audrey 0.23.1 → 1.0.0

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 (250) hide show
  1. package/CHANGELOG.md +81 -19
  2. package/LICENSE +21 -21
  3. package/README.md +209 -5
  4. package/SECURITY.md +2 -1
  5. package/benchmarks/adapter-kit.mjs +20 -0
  6. package/benchmarks/adapter-self-test.mjs +166 -0
  7. package/benchmarks/adapters/example-allow.mjs +28 -0
  8. package/benchmarks/adapters/mem0-platform.mjs +267 -0
  9. package/benchmarks/adapters/registry.json +51 -0
  10. package/benchmarks/adapters/zep-cloud.mjs +280 -0
  11. package/benchmarks/baselines.js +169 -0
  12. package/benchmarks/build-leaderboard.mjs +170 -0
  13. package/benchmarks/cases.js +537 -0
  14. package/benchmarks/create-conformance-card.mjs +139 -0
  15. package/benchmarks/create-submission-bundle.mjs +176 -0
  16. package/benchmarks/dry-run-external-adapters.mjs +165 -0
  17. package/benchmarks/guardbench.js +1035 -0
  18. package/benchmarks/output/adapter-self-test/guardbench-adapter-self-test.json +50 -0
  19. package/benchmarks/output/external/guardbench-external-dry-run.json +69 -0
  20. package/benchmarks/output/external/guardbench-external-evidence.json +56 -0
  21. package/benchmarks/output/guardbench-conformance-card.json +63 -0
  22. package/benchmarks/output/guardbench-manifest.json +414 -0
  23. package/benchmarks/output/guardbench-raw.json +1171 -0
  24. package/benchmarks/output/guardbench-summary.json +1981 -0
  25. package/benchmarks/output/leaderboard/guardbench-leaderboard.json +93 -0
  26. package/benchmarks/output/leaderboard/guardbench-leaderboard.md +7 -0
  27. package/benchmarks/output/submission-bundle/guardbench-conformance-card.json +63 -0
  28. package/benchmarks/output/submission-bundle/guardbench-manifest.json +414 -0
  29. package/benchmarks/output/submission-bundle/guardbench-raw.json +1171 -0
  30. package/benchmarks/output/submission-bundle/guardbench-summary.json +1981 -0
  31. package/benchmarks/output/submission-bundle/schemas/guardbench-adapter-registry.schema.json +69 -0
  32. package/benchmarks/output/submission-bundle/schemas/guardbench-adapter-self-test.schema.json +156 -0
  33. package/benchmarks/output/submission-bundle/schemas/guardbench-conformance-card.schema.json +184 -0
  34. package/benchmarks/output/submission-bundle/schemas/guardbench-external-dry-run.schema.json +74 -0
  35. package/benchmarks/output/submission-bundle/schemas/guardbench-external-evidence.schema.json +108 -0
  36. package/benchmarks/output/submission-bundle/schemas/guardbench-external-run.schema.json +160 -0
  37. package/benchmarks/output/submission-bundle/schemas/guardbench-leaderboard.schema.json +179 -0
  38. package/benchmarks/output/submission-bundle/schemas/guardbench-manifest.schema.json +213 -0
  39. package/benchmarks/output/submission-bundle/schemas/guardbench-publication-verification.schema.json +47 -0
  40. package/benchmarks/output/submission-bundle/schemas/guardbench-raw.schema.json +164 -0
  41. package/benchmarks/output/submission-bundle/schemas/guardbench-submission-manifest.schema.json +151 -0
