@pasko70/pibo 1.9.7 → 1.9.9

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 (705) hide show
  1. package/README.md +183 -183
  2. package/context/codex-base-prompt.md +148 -148
  3. package/context/compute-worker.md +23 -23
  4. package/context/pibo-compaction-prompt.md +100 -100
  5. package/context/pibo-native-tooling.md +18 -18
  6. package/context/pibo-system-prompt.md +77 -77
  7. package/docs/README.md +23 -23
  8. package/docs/ops/install-developer-host.md +112 -112
  9. package/docs/ops/install-user-host.md +96 -96
  10. package/docs/ops/upgrade-user-to-developer-host.md +69 -69
  11. package/docs/ops/vscode-extension-release.md +160 -160
  12. package/package.json +95 -95
  13. package/skills/builtin/graphify/SKILL.md +52 -52
  14. package/skills/builtin/pi-agent-harness/SKILL.md +319 -319
  15. package/skills/builtin/pi-agent-harness/agents/openai.yaml +4 -4
  16. package/skills/builtin/pibo-docker-system/SKILL.md +170 -170
  17. package/skills/builtin/pibo-spec-writing/SKILL.md +330 -330
  18. package/skills/builtin/prd/SKILL.md +143 -143
  19. package/skills/builtin/ralph-loop/SKILL.md +359 -359
  20. package/skills/builtin/ralph-prd-json/SKILL.md +123 -123
  21. package/skills/builtin/skill-creator/LICENSE.txt +201 -201
  22. package/skills/builtin/skill-creator/SKILL.md +513 -513
  23. package/skills/builtin/skill-creator/agents/analyzer.md +274 -274
  24. package/skills/builtin/skill-creator/agents/comparator.md +202 -202
  25. package/skills/builtin/skill-creator/agents/grader.md +223 -223
  26. package/skills/builtin/skill-creator/assets/eval_review.html +146 -146
  27. package/skills/builtin/skill-creator/eval-viewer/generate_review.py +471 -471
  28. package/skills/builtin/skill-creator/eval-viewer/viewer.html +1325 -1325
  29. package/skills/builtin/skill-creator/references/schemas.md +430 -430
  30. package/skills/builtin/skill-creator/scripts/aggregate_benchmark.py +401 -401
  31. package/skills/builtin/skill-creator/scripts/generate_report.py +326 -326
  32. package/skills/builtin/skill-creator/scripts/improve_description.py +247 -247
  33. package/skills/builtin/skill-creator/scripts/package_skill.py +136 -136
  34. package/skills/builtin/skill-creator/scripts/quick_validate.py +102 -102
  35. package/skills/builtin/skill-creator/scripts/run_eval.py +310 -310
  36. package/skills/builtin/skill-creator/scripts/run_loop.py +328 -328
  37. package/skills/builtin/skill-creator/scripts/utils.py +47 -47
  38. package/skills/builtin/web-annotations/SKILL.md +93 -93
  39. package/src/mcp/LICENSE.mcp-cli +21 -21
  40. package/dist/api/simple-agent-api.js +0 -136
  41. package/dist/app-context.js +0 -4
  42. package/dist/apps/chat/agent-profiles.js +0 -70
  43. package/dist/apps/chat/agent-store.js +0 -669
  44. package/dist/apps/chat/chat-api-routes.js +0 -325
  45. package/dist/apps/chat/chat-capability-routes.js +0 -90
  46. package/dist/apps/chat/chat-files.js +0 -178
  47. package/dist/apps/chat/chat-request-normalizers.js +0 -681
  48. package/dist/apps/chat/chat-settings-routes.js +0 -98
  49. package/dist/apps/chat/chat-trace-helpers.js +0 -139
  50. package/dist/apps/chat/chat-user-skill-routes.js +0 -178
  51. package/dist/apps/chat/cron-api.js +0 -213
  52. package/dist/apps/chat/data/chat-data-mappers.js +0 -82
  53. package/dist/apps/chat/data/event-command-service.js +0 -75
  54. package/dist/apps/chat/data/navigation-query-service.js +0 -11
