@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 +1,478 @@
1
+ #!/usr/bin/env node
2
+ import assert from "node:assert/strict";
3
+ import { mkdir, mkdtemp, rm, writeFile } from "node:fs/promises";
4
+ import { join } from "node:path";
5
+ import { tmpdir } from "node:os";
6
+
7
+ import { createVault, readOutputText } from "../../router/dist/index.js";
8
+ import freeflowExtension from "../../pi-extension/dist/index.js";
9
+
10
+ const REPORT_PATH = "evals/reports/runtime/pi-observed-routing-eval-1-report.md";
11
+ const DATE = "2026-06-24";
12
+
13
+ function loadExtension() {
14
+ const handlers = new Map();
15
+ const tools = [];
16
+ const pi = {
17
+ registerTool(tool) {
18
+ tools.push(tool);
19
+ },
20
+ registerCommand() {},
21
+ on(event, handler) {
22
+ handlers.set(event, handler);
23
+ },
24
+ appendEntry() {},
25
+ sendUserMessage() {},
26
+ };
27
+
28
+ freeflowExtension(pi);
29
+ return { handlers, tools };
30
+ }
31
+
32
+ function context(cwd, sessionId) {
33
+ return {
34
+ cwd,
35
+ sessionManager: {
36
+ getSessionId() {
37
+ return sessionId;
38
+ },
39
+ getEntries() {
40
+ return [];
41
+ },
42
+ },
43
+ ui: {
44
+ setStatus() {},
45
+ notify() {},
46
+ },
47
+ };
48
+ }
49
+
50
+ function bytes(value) {
51
+ return Buffer.byteLength(String(value), "utf8");
52
+ }
53
+
54
+ function lineCount(value) {
55
+ const text = String(value ?? "");
56
+ return text.length === 0 ? 0 : text.split(/\r?\n/).length;
57
+ }
58
+
59
+ function evidencePacketCount(text) {
60
+ return (String(text).match(/^Evidence \d+/gm) ?? []).length;
61
+ }
62
+
63
+ function passMark(value) {
64
+ return value ? "pass" : "fail";
65
+ }
66
+
67
+ function reductionPercent(rawBytes, routedBytes) {
68
+ if (!Number.isFinite(rawBytes) || rawBytes <= 0) {
69
+ return "n/a";
70
+ }
71
+ return `${((1 - routedBytes / rawBytes) * 100).toFixed(1)}%`;
72
+ }
73
+
74
+ function stableJson(value) {
75
+ return JSON.stringify(value, sortJsonKeys, 2);
76
+ }
77
+
78
+ function sortJsonKeys(_key, value) {
79
+ if (!value || typeof value !== "object" || Array.isArray(value)) {
80
+ return value;
81
+ }
82
+ return Object.keys(value).sort().reduce((sorted, key) => {
83
+ sorted[key] = value[key];
84
+ return sorted;
85
+ }, {});
86
+ }
87
+
88
+ function normalizeFixtureRaw(value) {
89
+ if (typeof value === "string") {
90
+ return value;
91
+ }
92
+ if (value && typeof value === "object" && !Array.isArray(value)) {
93
+ if (Array.isArray(value.content)) {
94
+ return value.content.map((block) => {
95
+ if (typeof block === "string") return block;
96
+ if (!block || typeof block !== "object") return String(block);
97
+ if (typeof block.text === "string") return block.text;
98
+ if (block.json !== undefined) return stableJson(block.json);
99
+ return stableJson(block);
100
+ }).join("\n");
101
+ }
102
+ if (typeof value.text === "string") {
103
+ return value.text;
104
+ }
105
+ }
106
+ return stableJson(value);
107
+ }
108
+
109
+ function countFixtureItems(value) {
110
+ if (Array.isArray(value)) return value.length;
111
+ if (!value || typeof value !== "object") return 0;
112
+ if (Array.isArray(value.items)) return value.items.length;
113
+ if (Array.isArray(value.results)) return value.results.length;
114
+ if (Array.isArray(value.messages)) return value.messages.length;
115
+ if (Array.isArray(value.content)) {
116
+ return value.content.reduce((total, block) => total + countFixtureItems(block?.json ?? block), 0);
117
+ }
118
+ if (value.data && typeof value.data === "object") return countFixtureItems(value.data);
119
+ return 1;
120
+ }
121
+
122
+ async function writeObservedConfig(cwd, vaultRoot, observedRouting) {
123
+ await mkdir(join(cwd, ".freeflow"), { recursive: true });
124
+ await writeFile(
125