  42. package/benchmarks/output/submission-bundle/schemas/guardbench-summary.schema.json +228 -0
  43. package/benchmarks/output/submission-bundle/submission-manifest.json +131 -0
  44. package/benchmarks/output/submission-bundle/validation-report.json +31 -0
  45. package/benchmarks/output/summary.json +2354 -0
  46. package/benchmarks/perf-snapshot.js +304 -0
  47. package/benchmarks/perf.bench.js +161 -0
  48. package/benchmarks/public-paths.mjs +78 -0
  49. package/benchmarks/reference-results.js +70 -0
  50. package/benchmarks/report.js +259 -0
  51. package/benchmarks/run-external-guardbench.mjs +281 -0
  52. package/benchmarks/run.js +682 -0
  53. package/benchmarks/schemas/guardbench-adapter-registry.schema.json +69 -0
  54. package/benchmarks/schemas/guardbench-adapter-self-test.schema.json +156 -0
  55. package/benchmarks/schemas/guardbench-conformance-card.schema.json +184 -0
  56. package/benchmarks/schemas/guardbench-external-dry-run.schema.json +74 -0
  57. package/benchmarks/schemas/guardbench-external-evidence.schema.json +108 -0
  58. package/benchmarks/schemas/guardbench-external-run.schema.json +160 -0
  59. package/benchmarks/schemas/guardbench-leaderboard.schema.json +179 -0
  60. package/benchmarks/schemas/guardbench-manifest.schema.json +213 -0
  61. package/benchmarks/schemas/guardbench-publication-verification.schema.json +47 -0
  62. package/benchmarks/schemas/guardbench-raw.schema.json +164 -0
  63. package/benchmarks/schemas/guardbench-submission-manifest.schema.json +151 -0
  64. package/benchmarks/schemas/guardbench-summary.schema.json +228 -0
  65. package/benchmarks/snapshots/perf-0.22.2.json +123 -0
  66. package/benchmarks/snapshots/perf-0.23.0.json +123 -0
  67. package/benchmarks/validate-adapter-module.mjs +104 -0
  68. package/benchmarks/validate-adapter-registry.mjs +134 -0
  69. package/benchmarks/validate-adapter-self-test.mjs +96 -0
  70. package/benchmarks/validate-guardbench-artifacts.mjs +343 -0
  71. package/benchmarks/verify-external-evidence.mjs +296 -0
  72. package/benchmarks/verify-publication-artifacts.mjs +286 -0
  73. package/benchmarks/verify-submission-bundle.mjs +167 -0
  74. package/dist/mcp-server/config.d.ts +1 -1
  75. package/dist/mcp-server/config.d.ts.map +1 -1
  76. package/dist/mcp-server/config.js +1 -1
  77. package/dist/mcp-server/config.js.map +1 -1
  78. package/dist/mcp-server/index.d.ts +65 -3
  79. package/dist/mcp-server/index.d.ts.map +1 -1
  80. package/dist/mcp-server/index.js +675 -157
  81. package/dist/mcp-server/index.js.map +1 -1
  82. package/dist/src/action-key.d.ts +9 -0
  83. package/dist/src/action-key.d.ts.map +1 -0
  84. package/dist/src/action-key.js +49 -0
  85. package/dist/src/action-key.js.map +1 -0
  86. package/dist/src/adaptive.js +5 -5
  87. package/dist/src/affect.js +8 -8
  88. package/dist/src/audrey.d.ts +3 -0
  89. package/dist/src/audrey.d.ts.map +1 -1
  90. package/dist/src/audrey.js +55 -3
  91. package/dist/src/audrey.js.map +1 -1
  92. package/dist/src/capsule.js +4 -4
  93. package/dist/src/causal.js +3 -3
  94. package/dist/src/consolidate.js +48 -48
  95. package/dist/src/controller.d.ts +61 -5
