@ryuenn3123/agentic-senior-core 3.0.37 → 3.0.39
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.agent-context/prompts/bootstrap-design.md +109 -146
- package/.agent-context/rules/frontend-architecture.md +92 -108
- package/.agent-context/state/README.md +26 -0
- package/.agent-context/state/architecture-map.md +32 -17
- package/.agent-context/state/dependency-map.md +31 -22
- package/.cursor/mcp.json +10 -0
- package/.cursor/rules/agentic-senior-core.mdc +48 -0
- package/.cursorrules +22 -88
- package/.gemini/instructions.md +25 -16
- package/.github/copilot-instructions.md +25 -16
- package/.github/instructions/agentic-senior-core.instructions.md +47 -0
- package/.instructions.md +98 -207
- package/.windsurf/rules/agentic-senior-core.md +43 -0
- package/.windsurfrules +22 -88
- package/AGENTS.md +23 -26
- package/CLAUDE.md +43 -0
- package/CONTRIBUTING.md +7 -2
- package/GEMINI.md +43 -0
- package/README.md +25 -7
- package/lib/cli/backup.mjs +4 -4
- package/lib/cli/commands/init/project-context.mjs +101 -0
- package/lib/cli/commands/init/runtime-environment.mjs +59 -0
- package/lib/cli/commands/init/setup-decisions.mjs +83 -0
- package/lib/cli/commands/init.mjs +33 -250
- package/lib/cli/commands/optimize.mjs +1 -1
- package/lib/cli/commands/upgrade.mjs +34 -16
- package/lib/cli/compiler.mjs +59 -17
- package/lib/cli/constants.mjs +5 -0
- package/lib/cli/detector.mjs +4 -0
- package/lib/cli/init-detection-flow.mjs +9 -1
- package/lib/cli/init-selection.mjs +0 -5
- package/lib/cli/preflight.mjs +3 -3
- package/lib/cli/project-scaffolder/design-contract/validation.mjs +789 -0
- package/lib/cli/project-scaffolder/design-contract.mjs +119 -924
- package/lib/cli/project-scaffolder/prompt-builders.mjs +69 -84
- package/lib/cli/project-scaffolder.mjs +0 -2
- package/lib/cli/utils/filesystem.mjs +79 -0
- package/lib/cli/utils/managed-surface.mjs +237 -0
- package/lib/cli/utils/prompting.mjs +44 -0
- package/lib/cli/utils.mjs +33 -335
- package/package.json +21 -2
- package/scripts/bump-version.mjs +15 -13
- package/scripts/clean-local-artifacts.mjs +76 -0
- package/scripts/docs-quality-drift-report.mjs +5 -0
- package/scripts/frontend-usability-audit.mjs +23 -19
- package/scripts/governance-weekly-report.mjs +37 -15
- package/scripts/single-source-lazy-loading-audit.mjs +24 -0
- package/scripts/sync-thin-adapters.mjs +99 -129
- package/scripts/v3-purge-audit.mjs +5 -0
- package/scripts/validate/config.mjs +10 -0
- package/scripts/validate/coverage-checks.mjs +55 -0
- package/scripts/validate.mjs +20 -0
- package/.agent-context/marketplace/trust-tiers.json +0 -114
- package/.agent-context/state/benchmark-analysis.json +0 -431
- package/.agent-context/state/benchmark-evidence-bundle.json +0 -1040
- package/.agent-context/state/benchmark-history.json +0 -75
- package/.agent-context/state/benchmark-trend-report.csv +0 -5
- package/.agent-context/state/benchmark-trend-report.json +0 -140
- package/.agent-context/state/benchmark-writer-judge-matrix.json +0 -462
- package/.agent-context/state/memory-continuity-benchmark.json +0 -132
- package/.agent-context/state/onboarding-report.json +0 -102
- package/.agent-context/state/quality-trend-report.json +0 -89
- package/.agent-context/state/token-optimization-benchmark.json +0 -130
- package/.agent-context/state/weekly-governance-report.json +0 -329
- package/lib/cli/compatibility.mjs +0 -124
- package/scripts/validate-evidence-bundle.mjs +0 -76
|
@@ -1,75 +0,0 @@
|
