@hassangameryt/freeflow 0.2.0 → 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 (639) 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 +19 -14
  6. package/assets/freeflow-plugin-icon.png +0 -0
  7. package/{plugins/freeflow/command-surface.json → command-surface.json} +10 -2
  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 +46 -12
  452. package/package.json +39 -19
  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/{plugins/freeflow/docs → plugin-docs}/README.md +3 -3
  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 +3 -2
  485. package/{plugins/freeflow/docs → plugin-docs}/workflow.md +4 -4
  486. package/{plugins/freeflow/router/dist → router/dist/benchmarks}/benchmark-harness.js +1 -1
  487. package/{plugins/freeflow/router/dist → router/dist/benchmarks}/benchmarks.js +14 -14
  488. package/{plugins/freeflow/router/dist → router/dist/benchmarks}/codex-qa-benchmarks.js +6 -6
  489. package/{plugins/freeflow/router/dist → router/dist/benchmarks}/command-benchmarks.d.ts +1 -1
  490. package/{plugins/freeflow/router/dist → router/dist/benchmarks}/command-benchmarks.js +11 -10
  491. package/router/dist/benchmarks/context-mode-normalized-benchmarks.d.ts +74 -0
  492. package/router/dist/benchmarks/context-mode-normalized-benchmarks.js +707 -0
  493. package/router/dist/benchmarks/context-mode-real-deep-benchmark.d.ts +124 -0
  494. package/router/dist/benchmarks/context-mode-real-deep-benchmark.js +1295 -0
  495. package/router/dist/benchmarks/context-saving-baseline.d.ts +54 -0
  496. package/router/dist/benchmarks/context-saving-baseline.js +439 -0
  497. package/{plugins/freeflow/router/dist → router/dist/benchmarks}/index-benchmarks.d.ts +16 -2
  498. package/{plugins/freeflow/router/dist → router/dist/benchmarks}/index-benchmarks.js +330 -26
  499. package/router/dist/benchmarks/storage-policy-benchmarks.d.ts +90 -0
  500. package/router/dist/benchmarks/storage-policy-benchmarks.js +538 -0
  501. package/router/dist/benchmarks/vault-index-benchmarks.d.ts +47 -0
  502. package/router/dist/benchmarks/vault-index-benchmarks.js +257 -0
  503. package/router/dist/config/config.d.ts +96 -0
  504. package/router/dist/config/config.js +453 -0
  505. package/{plugins/freeflow/router/dist → router/dist/config}/schema.js +248 -2
  506. package/router/dist/config/types.d.ts +521 -0
  507. package/router/dist/config/types.js +30 -0
  508. package/{plugins/freeflow/router/dist → router/dist/evidence}/bounded-evidence.d.ts +1 -1
  509. package/{plugins/freeflow/router/dist → router/dist/evidence}/evidence-range-selector.js +65 -14
  510. package/{plugins/freeflow/router/dist → router/dist/evidence}/evidence-search.js +18 -2
  511. package/{plugins/freeflow/router/dist → router/dist/evidence}/evidence.d.ts +1 -1
  512. package/router/dist/evidence/failure-contracts.d.ts +27 -0
  513. package/router/dist/evidence/failure-contracts.js +160 -0
  514. package/router/dist/index.d.ts +30 -0
  515. package/router/dist/index.js +32 -0
  516. package/router/dist/processing/engine.d.ts +108 -0
  517. package/router/dist/processing/engine.js +435 -0
  518. package/router/dist/processing/reducers.d.ts +266 -0
  519. package/router/dist/processing/reducers.js +1495 -0
  520. package/router/dist/processing/renderers.d.ts +25 -0
