feat(demo): add interview quality audit

This commit is contained in:
zhuyongxin
2026-07-09 11:18:49 +08:00
parent a6c2d4459c
commit 9c9a0024d4
37 changed files with 1162 additions and 86 deletions
@@ -0,0 +1,192 @@
{
"session": {
"sessionId": "eval-audit-metadata-low-confid",
"query": "订单超时是否可以确认由数据库主库故障导致,并检查审计元数据是否完整?",
"status": "SUCCESS",
"agentFlow": "CHAT",
"totalDurationMs": 45000,
"toolCallCount": 1,
"answer": "以下结论基于当前已获取证据,仍存在部分证据缺口,请谨慎参考。\n\n已确认信息:日志显示订单接口出现超时。\n\n仍需补充信息:目前没有数据库故障日志或主库状态证据,不能把该方向写成确认根因。",
"selfEvaluation": {
"verifier_evaluation": {
"verdict": "LOW_CONFID",
"groundedness_score": 0.42,
"critical_fact_count": 2,
"prompt_audit": {
"version": "chat-prompts-v1",
"prompts": [
{
"name": "chat_planner",
"version": "chat-planner-v1",
"resource": "prompts/chat-planner-prompt.md"
},
{
"name": "chat_executor",
"version": "chat-executor-v2",
"resource": "prompts/chat-executor-prompt.md"
},
{
"name": "chat_verifier",
"version": "chat-verifier-v2",
"resource": "prompts/chat-verifier-prompt.md"
},
{
"name": "chat_composer",
"version": "chat-composer-v1",
"resource": "prompts/chat-composer-prompt.md"
}
]
},
"gatekeeper_result": {
"status": "pass",
"severity": "none",
"rule_set_version": "gatekeeper-rules-v1",
"rules": [
{
"id": "evidence.invocation",
"description": "source_invocation_id must reference an existing tool invocation",
"enabled": true,
"default_severity": "reject"
},
{
"id": "evidence.excerpt",
"description": "evidence_excerpt must be supported by recorded evidence text",
"enabled": true,
"default_severity": "reject"
}
],
"checked_bindings": [
{
"claim_id": "claim-timeout",
"tool_name": "query_logs",
"source_invocation_id": 22,
"raw_path": "$.logs[0]",
"matched_text": "order api timeout",
"status": "pass"
}
],
"failed_rules": [],
"warnings": [],
"errors": []
},
"executor_structured_output": {
"answer_version": "executor_evidence_v2",
"claims": [
{
"claim_id": "claim-timeout",
"claim_type": "symptom",
"claim_text": "订单接口出现超时",
"support_level": "direct",
"evidence_bindings": [
{
"source_type": "tool_trace",
"tool_name": "query_logs",
"source_invocation_id": 22,
"raw_path": "$.logs[0]",
"evidence_excerpt": "order api timeout"
}
]
},
{
"claim_id": "claim-db-primary",
"claim_type": "root_cause",
"claim_text": "数据库主库故障导致订单超时",
"support_level": "weak",
"evidence_bindings": [
{
"source_type": "tool_trace",
"tool_name": "query_logs",
"source_invocation_id": 22,
"raw_path": "$.logs[0]",
"evidence_excerpt": "order api timeout"
}
]
}
],
"hypotheses": [],
"recommended_actions": [
{
"action_text": "补充查询数据库主库状态和错误日志",
"reason": "当前只有订单接口超时日志"
}
],
"missing_info": ["数据库主库状态", "数据库错误日志"]
},
"claim_checks": [
{
"claim_id": "claim-timeout",
"claim_text": "订单接口出现超时",
"claim_type": "symptom",
"verification": "direct_observation",
"detail": "日志直接记录 order api timeout",
"evidence_refs": [
{
"source_invocation_id": 22,
"raw_path": "$.logs[0]"
}
]
},
{
"claim_id": "claim-db-primary",
"claim_text": "数据库主库故障导致订单超时",
"claim_type": "root_cause",
"verification": "unsupported",
"detail": "日志只能证明订单接口超时,不能证明数据库主库故障",
"evidence_refs": [
{
"source_invocation_id": 22,
"raw_path": "$.logs[0]"
}
]
}
],
"facts_checked": [],
"composer_output": {
"status": "valid",
"answer_summary": "日志显示订单接口超时,但数据库方向证据不足。",
"recommended_actions": [
{
"action_text": "补充查询数据库主库状态和错误日志",
"reason": "当前只有订单接口超时日志"
}
],
"user_facing_answer": "以下结论基于当前已获取证据,仍存在部分证据缺口,请谨慎参考。\n\n已确认信息:日志显示订单接口出现超时。\n\n仍需补充信息:目前没有数据库故障日志或主库状态证据,不能把该方向写成确认根因。"
},
"tool_trace_summary": [
{
"tool_name": "query_logs",
"success": true,
"evidence_level": "direct"
}
]
}
}
},
"steps": [],
"toolInvocations": [
{
"id": 22,
"sessionId": "eval-audit-metadata-low-confid",
"toolName": "query_logs",
"outputPreview": "order api timeout",
"retrievalDetails": {
