@bjoernrochel/sevro 0.1.0-rc.2 → 0.1.0-rc.21

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 (243) hide show
  1. package/CONTRIBUTING.md +170 -0
  2. package/LICENSE +63 -136
  3. package/README.md +83 -66
  4. package/docs/README.md +44 -0
  5. package/docs/acknowledgements.md +14 -0
  6. package/docs/architecture.md +146 -0
  7. package/docs/assets/README.md +27 -0
  8. package/docs/assets/sevro-logo.png +0 -0
  9. package/docs/assets/sevro-symbol.svg +1 -0
  10. package/docs/assets/sevro-wordmark.svg +1 -0
  11. package/docs/builtin-graders-v1.md +41 -13
  12. package/docs/codex-host.md +184 -52
  13. package/docs/contracts.md +19 -0
  14. package/docs/creating-cases.md +139 -0
  15. package/docs/development-cli.md +190 -30
  16. package/docs/documentation-quality.md +61 -0
  17. package/docs/evaluation-workflow.md +110 -0
  18. package/docs/evidence/code-mode-controls-71.md +64 -0
  19. package/docs/evidence/code-mode-programs-85.md +64 -0
  20. package/docs/evidence/codex-state-73/README.md +204 -0
  21. package/docs/evidence/codex-state-73/darrow-migration.patch +182 -0
  22. package/docs/evidence/codex-state-73/results.json +661 -0
  23. package/docs/evidence/local-http-74.md +104 -0
  24. package/docs/evidence/runtime-startup-30/README.md +185 -0
  25. package/docs/evidence/runtime-startup-30/after.json +319 -0
  26. package/docs/evidence/runtime-startup-30/baseline-timeout.jsonl +2 -0
  27. package/docs/evidence/runtime-startup-30/before.json +403 -0
  28. package/docs/evidence/runtime-startup-30/consumer-smoke.json +63 -0
  29. package/docs/evidence/runtime-startup-30/full-policy-diagnostic.jsonl +3 -0
  30. package/docs/evidence/runtime-startup-30/minimal-policy-diagnostic.jsonl +3 -0
  31. package/docs/evidence/runtime-startup-30/plugin-template-assessment.json +20 -0
  32. package/docs/evidence/runtime-startup-30/seedless-timeout.jsonl +2 -0
  33. package/docs/evidence/skill-reads-70/results.json +823 -0
  34. package/docs/evidence.md +21 -0
  35. package/docs/extension-protocol-v1.md +50 -16
  36. package/docs/fixture-cleanup-validation.md +3 -0
  37. package/docs/getting-started.md +102 -0
  38. package/docs/guide-evaluation.md +89 -0
  39. package/docs/guide-verification.json +239 -0
  40. package/docs/identity-v1.md +35 -1
  41. package/docs/installing.md +88 -0
  42. package/docs/licenses/BUSL-1.1-0.1.0-rc.2.txt +159 -0
  43. package/docs/licensing.md +42 -0
  44. package/docs/native-controls.md +76 -5
  45. package/docs/native-hosts.md +228 -0
  46. package/docs/reading-results.md +141 -0
  47. package/docs/recipes.md +489 -0
  48. package/docs/releases.md +81 -40
  49. package/docs/report-v1.md +29 -1
  50. package/docs/results-v1.md +180 -0
  51. package/docs/run-settings-v1.md +147 -0
  52. package/docs/running-evaluations.md +31 -0
  53. package/docs/runtime-v1.md +614 -0
  54. package/docs/specs/repository-guide.md +58 -0
  55. package/docs/troubleshooting.md +30 -0
  56. package/docs/typescript-quality.md +234 -0
  57. package/docs/usability-study.md +114 -0
  58. package/examples/basic/host.ts +2 -2
  59. package/examples/recipes/candidate.ts +26 -0
  60. package/examples/recipes/cases/coding-change.json +21 -0
  61. package/examples/recipes/cases/host-tools.json +21 -0
  62. package/examples/recipes/cases/mise.json +21 -0
