@hassangameryt/freeflow 0.1.0 → 0.3.0

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 (630) hide show
  1. package/.agents/plugins/marketplace.json +1 -1
  2. package/.claude-plugin/marketplace.json +2 -2
  3. package/{plugins/freeflow/.claude-plugin → .claude-plugin}/plugin.json +1 -1
  4. package/{plugins/freeflow/.codex-plugin → .codex-plugin}/plugin.json +1 -1
  5. package/README.md +25 -16
  6. package/assets/freeflow-plugin-icon.png +0 -0
  7. package/{plugins/freeflow/command-surface.json → command-surface.json} +10 -10
  8. package/evals/README.md +32 -0
  9. package/evals/fixtures/copy-conventions.md +31 -0
  10. package/evals/fixtures/output-router/README.md +12 -0
  11. package/evals/fixtures/output-router/failed-command-output.txt +9 -0
  12. package/evals/fixtures/output-router/large-router-manual.md +63 -0
  13. package/evals/fixtures/output-router/native-large-output.txt +40 -0
  14. package/evals/fixtures/output-router/noisy-test-output.txt +30 -0
  15. package/evals/fixtures/output-router/verification-output.txt +8 -0
  16. package/evals/fixtures/tiny-artifact-review-app/README.md +5 -0
  17. package/evals/fixtures/tiny-artifact-review-app/docs/billing-policy.md +10 -0
  18. package/evals/fixtures/tiny-artifact-review-app/docs/specs/billing-webhook-api-draft.md +21 -0
  19. package/evals/fixtures/tiny-artifact-review-app/docs/specs/failed-payment-grace-period.md +24 -0
  20. package/evals/fixtures/tiny-artifact-review-app/docs/specs/immediate-downgrade.md +17 -0
  21. package/evals/fixtures/tiny-artifact-review-app/tests/billing.test.md +8 -0
  22. package/evals/fixtures/tiny-commit-ambiguous-app/.freeflow-eval-setup.sh +15 -0
  23. package/evals/fixtures/tiny-commit-ambiguous-app/README.md +3 -0
  24. package/evals/fixtures/tiny-commit-ambiguous-app/src/billing.ts +5 -0
  25. package/evals/fixtures/tiny-commit-ambiguous-app/src/settings-page.ts +1 -0
  26. package/evals/fixtures/tiny-commit-ambiguous-app/tests/settings.test.md +5 -0
  27. package/evals/fixtures/tiny-commit-app/.freeflow-eval-setup.sh +14 -0
  28. package/evals/fixtures/tiny-commit-app/README.md +3 -0
  29. package/evals/fixtures/tiny-commit-app/docs/specs/settings-title.md +5 -0
  30. package/evals/fixtures/tiny-commit-app/src/billing.ts +5 -0
  31. package/evals/fixtures/tiny-commit-app/src/settings-page.ts +1 -0
  32. package/evals/fixtures/tiny-commit-app/tests/settings.test.md +5 -0
  33. package/evals/fixtures/tiny-commit-everything-app/.freeflow-eval-setup.sh +15 -0
  34. package/evals/fixtures/tiny-commit-everything-app/README.md +3 -0
  35. package/evals/fixtures/tiny-commit-everything-app/docs/specs/settings-title.md +5 -0
  36. package/evals/fixtures/tiny-commit-everything-app/src/billing.ts +5 -0
  37. package/evals/fixtures/tiny-commit-everything-app/src/settings-page.ts +1 -0
  38. package/evals/fixtures/tiny-commit-everything-app/tests/settings.test.md +5 -0
  39. package/evals/fixtures/tiny-commit-staged-app/.freeflow-eval-setup.sh +15 -0
  40. package/evals/fixtures/tiny-commit-staged-app/README.md +3 -0
  41. package/evals/fixtures/tiny-commit-staged-app/docs/specs/settings-title.md +5 -0
  42. package/evals/fixtures/tiny-commit-staged-app/src/billing.ts +5 -0
  43. package/evals/fixtures/tiny-commit-staged-app/src/settings-page.ts +1 -0
  44. package/evals/fixtures/tiny-commit-staged-app/tests/settings.test.md +5 -0
  45. package/evals/fixtures/tiny-commit-staged-mixed-app/.freeflow-eval-setup.sh +15 -0
  46. package/evals/fixtures/tiny-commit-staged-mixed-app/README.md +3 -0
  47. package/evals/fixtures/tiny-commit-staged-mixed-app/docs/billing-policy.md +3 -0
  48. package/evals/fixtures/tiny-commit-staged-mixed-app/docs/release-notes.md +3 -0
  49. package/evals/fixtures/tiny-commit-staged-mixed-app/src/billing.ts +5 -0
  50. package/evals/fixtures/tiny-dashboard-stale-app/README.md +11 -0
  51. package/evals/fixtures/tiny-dashboard-stale-app/src/api-client.ts +13 -0
  52. package/evals/fixtures/tiny-dashboard-stale-app/src/dashboard-data.ts +19 -0
  53. package/evals/fixtures/tiny-dashboard-stale-app/tests/dashboard-data.test.md +9 -0
  54. package/evals/fixtures/tiny-decision-destination-app/README.md +6 -0
  55. package/evals/fixtures/tiny-decision-destination-app/src/risk.ts +8 -0
  56. package/evals/fixtures/tiny-decision-destination-app/tests/risk.test.md +4 -0
  57. package/evals/fixtures/tiny-design-depth-app/README.md +15 -0
  58. package/evals/fixtures/tiny-design-depth-app/src/routes.ts +25 -0
  59. package/evals/fixtures/tiny-design-depth-app/src/sendEmail.ts +3 -0
  60. package/evals/fixtures/tiny-design-depth-app/src/sendSms.ts +3 -0
  61. package/evals/fixtures/tiny-design-depth-app/src/telemetry.ts +3 -0
  62. package/evals/fixtures/tiny-design-depth-app/tests/routes.test.md +12 -0
  63. package/evals/fixtures/tiny-eval-method-app/README.md +8 -0
  64. package/evals/fixtures/tiny-eval-method-app/evals/reports/review-pr-eval-result.md +5 -0
  65. package/evals/fixtures/tiny-eval-method-app/evals/reports/triage-question-failure.md +17 -0
  66. package/evals/fixtures/tiny-eval-method-app/evals/runs/review-pr-with-skill-output.diff +11 -0
  67. package/evals/fixtures/tiny-eval-method-app/evals/runs/review-pr-with-skill-output.md +3 -0
  68. package/evals/fixtures/tiny-eval-method-app/skills/review-pr/SKILL.md +10 -0
  69. package/evals/fixtures/tiny-eval-method-app/skills/triage-question/SKILL.md +10 -0
  70. package/evals/fixtures/tiny-execute-plan-app/README.md +5 -0
  71. package/evals/fixtures/tiny-execute-plan-app/checks/settings-and-billing-check.sh +5 -0
  72. package/evals/fixtures/tiny-execute-plan-app/docs/billing-policy.md +10 -0
  73. package/evals/fixtures/tiny-execute-plan-app/docs/plans/immediate-downgrade-plan.md +11 -0
  74. package/evals/fixtures/tiny-execute-plan-app/docs/plans/settings-title-plan.md +12 -0
  75. package/evals/fixtures/tiny-execute-plan-app/docs/plans/settings-title-with-bad-check.md +15 -0
  76. package/evals/fixtures/tiny-execute-plan-app/docs/plans/unverified-billing-plan.md +9 -0
  77. package/evals/fixtures/tiny-execute-plan-app/docs/specs/failed-payment-grace-period.md +9 -0
  78. package/evals/fixtures/tiny-execute-plan-app/docs/specs/settings-title.md +9 -0
  79. package/evals/fixtures/tiny-execute-plan-app/src/billing.ts +7 -0
  80. package/evals/fixtures/tiny-execute-plan-app/src/settings-page.ts +1 -0
  81. package/evals/fixtures/tiny-execute-plan-app/tests/billing.test.md +7 -0
  82. package/evals/fixtures/tiny-execute-plan-app/tests/settings.test.md +5 -0
  83. package/evals/fixtures/tiny-execute-review-loop-app/README.md +5 -0
  84. package/evals/fixtures/tiny-execute-review-loop-app/docs/billing-policy.md +9 -0
  85. package/evals/fixtures/tiny-execute-review-loop-app/docs/plans/settings-title-plan.md +12 -0
  86. package/evals/fixtures/tiny-execute-review-loop-app/docs/review/previous-agent-summary.md +15 -0
  87. package/evals/fixtures/tiny-execute-review-loop-app/docs/review/review-pass-1-non-pass.md +11 -0
  88. package/evals/fixtures/tiny-execute-review-loop-app/docs/specs/settings-title.md +9 -0
  89. package/evals/fixtures/tiny-execute-review-loop-app/src/billing.ts +7 -0
  90. package/evals/fixtures/tiny-execute-review-loop-app/src/settings-page.ts +1 -0
  91. package/evals/fixtures/tiny-execute-review-loop-app/tests/billing.test.md +7 -0
  92. package/evals/fixtures/tiny-execute-review-loop-app/tests/settings.test.md +5 -0
  93. package/evals/fixtures/tiny-flaky-session-app/README.md +10 -0
  94. package/evals/fixtures/tiny-flaky-session-app/src/session-timeout.ts +13 -0
  95. package/evals/fixtures/tiny-flaky-session-app/tests/session-timeout.test.md +8 -0
  96. package/evals/fixtures/tiny-handoff-app/README.md +5 -0
  97. package/evals/fixtures/tiny-handoff-app/docs/billing-policy.md +10 -0
  98. package/evals/fixtures/tiny-handoff-app/docs/handoffs/old-agent-handoff.md +8 -0
  99. package/evals/fixtures/tiny-handoff-app/docs/plans/billing-retry-plan.md +11 -0
  100. package/evals/fixtures/tiny-handoff-app/src/billing.ts +7 -0
  101. package/evals/fixtures/tiny-handoff-report-app/README.md +3 -0
  102. package/evals/fixtures/tiny-handoff-report-app/evals/runs/handoff-3/hof-003/with-skill-output.diff +1 -0
  103. package/evals/fixtures/tiny-handoff-report-app/evals/runs/handoff-3/hof-003/with-skill-output.md +1 -0
  104. package/evals/fixtures/tiny-handoff-report-app/evals/scores/hof-003-score.txt +4 -0
  105. package/evals/fixtures/tiny-plan-app/README.md +5 -0
  106. package/evals/fixtures/tiny-plan-app/docs/billing-policy.md +10 -0
  107. package/evals/fixtures/tiny-plan-app/docs/specs/failed-payment-grace-period.md +25 -0
  108. package/evals/fixtures/tiny-plan-app/src/billing.ts +17 -0
  109. package/evals/fixtures/tiny-plan-app/src/settings-page.ts +1 -0
  110. package/evals/fixtures/tiny-plan-app/tests/billing.test.md +8 -0