  96. package/dist/src/controller.d.ts.map +1 -1
  97. package/dist/src/controller.js +230 -49
  98. package/dist/src/controller.js.map +1 -1
  99. package/dist/src/db.js +172 -172
  100. package/dist/src/decay.js +8 -8
  101. package/dist/src/embedding.d.ts +2 -1
  102. package/dist/src/embedding.d.ts.map +1 -1
  103. package/dist/src/embedding.js +39 -29
  104. package/dist/src/embedding.js.map +1 -1
  105. package/dist/src/encode.js +6 -6
  106. package/dist/src/feedback.d.ts +6 -0
  107. package/dist/src/feedback.d.ts.map +1 -1
  108. package/dist/src/feedback.js +6 -0
  109. package/dist/src/feedback.js.map +1 -1
  110. package/dist/src/forget.js +12 -12
  111. package/dist/src/hybrid-recall.js +9 -9
  112. package/dist/src/impact.js +6 -6
  113. package/dist/src/import.d.ts +3 -3
  114. package/dist/src/import.js +41 -41
  115. package/dist/src/index.d.ts +3 -3
  116. package/dist/src/index.d.ts.map +1 -1
  117. package/dist/src/index.js +2 -2
  118. package/dist/src/index.js.map +1 -1
  119. package/dist/src/interference.js +14 -14
  120. package/dist/src/introspect.js +18 -18
  121. package/dist/src/preflight.d.ts.map +1 -1
  122. package/dist/src/preflight.js +41 -0
  123. package/dist/src/preflight.js.map +1 -1
  124. package/dist/src/promote.js +7 -7
  125. package/dist/src/prompts.js +118 -118
  126. package/dist/src/recall.js +30 -30
  127. package/dist/src/reflexes.d.ts +1 -0
  128. package/dist/src/reflexes.d.ts.map +1 -1
  129. package/dist/src/reflexes.js +3 -0
  130. package/dist/src/reflexes.js.map +1 -1
  131. package/dist/src/rollback.js +4 -4
  132. package/dist/src/routes.d.ts.map +1 -1
  133. package/dist/src/routes.js +67 -1
  134. package/dist/src/routes.js.map +1 -1
  135. package/dist/src/validate.js +25 -25
  136. package/docs/AUDREY_PAPER_OUTLINE.md +175 -0
  137. package/docs/MEMORY_BENCHMARKING.md +59 -0
  138. package/docs/PRODUCTION_BACKLOG.md +304 -0
  139. package/docs/paper/00-master.md +48 -0
  140. package/docs/paper/01-introduction.md +27 -0
  141. package/docs/paper/02-related-work.md +47 -0
  142. package/docs/paper/03-problem-definition.md +108 -0
  143. package/docs/paper/04-design.md +164 -0
  144. package/docs/paper/05-guardbench-spec.md +412 -0
  145. package/docs/paper/06-implementation.md +113 -0
  146. package/docs/paper/07-evaluation.md +168 -0
  147. package/docs/paper/08-discussion-limitations.md +61 -0
  148. package/docs/paper/09-conclusion.md +11 -0
  149. package/docs/paper/SUBMISSION_README.md +162 -0
  150. package/docs/paper/appendix-a-demo-transcript.md +114 -0
  151. package/docs/paper/arxiv-compile-report.schema.json +116 -0
  152. package/docs/paper/arxiv-source.schema.json +61 -0
  153. package/docs/paper/audrey-paper-v1.md +1106 -0
  154. package/docs/paper/browser-launch-plan.json +209 -0
  155. package/docs/paper/browser-launch-plan.schema.json +100 -0
  156. package/docs/paper/browser-launch-results.json +86 -0
  157. package/docs/paper/browser-launch-results.schema.json +66 -0
  158. package/docs/paper/claim-register.json +138 -0
  159. package/docs/paper/claim-register.schema.json +81 -0