  55. package/dist/apps/chat/data/project-service.js +0 -877
  56. package/dist/apps/chat/data/read-state-service.js +0 -42
  57. package/dist/apps/chat/data/room-service.js +0 -52
  58. package/dist/apps/chat/data/session-query-service.js +0 -126
  59. package/dist/apps/chat/data/timeline-query-service.js +0 -102
  60. package/dist/apps/chat/event-log.js +0 -1
  61. package/dist/apps/chat/model-catalog.js +0 -53
  62. package/dist/apps/chat/output-compactor.js +0 -126
  63. package/dist/apps/chat/output-event-policy.js +0 -17
  64. package/dist/apps/chat/project-workflow-human-actions.js +0 -347
  65. package/dist/apps/chat/project-workflow-sessions.js +0 -260
  66. package/dist/apps/chat/provider-auth-actions.js +0 -43
  67. package/dist/apps/chat/ralph-api.js +0 -156
  68. package/dist/apps/chat/read-model.js +0 -1
  69. package/dist/apps/chat/rooms.js +0 -1
  70. package/dist/apps/chat/session-metadata.js +0 -14
  71. package/dist/apps/chat/static-assets.js +0 -997
  72. package/dist/apps/chat/stream.js +0 -145
  73. package/dist/apps/chat/telemetry-retention-service.js +0 -69
  74. package/dist/apps/chat/trace-v2.js +0 -307
  75. package/dist/apps/chat/trace.js +0 -572
  76. package/dist/apps/chat/types/event-store.js +0 -1
  77. package/dist/apps/chat/types/read-model.js +0 -1
  78. package/dist/apps/chat/types/rooms.js +0 -36
  79. package/dist/apps/chat/web-app.js +0 -4605
  80. package/dist/apps/chat/workflow-catalog.js +0 -572
  81. package/dist/apps/chat/workflow-edge-compatibility.js +0 -51
  82. package/dist/apps/chat/workflow-json-schema-validation.js +0 -335
  83. package/dist/apps/chat/workflow-manual-trigger-runtime.js +0 -232
  84. package/dist/apps/chat/workflow-persistence-model.js +0 -140
  85. package/dist/apps/chat/workflow-persistence.js +0 -633
  86. package/dist/apps/chat/workflow-registered-ref-params.js +0 -130
  87. package/dist/apps/chat/workflow-registered-ref-pickers.js +0 -179
  88. package/dist/apps/chat/workflow-registered-ref-validation.js +0 -210
  89. package/dist/apps/chat/workflow-v2-security-validation.js +0 -93
  90. package/dist/apps/chat/workflow-validation-helpers.js +0 -114
  91. package/dist/apps/chat-ui/assets/apl-BxEMbctQ.js +0 -1
  92. package/dist/apps/chat-ui/assets/asciiarmor-eFjeGRuZ.js +0 -1
  93. package/dist/apps/chat-ui/assets/asn1-Cfx-0pt9.js +0 -1
  94. package/dist/apps/chat-ui/assets/asterisk-B5BHTsBr.js +0 -1
  95. package/dist/apps/chat-ui/assets/brainfuck-CAA2xofr.js +0 -1
  96. package/dist/apps/chat-ui/assets/clike-BoDCOLzN.js +0 -1
  97. package/dist/apps/chat-ui/assets/clojure-kVFSWX0o.js +0 -1
  98. package/dist/apps/chat-ui/assets/cmake-BUPAhezI.js +0 -1
  99. package/dist/apps/chat-ui/assets/cobol-BfgHZgup.js +0 -1
  100. package/dist/apps/chat-ui/assets/coffeescript-G1Pe_1AZ.js +0 -1
  101. package/dist/apps/chat-ui/assets/commonlisp-B3N0CjHn.js +0 -1
  102. package/dist/apps/chat-ui/assets/crystal-C15ndaGM.js +0 -1
  103. package/dist/apps/chat-ui/assets/css-BqOeyZOV.js +0 -1
  104. package/dist/apps/chat-ui/assets/cypher-KjIKv-wW.js +0 -1
  105. package/dist/apps/chat-ui/assets/d-BlT5AEC-.js +0 -1
  106. package/dist/apps/chat-ui/assets/diff-oF98tbqj.js +0 -1
  107. package/dist/apps/chat-ui/assets/dist--55mTWk3.js +0 -1
  108. package/dist/apps/chat-ui/assets/dist-BDiYR_k0.js +0 -2
  109. package/dist/apps/chat-ui/assets/dist-BYMYH5s9.js +0 -11
  110. package/dist/apps/chat-ui/assets/dist-BZ39rB1W.js +0 -1
