audrey 1.1.3 → 1.2.1

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 (285) hide show
  1. package/CHANGELOG.md +97 -0
  2. package/README.md +39 -12
  3. package/dist/mcp-server/codex-hooks-probe.d.ts +22 -0
  4. package/dist/mcp-server/codex-hooks-probe.d.ts.map +1 -0
  5. package/dist/mcp-server/codex-hooks-probe.js +160 -0
  6. package/dist/mcp-server/codex-hooks-probe.js.map +1 -0
  7. package/dist/mcp-server/config.d.ts +26 -2
  8. package/dist/mcp-server/config.d.ts.map +1 -1
  9. package/dist/mcp-server/config.js +54 -22
  10. package/dist/mcp-server/config.js.map +1 -1
  11. package/dist/mcp-server/hooks.d.ts +28 -0
  12. package/dist/mcp-server/hooks.d.ts.map +1 -1
  13. package/dist/mcp-server/hooks.js +91 -2
  14. package/dist/mcp-server/hooks.js.map +1 -1
  15. package/dist/mcp-server/index.d.ts +242 -2
  16. package/dist/mcp-server/index.d.ts.map +1 -1
  17. package/dist/mcp-server/index.js +806 -240
  18. package/dist/mcp-server/index.js.map +1 -1
  19. package/dist/mcp-server/tool-schemas.d.ts +32 -2
  20. package/dist/mcp-server/tool-schemas.d.ts.map +1 -1
  21. package/dist/mcp-server/tool-schemas.js +55 -0
  22. package/dist/mcp-server/tool-schemas.js.map +1 -1
  23. package/dist/src/audrey.d.ts +14 -2
  24. package/dist/src/audrey.d.ts.map +1 -1
  25. package/dist/src/audrey.js +152 -28
  26. package/dist/src/audrey.js.map +1 -1
  27. package/dist/src/autopilot.d.ts +22 -0
  28. package/dist/src/autopilot.d.ts.map +1 -1
  29. package/dist/src/autopilot.js +271 -50
  30. package/dist/src/autopilot.js.map +1 -1
  31. package/dist/src/capsule.d.ts +23 -0
  32. package/dist/src/capsule.d.ts.map +1 -1
  33. package/dist/src/capsule.js +56 -11
  34. package/dist/src/capsule.js.map +1 -1
  35. package/dist/src/confidence.d.ts +9 -1
  36. package/dist/src/confidence.d.ts.map +1 -1
  37. package/dist/src/confidence.js +16 -2
  38. package/dist/src/confidence.js.map +1 -1
  39. package/dist/src/consolidate.d.ts +4 -0
  40. package/dist/src/consolidate.d.ts.map +1 -1
  41. package/dist/src/consolidate.js +206 -34
  42. package/dist/src/consolidate.js.map +1 -1
  43. package/dist/src/controller.d.ts +17 -1
  44. package/dist/src/controller.d.ts.map +1 -1
  45. package/dist/src/controller.js +244 -128
  46. package/dist/src/controller.js.map +1 -1
  47. package/dist/src/db.d.ts.map +1 -1
  48. package/dist/src/db.js +233 -56
  49. package/dist/src/db.js.map +1 -1
  50. package/dist/src/encode.d.ts +2 -1
  51. package/dist/src/encode.d.ts.map +1 -1
  52. package/dist/src/encode.js +41 -4
  53. package/dist/src/encode.js.map +1 -1
  54. package/dist/src/events.d.ts +48 -1
  55. package/dist/src/events.d.ts.map +1 -1
  56. package/dist/src/events.js +160 -62
  57. package/dist/src/events.js.map +1 -1
  58. package/dist/src/export.d.ts.map +1 -1
  59. package/dist/src/export.js +4 -4
  60. package/dist/src/export.js.map +1 -1
  61. package/dist/src/grounding.d.ts +111 -0
  62. package/dist/src/grounding.d.ts.map +1 -0
  63. package/dist/src/grounding.js +259 -0
  64. package/dist/src/grounding.js.map +1 -0
  65. package/dist/src/hybrid-recall.d.ts +16 -7
  66. package/dist/src/hybrid-recall.d.ts.map +1 -1
  67. package/dist/src/hybrid-recall.js +22 -11
  68. package/dist/src/hybrid-recall.js.map +1 -1
  69. package/dist/src/import.d.ts +10 -0
  70. package/dist/src/import.d.ts.map +1 -1
  71. package/dist/src/import.js +122 -22
  72. package/dist/src/import.js.map +1 -1
  73. package/dist/src/llm.d.ts.map +1 -1
  74. package/dist/src/llm.js +16 -0
  75. package/dist/src/llm.js.map +1 -1
  76. package/dist/src/preflight.d.ts.map +1 -1
  77. package/dist/src/preflight.js +89 -47
  78. package/dist/src/preflight.js.map +1 -1
  79. package/dist/src/project.d.ts +4 -1
  80. package/dist/src/project.d.ts.map +1 -1
  81. package/dist/src/project.js +65 -5
  82. package/dist/src/project.js.map +1 -1
  83. package/dist/src/recall.d.ts.map +1 -1
  84. package/dist/src/recall.js +138 -13
  85. package/dist/src/recall.js.map +1 -1
  86. package/dist/src/redact.d.ts +1 -1
  87. package/dist/src/redact.d.ts.map +1 -1
  88. package/dist/src/redact.js +185 -5
  89. package/dist/src/redact.js.map +1 -1
  90. package/dist/src/routes.d.ts.map +1 -1
  91. package/dist/src/routes.js +91 -18
  92. package/dist/src/routes.js.map +1 -1
  93. package/dist/src/trust.d.ts +35 -0
  94. package/dist/src/trust.d.ts.map +1 -0
  95. package/dist/src/trust.js +77 -0
  96. package/dist/src/trust.js.map +1 -0
  97. package/dist/src/types.d.ts +24 -0
  98. package/dist/src/types.d.ts.map +1 -1