  63. package/examples/recipes/cases/node.json +21 -0
  64. package/examples/recipes/cases/python-uv.json +21 -0
  65. package/examples/recipes/cases/semantic.json +17 -0
  66. package/examples/recipes/coding-change/check.ts +23 -0
  67. package/examples/recipes/extension-artifacts.ts +65 -0
  68. package/examples/recipes/extension-methods.ts +174 -0
  69. package/examples/recipes/extension.ts +37 -0
  70. package/examples/recipes/repository-skill/.agents/skills/startup-guide/SKILL.md +7 -0
  71. package/examples/recipes/repository-skill/.claude/skills/startup-guide/SKILL.md +7 -0
  72. package/examples/recipes/repository-skill/README.md +3 -0
  73. package/examples/recipes/run-inputs.ts +188 -0
  74. package/examples/recipes/run-options.ts +131 -0
  75. package/examples/recipes/run.ts +63 -0
  76. package/examples/recipes/runtime/empty.json +1 -0
  77. package/examples/recipes/runtime/goals.json +1 -0
  78. package/examples/recipes/runtime/mise.json +6 -0
  79. package/examples/recipes/runtime/path.json +1 -0
  80. package/examples/recipes/runtime/plugins.json +4 -0
  81. package/examples/recipes/runtime/python-uv.json +10 -0
  82. package/examples/recipes/semantic-judge.ts +29 -0
  83. package/examples/templates/coding/adapter.ts +17 -0
  84. package/examples/templates/coding/case.json +15 -0
  85. package/examples/templates/repository-skill/.agents/skills/startup-guide/SKILL.md +6 -0
  86. package/examples/templates/repository-skill/extension-data.ts +64 -0
  87. package/examples/templates/repository-skill/extension.ts +31 -0
  88. package/examples/templates/response/adapter.ts +12 -0
  89. package/examples/templates/response/case.json +13 -0
  90. package/package.json +39 -6
  91. package/schemas/report-v1.schema.json +9 -0
  92. package/schemas/run-evidence-v1.schema.json +2 -1
  93. package/schemas/runtime-v1.schema.json +193 -0
  94. package/src/advisory.ts +10 -5
  95. package/src/candidate-artifacts.ts +208 -0
  96. package/src/candidate-codex-state.ts +185 -0
  97. package/src/case-validation.ts +105 -0
  98. package/src/cli/cancellation.ts +20 -0
  99. package/src/cli/command.ts +81 -0
  100. package/src/cli/completion.ts +15 -0
  101. package/src/cli/demo.ts +59 -0
  102. package/src/cli/evaluation.ts +55 -0
  103. package/src/cli/extension.ts +79 -0
  104. package/src/cli/help.ts +222 -0
  105. package/src/cli/hosts.ts +59 -0
  106. package/src/cli/init-settings.ts +30 -0
  107. package/src/cli/init.ts +111 -0
  108. package/src/cli/invocation.ts +627 -0
  109. package/src/cli/loading.ts +151 -0
  110. package/src/cli/preparation.ts +163 -0
  111. package/src/cli/presentation.ts +91 -0
  112. package/src/cli/progress.ts +6 -0
  113. package/src/cli/run-manifest.ts +133 -0
  114. package/src/cli/run-options.ts +101 -0
  115. package/src/cli/run-overrides.ts +83 -0
  116. package/src/cli/settings.ts +160 -0
  117. package/src/cli/summary.ts +43 -0
  118. package/src/cli.ts +13 -843
  119. package/src/contract-types.ts +94 -0
  120. package/src/engine.ts +19 -2373
  121. package/src/evaluation/advisory.ts +150 -0
  122. package/src/evaluation/check-plan.ts +510 -0
  123. package/src/evaluation/collection.ts +88 -0
  124. package/src/evaluation/context.ts +10 -0
  125. package/src/evaluation/grading-host.ts +39 -0
  126. package/src/evaluation/grading.ts +258 -0