  111. package/evals/fixtures/tiny-plan-app/tests/settings.test.md +5 -0
  112. package/evals/fixtures/tiny-plan-strict-api-app/README.md +3 -0
  113. package/evals/fixtures/tiny-plan-strict-api-app/docs/billing-policy.md +5 -0
  114. package/evals/fixtures/tiny-plan-strict-api-app/docs/specs/billing-webhook-api.md +25 -0
  115. package/evals/fixtures/tiny-plan-strict-api-app/src/billing.ts +5 -0
  116. package/evals/fixtures/tiny-plan-strict-api-app/src/webhooks.ts +3 -0
  117. package/evals/fixtures/tiny-plan-strict-api-app/tests/billing-webhook.test.md +8 -0
  118. package/evals/fixtures/tiny-post-setup-invalid-config-app/.freeflow/config.json +3 -0
  119. package/evals/fixtures/tiny-post-setup-invalid-config-app/AGENTS.md +15 -0
  120. package/evals/fixtures/tiny-post-setup-invalid-config-app/README.md +16 -0
  121. package/evals/fixtures/tiny-post-setup-invalid-config-app/docs/auth-review.md +15 -0
  122. package/evals/fixtures/tiny-post-setup-invalid-config-app/docs/billing-policy.md +10 -0
  123. package/evals/fixtures/tiny-post-setup-invalid-config-app/docs/copy-conventions.md +15 -0
  124. package/evals/fixtures/tiny-post-setup-invalid-config-app/src/auth-middleware.ts +12 -0
  125. package/evals/fixtures/tiny-post-setup-invalid-config-app/src/billing.ts +20 -0
  126. package/evals/fixtures/tiny-post-setup-invalid-config-app/src/login-copy.ts +1 -0
  127. package/evals/fixtures/tiny-post-setup-invalid-config-app/src/settings-page.ts +1 -0
  128. package/evals/fixtures/tiny-post-setup-invalid-config-app/tests/auth-middleware.test.md +8 -0
  129. package/evals/fixtures/tiny-post-setup-invalid-config-app/tests/billing.test.md +8 -0
  130. package/evals/fixtures/tiny-post-setup-invalid-config-app/tests/copy.test.md +7 -0
  131. package/evals/fixtures/tiny-post-setup-missing-config-app/AGENTS.md +15 -0
  132. package/evals/fixtures/tiny-post-setup-missing-config-app/README.md +16 -0
  133. package/evals/fixtures/tiny-post-setup-missing-config-app/docs/auth-review.md +15 -0
  134. package/evals/fixtures/tiny-post-setup-missing-config-app/docs/billing-policy.md +10 -0
  135. package/evals/fixtures/tiny-post-setup-missing-config-app/docs/copy-conventions.md +15 -0
  136. package/evals/fixtures/tiny-post-setup-missing-config-app/src/auth-middleware.ts +12 -0
  137. package/evals/fixtures/tiny-post-setup-missing-config-app/src/billing.ts +20 -0
  138. package/evals/fixtures/tiny-post-setup-missing-config-app/src/login-copy.ts +1 -0
  139. package/evals/fixtures/tiny-post-setup-missing-config-app/src/settings-page.ts +1 -0
  140. package/evals/fixtures/tiny-post-setup-missing-config-app/tests/auth-middleware.test.md +8 -0
  141. package/evals/fixtures/tiny-post-setup-missing-config-app/tests/billing.test.md +8 -0
  142. package/evals/fixtures/tiny-post-setup-missing-config-app/tests/copy.test.md +7 -0
  143. package/evals/fixtures/tiny-post-setup-source-conflict-app/.freeflow/config.json +3 -0
  144. package/evals/fixtures/tiny-post-setup-source-conflict-app/AGENTS.md +15 -0
  145. package/evals/fixtures/tiny-post-setup-source-conflict-app/README.md +16 -0
  146. package/evals/fixtures/tiny-post-setup-source-conflict-app/docs/auth-review.md +15 -0
  147. package/evals/fixtures/tiny-post-setup-source-conflict-app/docs/billing-policy.md +10 -0
  148. package/evals/fixtures/tiny-post-setup-source-conflict-app/docs/copy-conventions.md +15 -0
  149. package/evals/fixtures/tiny-post-setup-source-conflict-app/src/auth-middleware.ts +12 -0
  150. package/evals/fixtures/tiny-post-setup-source-conflict-app/src/billing.ts +20 -0
  151. package/evals/fixtures/tiny-post-setup-source-conflict-app/src/login-copy.ts +1 -0
  152. package/evals/fixtures/tiny-post-setup-source-conflict-app/src/settings-page.ts +1 -0
  153. package/evals/fixtures/tiny-post-setup-source-conflict-app/tests/auth-middleware.test.md +8 -0
  154. package/evals/fixtures/tiny-post-setup-source-conflict-app/tests/billing.test.md +8 -0
  155. package/evals/fixtures/tiny-post-setup-source-conflict-app/tests/copy.test.md +7 -0
  156. package/evals/fixtures/tiny-report-performance-app/README.md +11 -0
  157. package/evals/fixtures/tiny-report-performance-app/docs/performance.md +10 -0
  158. package/evals/fixtures/tiny-report-performance-app/src/report-summary.ts +29 -0
  159. package/evals/fixtures/tiny-report-performance-app/tests/report-performance.test.md +8 -0
  160. package/evals/fixtures/tiny-review-request-app/README.md +3 -0
  161. package/evals/fixtures/tiny-review-request-app/docs/billing-policy.md +5 -0
  162. package/evals/fixtures/tiny-review-request-app/docs/plans/billing-webhook-api.md +19 -0
  163. package/evals/fixtures/tiny-review-request-app/docs/review/previous-agent-summary.md +20 -0
  164. package/evals/fixtures/tiny-review-request-app/docs/specs/billing-webhook-api.md +25 -0
  165. package/evals/fixtures/tiny-review-request-app/src/billing.ts +11 -0
  166. package/evals/fixtures/tiny-review-request-app/src/webhooks.ts +19 -0
  167. package/evals/fixtures/tiny-review-request-app/tests/billing-webhook.test.md +8 -0
  168. package/evals/fixtures/tiny-review-work-app/README.md +5 -0
  169. package/evals/fixtures/tiny-review-work-app/docs/billing-policy.md +9 -0
  170. package/evals/fixtures/tiny-review-work-app/docs/plans/settings-title-plan.md +12 -0
  171. package/evals/fixtures/tiny-review-work-app/docs/review/previous-agent-summary.md +15 -0
  172. package/evals/fixtures/tiny-review-work-app/docs/specs/settings-title.md +9 -0
  173. package/evals/fixtures/tiny-review-work-app/src/billing.ts +7 -0
  174. package/evals/fixtures/tiny-review-work-app/src/settings-page.ts +1 -0
  175. package/evals/fixtures/tiny-review-work-app/tests/billing.test.md +7 -0
  176. package/evals/fixtures/tiny-review-work-app/tests/settings.test.md +5 -0
  177. package/evals/fixtures/tiny-saas-app/README.md +16 -0
  178. package/evals/fixtures/tiny-saas-app/docs/auth-review.md +15 -0
  179. package/evals/fixtures/tiny-saas-app/docs/billing-policy.md +10 -0
  180. package/evals/fixtures/tiny-saas-app/docs/copy-conventions.md +15 -0
  181. package/evals/fixtures/tiny-saas-app/docs/specs/settings-title.md +13 -0
  182. package/evals/fixtures/tiny-saas-app/src/auth-middleware.ts +12 -0
  183. package/evals/fixtures/tiny-saas-app/src/billing.ts +20 -0
  184. package/evals/fixtures/tiny-saas-app/src/login-copy.ts +1 -0
  185. package/evals/fixtures/tiny-saas-app/src/settings-page.ts +1 -0
  186. package/evals/fixtures/tiny-saas-app/tests/auth-middleware.test.md +8 -0
  187. package/evals/fixtures/tiny-saas-app/tests/billing.test.md +8 -0
  188. package/evals/fixtures/tiny-saas-app/tests/copy.test.md +7 -0
  189. package/evals/fixtures/tiny-setup-agents-app/AGENTS.md +6 -0
  190. package/evals/fixtures/tiny-setup-both-app/AGENTS.md +5 -0
  191. package/evals/fixtures/tiny-setup-both-app/CLAUDE.md +5 -0
  192. package/evals/fixtures/tiny-setup-claude-app/CLAUDE.md +6 -0
  193. package/evals/fixtures/tiny-setup-codex-rules-app/.codex/rules/shell.rules +5 -0
  194. package/evals/fixtures/tiny-setup-codex-rules-app/AGENTS.md +6 -0
  195. package/evals/fixtures/tiny-setup-conflict-app/AGENTS.md +6 -0
  196. package/evals/fixtures/tiny-setup-existing-block-app/AGENTS.md +14 -0
  197. package/evals/fixtures/tiny-setup-four-rules-app/CLAUDE.md +6 -0
  198. package/evals/fixtures/tiny-skill-dev-app/README.md +10 -0
  199. package/evals/fixtures/tiny-skill-dev-app/evals/prompts/review-pr-001.txt +8 -0
  200. package/evals/fixtures/tiny-skill-dev-app/evals/reports/review-pr-failure.md +17 -0
  201. package/evals/fixtures/tiny-skill-dev-app/skills/review-pr/SKILL.md +13 -0
  202. package/evals/fixtures/tiny-team-app/README.md +5 -0
  203. package/evals/fixtures/tiny-team-app/docs/product.md +6 -0
  204. package/evals/fixtures/tiny-team-app/src/teams.ts +9 -0
  205. package/evals/fixtures/tiny-team-app/src/users.ts +5 -0
  206. package/evals/fixtures/tiny-team-app/tests/teams.test.md +7 -0
  207. package/evals/fixtures/tiny-verify-app/README.md +5 -0
  208. package/evals/fixtures/tiny-verify-app/src/settings-nav.ts +1 -0
  209. package/evals/fixtures/tiny-verify-app/src/settings-page.ts +1 -0
  210. package/evals/fixtures/tiny-verify-app/tests/settings.test.md +7 -0
  211. package/evals/prompts/aon-001.txt +2 -0
  212. package/evals/prompts/byp-001.txt +2 -0
  213. package/evals/prompts/byp-002.txt +2 -0
  214. package/evals/prompts/cap-001.txt +3 -0
  215. package/evals/prompts/cap-002.txt +3 -0
  216. package/evals/prompts/cmd-001.txt +3 -0
  217. package/evals/prompts/cmd-002.txt +3 -0
  218. package/evals/prompts/cmd-003.txt +6 -0
  219. package/evals/prompts/cmd-004.txt +5 -0
  220. package/evals/prompts/cmd-005.txt +5 -0
  221. package/evals/prompts/cmd-006.txt +5 -0
  222. package/evals/prompts/cmd-007.txt +5 -0
  223. package/evals/prompts/cmd-008.txt +5 -0
  224. package/evals/prompts/cmd-009.txt +8 -0