  111. package/dist/apps/chat-ui/assets/dist-BsedZGJo.js +0 -1
  112. package/dist/apps/chat-ui/assets/dist-BtZRJHYc.js +0 -1
  113. package/dist/apps/chat-ui/assets/dist-C5YJOwhH.js +0 -1
  114. package/dist/apps/chat-ui/assets/dist-C5oXtFSP.js +0 -1
  115. package/dist/apps/chat-ui/assets/dist-CKM5j-iy.js +0 -1
  116. package/dist/apps/chat-ui/assets/dist-CTqkBO4D.js +0 -1
  117. package/dist/apps/chat-ui/assets/dist-CUp9us2q.js +0 -1
  118. package/dist/apps/chat-ui/assets/dist-CZ9T4Cly.js +0 -1
  119. package/dist/apps/chat-ui/assets/dist-Ca0Nv2Sb.js +0 -1
  120. package/dist/apps/chat-ui/assets/dist-D75qd42l.js +0 -1
  121. package/dist/apps/chat-ui/assets/dist-DALz2b8B.js +0 -1
  122. package/dist/apps/chat-ui/assets/dist-DSKQpPaz.js +0 -1
  123. package/dist/apps/chat-ui/assets/dist-Hmv_Gd0d.js +0 -6
  124. package/dist/apps/chat-ui/assets/dist-JsdMHbep.js +0 -23
  125. package/dist/apps/chat-ui/assets/dist-MvkOuMpO.js +0 -1
  126. package/dist/apps/chat-ui/assets/dist-SVPsM5Oi.js +0 -13
  127. package/dist/apps/chat-ui/assets/dist-WDi-12_5.js +0 -9
  128. package/dist/apps/chat-ui/assets/dist-Zqt9kNG9.js +0 -1
  129. package/dist/apps/chat-ui/assets/dist-tGfufz3b.js +0 -1
  130. package/dist/apps/chat-ui/assets/dockerfile-CUaqzcqp.js +0 -1
  131. package/dist/apps/chat-ui/assets/dtd-VCA9yr61.js +0 -1
  132. package/dist/apps/chat-ui/assets/dylan-O-V5Dw5W.js +0 -1
  133. package/dist/apps/chat-ui/assets/ebnf-SPmdBkvT.js +0 -1
  134. package/dist/apps/chat-ui/assets/ecl-ChfCttfI.js +0 -1
  135. package/dist/apps/chat-ui/assets/eiffel-cB9EbjeN.js +0 -1
  136. package/dist/apps/chat-ui/assets/elm-BTiVflBU.js +0 -1
  137. package/dist/apps/chat-ui/assets/erlang-egf0TXFm.js +0 -1
  138. package/dist/apps/chat-ui/assets/factor-C2tAxNob.js +0 -1
  139. package/dist/apps/chat-ui/assets/fcl-BiCjh1tj.js +0 -1
  140. package/dist/apps/chat-ui/assets/forth-C4kDGW6u.js +0 -1
  141. package/dist/apps/chat-ui/assets/fortran-DzkLaPnd.js +0 -1
  142. package/dist/apps/chat-ui/assets/gas-DMOxskQF.js +0 -1
  143. package/dist/apps/chat-ui/assets/gherkin-BPxBpp-k.js +0 -1
  144. package/dist/apps/chat-ui/assets/groovy-CkEnc0ZY.js +0 -1
  145. package/dist/apps/chat-ui/assets/haskell-Dadpo9-w.js +0 -1
  146. package/dist/apps/chat-ui/assets/haxe-CDNZL9MW.js +0 -1
  147. package/dist/apps/chat-ui/assets/http-jy9Zxxt3.js +0 -1
  148. package/dist/apps/chat-ui/assets/idl-CGSB6iiy.js +0 -1
  149. package/dist/apps/chat-ui/assets/index-BUlHJWKP.js +0 -173
  150. package/dist/apps/chat-ui/assets/index-C0x9nEcf.css +0 -1
  151. package/dist/apps/chat-ui/assets/javascript-DSlzRUd8.js +0 -1
  152. package/dist/apps/chat-ui/assets/julia-DTiF9v6R.js +0 -1
  153. package/dist/apps/chat-ui/assets/livescript-Ci8Xxna6.js +0 -1
  154. package/dist/apps/chat-ui/assets/lua-eVxIrt9t.js +0 -1
  155. package/dist/apps/chat-ui/assets/mathematica-Da3grj36.js +0 -1
  156. package/dist/apps/chat-ui/assets/mbox-BWBMSafM.js +0 -1
  157. package/dist/apps/chat-ui/assets/mirc-CtHu9S1B.js +0 -1
  158. package/dist/apps/chat-ui/assets/mllike-wTFlPWXS.js +0 -1
  159. package/dist/apps/chat-ui/assets/modelica-cKbQ0UXu.js +0 -1
  160. package/dist/apps/chat-ui/assets/mscgen-C5pXQCMK.js +0 -1
  161. package/dist/apps/chat-ui/assets/mumps-CKBHkOQq.js +0 -1
  162. package/dist/apps/chat-ui/assets/nginx-B00AiQel.js +0 -1
  163. package/dist/apps/chat-ui/assets/nsis-SMDwKltR.js +0 -1
