akm-cli 0.7.0-rc1 → 0.7.1

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 (314) hide show
  1. package/dist/{src/cli.js → cli.js} +100 -16
  2. package/dist/{src/commands → commands}/config-cli.js +42 -0
  3. package/dist/{src/commands → commands}/history.js +78 -7
  4. package/dist/{src/commands → commands}/registry-search.js +69 -6
  5. package/dist/{src/commands → commands}/search.js +30 -3
  6. package/dist/{src/commands → commands}/show.js +29 -0
  7. package/dist/{src/commands → commands}/source-add.js +5 -1
  8. package/dist/{src/commands → commands}/source-manage.js +7 -1
  9. package/dist/{src/core → core}/config.js +28 -0
  10. package/dist/{src/indexer → indexer}/db-search.js +1 -0
  11. package/dist/{src/indexer → indexer}/indexer.js +16 -2
  12. package/dist/{src/indexer → indexer}/matchers.js +1 -1
  13. package/dist/{src/indexer → indexer}/search-source.js +4 -2
  14. package/dist/{src/integrations → integrations}/agent/profiles.js +1 -1
  15. package/dist/{src/integrations → integrations}/agent/spawn.js +67 -16
  16. package/dist/{src/integrations → integrations}/github.js +9 -3
  17. package/dist/{src/llm → llm}/embedders/remote.js +37 -3
  18. package/dist/{src/output → output}/cli-hints.js +15 -2
  19. package/dist/{src/output → output}/renderers.js +3 -1
  20. package/dist/{src/output → output}/shapes.js +8 -1
  21. package/dist/{src/output → output}/text.js +156 -3
  22. package/dist/{src/registry → registry}/build-index.js +5 -4
  23. package/dist/{src/registry → registry}/providers/static-index.js +3 -1
  24. package/dist/{src/setup → setup}/setup.js +9 -0
  25. package/dist/{src/wiki → wiki}/wiki.js +54 -6
  26. package/dist/{src/workflows → workflows}/runs.js +37 -3
  27. package/package.json +8 -8
  28. package/dist/tests/add-website-source.test.js +0 -119
  29. package/dist/tests/agent/agent-config-loader.test.js +0 -70
  30. package/dist/tests/agent/agent-config.test.js +0 -221
  31. package/dist/tests/agent/agent-detect.test.js +0 -100
  32. package/dist/tests/agent/agent-spawn.test.js +0 -234
  33. package/dist/tests/agent-output.test.js +0 -186
  34. package/dist/tests/architecture/agent-no-llm-sdk-guard.test.js +0 -103
  35. package/dist/tests/architecture/agent-spawn-seam.test.js +0 -193
  36. package/dist/tests/architecture/llm-stateless-seam.test.js +0 -112
  37. package/dist/tests/asset-ref.test.js +0 -192
  38. package/dist/tests/asset-registry.test.js +0 -103
  39. package/dist/tests/asset-spec.test.js +0 -241
  40. package/dist/tests/bench/attribution.test.js +0 -995
  41. package/dist/tests/bench/cleanup-sigint.test.js +0 -83
  42. package/dist/tests/bench/cleanup.js +0 -203
  43. package/dist/tests/bench/cleanup.test.js +0 -166
  44. package/dist/tests/bench/cli.js +0 -683
  45. package/dist/tests/bench/cli.test.js +0 -177
  46. package/dist/tests/bench/compare.test.js +0 -556
  47. package/dist/tests/bench/corpus.js +0 -314
  48. package/dist/tests/bench/corpus.test.js +0 -258
  49. package/dist/tests/bench/driver.js +0 -346
  50. package/dist/tests/bench/driver.test.js +0 -443
  51. package/dist/tests/bench/evolve-metrics.js +0 -179
  52. package/dist/tests/bench/evolve-metrics.test.js +0 -187
  53. package/dist/tests/bench/evolve.js +0 -580
  54. package/dist/tests/bench/evolve.test.js +0 -616