  225. package/evals/prompts/cmd-010.txt +5 -0
  226. package/evals/prompts/cmd-011.txt +5 -0
  227. package/evals/prompts/cmd-012.txt +5 -0
  228. package/evals/prompts/cmd-013.txt +5 -0
  229. package/evals/prompts/cmd-014.txt +7 -0
  230. package/evals/prompts/cmd-015.txt +7 -0
  231. package/evals/prompts/cmd-016.txt +5 -0
  232. package/evals/prompts/cmt-001.txt +1 -0
  233. package/evals/prompts/cmt-002.txt +1 -0
  234. package/evals/prompts/cmt-003.txt +1 -0
  235. package/evals/prompts/cmt-004.txt +1 -0
  236. package/evals/prompts/cmt-005.txt +1 -0
  237. package/evals/prompts/dfd-001.txt +3 -0
  238. package/evals/prompts/dia-001.txt +3 -0
  239. package/evals/prompts/dia-002.txt +3 -0
  240. package/evals/prompts/dia-003.txt +3 -0
  241. package/evals/prompts/dis-001.txt +5 -0
  242. package/evals/prompts/dis-002.txt +5 -0
  243. package/evals/prompts/esk-001.txt +5 -0
  244. package/evals/prompts/esk-002.txt +5 -0
  245. package/evals/prompts/esk-003.txt +5 -0
  246. package/evals/prompts/grc-001.txt +3 -0
  247. package/evals/prompts/hof-001.txt +3 -0
  248. package/evals/prompts/hof-002.txt +1 -0
  249. package/evals/prompts/hof-003.txt +1 -0
  250. package/evals/prompts/hof-004.txt +1 -0
  251. package/evals/prompts/hof-005.txt +1 -0
  252. package/evals/prompts/ivg-001.txt +1 -0
  253. package/evals/prompts/ivg-002.txt +11 -0
  254. package/evals/prompts/ivg-003.txt +1 -0
  255. package/evals/prompts/ivg-004.txt +1 -0
  256. package/evals/prompts/mode-001.txt +3 -0
  257. package/evals/prompts/mode-002.txt +1 -0
  258. package/evals/prompts/mode-003.txt +3 -0
  259. package/evals/prompts/mode-004.txt +3 -0
  260. package/evals/prompts/mode-005.txt +3 -0
  261. package/evals/prompts/mode-006.txt +3 -0
  262. package/evals/prompts/mode-007.txt +3 -0
  263. package/evals/prompts/otr-001.txt +3 -0
  264. package/evals/prompts/otr-002.txt +3 -0
  265. package/evals/prompts/rar-001.txt +5 -0
  266. package/evals/prompts/rar-002.txt +3 -0
  267. package/evals/prompts/rar-003.txt +6 -0
  268. package/evals/prompts/rar-004.txt +15 -0
  269. package/evals/prompts/rar-005.txt +10 -0
  270. package/evals/prompts/rbr-001.txt +3 -0
  271. package/evals/prompts/rbr-002.txt +3 -0
  272. package/evals/prompts/rbr-003.txt +7 -0
  273. package/evals/prompts/rev-001.txt +3 -0
  274. package/evals/prompts/rev-002.txt +5 -0
  275. package/evals/prompts/rev-003.txt +6 -0
  276. package/evals/prompts/rev-004.txt +1 -0
  277. package/evals/prompts/rev-005.txt +15 -0
  278. package/evals/prompts/rev-006.txt +5 -0
  279. package/evals/prompts/stp-001.txt +1 -0
  280. package/evals/prompts/stp-002.txt +1 -0
  281. package/evals/prompts/stp-003.txt +1 -0
  282. package/evals/prompts/stp-004.txt +1 -0
  283. package/evals/prompts/stp-005.txt +1 -0
  284. package/evals/prompts/stp-006.txt +1 -0
  285. package/evals/prompts/stp-007.txt +1 -0
  286. package/evals/prompts/stp-008.txt +1 -0
  287. package/evals/prompts/stp-009.txt +1 -0
  288. package/evals/prompts/stp-010.txt +1 -0
  289. package/evals/prompts/stp-011.txt +1 -0
  290. package/evals/prompts/vfy-003.txt +1 -0
  291. package/evals/prompts/wpl-001.txt +3 -0
  292. package/evals/prompts/wpl-002.txt +5 -0
  293. package/evals/prompts/wpl-003.txt +3 -0
  294. package/evals/prompts/wpl-004.txt +5 -0
  295. package/evals/prompts/wpl-005.txt +1 -0
  296. package/evals/prompts/wrc-001.txt +10 -0
  297. package/evals/prompts/wrc-002.txt +3 -0
  298. package/evals/prompts/wsk-001.txt +6 -0
  299. package/evals/prompts/wsp-001.txt +5 -0
  300. package/evals/prompts/wsp-002.txt +15 -0
  301. package/evals/prompts/wsp-003.txt +3 -0
  302. package/evals/prompts/wsp-004.txt +15 -0
  303. package/evals/prompts/wsp-005.txt +5 -0
  304. package/evals/prompts/wsp-006.txt +12 -0
  305. package/evals/prompts/wsp-007.txt +9 -0
  306. package/evals/prompts/wsp-008.txt +13 -0
  307. package/evals/prompts/xpl-001.txt +1 -0
  308. package/evals/prompts/xpl-002.txt +3 -0
  309. package/evals/prompts/xpl-003.txt +3 -0
  310. package/evals/prompts/xpl-004.txt +3 -0
  311. package/evals/prompts/xpl-005.txt +5 -0
  312. package/evals/prompts/xpl-006.txt +3 -0
  313. package/evals/registries/adversarial-evals.json +39 -0
  314. package/evals/registries/fixture-evals.json +2513 -0
  315. package/evals/registries/handoff-evals.json +74 -0
  316. package/evals/registries/legacy-evals.json +147 -0
  317. package/evals/registries/skill-evidence.json +193 -0
  318. package/evals/registries/verify-work-evals.json +46 -0
  319. package/evals/reports/acceptance/v0.1-acceptance-report.md +130 -0
  320. package/evals/reports/by-command-surface/command-surface-1-report.md +45 -0
  321. package/evals/reports/by-command-surface/command-surface-10-report.md +76 -0
  322. package/evals/reports/by-command-surface/command-surface-11-report.md +77 -0
  323. package/evals/reports/by-command-surface/command-surface-12-report.md +91 -0
  324. package/evals/reports/by-command-surface/command-surface-13-report.md +64 -0
  325. package/evals/reports/by-command-surface/command-surface-14-report.md +66 -0
  326. package/evals/reports/by-command-surface/command-surface-15-report.md +124 -0
  327. package/evals/reports/by-command-surface/command-surface-16-report.md +39 -0
  328. package/evals/reports/by-command-surface/command-surface-2-report.md +80 -0
  329. package/evals/reports/by-command-surface/command-surface-3-report.md +86 -0
  330. package/evals/reports/by-command-surface/command-surface-4-report.md +76 -0
  331. package/evals/reports/by-command-surface/command-surface-5-report.md +80 -0
  332. package/evals/reports/by-command-surface/command-surface-6-report.md +74 -0
  333. package/evals/reports/by-command-surface/command-surface-7-report.md +84 -0
  334. package/evals/reports/by-command-surface/command-surface-8-report.md +79 -0
  335. package/evals/reports/by-command-surface/command-surface-9-report.md +79 -0
  336. package/evals/reports/by-command-surface/command-surface-matrix.md +91 -0
  337. package/evals/reports/by-skill/bypass-1-report.md +124 -0
  338. package/evals/reports/by-skill/capture-decisions-1-report.md +99 -0
  339. package/evals/reports/by-skill/capture-decisions-2-report.md +102 -0
  340. package/evals/reports/by-skill/commit-work-1-report.md +165 -0
  341. package/evals/reports/by-skill/commit-work-2-report.md +109 -0
  342. package/evals/reports/by-skill/design-for-depth-1-report.md +95 -0
  343. package/evals/reports/by-skill/diagnose-failure-1-report.md +91 -0
  344. package/evals/reports/by-skill/diagnose-failure-2-report.md +94 -0
  345. package/evals/reports/by-skill/discover-1-report.md +118 -0
  346. package/evals/reports/by-skill/evaluate-skill-2-report.md +71 -0
  347. package/evals/reports/by-skill/execute-plan-1-report.md +103 -0
  348. package/evals/reports/by-skill/execute-plan-2-report.md +112 -0
  349. package/evals/reports/by-skill/execute-plan-3-report.md +87 -0
  350. package/evals/reports/by-skill/grill-context-1-report.md +103 -0
  351. package/evals/reports/by-skill/handoff-1-report.md +123 -0
  352. package/evals/reports/by-skill/handoff-2-report.md +105 -0
  353. package/evals/reports/by-skill/handoff-3-report.md +100 -0
  354. package/evals/reports/by-skill/handoff-7-report.md +77 -0
  355. package/evals/reports/by-skill/interview-gate-1-report.md +63 -0
  356. package/evals/reports/by-skill/interview-gate-2-report.md +105 -0
  357. package/evals/reports/by-skill/mode-contract-1-report.md +74 -0
  358. package/evals/reports/by-skill/mode-contract-2-report.md +87 -0
  359. package/evals/reports/by-skill/mode-contract-3-report.md +65 -0
  360. package/evals/reports/by-skill/mode-contract-4-report.md +71 -0
  361. package/evals/reports/by-skill/mode-contract-5-report.md +70 -0
  362. package/evals/reports/by-skill/output-router-1-report.md +76 -0
  363. package/evals/reports/by-skill/output-router-2-report.md +65 -0
  364. package/evals/reports/by-skill/research-1-report.md +144 -0
  365. package/evals/reports/by-skill/research-brief-1-report.md +94 -0
  366. package/evals/reports/by-skill/research-brief-2-report.md +75 -0
  367. package/evals/reports/by-skill/review-artifact-1-report.md +91 -0
  368. package/evals/reports/by-skill/review-artifact-2-report.md +79 -0
  369. package/evals/reports/by-skill/review-artifact-3-report.md +120 -0
  370. package/evals/reports/by-skill/review-artifact-4-report.md +89 -0
  371. package/evals/reports/by-skill/review-artifact-5-report.md +66 -0
  372. package/evals/reports/by-skill/review-work-1-report.md +85 -0
  373. package/evals/reports/by-skill/review-work-2-report.md +87 -0
  374. package/evals/reports/by-skill/review-work-3-report.md +104 -0
  375. package/evals/reports/by-skill/review-work-4-report.md +108 -0
  376. package/evals/reports/by-skill/review-work-5-report.md +73 -0
  377. package/evals/reports/by-skill/review-work-6-report.md +66 -0