|
|
1
|
-
{
|
|
2
|
-
"generatedAt": "2026-04-17T03:20:15.400Z",
|
|
3
|
-
"reportName": "benchmark-history",
|
|
4
|
-
"maxEntries": 90,
|
|
5
|
-
"history": [
|
|
6
|
-
{
|
|
7
|
-
"generatedAt": "2026-04-17T02:54:01.239Z",
|
|
8
|
-
"releaseVersion": "2.0.26",
|
|
9
|
-
"fixtureCount": 12,
|
|
10
|
-
"top1Accuracy": 0.9167,
|
|
11
|
-
"manualCorrectionRate": 0.0833,
|
|
12
|
-
"benchmarkGatePassed": true,
|
|
13
|
-
"intelligencePassed": true,
|
|
14
|
-
"staleWatchlistCount": 0,
|
|
15
|
-
"reliabilityPassed": true,
|
|
16
|
-
"reliabilityRiskLevel": "monitor",
|
|
17
|
-
"incorrectDetectionRate": 0.0833,
|
|
18
|
-
"lowConfidenceRate": 0.0833,
|
|
19
|
-
"vulnerabilityTotal": null,
|
|
20
|
-
"criticalVulnerabilityCount": null,
|
|
21
|
-
"forbiddenContentPassed": true
|
|
22
|
-
},
|
|
23
|
-
{
|
|
24
|
-
"generatedAt": "2026-04-17T02:54:57.419Z",
|
|
25
|
-
"releaseVersion": "2.0.26",
|
|
26
|
-
"fixtureCount": 12,
|
|
27
|
-
"top1Accuracy": 0.9167,
|
|
28
|
-
"manualCorrectionRate": 0.0833,
|
|
29
|
-
"benchmarkGatePassed": true,
|
|
30
|
-
"intelligencePassed": true,
|
|
31
|
-
"staleWatchlistCount": 0,
|
|
32
|
-
"reliabilityPassed": true,
|
|
33
|
-
"reliabilityRiskLevel": "monitor",
|
|
34
|
-
"incorrectDetectionRate": 0.0833,
|
|
35
|
-
"lowConfidenceRate": 0.0833,
|
|
36
|
-
"vulnerabilityTotal": null,
|
|
37
|
-
"criticalVulnerabilityCount": null,
|
|
38
|
-
"forbiddenContentPassed": true
|
|
39
|
-
},
|
|
40
|
-
{
|
|
41
|
-
"generatedAt": "2026-04-17T03:19:31.047Z",
|
|
42
|
-
"releaseVersion": "2.0.26",
|
|
43
|
-
"fixtureCount": 12,
|
|
44
|
-
"top1Accuracy": 0.9167,
|
|
45
|
-
"manualCorrectionRate": 0.0833,
|
|
46
|
-
"benchmarkGatePassed": true,
|
|
47
|
-
"intelligencePassed": true,
|
|
48
|
-
"staleWatchlistCount": 0,
|
|
49
|
-
"reliabilityPassed": true,
|
|
50
|
-
"reliabilityRiskLevel": "monitor",
|
|
51
|
-
"incorrectDetectionRate": 0.0833,
|
|
52
|
-
"lowConfidenceRate": 0.0833,
|
|
53
|
-
"vulnerabilityTotal": null,
|
|
54
|
-
"criticalVulnerabilityCount": null,
|
|
55
|
-
"forbiddenContentPassed": true
|
|
56
|
-
},
|
|
57
|
-
{
|
|
58
|
-
"generatedAt": "2026-04-17T03:20:15.400Z",
|
|
59
|
-
"releaseVersion": "2.0.26",
|
|
60
|
-
"fixtureCount": 12,
|
|
61
|
-
"top1Accuracy": 0.9167,
|
|
62
|
-
"manualCorrectionRate": 0.0833,
|
|
63
|
-
"benchmarkGatePassed": true,
|
|
64
|
-
"intelligencePassed": true,
|
|
65
|
-
"staleWatchlistCount": 0,
|
|
66
|
-
"reliabilityPassed": true,
|
|
67
|
-
"reliabilityRiskLevel": "monitor",
|
|
68
|
-
"incorrectDetectionRate": 0.0833,
|
|
69
|
-
"lowConfidenceRate": 0.0833,
|
|
70
|
-
"vulnerabilityTotal": null,
|
|
71
|
-
"criticalVulnerabilityCount": null,
|
|
72
|
-
"forbiddenContentPassed": true
|
|
73
|
-
}
|
|
74
|
-
]
|
|
75
|
-
}
|
|
@@ -1,5 +0,0 @@
|
|
|
1
|
-
snapshotIndex,generatedAt,releaseVersion,top1Accuracy,manualCorrectionRate,incorrectDetectionRate,lowConfidenceRate,staleWatchlistCount,vulnerabilityTotal,criticalVulnerabilityCount,benchmarkGatePassed,intelligencePassed,reliabilityPassed,reliabilityRiskLevel
|
|
2
|
-
"1","2026-04-17T02:54:01.239Z","2.0.26","0.9167","0.0833","0.0833","0.0833","0",,,"true","true","true","monitor"
|
|
3
|
-
"2","2026-04-17T02:54:57.419Z","2.0.26","0.9167","0.0833","0.0833","0.0833","0",,,"true","true","true","monitor"
|
|
4
|
-
"3","2026-04-17T03:19:31.047Z","2.0.26","0.9167","0.0833","0.0833","0.0833","0",,,"true","true","true","monitor"
|
|
5
|
-
