Усилить reliability gate и принять margin semantic replay
This commit is contained in:
@@ -0,0 +1,137 @@
|
||||
{
|
||||
"run_id": "eval-QvCdJw3L2F",
|
||||
"timestamp": "2026-05-24T07:11:10.815Z",
|
||||
"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": "6H5F0kDlkYF66l",
|
||||
"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": "e-Yrbn6kxhbKhv",
|
||||
"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": "mwO8qxdx71dFCd",
|
||||
"request_count_for_case": 0
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,112 @@
|
||||
{
|
||||
"run_id": "eval-_NYgFC2nU2",
|
||||
"timestamp": "2026-05-24T07:11:23.663Z",
|
||||
"mode": "single-pass-strict",
|
||||
"use_mock": true,
|
||||
"prompt_version": "normalizer_v2_0_2",
|
||||
"schema_version": "v2_0_2",
|
||||
"dataset": {
|
||||
"source": "inline_raw_questions",
|
||||
"file": null,
|
||||
"raw_questions_count": 2
|
||||
},
|
||||
"cases_total": 2,
|
||||
"metrics": {
|
||||
"schema_validation_pass_rate": 100,
|
||||
"scope_detection_accuracy": null,
|
||||
"scope_in_scope_rate": 100,
|
||||
"multi_intent_detected_rate": 0,
|
||||
"clarification_required_rate": 0,
|
||||
"avg_fragments_per_message": 1,
|
||||
"out_of_scope_fragment_rate": 0,
|
||||
"routed_fragment_rate": 100,
|
||||
"no_route_fragment_rate": 0,
|
||||
"route_resolution_accuracy": null,
|
||||
"no_route_precision": null,
|
||||
"false_no_route_rate": null,
|
||||
"execution_state_consistency_rate": 100,
|
||||
"executable_with_soft_assumptions_rate": 100,
|
||||
"soft_assumption_used_fragment_rate": 100,
|
||||
"clarification_precision": null,
|
||||
"clarification_recall": null,
|
||||
"false_clarification_rate": null
|
||||
},
|
||||
"budget": {
|
||||
"requests_total": 0,
|
||||
"retries_used": 0
|
||||
},
|
||||
"clarification_eval": {
|
||||
"labeled_cases": 0,
|
||||
"true_positive": 0,
|
||||
"false_positive": 0,
|
||||
"false_negative": 0
|
||||
},
|
||||
"route_eval": {
|
||||
"labeled_cases": 0,
|
||||
"correct_cases": 0,
|
||||
"expected_routed_cases": 0,
|
||||
"no_route_true_positive": 0,
|
||||
"no_route_false_positive": 0
|
||||
},
|
||||
"scope_eval": {
|
||||
"labeled_cases": 0,
|
||||
"correct_cases": 0
|
||||
},
|
||||
"execution_state_eval": {
|
||||
"checks_total": 2,
|
||||
"checks_passed": 2
|
||||
},
|
||||
"route_distribution": {
|
||||
"store_feature_risk": 1,
|
||||
"hybrid_store_plus_live": 1
|
||||
},
|
||||
"fallback_distribution": {
|
||||
"none": 2
|
||||
},
|
||||
"results": [
|
||||
{
|
||||
"case_id": "BQ-001",
|
||||
"raw_question": "Проверь счет 60 за июнь 2020",
|
||||
"validation_passed": true,
|
||||
"message_in_scope": true,
|
||||
"scope_confidence": "high",
|
||||
"contains_multiple_tasks": false,
|
||||
"fragments_total": 1,
|
||||
"in_scope_fragments": 1,
|
||||
"out_of_scope_fragments": 0,
|
||||
"unclear_fragments": 0,
|
||||
"fallback_type": "none",
|
||||
"predicted_route_status": "routed",
|
||||
"expected_route_status": null,
|
||||
"predicted_no_route_reason": null,
|
||||
"expected_no_route_reason": null,
|
||||
"predicted_clarification_required": false,
|
||||
"expected_clarification_required": null,
|
||||