  99. package/package.json +3 -37
  100. package/benchmarks/adapter-kit.mjs +0 -20
  101. package/benchmarks/adapter-self-test.mjs +0 -170
  102. package/benchmarks/adapters/example-allow.mjs +0 -31
  103. package/benchmarks/adapters/mem0-platform.mjs +0 -274
  104. package/benchmarks/adapters/registry.json +0 -51
  105. package/benchmarks/adapters/zep-cloud.mjs +0 -304
  106. package/benchmarks/baselines.js +0 -174
  107. package/benchmarks/build-leaderboard.mjs +0 -183
  108. package/benchmarks/cases.js +0 -549
  109. package/benchmarks/create-conformance-card.mjs +0 -148
  110. package/benchmarks/create-submission-bundle.mjs +0 -190
  111. package/benchmarks/dry-run-external-adapters.mjs +0 -177
  112. package/benchmarks/guardbench.js +0 -1265
  113. package/benchmarks/output/adapter-self-test/guardbench-adapter-self-test.json +0 -50
  114. package/benchmarks/output/external/guardbench-external-dry-run.json +0 -69
  115. package/benchmarks/output/external/guardbench-external-evidence.json +0 -56
  116. package/benchmarks/output/guardbench-conformance-card.json +0 -63
  117. package/benchmarks/output/guardbench-manifest.json +0 -414
  118. package/benchmarks/output/guardbench-raw.json +0 -1279
  119. package/benchmarks/output/guardbench-summary.json +0 -2123
  120. package/benchmarks/output/leaderboard/guardbench-leaderboard.json +0 -93
  121. package/benchmarks/output/leaderboard/guardbench-leaderboard.md +0 -7
  122. package/benchmarks/output/submission-bundle/guardbench-conformance-card.json +0 -63
  123. package/benchmarks/output/submission-bundle/guardbench-manifest.json +0 -414
  124. package/benchmarks/output/submission-bundle/guardbench-raw.json +0 -1279
  125. package/benchmarks/output/submission-bundle/guardbench-summary.json +0 -2123
  126. package/benchmarks/output/submission-bundle/schemas/guardbench-adapter-registry.schema.json +0 -69
  127. package/benchmarks/output/submission-bundle/schemas/guardbench-adapter-self-test.schema.json +0 -156
  128. package/benchmarks/output/submission-bundle/schemas/guardbench-conformance-card.schema.json +0 -184
  129. package/benchmarks/output/submission-bundle/schemas/guardbench-external-dry-run.schema.json +0 -74
  130. package/benchmarks/output/submission-bundle/schemas/guardbench-external-evidence.schema.json +0 -108
  131. package/benchmarks/output/submission-bundle/schemas/guardbench-external-run.schema.json +0 -160
  132. package/benchmarks/output/submission-bundle/schemas/guardbench-leaderboard.schema.json +0 -179
  133. package/benchmarks/output/submission-bundle/schemas/guardbench-manifest.schema.json +0 -213
  134. package/benchmarks/output/submission-bundle/schemas/guardbench-publication-verification.schema.json +0 -47
  135. package/benchmarks/output/submission-bundle/schemas/guardbench-raw.schema.json +0 -184
  136. package/benchmarks/output/submission-bundle/schemas/guardbench-submission-manifest.schema.json +0 -151
  137. package/benchmarks/output/submission-bundle/schemas/guardbench-summary.schema.json +0 -249
  138. package/benchmarks/output/submission-bundle/submission-manifest.json +0 -131
  139. package/benchmarks/output/submission-bundle/validation-report.json +0 -31
  140. package/benchmarks/output/summary.json +0 -2354
  141. package/benchmarks/perf-snapshot.js +0 -307
  142. package/benchmarks/perf.bench.js +0 -169
  143. package/benchmarks/public-paths.mjs +0 -97
  144. package/benchmarks/reference-results.js +0 -75
  145. package/benchmarks/report.js +0 -280
  146. package/benchmarks/run-external-guardbench.mjs +0 -303
  147. package/benchmarks/run.js +0 -735
  148. package/benchmarks/schemas/guardbench-adapter-registry.schema.json +0 -69
  149. package/benchmarks/schemas/guardbench-adapter-self-test.schema.json +0 -156
  150. package/benchmarks/schemas/guardbench-conformance-card.schema.json +0 -184
  151. package/benchmarks/schemas/guardbench-external-dry-run.schema.json +0 -74
  152. package/benchmarks/schemas/guardbench-external-evidence.schema.json +0 -108
  153. package/benchmarks/schemas/guardbench-external-run.schema.json +0 -160
  154. package/benchmarks/schemas/guardbench-leaderboard.schema.json +0 -179
  155. package/benchmarks/schemas/guardbench-manifest.schema.json +0 -213
  156. package/benchmarks/schemas/guardbench-publication-verification.schema.json +0 -47
  157. package/benchmarks/schemas/guardbench-raw.schema.json +0 -184
  158. package/benchmarks/schemas/guardbench-submission-manifest.schema.json +0 -151