  55. package/dist/tests/bench/failure-modes.test.js +0 -300
  56. package/dist/tests/bench/feedback-integrity.test.js +0 -456
  57. package/dist/tests/bench/leakage.test.js +0 -125
  58. package/dist/tests/bench/learning-curve.test.js +0 -133
  59. package/dist/tests/bench/metrics.js +0 -2319
  60. package/dist/tests/bench/metrics.test.js +0 -1144
  61. package/dist/tests/bench/no-os-tmpdir-invariant.test.js +0 -43
  62. package/dist/tests/bench/report.js +0 -1821
  63. package/dist/tests/bench/report.test.js +0 -989
  64. package/dist/tests/bench/runner.js +0 -536
  65. package/dist/tests/bench/runner.test.js +0 -958
  66. package/dist/tests/bench/search-bridge.test.js +0 -331
  67. package/dist/tests/bench/tmp.js +0 -41
  68. package/dist/tests/bench/trajectory.js +0 -116
  69. package/dist/tests/bench/trajectory.test.js +0 -127
  70. package/dist/tests/bench/verifier.js +0 -109
  71. package/dist/tests/bench/verifier.test.js +0 -118
  72. package/dist/tests/bench/workflow-evaluator.js +0 -557
  73. package/dist/tests/bench/workflow-evaluator.test.js +0 -421
  74. package/dist/tests/bench/workflow-spec.js +0 -358
  75. package/dist/tests/bench/workflow-spec.test.js +0 -363
  76. package/dist/tests/bench/workflow-trace.js +0 -438
  77. package/dist/tests/bench/workflow-trace.test.js +0 -254
  78. package/dist/tests/benchmark-search-quality.js +0 -536
  79. package/dist/tests/benchmark-suite.js +0 -1441
  80. package/dist/tests/capture-cli.test.js +0 -112
  81. package/dist/tests/cli-errors.test.js +0 -203
  82. package/dist/tests/commands/events.test.js +0 -370
  83. package/dist/tests/commands/history.test.js +0 -223
  84. package/dist/tests/commands/import.test.js +0 -103
  85. package/dist/tests/commands/proposal-cli.test.js +0 -209
  86. package/dist/tests/commands/reflect-propose-cli.test.js +0 -333
  87. package/dist/tests/commands/remember.test.js +0 -97
  88. package/dist/tests/commands/scope-flags.test.js +0 -300
  89. package/dist/tests/commands/search.test.js +0 -537
  90. package/dist/tests/commands/show-indexer-parity.test.js +0 -117
  91. package/dist/tests/commands/show.test.js +0 -294
  92. package/dist/tests/common.test.js +0 -266
  93. package/dist/tests/completions.test.js +0 -142
  94. package/dist/tests/config-cli.test.js +0 -193
  95. package/dist/tests/config-llm-features.test.js +0 -139
  96. package/dist/tests/config.test.js +0 -544
  97. package/dist/tests/contracts/migration-baseline.test.js +0 -43
  98. package/dist/tests/contracts/reflect-propose-envelope.test.js +0 -139
  99. package/dist/tests/contracts/spec-helpers.js +0 -46
  100. package/dist/tests/contracts/v1-spec-section-11-proposal-queue.test.js +0 -228
  101. package/dist/tests/contracts/v1-spec-section-12-agent-config.test.js +0 -56
  102. package/dist/tests/contracts/v1-spec-section-13-lesson-type.test.js +0 -34
  103. package/dist/tests/contracts/v1-spec-section-14-llm-features.test.js +0 -94
  104. package/dist/tests/contracts/v1-spec-section-4-1-asset-types.test.js +0 -39
  105. package/dist/tests/contracts/v1-spec-section-4-2-quality-rules.test.js +0 -44
  106. package/dist/tests/contracts/v1-spec-section-5-configuration.test.js +0 -47
  107. package/dist/tests/contracts/v1-spec-section-6-orchestration.test.js +0 -40
  108. package/dist/tests/contracts/v1-spec-section-7-module-layout.test.js +0 -58