+ join(cwd, ".freeflow/config.json"),
126
+ JSON.stringify(
127
+ {
128
+ defaultMode: "workflow",
129
+ outputRouter: {
130
+ largeOutputLines: 4,
131
+ largeOutputBytes: 520,
132
+ vaultRoot,
133
+ },
134
+ observedRouting,
135
+ },
136
+ null,
137
+ 2,
138
+ ),
139
+ "utf8",
140
+ );
141
+ }
142
+
143
+ function mcpEvent(server, tool, rawResult, details = {}) {
144
+ return {
145
+ type: "tool_result",
146
+ toolName: "mcp",
147
+ toolCallId: `${server}-${tool}`,
148
+ input: { server, tool },
149
+ content: [{ type: "text", text: normalizeFixtureRaw(rawResult) }],
150
+ details: { ...details, result: rawResult },
151
+ isError: false,
152
+ };
153
+ }
154
+
155
+ function builtInEvent(toolName, rawResult) {
156
+ return {
157
+ type: "tool_result",
158
+ toolName,
159
+ toolCallId: `${toolName}-fixture`,
160
+ input: {},
161
+ content: [{ type: "text", text: normalizeFixtureRaw(rawResult) }],
162
+ details: { result: rawResult },
163
+ isError: false,
164
+ };
165
+ }
166
+
167
+ async function runObservedFixture({ tmpRoot, id, config, event, criticalFacts, shouldReduce = true, recoverability = "exact", metadataOnly = false }) {
168
+ const cwd = join(tmpRoot, id);
169
+ const vaultRoot = join(cwd, "vault");
170
+ const sessionId = `${id}-session`;
171
+ await mkdir(cwd, { recursive: true });
172
+ await writeObservedConfig(cwd, vaultRoot, config);
173
+
174
+ const { handlers } = loadExtension();
175
+ const result = await handlers.get("tool_result")(event, context(cwd, sessionId));
176
+ assert.ok(result, `${id} did not route`);
177
+
178
+ const rawText = normalizeFixtureRaw(event.details.result);
179
+ const routedText = result.content[0].text;
180
+ const observed = result.details.freeflowObservedRouting;
181
+ const vault = createVault({ root: vaultRoot });
182
+
183
+ let recoveredText = null;
184
+ let recoveryError = null;
185
+ if (observed?.outputId) {
186
+ try {
187
+ recoveredText = await readOutputText(vault, sessionId, observed.outputId, "raw");
188
+ } catch (error) {
189
+ recoveryError = error instanceof Error ? error.message : String(error);
190
+ }
191
+ }
192
+
193
+ const gates = {
194
+ routedByPiHook: Boolean(observed && observed.route === "observed" && /Freeflow routed this observed/.test(routedText)),
195
+ boundedOutput: shouldReduce ? bytes(routedText) < bytes(rawText) : bytes(routedText) > 0,
196
+ criticalFactsPreserved: criticalFacts.every((pattern) => pattern.test(routedText)),
197
+ recoverabilityAccurate: metadataOnly
198
+ ? observed.persistence.recoverability === "metadata_only" && /No raw content stream is recoverable/.test(observed.recovery.how) && /metadata only/i.test(recoveryError ?? "")
199
+ : observed.persistence.recoverability === recoverability && recoveredText === rawText,
200
+ };
201
+
202
+ return {
203
+ id,
204
+ producer: [observed.producer.kind, observed.producer.server, observed.producer.tool].filter(Boolean).join(":"),
205
+ raw: {
206
+ bytes: bytes(rawText),
207
+ lines: lineCount(rawText),
208
+ items: countFixtureItems(event.details.result),
209
+ },
210
+ routed: {
211
+ bytes: bytes(routedText),
212
+ lines: lineCount(routedText),
213
+ evidencePackets: evidencePacketCount(routedText),
214
+ recoverability: observed.persistence.recoverability,
215
+ },
216
+ gates,
217
+ };
218
+ }
219
+
220
+ async function runStatusFixture(tmpRoot) {
221
+ const cwd = join(tmpRoot, "pi-capability-status");
222
+ await mkdir(join(cwd, ".freeflow"), { recursive: true });
223
+ await writeFile(
224
+ join(cwd, ".freeflow/config.json"),
225
+ JSON.stringify(
226
+ {
227
+ defaultMode: "workflow",
228
+ observedRouting: {
229
+ enabled: true,
230
+ mcp: { servers: { github: { enabled: true, persistence: "exact" } } },
231
+ web: { enabled: true, persistence: "exact" },