  159. package/benchmarks/schemas/guardbench-summary.schema.json +0 -249
  160. package/benchmarks/snapshots/perf-0.22.2.json +0 -123
  161. package/benchmarks/snapshots/perf-0.23.0.json +0 -123
  162. package/benchmarks/validate-adapter-module.mjs +0 -107
  163. package/benchmarks/validate-adapter-registry.mjs +0 -145
  164. package/benchmarks/validate-adapter-self-test.mjs +0 -96
  165. package/benchmarks/validate-guardbench-artifacts.mjs +0 -400
  166. package/benchmarks/verify-external-evidence.mjs +0 -351
  167. package/benchmarks/verify-publication-artifacts.mjs +0 -309
  168. package/benchmarks/verify-submission-bundle.mjs +0 -172
  169. package/docs/AUDREY_PAPER_OUTLINE.md +0 -178
  170. package/docs/MEMORY_BENCHMARKING.md +0 -59
  171. package/docs/PRODUCTION_BACKLOG.md +0 -321
  172. package/docs/assets/audrey-feature-grid.jpg +0 -0
  173. package/docs/assets/audrey-logo.svg +0 -45
  174. package/docs/assets/audrey-wordmark.png +0 -0
  175. package/docs/paper/00-master.md +0 -48
  176. package/docs/paper/01-introduction.md +0 -27
  177. package/docs/paper/02-related-work.md +0 -47
  178. package/docs/paper/03-problem-definition.md +0 -108
  179. package/docs/paper/04-design.md +0 -164
  180. package/docs/paper/05-guardbench-spec.md +0 -412
  181. package/docs/paper/06-implementation.md +0 -115
  182. package/docs/paper/07-evaluation.md +0 -168
  183. package/docs/paper/08-discussion-limitations.md +0 -61
  184. package/docs/paper/09-conclusion.md +0 -11
  185. package/docs/paper/SUBMISSION_README.md +0 -162
  186. package/docs/paper/appendix-a-demo-transcript.md +0 -114
  187. package/docs/paper/arxiv-compile-report.schema.json +0 -116
  188. package/docs/paper/arxiv-source.schema.json +0 -61
  189. package/docs/paper/audrey-paper-v1.md +0 -1108
  190. package/docs/paper/browser-launch-plan.json +0 -209
  191. package/docs/paper/browser-launch-plan.schema.json +0 -100
  192. package/docs/paper/browser-launch-results.json +0 -86
  193. package/docs/paper/browser-launch-results.schema.json +0 -66
  194. package/docs/paper/claim-register.json +0 -138
  195. package/docs/paper/claim-register.schema.json +0 -81
  196. package/docs/paper/evidence-ledger.md +0 -103
  197. package/docs/paper/output/arxiv/README-arxiv.txt +0 -8
  198. package/docs/paper/output/arxiv/arxiv-manifest.json +0 -41
  199. package/docs/paper/output/arxiv/main.tex +0 -951
  200. package/docs/paper/output/arxiv/references.bib +0 -222
  201. package/docs/paper/output/arxiv-compile-report.json +0 -24
  202. package/docs/paper/output/submission-bundle/LICENSE +0 -21
  203. package/docs/paper/output/submission-bundle/README.md +0 -440
  204. package/docs/paper/output/submission-bundle/benchmarks/output/adapter-self-test/guardbench-adapter-self-test.json +0 -50
  205. package/docs/paper/output/submission-bundle/benchmarks/output/external/guardbench-external-dry-run.json +0 -69
  206. package/docs/paper/output/submission-bundle/benchmarks/output/external/guardbench-external-evidence.json +0 -56
  207. package/docs/paper/output/submission-bundle/benchmarks/output/guardbench-conformance-card.json +0 -63
  208. package/docs/paper/output/submission-bundle/benchmarks/output/guardbench-manifest.json +0 -414
  209. package/docs/paper/output/submission-bundle/benchmarks/output/guardbench-raw.json +0 -1279
  210. package/docs/paper/output/submission-bundle/benchmarks/output/guardbench-summary.json +0 -2123
  211. package/docs/paper/output/submission-bundle/benchmarks/output/leaderboard/guardbench-leaderboard.json +0 -93
  212. package/docs/paper/output/submission-bundle/benchmarks/output/leaderboard/guardbench-leaderboard.md +0 -7
  213. package/docs/paper/output/submission-bundle/benchmarks/output/submission-bundle/submission-manifest.json +0 -131
  214. package/docs/paper/output/submission-bundle/benchmarks/output/submission-bundle/validation-report.json +0 -31
  215. package/docs/paper/output/submission-bundle/benchmarks/output/summary.json +0 -2354
  216. package/docs/paper/output/submission-bundle/benchmarks/schemas/guardbench-adapter-registry.schema.json +0 -69
  217. package/docs/paper/output/submission-bundle/benchmarks/schemas/guardbench-adapter-self-test.schema.json +0 -156
  218. package/docs/paper/output/submission-bundle/benchmarks/schemas/guardbench-conformance-card.schema.json +0 -184
  219. package/docs/paper/output/submission-bundle/benchmarks/schemas/guardbench-external-dry-run.schema.json +0 -74
  220. package/docs/paper/output/submission-bundle/benchmarks/schemas/guardbench-external-evidence.schema.json +0 -108