  521. package/router/dist/processing/renderers.js +186 -0
  522. package/router/dist/processing/scripts.d.ts +78 -0
  523. package/router/dist/processing/scripts.js +333 -0
  524. package/router/dist/routing/observed-reducers.d.ts +35 -0
  525. package/router/dist/routing/observed-reducers.js +647 -0
  526. package/router/dist/routing/observed-routing.d.ts +17 -0
  527. package/router/dist/routing/observed-routing.js +377 -0
  528. package/{plugins/freeflow/router/dist → router/dist/routing}/parsers.d.ts +1 -1
  529. package/{plugins/freeflow/router/dist → router/dist/routing}/parsers.js +1 -1
  530. package/router/dist/routing/run-filters.d.ts +56 -0
  531. package/router/dist/routing/run-filters.js +230 -0
  532. package/router/dist/routing/run-reducers.d.ts +30 -0
  533. package/router/dist/routing/run-reducers.js +110 -0
  534. package/router/dist/sandbox/adapter-roots.d.ts +38 -0
  535. package/router/dist/sandbox/adapter-roots.js +64 -0
  536. package/router/dist/sandbox/eryx-python-adapter.d.ts +9 -0
  537. package/router/dist/sandbox/eryx-python-adapter.js +797 -0
  538. package/router/dist/sandbox/jq-wasm-adapter.d.ts +9 -0
  539. package/router/dist/sandbox/jq-wasm-adapter.js +421 -0
  540. package/router/dist/sandbox/quickjs-wasi-adapter.d.ts +9 -0
  541. package/router/dist/sandbox/quickjs-wasi-adapter.js +381 -0
  542. package/router/dist/sandbox/script-sandbox.d.ts +113 -0
  543. package/router/dist/sandbox/script-sandbox.js +303 -0
  544. package/router/dist/setup/script-transform-adapters.d.ts +28 -0
  545. package/router/dist/setup/script-transform-adapters.js +259 -0
  546. package/router/dist/tools/batch.d.ts +22 -0
  547. package/router/dist/tools/batch.js +509 -0
  548. package/router/dist/tools/run.d.ts +50 -0
  549. package/router/dist/tools/run.js +1219 -0
  550. package/router/dist/tools/search.d.ts +44 -0
  551. package/{plugins/freeflow/router/dist/retrieve.js → router/dist/tools/search.js} +395 -45
  552. package/router/dist/transform/engine.d.ts +143 -0
  553. package/router/dist/transform/engine.js +1955 -0
  554. package/router/dist/vault/vault-index.d.ts +106 -0
  555. package/router/dist/vault/vault-index.js +411 -0
  556. package/{plugins/freeflow/router/dist → router/dist/vault}/vault.d.ts +24 -1
  557. package/{plugins/freeflow/router/dist → router/dist/vault}/vault.js +152 -1
  558. package/skills/design-for-depth/SKILL.md +90 -0
  559. package/skills/design-for-depth/references/design-pressure-signals.md +265 -0
  560. package/skills/design-for-depth/references/software-design-philosophy.md +219 -0
  561. package/{plugins/freeflow/skills → skills}/diagnose-failure/SKILL.md +6 -1
  562. package/{plugins/freeflow/skills/research → skills/discover}/ARTIFACT-DESTINATIONS.md +4 -4
  563. package/{plugins/freeflow/skills/research → skills/discover}/CHECKPOINTS.md +4 -4
  564. package/skills/discover/SKILL.md +173 -0
  565. package/{plugins/freeflow/skills → skills}/execute-plan/SKILL.md +5 -4
  566. package/{plugins/freeflow/skills → skills}/execute-plan/references/execution-map.md +2 -2
  567. package/{plugins/freeflow/skills → skills}/mode-contract/SKILL.md +9 -4
  568. package/skills/output-router/SKILL.md +202 -0
  569. package/skills/output-router/references/safety-policy.md +40 -0