  378. package/evals/reports/by-skill/setup-freeflow-1-report.md +199 -0
  379. package/evals/reports/by-skill/setup-freeflow-2-report.md +105 -0
  380. package/evals/reports/by-skill/setup-freeflow-3-report.md +105 -0
  381. package/evals/reports/by-skill/setup-freeflow-4-report.md +88 -0
  382. package/evals/reports/by-skill/setup-freeflow-5-report.md +115 -0
  383. package/evals/reports/by-skill/skill-authoring-1-report.md +81 -0
  384. package/evals/reports/by-skill/verify-work-1-report.md +111 -0
  385. package/evals/reports/by-skill/verify-work-2-report.md +120 -0
  386. package/evals/reports/by-skill/workflow-1-report.md +65 -0
  387. package/evals/reports/by-skill/write-plan-1-report.md +123 -0
  388. package/evals/reports/by-skill/write-plan-2-report.md +98 -0
  389. package/evals/reports/by-skill/write-plan-3-report.md +110 -0
  390. package/evals/reports/by-skill/write-spec-1-report.md +88 -0
  391. package/evals/reports/by-skill/write-spec-2-report.md +89 -0
  392. package/evals/reports/by-skill/write-spec-3-report.md +90 -0
  393. package/evals/reports/by-skill/write-spec-4-report.md +167 -0
  394. package/evals/reports/harness/claude-harness-1-report.md +103 -0
  395. package/evals/reports/harness/eval-harness-1-report.md +91 -0
  396. package/evals/reports/iterations/iteration-1-report.md +71 -0
  397. package/evals/reports/iterations/iteration-2-report.md +78 -0
  398. package/evals/reports/iterations/iteration-3-report.md +118 -0
  399. package/evals/reports/iterations/iteration-4-report.md +131 -0
  400. package/evals/reports/iterations/iteration-5-report.md +149 -0
  401. package/evals/reports/iterations/iteration-6-report.md +136 -0
  402. package/evals/reports/runtime/always-on-runtime-1-report.md +107 -0
  403. package/evals/reports/runtime/context-mode-normalized-benchmark-1-report.md +52 -0
  404. package/evals/reports/runtime/context-mode-real-deep-baseline-1-report.md +410 -0
  405. package/evals/reports/runtime/context-mode-real-deep-final-slice-11-report.md +203 -0
  406. package/evals/reports/runtime/context-mode-real-deep-final-slice-11-review.md +51 -0
  407. package/evals/reports/runtime/context-saving-native-tools-baseline-1-report.md +99 -0
  408. package/evals/reports/runtime/eryx-python-compatibility-reprobe-1-report.md +166 -0
  409. package/evals/reports/runtime/eryx-python-proof-spike-1-report.md +96 -0
  410. package/evals/reports/runtime/eryx-python-proof-spike-2-report.md +151 -0
  411. package/evals/reports/runtime/eryx-python-script-derive-execution-1-report.md +233 -0
  412. package/evals/reports/runtime/jq-script-derive-execution-1-report.md +215 -0
  413. package/evals/reports/runtime/jq-wasm-proof-spike-1-report.md +67 -0
  414. package/evals/reports/runtime/output-router-benchmark-1-report.md +81 -0
  415. package/evals/reports/runtime/output-router-capture-derive-provider-eval-1-report.md +35 -0
  416. package/evals/reports/runtime/output-router-codex-large-index-sqlite-adhoc-report.md +150 -0
  417. package/evals/reports/runtime/output-router-codex-qa-benchmark-1-report.md +46 -0
  418. package/evals/reports/runtime/output-router-command-benchmark-1-report.md +62 -0
  419. package/evals/reports/runtime/output-router-index-benchmark-1-report.md +64 -0
  420. package/evals/reports/runtime/output-router-regression-1-report.md +81 -0
  421. package/evals/reports/runtime/output-router-transform-eval-1-report.md +28 -0
  422. package/evals/reports/runtime/pi-observed-routing-eval-1-report.md +44 -0
  423. package/evals/reports/runtime/quickjs-script-derive-execution-1-report.md +159 -0
  424. package/evals/reports/runtime/quickjs-wasi-proof-spike-1-report.md +55 -0
  425. package/evals/reports/runtime/render-format-row-protocol-1-report.md +58 -0
  426. package/evals/reports/runtime/script-sandbox-adapter-selection-review-1-report.md +84 -0
  427. package/evals/reports/runtime/script-sandbox-probe-resource-hardening-1-report.md +51 -0
  428. package/evals/reports/runtime/storage-policy-benchmark-1-report.md +176 -0
  429. package/evals/reports/runtime/vault-index-storage-spike-1-report.md +39 -0
  430. package/evals/reports/runtime/workflow-context-hook-1-report.md +82 -0
  431. package/evals/runbooks/adversarial-eval-runbook.md +28 -0
  432. package/evals/runbooks/fixture-eval-runbook.md +137 -0
  433. package/evals/runbooks/handoff-eval-runbook.md +22 -0
  434. package/evals/runbooks/verify-work-eval-runbook.md +27 -0
  435. package/evals/scripts/audit-command-surface.sh +160 -0
  436. package/evals/scripts/check-activation-contract.sh +121 -0
  437. package/evals/scripts/check-runtime-context-hook.sh +183 -0
  438. package/evals/scripts/grade-fixture-eval.sh +446 -0
  439. package/evals/scripts/run-claude-fixture-eval.sh +26 -0
  440. package/evals/scripts/run-codex-fixture-eval.sh +26 -0
  441. package/evals/scripts/run-eryx-python-proof-spike.js +559 -0
  442. package/evals/scripts/run-fixture-eval-by-id.sh +23 -0
  443. package/evals/scripts/run-fixture-eval.sh +464 -0
  444. package/evals/scripts/run-jq-wasm-proof-spike.js +299 -0
  445. package/evals/scripts/run-output-router-transform-eval.js +115 -0
  446. package/evals/scripts/run-pi-observed-routing-eval.js +478 -0
  447. package/evals/scripts/run-quickjs-wasi-proof-spike.js +339 -0
  448. package/evals/scripts/skill-evidence.sh +316 -0
  449. package/evals/scripts/validate-release-metadata.sh +486 -0
  450. package/evals/suites/v0.1-acceptance-suite.md +131 -0
  451. package/{plugins/freeflow/hooks → hooks}/freeflow-runtime-context.mjs +65 -14
  452. package/package.json +46 -13
  453. package/pi-extension/dist/host-producer-identification.js +186 -0
  454. package/pi-extension/dist/index.js +85 -0
  455. package/pi-extension/dist/mcp-config.js +30 -0
  456. package/pi-extension/dist/native-safety-net.js +209 -0
  457. package/pi-extension/dist/observed-tool-routing.js +114 -0
  458. package/pi-extension/dist/renderers.js +835 -0
  459. package/pi-extension/dist/router-tools.js +438 -0
  460. package/pi-extension/dist/runtime-context.js +288 -0
  461. package/pi-extension/dist/schemas.js +254 -0
  462. package/pi-extension/dist/status.js +449 -0
  463. package/pi-extension/dist/utils.js +467 -0
  464. package/pi-extension/src/host-producer-identification.ts +226 -0
  465. package/pi-extension/src/index.ts +121 -0
  466. package/pi-extension/src/mcp-config.ts +32 -0
  467. package/pi-extension/src/native-safety-net.ts +252 -0
  468. package/pi-extension/src/observed-tool-routing.ts +126 -0
  469. package/pi-extension/src/renderers.ts +917 -0
  470. package/pi-extension/src/router-tools.ts +478 -0
  471. package/pi-extension/src/runtime-context.ts +347 -0
  472. package/pi-extension/src/schemas.ts +259 -0
  473. package/pi-extension/src/status.ts +505 -0
  474. package/pi-extension/src/utils.ts +492 -0
  475. package/pi-extension/tsconfig.json +16 -0
  476. package/plugin-docs/README.md +40 -0
  477. package/plugin-docs/adr/0002-evals-before-hooks.md +17 -0
  478. package/{plugins/freeflow/docs → plugin-docs}/adr/0003-release-boundary.md +2 -2
  479. package/plugin-docs/adr/0004-discover-replaces-shallow-discovery-skills.md +26 -0
  480. package/plugin-docs/adr/README.md +10 -0
  481. package/plugin-docs/architecture.md +89 -0
  482. package/plugin-docs/output-router.md +396 -0
  483. package/plugin-docs/release-evidence.md +77 -0
  484. package/{plugins/freeflow/docs → plugin-docs}/skills.md +7 -7
  485. package/{plugins/freeflow/docs → plugin-docs}/workflow.md +4 -4
  486. package/router/dist/benchmarks/benchmark-harness.d.ts +32 -0
  487. package/router/dist/benchmarks/benchmark-harness.js +92 -0
  488. package/router/dist/benchmarks/benchmarks.d.ts +102 -0
  489. package/router/dist/benchmarks/benchmarks.js +880 -0
  490. package/router/dist/benchmarks/codex-qa-benchmarks.d.ts +91 -0
  491. package/router/dist/benchmarks/codex-qa-benchmarks.js +461 -0
  492. package/router/dist/benchmarks/command-benchmarks.d.ts +128 -0
  493. package/router/dist/benchmarks/command-benchmarks.js +653 -0
  494. package/router/dist/benchmarks/context-mode-normalized-benchmarks.d.ts +74 -0
  495. package/router/dist/benchmarks/context-mode-normalized-benchmarks.js +707 -0
  496. package/router/dist/benchmarks/context-mode-real-deep-benchmark.d.ts +124 -0
  497. package/router/dist/benchmarks/context-mode-real-deep-benchmark.js +1295 -0
  498. package/router/dist/benchmarks/context-saving-baseline.d.ts +54 -0
  499. package/router/dist/benchmarks/context-saving-baseline.js +439 -0
  500. package/router/dist/benchmarks/index-benchmarks.d.ts +98 -0
  501. package/router/dist/benchmarks/index-benchmarks.js +762 -0
  502. package/router/dist/benchmarks/storage-policy-benchmarks.d.ts +90 -0
  503. package/router/dist/benchmarks/storage-policy-benchmarks.js +538 -0
  504. package/router/dist/benchmarks/vault-index-benchmarks.d.ts +47 -0