"4","2026-04-17T03:20:15.400Z","2.0.26","0.9167","0.0833","0.0833","0.0833","0",,,"true","true","true","monitor"
|
|
@@ -1,140 +0,0 @@
|
|
|
1
|
-
{
|
|
2
|
-
"generatedAt": "2026-04-17T03:20:15.400Z",
|
|
3
|
-
"reportName": "benchmark-trend-report",
|
|
4
|
-
"releaseVersion": "2.0.26",
|
|
5
|
-
"historyCount": 4,
|
|
6
|
-
"releaseDelta": {
|
|
7
|
-
"currentReleaseVersion": "2.0.26",
|
|
8
|
-
"previousReleaseVersion": "2.0.26",
|
|
9
|
-
"comparedSnapshot": {
|
|
10
|
-
"currentGeneratedAt": "2026-04-17T03:20:15.400Z",
|
|
11
|
-
"previousGeneratedAt": "2026-04-17T03:19:31.047Z"
|
|
12
|
-
},
|
|
13
|
-
"top1AccuracyDelta": 0,
|
|
14
|
-
"manualCorrectionRateDelta": 0,
|
|
15
|
-
"staleWatchlistCountDelta": 0,
|
|
16
|
-
"vulnerabilityTotalDelta": 0,
|
|
17
|
-
"summary": [
|
|
18
|
-
"top1Accuracy: +0",
|
|
19
|
-
"manualCorrectionRate: +0",
|
|
20
|
-
"staleWatchlistCount: +0",
|
|
21
|
-
"vulnerabilityTotal: +0"
|
|
22
|
-
]
|
|
23
|
-
},
|
|
24
|
-
"trendTable": [
|
|
25
|
-
{
|
|
26
|
-
"snapshotIndex": 1,
|
|
27
|
-
"generatedAt": "2026-04-17T02:54:01.239Z",
|
|
28
|
-
"releaseVersion": "2.0.26",
|
|
29
|
-
"top1Accuracy": 0.9167,
|
|
30
|
-
"manualCorrectionRate": 0.0833,
|
|
31
|
-
"incorrectDetectionRate": 0.0833,
|
|
32
|
-
"lowConfidenceRate": 0.0833,
|
|
33
|
-
"staleWatchlistCount": 0,
|
|
34
|
-
"vulnerabilityTotal": null,
|
|
35
|
-
"criticalVulnerabilityCount": null,
|
|
36
|
-
"benchmarkGatePassed": true,
|
|
37
|
-
"intelligencePassed": true,
|
|
38
|
-
"reliabilityPassed": true,
|
|
39
|
-
"reliabilityRiskLevel": "monitor"
|
|
40
|
-
},
|
|
41
|
-
{
|
|
42
|
-
"snapshotIndex": 2,
|
|
43
|
-
"generatedAt": "2026-04-17T02:54:57.419Z",
|
|
44
|
-
"releaseVersion": "2.0.26",
|
|
45
|
-
"top1Accuracy": 0.9167,
|
|
46
|
-
"manualCorrectionRate": 0.0833,
|
|
47
|
-
"incorrectDetectionRate": 0.0833,
|
|
48
|
-
"lowConfidenceRate": 0.0833,
|
|
49
|
-
"staleWatchlistCount": 0,
|
|
50
|
-
"vulnerabilityTotal": null,
|
|
51
|
-
"criticalVulnerabilityCount": null,
|
|
52
|
-
"benchmarkGatePassed": true,
|
|
53
|
-
"intelligencePassed": true,
|
|
54
|
-
"reliabilityPassed": true,
|
|
55
|
-
"reliabilityRiskLevel": "monitor"
|
|
56
|
-
},
|
|
57
|
-
{
|
|
58
|
-
"snapshotIndex": 3,
|
|
59
|
-
"generatedAt": "2026-04-17T03:19:31.047Z",
|
|
60
|
-
"releaseVersion": "2.0.26",
|
|
61
|
-
"top1Accuracy": 0.9167,
|
|
62
|
-
"manualCorrectionRate": 0.0833,
|
|
63
|
-
"incorrectDetectionRate": 0.0833,
|
|
64
|
-
"lowConfidenceRate": 0.0833,
|
|
65
|
-
"staleWatchlistCount": 0,
|
|
66
|
-
"vulnerabilityTotal": null,
|
|
67
|
-
"criticalVulnerabilityCount": null,
|
|
68
|
-
"benchmarkGatePassed": true,
|
|
69
|
-
"intelligencePassed": true,
|
|
70
|
-
"reliabilityPassed": true,
|
|
71
|
-
"reliabilityRiskLevel": "monitor"
|
|
72
|
-
},
|
|
73
|
-
{
|
|
74
|
-
"snapshotIndex": 4,
|
|
75
|
-
"generatedAt": "2026-04-17T03:20:15.400Z",
|
|
76
|
-
"releaseVersion": "2.0.26",
|
|
77
|
-
"top1Accuracy": 0.9167,
|
|
78
|
-
"manualCorrectionRate": 0.0833,
|
|
79
|
-
"incorrectDetectionRate": 0.0833,
|
|
80
|
-
"lowConfidenceRate": 0.0833,
|
|
81
|
-
"staleWatchlistCount": 0,
|
|
82
|
-
"vulnerabilityTotal": null,
|
|
83
|
-
"criticalVulnerabilityCount": null,
|
|
84
|
-
"benchmarkGatePassed": true,
|
|
85
|
-
"intelligencePassed": true,
|
|
86
|
-
"reliabilityPassed": true,
|
|
87
|
-
"reliabilityRiskLevel": "monitor"
|
|
88
|
-
}
|
|
89
|
-
],
|
|
90
|
-
"chartSeries": {
|
|
91
|
-
"generatedAt": [
|
|
92
|
-
"2026-04-17T02:54:01.239Z",
|
|
93
|
-
