audrey 1.0.0 → 1.0.1
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/CHANGELOG.md +24 -0
- package/README.md +27 -5
- package/benchmarks/guardbench.js +98 -8
- package/benchmarks/output/adapter-self-test/guardbench-adapter-self-test.json +7 -7
- package/benchmarks/output/external/guardbench-external-dry-run.json +1 -1
- package/benchmarks/output/external/guardbench-external-evidence.json +1 -1
- package/benchmarks/output/guardbench-conformance-card.json +12 -12
- package/benchmarks/output/guardbench-raw.json +240 -140
- package/benchmarks/output/guardbench-summary.json +350 -224
- package/benchmarks/output/leaderboard/guardbench-leaderboard.json +5 -5
- package/benchmarks/output/leaderboard/guardbench-leaderboard.md +2 -2
- package/benchmarks/output/submission-bundle/guardbench-conformance-card.json +12 -12
- package/benchmarks/output/submission-bundle/guardbench-raw.json +240 -140
- package/benchmarks/output/submission-bundle/guardbench-summary.json +350 -224
- package/benchmarks/output/submission-bundle/schemas/guardbench-raw.schema.json +21 -1
- package/benchmarks/output/submission-bundle/schemas/guardbench-summary.schema.json +23 -2
- package/benchmarks/output/submission-bundle/submission-manifest.json +14 -14
- package/benchmarks/output/submission-bundle/validation-report.json +1 -1
- package/benchmarks/output/summary.json +56 -56
- package/benchmarks/schemas/guardbench-raw.schema.json +21 -1
- package/benchmarks/schemas/guardbench-summary.schema.json +23 -2
- package/dist/mcp-server/config.d.ts +1 -1
- package/dist/mcp-server/config.js +1 -1
- package/dist/src/audrey.d.ts +10 -0
- package/dist/src/audrey.d.ts.map +1 -1
- package/dist/src/audrey.js +17 -4
- package/dist/src/audrey.js.map +1 -1
- package/dist/src/controller.d.ts +17 -1
- package/dist/src/controller.d.ts.map +1 -1
- package/dist/src/controller.js +52 -13
- package/dist/src/controller.js.map +1 -1
- package/dist/src/index.d.ts +2 -1
- package/dist/src/index.d.ts.map +1 -1
- package/dist/src/index.js +1 -1
- package/dist/src/index.js.map +1 -1
- package/dist/src/routes.d.ts.map +1 -1
- package/dist/src/routes.js +4 -1
- package/dist/src/routes.js.map +1 -1
- package/docs/paper/07-evaluation.md +4 -4
- package/docs/paper/audrey-paper-v1.md +5 -5
- package/docs/paper/evidence-ledger.md +1 -1
- package/docs/paper/output/arxiv/arxiv-manifest.json +4 -4
- package/docs/paper/output/arxiv/main.tex +5 -5
- package/docs/paper/output/arxiv-compile-report.json +3 -3
- package/docs/paper/output/submission-bundle/README.md +27 -5
- package/docs/paper/output/submission-bundle/benchmarks/output/adapter-self-test/guardbench-adapter-self-test.json +7 -7
- package/docs/paper/output/submission-bundle/benchmarks/output/external/guardbench-external-dry-run.json +1 -1
- package/docs/paper/output/submission-bundle/benchmarks/output/external/guardbench-external-evidence.json +1 -1