  570. package/{plugins/freeflow/skills → skills}/review-artifact/SKILL.md +5 -2
  571. package/{plugins/freeflow/skills → skills}/review-artifact/references/reviewer-prompt.md +2 -1
  572. package/{plugins/freeflow/skills → skills}/review-work/SKILL.md +6 -1
  573. package/{plugins/freeflow/skills → skills}/setup-freeflow/SKILL.md +21 -9
  574. package/{plugins/freeflow/skills → skills}/setup-freeflow/references/activation-contract.md +11 -10
  575. package/{plugins/freeflow/skills → skills}/setup-freeflow/references/host-setup.md +3 -3
  576. package/skills/setup-freeflow/references/output-router-setup.md +102 -0
  577. package/{plugins/freeflow/skills → skills}/verify-work/SKILL.md +3 -1
  578. package/{plugins/freeflow/skills → skills}/workflow/SKILL.md +16 -14
  579. package/{plugins/freeflow/skills → skills}/workflow/references/workflow-map.md +16 -14
  580. package/{plugins/freeflow/skills → skills}/write-plan/SKILL.md +9 -1
  581. package/{plugins/freeflow/skills → skills}/write-spec/SKILL.md +9 -6
  582. package/plugins/freeflow/docs/adr/0002-evals-before-hooks.md +0 -17
  583. package/plugins/freeflow/docs/adr/0004-research-replaces-shallow-discovery-skills.md +0 -26
  584. package/plugins/freeflow/docs/adr/README.md +0 -8
  585. package/plugins/freeflow/docs/architecture.md +0 -86
  586. package/plugins/freeflow/docs/output-router.md +0 -212
  587. package/plugins/freeflow/docs/release-evidence.md +0 -69
  588. package/plugins/freeflow/pi-extension/index.js +0 -1176
  589. package/plugins/freeflow/router/dist/config.d.ts +0 -22
  590. package/plugins/freeflow/router/dist/config.js +0 -114
  591. package/plugins/freeflow/router/dist/experimental-local-index.d.ts +0 -1
  592. package/plugins/freeflow/router/dist/experimental-local-index.js +0 -1
  593. package/plugins/freeflow/router/dist/index.d.ts +0 -12
  594. package/plugins/freeflow/router/dist/index.js +0 -12
  595. package/plugins/freeflow/router/dist/retrieve.d.ts +0 -33
  596. package/plugins/freeflow/router/dist/run.d.ts +0 -26
  597. package/plugins/freeflow/router/dist/run.js +0 -356
  598. package/plugins/freeflow/router/dist/types.d.ts +0 -234
  599. package/plugins/freeflow/router/dist/types.js +0 -9
  600. package/plugins/freeflow/skills/output-router/SKILL.md +0 -69
  601. package/plugins/freeflow/skills/output-router/references/safety-policy.md +0 -33
  602. package/plugins/freeflow/skills/research/LANGUAGE.md +0 -61
  603. package/plugins/freeflow/skills/research/SKILL.md +0 -128
  604. package/plugins/freeflow/skills/setup-freeflow/references/output-router-setup.md +0 -52
  605. /package/{plugins/freeflow/assets → assets}/freeflow-plugin-icon-transparent.png +0 -0
  606. /package/{plugins/freeflow/hooks → hooks}/hooks.json +0 -0
  607. /package/{plugins/freeflow/docs → plugin-docs}/adr/0001-three-modes.md +0 -0
  608. /package/{plugins/freeflow/router/dist → router/dist/benchmarks}/benchmark-harness.d.ts +0 -0
  609. /package/{plugins/freeflow/router/dist → router/dist/benchmarks}/benchmarks.d.ts +0 -0
  610. /package/{plugins/freeflow/router/dist → router/dist/benchmarks}/codex-qa-benchmarks.d.ts +0 -0
  611. /package/{plugins/freeflow/router/dist → router/dist/config}/router-contract.d.ts +0 -0
  612. /package/{plugins/freeflow/router/dist → router/dist/config}/router-contract.js +0 -0