  221. package/docs/paper/output/submission-bundle/benchmarks/schemas/guardbench-external-run.schema.json +0 -160
  222. package/docs/paper/output/submission-bundle/benchmarks/schemas/guardbench-leaderboard.schema.json +0 -179
  223. package/docs/paper/output/submission-bundle/benchmarks/schemas/guardbench-manifest.schema.json +0 -213
  224. package/docs/paper/output/submission-bundle/benchmarks/schemas/guardbench-publication-verification.schema.json +0 -47
  225. package/docs/paper/output/submission-bundle/benchmarks/schemas/guardbench-raw.schema.json +0 -184
  226. package/docs/paper/output/submission-bundle/benchmarks/schemas/guardbench-submission-manifest.schema.json +0 -151
  227. package/docs/paper/output/submission-bundle/benchmarks/schemas/guardbench-summary.schema.json +0 -249
  228. package/docs/paper/output/submission-bundle/docs/AUDREY_PAPER_OUTLINE.md +0 -178
  229. package/docs/paper/output/submission-bundle/docs/paper/00-master.md +0 -48
  230. package/docs/paper/output/submission-bundle/docs/paper/01-introduction.md +0 -27
  231. package/docs/paper/output/submission-bundle/docs/paper/02-related-work.md +0 -47
  232. package/docs/paper/output/submission-bundle/docs/paper/03-problem-definition.md +0 -108
  233. package/docs/paper/output/submission-bundle/docs/paper/04-design.md +0 -164
  234. package/docs/paper/output/submission-bundle/docs/paper/05-guardbench-spec.md +0 -412
  235. package/docs/paper/output/submission-bundle/docs/paper/06-implementation.md +0 -115
  236. package/docs/paper/output/submission-bundle/docs/paper/07-evaluation.md +0 -168
  237. package/docs/paper/output/submission-bundle/docs/paper/08-discussion-limitations.md +0 -61
  238. package/docs/paper/output/submission-bundle/docs/paper/09-conclusion.md +0 -11
  239. package/docs/paper/output/submission-bundle/docs/paper/SUBMISSION_README.md +0 -162
  240. package/docs/paper/output/submission-bundle/docs/paper/appendix-a-demo-transcript.md +0 -114
  241. package/docs/paper/output/submission-bundle/docs/paper/arxiv-compile-report.schema.json +0 -116
  242. package/docs/paper/output/submission-bundle/docs/paper/arxiv-source.schema.json +0 -61
  243. package/docs/paper/output/submission-bundle/docs/paper/audrey-paper-v1.md +0 -1108
  244. package/docs/paper/output/submission-bundle/docs/paper/browser-launch-plan.json +0 -209
  245. package/docs/paper/output/submission-bundle/docs/paper/browser-launch-plan.schema.json +0 -100
  246. package/docs/paper/output/submission-bundle/docs/paper/browser-launch-results.json +0 -86
  247. package/docs/paper/output/submission-bundle/docs/paper/browser-launch-results.schema.json +0 -66
  248. package/docs/paper/output/submission-bundle/docs/paper/claim-register.json +0 -138
  249. package/docs/paper/output/submission-bundle/docs/paper/claim-register.schema.json +0 -81
  250. package/docs/paper/output/submission-bundle/docs/paper/evidence-ledger.md +0 -103
  251. package/docs/paper/output/submission-bundle/docs/paper/output/arxiv/README-arxiv.txt +0 -8
  252. package/docs/paper/output/submission-bundle/docs/paper/output/arxiv/arxiv-manifest.json +0 -41
  253. package/docs/paper/output/submission-bundle/docs/paper/output/arxiv/main.tex +0 -951
  254. package/docs/paper/output/submission-bundle/docs/paper/output/arxiv/references.bib +0 -222
  255. package/docs/paper/output/submission-bundle/docs/paper/output/arxiv-compile-report.json +0 -24
  256. package/docs/paper/output/submission-bundle/docs/paper/paper-submission-bundle.schema.json +0 -70
  257. package/docs/paper/output/submission-bundle/docs/paper/publication-pack.json +0 -81
  258. package/docs/paper/output/submission-bundle/docs/paper/publication-pack.schema.json +0 -60
  259. package/docs/paper/output/submission-bundle/docs/paper/references.bib +0 -222
  260. package/docs/paper/output/submission-bundle/package.json +0 -235
  261. package/docs/paper/output/submission-bundle/paper-submission-manifest.json +0 -379
  262. package/docs/paper/paper-submission-bundle.schema.json +0 -70
  263. package/docs/paper/publication-pack.json +0 -81
  264. package/docs/paper/publication-pack.schema.json +0 -60
  265. package/docs/paper/references.bib +0 -222
  266. package/scripts/audit-release-completion.mjs +0 -440
  267. package/scripts/create-arxiv-source.mjs +0 -368
  268. package/scripts/create-paper-submission-bundle.mjs +0 -214
  269. package/scripts/finalize-release.mjs +0 -601
  270. package/scripts/prepare-release-cut.mjs +0 -277
  271. package/scripts/publish-release-bundle.mjs +0 -252
