audrey 1.1.2 → 1.1.3

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 (45) hide show
  1. package/CHANGELOG.md +8 -0
  2. package/README.md +1 -1
  3. package/benchmarks/output/adapter-self-test/guardbench-adapter-self-test.json +4 -4
  4. package/benchmarks/output/external/guardbench-external-dry-run.json +1 -1
  5. package/benchmarks/output/external/guardbench-external-evidence.json +1 -1
  6. package/benchmarks/output/guardbench-conformance-card.json +9 -9
  7. package/benchmarks/output/guardbench-raw.json +108 -108
  8. package/benchmarks/output/guardbench-summary.json +174 -174
  9. package/benchmarks/output/leaderboard/guardbench-leaderboard.json +5 -5
  10. package/benchmarks/output/leaderboard/guardbench-leaderboard.md +2 -2
  11. package/benchmarks/output/submission-bundle/guardbench-conformance-card.json +9 -9
  12. package/benchmarks/output/submission-bundle/guardbench-raw.json +108 -108
  13. package/benchmarks/output/submission-bundle/guardbench-summary.json +174 -174
  14. package/benchmarks/output/submission-bundle/submission-manifest.json +10 -10
  15. package/benchmarks/output/submission-bundle/validation-report.json +1 -1
  16. package/benchmarks/output/summary.json +54 -54
  17. package/dist/mcp-server/config.d.ts +1 -1
  18. package/dist/mcp-server/config.js +1 -1
  19. package/docs/paper/07-evaluation.md +6 -6
  20. package/docs/paper/audrey-paper-v1.md +6 -6
  21. package/docs/paper/evidence-ledger.md +1 -1
  22. package/docs/paper/output/arxiv/arxiv-manifest.json +4 -4
  23. package/docs/paper/output/arxiv/main.tex +6 -6
  24. package/docs/paper/output/arxiv-compile-report.json +3 -3
  25. package/docs/paper/output/submission-bundle/README.md +1 -1
  26. package/docs/paper/output/submission-bundle/benchmarks/output/adapter-self-test/guardbench-adapter-self-test.json +4 -4
  27. package/docs/paper/output/submission-bundle/benchmarks/output/external/guardbench-external-dry-run.json +1 -1
  28. package/docs/paper/output/submission-bundle/benchmarks/output/external/guardbench-external-evidence.json +1 -1
  29. package/docs/paper/output/submission-bundle/benchmarks/output/guardbench-conformance-card.json +9 -9
  30. package/docs/paper/output/submission-bundle/benchmarks/output/guardbench-raw.json +108 -108
  31. package/docs/paper/output/submission-bundle/benchmarks/output/guardbench-summary.json +174 -174
  32. package/docs/paper/output/submission-bundle/benchmarks/output/leaderboard/guardbench-leaderboard.json +5 -5
  33. package/docs/paper/output/submission-bundle/benchmarks/output/leaderboard/guardbench-leaderboard.md +2 -2
  34. package/docs/paper/output/submission-bundle/benchmarks/output/submission-bundle/submission-manifest.json +10 -10
  35. package/docs/paper/output/submission-bundle/benchmarks/output/submission-bundle/validation-report.json +1 -1
  36. package/docs/paper/output/submission-bundle/benchmarks/output/summary.json +60 -60
  37. package/docs/paper/output/submission-bundle/docs/paper/07-evaluation.md +6 -6
  38. package/docs/paper/output/submission-bundle/docs/paper/audrey-paper-v1.md +6 -6
  39. package/docs/paper/output/submission-bundle/docs/paper/evidence-ledger.md +1 -1
  40. package/docs/paper/output/submission-bundle/docs/paper/output/arxiv/arxiv-manifest.json +4 -4
  41. package/docs/paper/output/submission-bundle/docs/paper/output/arxiv/main.tex +6 -6
  42. package/docs/paper/output/submission-bundle/docs/paper/output/arxiv-compile-report.json +3 -3
  43. package/docs/paper/output/submission-bundle/package.json +2 -2
  44. package/docs/paper/output/submission-bundle/paper-submission-manifest.json +28 -28
  45. package/package.json +2 -2
package/benchmarks/output/leaderboard/guardbench-leaderboard.json CHANGED
@@ -1,7 +1,7 @@
1
1
  {
2
2
  "schemaVersion": "1.0.0",
3
3
  "suite": "GuardBench leaderboard",
4
- "generatedAt": "2026-07-13T14:48:50.016Z",
4
+ "generatedAt": "2026-07-13T15:07:31.942Z",
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": 4.253,
32
- "p95Ms": 21.196,
33
- "maxMs": 21.196
31
+ "p50Ms": 4.607,
32
+ "p95Ms": 21.585,
33
+ "maxMs": 21.585
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": "2026-07-13T14:48:49.680Z",
44
+ "manifestGeneratedAt": "2026-07-13T15:07:31.582Z",
45
45
  "fileCount": 17
46
46
  },
47
47
  "verification": {
package/benchmarks/output/leaderboard/guardbench-leaderboard.md CHANGED
@@ -1,7 +1,7 @@
1
1
  # GuardBench Leaderboard
2
2
 
3
- Generated: 2026-07-13T14:48:50.016Z
3
+ Generated: 2026-07-13T15:07:31.942Z
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 | 21.196ms | benchmarks/output/submission-bundle |
7
+ | 1 | Audrey Guard | yes | yes | 100.0% | 100.0% | 100.0% | 0 | 21.585ms | benchmarks/output/submission-bundle |
package/benchmarks/output/submission-bundle/guardbench-conformance-card.json CHANGED
@@ -1,7 +1,7 @@
1
1
  {
2
2
  "schemaVersion": "1.0.0",
3
3
  "suite": "GuardBench conformance card",
4
- "generatedAt": "2026-07-13T14:48:49.667Z",
4
+ "generatedAt": "2026-07-13T15:07:31.567Z",
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": 4.253,
29
- "p95Ms": 21.196,
30
- "maxMs": 21.196
28
+ "p50Ms": 4.607,
29
+ "p95Ms": 21.585,
30
+ "maxMs": 21.585
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": "3ba1c059558aa8b511ae510276078930649ba6aca9669324148726fac10c7ee8",
43
- "guardbench-raw.json": "786b03ff8570444620c23b35621bbb14897f06310de7e8bd3a337a1acf5ce776"
42
+ "guardbench-summary.json": "53b22e040ace0b91784e99684ffd740c95740171c00bf65388590aeb493c7c7d",
43
+ "guardbench-raw.json": "20a91ed7ca54a3b5b47b3a3f9ecde4ae8d53cc2b9bdbb5cb1ce6347e2224497b"
44
44
  },
45
45
  "externalRunMetadataHash": null
46
46
  },
47
47
  "provenance": {
48
- "generatedAt": "2026-07-13T14:48:49.313Z",
49
- "gitSha": "7111c630be69d3ab96439018f094dc4fac826aca",
48
+ "generatedAt": "2026-07-13T15:07:31.179Z",
49
+ "gitSha": "36842cfb0cad7ca5da864231a7e265229ba56fbd",
50
50
  "gitDirty": false,
51
51
  "node": "v24.18.0",
52
52
  "v8": "13.6.233.17-node.50",
53
53
  "platform": "linux",
54
54
  "arch": "x64",
55
55
  "osRelease": "6.17.0-1018-azure",
56
- "cpuModel": "AMD EPYC 9V74 80-Core Processor",
56
+ "cpuModel": "AMD EPYC 7763 64-Core Processor",
57
57
  "cpuCount": 4,
58
58
  "totalMemoryGb": 15.61,
59
59
  "embeddingProvider": "mock",