Этап 4 / Волна 16: смысловая изоляция РБП и ОС, фиксы лайв-ответов и добивка экспорта

This commit is contained in:
2026-03-28 21:11:11 +03:00
parent 6123fafd5b
commit 7eb1410501
35 changed files with 4120 additions and 155 deletions
@@ -0,0 +1,111 @@
{
"run_id": "eval-0E46_gT0ds",
"timestamp": "2026-03-28T14:52:43.266Z",
"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": {
"hybrid_store_plus_live": 2
},
"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": "j4C5JaGsdTX31w",
"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": "EiQ_YNd0Z7R8dD",
"request_count_for_case": 0
}
]
}
@@ -0,0 +1,111 @@
{
"run_id": "eval-0yLbBfl8QU",
"timestamp": "2026-03-28T14:16:11.152Z",
"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": {
"hybrid_store_plus_live": 2
},
"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": "zeDz4lWmOU-sXS",
"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": "Igp7ZjWw22GURw",
"request_count_for_case": 0
}
]
}
@@ -0,0 +1,111 @@
{
"run_id": "eval-1yuAQTgSrA",
"timestamp": "2026-03-28T14:52:43.542Z",
"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": {
"hybrid_store_plus_live": 2
},
"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": "dFofCt0krmlNxt",
"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": "yuuGwyY-66-Acz",
"request_count_for_case": 0
}
]
}
@@ -0,0 +1,111 @@
{
"run_id": "eval-3lDLPY889T",
"timestamp": "2026-03-28T14:17:31.550Z",
"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": {
"hybrid_store_plus_live": 2
},
"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": "QsfgBqSscHBfPL",
"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": "lrWC9XpjJMN6AA",
"request_count_for_case": 0
}
]
}
@@ -0,0 +1,111 @@
{
"run_id": "eval-48cua6GzNX",
"timestamp": "2026-03-28T17:57:44.019Z",
"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": {
"hybrid_store_plus_live": 2
},
"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": "60LijB0t8hI6Rv",
"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": "tpPYPTRrOcZlBe",
"request_count_for_case": 0
}
]
}
@@ -0,0 +1,137 @@
{
"run_id": "eval-LbmAxVpEYt",
"timestamp": "2026-03-28T14:17:29.773Z",
"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": "THNkvQLVaISlq3",
"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": "0kU7UfIyaxB3TA",
"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": "ZCKIUbbI9qTMwd",
"request_count_for_case": 0
}
]
}
@@ -0,0 +1,137 @@
{
"run_id": "eval-LpNMUq6e64",
"timestamp": "2026-03-28T14:52:41.774Z",
"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": "jjxZOJBxrjPdsX",
"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": "bYY62dikNsLECZ",
"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": "baezDULblEFYkL",
"request_count_for_case": 0
}
]
}
@@ -0,0 +1,111 @@
{
"run_id": "eval-Mk-Ep58vC0",
"timestamp": "2026-03-28T17:57:43.813Z",
"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": {
"hybrid_store_plus_live": 2
},
"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": "p_blMcrrCin_H_",
"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": "esnlDt05yjx_03",
"request_count_for_case": 0
}
]
}
@@ -0,0 +1,137 @@
{
"run_id": "eval-N-nY96elpX",
"timestamp": "2026-03-28T14:23:36.202Z",
"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": "7mDZkne0GBSe62",
"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": "wAVEOezciqQrtm",
"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": "t5shV55ZPr8wir",
"request_count_for_case": 0
}
]
}
@@ -0,0 +1,111 @@
{
"run_id": "eval-S-kDKKK4xO",
"timestamp": "2026-03-28T14:17:31.390Z",
"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": {
"hybrid_store_plus_live": 2
},
"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": "kl3P7qQGw4BRHD",
"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": "yn8Ku_R5880RIB",
"request_count_for_case": 0
}
]
}
@@ -0,0 +1,137 @@
{
"run_id": "eval-UNNoKia3JQ",
"timestamp": "2026-03-28T17:57:42.190Z",
"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": "MY7YLMfaYP3kVR",
"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": "gpwnhjSvR3NClQ",
"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": "WYxkGFarO1WeXH",
"request_count_for_case": 0
}
]
}
@@ -0,0 +1,111 @@
{
"run_id": "eval-X71VuszUM2",
"timestamp": "2026-03-28T14:47:45.410Z",
"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": {
"hybrid_store_plus_live": 2
},
"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": "QacgRS_Ur2ayEH",
"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": "qtDYC8oP9w1v9B",
"request_count_for_case": 0
}
]
}
@@ -0,0 +1,111 @@
{
"run_id": "eval-ZBwXbFcCs9",
"timestamp": "2026-03-28T14:23:37.997Z",
"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": {
"hybrid_store_plus_live": 2
},
"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": "NMt3FqmnkEylaF",
"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": "TNvDsELGZj_UDF",
"request_count_for_case": 0
}
]
}
@@ -0,0 +1,137 @@
{
"run_id": "eval-_XbcacYQdg",
"timestamp": "2026-03-28T14:16:09.590Z",
"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": "84nqlo6CKGkRZm",
"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": "Z-6QeOaELWJ40H",
"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": "fq5Nw3FI86Ldc1",
"request_count_for_case": 0
}
]
}
@@ -0,0 +1,111 @@
{
"run_id": "eval-bNqkZdQS9g",
"timestamp": "2026-03-28T14:23:37.732Z",
"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": {
"hybrid_store_plus_live": 2
},
"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": "AnVPMdNwg-rf3T",
"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": "utvJRunZgTZrKu",
"request_count_for_case": 0
}
]
}
@@ -0,0 +1,137 @@
{
"run_id": "eval-c2aEXxAGeh",
"timestamp": "2026-03-28T14:47:43.841Z",
"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": "r6cJKlGb3sAo1h",
"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": "RwtT5cfOm8EQzm",
"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": "aTubcVPJxRPKKy",
"request_count_for_case": 0
}
]
}
@@ -0,0 +1,111 @@
{
"run_id": "eval-giqMXxi5Cr",
"timestamp": "2026-03-28T14:16:11.355Z",
"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": {
"hybrid_store_plus_live": 2
},
"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": "lqgRK3iNNLJBPj",
"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": "8F-6dbOWrrZ8DS",
"request_count_for_case": 0
}
]
}
@@ -0,0 +1,111 @@
{
"run_id": "eval-rbxdQ0Yd-g",
"timestamp": "2026-03-28T14:47:45.752Z",
"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": {
"hybrid_store_plus_live": 2
},
"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": "KRtUQA4OmuvZXo",
"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": "6HH1OsFaNsR6hO",
"request_count_for_case": 0
}
]
}