  613. /package/{plugins/freeflow/router/dist → router/dist/config}/schema.d.ts +0 -0
  614. /package/{plugins/freeflow/router/dist → router/dist/evidence}/bounded-evidence.js +0 -0
  615. /package/{plugins/freeflow/router/dist → router/dist/evidence}/evidence-range-selector.d.ts +0 -0
  616. /package/{plugins/freeflow/router/dist → router/dist/evidence}/evidence-search.d.ts +0 -0
  617. /package/{plugins/freeflow/router/dist → router/dist/evidence}/evidence.js +0 -0
  618. /package/{plugins/freeflow/router/dist → router/dist/evidence}/line-ranges.d.ts +0 -0
  619. /package/{plugins/freeflow/router/dist → router/dist/evidence}/line-ranges.js +0 -0
  620. /package/{plugins/freeflow/router → router}/dist/experiments/local-index.d.ts +0 -0
  621. /package/{plugins/freeflow/router → router}/dist/experiments/local-index.js +0 -0
  622. /package/{plugins/freeflow/router/dist → router/dist/repo}/repo-traversal.d.ts +0 -0
  623. /package/{plugins/freeflow/router/dist → router/dist/repo}/repo-traversal.js +0 -0
  624. /package/{plugins/freeflow/skills → skills}/bypass/SKILL.md +0 -0
  625. /package/{plugins/freeflow/skills → skills}/commit-work/SKILL.md +0 -0
  626. /package/{plugins/freeflow/skills → skills}/commit-work/references/staging-decisions.md +0 -0
  627. /package/{plugins/freeflow/skills → skills}/diagnose-failure/references/feedback-loop-catalog.md +0 -0
  628. /package/{plugins/freeflow/skills → skills}/diagnose-failure/references/flaky-and-performance.md +0 -0
  629. /package/{plugins/freeflow/skills → skills}/evaluate-skill/SKILL.md +0 -0
  630. /package/{plugins/freeflow/skills → skills}/evaluate-skill/references/eval-patterns.md +0 -0
  631. /package/{plugins/freeflow/skills → skills}/evaluate-skill/references/grading-priority.md +0 -0
  632. /package/{plugins/freeflow/skills → skills}/handoff/SKILL.md +0 -0
  633. /package/{plugins/freeflow/skills → skills}/handoff/references/templates.md +0 -0
  634. /package/{plugins/freeflow/skills → skills}/interview-gate/SKILL.md +0 -0
  635. /package/{plugins/freeflow/skills → skills}/review-work/references/reviewer-prompt.md +0 -0
  636. /package/{plugins/freeflow/skills → skills}/write-plan/references/plan-shapes.md +0 -0
  637. /package/{plugins/freeflow/skills → skills}/write-skill/SKILL.md +0 -0
  638. /package/{plugins/freeflow/skills → skills}/write-spec/references/artifact-standards.md +0 -0
  639. /package/{plugins/freeflow/skills → skills}/write-spec/references/spec-shapes.md +0 -0
@@ -0,0 +1,124 @@
1
+ export declare const CONTEXT_MODE_REAL_DEEP_IMPLEMENTATION = "context-mode-real-deep-benchmark-v1";
2
+ export declare const EXPECTED_BASELINE_FAILURE_KEYS: readonly ["outside-file-boundary/freeflow:run-cat-host-shell"];
3
+ export interface RunContextModeRealDeepBenchmarkOptions {
4
+ contextModeRepo?: string;
5
+ contextModeServer?: string;
6
+ fixtureSource?: string;
7
+ freeflowRepo?: string;
8
+ generatedAt?: string;
9
+ keepArtifacts?: boolean;
10
+ }
11
+ export interface ContextModeAvailability {
12
+ status: "available" | "unavailable";
13
+ repo: string;
14
+ server: string;
15
+ fixtureSource: string;
16
+ clientModulePath: string;
17
+ transportModulePath: string;
18
+ missingPaths: string[];
19
+ reason?: string;
20
+ }
21