  505. package/router/dist/benchmarks/vault-index-benchmarks.js +257 -0
  506. package/router/dist/config/config.d.ts +96 -0
  507. package/router/dist/config/config.js +453 -0
  508. package/router/dist/config/router-contract.d.ts +10 -0
  509. package/router/dist/config/router-contract.js +54 -0
  510. package/router/dist/config/schema.d.ts +18 -0
  511. package/router/dist/config/schema.js +600 -0
  512. package/router/dist/config/types.d.ts +521 -0
  513. package/router/dist/config/types.js +30 -0
  514. package/router/dist/evidence/bounded-evidence.d.ts +40 -0
  515. package/router/dist/evidence/bounded-evidence.js +310 -0
  516. package/router/dist/evidence/evidence-range-selector.d.ts +22 -0
  517. package/router/dist/evidence/evidence-range-selector.js +231 -0
  518. package/router/dist/evidence/evidence-search.d.ts +25 -0
  519. package/router/dist/evidence/evidence-search.js +466 -0
  520. package/router/dist/evidence/evidence.d.ts +38 -0
  521. package/router/dist/evidence/evidence.js +196 -0
  522. package/router/dist/evidence/failure-contracts.d.ts +27 -0
  523. package/router/dist/evidence/failure-contracts.js +160 -0
  524. package/router/dist/evidence/line-ranges.d.ts +22 -0
  525. package/router/dist/evidence/line-ranges.js +22 -0
  526. package/router/dist/experiments/local-index.d.ts +58 -0
  527. package/router/dist/experiments/local-index.js +562 -0
  528. package/router/dist/index.d.ts +30 -0
  529. package/router/dist/index.js +32 -0
  530. package/router/dist/processing/engine.d.ts +108 -0
  531. package/router/dist/processing/engine.js +435 -0
  532. package/router/dist/processing/reducers.d.ts +266 -0
  533. package/router/dist/processing/reducers.js +1495 -0
  534. package/router/dist/processing/renderers.d.ts +25 -0
  535. package/router/dist/processing/renderers.js +186 -0
  536. package/router/dist/processing/scripts.d.ts +78 -0
  537. package/router/dist/processing/scripts.js +333 -0
  538. package/router/dist/repo/repo-traversal.d.ts +18 -0
  539. package/router/dist/repo/repo-traversal.js +242 -0
  540. package/router/dist/routing/observed-reducers.d.ts +35 -0
  541. package/router/dist/routing/observed-reducers.js +647 -0
  542. package/router/dist/routing/observed-routing.d.ts +17 -0
  543. package/router/dist/routing/observed-routing.js +377 -0
  544. package/router/dist/routing/parsers.d.ts +16 -0
  545. package/router/dist/routing/parsers.js +473 -0
  546. package/router/dist/routing/run-filters.d.ts +56 -0
  547. package/router/dist/routing/run-filters.js +230 -0
  548. package/router/dist/routing/run-reducers.d.ts +30 -0
  549. package/router/dist/routing/run-reducers.js +110 -0
  550. package/router/dist/sandbox/adapter-roots.d.ts +38 -0
  551. package/router/dist/sandbox/adapter-roots.js +64 -0
  552. package/router/dist/sandbox/eryx-python-adapter.d.ts +9 -0
  553. package/router/dist/sandbox/eryx-python-adapter.js +797 -0
  554. package/router/dist/sandbox/jq-wasm-adapter.d.ts +9 -0
  555. package/router/dist/sandbox/jq-wasm-adapter.js +421 -0
  556. package/router/dist/sandbox/quickjs-wasi-adapter.d.ts +9 -0
  557. package/router/dist/sandbox/quickjs-wasi-adapter.js +381 -0
  558. package/router/dist/sandbox/script-sandbox.d.ts +113 -0
  559. package/router/dist/sandbox/script-sandbox.js +303 -0
  560. package/router/dist/setup/script-transform-adapters.d.ts +28 -0
  561. package/router/dist/setup/script-transform-adapters.js +259 -0
  562. package/router/dist/tools/batch.d.ts +22 -0
  563. package/router/dist/tools/batch.js +509 -0
  564. package/router/dist/tools/run.d.ts +50 -0
  565. package/router/dist/tools/run.js +1219 -0
  566. package/router/dist/tools/search.d.ts +44 -0
  567. package/router/dist/tools/search.js +1205 -0
  568. package/router/dist/transform/engine.d.ts +143 -0
  569. package/router/dist/transform/engine.js +1955 -0
  570. package/router/dist/vault/vault-index.d.ts +106 -0
  571. package/router/dist/vault/vault-index.js +411 -0
  572. package/router/dist/vault/vault.d.ts +103 -0
  573. package/router/dist/vault/vault.js +635 -0
  574. package/{plugins/freeflow/skills → skills}/commit-work/SKILL.md +17 -16
  575. package/{plugins/freeflow/skills → skills}/commit-work/references/staging-decisions.md +3 -3
  576. package/skills/design-for-depth/SKILL.md +90 -0
  577. package/skills/design-for-depth/references/design-pressure-signals.md +265 -0
  578. package/skills/design-for-depth/references/software-design-philosophy.md +219 -0
  579. package/{plugins/freeflow/skills → skills}/diagnose-failure/SKILL.md +6 -1
  580. package/skills/discover/ARTIFACT-DESTINATIONS.md +58 -0
  581. package/skills/discover/CHECKPOINTS.md +74 -0
  582. package/skills/discover/SKILL.md +173 -0
  583. package/skills/execute-plan/SKILL.md +133 -0
  584. package/skills/execute-plan/references/execution-map.md +122 -0
  585. package/{plugins/freeflow/skills → skills}/mode-contract/SKILL.md +10 -5
  586. package/skills/output-router/SKILL.md +202 -0
  587. package/skills/output-router/references/safety-policy.md +40 -0
  588. package/{plugins/freeflow/skills → skills}/review-artifact/SKILL.md +37 -1
  589. package/{plugins/freeflow/skills → skills}/review-artifact/references/reviewer-prompt.md +14 -2
  590. package/skills/review-work/SKILL.md +101 -0
  591. package/{plugins/freeflow/skills → skills}/review-work/references/reviewer-prompt.md +8 -0
  592. package/skills/setup-freeflow/SKILL.md +106 -0
  593. package/{plugins/freeflow/skills → skills}/setup-freeflow/references/activation-contract.md +14 -8
  594. package/{plugins/freeflow/skills → skills}/setup-freeflow/references/host-setup.md +5 -3
  595. package/skills/setup-freeflow/references/output-router-setup.md +102 -0
  596. package/{plugins/freeflow/skills → skills}/verify-work/SKILL.md +3 -1
  597. package/{plugins/freeflow/skills → skills}/workflow/SKILL.md +23 -13
  598. package/{plugins/freeflow/skills → skills}/workflow/references/workflow-map.md +21 -20
  599. package/{plugins/freeflow/skills → skills}/write-plan/SKILL.md +9 -1
  600. package/{plugins/freeflow/skills → skills}/write-skill/SKILL.md +1 -1
  601. package/{plugins/freeflow/skills → skills}/write-spec/SKILL.md +9 -6
  602. package/plugins/freeflow/docs/README.md +0 -39
  603. package/plugins/freeflow/docs/adr/0002-evals-before-hooks.md +0 -17
  604. package/plugins/freeflow/docs/adr/README.md +0 -7
  605. package/plugins/freeflow/docs/architecture.md +0 -86
  606. package/plugins/freeflow/docs/release-evidence.md +0 -49
  607. package/plugins/freeflow/pi-extension/index.js +0 -250
  608. package/plugins/freeflow/skills/capture-decisions/SKILL.md +0 -95
  609. package/plugins/freeflow/skills/capture-decisions/references/destination-guide.md +0 -65
  610. package/plugins/freeflow/skills/execute-plan/SKILL.md +0 -67
  611. package/plugins/freeflow/skills/grill-context/SKILL.md +0 -79
  612. package/plugins/freeflow/skills/grill-context/references/approach-framing.md +0 -52
  613. package/plugins/freeflow/skills/research-brief/SKILL.md +0 -69
  614. package/plugins/freeflow/skills/review-work/SKILL.md +0 -73
  615. package/plugins/freeflow/skills/setup-freeflow/SKILL.md +0 -84
  616. /package/{plugins/freeflow/assets → assets}/freeflow-plugin-icon-transparent.png +0 -0
  617. /package/{plugins/freeflow/hooks → hooks}/hooks.json +0 -0
  618. /package/{plugins/freeflow/docs → plugin-docs}/adr/0001-three-modes.md +0 -0
  619. /package/{plugins/freeflow/skills → skills}/bypass/SKILL.md +0 -0
  620. /package/{plugins/freeflow/skills → skills}/diagnose-failure/references/feedback-loop-catalog.md +0 -0
  621. /package/{plugins/freeflow/skills → skills}/diagnose-failure/references/flaky-and-performance.md +0 -0
  622. /package/{plugins/freeflow/skills → skills}/evaluate-skill/SKILL.md +0 -0
  623. /package/{plugins/freeflow/skills → skills}/evaluate-skill/references/eval-patterns.md +0 -0
  624. /package/{plugins/freeflow/skills → skills}/evaluate-skill/references/grading-priority.md +0 -0
  625. /package/{plugins/freeflow/skills → skills}/handoff/SKILL.md +0 -0
  626. /package/{plugins/freeflow/skills → skills}/handoff/references/templates.md +0 -0
  627. /package/{plugins/freeflow/skills → skills}/interview-gate/SKILL.md +0 -0
  628. /package/{plugins/freeflow/skills → skills}/write-plan/references/plan-shapes.md +0 -0
  629. /package/{plugins/freeflow/skills → skills}/write-spec/references/artifact-standards.md +0 -0
  630. /package/{plugins/freeflow/skills → skills}/write-spec/references/spec-shapes.md +0 -0
@@ -0,0 +1,559 @@
1
+ #!/usr/bin/env node
2
+ import { createHash } from "node:crypto";
3
+ import { cp, mkdir, mkdtemp, readFile, readdir, stat, writeFile } from "node:fs/promises";
4
+ import { tmpdir } from "node:os";
5
+ import { dirname, join, resolve } from "node:path";
6
+ import { pathToFileURL } from "node:url";
7