  272. package/scripts/publish-release-github-api.mjs +0 -494
  273. package/scripts/run-vitest.mjs +0 -34
  274. package/scripts/smoke-cli.js +0 -92
  275. package/scripts/sync-paper-artifacts.mjs +0 -112
  276. package/scripts/verify-arxiv-compile.mjs +0 -476
  277. package/scripts/verify-arxiv-source.mjs +0 -224
  278. package/scripts/verify-browser-launch-plan.mjs +0 -254
  279. package/scripts/verify-browser-launch-results.mjs +0 -303
  280. package/scripts/verify-paper-artifacts.mjs +0 -798
  281. package/scripts/verify-paper-claims.mjs +0 -254
  282. package/scripts/verify-paper-submission-bundle.mjs +0 -218
  283. package/scripts/verify-publication-pack.mjs +0 -210
  284. package/scripts/verify-python-package.py +0 -201
  285. package/scripts/verify-release-readiness.mjs +0 -920
@@ -1,160 +0,0 @@
1
- {
2
- "$schema": "https://json-schema.org/draft/2020-12/schema",
3
- "$id": "https://audrey-memory.org/schemas/guardbench-external-run.schema.json",
4
- "title": "GuardBench External Run Metadata",
5
- "type": "object",
6
- "additionalProperties": false,
7
- "required": [
8
- "suite",
9
- "startedAt",
10
- "adapter",
11
- "adapterPath",
12
- "outDir",
13
- "requiredEnv",
14
- "missingEnv",
15
- "command",
16
- "validationCommand",
17
- "dryRun",
18
- "status"
19
- ],
20
- "properties": {
21
- "suite": { "const": "GuardBench external adapter run" },
22
- "startedAt": { "type": "string", "minLength": 1 },
23
- "completedAt": { "type": "string", "minLength": 1 },
24
- "adapter": { "type": "string", "minLength": 1 },
25
- "adapterPath": { "type": "string", "minLength": 1 },
26
- "outDir": { "type": "string", "minLength": 1 },
27
- "requiredEnv": {
28
- "type": "array",
29
- "items": { "type": "string", "minLength": 1 }
30
- },
31
- "missingEnv": {
32
- "type": "array",
33
- "items": { "type": "string", "minLength": 1 }
34
- },
35
- "command": {
36
- "type": "array",
37
- "minItems": 1,
38
- "items": { "type": "string", "minLength": 1 }
39
- },
40
- "validationCommand": {
41
- "type": "array",
42
- "minItems": 1,
43
- "items": { "type": "string", "minLength": 1 }
44
- },
45
- "dryRun": { "type": "boolean" },
46
- "status": {
47
- "enum": [
48
- "blocked",
49
- "dry-run-missing-env",
50
- "dry-run-ready",
51
- "failed",
52
- "passed",
53
- "running"
54
- ]
55
- },
56
- "blockReason": { "type": "string", "minLength": 1 },
57
- "exitCode": {
58
- "anyOf": [
59
- { "type": "integer" },
60
- { "type": "null" }
61
- ]
62
- },
63
- "signal": {
64
- "anyOf": [
65
- { "type": "string", "minLength": 1 },
66
- { "type": "null" }
67
- ]
68
- },
69
- "artifactHashes": { "$ref": "#/$defs/artifactHashes" },
70
- "artifactValidation": { "$ref": "#/$defs/artifactValidation" },
71
- "adapterConformance": { "$ref": "#/$defs/adapterConformance" }
72
- },
73
- "$defs": {
74
- "artifactHashes": {
75
- "type": "object",
76
- "additionalProperties": false,
77
- "required": [
78
- "guardbench-manifest.json",
79
- "guardbench-summary.json",
80
- "guardbench-raw.json"
81
- ],
82
- "properties": {
83
- "guardbench-manifest.json": { "$ref": "#/$defs/sha256" },
84
- "guardbench-summary.json": { "$ref": "#/$defs/sha256" },
85
- "guardbench-raw.json": { "$ref": "#/$defs/sha256" }
86
- }
87
- },
88
- "sha256": {
89
- "type": "string",
90
- "pattern": "^[a-f0-9]{64}$"
91
- },
92
- "artifactValidation": {
93
- "type": "object",
94
- "additionalProperties": false,
95
- "required": ["ok", "dir", "schemasDir", "files", "failures"],
96
- "properties": {
97
- "ok": { "type": "boolean" },
98
- "dir": { "type": "string", "minLength": 1 },
99
- "schemasDir": { "type": "string", "minLength": 1 },
100
- "files": {
101
- "type": "array",
102
- "minItems": 3,
103
- "items": { "type": "string", "minLength": 1 }
104
- },
105
- "optionalFiles": {
106
- "type": "array",
107
- "items": { "type": "string", "minLength": 1 }
108
- },
109
- "failures": {
110
- "type": "array",
111
- "items": { "type": "string" }
112
- }
113
- }
114
- },
115
- "adapterConformance": {
116
- "type": "object",
117
- "additionalProperties": false,
118
- "required": [
119
- "ok",
120
- "adapter",
121
- "requestedAdapter",
122
- "scenarios",
123
- "expectedScenarios",
124
- "fullContractPassRate",
125
- "decisionAccuracy",
126
- "redactionLeaks",
127
- "failures"
128
- ],
129
- "properties": {
130
- "ok": { "type": "boolean" },
131
- "adapter": { "type": "string", "minLength": 1 },
132
- "requestedAdapter": { "type": "string", "minLength": 1 },
133
- "scenarios": { "type": "integer", "minimum": 0 },
134