  160. package/docs/paper/evidence-ledger.md +103 -0
  161. package/docs/paper/output/arxiv/README-arxiv.txt +8 -0
  162. package/docs/paper/output/arxiv/arxiv-manifest.json +41 -0
  163. package/docs/paper/output/arxiv/main.tex +949 -0
  164. package/docs/paper/output/arxiv/references.bib +222 -0
  165. package/docs/paper/output/arxiv-compile-report.json +24 -0
  166. package/docs/paper/output/submission-bundle/LICENSE +21 -0
  167. package/docs/paper/output/submission-bundle/README.md +533 -0
  168. package/docs/paper/output/submission-bundle/benchmarks/output/adapter-self-test/guardbench-adapter-self-test.json +50 -0
  169. package/docs/paper/output/submission-bundle/benchmarks/output/external/guardbench-external-dry-run.json +69 -0
  170. package/docs/paper/output/submission-bundle/benchmarks/output/external/guardbench-external-evidence.json +56 -0
  171. package/docs/paper/output/submission-bundle/benchmarks/output/guardbench-conformance-card.json +63 -0
  172. package/docs/paper/output/submission-bundle/benchmarks/output/guardbench-manifest.json +414 -0
  173. package/docs/paper/output/submission-bundle/benchmarks/output/guardbench-raw.json +1171 -0
  174. package/docs/paper/output/submission-bundle/benchmarks/output/guardbench-summary.json +1981 -0
  175. package/docs/paper/output/submission-bundle/benchmarks/output/leaderboard/guardbench-leaderboard.json +93 -0
  176. package/docs/paper/output/submission-bundle/benchmarks/output/leaderboard/guardbench-leaderboard.md +7 -0
  177. package/docs/paper/output/submission-bundle/benchmarks/output/submission-bundle/submission-manifest.json +131 -0
  178. package/docs/paper/output/submission-bundle/benchmarks/output/submission-bundle/validation-report.json +31 -0
  179. package/docs/paper/output/submission-bundle/benchmarks/output/summary.json +2354 -0
  180. package/docs/paper/output/submission-bundle/benchmarks/schemas/guardbench-adapter-registry.schema.json +69 -0
  181. package/docs/paper/output/submission-bundle/benchmarks/schemas/guardbench-adapter-self-test.schema.json +156 -0
  182. package/docs/paper/output/submission-bundle/benchmarks/schemas/guardbench-conformance-card.schema.json +184 -0
  183. package/docs/paper/output/submission-bundle/benchmarks/schemas/guardbench-external-dry-run.schema.json +74 -0
  184. package/docs/paper/output/submission-bundle/benchmarks/schemas/guardbench-external-evidence.schema.json +108 -0
  185. package/docs/paper/output/submission-bundle/benchmarks/schemas/guardbench-external-run.schema.json +160 -0
  186. package/docs/paper/output/submission-bundle/benchmarks/schemas/guardbench-leaderboard.schema.json +179 -0
  187. package/docs/paper/output/submission-bundle/benchmarks/schemas/guardbench-manifest.schema.json +213 -0
  188. package/docs/paper/output/submission-bundle/benchmarks/schemas/guardbench-publication-verification.schema.json +47 -0
  189. package/docs/paper/output/submission-bundle/benchmarks/schemas/guardbench-raw.schema.json +164 -0
  190. package/docs/paper/output/submission-bundle/benchmarks/schemas/guardbench-submission-manifest.schema.json +151 -0
