soft_assumptions_rate": 100,
"soft_assumption_used_fragment_rate": 100,
"clarification_precision": null,
"clarification_recall": null,
"false_clarification_rate": null
},
"budget": {
"requests_total": 0,
"retries_used": 0
},
"clarification_eval": {
"labeled_cases": 0,
"true_positive": 0,
"false_positive": 0,
"false_negative": 0
},
"route_eval": {
"labeled_cases": 0,
"correct_cases": 0,
"expected_routed_cases": 0,
"no_route_true_positive": 0,
"no_route_false_positive": 0
},
"scope_eval": {
"labeled_cases": 0,
"correct_cases": 0
},
"execution_state_eval": {
"checks_total": 2,
"checks_passed": 2
},
"route_distribution": {
"store_feature_risk": 1,
"hybrid_store_plus_live": 1
},
"fallback_distribution": {
"none": 2
},
"results": [
{
"case_id": "BQ-001",
"raw_question": "Проверь счет 60 за июнь 2020",
"validation_passed": true,
"message_in_scope": true,
"scope_confidence": "high",
"contains_multiple_tasks": false,
"fragments_total": 1,
"in_scope_fragments": 1,
"out_of_scope_fragments": 0,
"unclear_fragments": 0,
"fallback_type": "none",
"predicted_route_status": "routed",
"expected_route_status": null,
"predicted_no_route_reason": null,
"expected_no_route_reason": null,
"predicted_clarification_required": false,
"expected_clarification_required": null,
"executable_with_soft_assumptions_fragments": 1,
"trace_id": "ZQ4J6HgngY7JB4",
"request_count_for_case": 0
},
{
"case_id": "BQ-002",
"raw_question": "Покажи риски по НДС и по закрытию",
"validation_passed": true,
"message_in_scope": true,
"scope_confidence": "high",
"contains_multiple_tasks": false,
"fragments_total": 1,
"in_scope_fragments": 1,
"out_of_scope_fragments": 0,
"unclear_fragments": 0,
"fallback_type": "none",
"predicted_route_status": "routed",
"expected_route_status": null,
"predicted_no_route_reason": null,
"expected_no_route_reason": null,
"predicted_clarification_required": false,
"expected_clarification_required": null,
"executable_with_soft_assumptions_fragments": 1,
"trace_id": "Vk2rIlI-UGAuAE",
"request_count_for_case": 0
}
]
}
@@ -0,0 +1,112 @@
{
"run_id": "eval-nL2h6Z0kKG",
"timestamp": "2026-04-11T10:35:37.559Z",
"mode": "single-pass-strict",
"use_mock": true,
"prompt_version": "normalizer_v2_0_2",
"schema_version": "v2_0_2",
"dataset": {
"source": "inline_raw_questions",
"file": null,
"raw_questions_count": 2
},
"cases_total": 2,
"metrics": {
"schema_validation_pass_rate": 100,
"scope_detection_accuracy": null,
"scope_in_scope_rate": 100,
"multi_intent_detected_rate": 0,
"clarification_required_rate": 0,
"avg_fragments_per_message": 1,
"out_of_scope_fragment_rate": 0,
"routed_fragment_rate": 100,
"no_route_fragment_rate": 0,
"route_resolution_accuracy": null,
"no_route_precision": null,
"false_no_route_rate": null,
"execution_state_consistency_rate": 100,
"executable_with_soft_assumptions_rate": 100,
"soft_assumption_used_fragment_rate": 100,
"clarification_precision": null,
"clarification_recall": null,
"false_clarification_rate": null
},
"budget": {
"requests_total": 0,
"retries_used": 0
},
"clarification_eval": {
"labeled_cases": 0,
"true_positive": 0,
"false_positive": 0,
"false_negative": 0
},
"route_eval": {
"labeled_cases": 0,
"correct_cases": 0,
"expected_routed_cases": 0,
"no_route_true_positive": 0,
"no_route_false_positive": 0
},
"scope_eval": {
"labeled_cases": 0,
"correct_cases": 0
},
"execution_state_eval": {
"checks_total": 2,
"checks_passed": 2
},
"route_distribution": {
"store_feature_risk": 1,