  127. package/src/evaluation/invocation-plan.ts +548 -0
  128. package/src/evaluation/plan.ts +736 -0
  129. package/src/evaluation/progress.ts +19 -0
  130. package/src/evaluation/resources.ts +241 -0
  131. package/src/evaluation/run.ts +206 -0
  132. package/src/{trial-scheduler.ts → evaluation/scheduler.ts} +3 -1
  133. package/src/evaluation/semantic.ts +312 -0
  134. package/src/evaluation/trial.ts +866 -0
  135. package/src/evaluation/types.ts +207 -0
  136. package/src/evidence/host-results.ts +92 -0
  137. package/src/evidence/retained-artifacts.ts +18 -0
  138. package/src/evidence/trial-writer.ts +203 -0
  139. package/src/evidence/usage.ts +17 -0
  140. package/src/extension-client.ts +228 -148
  141. package/src/extension-session.ts +326 -195
  142. package/src/fixtures/advisory.ts +338 -0
  143. package/src/fixtures/bin.ts +57 -0
  144. package/src/{fixture-cleanup.ts → fixtures/cleanup.ts} +13 -7
  145. package/src/fixtures/create.ts +187 -0
  146. package/src/fixtures/generated.ts +300 -0
  147. package/src/fixtures/git-hooks.ts +24 -0
  148. package/src/fixtures/preparation.ts +270 -0
  149. package/src/{repository-fixture.ts → fixtures/repository.ts} +207 -85
  150. package/src/fixtures/setup.ts +224 -0
  151. package/src/fixtures/tools.ts +88 -0
  152. package/src/fixtures/workspace-state.ts +212 -0
  153. package/src/generated/cli-result.cjs +2 -0
  154. package/src/generated/cli-result.d.cts +3 -0
  155. package/src/generated/extension.cjs +2 -0
  156. package/src/generated/extension.d.cts +3 -0
  157. package/src/generated/report.cjs +2 -0
  158. package/src/generated/report.d.cts +3 -0
  159. package/src/generated/run-evidence.cjs +2 -0
  160. package/src/generated/run-evidence.d.cts +3 -0
  161. package/src/generated/runtime.cjs +2 -0
  162. package/src/generated/runtime.d.cts +3 -0
  163. package/src/graders/artifact.ts +56 -23
  164. package/src/graders/git-head.ts +79 -75
  165. package/src/graders/output.ts +222 -140
  166. package/src/graders/semantic.ts +102 -43
  167. package/src/graders/shell.ts +379 -207
  168. package/src/host-diagnostic-redaction.ts +52 -0
  169. package/src/host-diagnostics.ts +319 -0
  170. package/src/hosts/claude-continuation.ts +63 -18
  171. package/src/hosts/claude-credential.ts +43 -62
  172. package/src/hosts/claude-events.ts +86 -51
  173. package/src/hosts/claude-keychain.ts +59 -0
  174. package/src/hosts/claude-native-goal.ts +57 -33
  175. package/src/hosts/claude-process.ts +111 -0
  176. package/src/hosts/claude-repository-invocation.ts +208 -117
  177. package/src/hosts/claude-settings.ts +240 -21
  178. package/src/hosts/claude-skill-activations.ts +166 -0
  179. package/src/hosts/claude-state.ts +403 -0
  180. package/src/hosts/claude-tool-calls.ts +171 -106
  181. package/src/hosts/claude.ts +561 -451
  182. package/src/hosts/codex-app-server.ts +326 -178
  183. package/src/hosts/codex-configuration.ts +44 -18
  184. package/src/hosts/codex-events.ts +97 -60
  185. package/src/hosts/codex-exec-controls.ts +516 -0
  186. package/src/hosts/codex-invocation.ts +70 -0
  187. package/src/hosts/codex-marketplace.ts +283 -0
  188. package/src/hosts/codex-native-calls.ts +546 -500
  189. package/src/hosts/codex-process.ts +202 -0
  190. package/src/hosts/codex-profile.ts +257 -28