  164. package/dist/apps/chat-ui/assets/ntriples-B_36EBV0.js +0 -1
  165. package/dist/apps/chat-ui/assets/octave-BXPjzAif.js +0 -1
  166. package/dist/apps/chat-ui/assets/oz-Dedpat1M.js +0 -1
  167. package/dist/apps/chat-ui/assets/pascal-CMcUg72K.js +0 -1
  168. package/dist/apps/chat-ui/assets/perl-DoVTbnzt.js +0 -1
  169. package/dist/apps/chat-ui/assets/pig-CULXT1YV.js +0 -1
  170. package/dist/apps/chat-ui/assets/powershell-Cv5Uhf6b.js +0 -1
  171. package/dist/apps/chat-ui/assets/properties-CQ1C2P-M.js +0 -1
  172. package/dist/apps/chat-ui/assets/protobuf-SRlvzrl6.js +0 -1
  173. package/dist/apps/chat-ui/assets/pug-Bo3wfL-f.js +0 -1
  174. package/dist/apps/chat-ui/assets/puppet-ClSqCGj6.js +0 -1
  175. package/dist/apps/chat-ui/assets/pwa-images/android/launchericon-144x144.png +0 -0
  176. package/dist/apps/chat-ui/assets/pwa-images/android/launchericon-192x192.png +0 -0
  177. package/dist/apps/chat-ui/assets/pwa-images/android/launchericon-48x48.png +0 -0
  178. package/dist/apps/chat-ui/assets/pwa-images/android/launchericon-512x512.png +0 -0
  179. package/dist/apps/chat-ui/assets/pwa-images/android/launchericon-72x72.png +0 -0
  180. package/dist/apps/chat-ui/assets/pwa-images/android/launchericon-96x96.png +0 -0
  181. package/dist/apps/chat-ui/assets/pwa-images/ios/100.png +0 -0
  182. package/dist/apps/chat-ui/assets/pwa-images/ios/1024.png +0 -0
  183. package/dist/apps/chat-ui/assets/pwa-images/ios/114.png +0 -0
  184. package/dist/apps/chat-ui/assets/pwa-images/ios/120.png +0 -0
  185. package/dist/apps/chat-ui/assets/pwa-images/ios/128.png +0 -0
  186. package/dist/apps/chat-ui/assets/pwa-images/ios/144.png +0 -0
  187. package/dist/apps/chat-ui/assets/pwa-images/ios/152.png +0 -0
  188. package/dist/apps/chat-ui/assets/pwa-images/ios/16.png +0 -0
  189. package/dist/apps/chat-ui/assets/pwa-images/ios/167.png +0 -0
  190. package/dist/apps/chat-ui/assets/pwa-images/ios/180.png +0 -0
  191. package/dist/apps/chat-ui/assets/pwa-images/ios/192.png +0 -0
  192. package/dist/apps/chat-ui/assets/pwa-images/ios/20.png +0 -0
  193. package/dist/apps/chat-ui/assets/pwa-images/ios/256.png +0 -0
  194. package/dist/apps/chat-ui/assets/pwa-images/ios/29.png +0 -0
  195. package/dist/apps/chat-ui/assets/pwa-images/ios/32.png +0 -0
  196. package/dist/apps/chat-ui/assets/pwa-images/ios/40.png +0 -0
  197. package/dist/apps/chat-ui/assets/pwa-images/ios/50.png +0 -0
  198. package/dist/apps/chat-ui/assets/pwa-images/ios/512.png +0 -0
  199. package/dist/apps/chat-ui/assets/pwa-images/ios/57.png +0 -0
  200. package/dist/apps/chat-ui/assets/pwa-images/ios/58.png +0 -0
  201. package/dist/apps/chat-ui/assets/pwa-images/ios/60.png +0 -0
  202. package/dist/apps/chat-ui/assets/pwa-images/ios/64.png +0 -0
  203. package/dist/apps/chat-ui/assets/pwa-images/ios/72.png +0 -0
  204. package/dist/apps/chat-ui/assets/pwa-images/ios/76.png +0 -0
  205. package/dist/apps/chat-ui/assets/pwa-images/ios/80.png +0 -0
  206. package/dist/apps/chat-ui/assets/pwa-images/ios/87.png +0 -0
  207. package/dist/apps/chat-ui/assets/pwa-images/windows/LargeTile.scale-100.png +0 -0
  208. package/dist/apps/chat-ui/assets/pwa-images/windows/LargeTile.scale-125.png +0 -0
  209. package/dist/apps/chat-ui/assets/pwa-images/windows/LargeTile.scale-150.png +0 -0
  210. package/dist/apps/chat-ui/assets/pwa-images/windows/LargeTile.scale-200.png +0 -0
  211. package/dist/apps/chat-ui/assets/pwa-images/windows/LargeTile.scale-400.png +0 -0