"hybrid_store_plus_live": 1
},
"fallback_distribution": {
"none": 2
},
"results": [
{
"case_id": "BQ-001",
"raw_question": "Проверь счет 60 за июнь 2020",
"validation_passed": true,
"message_in_scope": true,
"scope_confidence": "high",
"contains_multiple_tasks": false,
"fragments_total": 1,
"in_scope_fragments": 1,
"out_of_scope_fragments": 0,
"unclear_fragments": 0,
"fallback_type": "none",
"predicted_route_status": "routed",
"expected_route_status": null,
"predicted_no_route_reason": null,
"expected_no_route_reason": null,
"predicted_clarification_required": false,
"expected_clarification_required": null,
"executable_with_soft_assumptions_fragments": 1,
"trace_id": "gKYkJDhEWkCQTw",
"request_count_for_case": 0
},
{
"case_id": "BQ-002",
"raw_question": "Покажи риски по счету 97",
"validation_passed": true,
"message_in_scope": true,
"scope_confidence": "high",
"contains_multiple_tasks": false,
"fragments_total": 1,
"in_scope_fragments": 1,
"out_of_scope_fragments": 0,
"unclear_fragments": 0,
"fallback_type": "none",
"predicted_route_status": "routed",
"expected_route_status": null,
"predicted_no_route_reason": null,
"expected_no_route_reason": null,
"predicted_clarification_required": false,
"expected_clarification_required": null,
"executable_with_soft_assumptions_fragments": 1,
"trace_id": "YDK8VaP88Tx8dy",
"request_count_for_case": 0
}
]
}
@@ -0,0 +1,112 @@
{
"run_id": "eval-qYzl2S0IV9",
"timestamp": "2026-04-11T10:37:58.754Z",
"mode": "single-pass-strict",
"use_mock": true,
"prompt_version": "normalizer_v2_0_2",
"schema_version": "v2_0_2",
"dataset": {
"source": "inline_raw_questions",
"file": null,
"raw_questions_count": 2
},
"cases_total": 2,
"metrics": {
"schema_validation_pass_rate": 100,
"scope_detection_accuracy": null,
"scope_in_scope_rate": 100,
"multi_intent_detected_rate": 0,
"clarification_required_rate": 0,
"avg_fragments_per_message": 1,
"out_of_scope_fragment_rate": 0,
"routed_fragment_rate": 100,
"no_route_fragment_rate": 0,
"route_resolution_accuracy": null,
"no_route_precision": null,
"false_no_route_rate": null,
"execution_state_consistency_rate": 100,
"executable_with_soft_assumptions_rate": 100,
"soft_assumption_used_fragment_rate": 100,
"clarification_precision": null,
"clarification_recall": null,
"false_clarification_rate": null
},
"budget": {
"requests_total": 0,
"retries_used": 0
},
"clarification_eval": {
"labeled_cases": 0,
"true_positive": 0,
"false_positive": 0,
"false_negative": 0
},
"route_eval": {
"labeled_cases": 0,
"correct_cases": 0,
"expected_routed_cases": 0,
"no_route_true_positive": 0,
"no_route_false_positive": 0
},
"scope_eval": {
"labeled_cases": 0,
"correct_cases": 0
},
"execution_state_eval": {
"checks_total": 2,
"checks_passed": 2
},
"route_distribution": {
"store_feature_risk": 1,
"hybrid_store_plus_live": 1
},
"fallback_distribution": {
"none": 2
},
"results": [
{
"case_id": "BQ-001",
"raw_question": "Проверь счет 60 за июнь 2020",
"validation_passed": true,
"message_in_scope": true,
"scope_confidence": "high",
"contains_multiple_tasks": false,
"fragments_total": 1,
"in_scope_fragments": 1,
"out_of_scope_fragments": 0,
"unclear_fragments": 0,
"fallback_type": "none",
"predicted_route_status": "routed",
"expected_route_status": null,
"predicted_no_route_reason": null,
"expected_no_route_reason": null,
"predicted_clarification_required": false,
"expected_clarification_required": null,
"executable_with_soft_assumptions_fragments": 1,
"trace_id": "3a_NZFB9MhKiKT",