- package/docs/paper/output/submission-bundle/benchmarks/output/guardbench-conformance-card.json +12 -12
- package/docs/paper/output/submission-bundle/benchmarks/output/guardbench-raw.json +240 -140
- package/docs/paper/output/submission-bundle/benchmarks/output/guardbench-summary.json +350 -224
- package/docs/paper/output/submission-bundle/benchmarks/output/leaderboard/guardbench-leaderboard.json +5 -5
- package/docs/paper/output/submission-bundle/benchmarks/output/leaderboard/guardbench-leaderboard.md +2 -2
- package/docs/paper/output/submission-bundle/benchmarks/output/submission-bundle/submission-manifest.json +14 -14
- package/docs/paper/output/submission-bundle/benchmarks/output/submission-bundle/validation-report.json +1 -1
- package/docs/paper/output/submission-bundle/benchmarks/output/summary.json +67 -67
- package/docs/paper/output/submission-bundle/benchmarks/schemas/guardbench-raw.schema.json +21 -1
- package/docs/paper/output/submission-bundle/benchmarks/schemas/guardbench-summary.schema.json +23 -2
- package/docs/paper/output/submission-bundle/docs/paper/07-evaluation.md +4 -4
- package/docs/paper/output/submission-bundle/docs/paper/audrey-paper-v1.md +5 -5
- package/docs/paper/output/submission-bundle/docs/paper/evidence-ledger.md +1 -1
- package/docs/paper/output/submission-bundle/docs/paper/output/arxiv/arxiv-manifest.json +4 -4
- package/docs/paper/output/submission-bundle/docs/paper/output/arxiv/main.tex +5 -5
- package/docs/paper/output/submission-bundle/docs/paper/output/arxiv-compile-report.json +3 -3
- package/docs/paper/output/submission-bundle/package.json +2 -2
- package/docs/paper/output/submission-bundle/paper-submission-manifest.json +35 -35
- package/package.json +2 -2
- package/scripts/smoke-cli.js +22 -2
- package/scripts/verify-release-readiness.mjs +50 -6
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
{
|
|
2
2
|
"schemaVersion": "1.0.0",
|
|
3
3
|
"suite": "GuardBench leaderboard",
|
|
4
|
-
"generatedAt": "2026-05-
|
|
4
|
+
"generatedAt": "2026-05-15T17:52:13.304Z",
|
|
5
5
|
"ranking": [
|
|
6
6
|
"verified bundle",
|
|
7
7
|
"adapter conformance",
|
|
@@ -28,9 +28,9 @@
|
|
|
28
28
|
"evidenceRecall": 1,
|
|
29
29
|
"redactionLeaks": 0,
|
|
30
30
|
"latency": {
|
|
31
|
-
"p50Ms":
|
|
32
|
-
"p95Ms":
|
|
33
|
-
"maxMs":
|
|
31
|
+
"p50Ms": 2.465,
|
|
32
|
+
"p95Ms": 30.791,
|
|
33
|
+
"maxMs": 30.791
|
|
34
34
|
}
|
|
35
35
|
},
|
|
36
36
|
"conformance": {
|
|
@@ -41,7 +41,7 @@
|
|
|
41
41
|
},
|
|
42
42
|
"source": {
|
|
43
43
|
"dir": "benchmarks/output/submission-bundle",
|
|
44
|
-
"manifestGeneratedAt": "2026-05-
|
|
44
|
+
"manifestGeneratedAt": "2026-05-15T17:52:13.050Z",
|
|
45
45
|
"fileCount": 17
|
|
46
46
|
},
|
|
47
47
|
"verification": {
|
package/docs/paper/output/submission-bundle/benchmarks/output/leaderboard/guardbench-leaderboard.md
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
# GuardBench Leaderboard
|
|
2
2
|
|
|
3
|
-
Generated: 2026-05-
|
|
3
|
+