  191. package/docs/paper/output/submission-bundle/benchmarks/schemas/guardbench-summary.schema.json +228 -0
  192. package/docs/paper/output/submission-bundle/docs/AUDREY_PAPER_OUTLINE.md +175 -0
  193. package/docs/paper/output/submission-bundle/docs/paper/00-master.md +48 -0
  194. package/docs/paper/output/submission-bundle/docs/paper/01-introduction.md +27 -0
  195. package/docs/paper/output/submission-bundle/docs/paper/02-related-work.md +47 -0
  196. package/docs/paper/output/submission-bundle/docs/paper/03-problem-definition.md +108 -0
  197. package/docs/paper/output/submission-bundle/docs/paper/04-design.md +164 -0
  198. package/docs/paper/output/submission-bundle/docs/paper/05-guardbench-spec.md +412 -0
  199. package/docs/paper/output/submission-bundle/docs/paper/06-implementation.md +113 -0
  200. package/docs/paper/output/submission-bundle/docs/paper/07-evaluation.md +168 -0
  201. package/docs/paper/output/submission-bundle/docs/paper/08-discussion-limitations.md +61 -0
  202. package/docs/paper/output/submission-bundle/docs/paper/09-conclusion.md +11 -0
  203. package/docs/paper/output/submission-bundle/docs/paper/SUBMISSION_README.md +162 -0
  204. package/docs/paper/output/submission-bundle/docs/paper/appendix-a-demo-transcript.md +114 -0
  205. package/docs/paper/output/submission-bundle/docs/paper/arxiv-compile-report.schema.json +116 -0
  206. package/docs/paper/output/submission-bundle/docs/paper/arxiv-source.schema.json +61 -0
  207. package/docs/paper/output/submission-bundle/docs/paper/audrey-paper-v1.md +1106 -0
  208. package/docs/paper/output/submission-bundle/docs/paper/browser-launch-plan.json +209 -0
  209. package/docs/paper/output/submission-bundle/docs/paper/browser-launch-plan.schema.json +100 -0
  210. package/docs/paper/output/submission-bundle/docs/paper/browser-launch-results.json +86 -0
  211. package/docs/paper/output/submission-bundle/docs/paper/browser-launch-results.schema.json +66 -0
  212. package/docs/paper/output/submission-bundle/docs/paper/claim-register.json +138 -0
  213. package/docs/paper/output/submission-bundle/docs/paper/claim-register.schema.json +81 -0
  214. package/docs/paper/output/submission-bundle/docs/paper/evidence-ledger.md +103 -0
  215. package/docs/paper/output/submission-bundle/docs/paper/output/arxiv/README-arxiv.txt +8 -0
  216. package/docs/paper/output/submission-bundle/docs/paper/output/arxiv/arxiv-manifest.json +41 -0
  217. package/docs/paper/output/submission-bundle/docs/paper/output/arxiv/main.tex +949 -0
  218. package/docs/paper/output/submission-bundle/docs/paper/output/arxiv/references.bib +222 -0
  219. package/docs/paper/output/submission-bundle/docs/paper/output/arxiv-compile-report.json +24 -0
  220. package/docs/paper/output/submission-bundle/docs/paper/paper-submission-bundle.schema.json +70 -0
  221. package/docs/paper/output/submission-bundle/docs/paper/publication-pack.json +81 -0
  222. package/docs/paper/output/submission-bundle/docs/paper/publication-pack.schema.json +60 -0
  223. package/docs/paper/output/submission-bundle/docs/paper/references.bib +222 -0
  224. package/docs/paper/output/submission-bundle/package.json +212 -0