  109. package/dist/tests/contracts/v1-spec-section-8-extension-points.test.js +0 -34
  110. package/dist/tests/contracts/v1-spec-section-9-4-cli-surface.test.js +0 -75
  111. package/dist/tests/contracts/v1-spec-section-9-7-llm-agent-boundary.test.js +0 -36
  112. package/dist/tests/core/write-source.test.js +0 -366
  113. package/dist/tests/curate-command.test.js +0 -87
  114. package/dist/tests/db-scoring.test.js +0 -201
  115. package/dist/tests/db.test.js +0 -654
  116. package/dist/tests/distill-cli-flag.test.js +0 -208
  117. package/dist/tests/distill.test.js +0 -515
  118. package/dist/tests/docker-install.test.js +0 -120
  119. package/dist/tests/e2e.test.js +0 -1398
  120. package/dist/tests/embedder.test.js +0 -340
  121. package/dist/tests/embedding-model-config.test.js +0 -379
  122. package/dist/tests/feedback-command.test.js +0 -172
  123. package/dist/tests/file-context.test.js +0 -552
  124. package/dist/tests/fixtures/scripts/git/summarize-diff.js +0 -9
  125. package/dist/tests/fixtures/scripts/lint/eslint-check.js +0 -7
  126. package/dist/tests/fixtures/stashes/load.js +0 -166
  127. package/dist/tests/fixtures/stashes/load.test.js +0 -88
  128. package/dist/tests/fixtures/stashes/ranking-baseline/scripts/mem0-search.js +0 -12
  129. package/dist/tests/frontmatter.test.js +0 -190
  130. package/dist/tests/fts-field-weighting.test.js +0 -254
  131. package/dist/tests/fuzzy-search.test.js +0 -230
  132. package/dist/tests/git-provider-clone.test.js +0 -45
  133. package/dist/tests/github.test.js +0 -161
  134. package/dist/tests/graph-boost-ranking.test.js +0 -305
  135. package/dist/tests/graph-extraction.test.js +0 -282
  136. package/dist/tests/helpers/usage-events.js +0 -8
  137. package/dist/tests/index-pass-llm.test.js +0 -161
  138. package/dist/tests/indexer.test.js +0 -559
  139. package/dist/tests/info-command.test.js +0 -166
  140. package/dist/tests/init.test.js +0 -69
  141. package/dist/tests/install-script.test.js +0 -246
  142. package/dist/tests/integration/agent-real-profile.test.js +0 -94
  143. package/dist/tests/issue-36-repro.test.js +0 -304
  144. package/dist/tests/issues-191-194.test.js +0 -160
  145. package/dist/tests/lesson-lint.test.js +0 -111
  146. package/dist/tests/llm-client.test.js +0 -115
  147. package/dist/tests/llm-feature-gate.test.js +0 -151
  148. package/dist/tests/llm.test.js +0 -139
  149. package/dist/tests/lockfile.test.js +0 -216
  150. package/dist/tests/manifest.test.js +0 -205
  151. package/dist/tests/markdown.test.js +0 -126
  152. package/dist/tests/matchers-unit.test.js +0 -189
  153. package/dist/tests/memory-inference.test.js +0 -299
  154. package/dist/tests/merge-scoring.test.js +0 -136
  155. package/dist/tests/metadata.test.js +0 -313
  156. package/dist/tests/migration-help.test.js +0 -89
  157. package/dist/tests/origin-resolve.test.js +0 -124
  158. package/dist/tests/output-baseline.test.js +0 -217
  159. package/dist/tests/output-shapes-unit.test.js +0 -476
  160. package/dist/tests/parallel-search.test.js +0 -272
  161. package/dist/tests/parameter-metadata.test.js +0 -365
  162. package/dist/tests/paths.test.js +0 -177
  163. package/dist/tests/progressive-disclosure.test.js +0 -280
  164. package/dist/tests/proposals.test.js +0 -279
