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.
Files changed (69) hide show
  1. package/CHANGELOG.md +24 -0
  2. package/README.md +27 -5
  3. package/benchmarks/guardbench.js +98 -8
  4. package/benchmarks/output/adapter-self-test/guardbench-adapter-self-test.json +7 -7
  5. package/benchmarks/output/external/guardbench-external-dry-run.json +1 -1
  6. package/benchmarks/output/external/guardbench-external-evidence.json +1 -1
  7. package/benchmarks/output/guardbench-conformance-card.json +12 -12
  8. package/benchmarks/output/guardbench-raw.json +240 -140
  9. package/benchmarks/output/guardbench-summary.json +350 -224
  10. package/benchmarks/output/leaderboard/guardbench-leaderboard.json +5 -5
  11. package/benchmarks/output/leaderboard/guardbench-leaderboard.md +2 -2
  12. package/benchmarks/output/submission-bundle/guardbench-conformance-card.json +12 -12
  13. package/benchmarks/output/submission-bundle/guardbench-raw.json +240 -140
  14. package/benchmarks/output/submission-bundle/guardbench-summary.json +350 -224
  15. package/benchmarks/output/submission-bundle/schemas/guardbench-raw.schema.json +21 -1
  16. package/benchmarks/output/submission-bundle/schemas/guardbench-summary.schema.json +23 -2
  17. package/benchmarks/output/submission-bundle/submission-manifest.json +14 -14
  18. package/benchmarks/output/submission-bundle/validation-report.json +1 -1
  19. package/benchmarks/output/summary.json +56 -56
  20. package/benchmarks/schemas/guardbench-raw.schema.json +21 -1
  21. package/benchmarks/schemas/guardbench-summary.schema.json +23 -2
  22. package/dist/mcp-server/config.d.ts +1 -1
  23. package/dist/mcp-server/config.js +1 -1
  24. package/dist/src/audrey.d.ts +10 -0
  25. package/dist/src/audrey.d.ts.map +1 -1
  26. package/dist/src/audrey.js +17 -4
  27. package/dist/src/audrey.js.map +1 -1
  28. package/dist/src/controller.d.ts +17 -1
  29. package/dist/src/controller.d.ts.map +1 -1
  30. package/dist/src/controller.js +52 -13
  31. package/dist/src/controller.js.map +1 -1
  32. package/dist/src/index.d.ts +2 -1
  33. package/dist/src/index.d.ts.map +1 -1
  34. package/dist/src/index.js +1 -1
  35. package/dist/src/index.js.map +1 -1
  36. package/dist/src/routes.d.ts.map +1 -1
  37. package/dist/src/routes.js +4 -1
  38. package/dist/src/routes.js.map +1 -1
  39. package/docs/paper/07-evaluation.md +4 -4
  40. package/docs/paper/audrey-paper-v1.md +5 -5
  41. package/docs/paper/evidence-ledger.md +1 -1
  42. package/docs/paper/output/arxiv/arxiv-manifest.json +4 -4
  43. package/docs/paper/output/arxiv/main.tex +5 -5
  44. package/docs/paper/output/arxiv-compile-report.json +3 -3
  45. package/docs/paper/output/submission-bundle/README.md +27 -5
  46. package/docs/paper/output/submission-bundle/benchmarks/output/adapter-self-test/guardbench-adapter-self-test.json +7 -7
  47. package/docs/paper/output/submission-bundle/benchmarks/output/external/guardbench-external-dry-run.json +1 -1
  48. package/docs/paper/output/submission-bundle/benchmarks/output/external/guardbench-external-evidence.json +1 -1
  49. package/docs/paper/output/submission-bundle/benchmarks/output/guardbench-conformance-card.json +12 -12
  50. package/docs/paper/output/submission-bundle/benchmarks/output/guardbench-raw.json +240 -140
  51. package/docs/paper/output/submission-bundle/benchmarks/output/guardbench-summary.json +350 -224
  52. package/docs/paper/output/submission-bundle/benchmarks/output/leaderboard/guardbench-leaderboard.json +5 -5
  53. package/docs/paper/output/submission-bundle/benchmarks/output/leaderboard/guardbench-leaderboard.md +2 -2
  54. package/docs/paper/output/submission-bundle/benchmarks/output/submission-bundle/submission-manifest.json +14 -14