  191. package/src/hosts/codex-session-files.ts +106 -0
  192. package/src/hosts/codex-state.ts +492 -0
  193. package/src/hosts/codex.ts +783 -832
  194. package/src/hosts/isolation-common.ts +94 -0
  195. package/src/hosts/isolation-roots.ts +54 -27
  196. package/src/hosts/isolation.ts +10 -0
  197. package/src/hosts/linux-sandbox.ts +159 -0
  198. package/src/hosts/mac-sandbox.ts +187 -61
  199. package/src/hosts/native-controls.ts +152 -62
  200. package/src/hosts/process-lifecycle.ts +37 -0
  201. package/src/hosts/protected-worktrees.ts +51 -19
  202. package/src/hosts/skill-hook-catalog.ts +131 -0
  203. package/src/hosts/skill-hook-handler.ts +374 -0
  204. package/src/hosts/skill-hooks.ts +580 -0
  205. package/src/hosts/workspace-fingerprint.ts +55 -35
  206. package/src/identity.ts +102 -48
  207. package/src/instrumentation.ts +109 -48
  208. package/src/native-transcript-state.ts +131 -0
  209. package/src/native-transcript-view.ts +90 -0
  210. package/src/native-transcripts.ts +286 -0
  211. package/src/process-lifecycle.ts +150 -0
  212. package/src/provenance.ts +161 -81
  213. package/src/prune.ts +215 -0
  214. package/src/report.ts +172 -140
  215. package/src/resolved-case.ts +33 -0
  216. package/src/results-lock.ts +29 -0
  217. package/src/results.ts +133 -86
  218. package/src/run-owner.ts +154 -63
  219. package/src/runtime/config.ts +456 -0
  220. package/src/runtime/discovery-apple.ts +90 -0
  221. package/src/runtime/discovery-providers.ts +63 -0
  222. package/src/runtime/discovery.ts +70 -0
  223. package/src/runtime/hook-processes.ts +97 -0
  224. package/src/runtime/hooks.ts +476 -0
  225. package/src/runtime/paths.ts +313 -0
  226. package/src/runtime/query.ts +85 -0
  227. package/src/runtime/seeds.ts +134 -0
  228. package/src/runtime/shared-cache.ts +143 -0
  229. package/src/runtime/state.ts +143 -0
  230. package/src/schema-types.ts +198 -0
  231. package/src/schema.ts +15 -19
  232. package/src/transcript-retention.ts +146 -0
  233. package/src/value-guards.ts +20 -0
  234. package/src/advisory-fixture.ts +0 -282
  235. package/src/fixture-bin.ts +0 -87
  236. package/src/fixture-setup.ts +0 -163
  237. package/src/generated-fixture.ts +0 -220
  238. package/src/git-hooks.ts +0 -63
  239. package/src/hosts/claude-nested-skills.ts +0 -218
  240. package/src/hosts/codex-command-output.ts +0 -399
  241. package/src/hosts/codex-executor-command.ts +0 -195
  242. package/src/hosts/codex-skill-reads.ts +0 -391
  243. package/src/preparation.ts +0 -211
@@ -0,0 +1,403 @@
1
+ {
2
+ "format": "sevro.runtime-startup-benchmark.v1",
3
+ "sourceRoot": "/Users/bjro/Sources/sevro",
4
+ "platform": "darwin",
5
+ "arch": "arm64",
6
+ "bun": "1.3.13",
7
+ "codex": "codex-cli 0.162.1",
8
+ "case": "synthetic-plugin-response",
9
+ "model": "synthetic-candidate / synthetic-semantic",
10
+ "effort": "low",
11
+ "seed": {
12
+ "entries": 2049,
13
+ "bytes": 33554432
14
+ },
15
+ "repetitions": 3,
16
+ "conditions": "Fresh role homes each invocation; first verified snapshot cold, later repetitions warm; OS filesystem caches uncontrolled; no live API/model calls",
17
+ "rows": [
18
+ {
19
+ "repetition": 0,
20
+ "role": "candidate",
21
+ "phase": "configuration",
22
+ "milliseconds": 261.92554200000006,
23
+ "status": "completed"
24
+ },