  225. package/docs/paper/output/submission-bundle/paper-submission-manifest.json +379 -0
  226. package/docs/paper/paper-submission-bundle.schema.json +70 -0
  227. package/docs/paper/publication-pack.json +81 -0
  228. package/docs/paper/publication-pack.schema.json +60 -0
  229. package/docs/paper/references.bib +222 -0
  230. package/package.json +87 -4
  231. package/scripts/audit-release-completion.mjs +362 -0
  232. package/scripts/create-arxiv-source.mjs +362 -0
  233. package/scripts/create-paper-submission-bundle.mjs +210 -0
  234. package/scripts/finalize-release.mjs +526 -0
  235. package/scripts/prepare-release-cut.mjs +269 -0
  236. package/scripts/publish-release-bundle.mjs +209 -0
  237. package/scripts/publish-release-github-api.mjs +429 -0
  238. package/scripts/run-vitest.mjs +34 -0
  239. package/scripts/smoke-cli.js +72 -0
  240. package/scripts/sync-paper-artifacts.mjs +109 -0
  241. package/scripts/verify-arxiv-compile.mjs +440 -0
  242. package/scripts/verify-arxiv-source.mjs +194 -0
  243. package/scripts/verify-browser-launch-plan.mjs +237 -0
  244. package/scripts/verify-browser-launch-results.mjs +285 -0
  245. package/scripts/verify-paper-artifacts.mjs +338 -0
  246. package/scripts/verify-paper-claims.mjs +226 -0
  247. package/scripts/verify-paper-submission-bundle.mjs +207 -0
  248. package/scripts/verify-publication-pack.mjs +196 -0
  249. package/scripts/verify-python-package.py +201 -0
  250. package/scripts/verify-release-readiness.mjs +741 -0
@@ -0,0 +1,93 @@
1
+ {
2
+ "schemaVersion": "1.0.0",
3
+ "suite": "GuardBench leaderboard",
4
+ "generatedAt": "2026-05-13T23:33:51.927Z",
5
+ "ranking": [
6
+ "verified bundle",
7
+ "adapter conformance",
8
+ "fullContractPassRate",
9
+ "decisionAccuracy",
10
+ "evidenceRecall",
11
+ "redactionLeaks ascending",
12
+ "latency.p95Ms ascending",
13
+ "subject.name"
14
+ ],
15
+ "rows": [
16
+ {
17
+ "rank": 1,
18
+ "subject": {
19
+ "name": "Audrey Guard",
20
+ "requestedAdapter": null,
21
+ "external": false
22
+ },
23
+ "score": {
24
+ "scenarios": 10,
25
+ "fullContractPassed": 10,
26
+ "fullContractPassRate": 1,
27
+ "decisionAccuracy": 1,
28
+ "evidenceRecall": 1,
29
+ "redactionLeaks": 0,
30
+ "latency": {
31
+ "p50Ms": 3.097,
32
+ "p95Ms": 29.711,
33
+ "maxMs": 29.711
34
+ }
35
+ },
36
+ "conformance": {
37
+ "ok": true,
38
+ "failures": [],
39
+ "artifactValidationOk": true,
40
+ "artifactValidationFailures": []
41
+ },
42
+ "source": {
43
+ "dir": "benchmarks/output/submission-bundle",
44
+ "manifestGeneratedAt": "2026-05-13T23:33:51.597Z",
45
+ "fileCount": 17
46
+ },
47
+ "verification": {
48
+ "ok": true,
49
+ "dir": "benchmarks/output/submission-bundle",
50
+ "subject": {
51
+ "name": "Audrey Guard",
52
+ "requestedAdapter": null,
53
+ "external": false
54
+ },
55
+ "files": [
56
+ "guardbench-conformance-card.json",
57
+ "guardbench-manifest.json",
58
+ "guardbench-raw.json",
59
+ "guardbench-summary.json",
60
+ "schemas/guardbench-adapter-registry.schema.json",
61
+ "schemas/guardbench-adapter-self-test.schema.json",
62
+ "schemas/guardbench-conformance-card.schema.json",