"2026-04-17T02:54:57.419Z",
|
|
94
|
-
"2026-04-17T03:19:31.047Z",
|
|
95
|
-
"2026-04-17T03:20:15.400Z"
|
|
96
|
-
],
|
|
97
|
-
"top1Accuracy": [
|
|
98
|
-
0.9167,
|
|
99
|
-
0.9167,
|
|
100
|
-
0.9167,
|
|
101
|
-
0.9167
|
|
102
|
-
],
|
|
103
|
-
"manualCorrectionRate": [
|
|
104
|
-
0.0833,
|
|
105
|
-
0.0833,
|
|
106
|
-
0.0833,
|
|
107
|
-
0.0833
|
|
108
|
-
],
|
|
109
|
-
"incorrectDetectionRate": [
|
|
110
|
-
0.0833,
|
|
111
|
-
0.0833,
|
|
112
|
-
0.0833,
|
|
113
|
-
0.0833
|
|
114
|
-
],
|
|
115
|
-
"lowConfidenceRate": [
|
|
116
|
-
0.0833,
|
|
117
|
-
0.0833,
|
|
118
|
-
0.0833,
|
|
119
|
-
0.0833
|
|
120
|
-
],
|
|
121
|
-
"staleWatchlistCount": [
|
|
122
|
-
0,
|
|
123
|
-
0,
|
|
124
|
-
0,
|
|
125
|
-
0
|
|
126
|
-
],
|
|
127
|
-
"vulnerabilityTotal": [
|
|
128
|
-
null,
|
|
129
|
-
null,
|
|
130
|
-
null,
|
|
131
|
-
null
|
|
132
|
-
]
|
|
133
|
-
},
|
|
134
|
-
"artifacts": {
|
|
135
|
-
"historyPath": ".agent-context/state/benchmark-history.json",
|
|
136
|
-
"jsonPath": ".agent-context/state/benchmark-trend-report.json",
|
|
137
|
-
"csvPath": ".agent-context/state/benchmark-trend-report.csv",
|
|
138
|
-
"writeMode": "stdout-and-file"
|
|
139
|
-
}
|
|
140
|
-
}
|
|
@@ -1,462 +0,0 @@
|
|
|
1
|
-
{
|
|
2
|
-
"generatedAt": "2026-04-14T06:57:14.623Z",
|
|
3
|
-
"reportName": "benchmark-writer-judge-matrix",
|
|
4
|
-
"phase": "v2.5.1",
|
|
5
|
-
"passed": true,
|
|
6
|
-
"failureCount": 0,
|
|
7
|
-
"methodology": {
|
|
8
|
-
"blindReviewMode": true,
|
|
9
|
-
"writerLaneModelCount": 3,
|
|
10
|
-
"judgeLaneModelCount": 2,
|
|
11
|
-
"scenarioCount": 4,
|
|
12
|
-
"writerWeights": {
|
|
13
|
-
"quality": 40,
|
|
14
|
-
"efficiency": 20,
|
|
15
|
-
"reliability": 25,
|
|
16
|
-
"freshness": 15
|
|
17
|
-
},
|
|
18
|
-
"judgeWeights": {
|
|
19
|
-
"clarity": 35,
|
|
20
|
-
"correctness": 35,
|
|
21
|
-
"risk": 20,
|
|
22
|
-
"consistency": 10
|
|
23
|
-
}
|
|
24
|
-
},
|
|
25
|
-
"coreSignals": {
|
|
26
|
-
"top1Accuracy": 0.9167,
|
|
27
|
-
"manualCorrectionRate": 0.0833,
|
|
28
|
-
"nativeSavingsPercent": 81.52,
|
|
29
|
-
"benchmarkGatePassed": true,
|
|
30
|
-
"benchmarkGateFailureCount": 0,
|
|
31
|
-
"intelligenceFailureCount": 0,
|
|
32
|
-
"staleWatchlistCount": 0,
|
|
33
|
-
"top1AccuracyMet": true,
|
|
34
|
-
"manualCorrectionMet": true
|
|
35
|
-
},
|
|
36
|
-
"writerDirectory": [
|
|
37
|
-
{
|
|
38
|
-
"writerToken": "W1",
|
|
39
|
-
"writerModel": {
|
|
40
|
-
"id": "writer-copilot-balanced",
|
|
41
|
-
"provider": "github-copilot",
|
|
42
|
-
"profile": "balanced"
|
|
43
|
-
},
|
|
44
|
-
"averageCompositeScore": 93.7
|
|
45
|
-
},
|
|
46
|
-
{
|
|
47
|
-
"writerToken": "W2",
|
|
48
|
-
"writerModel": {
|
|
49
|
-
"id": "writer-claude-architect",
|
|
50
|
-
"provider": "anthropic",
|
|
51
|
-
"profile": "architect"
|
|
52
|
-
},
|
|
53
|
-
"averageCompositeScore": 92.8
|
|
54
|
-
},
|
|
55
|
-
{
|
|
56
|
-
"writerToken": "W3",
|
|
57
|
-
"writerModel": {
|
|
58
|
-
"id": "writer-gemini-ops",
|
|
59
|
-
"provider": "google",
|
|
60
|
-
"profile": "operations"
|
|
61
|
-
},
|
|
62
|
-
"averageCompositeScore": 92.65
|
|
63
|
-
}
|
|
64
|
-
],
|
|
65
|
-
"comparisonMatrix": [
|
|
66
|
-
{
|
|
67
|
-
"scenarioId": "planning",
|
|
68
|
-
"scenarioCategory": "planning",
|
|
69
|
-
"writerToken": "W1",
|
|
70
|
-
"writerModelId": null,
|
|
71
|
-
"judgeModelId": "judge-claude-audit",
|
|
72
|
-
"blindPairId": "planning:W1:judge-claude-audit",
|
|
73
|
-
"writerCompositeScore": 92.12,
|
|
74
