Этап 4 / Волна 11: объектный трейс по бизнес-якорям, доменное заземление, cleanup утечки дебага

This commit is contained in:
2026-03-28 13:12:09 +03:00
parent 553a5c407a
commit 8b84f5e989
34 changed files with 5517 additions and 173 deletions
@@ -0,0 +1,111 @@
{
"run_id": "eval-7Sx8faOQpm",
"timestamp": "2026-03-28T09:54:19.332Z",
"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": "1wEfvoR_2DJrlV",
"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": "wp-jtQq3mp7uMk",
"request_count_for_case": 0
}
]
}
@@ -0,0 +1,137 @@
{
"run_id": "eval-DI-aCpLWqK",
"timestamp": "2026-03-28T09:54:17.753Z",
"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": "LQSTgr_jZDLKSE",
"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": "C_DgPdm03zoNRm",
"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": "ou478il0iFNsIQ",
"request_count_for_case": 0
}
]
}
@@ -0,0 +1,137 @@
{
"run_id": "eval-KEtQ8SYPKI",
"timestamp": "2026-03-28T09:23:28.807Z",
"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": "wKL8CXbPIJDi5V",
"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": "VGu1HWqb9Ka5QF",
"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": "rvXo7PioBUelzY",
"request_count_for_case": 0
}
]
}
@@ -0,0 +1,111 @@
{
"run_id": "eval-KSX4Dsn7Xg",
"timestamp": "2026-03-28T09:54:19.191Z",
"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": "airV6dR4a5sk0p",
"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": "FpNPo_qn_TakTC",
"request_count_for_case": 0
}
]
}
@@ -0,0 +1,111 @@
{
"run_id": "eval-O1pl1uP_Kc",
"timestamp": "2026-03-28T09:09:42.733Z",
"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": "DYfGFpealu2tnx",
"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": "ZweuomcToD_MJn",
"request_count_for_case": 0
}
]
}
@@ -0,0 +1,111 @@
{
"run_id": "eval-WTP_zUxzSk",
"timestamp": "2026-03-28T09:23:30.429Z",
"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": "pgJG_e5WDfRPGr",
"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": "0iHAq9Sf3LQoGv",
"request_count_for_case": 0
}
]
}
@@ -0,0 +1,137 @@
{
"run_id": "eval-XunNzxsTLF",
"timestamp": "2026-03-28T09:43:10.148Z",
"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": "iwEKj8yXXL_94j",
"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": "Ww5O8UQ8xVYdqX",
"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": "U2ODfQtj3y9ieS",
"request_count_for_case": 0
}
]
}
@@ -0,0 +1,111 @@
{
"run_id": "eval-XyP2pAdsJB",
"timestamp": "2026-03-28T09:58:48.945Z",
"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": "KH-f-MZ4cm--WR",
"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": "yiAsfJaSW5Qm3o",
"request_count_for_case": 0
}
]
}
@@ -0,0 +1,111 @@
{
"run_id": "eval-a3v4udOWPA",
"timestamp": "2026-03-28T09:43:11.528Z",
"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": "YGuB_vMi7qg803",
"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": "snXRfmWFgVHm3i",
"request_count_for_case": 0
}
]
}
@@ -0,0 +1,111 @@
{
"run_id": "eval-do0FoiH-Xe",
"timestamp": "2026-03-28T09:43:11.767Z",
"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": "dOLnE76GCDaC7H",
"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": "cTDkKra0xTEPWK",
"request_count_for_case": 0
}
]
}
@@ -0,0 +1,111 @@
{
"run_id": "eval-gt_MR9X37J",
"timestamp": "2026-03-28T09:09:42.504Z",
"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": "u0PbQMwXMrEkkc",
"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": "HzY3_UubbqgLW1",
"request_count_for_case": 0
}
]
}
@@ -0,0 +1,137 @@
{
"run_id": "eval-nBbn-LjIiA",
"timestamp": "2026-03-28T09:09:41.153Z",
"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": "-H_wQprzOS7_Id",
"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": "fQOvPenqT3TF8w",
"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": "Z3MSiUIB6-qCqJ",
"request_count_for_case": 0
}
]
}
@@ -0,0 +1,111 @@
{
"run_id": "eval-qsqmRe1REB",
"timestamp": "2026-03-28T09:23:30.226Z",
"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": "t27mUt40DZkNxA",
"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": "SRUJifR4MwjGqq",
"request_count_for_case": 0
}
]
}
@@ -0,0 +1,111 @@
{
"run_id": "eval-vXCfmE5dFG",
"timestamp": "2026-03-28T09:58:49.158Z",
"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": "ZU34_DiRow0vZ5",
"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": "Nojaq_kesX2XGI",
"request_count_for_case": 0
}
]
}
@@ -0,0 +1,137 @@
{
"run_id": "eval-xytqNgINxK",
"timestamp": "2026-03-28T09:58:47.522Z",
"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": "JUjGkgksG-QX_y",
"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": "9Os3edsGypmVvr",
"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": "FgsR4vO6BqpNvV",
"request_count_for_case": 0
}
]
}