Generated: 2026-05-15T17:52:13.304Z
|
|
4
4
|
|
|
5
5
|
| Rank | Subject | Verified | Conformant | Full Contract | Decision Accuracy | Evidence Recall | Redaction Leaks | p95 Latency | Bundle |
|
|
6
6
|
|---:|---|---:|---:|---:|---:|---:|---:|---:|---|
|
|
7
|
-
| 1 | Audrey Guard | yes | yes | 100.0% | 100.0% | 100.0% | 0 |
|
|
7
|
+
| 1 | Audrey Guard | yes | yes | 100.0% | 100.0% | 100.0% | 0 | 30.791ms | benchmarks/output/submission-bundle |
|
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
{
|
|
2
2
|
"schemaVersion": "1.0.0",
|
|
3
3
|
"suite": "GuardBench submission bundle",
|
|
4
|
-
"generatedAt": "2026-05-
|
|
4
|
+
"generatedAt": "2026-05-15T17:52:13.050Z",
|
|
5
5
|
"sourceDir": "benchmarks/output",
|
|
6
6
|
"subject": {
|
|
7
7
|
"name": "Audrey Guard",
|
|
@@ -16,9 +16,9 @@
|
|
|
16
16
|
"evidenceRecall": 1,
|
|
17
17
|
"redactionLeaks": 0,
|
|
18
18
|
"latency": {
|
|
19
|
-
"p50Ms":
|
|
20
|
-
"p95Ms":
|
|
21
|
-
"maxMs":
|
|
19
|
+
"p50Ms": 2.465,
|
|
20
|
+
"p95Ms": 30.791,
|
|
21
|
+
"maxMs": 30.791
|
|
22
22
|
}
|
|
23
23
|
},
|
|
24
24
|
"conformance": {
|
|
@@ -45,7 +45,7 @@
|
|
|
45
45
|
{
|
|
46
46
|
"path": "guardbench-conformance-card.json",
|
|
47
47
|
"bytes": 1735,
|
|
48
|
-
"sha256": "
|
|
48
|
+
"sha256": "65d4a10afe10178e4e4e3d508e0e06ce5a4b28713debc27cf4d9b60a46050d2f"
|
|
49
49
|
},
|
|
50
50
|
{
|
|
51
51
|
"path": "guardbench-manifest.json",
|
|
@@ -54,13 +54,13 @@
|
|
|
54
54
|
},
|
|
55
55
|
{
|
|
56
56
|
"path": "guardbench-raw.json",
|
|
57
|
-
"bytes":
|
|
58
|
-
"sha256": "
|
|
57
|
+
"bytes": 43455,
|
|
58
|
+
"sha256": "3b78d1a2432e7d72752f96d9ac4b2b49cf6f59eb65548fbadb21ea6adbb86b37"
|
|
59
59
|
},
|
|
60
60
|
{
|
|
61
61
|
"path": "guardbench-summary.json",
|
|
62
|
-
"bytes":
|
|
63
|
-
"sha256": "
|
|
62
|
+
"bytes": 69350,
|
|
63
|
+
"sha256": "21023f230b761f1b43f8ecabe519dd6b320c62ad56f0b6aa28bbcf7a2c8838f5"
|
|
64
64
|
},
|
|
65
65
|
{
|
|
66
66
|
"path": "schemas/guardbench-adapter-registry.schema.json",
|
|
@@ -109,8 +109,8 @@
|
|
|
109
109
|
},
|
|
110
110
|
{
|
|
111
111
|
"path": "schemas/guardbench-raw.schema.json",
|
|
112
|
-
"bytes":
|
|
113
|
-
"sha256": "
|
|
112
|
+
"bytes": 5653,
|
|
113
|
+
"sha256": "2893204554696b69e4e1478f0d147cb95603b5f698ff112ebe9de45904b44045"
|
|
114
114
|
},
|
|
115
115
|
{
|
|
116
116
|
"path": "schemas/guardbench-submission-manifest.schema.json",
|
|
@@ -119,13 +119,13 @@
|
|
|
119
119
|
},
|
|
120
120
|
{
|
|
121
121
|
"path": "schemas/guardbench-summary.schema.json",
|
|
122
|
-
"bytes":
|
|
123
|
-
"sha256": "
|
|
122
|
+
"bytes": 8004,
|
|
123
|
+
"sha256": "2545b83cdd1d5d5d9abd535950779b5bbf3e5a2b04c3a36c35c2bbacc5efd9d9"
|
|
124
124
|
},
|
|
125
125
|
{
|
|
126
126
|
"path": "validation-report.json",
|
|
127
127
|
"bytes": 739,
|
|
128
|
-
"sha256": "
|
|
128
|
+
"sha256": "570d28760ad3611ccf4f08e98281a3fe659730463d13e96ff31073c7ee10ce65"
|
|
129
129
|
}
|
|
130
130
|
]
|
|
131
131
|
}
|