25
+ {
26
+ "repetition": 1,
27
+ "role": "candidate",
28
+ "phase": "runtime.candidate",
29
+ "milliseconds": 1969.3474580000002,
30
+ "status": "completed"
31
+ },
32
+ {
33
+ "repetition": 1,
34
+ "role": "candidate",
35
+ "phase": "plugin-command",
36
+ "milliseconds": 300.13179200000013,
37
+ "status": "completed"
38
+ },
39
+ {
40
+ "repetition": 1,
41
+ "role": "candidate",
42
+ "phase": "plugin-command",
43
+ "milliseconds": 81.15104199999996,
44
+ "status": "completed"
45
+ },
46
+ {
47
+ "repetition": 1,
48
+ "role": "candidate",
49
+ "phase": "installation-assets",
50
+ "files": [
51
+ "cache"
52
+ ],
53
+ "configurationContainsPrivateHome": true,
54
+ "configurationContainsWorkspace": true
55
+ },
56
+ {
57
+ "repetition": 1,
58
+ "role": "candidate",
59
+ "phase": "plugin-install",
60
+ "milliseconds": 385.09974999999986,
61
+ "status": "completed"
62
+ },
63
+ {
64
+ "repetition": 1,
65
+ "role": "candidate",
66
+ "phase": "runtime.hooks",
67
+ "milliseconds": 1225.7079159999994,
68
+ "status": "completed"
69
+ },
70
+ {
71
+ "repetition": 1,
72
+ "role": "candidate",
73
+ "phase": "sandbox-probe",
74
+ "milliseconds": 5528.486166999999,
75
+ "status": "completed"
76
+ },
77
+ {
78
+ "repetition": 1,
79
+ "role": "candidate",
80
+ "phase": "sandbox-probe",
81
+ "milliseconds": 5409.168874999999,
82
+ "status": "completed"
83
+ },
84
+ {
85
+ "repetition": 1,
86
+ "role": "candidate",
87
+ "phase": "participant-execution",
88
+ "milliseconds": 27.37004100000013,
89
+ "status": "completed"
90
+ },
91
+ {
92
+ "repetition": 1,
93
+ "role": "candidate",
94
+ "phase": "candidate-total",
95
+ "milliseconds": 14924.6165,
96
+ "status": "completed"
97
+ },
98
+ {
99
+ "repetition": 1,
100
+ "role": "semantic",
101
+ "phase": "runtime.semantic",
102
+ "milliseconds": 1174.1918750000004,
103
+ "status": "completed"
104
+ },
105
+ {
106
+ "repetition": 1,
107
+ "role": "semantic",
108
+ "phase": "plugin-install",
109
+ "milliseconds": 0.014666000002762303,
110
+ "status": "completed"
111
+ },
112
+ {
113
+ "repetition": 1,
114
+ "role": "semantic",
115
+ "phase": "runtime.hooks",
116
+ "milliseconds": 1104.8465419999993,
117
+ "status": "completed"
118
+ },
119
+ {
120
+ "repetition": 1,
121
+ "role": "semantic",
122
+ "phase": "sandbox-probe",
123
+ "milliseconds": 5485.405999999999,
124
+ "status": "completed"
125
+ },
126
+ {
127
+ "repetition": 1,
128
+ "role": "semantic",
129
+ "phase": "sandbox-probe",
130
+ "milliseconds": 5369.393208999998,
131
+ "status": "completed"
132
+ },
133
+ {
134
+ "repetition": 1,
135
+ "role": "semantic",
136
+ "phase": "participant-execution",
137
+ "milliseconds": 27.99250000000029,
138
+ "status": "completed"
139
+ },
140
+ {
141
+ "repetition": 1,
142
+ "role": "semantic",
143
+ "phase": "grading",
144
+ "milliseconds": 13494.667042000001,
145
+ "status": "completed"
146
+ },
147
+ {
148
+ "repetition": 2,
149
+ "role": "candidate",
150
+ "phase": "runtime.candidate",
151
+ "milliseconds": 1357.1145419999993,
152
+ "status": "completed"
153
+ },
154
+ {
155
+ "repetition": 2,
156
+ "role": "candidate",
157
+ "phase": "plugin-command",
158
+ "milliseconds": 72.52966600000218,
159
+ "status": "completed"
160
+ },
161
+ {
162
+ "repetition": 2,
163
+ "role": "candidate",
164
+ "phase": "plugin-command",
165