63
+ "schemas/guardbench-external-dry-run.schema.json",
64
+ "schemas/guardbench-external-evidence.schema.json",
65
+ "schemas/guardbench-external-run.schema.json",
66
+ "schemas/guardbench-leaderboard.schema.json",
67
+ "schemas/guardbench-manifest.schema.json",
68
+ "schemas/guardbench-publication-verification.schema.json",
69
+ "schemas/guardbench-raw.schema.json",
70
+ "schemas/guardbench-submission-manifest.schema.json",
71
+ "schemas/guardbench-summary.schema.json",
72
+ "validation-report.json"
73
+ ],
74
+ "artifactValidation": {
75
+ "ok": true,
76
+ "dir": "benchmarks/output/submission-bundle",
77
+ "schemasDir": "benchmarks/output/submission-bundle/schemas",
78
+ "files": [
79
+ "guardbench-manifest.json",
80
+ "guardbench-summary.json",
81
+ "guardbench-raw.json"
82
+ ],
83
+ "optionalFiles": [
84
+ "guardbench-conformance-card.json"
85
+ ],
86
+ "failures": []
87
+ },
88
+ "failures": []
89
+ }
90
+ }
91
+ ],
92
+ "failures": []
93
+ }
@@ -0,0 +1,7 @@
1
+ # GuardBench Leaderboard
2
+
3
+ Generated: 2026-05-13T23:33:51.927Z
4
+
5
+ | Rank | Subject | Verified | Conformant | Full Contract | Decision Accuracy | Evidence Recall | Redaction Leaks | p95 Latency | Bundle |
6
+ |---:|---|---:|---:|---:|---:|---:|---:|---:|---|
7
+ | 1 | Audrey Guard | yes | yes | 100.0% | 100.0% | 100.0% | 0 | 29.711ms | benchmarks/output/submission-bundle |
@@ -0,0 +1,131 @@
1
+ {
2
+ "schemaVersion": "1.0.0",
3
+ "suite": "GuardBench submission bundle",
4
+ "generatedAt": "2026-05-13T23:33:51.597Z",
5
+ "sourceDir": "benchmarks/output",
6
+ "subject": {
7
+ "name": "Audrey Guard",
8
+ "requestedAdapter": null,
9
+ "external": false
10
+ },
11
+ "score": {
12
+ "scenarios": 10,
13
+ "fullContractPassed": 10,
14
+ "fullContractPassRate": 1,
15
+ "decisionAccuracy": 1,
16
+ "evidenceRecall": 1,
17
+ "redactionLeaks": 0,
18
+ "latency": {
19
+ "p50Ms": 3.097,
20
+ "p95Ms": 29.711,
21
+ "maxMs": 29.711
22
+ }
23
+ },
24
+ "conformance": {
25
+ "ok": true,
26
+ "failures": [],
27
+ "artifactValidationOk": true,
28
+ "artifactValidationFailures": []
29
+ },
30
+ "validation": {
31
+ "ok": true,
32
+ "dir": "benchmarks/output/submission-bundle",
33
+ "schemasDir": "benchmarks/output/submission-bundle/schemas",
34
+ "files": [
35
+ "guardbench-manifest.json",
36
+ "guardbench-summary.json",
37
+ "guardbench-raw.json"
38
+ ],
39
+ "optionalFiles": [
40
+ "guardbench-conformance-card.json"
41
+ ],
42
+ "failures": []
43
+ },
44
+ "files": [
45
+ {
46
+ "path": "guardbench-conformance-card.json",
47
+ "bytes": 1735,
48
+ "sha256": "0709bb4d93a797764e4ed5655c575390a57554a42625398d378c8ec0f23bd2b4"
49
+ },
50
+ {
51
+ "path": "guardbench-manifest.json",
52
+ "bytes": 12056,
53
+ "sha256": "57636ce19fdaa6e50fc3fc961d9e499a9f43632f588c713a9fefe8e8a6fa724c"
54
+ },
55
+ {
56
+ "path": "guardbench-raw.json",
57
+ "bytes": 39429,
58
+ "sha256": "c5b9c68cf946478fbfba617f17717e05ea3e01301089de19153d59e77e674bc6"
59
+ },
60
+ {
61
+ "path": "guardbench-summary.json",
62
+ "bytes": 64381,
63
+ "sha256": "2a6d5ee83cce2502135fb0442ef8cd3f2679fdc38c84207612c22a800a7a113a"
64
+ },
65