+ export interface ContextModeRealDeepReport {
22
+ generatedAt: string;
23
+ implementation: string;
24
+ benchmarkLabel: string;
25
+ contextMode: ContextModeReportMetadata;
26
+ freeflow: FreeflowReportMetadata;
27
+ benchmarkRoot: string;
28
+ publicClaimsAllowed: boolean;
29
+ methodology: string[];
30
+ summaries: BenchmarkModeSummary[];
31
+ baselineChecks: BaselineChecks;
32
+ failureClusters: FailureClusters;
33
+ rows: DeepBenchmarkRow[];
34
+ contextModeStatsPreview: string;
35
+ notes: string[];
36
+ }
37
+ export interface ContextModeReportMetadata {
38
+ status: "available" | "unavailable";
39
+ repo: string;
40
+ server: string;
41
+ fixtureSource: string;
42
+ commit: string;
43
+ version: string;
44
+ storeRoot?: string;
45
+ unavailableReason?: string;
46
+ missingPaths: string[];
47
+ }
48
+ export interface FreeflowReportMetadata {
49
+ repo: string;
50
+ commit: string;
51
+ vaultRoot?: string;
52
+ sessionId?: string;
53
+ }
54
+ export interface BenchmarkModeSummary {
55
+ mode: string;
56
+ scenarios: number;
57
+ correct: number;
58
+ totalFactsFound: number;
59
+ totalFacts: number;
60
+ totalRawBytes: number;
61
+ totalVisibleBytes: number;
62
+ avgLatencyMs: number;
63
+ exactRecovery: number;
64
+ metadataOnly: number;
65
+ weightedReductionPct: number;
66
+ }
67
+ export interface BaselineChecks {
68
+ expectedCurrentFailuresDetected: boolean;
69
+ expectedFailureKeys: string[];
70
+ detectedFailureKeys: string[];
71
+ missingExpectedFailureKeys: string[];
72
+ notes: string[];
73
+ }
74
+ export interface FailureClusters {
75
+ freeflowIncorrect: FailureClusterEntry[];
76
+ contextModeIncorrect: FailureClusterEntry[];
77
+ freeflowVerbose: VerboseClusterEntry[];
78
+ metadataOnly: MetadataOnlyClusterEntry[];
79
+ }
80
+ export interface FailureClusterEntry {
81
+ fixture: string;
82
+ mode: string;
83
+ category: string;
84
+ facts: string;
85
+ notes: string;
86
+ visibleBytes: number;
87
+ }
88
+ export interface VerboseClusterEntry {
89
+ fixture: string;
90
+ mode: string;
91
+ reductionPct: number;
92
+ visibleBytes: number;
93
+ rawBytes: number;
94
+ }
95
+ export interface MetadataOnlyClusterEntry {
96
+ fixture: string;
97
+ mode: string;
98
+ notes: string;
99
+ }
100
+ export interface DeepBenchmarkRow {
101
+ fixture: string;
102
+ category: string;
103
+ mode: string;
104
+ capability: string;
105
+ correct: boolean;
106
+ factsFound: number;
107
+ factsTotal: number;
108
+ rawBytes: number;
109
+ visibleBytes: number;
110
+ reductionPct: number;
111
+ latencyMs: number;
112
+ recovery: string;
113
+ notes: string;
114
+ preview: string;
115
+ }
116
+ export declare function runContextModeRealDeepBenchmark(options?: RunContextModeRealDeepBenchmarkOptions): Promise<ContextModeRealDeepReport>;
117
+ export declare function renderContextModeRealDeepBenchmarkReport(report: ContextModeRealDeepReport): string;
118
+ export declare function writeContextModeRealDeepBenchmarkReports(report: ContextModeRealDeepReport, markdownReportPath: string, options?: {
119
+ jsonReportPath?: string | false;
120
+ }): Promise<{
121
+ markdown: string;
122
+ json?: string;
123
+ }>;
124
+ export declare function baselineFailureClassesDetected(report: Pick<ContextModeRealDeepReport, "failureClusters">): boolean;