|
-
"judgeCompositeScore": 94.12,
|
|
75
|
-
"scoreThreshold": 75,
|
|
76
|
-
"leniencyWindow": 2,
|
|
77
|
-
"meetsScoreThreshold": true,
|
|
78
|
-
"meetsCoreSignals": true,
|
|
79
|
-
"verdict": "pass"
|
|
80
|
-
},
|
|
81
|
-
{
|
|
82
|
-
"scenarioId": "planning",
|
|
83
|
-
"scenarioCategory": "planning",
|
|
84
|
-
"writerToken": "W1",
|
|
85
|
-
"writerModelId": null,
|
|
86
|
-
"judgeModelId": "judge-gpt-risk",
|
|
87
|
-
"blindPairId": "planning:W1:judge-gpt-risk",
|
|
88
|
-
"writerCompositeScore": 92.12,
|
|
89
|
-
"judgeCompositeScore": 94.12,
|
|
90
|
-
"scoreThreshold": 75,
|
|
91
|
-
"leniencyWindow": 2,
|
|
92
|
-
"meetsScoreThreshold": true,
|
|
93
|
-
"meetsCoreSignals": true,
|
|
94
|
-
"verdict": "pass"
|
|
95
|
-
},
|
|
96
|
-
{
|
|
97
|
-
"scenarioId": "refactor",
|
|
98
|
-
"scenarioCategory": "refactor",
|
|
99
|
-
"writerToken": "W1",
|
|
100
|
-
"writerModelId": null,
|
|
101
|
-
"judgeModelId": "judge-claude-audit",
|
|
102
|
-
"blindPairId": "refactor:W1:judge-claude-audit",
|
|
103
|
-
"writerCompositeScore": 95.26,
|
|
104
|
-
"judgeCompositeScore": 93.26,
|
|
105
|
-
"scoreThreshold": 75,
|
|
106
|
-
"leniencyWindow": 2,
|
|
107
|
-
"meetsScoreThreshold": true,
|
|
108
|
-
"meetsCoreSignals": true,
|
|
109
|
-
"verdict": "pass"
|
|
110
|
-
},
|
|
111
|
-
{
|
|
112
|
-
"scenarioId": "refactor",
|
|
113
|
-
"scenarioCategory": "refactor",
|
|
114
|
-
"writerToken": "W1",
|
|
115
|
-
"writerModelId": null,
|
|
116
|
-
"judgeModelId": "judge-gpt-risk",
|
|
117
|
-
"blindPairId": "refactor:W1:judge-gpt-risk",
|
|
118
|
-
"writerCompositeScore": 95.26,
|
|
119
|
-
"judgeCompositeScore": 93.26,
|
|
120
|
-
"scoreThreshold": 75,
|
|
121
|
-
"leniencyWindow": 2,
|
|
122
|
-
"meetsScoreThreshold": true,
|
|
123
|
-
"meetsCoreSignals": true,
|
|
124
|
-
"verdict": "pass"
|
|
125
|
-
},
|
|
126
|
-
{
|
|
127
|
-
"scenarioId": "security",
|
|
128
|
-
"scenarioCategory": "security",
|
|
129
|
-
"writerToken": "W1",
|
|
130
|
-
"writerModelId": null,
|
|
131
|
-
"judgeModelId": "judge-claude-audit",
|
|
132
|
-
"blindPairId": "security:W1:judge-claude-audit",
|
|
133
|
-
"writerCompositeScore": 94.42,
|
|
134
|
-
"judgeCompositeScore": 92.42,
|
|
135
|
-
"scoreThreshold": 75,
|
|
136
|
-
"leniencyWindow": 2,
|
|
137
|
-
"meetsScoreThreshold": true,
|
|
138
|
-
"meetsCoreSignals": true,
|
|
139
|
-
"verdict": "pass"
|
|
140
|
-
},
|
|
141
|
-
{
|
|
142
|
-
"scenarioId": "security",
|
|
143
|
-
"scenarioCategory": "security",
|
|
144
|
-
"writerToken": "W1",
|
|
145
|
-
"writerModelId": null,
|
|
146
|
-
"judgeModelId": "judge-gpt-risk",
|
|
147
|
-
"blindPairId": "security:W1:judge-gpt-risk",
|
|
148
|
-
"writerCompositeScore": 94.42,
|
|
149
|
-
"judgeCompositeScore": 93.42,
|
|
150
|
-
"scoreThreshold": 75,
|
|
151
|
-
"leniencyWindow": 2,
|
|
152
|
-
"meetsScoreThreshold": true,
|
|
153
|
-
"meetsCoreSignals": true,
|
|
154
|
-
"verdict": "pass"
|
|
155
|
-
},
|
|
156
|
-
{
|
|
157
|
-
"scenarioId": "delivery",
|
|
158
|
-
"scenarioCategory": "delivery",
|
|
159
|
-
"writerToken": "W1",
|
|
160
|
-
"writerModelId": null,
|
|
161
|
-
"judgeModelId": "judge-claude-audit",
|
|
162
|
-
"blindPairId": "delivery:W1:judge-claude-audit",
|
|
163
|
-
"writerCompositeScore": 92.99,
|
|
164
|
-
"judgeCompositeScore": 93.99,
|
|
165
|
-
"scoreThreshold": 75,
|
|
166
|
-
"leniencyWindow": 2,
|
|
167
|
-
"meetsScoreThreshold": true,
|
|
168
|
-
"meetsCoreSignals": true,
|
|
169
|
-
"verdict": "pass"
|