"request_count_for_case": 0
},
{
"case_id": "BQ-002",
"raw_question": "Покажи риски по счету 97",
"validation_passed": true,
"message_in_scope": true,
"scope_confidence": "high",
"contains_multiple_tasks": false,
"fragments_total": 1,
"in_scope_fragments": 1,
"out_of_scope_fragments": 0,
"unclear_fragments": 0,
"fallback_type": "none",
"predicted_route_status": "routed",
"expected_route_status": null,
"predicted_no_route_reason": null,
"expected_no_route_reason": null,
"predicted_clarification_required": false,
"expected_clarification_required": null,
"executable_with_soft_assumptions_fragments": 1,
"trace_id": "BrD8ORrgm8qsAy",
"request_count_for_case": 0
}
]
}
@@ -0,0 +1,112 @@
{
"run_id": "eval-wWlVBoabZW",
"timestamp": "2026-04-11T10:14:44.777Z",
"mode": "single-pass-strict",
"use_mock": true,
"prompt_version": "normalizer_v2_0_2",
"schema_version": "v2_0_2",
"dataset": {
"source": "inline_raw_questions",
"file": null,
"raw_questions_count": 2
},
"cases_total": 2,
"metrics": {
"schema_validation_pass_rate": 100,
"scope_detection_accuracy": null,
"scope_in_scope_rate": 100,
"multi_intent_detected_rate": 0,
"clarification_required_rate": 0,
"avg_fragments_per_message": 1,
"out_of_scope_fragment_rate": 0,
"routed_fragment_rate": 100,
"no_route_fragment_rate": 0,
"route_resolution_accuracy": null,
"no_route_precision": null,
"false_no_route_rate": null,
"execution_state_consistency_rate": 100,
"executable_with_soft_assumptions_rate": 100,
"soft_assumption_used_fragment_rate": 100,
"clarification_precision": null,
"clarification_recall": null,
"false_clarification_rate": null
},
"budget": {
"requests_total": 0,
"retries_used": 0
},
"clarification_eval": {
"labeled_cases": 0,
"true_positive": 0,
"false_positive": 0,
"false_negative": 0
},
"route_eval": {
"labeled_cases": 0,
"correct_cases": 0,
"expected_routed_cases": 0,
"no_route_true_positive": 0,
"no_route_false_positive": 0
},
"scope_eval": {
"labeled_cases": 0,
"correct_cases": 0
},
"execution_state_eval": {
"checks_total": 2,
"checks_passed": 2
},
"route_distribution": {
"store_feature_risk": 1,
"hybrid_store_plus_live": 1
},
"fallback_distribution": {
"none": 2
},
"results": [
{
"case_id": "BQ-001",
"raw_question": "Проверь счет 60 за июнь 2020",
"validation_passed": true,
"message_in_scope": true,
"scope_confidence": "high",
"contains_multiple_tasks": false,
"fragments_total": 1,
"in_scope_fragments": 1,
"out_of_scope_fragments": 0,
"unclear_fragments": 0,
"fallback_type": "none",
"predicted_route_status": "routed",
"expected_route_status": null,
"predicted_no_route_reason": null,
"expected_no_route_reason": null,
"predicted_clarification_required": false,
"expected_clarification_required": null,
"executable_with_soft_assumptions_fragments": 1,
"trace_id": "3CW7yHQOH32rKS",
"request_count_for_case": 0
},
{
"case_id": "BQ-002",
"raw_question": "Покажи риски по счету 97",
"validation_passed": true,
"message_in_scope": true,
"scope_confidence": "high",
"contains_multiple_tasks": false,
"fragments_total": 1,
"in_scope_fragments": 1,
"out_of_scope_fragments": 0,
"unclear_fragments": 0,
"fallback_type": "none",
"predicted_route_status": "routed",
"expected_route_status": null,
"predicted_no_route_reason": null,
"expected_no_route_reason": null,
"predicted_clarification_required": false,
"expected_clarification_required": null,
"executable_with_soft_assumptions_fragments": 1,
"trace_id": "Gdw6ytd-K55hUm",
"request_count_for_case": 0
}
]
}