232
+ },
233
+ },
234
+ null,
235
+ 2,
236
+ ),
237
+ "utf8",
238
+ );
239
+
240
+ const { tools } = loadExtension();
241
+ const statusTool = tools.find((tool) => tool.name === "freeflow_status");
242
+ assert.ok(statusTool);
243
+ const result = await statusTool.execute("pi-observed-status", { action: "status" }, undefined, undefined, context(cwd, "status-session"));
244
+ const report = JSON.parse(result.content[0].text);
245
+ const gates = {
246
+ hostCapabilityReported: report.observedRouting.host.name === "pi" && report.observedRouting.host.outputReplacement === "available",
247
+ persistenceModesReported: ["exact", "metadata-only", "none"].every((mode) => report.observedRouting.persistenceModes.includes(mode)),
248
+ unsupportedRedactedReported: report.observedRouting.unsupportedPersistenceModes.includes("redacted"),
249
+ configuredProducerReported: report.observedRouting.mcp.servers.some((server) => server.id === "github" && server.persistence === "exact") && report.observedRouting.web.enabled === true,
250
+ };
251
+
252
+ return {
253
+ id: "pi-capability-status",
254
+ producer: "status",
255
+ raw: { bytes: 0, lines: 0, items: 0 },
256
+ routed: { bytes: bytes(result.content[0].text), lines: lineCount(result.content[0].text), evidencePackets: 0, recoverability: "n/a" },
257
+ gates,
258
+ };
259
+ }
260
+
261
+ function assertAllPassed(results) {
262
+ for (const result of results) {
263
+ for (const [name, passed] of Object.entries(result.gates)) {
264
+ assert.equal(passed, true, `${result.id} gate failed: ${name}`);
265
+ }
266
+ }
267
+ }
268
+
269
+ function renderReport(results) {
270
+ const totalGates = results.reduce((count, result) => count + Object.keys(result.gates).length, 0);
271
+ const passedGates = results.reduce((count, result) => count + Object.values(result.gates).filter(Boolean).length, 0);
272
+ const reductionRows = results.filter((result) => result.raw.bytes > 0);
273
+ const totalRawBytes = reductionRows.reduce((total, result) => total + result.raw.bytes, 0);
274
+ const totalRoutedBytes = reductionRows.reduce((total, result) => total + result.routed.bytes, 0);
275
+ const rows = results.map((result) => {
276
+ const gates = Object.entries(result.gates).map(([name, passed]) => `${name} ${passed ? "✓" : "✗"}`).join("; ");
277
+ return `| ${result.id} | ${result.producer} | ${result.raw.bytes} / ${result.raw.lines} / ${result.raw.items} | ${result.routed.bytes} / ${result.routed.lines} / ${result.routed.evidencePackets} | ${reductionPercent(result.raw.bytes, result.routed.bytes)} | ${result.routed.recoverability} | ${passMark(Object.values(result.gates).every(Boolean))} | ${gates} |`;
278
+ }).join("\n");
279
+
280
+ return `# Pi Observed Routing Eval - Iteration 1
281
+
282
+ Date: ${DATE}
283
+
284
+ ## Scope
285
+
286
+ Targeted deterministic eval for the Pi-only observed output routing slice. It exercises Pi's \`tool_result\` path for configured MCP, web, fetch, and code-search producers after direct host execution.
287
+
288
+ This eval compares raw direct tool-output fixtures against the routed result returned to the agent. It verifies bounded output, exact critical fact preservation, persistence/recovery claims, metadata-only no-raw-recovery behavior, mutating MCP routing as metadata (not a gate), and Pi status capability reporting.
289
+
290
+ It does not claim Context Mode or cross-host superiority. Claude and Codex observed-routing adapters remain out of scope.
291
+
292
+ ## Command
293
+
294
+ \`\`\`sh
295
+ npm run build && node evals/scripts/run-pi-observed-routing-eval.js
296
+ \`\`\`
297
+
298
+ ## Summary
299
+
300
+ - Fixtures: ${results.length}
301
+ - Objective gates passed: ${passedGates}/${totalGates}
302
+ - Host: Pi only.