  165. package/dist/tests/proposed-quality.test.js +0 -271
  166. package/dist/tests/provider-registry.test.js +0 -32
  167. package/dist/tests/ranking-regression.test.js +0 -548
  168. package/dist/tests/reflect-propose.test.js +0 -455
  169. package/dist/tests/registry-build-index.test.js +0 -378
  170. package/dist/tests/registry-cli.test.js +0 -290
  171. package/dist/tests/registry-index-v2.test.js +0 -430
  172. package/dist/tests/registry-install.test.js +0 -728
  173. package/dist/tests/registry-providers/parity.test.js +0 -189
  174. package/dist/tests/registry-providers/skills-sh.test.js +0 -309
  175. package/dist/tests/registry-providers/static-index.test.js +0 -204
  176. package/dist/tests/registry-resolve.test.js +0 -126
  177. package/dist/tests/registry-search.test.js +0 -723
  178. package/dist/tests/remember-frontmatter.test.js +0 -380
  179. package/dist/tests/remember-unit.test.js +0 -123
  180. package/dist/tests/ripgrep-install.test.js +0 -251
  181. package/dist/tests/ripgrep-resolve.test.js +0 -108
  182. package/dist/tests/ripgrep.test.js +0 -163
  183. package/dist/tests/save-command.test.js +0 -94
  184. package/dist/tests/save-trust-qa-fixes.test.js +0 -270
  185. package/dist/tests/scoring-pipeline.test.js +0 -648
  186. package/dist/tests/search-include-proposed-cli.test.js +0 -118
  187. package/dist/tests/self-update.test.js +0 -442
  188. package/dist/tests/semantic-search-e2e.test.js +0 -512
  189. package/dist/tests/semantic-status.test.js +0 -471
  190. package/dist/tests/setup-run.integration.js +0 -877
  191. package/dist/tests/setup-wizard.test.js +0 -198
  192. package/dist/tests/setup.test.js +0 -131
  193. package/dist/tests/source-add.test.js +0 -11
  194. package/dist/tests/source-clone.test.js +0 -254
  195. package/dist/tests/source-manage.test.js +0 -366
  196. package/dist/tests/source-providers/filesystem.test.js +0 -82
  197. package/dist/tests/source-providers/git.test.js +0 -252
  198. package/dist/tests/source-providers/website.test.js +0 -128
  199. package/dist/tests/source-qa-fixes.test.js +0 -268
  200. package/dist/tests/source-registry.test.js +0 -350
  201. package/dist/tests/source-resolve.test.js +0 -100
  202. package/dist/tests/source-source.test.js +0 -221
  203. package/dist/tests/source.test.js +0 -533
  204. package/dist/tests/tar-utils-scan.test.js +0 -73
  205. package/dist/tests/toggle-components.test.js +0 -73
  206. package/dist/tests/usage-telemetry.test.js +0 -265
  207. package/dist/tests/utility-scoring.test.js +0 -558
  208. package/dist/tests/vault-load-error.test.js +0 -78
  209. package/dist/tests/vault-qa-fixes.test.js +0 -194
  210. package/dist/tests/vault.test.js +0 -429
  211. package/dist/tests/vector-search.test.js +0 -608
  212. package/dist/tests/walker.test.js +0 -252
  213. package/dist/tests/wave2-cluster-bc.test.js +0 -228
  214. package/dist/tests/wave2-cluster-d.test.js +0 -180
  215. package/dist/tests/wave2-cluster-e.test.js +0 -179
  216. package/dist/tests/wiki-qa-fixes.test.js +0 -270
  217. package/dist/tests/wiki.test.js +0 -529
  218. package/dist/tests/workflow-cli.test.js +0 -271
  219. package/dist/tests/workflow-markdown.test.js +0 -171
  220. package/dist/tests/workflow-path-escape.test.js +0 -132
  221. package/dist/tests/workflow-qa-fixes.test.js +0 -377