+ "milliseconds": 67.09337500000038,
166
+ "status": "completed"
167
+ },
168
+ {
169
+ "repetition": 2,
170
+ "role": "candidate",
171
+ "phase": "installation-assets",
172
+ "files": [
173
+ "cache"
174
+ ],
175
+ "configurationContainsPrivateHome": true,
176
+ "configurationContainsWorkspace": true
177
+ },
178
+ {
179
+ "repetition": 2,
180
+ "role": "candidate",
181
+ "phase": "plugin-install",
182
+ "milliseconds": 141.13416599999982,
183
+ "status": "completed"
184
+ },
185
+ {
186
+ "repetition": 2,
187
+ "role": "candidate",
188
+ "phase": "runtime.hooks",
189
+ "milliseconds": 1464.9581660000003,
190
+ "status": "completed"
191
+ },
192
+ {
193
+ "repetition": 2,
194
+ "role": "candidate",
195
+ "phase": "sandbox-probe",
196
+ "milliseconds": 5689.016333,
197
+ "status": "completed"
198
+ },
199
+ {
200
+ "repetition": 2,
201
+ "role": "candidate",
202
+ "phase": "sandbox-probe",
203
+ "milliseconds": 5342.566417000002,
204
+ "status": "completed"
205
+ },
206
+ {
207
+ "repetition": 2,
208
+ "role": "candidate",
209
+ "phase": "participant-execution",
210
+ "milliseconds": 28.610333000004175,
211
+ "status": "completed"
212
+ },
213
+ {
214
+ "repetition": 2,
215
+ "role": "candidate",
216
+ "phase": "candidate-total",
217
+ "milliseconds": 14369.195708,
218
+ "status": "completed"
219
+ },
220
+ {
221
+ "repetition": 2,
222
+ "role": "semantic",
223
+ "phase": "runtime.semantic",
224
+ "milliseconds": 1235.6402080000043,
225
+ "status": "completed"
226
+ },
227
+ {
228
+ "repetition": 2,
229
+ "role": "semantic",
230
+ "phase": "plugin-install",
231
+ "milliseconds": 0.014084000002185348,
232
+ "status": "completed"
233
+ },
234
+ {
235
+ "repetition": 2,
236
+ "role": "semantic",
237
+ "phase": "runtime.hooks",
238
+ "milliseconds": 1087.1219169999968,
239
+ "status": "completed"
240
+ },
241
+ {
242
+ "repetition": 2,
243
+ "role": "semantic",
244
+ "phase": "sandbox-probe",
245
+ "milliseconds": 5409.527834,
246
+ "status": "completed"
247
+ },
248
+ {
249
+ "repetition": 2,
250
+ "role": "semantic",
251
+ "phase": "sandbox-probe",
252
+ "milliseconds": 5393.348124999997,
253
+ "status": "completed"
254
+ },
255
+ {
256
+ "repetition": 2,
257
+ "role": "semantic",
258
+ "phase": "participant-execution",
259
+ "milliseconds": 44.382833999996365,
260
+ "status": "completed"
261
+ },
262
+ {
263
+ "repetition": 2,
264
+ "role": "semantic",
265
+ "phase": "grading",
266
+ "milliseconds": 13533.550041999995,
267
+ "status": "completed"
268
+ },
269
+ {
270
+ "repetition": 3,
271
+ "role": "candidate",
272
+ "phase": "runtime.candidate",
273
+ "milliseconds": 1273.4362919999985,
274
+ "status": "completed"
275
+ },
276
+ {
277
+ "repetition": 3,
278
+ "role": "candidate",
279
+ "phase": "plugin-command",
280
+ "milliseconds": 75.75125000000116,
281
+ "status": "completed"
282
+ },
283
+ {
284
+ "repetition": 3,
285
+ "role": "candidate",
286
+ "phase": "plugin-command",
287
+ "milliseconds": 65.14912499999627,
288
+ "status": "completed"
289
+ },
290
+ {
291
+ "repetition": 3,
292
+ "role": "candidate",
293
+ "phase": "installation-assets",
294
+ "files": [
295
+ "cache"
296
+ ],
297
+ "configurationContainsPrivateHome": true,
298
+ "configurationContainsWorkspace": true
299
+ },
300
+ {
301
+ "repetition": 3,
302
+ "role": "candidate",
303
+ "phase": "plugin-install",