|
170
|
-
},
|
|
171
|
-
{
|
|
172
|
-
"scenarioId": "delivery",
|
|
173
|
-
"scenarioCategory": "delivery",
|
|
174
|
-
"writerToken": "W1",
|
|
175
|
-
"writerModelId": null,
|
|
176
|
-
"judgeModelId": "judge-gpt-risk",
|
|
177
|
-
"blindPairId": "delivery:W1:judge-gpt-risk",
|
|
178
|
-
"writerCompositeScore": 92.99,
|
|
179
|
-
"judgeCompositeScore": 92.99,
|
|
180
|
-
"scoreThreshold": 75,
|
|
181
|
-
"leniencyWindow": 2,
|
|
182
|
-
"meetsScoreThreshold": true,
|
|
183
|
-
"meetsCoreSignals": true,
|
|
184
|
-
"verdict": "pass"
|
|
185
|
-
},
|
|
186
|
-
{
|
|
187
|
-
"scenarioId": "planning",
|
|
188
|
-
"scenarioCategory": "planning",
|
|
189
|
-
"writerToken": "W2",
|
|
190
|
-
"writerModelId": null,
|
|
191
|
-
"judgeModelId": "judge-claude-audit",
|
|
192
|
-
"blindPairId": "planning:W2:judge-claude-audit",
|
|
193
|
-
"writerCompositeScore": 93.12,
|
|
194
|
-
"judgeCompositeScore": 94.12,
|
|
195
|
-
"scoreThreshold": 75,
|
|
196
|
-
"leniencyWindow": 2,
|
|
197
|
-
"meetsScoreThreshold": true,
|
|
198
|
-
"meetsCoreSignals": true,
|
|
199
|
-
"verdict": "pass"
|
|
200
|
-
},
|
|
201
|
-
{
|
|
202
|
-
"scenarioId": "planning",
|
|
203
|
-
"scenarioCategory": "planning",
|
|
204
|
-
"writerToken": "W2",
|
|
205
|
-
"writerModelId": null,
|
|
206
|
-
"judgeModelId": "judge-gpt-risk",
|
|
207
|
-
"blindPairId": "planning:W2:judge-gpt-risk",
|
|
208
|
-
"writerCompositeScore": 93.12,
|
|
209
|
-
"judgeCompositeScore": 94.12,
|
|
210
|
-
"scoreThreshold": 75,
|
|
211
|
-
"leniencyWindow": 2,
|
|
212
|
-
"meetsScoreThreshold": true,
|
|
213
|
-
"meetsCoreSignals": true,
|
|
214
|
-
"verdict": "pass"
|
|
215
|
-
},
|
|
216
|
-
{
|
|
217
|
-
"scenarioId": "refactor",
|
|
218
|
-
"scenarioCategory": "refactor",
|
|
219
|
-
"writerToken": "W2",
|
|
220
|
-
"writerModelId": null,
|
|
221
|
-
"judgeModelId": "judge-claude-audit",
|
|
222
|
-
"blindPairId": "refactor:W2:judge-claude-audit",
|
|
223
|
-
"writerCompositeScore": 93.06,
|
|
224
|
-
"judgeCompositeScore": 95.06,
|
|
225
|
-
"scoreThreshold": 75,
|
|
226
|
-
"leniencyWindow": 2,
|
|
227
|
-
"meetsScoreThreshold": true,
|
|
228
|
-
"meetsCoreSignals": true,
|
|
229
|
-
"verdict": "pass"
|
|
230
|
-
},
|
|
231
|
-
{
|
|
232
|
-
"scenarioId": "refactor",
|
|
233
|
-
"scenarioCategory": "refactor",
|
|
234
|
-
"writerToken": "W2",
|
|
235
|
-
"writerModelId": null,
|
|
236
|
-
"judgeModelId": "judge-gpt-risk",
|
|
237
|
-
"blindPairId": "refactor:W2:judge-gpt-risk",
|
|
238
|
-
"writerCompositeScore": 93.06,
|
|
239
|
-
"judgeCompositeScore": 95.06,
|
|
240
|
-
"scoreThreshold": 75,
|
|
241
|
-
"leniencyWindow": 2,
|
|
242
|
-
"meetsScoreThreshold": true,
|
|
243
|
-
"meetsCoreSignals": true,
|
|
244
|
-
"verdict": "pass"
|
|
245
|
-
},
|
|
246
|
-
{
|
|
247
|
-
"scenarioId": "security",
|
|
248
|
-
"scenarioCategory": "security",
|
|
249
|
-
"writerToken": "W2",
|
|
250
|
-
"writerModelId": null,
|
|
251
|
-
"judgeModelId": "judge-claude-audit",
|
|
252
|
-
"blindPairId": "security:W2:judge-claude-audit",
|
|
253
|
-
"writerCompositeScore": 91.82,
|
|
254
|
-
"judgeCompositeScore": 90.82,
|
|
255
|
-
"scoreThreshold": 75,
|
|
256
|
-
"leniencyWindow": 2,
|
|
257
|
-
"meetsScoreThreshold": true,
|
|
258
|
-
"meetsCoreSignals": true,
|
|
259
|
-
"verdict": "pass"
|
|
260
|
-
},
|
|
261
|
-
{
|
|
262
|
-
"scenarioId": "security",
|
|
263
|
-
"scenarioCategory": "security",
|
|
264
|
-
"writerToken": "W2",
|
|
265
|
-
"writerModelId": null,
|
|
266
|