  212. package/dist/apps/chat-ui/assets/pwa-images/windows/SmallTile.scale-100.png +0 -0
  213. package/dist/apps/chat-ui/assets/pwa-images/windows/SmallTile.scale-125.png +0 -0
  214. package/dist/apps/chat-ui/assets/pwa-images/windows/SmallTile.scale-150.png +0 -0
  215. package/dist/apps/chat-ui/assets/pwa-images/windows/SmallTile.scale-200.png +0 -0
  216. package/dist/apps/chat-ui/assets/pwa-images/windows/SmallTile.scale-400.png +0 -0
  217. package/dist/apps/chat-ui/assets/pwa-images/windows/SplashScreen.scale-100.png +0 -0
  218. package/dist/apps/chat-ui/assets/pwa-images/windows/SplashScreen.scale-125.png +0 -0
  219. package/dist/apps/chat-ui/assets/pwa-images/windows/SplashScreen.scale-150.png +0 -0
  220. package/dist/apps/chat-ui/assets/pwa-images/windows/SplashScreen.scale-200.png +0 -0
  221. package/dist/apps/chat-ui/assets/pwa-images/windows/SplashScreen.scale-400.png +0 -0
  222. package/dist/apps/chat-ui/assets/pwa-images/windows/Square150x150Logo.scale-100.png +0 -0
  223. package/dist/apps/chat-ui/assets/pwa-images/windows/Square150x150Logo.scale-125.png +0 -0
  224. package/dist/apps/chat-ui/assets/pwa-images/windows/Square150x150Logo.scale-150.png +0 -0
  225. package/dist/apps/chat-ui/assets/pwa-images/windows/Square150x150Logo.scale-200.png +0 -0
  226. package/dist/apps/chat-ui/assets/pwa-images/windows/Square150x150Logo.scale-400.png +0 -0
  227. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.altform-lightunplated_targetsize-16.png +0 -0
  228. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.altform-lightunplated_targetsize-20.png +0 -0
  229. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.altform-lightunplated_targetsize-24.png +0 -0
  230. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.altform-lightunplated_targetsize-256.png +0 -0
  231. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.altform-lightunplated_targetsize-30.png +0 -0
  232. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.altform-lightunplated_targetsize-32.png +0 -0
  233. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.altform-lightunplated_targetsize-36.png +0 -0
  234. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.altform-lightunplated_targetsize-40.png +0 -0
  235. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.altform-lightunplated_targetsize-44.png +0 -0
  236. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.altform-lightunplated_targetsize-48.png +0 -0
  237. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.altform-lightunplated_targetsize-60.png +0 -0
  238. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.altform-lightunplated_targetsize-64.png +0 -0
  239. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.altform-lightunplated_targetsize-72.png +0 -0
  240. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.altform-lightunplated_targetsize-80.png +0 -0
  241. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.altform-lightunplated_targetsize-96.png +0 -0
  242. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.altform-unplated_targetsize-16.png +0 -0
  243. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.altform-unplated_targetsize-20.png +0 -0
  244. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.altform-unplated_targetsize-24.png +0 -0
  245. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.altform-unplated_targetsize-256.png +0 -0