- "expectedScenarios": { "type": "integer", "minimum": 0 },
135
- "fullContractPassRate": {
136
- "anyOf": [
137
- { "type": "null" },
138
- { "type": "number", "minimum": 0, "maximum": 1 }
139
- ]
140
- },
141
- "decisionAccuracy": {
142
- "anyOf": [
143
- { "type": "null" },
144
- { "type": "number", "minimum": 0, "maximum": 1 }
145
- ]
146
- },
147
- "redactionLeaks": {
148
- "anyOf": [
149
- { "type": "null" },
150
- { "type": "integer", "minimum": 0 }
151
- ]
152
- },
153
- "failures": {
154
- "type": "array",
155
- "items": { "type": "string" }
156
- }
157
- }
158
- }
159
- }
160
- }
@@ -1,179 +0,0 @@
1
- {
2
- "$schema": "https://json-schema.org/draft/2020-12/schema",
3
- "$id": "https://audrey-memory.org/schemas/guardbench-leaderboard.schema.json",
4
- "title": "GuardBench Leaderboard",
5
- "type": "object",
6
- "additionalProperties": false,
7
- "required": ["schemaVersion", "suite", "generatedAt", "ranking", "rows", "failures"],
8
- "properties": {
9
- "schemaVersion": { "const": "1.0.0" },
10
- "suite": { "const": "GuardBench leaderboard" },
11
- "generatedAt": { "type": "string", "minLength": 1 },
12
- "ranking": {
13
- "type": "array",
14
- "minItems": 1,
15
- "items": { "type": "string", "minLength": 1 }
16
- },
17
- "rows": {
18
- "type": "array",
19
- "items": { "$ref": "#/$defs/row" }
20
- },
21
- "failures": {
22
- "type": "array",
23
- "items": { "type": "string" }
24
- }
25
- },
26
- "$defs": {
27
- "row": {
28
- "type": "object",
29
- "additionalProperties": false,
30
- "required": [
31
- "rank",
32
- "subject",
33
- "score",
34
- "conformance",
35
- "source",
36
- "verification"
37
- ],
38
- "properties": {
39
- "rank": { "type": "integer", "minimum": 1 },
40
- "subject": { "$ref": "#/$defs/subject" },
41
- "score": { "$ref": "#/$defs/score" },
42
- "conformance": { "$ref": "#/$defs/conformance" },
43
- "source": { "$ref": "#/$defs/source" },
44
- "verification": { "$ref": "#/$defs/verification" }
45
- }
46
- },
47
- "subject": {
48
- "type": "object",
49
- "additionalProperties": false,
50
- "required": ["name", "requestedAdapter", "external"],
51
- "properties": {
52
- "name": { "type": "string", "minLength": 1 },
53
- "requestedAdapter": {
54
- "anyOf": [
55
- { "type": "string", "minLength": 1 },
56
- { "type": "null" }
57
- ]
58
- },
59
- "external": { "type": "boolean" }
60
- }
61
- },
62
- "score": {
63
- "type": "object",
64
- "additionalProperties": false,
65
- "required": [
66
- "scenarios",
67
- "fullContractPassed",
68
- "fullContractPassRate",
69
- "decisionAccuracy",
70
- "evidenceRecall",
71
- "redactionLeaks",
72
- "latency"
73
- ],
74
- "properties": {
75
- "scenarios": { "type": "integer", "minimum": 0 },
76
- "fullContractPassed": { "$ref": "#/$defs/nullableNumber" },
77
- "fullContractPassRate": { "$ref": "#/$defs/nullableRate" },
78
- "decisionAccuracy": { "$ref": "#/$defs/nullableRate" },
79
- "evidenceRecall": { "$ref": "#/$defs/nullableRate" },
80
- "redactionLeaks": { "$ref": "#/$defs/nullableNumber" },
81
- "latency": {
82
- "anyOf": [
83
- {
84
- "type": "object",
85
- "additionalProperties": false,
86
- "required": ["p50Ms", "p95Ms", "maxMs"],
87
- "properties": {
88
- "p50Ms": { "type": "number", "minimum": 0 },
89
- "p95Ms": { "type": "number", "minimum": 0 },
90
- "maxMs": { "type": "number", "minimum": 0 }
91
- }
92
- },
93
- { "type": "null" }
94
- ]
95
- }
96
- }
97
- },
98
- "conformance": {
99
- "type": "object",
100
- "additionalProperties": false,
101
- "required": ["ok", "failures", "artifactValidationOk", "artifactValidationFailures"],
102
- "properties": {
103
- "ok": { "type": "boolean" },
104
- "failures": {
105
- "type": "array",
106
- "items": { "type": "string" }
107
- },
108
- "artifactValidationOk": { "type": "boolean" },
109
- "artifactValidationFailures": {
110
- "type": "array",
111
- "items": { "type": "string" }
112
- }
113
- }
114
- },
115
- "source": {
116
- "type": "object",
117
- "additionalProperties": false,
118
- "required": ["dir", "manifestGeneratedAt", "fileCount"],
119
- "properties": {
120
- "dir": { "type": "string", "minLength": 1 },
121
- "manifestGeneratedAt": { "type": "string", "minLength": 1 },
122
- "fileCount": { "type": "integer", "minimum": 0 }
123
- }
124
- },
125
- "verification": {
126
- "type": "object",
127
- "additionalProperties": false,
128
- "required": ["ok", "dir", "subject", "files", "artifactValidation", "failures"],
129
- "properties": {
130
- "ok": { "type": "boolean" },
131
- "dir": { "type": "string", "minLength": 1 },
132