-
"judgeModelId": "judge-gpt-risk",
|
|
267
|
-
"blindPairId": "security:W2:judge-gpt-risk",
|
|
268
|
-
"writerCompositeScore": 91.82,
|
|
269
|
-
"judgeCompositeScore": 89.82,
|
|
270
|
-
"scoreThreshold": 75,
|
|
271
|
-
"leniencyWindow": 2,
|
|
272
|
-
"meetsScoreThreshold": true,
|
|
273
|
-
"meetsCoreSignals": true,
|
|
274
|
-
"verdict": "pass"
|
|
275
|
-
},
|
|
276
|
-
{
|
|
277
|
-
"scenarioId": "delivery",
|
|
278
|
-
"scenarioCategory": "delivery",
|
|
279
|
-
"writerToken": "W2",
|
|
280
|
-
"writerModelId": null,
|
|
281
|
-
"judgeModelId": "judge-claude-audit",
|
|
282
|
-
"blindPairId": "delivery:W2:judge-claude-audit",
|
|
283
|
-
"writerCompositeScore": 93.19,
|
|
284
|
-
"judgeCompositeScore": 93.19,
|
|
285
|
-
"scoreThreshold": 75,
|
|
286
|
-
"leniencyWindow": 2,
|
|
287
|
-
"meetsScoreThreshold": true,
|
|
288
|
-
"meetsCoreSignals": true,
|
|
289
|
-
"verdict": "pass"
|
|
290
|
-
},
|
|
291
|
-
{
|
|
292
|
-
"scenarioId": "delivery",
|
|
293
|
-
"scenarioCategory": "delivery",
|
|
294
|
-
"writerToken": "W2",
|
|
295
|
-
"writerModelId": null,
|
|
296
|
-
"judgeModelId": "judge-gpt-risk",
|
|
297
|
-
"blindPairId": "delivery:W2:judge-gpt-risk",
|
|
298
|
-
"writerCompositeScore": 93.19,
|
|
299
|
-
"judgeCompositeScore": 94.19,
|
|
300
|
-
"scoreThreshold": 75,
|
|
301
|
-
"leniencyWindow": 2,
|
|
302
|
-
"meetsScoreThreshold": true,
|
|
303
|
-
"meetsCoreSignals": true,
|
|
304
|
-
"verdict": "pass"
|
|
305
|
-
},
|
|
306
|
-
{
|
|
307
|
-
"scenarioId": "planning",
|
|
308
|
-
"scenarioCategory": "planning",
|
|
309
|
-
"writerToken": "W3",
|
|
310
|
-
"writerModelId": null,
|
|
311
|
-
"judgeModelId": "judge-claude-audit",
|
|
312
|
-
"blindPairId": "planning:W3:judge-claude-audit",
|
|
313
|
-
"writerCompositeScore": 93.27,
|
|
314
|
-
"judgeCompositeScore": 93.27,
|
|
315
|
-
"scoreThreshold": 75,
|
|
316
|
-
"leniencyWindow": 2,
|
|
317
|
-
"meetsScoreThreshold": true,
|
|
318
|
-
"meetsCoreSignals": true,
|
|
319
|
-
"verdict": "pass"
|
|
320
|
-
},
|
|
321
|
-
{
|
|
322
|
-
"scenarioId": "planning",
|
|
323
|
-
"scenarioCategory": "planning",
|
|
324
|
-
"writerToken": "W3",
|
|
325
|
-
"writerModelId": null,
|
|
326
|
-
"judgeModelId": "judge-gpt-risk",
|
|
327
|
-
"blindPairId": "planning:W3:judge-gpt-risk",
|
|
328
|
-
"writerCompositeScore": 93.27,
|
|
329
|
-
"judgeCompositeScore": 93.27,
|
|
330
|
-
"scoreThreshold": 75,
|
|
331
|
-
"leniencyWindow": 2,
|
|
332
|
-
"meetsScoreThreshold": true,
|
|
333
|
-
"meetsCoreSignals": true,
|
|
334
|
-
"verdict": "pass"
|
|
335
|
-
},
|
|
336
|
-
{
|
|
337
|
-
"scenarioId": "refactor",
|
|
338
|
-
"scenarioCategory": "refactor",
|
|
339
|
-
"writerToken": "W3",
|
|
340
|
-
"writerModelId": null,
|
|
341
|
-
"judgeModelId": "judge-claude-audit",
|
|
342
|
-
"blindPairId": "refactor:W3:judge-claude-audit",
|
|
343
|
-
"writerCompositeScore": 94.01,
|
|
344
|
-
"judgeCompositeScore": 95.01,
|
|
345
|
-
"scoreThreshold": 75,
|
|
346
|
-
"leniencyWindow": 2,
|
|
347
|
-
"meetsScoreThreshold": true,
|
|
348
|
-
"meetsCoreSignals": true,
|
|
349
|
-
"verdict": "pass"
|
|
350
|
-
},
|
|
351
|
-
{
|
|
352
|
-
"scenarioId": "refactor",
|
|
353
|
-
"scenarioCategory": "refactor",
|
|
354
|
-
"writerToken": "W3",
|
|
355
|
-
"writerModelId": null,
|
|
356
|
-
"judgeModelId": "judge-gpt-risk",
|
|
357
|
-
"blindPairId": "refactor:W3:judge-gpt-risk",
|
|
358
|
-
"writerCompositeScore": 94.01,
|
|
359
|
-
"judgeCompositeScore": 95.01,
|
|
360
|