  246. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.altform-unplated_targetsize-30.png +0 -0
  247. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.altform-unplated_targetsize-32.png +0 -0
  248. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.altform-unplated_targetsize-36.png +0 -0
  249. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.altform-unplated_targetsize-40.png +0 -0
  250. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.altform-unplated_targetsize-44.png +0 -0
  251. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.altform-unplated_targetsize-48.png +0 -0
  252. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.altform-unplated_targetsize-60.png +0 -0
  253. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.altform-unplated_targetsize-64.png +0 -0
  254. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.altform-unplated_targetsize-72.png +0 -0
  255. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.altform-unplated_targetsize-80.png +0 -0
  256. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.altform-unplated_targetsize-96.png +0 -0
  257. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.scale-100.png +0 -0
  258. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.scale-125.png +0 -0
  259. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.scale-150.png +0 -0
  260. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.scale-200.png +0 -0
  261. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.scale-400.png +0 -0
  262. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.targetsize-16.png +0 -0
  263. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.targetsize-20.png +0 -0
  264. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.targetsize-24.png +0 -0
  265. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.targetsize-256.png +0 -0
  266. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.targetsize-30.png +0 -0
  267. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.targetsize-32.png +0 -0
  268. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.targetsize-36.png +0 -0
  269. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.targetsize-40.png +0 -0
  270. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.targetsize-44.png +0 -0
  271. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.targetsize-48.png +0 -0
  272. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.targetsize-60.png +0 -0
  273. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.targetsize-64.png +0 -0
  274. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.targetsize-72.png +0 -0
  275. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.targetsize-80.png +0 -0
  276. package/dist/apps/chat-ui/assets/pwa-images/windows/Square44x44Logo.targetsize-96.png +0 -0
  277. package/dist/apps/chat-ui/assets/pwa-images/windows/StoreLogo.scale-100.png +0 -0
  278. package/dist/apps/chat-ui/assets/pwa-images/windows/StoreLogo.scale-125.png +0 -0
  279. package/dist/apps/chat-ui/assets/pwa-images/windows/StoreLogo.scale-150.png +0 -0
  280. package/dist/apps/chat-ui/assets/pwa-images/windows/StoreLogo.scale-200.png +0 -0
  281. package/dist/apps/chat-ui/assets/pwa-images/windows/StoreLogo.scale-400.png +0 -0
  282. package/dist/apps/chat-ui/assets/pwa-images/windows/Wide310x150Logo.scale-100.png +0 -0
  283. package/dist/apps/chat-ui/assets/pwa-images/windows/Wide310x150Logo.scale-125.png +0 -0