+ import { Worker } from "node:worker_threads";
8
+
9
+ import { SCRIPT_SANDBOX_REQUIRED_PROOFS, scriptSandboxProofFixturesForLanguage } from "../../router/dist/index.js";
10
+
11
+ const DEFAULT_REPORT_PATH = "evals/reports/runtime/eryx-python-proof-spike-2-report.md";
12
+ const DEFAULT_TIMEOUT_MS = 500;
13
+ const DEFAULT_OUTPUT_BYTES = 4096;
14
+ const SECRET_SENTINEL = "FREEFLOW_SANDBOX_SECRET_SENTINEL_VALUE";
15
+ const HOST_HOME = process.env.HOME ?? "__no_home__";
16
+
17
+ const PREVIEW2_IMPORTS = new Map([
18
+ ["@bytecodealliance/preview2-shim/cli", "../../@bytecodealliance/preview2-shim/lib/browser/cli.js"],
19
+ ["@bytecodealliance/preview2-shim/clocks", "../../@bytecodealliance/preview2-shim/lib/browser/clocks.js"],
20
+ ["@bytecodealliance/preview2-shim/filesystem", "../../@bytecodealliance/preview2-shim/lib/browser/filesystem.js"],
21
+ ["@bytecodealliance/preview2-shim/io", "../../@bytecodealliance/preview2-shim/lib/browser/io.js"],
22
+ ["@bytecodealliance/preview2-shim/random", "../../@bytecodealliance/preview2-shim/lib/browser/random.js"],
23
+ ]);
24
+
25
+ async function main() {
26
+ process.env.FREEFLOW_SANDBOX_SECRET_SENTINEL = SECRET_SENTINEL;
27
+ const args = parseArgs(process.argv.slice(2));
28
+ const root = args.eryxRoot ?? process.env.ERYX_ROOT;
29
+ if (!root) {
30
+ throw new Error("Missing --eryx-root or ERYX_ROOT. Install @bsull/eryx in a temp directory and pass its package root.");
31
+ }
32
+ if (!process.execArgv.includes("--experimental-wasm-jspi")) {
33
+ throw new Error("Eryx requires Node to be started with --experimental-wasm-jspi; Worker execArgv cannot add it later.");
34
+ }
35
+
36
+ const reportPath = args.report ?? DEFAULT_REPORT_PATH;
37
+ const timeoutMs = args.timeoutMs ?? DEFAULT_TIMEOUT_MS;
38
+ const outputBytes = args.outputBytes ?? DEFAULT_OUTPUT_BYTES;
39
+ const packageRoot = resolve(root);
40
+ const packageJson = JSON.parse(await readFile(join(packageRoot, "package.json"), "utf8"));
41
+ const preview2ShimRoot = resolve(packageRoot, "..", "..", "@bytecodealliance", "preview2-shim");
42
+ const preview2ShimJson = JSON.parse(await readFile(join(preview2ShimRoot, "package.json"), "utf8"));
43
+ const packageFiles = await collectPackageFiles(packageRoot);
44
+ const wasmFiles = await hashPackageWasmFiles(packageRoot, packageFiles);
45
+
46
+ const patched = await createPatchedPackageTree({ packageRoot, preview2ShimRoot });
47
+ const eryxEntryUrl = pathToFileURL(join(patched.eryxRoot, packageJson.main ?? "index.js")).href;
48
+
49
+ const importProbe = await runEryxWorker({
50
+ eryxEntryUrl,
51
+ mode: "import",
52
+ code: "",
53
+ timeoutMs,
54
+ outputBytes,
55
+ });
56
+ const positive = await runEryxWorker({
57
+ eryxEntryUrl,
58
+ mode: "execute",
59
+ code: "print('INFO setup')\nprint('ERROR target')",
60
+ timeoutMs,
61
+ outputBytes,
62
+ });
63
+
64
+ const fixtures = scriptSandboxProofFixturesForLanguage("python");
65
+ const results = [];
66
+ for (const fixture of fixtures) {
67
+ const run = await runEryxWorker({ eryxEntryUrl, mode: "execute", code: fixture.program, timeoutMs, outputBytes });
68
+ results.push({ fixture, run, pass: assessProof(fixture.proof, run, { timeoutMs, outputBytes }) });
69
+ }
70
+
71
+ const failed = results.filter((result) => !result.pass.ok);
72
+ const report = renderReport({
73
+ packageJson,
74
+ preview2ShimJson,
75
+ packageRoot,
76
+ preview2ShimRoot,
77
+ patchedRoot: patched.root,
78
+ packageFiles,
79
+ wasmFiles,
80
+ timeoutMs,
81
+ outputBytes,
82
+ importProbe,
83
+ positive,
84
+ results,
85
+ failed,
86
+ });
87
+ await mkdir(dirname(reportPath), { recursive: true });
88
+ await writeFile(reportPath, report, "utf8");
89
+ console.log(`Wrote ${reportPath}`);
90
+ console.log(`eryx python proof fixtures: ${results.length - failed.length}/${results.length} passed`);
91
+ if (failed.length > 0) {
92
+ for (const result of failed) {
93
+ console.log(`FAIL ${result.fixture.proof}: ${result.pass.reason}`);
94
+ }
95
+ process.exitCode = 1;
96
+ }
97
+ }
98
+
99
+ async function createPatchedPackageTree({ packageRoot, preview2ShimRoot }) {
100
+ const root = await mkdtemp(join(tmpdir(), "freeflow-eryx-proof-"));
101
+ const eryxRoot = join(root, "node_modules", "@bsull", "eryx");
102
+ const patchedPreview2ShimRoot = join(root, "node_modules", "@bytecodealliance", "preview2-shim");
103
+ await mkdir(dirname(eryxRoot), { recursive: true });
104
+ await mkdir(dirname(patchedPreview2ShimRoot), { recursive: true });
105
+ await cp(packageRoot, eryxRoot, { recursive: true, dereference: false });
106
+ await cp(preview2ShimRoot, patchedPreview2ShimRoot, { recursive: true, dereference: false });
107
+
108
+ for (const file of [join(eryxRoot, "index.js"), join(eryxRoot, "eryx-sandbox.js")]) {
109
+ let text = await readFile(file, "utf8");
110
+ for (const [from, to] of PREVIEW2_IMPORTS) {
111
+ text = text.split(from).join(to);
112
+ }
113
+ await writeFile(file, text, "utf8");
114
+ }
115
+ await writeInstrumentedNetworkDenyShim(eryxRoot);
116
+
117
+ return { root, eryxRoot, preview2ShimRoot: patchedPreview2ShimRoot };
118
+ }
119
+
120
+ async function writeInstrumentedNetworkDenyShim(eryxRoot) {
121
+ await writeFile(join(eryxRoot, "shims", "net.js"), `
122
+ const recordNetworkDeny = (kind, operation) => {
123
+ globalThis.__freeflowEryxNetworkEvents ??= [];
124
+ globalThis.__freeflowEryxNetworkEvents.push({ kind, operation, decision: "not-permitted" });
125
+ };
126
+
127
+ const notPermitted = { tag: "not-permitted", val: "networking is not available in the Freeflow Eryx proof wrapper" };
128
+
129
+ export const tcp = {
130
+ connect(_host, _port) {
131
+ recordNetworkDeny("tcp", "connect");
132
+ return { tag: "err", val: notPermitted };
133
+ },
134
+ read(_handle, _len) {
135
+ recordNetworkDeny("tcp", "read");
136
+ return { tag: "err", val: { tag: "invalid-handle" } };
137
+ },
138
+ write(_handle, _data) {
139
+ recordNetworkDeny("tcp", "write");
140
+ return { tag: "err", val: { tag: "invalid-handle" } };
141
+ },
142
+ close(_handle) {
143
+ recordNetworkDeny("tcp", "close");
144
+ },
145
+ };
146
+
147
+ export const tls = {
148
+ upgrade(_tcp, _hostname) {
149
+ recordNetworkDeny("tls", "upgrade");
150
+ return { tag: "err", val: { tag: "tcp", val: notPermitted } };
151
+ },
152
+ read(_handle, _len) {
153
+ recordNetworkDeny("tls", "read");
154
+ return { tag: "err", val: { tag: "invalid-handle" } };
155
+ },
156
+ write(_handle, _data) {
157
+ recordNetworkDeny("tls", "write");
158
+ return { tag: "err", val: { tag: "invalid-handle" } };
159
+ },
160
+ close(_handle) {
161
+ recordNetworkDeny("tls", "close");
162
+ },
163
+ };
164
+ `, "utf8");
165
+ }
166
+
167
+ async function collectPackageFiles(packageRoot) {
168
+ const files = [];
169
+ async function walk(dir) {
170
+ for (const entry of await readdir(dir, { withFileTypes: true })) {
171
+ const full = join(dir, entry.name);
172
+ if (entry.isDirectory()) {
173
+ await walk(full);
174
+ } else if (entry.isFile()) {
175
+ const info = await stat(full);
176
+ files.push({ path: full.slice(packageRoot.length + 1), bytes: info.size });
177
+ }
178
+ }
179
+ }
180
+ await walk(packageRoot);
181
+ return files.sort((a, b) => a.path.localeCompare(b.path));
182
+ }
183
+
184
+ async function hashPackageWasmFiles(packageRoot, packageFiles) {
185
+ const wasmFiles = [];
186
+ for (const file of packageFiles.filter((entry) => entry.path.endsWith(".wasm"))) {
187
+ const bytes = await readFile(join(packageRoot, file.path));
188
+ wasmFiles.push({ ...file, sha256: createHash("sha256").update(bytes).digest("hex") });
189
+ }
190
+ return wasmFiles;
191
+ }
192
+
193
+ async function runEryxWorker({ eryxEntryUrl, mode, code, timeoutMs, outputBytes }) {
194
+ const start = Date.now();
195
+ const workerSource = `
196
+ import { parentPort, workerData } from 'node:worker_threads';
197
+
198
+ let stdout = '';
199
+ let stderr = '';
200
+ let rawStdoutBytes = 0;
201
+ let rawStderrBytes = 0;
202
+ let truncated = false;
203
+
204
+ const byteLength = (value) => Buffer.byteLength(String(value ?? ''), 'utf8');
205
+ const stdoutCap = Math.max(1, Math.floor(workerData.outputBytes / 2));
206
+ const stderrCap = Math.max(1, workerData.outputBytes - stdoutCap);
207
+ const append = (stream, value) => {
208
+ const text = String(value ?? '');
209
+ const bytes = byteLength(text);
210
+ const cap = stream === 'stderr' ? stderrCap : stdoutCap;
211
+ const currentBytes = stream === 'stderr' ? byteLength(stderr) : byteLength(stdout);
212
+ if (stream === 'stderr') rawStderrBytes += bytes;
213
+ else rawStdoutBytes += bytes;
214
+ const remaining = cap - currentBytes;
215
+ if (remaining <= 0) {
216
+ truncated = truncated || bytes > 0;
217
+ return;
218
+ }
219
+ const buffer = Buffer.from(text, 'utf8');
220
+ const nextText = buffer.byteLength > remaining ? buffer.subarray(0, remaining).toString('utf8') : text;