- "subject": { "$ref": "#/$defs/subject" },
133
- "files": {
134
- "type": "array",
135
- "items": { "type": "string", "minLength": 1 }
136
- },
137
- "artifactValidation": { "$ref": "#/$defs/artifactValidation" },
138
- "failures": {
139
- "type": "array",
140
- "items": { "type": "string" }
141
- }
142
- }
143
- },
144
- "artifactValidation": {
145
- "type": "object",
146
- "additionalProperties": false,
147
- "required": ["ok", "dir", "schemasDir", "files", "optionalFiles", "failures"],
148
- "properties": {
149
- "ok": { "type": "boolean" },
150
- "dir": { "type": "string", "minLength": 1 },
151
- "schemasDir": { "type": "string", "minLength": 1 },
152
- "files": {
153
- "type": "array",
154
- "items": { "type": "string", "minLength": 1 }
155
- },
156
- "optionalFiles": {
157
- "type": "array",
158
- "items": { "type": "string", "minLength": 1 }
159
- },
160
- "failures": {
161
- "type": "array",
162
- "items": { "type": "string" }
163
- }
164
- }
165
- },
166
- "nullableNumber": {
167
- "anyOf": [
168
- { "type": "number", "minimum": 0 },
169
- { "type": "null" }
170
- ]
171
- },
172
- "nullableRate": {
173
- "anyOf": [
174
- { "type": "number", "minimum": 0, "maximum": 1 },
175
- { "type": "null" }
176
- ]
177
- }
178
- }
179
- }
@@ -1,213 +0,0 @@
1
- {
2
- "$schema": "https://json-schema.org/draft/2020-12/schema",
3
- "$id": "https://audrey-memory.org/schemas/guardbench-manifest.schema.json",
4
- "title": "GuardBench Manifest",
5
- "type": "object",
6
- "additionalProperties": false,
7
- "required": [
8
- "manifestVersion",
9
- "suiteId",
10
- "suiteName",
11
- "generatedBy",
12
- "decisionVocabulary",
13
- "subjects",
14
- "metrics",
15
- "contract",
16
- "scenarios"
17
- ],
18
- "properties": {
19
- "manifestVersion": { "type": "string", "minLength": 1 },
20
- "suiteId": { "type": "string", "minLength": 1 },
21
- "suiteName": { "type": "string", "minLength": 1 },
22
- "generatedBy": { "type": "string", "minLength": 1 },
23
- "decisionVocabulary": {
24
- "type": "array",
25
- "minItems": 3,
26
- "items": { "enum": ["allow", "warn", "block"] },
27
- "contains": { "const": "allow" }
28
- },
29
- "subjects": {
30
- "type": "array",
31
- "minItems": 5,
32
- "items": { "$ref": "#/$defs/subject" }
33
- },
34
- "metrics": {
35
- "type": "array",
36
- "minItems": 9,
37
- "items": {
38
- "enum": [
39
- "fullContractPassRate",
40
- "decisionAccuracy",
41
- "preventionRate",
42
- "falseBlockRate",
43
- "evidenceRecall",
44
- "redactionLeaks",
45
- "recallDegradationDetectionRate",
46
- "latencyP50Ms",
47
- "latencyP95Ms"
48
- ]
49
- }
50
- },
51
- "contract": {
52
- "type": "object",
53
- "additionalProperties": false,
54
- "required": ["fullContractPass", "externalAdapterRule"],
55
- "properties": {
56
- "fullContractPass": { "type": "string", "minLength": 1 },
57
- "externalAdapterRule": { "type": "string", "minLength": 1 }
58
- }
59
- },
60
- "scenarios": {
61
- "type": "array",
62
- "minItems": 10,
63
- "items": { "$ref": "#/$defs/scenario" }
64
- }
65
- },
66
- "$defs": {
67
- "subject": {
68
- "type": "object",
69
- "additionalProperties": false,
70
- "required": ["id", "name", "description", "external"],
71
- "properties": {
72
- "id": { "type": "string", "minLength": 1 },
73
- "name": { "type": "string", "minLength": 1 },
74
- "description": { "type": "string", "minLength": 1 },
75
- "external": { "type": "boolean" }
76
- }
77
- },
78
- "scenario": {
79
- "type": "object",
80
- "additionalProperties": false,
81
- "required": [
82
- "id",
83
- "name",
84
- "expectedDecision",
85
- "action",
86
- "seed",
87
- "expectedEvidenceClass",
88
- "requiredEvidence",
89
- "redactionSecretsSeeded"
90
- ],
91
- "properties": {
92
- "id": { "type": "string", "pattern": "^GB-[0-9]{2}$" },
93
- "name": { "type": "string", "minLength": 1 },
94
- "expectedDecision": { "enum": ["allow", "warn", "block"] },
95
- "action": { "$ref": "#/$defs/action" },
96
- "seed": { "$ref": "#/$defs/seed" },
97
- "expectedEvidenceClass": { "type": "string", "minLength": 1 },
98
- "requiredEvidence": {
99
- "type": "array",
100
- "items": { "type": "string", "minLength": 1 }
101
- },
102
- "redactionSecretsSeeded": { "type": "integer", "minimum": 0 }
103
- }
104
- },
105
- "action": {
106
- "type": "object",
107
- "additionalProperties": false,
108
- "required": ["tool", "action"],
109
- "properties": {
110
- "tool": { "type": "string", "minLength": 1 },
111
- "action": { "type": "string", "minLength": 1 },
112
- "command": { "type": "string", "minLength": 1 },
113
- "cwd": { "type": "string" },
114