303
+ - Direct execution/permissions: owned by Pi; Freeflow routes only completed tool output.
304
+ - Persistence modes covered: exact and metadata-only.
305
+ - Overall byte reduction, excluding status-only fixtures: ${reductionPercent(totalRawBytes, totalRoutedBytes)}.
306
+
307
+ ## Results
308
+
309
+ Raw and routed columns are \`bytes / lines / items-or-evidence-packets\`. Reduction is calculated from raw bytes to routed-result bytes.
310
+
311
+ | fixture | producer | raw direct output | routed output | byte reduction | recoverability | status | gates |
312
+ | --- | --- | ---: | ---: | ---: | --- | --- | --- |
313
+ ${rows}
314
+
315
+ ## Result
316
+
317
+ All targeted Pi observed-routing gates passed for these deterministic fixtures. Pi observed routing materially reduced large/noisy fixture output while preserving critical facts and truthful recovery behavior.
318
+ `;
319
+ }
320
+
321
+ async function main() {
322
+ const tmpRoot = await mkdtemp(join(tmpdir(), "freeflow-pi-observed-eval-"));
323
+ try {
324
+ const commonObserved = {
325
+ enabled: true,
326
+ mcp: {
327
+ servers: {
328
+ github: { enabled: true, persistence: "exact" },
329
+ gmail: { enabled: true, persistence: "metadata-only" },
330
+ },
331
+ },
332
+ web: { enabled: true, persistence: "exact" },
333
+ fetch: { enabled: true, persistence: "exact" },
334
+ codeSearch: { enabled: true, persistence: "exact" },
335
+ };
336
+
337
+ const githubSearch = {
338
+ content: [
339
+ {
340
+ type: "json",
341
+ json: {
342
+ items: [
343
+ { id: 101, number: 1, title: "Observed routing bug", state: "open", html_url: "https://github.com/acme/freeflow/issues/101", body: "diagnostic noise ".repeat(120) },
344
+ { id: 102, number: 2, title: "Vault recovery docs", state: "closed", html_url: "https://github.com/acme/freeflow/issues/102", body: "release chatter ".repeat(120) },
345
+ { id: 103, number: 3, title: "Reducer fixture", state: "open", html_url: "https://github.com/acme/freeflow/issues/103", body: "triage details ".repeat(120) },
346
+ { id: 104, number: 4, title: "Large output follow-up", state: "open", html_url: "https://github.com/acme/freeflow/issues/104", body: "followup details ".repeat(120) },
347
+ ],
348
+ },
349
+ },
350
+ ],
351
+ };
352
+
353
+ const githubCreate = {
354
+ content: [
355
+ {
356
+ type: "json",
357
+ json: {
358
+ id: 2201,
359
+ number: 22,
360
+ title: "Created by observed routing eval",
361
+ state: "open",
362
+ html_url: "https://github.com/acme/freeflow/issues/22",
363
+ body: "created issue response noise ".repeat(80),
364
+ },
365
+ },
366
+ ],
367
+ };
368
+
369
+ const gmailSearch = {
370
+ content: [
371
+ {
372
+ type: "text",
373
+ text: [
374
+ "Subject: Customer secret renewal",
375
+ "From: private@example.test",
376
+ "Snippet: token should not be vaulted",
377
+ "noise ".repeat(2000),
378
+ ].join("\n"),
379
+ },
380
+ ],
381
+ };
382
+
383
+ const webSearch = {
384
+ query: "Freeflow observed routing",
385
+ results: [
386
+ { title: "Observed Routing Design", url: "https://example.test/freeflow/observed", snippet: "Routes completed tool output after host execution.", citation: "[1]" },
387
+ { title: "Vault Recovery", url: "https://example.test/freeflow/vault", snippet: "Exact recovery uses outputId and raw streams.", citation: "[2]" },
388
+ { title: "Reducer Registry", url: "https://example.test/freeflow/reducers", snippet: "Producer reducers keep critical URLs and snippets.", citation: "[3]" },
389
+ { title: "Long Result", url: "https://example.test/freeflow/noise", snippet: "noise ".repeat(160), citation: "[4]" },