  222. package/dist/tests/workflows/indexer-rejection.test.js +0 -213
  223. /package/dist/{src/commands → commands}/completions.js +0 -0
  224. /package/dist/{src/commands → commands}/curate.js +0 -0
  225. /package/dist/{src/commands → commands}/distill.js +0 -0
  226. /package/dist/{src/commands → commands}/events.js +0 -0
  227. /package/dist/{src/commands → commands}/info.js +0 -0
  228. /package/dist/{src/commands → commands}/init.js +0 -0
  229. /package/dist/{src/commands → commands}/install-audit.js +0 -0
  230. /package/dist/{src/commands → commands}/installed-stashes.js +0 -0
  231. /package/dist/{src/commands → commands}/migration-help.js +0 -0
  232. /package/dist/{src/commands → commands}/proposal.js +0 -0
  233. /package/dist/{src/commands → commands}/propose.js +0 -0
  234. /package/dist/{src/commands → commands}/reflect.js +0 -0
  235. /package/dist/{src/commands → commands}/remember.js +0 -0
  236. /package/dist/{src/commands → commands}/self-update.js +0 -0
  237. /package/dist/{src/commands → commands}/source-clone.js +0 -0
  238. /package/dist/{src/commands → commands}/vault.js +0 -0
  239. /package/dist/{src/core → core}/asset-ref.js +0 -0
  240. /package/dist/{src/core → core}/asset-registry.js +0 -0
  241. /package/dist/{src/core → core}/asset-spec.js +0 -0
  242. /package/dist/{src/core → core}/common.js +0 -0
  243. /package/dist/{src/core → core}/errors.js +0 -0
  244. /package/dist/{src/core → core}/events.js +0 -0
  245. /package/dist/{src/core → core}/frontmatter.js +0 -0
  246. /package/dist/{src/core → core}/lesson-lint.js +0 -0
  247. /package/dist/{src/core → core}/markdown.js +0 -0
  248. /package/dist/{src/core → core}/paths.js +0 -0
  249. /package/dist/{src/core → core}/proposals.js +0 -0
  250. /package/dist/{src/core → core}/warn.js +0 -0
  251. /package/dist/{src/core → core}/write-source.js +0 -0
  252. /package/dist/{src/indexer → indexer}/db.js +0 -0
  253. /package/dist/{src/indexer → indexer}/file-context.js +0 -0
  254. /package/dist/{src/indexer → indexer}/graph-boost.js +0 -0
  255. /package/dist/{src/indexer → indexer}/graph-extraction.js +0 -0
  256. /package/dist/{src/indexer → indexer}/manifest.js +0 -0
  257. /package/dist/{src/indexer → indexer}/memory-inference.js +0 -0
  258. /package/dist/{src/indexer → indexer}/metadata.js +0 -0
  259. /package/dist/{src/indexer → indexer}/search-fields.js +0 -0
  260. /package/dist/{src/indexer → indexer}/semantic-status.js +0 -0
  261. /package/dist/{src/indexer → indexer}/usage-events.js +0 -0
  262. /package/dist/{src/indexer → indexer}/walker.js +0 -0
  263. /package/dist/{src/integrations → integrations}/agent/config.js +0 -0
  264. /package/dist/{src/integrations → integrations}/agent/detect.js +0 -0
  265. /package/dist/{src/integrations → integrations}/agent/index.js +0 -0
  266. /package/dist/{src/integrations → integrations}/agent/prompts.js +0 -0
  267. /package/dist/{src/integrations → integrations}/lockfile.js +0 -0
  268. /package/dist/{src/llm → llm}/client.js +0 -0
  269. /package/dist/{src/llm → llm}/embedder.js +0 -0
  270. /package/dist/{src/llm → llm}/embedders/cache.js +0 -0
  271. /package/dist/{src/llm → llm}/embedders/local.js +0 -0
  272. /package/dist/{src/llm → llm}/embedders/types.js +0 -0
  273. /package/dist/{src/llm → llm}/feature-gate.js +0 -0