304
+ "milliseconds": 143.153999999995,
305
+ "status": "completed"
306
+ },
307
+ {
308
+ "repetition": 3,
309
+ "role": "candidate",
310
+ "phase": "runtime.hooks",
311
+ "milliseconds": 1234.849000000002,
312
+ "status": "completed"
313
+ },
314
+ {
315
+ "repetition": 3,
316
+ "role": "candidate",
317
+ "phase": "sandbox-probe",
318
+ "milliseconds": 5916.286457999995,
319
+ "status": "completed"
320
+ },
321
+ {
322
+ "repetition": 3,
323
+ "role": "candidate",
324
+ "phase": "sandbox-probe",
325
+ "milliseconds": 5706.173332999999,
326
+ "status": "completed"
327
+ },
328
+ {
329
+ "repetition": 3,
330
+ "role": "candidate",
331
+ "phase": "participant-execution",
332
+ "milliseconds": 38.983124999998836,
333
+ "status": "completed"
334
+ },
335
+ {
336
+ "repetition": 3,
337
+ "role": "candidate",
338
+ "phase": "candidate-total",
339
+ "milliseconds": 14666.299250000004,
340
+ "status": "completed"
341
+ },
342
+ {
343
+ "repetition": 3,
344
+ "role": "semantic",
345
+ "phase": "runtime.semantic",
346
+ "milliseconds": 2261.5522090000013,
347
+ "status": "completed"
348
+ },
349
+ {
350
+ "repetition": 3,
351
+ "role": "semantic",
352
+ "phase": "plugin-install",
353
+ "milliseconds": 0.016417000006185845,
354
+ "status": "completed"
355
+ },
356
+ {
357
+ "repetition": 3,
358
+ "role": "semantic",
359
+ "phase": "runtime.hooks",
360
+ "milliseconds": 1363.224583999996,
361
+ "status": "completed"
362
+ },
363
+ {
364
+ "repetition": 3,
365
+ "role": "semantic",
366
+ "phase": "sandbox-probe",
367
+ "milliseconds": 5592.143207999994,
368
+ "status": "completed"
369
+ },
370
+ {
371
+ "repetition": 3,
372
+ "role": "semantic",
373
+ "phase": "sandbox-probe",
374
+ "milliseconds": 5439.415540999995,
375
+ "status": "completed"
376
+ },
377
+ {
378
+ "repetition": 3,
379
+ "role": "semantic",
380
+ "phase": "participant-execution",
381
+ "milliseconds": 27.27187499999127,
382
+ "status": "completed"
383
+ },
384
+ {
385
+ "repetition": 3,
386
+ "role": "semantic",
387
+ "phase": "grading",
388
+ "milliseconds": 15030.493917,
389
+ "status": "completed"
390
+ },
391
+ {
392
+ "repetition": 4,
393
+ "role": "semantic",
394
+ "phase": "cow-copy",
395
+ "milliseconds": 1.0108749999926658,
396
+ "status": "completed"
397
+ },
398
+ {
399
+ "phase": "cow-isolation",
400
+ "sourceUnchanged": true
401
+ }
402
+ ]
403
+ }
@@ -0,0 +1,63 @@
1
+ {
2
+ "format": "sevro.consumer-smoke.v1",
3
+ "date": "2026-10-11",
4
+ "consumer": {
5
+ "repository": "https://github.com/BjRo/darrow",
6
+ "revision": "34606ad9e1952b7f4e9c56befa446c18e1a2eb5d",
7
+ "trackedChanges": false
8
+ },
9
+ "environment": {
10
+ "platform": "darwin",
11
+ "arch": "arm64",
12
+ "bun": "1.3.13",
13
+ "codex": "0.162.1",
14
+ "candidateModel": "gpt-6-luna",
15
+ "candidateEffort": "medium",
16
+ "semanticModel": "gpt-6-luna",
17
+ "semanticEffort": "medium"
18
+ },
19
+ "sampling": {
20
+ "trials": 1,
21
+ "jobs": 1,
22
+ "threshold": 1
23
+ },
24
+ "runs": [
25
+ {
26
+ "runner": "unchanged c205482b25d4d52a395c70434f2b392f6acfb279",
27
+ "case": "create-commit-conventional-format",
28
+ "execution": "failed",
29
+ "task": "not_assessed",
30
+ "activation": "unavailable",
31
+ "participantReached": false,
32
+ "diagnostic": "First sandbox preflight exceeded its 10-second deadline."
