osiman/SuperBizAgent-java
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(harness,rag): dual LLM audit fields, run conclusion, and hybrid quality

Browse Source 
Persist provider reasoning and assistant text separately on agent_reasoning_audit
(DeepSeekAssistantMessage path), extract diagnosis_run.conclusion, enrich RAG
tool audit (step_id/query/qualityScore), gate empty mysql tools, drop devtools,
and align MVP docs after live E2E verification.
This commit is contained in:
zhuyongxin
2026-07-28 19:43:13 +08:00
parent 2f40536248
commit 7ae9707a3b
116 changed files with 8364 additions and 1141 deletions
Download Patch File Download Diff File Expand all files Collapse all files
eval/rag-retrieval/reports/baseline.json
+38 -14
View File
@@ -1,5 +1,5 @@
{
"generatedAt": "2026-07-06T13:37:59.726351+00:00",
"generatedAt": "2026-07-28T06:55:09.379164+00:00",
"caseFile": "eval/rag-retrieval/cases/golden-cases.json",
"fixtureDir": "eval/rag-retrieval/fixtures",
"aggregate": {
@@ -28,7 +28,7 @@
"firstExpectedRank": 1,
"topCandidates": [
"1:mysql-connection-pool",
"2:incident-diagnosis-flow"
"2:mysql-connection-pool"
],
"matchedKeywords": [
"connection pool",
@@ -41,7 +41,7 @@
"evidenceStatus": "supported",
"includedSources": [
"mysql-connection-pool",
"incident-diagnosis-flow"
"mysql-connection-pool"
],
"omittedSources": [],
"rerankTopSource": "mysql-connection-pool",
@@ -57,7 +57,7 @@
"firstExpectedRank": 1,
"topCandidates": [
"1:incident-diagnosis-flow",
"2:rag-chunk-context-reconstruction"
"2:incident-diagnosis-flow"
],
"matchedKeywords": [
"collect evidence",
@@ -70,7 +70,7 @@
"evidenceStatus": "supported",
"includedSources": [
"incident-diagnosis-flow",
"rag-chunk-context-reconstruction"
"incident-diagnosis-flow"
],
"omittedSources": [],
"rerankTopSource": "incident-diagnosis-flow",
@@ -86,7 +86,9 @@
"firstExpectedRank": 1,
"topCandidates": [
"1:payment-service-latency",
"2:mysql-connection-pool"
"2:aiops-alert-scope-control",
"3:payment-service-latency",
"4:aiops-alert-scope-control"
],
"matchedKeywords": [
"p95 latency",
@@ -99,7 +101,9 @@
"evidenceStatus": "supported",
"includedSources": [
"payment-service-latency",
"mysql-connection-pool"
"aiops-alert-scope-control",
"payment-service-latency",
"aiops-alert-scope-control"
],
"omittedSources": [],
"rerankTopSource": "payment-service-latency",
@@ -114,7 +118,10 @@
"passed": true,
"firstExpectedRank": 1,
"topCandidates": [
"1:aiops-alert-scope-control"
"1:aiops-alert-scope-control",
"2:payment-service-latency",
"3:payment-service-latency",
"4:aiops-alert-scope-control"
],
"matchedKeywords": [
"payload",
@@ -126,6 +133,9 @@
"fallbackReason": null,
"evidenceStatus": "supported",
"includedSources": [
"aiops-alert-scope-control",
"payment-service-latency",
"payment-service-latency",
"aiops-alert-scope-control"
],
"omittedSources": [],
@@ -142,7 +152,9 @@
"firstExpectedRank": 1,
"topCandidates": [
"1:rag-chunk-context-reconstruction",
"2:rag-breadcrumb-embedding-gap"
"2:rag-l0-domain-entity-hint",
"3:rag-chunk-context-reconstruction",
"4:rag-l0-domain-entity-hint"
],
"matchedKeywords": [
"neighbor chunk",
@@ -155,7 +167,9 @@
"evidenceStatus": "supported",
"includedSources": [
"rag-chunk-context-reconstruction",
"rag-breadcrumb-embedding-gap"
"rag-l0-domain-entity-hint",
"rag-chunk-context-reconstruction",
"rag-l0-domain-entity-hint"
],
"omittedSources": [],
"rerankTopSource": "rag-chunk-context-reconstruction",
@@ -171,7 +185,9 @@
"firstExpectedRank": 1,
"topCandidates": [
"1:rag-l0-domain-entity-hint",
"2:rag-l0-l1-fusion-ranking"
"2:rag-chunk-context-reconstruction",
"3:rag-l0-domain-entity-hint",
"4:rag-chunk-context-reconstruction"
],
"matchedKeywords": [
"domain detector",
@@ -184,7 +200,9 @@
"evidenceStatus": "supported",
"includedSources": [
"rag-l0-domain-entity-hint",
"rag-l0-l1-fusion-ranking"
"rag-chunk-context-reconstruction",
"rag-l0-domain-entity-hint",
"rag-chunk-context-reconstruction"
],
"omittedSources": [],
"rerankTopSource": "rag-l0-domain-entity-hint",
@@ -200,7 +218,10 @@
"firstExpectedRank": 1,
"topCandidates": [
"1:rag-l0-filter-fallback",
"2:rag-l0-domain-entity-hint"
"2:rag-l0-filter-decoy",
"3:rag-l0-domain-entity-hint",
"4:rag-l0-domain-entity-hint",
"5:rag-chunk-context-reconstruction"
],
"matchedKeywords": [
"skip the l0 filter",
@@ -213,7 +234,10 @@
"evidenceStatus": "supported",
"includedSources": [
"rag-l0-filter-fallback",
"rag-l0-domain-entity-hint"
"rag-l0-filter-decoy",
"rag-l0-domain-entity-hint",
"rag-l0-domain-entity-hint",
"rag-chunk-context-reconstruction"
],
"omittedSources": [],
"rerankTopSource": "rag-l0-filter-fallback",