  274. /package/dist/{src/llm → llm}/graph-extract.js +0 -0
  275. /package/dist/{src/llm → llm}/index-passes.js +0 -0
  276. /package/dist/{src/llm → llm}/memory-infer.js +0 -0
  277. /package/dist/{src/llm → llm}/metadata-enhance.js +0 -0
  278. /package/dist/{src/output → output}/context.js +0 -0
  279. /package/dist/{src/registry → registry}/create-provider-registry.js +0 -0
  280. /package/dist/{src/registry → registry}/factory.js +0 -0
  281. /package/dist/{src/registry → registry}/origin-resolve.js +0 -0
  282. /package/dist/{src/registry → registry}/providers/index.js +0 -0
  283. /package/dist/{src/registry → registry}/providers/skills-sh.js +0 -0
  284. /package/dist/{src/registry → registry}/providers/types.js +0 -0
  285. /package/dist/{src/registry → registry}/resolve.js +0 -0
  286. /package/dist/{src/registry → registry}/types.js +0 -0
  287. /package/dist/{src/setup → setup}/detect.js +0 -0
  288. /package/dist/{src/setup → setup}/ripgrep-install.js +0 -0
  289. /package/dist/{src/setup → setup}/ripgrep-resolve.js +0 -0
  290. /package/dist/{src/setup → setup}/steps.js +0 -0
  291. /package/dist/{src/sources → sources}/include.js +0 -0
  292. /package/dist/{src/sources → sources}/provider-factory.js +0 -0
  293. /package/dist/{src/sources → sources}/provider.js +0 -0
  294. /package/dist/{src/sources → sources}/providers/filesystem.js +0 -0
  295. /package/dist/{src/sources → sources}/providers/git.js +0 -0
  296. /package/dist/{src/sources → sources}/providers/index.js +0 -0
  297. /package/dist/{src/sources → sources}/providers/install-types.js +0 -0
  298. /package/dist/{src/sources → sources}/providers/npm.js +0 -0
  299. /package/dist/{src/sources → sources}/providers/provider-utils.js +0 -0
  300. /package/dist/{src/sources → sources}/providers/sync-from-ref.js +0 -0
  301. /package/dist/{src/sources → sources}/providers/tar-utils.js +0 -0
  302. /package/dist/{src/sources → sources}/providers/website.js +0 -0
  303. /package/dist/{src/sources → sources}/resolve.js +0 -0
  304. /package/dist/{src/sources → sources}/types.js +0 -0
  305. /package/dist/{src/templates → templates}/wiki-templates.js +0 -0
  306. /package/dist/{src/version.js → version.js} +0 -0
  307. /package/dist/{src/workflows → workflows}/authoring.js +0 -0
  308. /package/dist/{src/workflows → workflows}/cli.js +0 -0
  309. /package/dist/{src/workflows → workflows}/db.js +0 -0
  310. /package/dist/{src/workflows → workflows}/document-cache.js +0 -0
  311. /package/dist/{src/workflows → workflows}/parser.js +0 -0
  312. /package/dist/{src/workflows → workflows}/renderer.js +0 -0
  313. /package/dist/{src/workflows → workflows}/schema.js +0 -0
  314. /package/dist/{src/workflows → workflows}/validator.js +0 -0
@@ -1,109 +0,0 @@
1
- /**
2
- * akm-bench verifier dispatcher (spec §5.3).
3
- *
4
- * • `script` — spawn `<taskDir>/verify.sh` with cwd = workspace.
5
- * • `pytest` — spawn `pytest -q --tb=line` with cwd = workspace.
6
- * • `regex` — match `expected_match` against `agentStdout`.
7
- *
8
- * No LLM-as-judge anywhere. Static dispatch only.
9
- *
10
- * Missing runtime (e.g. `pytest` not on PATH) returns exit code 127 with a
11
- * clear stdout message. The driver maps that to `outcome: "harness_error"`,
12
- * NOT `fail` — a missing tool is not an agent failure.