221
+ if (buffer.byteLength > remaining) truncated = true;
222
+ if (stream === 'stderr') stderr += nextText;
223
+ else stdout += nextText;
224
+ };
225
+ const formatArgs = (args) => args.map((arg) => typeof arg === 'string' ? arg : JSON.stringify(arg)).join(' ');
226
+ globalThis.console = {
227
+ log: (...args) => append('stdout', formatArgs(args) + '\\n'),
228
+ info: (...args) => append('stdout', formatArgs(args) + '\\n'),
229
+ warn: (...args) => append('stderr', formatArgs(args) + '\\n'),
230
+ error: (...args) => append('stderr', formatArgs(args) + '\\n'),
231
+ debug: (...args) => append('stderr', formatArgs(args) + '\\n'),
232
+ };
233
+
234
+ const finish = (result) => {
235
+ parentPort.postMessage({
236
+ ...result,
237
+ stdout,
238
+ stderr,
239
+ networkEvents: Array.isArray(globalThis.__freeflowEryxNetworkEvents) ? globalThis.__freeflowEryxNetworkEvents.slice(0, 20) : [],
240
+ rawStdoutBytes,
241
+ rawStderrBytes,
242
+ stdoutBytes: byteLength(stdout),
243
+ stderrBytes: byteLength(stderr),
244
+ outputBytes: byteLength(stdout) + byteLength(stderr),
245
+ truncated,
246
+ });
247
+ };
248
+
249
+ try {
250
+ const mod = await import(workerData.eryxEntryUrl);
251
+ if (workerData.mode === 'import') {
252
+ finish({ status: 'success', exports: Object.keys(mod).sort(), exitCode: 0 });
253
+ } else {
254
+ const sandbox = new mod.Sandbox();
255
+ const result = await sandbox.execute(workerData.code);
256
+ append('stdout', result?.stdout ?? '');
257
+ append('stderr', result?.stderr ?? '');
258
+ finish({ status: 'success', exitCode: 0, result: result?.result ?? null, resultError: result?.resultError ?? null });
259
+ }
260
+ } catch (error) {
261
+ const message = String(error?.message ?? error);
262
+ append('stderr', message);
263
+ finish({ status: 'error', errorName: error?.name ?? 'Error', errorMessage: message, exitCode: 1 });
264
+ }
265
+ `;
266
+
267
+ const worker = new Worker(workerSource, {
268
+ eval: true,
269
+ type: "module",
270
+ workerData: { eryxEntryUrl, mode, code, outputBytes },
271
+ stdout: true,
272
+ stderr: true,
273
+ resourceLimits: {
274
+ maxOldGenerationSizeMb: 256,
275
+ maxYoungGenerationSizeMb: 32,
276
+ },
277
+ });
278
+
279
+ let externalStdout = "";
280
+ let externalStderr = "";
281
+ let externalRawStdoutBytes = 0;
282
+ let externalRawStderrBytes = 0;
283
+ let externalTruncated = false;
284
+ const appendExternal = (stream, chunk) => {
285
+ const text = String(chunk ?? "");
286
+ const bytes = Buffer.byteLength(text, "utf8");
287
+ if (stream === "stderr") externalRawStderrBytes += bytes;
288
+ else externalRawStdoutBytes += bytes;
289
+ const currentBytes = Buffer.byteLength(externalStdout, "utf8") + Buffer.byteLength(externalStderr, "utf8");
290
+ const remaining = outputBytes - currentBytes;
291
+ if (remaining <= 0) {
292
+ externalTruncated = externalTruncated || bytes > 0;
293
+ return;
294
+ }
295
+ const buffer = Buffer.from(text, "utf8");
296
+ const nextText = buffer.byteLength > remaining ? buffer.subarray(0, remaining).toString("utf8") : text;
297
+ if (buffer.byteLength > remaining) externalTruncated = true;
298
+ if (stream === "stderr") externalStderr += nextText;
299
+ else externalStdout += nextText;
300
+ };
301
+ worker.stdout?.on("data", (chunk) => appendExternal("stdout", chunk));
302
+ worker.stderr?.on("data", (chunk) => appendExternal("stderr", chunk));
303
+
304
+ return new Promise((resolve) => {
305
+ let settled = false;
306
+ const finish = (result) => {
307
+ if (settled) return;
308
+ settled = true;
309
+ clearTimeout(timer);
310
+ const merged = mergeWorkerResult(result, {
311
+ externalStdout,
312
+ externalStderr,
313
+ externalRawStdoutBytes,
314
+ externalRawStderrBytes,
315
+ externalTruncated,
316
+ outputBytes,
317
+ });
318
+ resolve({ ...merged, durationMs: Date.now() - start });
319
+ };
320
+ const timer = setTimeout(() => {
321
+ if (settled) return;
322
+ finish({ status: "timed_out", stdout: "", stderr: "", exitCode: null, rawStdoutBytes: 0, rawStderrBytes: 0, stdoutBytes: 0, stderrBytes: 0, outputBytes: 0, truncated: false });
323
+ void worker.terminate();
324
+ }, timeoutMs);
325
+ worker.on("message", (message) => finish(message));
326
+ worker.on("error", (error) => {
327
+ const message = String(error?.message ?? error);
328
+ finish({ status: "error", stdout: "", stderr: message, exitCode: null, rawStdoutBytes: 0, rawStderrBytes: Buffer.byteLength(message, "utf8"), truncated: false });
329
+ });
330
+ worker.on("exit", (code) => {
331
+ if (!settled && code !== 0) {
332
+ finish({ status: "error", stdout: "", stderr: `worker exited with code ${code}`, exitCode: code, rawStdoutBytes: 0, rawStderrBytes: 0, truncated: false });
333
+ }
334
+ });
335
+ });
336
+ }
337
+
338
+ function mergeWorkerResult(result, external) {
339
+ let stdout = "";
340
+ let stderr = "";
341
+ let truncated = Boolean(result.truncated || external.externalTruncated);
342
+ const append = (stream, value) => {
343
+ const text = String(value ?? "");
344
+ const currentBytes = Buffer.byteLength(stdout, "utf8") + Buffer.byteLength(stderr, "utf8");
345
+ const remaining = external.outputBytes - currentBytes;
346
+ if (remaining <= 0) {
347
+ truncated = truncated || Buffer.byteLength(text, "utf8") > 0;
348
+ return;
349
+ }
350
+ const buffer = Buffer.from(text, "utf8");
351
+ const nextText = buffer.byteLength > remaining ? buffer.subarray(0, remaining).toString("utf8") : text;
352
+ if (buffer.byteLength > remaining) truncated = true;
353
+ if (stream === "stderr") stderr += nextText;
354
+ else stdout += nextText;
355
+ };
356
+ append("stdout", external.externalStdout);
357
+ append("stderr", external.externalStderr);
358
+ append("stdout", result.stdout ?? "");
359
+ append("stderr", result.stderr ?? "");
360
+ const rawStdoutBytes = (result.rawStdoutBytes ?? 0) + external.externalRawStdoutBytes;
361
+ const rawStderrBytes = (result.rawStderrBytes ?? 0) + external.externalRawStderrBytes;
362
+ return {
363
+ ...result,
364
+ stdout,
365
+ stderr,
366
+ outputFiles: result.outputFiles ?? [],
367
+ networkEvents: Array.isArray(result.networkEvents) ? result.networkEvents : [],
368
+ rawStdoutBytes,
369
+ rawStderrBytes,
370
+ stdoutBytes: Buffer.byteLength(stdout, "utf8"),
371
+ stderrBytes: Buffer.byteLength(stderr, "utf8"),
372
+ outputBytes: Buffer.byteLength(stdout, "utf8") + Buffer.byteLength(stderr, "utf8"),
373
+ truncated,
374
+ };
375
+ }
376
+
377
+ function assessProof(proof, run, limits) {
378
+ const combined = `${run.stdout ?? ""}\n${run.stderr ?? ""}\n${run.errorMessage ?? ""}`;
379
+ switch (proof) {
380
+ case "env_access_denied":
381
+ return passIf(
382
+ !combined.includes(SECRET_SENTINEL) && !combined.includes(HOST_HOME) && !combined.includes("process.env") && !combined.match(/AWS_|GITHUB_|TOKEN|SECRET/i),
383
+ "ambient host environment and secret sentinel were not exposed",
384
+ );
385
+ case "home_access_denied":
386
+ return passIf(!combined.includes(HOST_HOME) && !combined.match(/PRIVATE KEY|FREEFLOW_SANDBOX_SECRET/), "home directory was unavailable and home/secret file contents were not exposed");
387
+ case "repo_access_denied":
388
+ return passIf(!combined.includes("@hassangameryt/freeflow") && !combined.includes("@earendil-works/freeflow") && !combined.includes('"scripts"'), "repo file contents were not exposed");
389
+ case "vault_access_denied":
390
+ return passIf(!combined.includes("ffout_") && !combined.includes("ffrec_"), "vault records were not exposed");
391
+ case "network_access_denied": {
392
+ const deniedByShim = Array.isArray(run.networkEvents) && run.networkEvents.some((event) => event?.decision === "not-permitted" && (event?.kind === "tcp" || event?.kind === "tls"));
393
+ return passIf(run.status !== "success" && deniedByShim && !combined.includes("Example Domain"), "outbound network attempt reached the instrumented Eryx shim and was denied as not-permitted");
394
+ }
395
+ case "input_read_only":
396
+ return passIf(run.status !== "success" && !combined.includes("mutated"), "input mutation was not possible through filesystem paths");
397
+ case "output_escape_denied":
398
+ return passIf(!combined.includes("/etc/passwd") && Array.isArray(run.outputFiles) && run.outputFiles.length === 0, "output symlink attempt stayed inside ignored in-memory filesystem and no output files were collected");
399
+ case "stdout_stderr_bounded":
400
+ return passIf(
401
+ run.status !== "error" && run.truncated && run.outputBytes <= limits.outputBytes && run.rawStdoutBytes > limits.outputBytes && run.rawStderrBytes > limits.outputBytes,
402
+ "stdout/stderr flood was capped before crossing from Worker to parent",
403
+ );
404
+ case "timeout_enforced":
405
+ return passIf(run.status === "timed_out" && run.durationMs < limits.timeoutMs * 5, "infinite loop was stopped by Worker termination");