- "files": {
115
- "type": "array",
116
- "items": { "type": "string", "minLength": 1 }
117
- }
118
- }
119
- },
120
- "seed": {
121
- "type": "object",
122
- "additionalProperties": false,
123
- "required": [
124
- "seededMemories",
125
- "seededToolEvents",
126
- "seededNoise",
127
- "faultInjection",
128
- "seededSecretRefs"
129
- ],
130
- "properties": {
131
- "seededMemories": {
132
- "type": "array",
133
- "items": { "$ref": "#/$defs/memorySeed" }
134
- },
135
- "seededToolEvents": {
136
- "type": "array",
137
- "items": { "$ref": "#/$defs/toolEventSeed" }
138
- },
139
- "seededNoise": {
140
- "anyOf": [
141
- { "type": "null" },
142
- { "$ref": "#/$defs/noiseSeed" }
143
- ]
144
- },
145
- "faultInjection": {
146
- "anyOf": [
147
- { "type": "null" },
148
- { "type": "string", "minLength": 1 }
149
- ]
150
- },
151
- "seededSecretRefs": {
152
- "type": "array",
153
- "items": { "$ref": "#/$defs/secretRef" }
154
- }
155
- }
156
- },
157
- "memorySeed": {
158
- "type": "object",
159
- "additionalProperties": false,
160
- "required": ["content", "source", "tags", "salience"],
161
- "properties": {
162
- "content": { "type": "string", "minLength": 1 },
163
- "source": { "type": "string", "minLength": 1 },
164
- "tags": {
165
- "type": "array",
166
- "items": { "type": "string", "minLength": 1 }
167
- },
168
- "salience": { "type": "number", "minimum": 0, "maximum": 1 }
169
- }
170
- },
171
- "toolEventSeed": {
172
- "type": "object",
173
- "additionalProperties": false,
174
- "required": ["tool"],
175
- "properties": {
176
- "tool": { "type": "string", "minLength": 1 },
177
- "action": { "type": "string", "minLength": 1 },
178
- "files": {
179
- "type": "array",
180
- "items": { "type": "string", "minLength": 1 }
181
- },
182
- "outcome": { "type": "string", "minLength": 1 },
183
- "errorSummary": { "type": "string", "minLength": 1 },
184
- "errorSummaryPattern": { "type": "string", "minLength": 1 },
185
- "output": { "type": "string", "minLength": 1 }
186
- }
187
- },
188
- "noiseSeed": {
189
- "type": "object",
190
- "additionalProperties": false,
191
- "required": ["count", "source", "tags", "salience"],
192
- "properties": {
193
- "count": { "type": "integer", "minimum": 0 },
194
- "source": { "type": "string", "minLength": 1 },
195
- "tags": {
196
- "type": "array",
197
- "items": { "type": "string", "minLength": 1 }
198
- },
199
- "salience": { "type": "number", "minimum": 0, "maximum": 1 }
200
- }
201
- },
202
- "secretRef": {
203
- "type": "object",
204
- "additionalProperties": false,
205
- "required": ["id", "fingerprint", "length"],
206
- "properties": {
207
- "id": { "type": "string", "minLength": 1 },
208
- "fingerprint": { "type": "string", "pattern": "^[a-f0-9]{16}$" },
209
- "length": { "type": "integer", "minimum": 1 }
210
- }
211
- }
212
- }
213
- }
@@ -1,47 +0,0 @@
1
- {
2
- "$schema": "https://json-schema.org/draft/2020-12/schema",
3
- "$id": "https://audrey-memory.org/schemas/guardbench-publication-verification.schema.json",
4
- "title": "GuardBench Publication Artifact Verification",
5
- "type": "object",
6
- "additionalProperties": false,
7
- "required": ["schemaVersion", "suite", "generatedAt", "ok", "checks", "failures"],
8
- "properties": {
9
- "schemaVersion": { "const": "1.0.0" },
10
- "suite": { "const": "GuardBench publication artifact verification" },
11
- "generatedAt": { "type": "string", "minLength": 1 },
12
- "ok": { "type": "boolean" },
13
- "checks": {
14
- "type": "object",
15
- "additionalProperties": false,
16
- "required": ["registry", "adapterModule", "selfTest", "artifacts", "bundle", "externalDryRun", "externalEvidence", "leaderboard", "localPaths"],
17
- "properties": {
18
- "registry": { "$ref": "#/$defs/basicCheck" },
19
- "adapterModule": { "$ref": "#/$defs/basicCheck" },
20
- "selfTest": { "$ref": "#/$defs/basicCheck" },
21
- "artifacts": { "$ref": "#/$defs/basicCheck" },
22
- "bundle": { "$ref": "#/$defs/basicCheck" },
23
- "externalDryRun": { "$ref": "#/$defs/basicCheck" },
24
- "externalEvidence": { "$ref": "#/$defs/basicCheck" },
25
- "leaderboard": { "$ref": "#/$defs/basicCheck" },
26
- "localPaths": { "$ref": "#/$defs/basicCheck" }
27
- }
28
- },
29
- "failures": {
30
- "type": "array",
31
- "items": { "type": "string" }
32
- }
33
- },
34
- "$defs": {
35
- "basicCheck": {
36
- "type": "object",
37
- "required": ["ok", "failures"],
38
- "properties": {
39
- "ok": { "type": "boolean" },
40
- "failures": {
41
- "type": "array",
42
- "items": { "type": "string" }
43
- }
44
- }
45
- }
46
- }
47
- }