13
- */
14
- import fs from "node:fs";
15
- import path from "node:path";
16
- function resolveSpawn(config) {
17
- if (config?.spawn)
18
- return config.spawn;
19
- const bun = globalThis.Bun;
20
- if (!bun?.spawn)
21
- throw new Error("Bun.spawn unavailable; pass config.spawn");
22
- return bun.spawn.bind(bun);
23
- }
24
- async function readStream(stream) {
25
- if (!stream)
26
- return "";
27
- try {
28
- return await new Response(stream).text();
29
- }
30
- catch {
31
- return "";
32
- }
33
- }
34
- async function runProcess(cmd, cwd, spawn) {
35
- let proc;
36
- try {
37
- proc = spawn(cmd, {
38
- cwd,
39
- stdout: "pipe",
40
- stderr: "pipe",
41
- });
42
- }
43
- catch (err) {
44
- const message = err instanceof Error ? err.message : String(err);
45
- // ENOENT (binary missing) maps to 127 — the conventional "command not found".
46
- return {
47
- exitCode: 127,
48
- stdout: `verifier failed to spawn: ${message}`,
49
- };
50
- }
51
- const stdoutPromise = readStream(proc.stdout ?? null);
52
- const stderrPromise = readStream(proc.stderr ?? null);
53
- let exitCode;
54
- try {
55
- exitCode = await proc.exited;
56
- }
57
- catch (err) {
58
- const message = err instanceof Error ? err.message : String(err);
59
- return {
60
- exitCode: 127,
61
- stdout: `verifier exited with error: ${message}`,
62
- };
63
- }
64
- const [stdout, stderr] = await Promise.all([stdoutPromise, stderrPromise]);
65
- // Combine stdout+stderr so the operator sees the full verifier output.
66
- const combined = stderr ? `${stdout}\n--- stderr ---\n${stderr}` : stdout;
67
- return { exitCode, stdout: combined };
68
- }
69
- /**
70
- * Dispatch a verifier run. Each branch maps a `task.yaml` `verifier:` field
71
- * onto a deterministic check.
72
- */
73
- export async function runVerifier(taskDir, workspace, kind, config) {
74
- if (kind === "script") {
75
- const script = path.join(taskDir, "verify.sh");
76
- if (!fs.existsSync(script)) {
77
- return { exitCode: 127, stdout: `verify.sh not found at ${script}` };
78
- }
79
- return runProcess(["bash", script], workspace, resolveSpawn(config));
80
- }
81
- if (kind === "pytest") {
82
- return runProcess(["pytest", "-q", "--tb=line"], workspace, resolveSpawn(config));
83
- }
84
- if (kind === "regex") {
85
- const pattern = config?.expectedMatch;
86
- const input = config?.agentStdout ?? "";
87
- if (!pattern) {
88
- return {
89
- exitCode: 127,
90
- stdout: 'regex verifier requires "expected_match" in task.yaml',
91
- };
92
- }
93
- let regex;
94
- try {
95
- regex = new RegExp(pattern);
96
- }
97
- catch (err) {
98
- const message = err instanceof Error ? err.message : String(err);
99
- return { exitCode: 127, stdout: `invalid regex: ${message}` };
100
- }
101
- const matched = regex.test(input);
102
- return {
103
- exitCode: matched ? 0 : 1,
104
- stdout: matched ? `regex match: ${pattern}` : `regex did not match: ${pattern}`,
105
- };
106
- }
107
- // Compiler should refuse to land an unknown kind; runtime guard is belt-and-braces.
108
- return { exitCode: 127, stdout: `unknown verifier kind: ${String(kind)}` };
109
- }
@@ -1,118 +0,0 @@
1
- /**
2
- * Unit tests for the verifier dispatcher. Covers each of the three
3
- * verifier kinds plus the missing-pytest graceful-127 path.