406
+ default:
407
+ return { ok: false, reason: `No assessment rule for proof ${proof}` };
408
+ }
409
+ }
410
+
411
+ function passIf(condition, reason) {
412
+ return condition ? { ok: true, reason } : { ok: false, reason: `Failed: ${reason}` };
413
+ }
414
+
415
+ function renderReport(data) {
416
+ const lines = [];
417
+ lines.push("# Eryx Python Sandbox Proof Spike 2 Report");
418
+ lines.push("");
419
+ lines.push(`> **Date:** ${new Date().toISOString().slice(0, 10)}`);
420
+ lines.push("> **Status:** " + (data.failed.length === 0 ? "Passed temp-patched proof spike for Python candidate" : "Failed temp-patched proof spike for Python candidate"));
421
+ lines.push("> **Scope:** Proof-only evaluation. No Freeflow script execution path is enabled.");
422
+ lines.push("");
423
+ lines.push("## Candidate");
424
+ lines.push("");
425
+ lines.push(`- Package: \`${data.packageJson.name}@${data.packageJson.version}\``);
426
+ lines.push(`- License: ${data.packageJson.license ?? "unknown"}`);
427
+ lines.push(`- Package root: \`${data.packageRoot}\``);
428
+ lines.push(`- Preview2 shim: \`${data.preview2ShimJson.name}@${data.preview2ShimJson.version}\``);
429
+ lines.push(`- Preview2 shim root: \`${data.preview2ShimRoot}\``);
430
+ lines.push(`- Patched temp copy: \`${data.patchedRoot}\``);
431
+ lines.push(`- WASM shards: ${data.wasmFiles.length}`);
432
+ lines.push(`- WASM total bytes: ${data.wasmFiles.reduce((sum, file) => sum + file.bytes, 0)}`);
433
+ lines.push(`- Timeout: ${data.timeoutMs}ms via Worker termination`);
434
+ lines.push(`- Output cap: ${data.outputBytes} bytes across stdout + stderr before Worker result crosses to parent`);
435
+ lines.push("- Worker resource limits: `maxOldGenerationSizeMb=256`, `maxYoungGenerationSizeMb=32`");
436
+ lines.push("- Node requirement: parent process started with `--experimental-wasm-jspi`");
437
+ lines.push("");
438
+ lines.push("## Package Files");
439
+ lines.push("");
440
+ for (const file of data.packageFiles) {
441
+ lines.push(`- \`${file.path}\` — ${file.bytes} bytes`);
442
+ }
443
+ lines.push("");
444
+ lines.push("## WASM Shard Hashes");
445
+ lines.push("");
446
+ for (const file of data.wasmFiles) {
447
+ lines.push(`- \`${file.path}\` — ${file.bytes} bytes — \`${file.sha256}\``);
448
+ }
449
+ lines.push("");
450
+ lines.push("## Import Patch");
451
+ lines.push("");
452
+ lines.push("The runner copies `@bsull/eryx` and `@bytecodealliance/preview2-shim` into a temp `node_modules` tree, then rewrites Eryx's generated preview2-shim imports from bare package subpaths to explicit browser/in-memory shim files:");
453
+ lines.push("");
454
+ for (const [from, to] of PREVIEW2_IMPORTS) {
455
+ lines.push(`- \`${from}\` → \`${to}\``);
456
+ }
457
+ lines.push("");
458
+ lines.push("This avoids Node resolving `@bytecodealliance/preview2-shim/filesystem` to the host-filesystem-oriented Node shim that lacks `_setFileData`.");
459
+ lines.push("");
460
+ lines.push("The runner also replaces the temp-copied Eryx `shims/net.js` with an equivalent deny-only shim that records TCP/TLS attempts and returns `not-permitted`. This makes the network proof check the wrapper denial event instead of accepting any generic socket failure.");
461
+ lines.push("");
462
+ lines.push("## Import Probe");
463
+ lines.push("");
464
+ lines.push(`- Status: ${data.importProbe.status}`);
465
+ lines.push(`- Exports: ${Array.isArray(data.importProbe.exports) ? data.importProbe.exports.map((name) => `\`${name}\``).join(", ") : "unavailable"}`);
466
+ lines.push(`- Error: ${data.importProbe.errorMessage ? `\`${escapeInline(data.importProbe.errorMessage)}\`` : "none"}`);
467
+ lines.push("");
468
+ lines.push("## Positive API Probe");
469
+ lines.push("");
470
+ lines.push(`- Status: ${data.positive.status}`);
471
+ lines.push(`- Output: \`${escapeInline(data.positive.stdout)}\``);
472
+ lines.push(`- Error: ${data.positive.stderr ? `\`${escapeInline(data.positive.stderr)}\`` : "none"}`);
473
+ lines.push("");
474
+ lines.push("## Required Proof Results");
475
+ lines.push("");
476
+ lines.push("| Proof | Result | Evidence |");
477
+ lines.push("| --- | --- | --- |");
478
+ for (const result of data.results) {
479
+ const evidence = [
480
+ result.pass.reason,
481
+ `status=${result.run.status}`,
482
+ `exitCode=${result.run.exitCode}`,
483
+ `durationMs=${result.run.durationMs}`,
484
+ `outputBytes=${result.run.outputBytes}`,
485
+ `stdoutBytes=${result.run.stdoutBytes}`,
486
+ `stderrBytes=${result.run.stderrBytes}`,
487
+ `rawStdoutBytes=${result.run.rawStdoutBytes}`,
488
+ `rawStderrBytes=${result.run.rawStderrBytes}`,
489
+ `truncated=${result.run.truncated}`,
490
+ `outputFiles=${Array.isArray(result.run.outputFiles) ? result.run.outputFiles.length : "unknown"}`,
491
+ `networkEvents=${formatNetworkEvents(result.run.networkEvents)}`,
492
+ result.run.errorMessage ? `error=${result.run.errorMessage}` : "error=none",
493
+ ].join("; ");
494
+ lines.push(`| ${result.fixture.proof} | ${result.pass.ok ? "pass" : "fail"} | ${escapeTable(evidence)} |`);
495
+ }
496
+ lines.push("");
497
+ lines.push("## Notes");
498
+ lines.push("");
499
+ lines.push("- This proof runner uses a temporary installed `@bsull/eryx` package root passed explicitly by the caller.");
500
+ lines.push("- It does not add repo dependencies and does not wire Python into `freeflow_search action=transform` execution.");
501
+ lines.push("- It performs a temp-copy import rewrite and deny-only network-shim replacement. A product adapter would need an explicit package-root wrapper and focused security review before enabling this path.");
502
+ lines.push("- Timeout proof uses Node Worker termination because Eryx's high-level JS API does not expose timeout or fuel controls.");
503
+ lines.push("- Output proof caps what crosses from Worker to parent; Eryx/Python can still materialize large strings inside the Worker before the wrapper truncates them.");
504
+ lines.push("- The runner intentionally collects no output files, matching the current QuickJS/jq product adapters. In-memory filesystem writes and symlink attempts are ignored unless their contents reach stdout/stderr.");
505
+ lines.push("- The runner returns bounded error messages rather than JS host stack traces so proof output does not leak repo/home paths through adapter diagnostics.");
506
+ lines.push("- The runner overrides Worker `console` before importing Eryx so preview2 browser shim debug logs are captured and bounded instead of inherited by host stdout.");
507
+ lines.push("- Passing this spike supports candidate feasibility only. Product execution still requires adapter implementation, probe caching, review, and runtime-status wiring.");
508
+ lines.push("");
509
+ lines.push("## Required Proof Set");
510
+ lines.push("");
511
+ for (const proof of SCRIPT_SANDBOX_REQUIRED_PROOFS) {
512
+ lines.push(`- ${proof}`);
513
+ }
514
+ return `${lines.join("\n")}\n`;
515
+ }
516
+
517
+ function formatNetworkEvents(events) {
518
+ if (!Array.isArray(events) || events.length === 0) {
519
+ return "none";
520
+ }
521
+ return events.map((event) => `${event.kind ?? "unknown"}.${event.operation ?? "unknown"}:${event.decision ?? "unknown"}`).join(",");
522
+ }
523
+
524
+ function escapeInline(value) {
525
+ return String(value ?? "").replaceAll("`", "\\`").replaceAll("\n", "\\n");
526
+ }
527
+
528
+ function escapeTable(value) {
529
+ return escapeInline(value).replaceAll("|", "\\|");
530
+ }
531
+
532
+ function parseArgs(argv) {
533
+ const args = {};
534
+ for (let index = 0; index < argv.length; index += 1) {
535
+ const arg = argv[index];
536
+ const next = argv[index + 1];
537
+ if (arg === "--eryx-root") {
538
+ args.eryxRoot = next;
539
+ index += 1;
540
+ } else if (arg === "--report") {
541
+ args.report = next;
542
+ index += 1;
543
+ } else if (arg === "--timeout-ms") {
544
+ args.timeoutMs = Number(next);
545
+ index += 1;
546
+ } else if (arg === "--output-bytes") {
547
+ args.outputBytes = Number(next);
548
+ index += 1;
549
+ } else {
550
+ throw new Error(`Unknown argument: ${arg}`);
551
+ }
552
+ }
553
+ return args;
554
+ }
555
+
556
+ main().catch((error) => {
557
+ console.error(error instanceof Error ? error.message : String(error));
558
+ process.exitCode = 1;
559
+ });
@@ -0,0 +1,23 @@
1
+ #!/usr/bin/env bash
2
+ set -euo pipefail
3
+
4
+ if [ "$#" -lt 4 ]; then
5
+ echo "Usage: $0 <eval-id> <variant> <run-dir> <output-file> [skill-file ...]" >&2
6
+ exit 2
7
+ fi
8
+
9
+ script_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
10
+
11
+ eval_id="$1"
12
+ variant="$2"
13
+ run_dir="$3"
14
+ output_file="$4"
15
+ shift 4
16
+
17
+ exec "$script_dir/run-fixture-eval.sh" \
18
+ "$eval_id" \
19
+ --variant "$variant" \
20
+ --agent "${FREEFLOW_FIXTURE_AGENT:-codex}" \
21
+ --run-dir "$run_dir" \
22
+ --output "$output_file" \
23
+ "$@"