  55. package/docs/paper/output/submission-bundle/benchmarks/output/submission-bundle/validation-report.json +1 -1
  56. package/docs/paper/output/submission-bundle/benchmarks/output/summary.json +67 -67
  57. package/docs/paper/output/submission-bundle/benchmarks/schemas/guardbench-raw.schema.json +21 -1
  58. package/docs/paper/output/submission-bundle/benchmarks/schemas/guardbench-summary.schema.json +23 -2
  59. package/docs/paper/output/submission-bundle/docs/paper/07-evaluation.md +4 -4
  60. package/docs/paper/output/submission-bundle/docs/paper/audrey-paper-v1.md +5 -5
  61. package/docs/paper/output/submission-bundle/docs/paper/evidence-ledger.md +1 -1
  62. package/docs/paper/output/submission-bundle/docs/paper/output/arxiv/arxiv-manifest.json +4 -4
  63. package/docs/paper/output/submission-bundle/docs/paper/output/arxiv/main.tex +5 -5
  64. package/docs/paper/output/submission-bundle/docs/paper/output/arxiv-compile-report.json +3 -3
  65. package/docs/paper/output/submission-bundle/package.json +2 -2
  66. package/docs/paper/output/submission-bundle/paper-submission-manifest.json +35 -35
  67. package/package.json +2 -2
  68. package/scripts/smoke-cli.js +22 -2
  69. 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": "2026-05-13T23:33:51.927Z",
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": 3.097,
32
- "p95Ms": 29.711,
33
- "maxMs": 29.711
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": "2026-05-13T23:33:51.597Z",
44
+ "manifestGeneratedAt": "2026-05-15T17:52:13.050Z",
45
45
  "fileCount": 17
46
46
  },
47
47
  "verification": {
@@ -1,7 +1,7 @@
1
1
  # GuardBench Leaderboard
2
2
 
3
- Generated: 2026-05-13T23:33:51.927Z
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 | 29.711ms | benchmarks/output/submission-bundle |
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 conformance card",
4
- "generatedAt": "2026-05-13T23:33:51.583Z",
4
+ "generatedAt": "2026-05-15T17:52:13.040Z",
5
5
  "sourceDir": "benchmarks/output",
6
6
  "manifestVersion": "0.2.0",
7
7
  "suiteId": "guardbench-local-comparative",
@@ -25,9 +25,9 @@
25
25
  "evidenceRecall": 1,
26
26
  "redactionLeaks": 0,
27
27
  "latency": {
28
- "p50Ms": 3.097,
29
- "p95Ms": 29.711,
30
- "maxMs": 29.711
28
+ "p50Ms": 2.465,
29
+ "p95Ms": 30.791,
30
+ "maxMs": 30.791
31
31
  }
32
32
  },
33
33
  "conformance": {
@@ -39,21 +39,21 @@
39
39
  "integrity": {
40
40
  "artifactHashes": {
41
41
  "guardbench-manifest.json": "57636ce19fdaa6e50fc3fc961d9e499a9f43632f588c713a9fefe8e8a6fa724c",
42
- "guardbench-summary.json": "2a6d5ee83cce2502135fb0442ef8cd3f2679fdc38c84207612c22a800a7a113a",
43
- "guardbench-raw.json": "c5b9c68cf946478fbfba617f17717e05ea3e01301089de19153d59e77e674bc6"
42
+ "guardbench-summary.json": "21023f230b761f1b43f8ecabe519dd6b320c62ad56f0b6aa28bbcf7a2c8838f5",
43
+ "guardbench-raw.json": "3b78d1a2432e7d72752f96d9ac4b2b49cf6f59eb65548fbadb21ea6adbb86b37"
44
44
  },
45
45
  "externalRunMetadataHash": null
46
46
  },
47
47
  "provenance": {
48
- "generatedAt": "2026-05-13T23:33:51.221Z",
49
- "gitSha": "970752172441967c3ede79562eca69b08efb1f12",
48
+ "generatedAt": "2026-05-15T17:52:12.761Z",
49
+ "gitSha": "82b0e9979680acf751b9e80f6f90f8c6ac74befb",
50
50
  "gitDirty": false,
51
- "node": "v24.14.1",
52
- "v8": "13.6.233.17-node.44",
51
+ "node": "v24.15.0",
52
+ "v8": "13.6.233.17-node.48",
53
53
  "platform": "linux",
54
54
  "arch": "x64",
55
- "osRelease": "6.17.0-1010-azure",
56
- "cpuModel": "AMD EPYC 7763 64-Core Processor",
55
+ "osRelease": "6.17.0-1013-azure",
56
+ "cpuModel": "AMD EPYC 9V74 80-Core Processor",
57
57
  "cpuCount": 4,
58
58
  "totalMemoryGb": 15.61,
59
59
  "embeddingProvider": "mock",