4
- */
5
- import { afterAll, beforeAll, describe, expect, test } from "bun:test";
6
- import fs from "node:fs";
7
- import path from "node:path";
8
- import { benchMkdtemp } from "./tmp";
9
- import { runVerifier } from "./verifier";
10
- let scratch;
11
- beforeAll(() => {
12
- scratch = benchMkdtemp("bench-verifier-test-");
13
- });
14
- afterAll(() => {
15
- fs.rmSync(scratch, { recursive: true, force: true });
16
- });
17
- function fakeSpawn(exitCode, stdout = "", stderr = "", throwSync) {
18
- return (_cmd, _options) => {
19
- if (throwSync)
20
- throw throwSync;
21
- const proc = {
22
- exitCode,
23
- exited: Promise.resolve(exitCode),
24
- stdout: stdout
25
- ? new ReadableStream({
26
- start(controller) {
27
- controller.enqueue(new TextEncoder().encode(stdout));
28
- controller.close();
29
- },
30
- })
31
- : null,
32
- stderr: stderr
33
- ? new ReadableStream({
34
- start(controller) {
35
- controller.enqueue(new TextEncoder().encode(stderr));
36
- controller.close();
37
- },
38
- })
39
- : null,
40
- stdin: null,
41
- kill() {
42
- /* noop */
43
- },
44
- };
45
- return proc;
46
- };
47
- }
48
- describe("runVerifier — script", () => {
49
- test("returns exit 0 when verify.sh succeeds", async () => {
50
- const taskDir = path.join(scratch, "script-pass");
51
- fs.mkdirSync(taskDir);
52
- fs.writeFileSync(path.join(taskDir, "verify.sh"), "");
53
- const workspace = fs.mkdtempSync(path.join(scratch, "ws-"));
54
- const result = await runVerifier(taskDir, workspace, "script", {
55
- spawn: fakeSpawn(0, "ok"),
56
- });
57
- expect(result.exitCode).toBe(0);
58
- expect(result.stdout).toContain("ok");
59
- });
60
- test("returns 127 when verify.sh is missing", async () => {
61
- const taskDir = path.join(scratch, "script-missing");
62
- fs.mkdirSync(taskDir);
63
- const workspace = fs.mkdtempSync(path.join(scratch, "ws-"));
64
- const result = await runVerifier(taskDir, workspace, "script", {
65
- spawn: fakeSpawn(0),
66
- });
67
- expect(result.exitCode).toBe(127);
68
- expect(result.stdout).toContain("verify.sh not found");
69
- });
70
- });
71
- describe("runVerifier — regex", () => {
72
- test("returns 0 when expected_match matches agent stdout", async () => {
73
- const result = await runVerifier(scratch, scratch, "regex", {
74
- agentStdout: "the agent printed: hello world",
75
- expectedMatch: "hello",
76
- });
77
- expect(result.exitCode).toBe(0);
78
- });
79
- test("returns 1 when expected_match does not match", async () => {
80
- const result = await runVerifier(scratch, scratch, "regex", {
81
- agentStdout: "different output",
82
- expectedMatch: "hello",
83
- });
84
- expect(result.exitCode).toBe(1);
85
- });
86
- test("returns 127 when expected_match missing", async () => {
87
- const result = await runVerifier(scratch, scratch, "regex", {
88
- agentStdout: "anything",
89
- });
90
- expect(result.exitCode).toBe(127);
91
- expect(result.stdout).toContain("expected_match");
92
- });
93
- test("returns 127 on invalid regex pattern", async () => {
94
- const result = await runVerifier(scratch, scratch, "regex", {
95
- agentStdout: "x",
96
- expectedMatch: "(",
97
- });
98
- expect(result.exitCode).toBe(127);
99
- expect(result.stdout).toContain("invalid regex");
100
- });
101
- });
102
- describe("runVerifier — pytest", () => {
103
- test("returns 127 with a clear message when pytest is missing", async () => {
104
- const result = await runVerifier(scratch, scratch, "pytest", {
105
- // Simulate ENOENT: spawn throws when bin not on PATH.
106
- spawn: fakeSpawn(0, "", "", new Error("ENOENT: pytest not found")),
107
- });
108
- expect(result.exitCode).toBe(127);
109
- expect(result.stdout).toContain("ENOENT");
110
- });
111
- test("returns the pytest exit code when present", async () => {
112
- const result = await runVerifier(scratch, scratch, "pytest", {
113
- spawn: fakeSpawn(0, "1 passed in 0.05s"),
114
- });
115
- expect(result.exitCode).toBe(0);
116
- expect(result.stdout).toContain("passed");
117
- });
118
- });