+ {
66
+ "path": "schemas/guardbench-adapter-registry.schema.json",
67
+ "bytes": 2016,
68
+ "sha256": "0fb401e0b00270f16287a47cdb868ec6ac23e85f134958141f37519bf0c67164"
69
+ },
70
+ {
71
+ "path": "schemas/guardbench-adapter-self-test.schema.json",
72
+ "bytes": 4572,
73
+ "sha256": "369402022870257c0bca52c05f21e53b40e310547bf49871ce08b2976c755127"
74
+ },
75
+ {
76
+ "path": "schemas/guardbench-conformance-card.schema.json",
77
+ "bytes": 5251,
78
+ "sha256": "337e197617e889388ff9f71f361b6c75450b43c1c131af622d4a59bc4faca89e"
79
+ },
80
+ {
81
+ "path": "schemas/guardbench-external-dry-run.schema.json",
82
+ "bytes": 2177,
83
+ "sha256": "df327a2b2c1cd7bf4453457c83ebc10708e6f56aa1d3526c7ac492a1b254880c"
84
+ },
85
+ {
86
+ "path": "schemas/guardbench-external-evidence.schema.json",
87
+ "bytes": 3075,
88
+ "sha256": "c6f7af89c53d039ff7e3b3b9f5829a7524e4a24c254dd17754dd51469c0295d1"
89
+ },
90
+ {
91
+ "path": "schemas/guardbench-external-run.schema.json",
92
+ "bytes": 4443,
93
+ "sha256": "36f79172e6b9264fa7f16a90684f2c75fb3f8432c5226be4181d93622b17b40b"
94
+ },
95
+ {
96
+ "path": "schemas/guardbench-leaderboard.schema.json",
97
+ "bytes": 5457,
98
+ "sha256": "ac3414af9f97d3c3b241ffea3fe9995295cb107dbc4fddef2f32f0d3de2d1abf"
99
+ },
100
+ {
101
+ "path": "schemas/guardbench-manifest.schema.json",
102
+ "bytes": 6345,
103
+ "sha256": "a2995e946908f094dfd5db264db87615167586d57f1a335aa9bf2262b709ef4d"
104
+ },
105
+ {
106
+ "path": "schemas/guardbench-publication-verification.schema.json",
107
+ "bytes": 1713,
108
+ "sha256": "a83442c23dee3805b6c1bd3b8524b16948b5dc78d3d65074142c2a99c733f1b9"
109
+ },
110
+ {
111
+ "path": "schemas/guardbench-raw.schema.json",
112
+ "bytes": 5057,
113
+ "sha256": "f419685932a5549d5efef611b1dbbe585300365de3c977fcfedf174672f6bc3a"
114
+ },
115
+ {
116
+ "path": "schemas/guardbench-submission-manifest.schema.json",
117
+ "bytes": 4469,
118
+ "sha256": "4d624bec3cbb7f3043064a874bd869ac8556f42231f0871a179f58cd8fbcfb23"
119
+ },
120
+ {
121
+ "path": "schemas/guardbench-summary.schema.json",
122
+ "bytes": 7331,
123
+ "sha256": "ac70b448c730fb8b01899615477a167a64734d16304c39d661b2b3130e8aa1da"
124
+ },
125
+ {
126
+ "path": "validation-report.json",
127
+ "bytes": 739,
128
+ "sha256": "9734a26b31a7511fbba361f22245dd6325b65fe47d1072fa59df7eeb15d724a1"
129
+ }
130
+ ]
131
+ }
@@ -0,0 +1,31 @@
1
+ {
2
+ "generatedAt": "2026-05-13T23:33:51.596Z",
3
+ "sourceValidation": {
4
+ "ok": true,
5
+ "dir": "benchmarks/output",
6
+ "schemasDir": "benchmarks/schemas",
7
+ "files": [
8
+ "guardbench-manifest.json",
9
+ "guardbench-summary.json",
10
+ "guardbench-raw.json"
11
+ ],
12
+ "optionalFiles": [
13
+ "guardbench-conformance-card.json"
14
+ ],
15
+ "failures": []
16
+ },
17
+ "bundleValidation": {
18
+ "ok": true,
19
+ "dir": "benchmarks/output/submission-bundle",
20
+ "schemasDir": "benchmarks/output/submission-bundle/schemas",
21
+ "files": [
22
+ "guardbench-manifest.json",
23
+ "guardbench-summary.json",
24
+ "guardbench-raw.json"
25
+ ],
26
+ "optionalFiles": [
27
+ "guardbench-conformance-card.json"
28
+ ],
29
+ "failures": []
30
+ }
31
+ }