"executable_with_soft_assumptions_fragments": 1,
|
||||
"trace_id": "A1V4KbeK6NiYJK",
|
||||
"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": "Bg-XArIzpQzoHW",
|
||||
"request_count_for_case": 0
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,112 @@
|
||||
{
|
||||
"run_id": "eval-lFWABdc8V1",
|
||||
"timestamp": "2026-05-24T07:11:24.006Z",
|
||||
"mode": "single-pass-strict",
|
||||
"use_mock": true,
|
||||
"prompt_version": "normalizer_v2_0_2",
|
||||
"schema_version": "v2_0_2",
|
||||
"dataset": {
|
||||
"source": "inline_raw_questions",
|
||||
"file": null,
|
||||
"raw_questions_count": 2
|
||||
},
|
||||
"cases_total": 2,
|
||||
"metrics": {
|
||||
"schema_validation_pass_rate": 100,
|
||||
"scope_detection_accuracy": null,
|
||||
"scope_in_scope_rate": 100,
|
||||
"multi_intent_detected_rate": 0,
|
||||
"clarification_required_rate": 0,
|
||||
"avg_fragments_per_message": 1,
|
||||
"out_of_scope_fragment_rate": 0,
|
||||
"routed_fragment_rate": 100,
|
||||
"no_route_fragment_rate": 0,
|
||||
"route_resolution_accuracy": null,
|
||||
"no_route_precision": null,
|
||||
"false_no_route_rate": null,
|
||||
"execution_state_consistency_rate": 100,
|
||||
"executable_with_soft_assumptions_rate": 100,
|
||||
"soft_assumption_used_fragment_rate": 100,
|
||||
"clarification_precision": null,
|
||||
"clarification_recall": null,
|
||||
"false_clarification_rate": null
|
||||
},
|
||||
"budget": {
|
||||
"requests_total": 0,
|
||||
"retries_used": 0
|
||||
},
|
||||
"clarification_eval": {
|
||||
"labeled_cases": 0,
|
||||
"true_positive": 0,
|
||||
"false_positive": 0,
|
||||
"false_negative": 0
|
||||
},
|
||||
"route_eval": {
|
||||
"labeled_cases": 0,
|
||||
"correct_cases": 0,
|
||||
"expected_routed_cases": 0,
|
||||
"no_route_true_positive": 0,
|
||||
"no_route_false_positive": 0
|
||||
},
|
||||
"scope_eval": {
|
||||
"labeled_cases": 0,
|
||||
"correct_cases": 0
|
||||
},
|
||||
"execution_state_eval": {
|
||||
"checks_total": 2,
|
||||
"checks_passed": 2
|
||||
},
|
||||
"route_distribution": {
|
||||
"store_feature_risk": 1,
|
||||
"hybrid_store_plus_live": 1
|
||||
},
|
||||
"fallback_distribution": {
|
||||
"none": 2
|
||||
},
|
||||
"results": [
|
||||
{
|
||||
"case_id": "BQ-001",
|
||||
"raw_question": "Проверь счет 60 за июнь 2020",
|
||||
"validation_passed": true,
|
||||
"message_in_scope": true,
|
||||
"scope_confidence": "high",
|
||||
"contains_multiple_tasks": false,
|
||||
"fragments_total": 1,
|
||||
"in_scope_fragments": 1,
|
||||
"out_of_scope_fragments": 0,
|
||||
"unclear_fragments": 0,
|
||||
"fallback_type": "none",
|
||||
"predicted_route_status": "routed",
|
||||
"expected_route_status": null,
|
||||
"predicted_no_route_reason": null,
|
||||
"expected_no_route_reason": null,
|
||||
"predicted_clarification_required": false,
|
||||
"expected_clarification_required": null,
|
||||
"executable_with_soft_assumptions_fragments": 1,
|
||||
"trace_id": "9NqELSDEJeKcZl",
|
||||
"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": "AWGkBh8taBraRd",
|
||||
"request_count_for_case": 0
|
||||
}
|
||||
]
|
||||
}
|
||||
Reference in New Issue
Block a user