390
+ ],
391
+ };
392
+
393
+ const fetchResult = {
394
+ url: "https://docs.example.test/freeflow/observed-routing",
395
+ title: "Observed Routing Docs",
396
+ contentType: "text/markdown",
397
+ content: [
398
+ "# Observed Routing Docs",
399
+ "Intro noise ".repeat(80),
400
+ "## Configure",
401
+ "```json",
402
+ "{ \"observedRouting\": { \"enabled\": true } }",
403
+ "```",
404
+ "## Recover",
405
+ "```sh",
406
+ "freeflow_search action=retrieve source.kind=vault outputId=ffout_example stream=raw",
407
+ "```",
408
+ "tail noise ".repeat(120),
409
+ ].join("\n"),
410
+ };
411
+
412
+ const codeSearch = {
413
+ query: "routeObservedToolOutput",
414
+ results: [
415
+ { repo: "acme/freeflow", path: "router/src/observed-routing.ts", line: 41, symbol: "routeObservedToolOutput", snippet: "export async function routeObservedToolOutput(options) {" },
416
+ { repo: "acme/freeflow", path: "pi-extension/src/observed-tool-routing.ts", line: 6, symbol: "handleObservedToolRouting", snippet: "export async function handleObservedToolRouting(event, ctx) {" },
417
+ { repo: "acme/freeflow", path: "generated/noise.ts", line: 999, symbol: "decoy", snippet: "generated noise ".repeat(500) },
418
+ ],
419
+ };
420
+
421
+ const results = [];
422
+ results.push(await runObservedFixture({
423
+ tmpRoot,
424
+ id: "mcp-github-search-exact",
425
+ config: commonObserved,
426
+ event: mcpEvent("github", "search_issues", githubSearch),
427
+ criticalFacts: [/Observed routing bug/, /https:\/\/github\.com\/acme\/freeflow\/issues\/101/, /Vault recovery docs/],
428
+ }));
429
+ results.push(await runObservedFixture({
430
+ tmpRoot,
431
+ id: "mcp-github-create-mutating",
432
+ config: commonObserved,
433
+ event: mcpEvent("github", "create_issue", githubCreate, { mcp: { annotations: { destructiveHint: true } } }),
434
+ criticalFacts: [/Created by observed routing eval/, /https:\/\/github\.com\/acme\/freeflow\/issues\/22/],
435
+ }));
436
+ results.push(await runObservedFixture({
437
+ tmpRoot,
438
+ id: "mcp-gmail-search-metadata-only",
439
+ config: commonObserved,
440
+ event: mcpEvent("gmail", "search", gmailSearch),
441
+ criticalFacts: [/Customer secret renewal/, /metadata_only|metadata-only/i],
442
+ metadataOnly: true,
443
+ }));
444
+ results.push(await runObservedFixture({
445
+ tmpRoot,
446
+ id: "pi-web-search-exact",
447
+ config: commonObserved,
448
+ event: builtInEvent("web_search", webSearch),
449
+ criticalFacts: [/Observed Routing Design/, /https:\/\/example\.test\/freeflow\/observed/, /\[1\]/],
450
+ }));
451
+ results.push(await runObservedFixture({
452
+ tmpRoot,
453
+ id: "pi-fetch-content-exact",
454
+ config: commonObserved,
455
+ event: builtInEvent("fetch_content", fetchResult),
456
+ criticalFacts: [/Observed Routing Docs/, /## Configure/, /freeflow_search action=retrieve source\.kind=vault/],
457
+ }));
458
+ results.push(await runObservedFixture({
459
+ tmpRoot,
460
+ id: "pi-code-search-exact",
461
+ config: commonObserved,
462
+ event: builtInEvent("code_search", codeSearch),
463
+ criticalFacts: [/plugins\/freeflow\/router\/src\/observed-routing\.ts/, /"line": 41/, /routeObservedToolOutput/],
464
+ }));
465
+ results.push(await runStatusFixture(tmpRoot));
466
+
467
+ assertAllPassed(results);
468
+ await mkdir(join("evals/reports/runtime"), { recursive: true });
469
+ await writeFile(REPORT_PATH, renderReport(results), "utf8");
470
+ } finally {
471
+ await rm(tmpRoot, { recursive: true, force: true });
472
+ }
473
+ }
474
+
475
+ main().catch((error) => {
476
+ console.error(error);
477
+ process.exitCode = 1;
478
+ });