  284. package/dist/apps/chat-ui/assets/pwa-images/windows/Wide310x150Logo.scale-150.png +0 -0
  285. package/dist/apps/chat-ui/assets/pwa-images/windows/Wide310x150Logo.scale-200.png +0 -0
  286. package/dist/apps/chat-ui/assets/pwa-images/windows/Wide310x150Logo.scale-400.png +0 -0
  287. package/dist/apps/chat-ui/assets/python-C2_X1GpX.js +0 -1
  288. package/dist/apps/chat-ui/assets/q-B_6Gdyzl.js +0 -1
  289. package/dist/apps/chat-ui/assets/r-BD07NGED.js +0 -1
  290. package/dist/apps/chat-ui/assets/rolldown-runtime-S-ySWqyJ.js +0 -1
  291. package/dist/apps/chat-ui/assets/rpm-CRu5Z2Jl.js +0 -1
  292. package/dist/apps/chat-ui/assets/ruby-dZPnOz8h.js +0 -1
  293. package/dist/apps/chat-ui/assets/sas-S2t8_sDI.js +0 -1
  294. package/dist/apps/chat-ui/assets/scheme-WcyFWLW2.js +0 -1
  295. package/dist/apps/chat-ui/assets/shell-DUelnYSh.js +0 -1
  296. package/dist/apps/chat-ui/assets/sieve-jDjlVhNh.js +0 -1
  297. package/dist/apps/chat-ui/assets/simple-mode-CL04yRVp.js +0 -1
  298. package/dist/apps/chat-ui/assets/smalltalk-ddWDYy10.js +0 -1
  299. package/dist/apps/chat-ui/assets/solr-C7rQhLuW.js +0 -1
  300. package/dist/apps/chat-ui/assets/sparql--fPCCgVd.js +0 -1
  301. package/dist/apps/chat-ui/assets/spreadsheet-DjthqD5G.js +0 -1
  302. package/dist/apps/chat-ui/assets/sql-D_dieYbr.js +0 -1
  303. package/dist/apps/chat-ui/assets/stex-rHcFYcA0.js +0 -1
  304. package/dist/apps/chat-ui/assets/stylus-DxF70RNr.js +0 -1
  305. package/dist/apps/chat-ui/assets/swift-T0hDoOb-.js +0 -1
  306. package/dist/apps/chat-ui/assets/tcl-Dlzy1mPk.js +0 -1
  307. package/dist/apps/chat-ui/assets/textile-Dy5rFZe5.js +0 -1
  308. package/dist/apps/chat-ui/assets/tiddlywiki-DQP1OymS.js +0 -1
  309. package/dist/apps/chat-ui/assets/tiki-0vOj3DB2.js +0 -1
  310. package/dist/apps/chat-ui/assets/toml-DEltN0lI.js +0 -1
  311. package/dist/apps/chat-ui/assets/troff-CRbBpEqY.js +0 -1
  312. package/dist/apps/chat-ui/assets/ttcn-M5q1nLKg.js +0 -1
  313. package/dist/apps/chat-ui/assets/ttcn-cfg-Rmw9NWq9.js +0 -1
  314. package/dist/apps/chat-ui/assets/turtle-BCDWhJK0.js +0 -1
  315. package/dist/apps/chat-ui/assets/vb-QQ7LGlOz.js +0 -1
  316. package/dist/apps/chat-ui/assets/vbscript-BiSEdUzz.js +0 -1
  317. package/dist/apps/chat-ui/assets/velocity-CzMg5_6w.js +0 -1
  318. package/dist/apps/chat-ui/assets/verilog-BJOO83gk.js +0 -1
  319. package/dist/apps/chat-ui/assets/vhdl-ed4zAZAA.js +0 -1
  320. package/dist/apps/chat-ui/assets/webidl-Ddy6hbV6.js +0 -1
  321. package/dist/apps/chat-ui/assets/xquery-Bw1zwhh6.js +0 -1
  322. package/dist/apps/chat-ui/assets/yacas-DZdTXy3s.js +0 -1
  323. package/dist/apps/chat-ui/assets/z80-DMG02_YV.js +0 -1
  324. package/dist/apps/chat-ui/index.html +0 -20
  325. package/dist/apps/chat-ui/manifest.webmanifest +0 -25
  326. package/dist/apps/chat-ui/sw.js +0 -47
  327. package/dist/apps/chat-vscode-web/assets/index-B5QK07zO.css +0 -2
  328. package/dist/apps/chat-vscode-web/assets/index-BAMxIaI_.js +0 -41
  329. package/dist/apps/chat-vscode-web/index.html +0 -14
  330. package/dist/apps/cli-ui/InkSessionApp.js +0 -1218
  331. package/dist/apps/cli-ui/InkTerminalLine.js +0 -53
  332. package/dist/apps/cli-ui/InkTerminalRow.js +0 -304
  333. package/dist/apps/cli-ui/InkTerminalView.js +0 -25
  334. package/dist/apps/cli-ui/cliSessionsCommand.js +0 -232
  335. package/dist/apps/cli-ui/index.js +0 -8
  336. package/dist/apps/cli-ui/inkColors.js +0 -67