-
"scoreThreshold": 75,
|
|
361
|
-
"leniencyWindow": 2,
|
|
362
|
-
"meetsScoreThreshold": true,
|
|
363
|
-
"meetsCoreSignals": true,
|
|
364
|
-
"verdict": "pass"
|
|
365
|
-
},
|
|
366
|
-
{
|
|
367
|
-
"scenarioId": "security",
|
|
368
|
-
"scenarioCategory": "security",
|
|
369
|
-
"writerToken": "W3",
|
|
370
|
-
"writerModelId": null,
|
|
371
|
-
"judgeModelId": "judge-claude-audit",
|
|
372
|
-
"blindPairId": "security:W3:judge-claude-audit",
|
|
373
|
-
"writerCompositeScore": 92.37,
|
|
374
|
-
"judgeCompositeScore": 92.37,
|
|
375
|
-
"scoreThreshold": 75,
|
|
376
|
-
"leniencyWindow": 2,
|
|
377
|
-
"meetsScoreThreshold": true,
|
|
378
|
-
"meetsCoreSignals": true,
|
|
379
|
-
"verdict": "pass"
|
|
380
|
-
},
|
|
381
|
-
{
|
|
382
|
-
"scenarioId": "security",
|
|
383
|
-
"scenarioCategory": "security",
|
|
384
|
-
"writerToken": "W3",
|
|
385
|
-
"writerModelId": null,
|
|
386
|
-
"judgeModelId": "judge-gpt-risk",
|
|
387
|
-
"blindPairId": "security:W3:judge-gpt-risk",
|
|
388
|
-
"writerCompositeScore": 92.37,
|
|
389
|
-
"judgeCompositeScore": 94.37,
|
|
390
|
-
"scoreThreshold": 75,
|
|
391
|
-
"leniencyWindow": 2,
|
|
392
|
-
"meetsScoreThreshold": true,
|
|
393
|
-
"meetsCoreSignals": true,
|
|
394
|
-
"verdict": "pass"
|
|
395
|
-
},
|
|
396
|
-
{
|
|
397
|
-
"scenarioId": "delivery",
|
|
398
|
-
"scenarioCategory": "delivery",
|
|
399
|
-
"writerToken": "W3",
|
|
400
|
-
"writerModelId": null,
|
|
401
|
-
"judgeModelId": "judge-claude-audit",
|
|
402
|
-
"blindPairId": "delivery:W3:judge-claude-audit",
|
|
403
|
-
"writerCompositeScore": 90.94,
|
|
404
|
-
"judgeCompositeScore": 89.94,
|
|
405
|
-
"scoreThreshold": 75,
|
|
406
|
-
"leniencyWindow": 2,
|
|
407
|
-
"meetsScoreThreshold": true,
|
|
408
|
-
"meetsCoreSignals": true,
|
|
409
|
-
"verdict": "pass"
|
|
410
|
-
},
|
|
411
|
-
{
|
|
412
|
-
"scenarioId": "delivery",
|
|
413
|
-
"scenarioCategory": "delivery",
|
|
414
|
-
"writerToken": "W3",
|
|
415
|
-
"writerModelId": null,
|
|
416
|
-
"judgeModelId": "judge-gpt-risk",
|
|
417
|
-
"blindPairId": "delivery:W3:judge-gpt-risk",
|
|
418
|
-
"writerCompositeScore": 90.94,
|
|
419
|
-
"judgeCompositeScore": 92.94,
|
|
420
|
-
"scoreThreshold": 75,
|
|
421
|
-
"leniencyWindow": 2,
|
|
422
|
-
"meetsScoreThreshold": true,
|
|
423
|
-
"meetsCoreSignals": true,
|
|
424
|
-
"verdict": "pass"
|
|
425
|
-
}
|
|
426
|
-
],
|
|
427
|
-
"summary": {
|
|
428
|
-
"passCount": 24,
|
|
429
|
-
"failCount": 0,
|
|
430
|
-
"passRatePercent": 100
|
|
431
|
-
},
|
|
432
|
-
"executions": [
|
|
433
|
-
{
|
|
434
|
-
"scriptPath": "scripts/detection-benchmark.mjs",
|
|
435
|
-
"exitCode": 0,
|
|
436
|
-
"parseError": null,
|
|
437
|
-
"reportName": null,
|
|
438
|
-
"passed": null
|
|
439
|
-
},
|
|
440
|
-
{
|
|
441
|
-
"scriptPath": "scripts/token-optimization-benchmark.mjs",
|
|
442
|
-
"exitCode": 0,
|
|
443
|
-
"parseError": null,
|
|
444
|
-
"reportName": "token-optimization-benchmark",
|
|
445
|
-
"passed": null
|
|
446
|
-
},
|
|
447
|
-
{
|
|
448
|
-
"scriptPath": "scripts/benchmark-gate.mjs",
|
|
449
|
-
"exitCode": 0,
|
|
450
|
-
"parseError": null,
|
|
451
|
-
"reportName": "benchmark-gate",
|
|
452
|
-
"passed": true
|
|
453
|
-
},
|
|
454
|
-
{
|
|
455
|
-
"scriptPath": "scripts/benchmark-intelligence.mjs",
|
|
456
|
-
"exitCode": 0,
|
|
457
|
-
"parseError": null,
|
|
458
|
-
"reportName": "benchmark-intelligence",
|
|
459
|
-
"passed": true
|
|
460
|
-
}
|
|
461
|
-
]
|
|
462
|
-
}
|