"evidence_status": "supported",
"evidence_refs": [
{
"raw_path": "$.logs[0]",
"text": "order api timeout"
}
]
},
"success": true
}
],
"summary": {
"persistedStepCount": 3,
"returnedStepCount": 3,
"persistedToolCallCount": 1,
"returnedToolCallCount": 1,
"hasVerifierEvaluation": true,
"hasFeedback": false
}
}
@@ -0,0 +1,155 @@
{
"session": {
"sessionId": "eval-prompt-gatekeeper-audit-closure",
"query": "确认 payment-service 当前是否存在 HighCPUUsage 告警,并检查审计元数据是否完整。",
"status": "SUCCESS",
"agentFlow": "CHAT",
"totalDurationMs": 19000,
"toolCallCount": 1,
"answer": "payment-service 当前存在 HighCPUUsage 告警,CPU 使用率为 92%。",
"selfEvaluation": {
"verifier_evaluation": {
"verdict": "PASS",
"groundedness_score": 1.0,
"critical_fact_count": 1,
"prompt_audit": {
"version": "chat-prompts-v1",
"prompts": [
{
"name": "chat_planner",
"version": "chat-planner-v1",
"resource": "prompts/chat-planner-prompt.md"
},
{
"name": "chat_executor",
"version": "chat-executor-v2",
"resource": "prompts/chat-executor-prompt.md"
},
{
"name": "chat_verifier",
"version": "chat-verifier-v2",
"resource": "prompts/chat-verifier-prompt.md"
},
{
"name": "chat_composer",
"version": "chat-composer-v1",
"resource": "prompts/chat-composer-prompt.md"
}
]
},
"gatekeeper_result": {
"status": "pass",
"severity": "none",
"rule_set_version": "gatekeeper-rules-v1",
"rules": [
{
"id": "evidence.invocation",
"description": "source_invocation_id must reference an existing tool invocation",
"enabled": true,
"default_severity": "reject"
},
{
"id": "evidence.raw_path",
"description": "raw_path must exist in retrieval_details.evidence_refs",
"enabled": true,
"default_severity": "reject"
}
],
"checked_bindings": [
{
"claim_id": "claim-1",
"tool_name": "query_metrics",
"source_invocation_id": 21,
"raw_path": "$.alerts[0]",
"matched_text": "HighCPUUsage firing, service=payment-service, current=92%, duration=25m",
"status": "pass"
}
],
"failed_rules": [],
"warnings": [],
"errors": []
},
"executor_structured_output": {
"answer_version": "executor_evidence_v2",
"claims": [
{
"claim_id": "claim-1",
"claim_type": "observation",
"claim_text": "payment-service 当前存在 HighCPUUsage 告警,CPU 使用率为 92%。",
"support_level": "direct",
"evidence_bindings": [
{
"source_type": "tool_trace",
"tool_name": "query_metrics",
"source_invocation_id": 21,
"raw_path": "$.alerts[0]",
"evidence_excerpt": "HighCPUUsage firing, service=payment-service, current=92%, duration=25m"
}
]
}
],
"hypotheses": [],
"recommended_actions": [],
"missing_info": []
},
"claim_checks": [
{
"claim_id": "claim-1",
"claim_text": "payment-service 当前存在 HighCPUUsage 告警,CPU 使用率为 92%。",
"claim_type": "observation",
"verification": "direct_observation",
"detail": "已核验的指标证据直接包含服务名、告警名和 CPU 当前值。",
"evidence_refs": [
{
"source_invocation_id": 21,
"raw_path": "$.alerts[0]"
}
]
}
],
"facts_checked": [],
"composer_output": {
"status": "valid",
"answer_summary": "payment-service 当前存在 HighCPUUsage 告警。",
"recommended_actions": [],
"user_facing_answer": "payment-service 当前存在 HighCPUUsage 告警,CPU 使用率为 92%。"
},
"tool_trace_summary": [
{
"tool_name": "query_metrics",
"success": true,
"source_invocation_ids": [21],
"evidence_level": "direct"
}
]
}
}
},
"steps": [],
"toolInvocations": [
{
"id": 21,
"sessionId": "eval-prompt-gatekeeper-audit-closure",
"toolName": "query_metrics",
"outputPreview": "HighCPUUsage firing, service=payment-service, current=92%, duration=25m",
"retrievalDetails": {
"evidence_status": "supported",
"evidence_refs": [
{
"raw_path": "$.alerts[0]",
"text": "HighCPUUsage firing, service=payment-service, current=92%, duration=25m"
}
]
},
"success": true
}
],
"summary": {
"persistedStepCount": 3,
"returnedStepCount": 3,
"persistedToolCallCount": 1,
"returnedToolCallCount": 1,
"hasVerifierEvaluation": true,
"hasFeedback": false
}
}