33
+ },
34
+ {
35
+ "runner": "issue-30 candidate",
36
+ "case": "create-commit-conventional-format",
37
+ "execution": "completed",
38
+ "grading": "completed",
39
+ "task": "failed",
40
+ "shellChecksPassed": 3,
41
+ "activation": "unavailable",
42
+ "limitation": "Implicit repository fixture omitted plugin manifests required by its backend launcher. Candidate correctly refused to create the requested commit; head-change assertion failed."
43
+ },
44
+ {
45
+ "runner": "issue-30 candidate",
46
+ "case": "tdd-explicit-invocation",
47
+ "execution": "completed",
48
+ "grading": "completed",
49
+ "task": "passed",
50
+ "shellCheck": "passed",
51
+ "semanticCheck": "passed",
52
+ "activation": "passed",
53
+ "activationCompleteness": "complete",
54
+ "activationEvidence": "Native Codex explicit-invocation receipt"
55
+ }
56
+ ],
57
+ "limits": [
58
+ "Only one authenticated trial per listed run.",
59
+ "Different cases are not a matched live performance comparison.",
60
+ "No live API/model latency saving is inferred.",
61
+ "Private transcripts, prompts, tool arguments, and credentials are omitted."
62
+ ]
63
+ }
@@ -0,0 +1,3 @@
1
+ {"phase":"sandbox-probe","durationMs":10649.106041000001,"code":0}
2
+ {"phase":"sandbox-probe","durationMs":10690.409208999998,"code":0}
3
+ {"phase":"participant","status":"withheld-diagnostic-control"}
@@ -0,0 +1,3 @@
1
+ {"phase":"sandbox-probe","durationMs":5372.77075,"code":0}
2
+ {"phase":"sandbox-probe","durationMs":5681.134667,"code":0}
3
+ {"phase":"participant","status":"withheld-diagnostic-control"}
@@ -0,0 +1,20 @@
1
+ {
2
+ "codex": "codex-cli 0.162.1",
3
+ "registered": {
4
+ "code": 0,
5
+ "out": "{\n \"marketplaceName\": \"sevro-assessment\",\n \"installedRoot\": \"<assessment>/market\",\n \"alreadyAdded\": false\n}\n",
6
+ "err": ""
7
+ },
8
+ "installed": {
9
+ "code": 0,
10
+ "out": "{\n \"pluginId\": \"probe@sevro-assessment\",\n \"name\": \"probe\",\n \"marketplaceName\": \"sevro-assessment\",\n \"version\": \"1.0.0\",\n \"installedPath\": \"<assessment>/home/plugins/cache/sevro-assessment/probe/1.0.0\",\n \"authPolicy\": \"ON_INSTALL\"\n}\n",
11
+ "err": ""
12
+ },
13
+ "configuration": "[marketplaces.sevro-assessment]\nsource_type = \"local\"\nsource = \"<assessment>/market\"\n\n[plugins.\"probe@sevro-assessment\"]\nenabled = true\n",
14
+ "cacheOnlyFreshHomeList": {
15
+ "code": 0,
16
+ "out": "{\n \"installed\": [],\n \"available\": []\n}\n",
17
+ "err": ""
18
+ },
19
+ "conditions": "Local synthetic plugin; fresh homes without credentials; installed files copied to a second home; no registration copied"
20
+ }
@@ -0,0 +1,2 @@
1
+ {"phase":"sandbox-probe","durationMs":10004.197417000001,"error":"Codex run timed out"}
2
+ {"phase":"host-failure","error":"Codex run timed out"}