  337. package/dist/apps/cli-ui/inkJson.js +0 -244
  338. package/dist/apps/cli-ui/inkMarkdown.js +0 -127
  339. package/dist/apps/cli-ui/inkSyntaxHighlighter.js +0 -166
  340. package/dist/apps/context-files-ui/assets/apl-14BqhLYK.js +0 -1
  341. package/dist/apps/context-files-ui/assets/asciiarmor-WLvjqI7d.js +0 -1
  342. package/dist/apps/context-files-ui/assets/asn1-Bg4FbdCg.js +0 -1
  343. package/dist/apps/context-files-ui/assets/asterisk-B2MO-X4d.js +0 -1
  344. package/dist/apps/context-files-ui/assets/brainfuck-CV9kufud.js +0 -1
  345. package/dist/apps/context-files-ui/assets/clike-CjmcUpt6.js +0 -1
  346. package/dist/apps/context-files-ui/assets/clojure-De3QGfx6.js +0 -1
  347. package/dist/apps/context-files-ui/assets/cmake-i2VDNaRq.js +0 -1
  348. package/dist/apps/context-files-ui/assets/cobol-BwO6DF08.js +0 -1
  349. package/dist/apps/context-files-ui/assets/coffeescript-BtivDvRz.js +0 -1
  350. package/dist/apps/context-files-ui/assets/commonlisp-DFkEQdLP.js +0 -1
  351. package/dist/apps/context-files-ui/assets/crystal-CU0NkcVL.js +0 -1
  352. package/dist/apps/context-files-ui/assets/css-CbMZAQ1W.js +0 -1
  353. package/dist/apps/context-files-ui/assets/cypher-Dke5QOzv.js +0 -1
  354. package/dist/apps/context-files-ui/assets/d-TPqSVaHM.js +0 -1
  355. package/dist/apps/context-files-ui/assets/diff-B365LSoZ.js +0 -1
  356. package/dist/apps/context-files-ui/assets/dist-B5PTVnox.js +0 -1
  357. package/dist/apps/context-files-ui/assets/dist-B5ZAfwf5.js +0 -1
  358. package/dist/apps/context-files-ui/assets/dist-BOiGdrG-.js +0 -1
  359. package/dist/apps/context-files-ui/assets/dist-BkUONE3N.js +0 -1
  360. package/dist/apps/context-files-ui/assets/dist-D1KyNDg5.js +0 -13
  361. package/dist/apps/context-files-ui/assets/dist-DK01b7x4.js +0 -1
  362. package/dist/apps/context-files-ui/assets/dist-DKoyMSNr.js +0 -1
  363. package/dist/apps/context-files-ui/assets/dist-DLMjd26T.js +0 -1
  364. package/dist/apps/context-files-ui/assets/dist-DPG9jOQ-.js +0 -1
  365. package/dist/apps/context-files-ui/assets/dist-DotDq_kD.js +0 -1
  366. package/dist/apps/context-files-ui/assets/dist-Dp5AH00p.js +0 -1
  367. package/dist/apps/context-files-ui/assets/dist-DqYw0LH7.js +0 -2
  368. package/dist/apps/context-files-ui/assets/dist-QQuDy4KA.js +0 -1
  369. package/dist/apps/context-files-ui/assets/dist-TF5iO5ML.js +0 -9
  370. package/dist/apps/context-files-ui/assets/dist-TbjAhles.js +0 -1
  371. package/dist/apps/context-files-ui/assets/dist-ZsBbt0uY.js +0 -1
  372. package/dist/apps/context-files-ui/assets/dist-kmsvtHkH.js +0 -1
  373. package/dist/apps/context-files-ui/assets/dist-vnd7PMu3.js +0 -11
  374. package/dist/apps/context-files-ui/assets/dockerfile-CJb2sekW.js +0 -1
  375. package/dist/apps/context-files-ui/assets/dtd-CBMymJ7O.js +0 -1
  376. package/dist/apps/context-files-ui/assets/dylan-08Azy1NK.js +0 -1
  377. package/dist/apps/context-files-ui/assets/ebnf-Dkum_1J8.js +0 -1
  378. package/dist/apps/context-files-ui/assets/ecl-dhxjHL8y.js +0 -1
  379. package/dist/apps/context-files-ui/assets/eiffel-C446m6dI.js +0 -1
  380. package/dist/apps/context-files-ui/assets/elm-po1E9de0.js +0 -1
  381. package/dist/apps/context-files-ui/assets/erlang-BD5LkVkR.js +0 -1
  382. package/dist/apps/context-files-ui/assets/factor-B2EMQZkP.js +0 -1
  383. package/dist/apps/context-files-ui/assets/fcl-DkEOamHd.js +0 -1
  384. package/dist/apps/context-files-ui/assets/forth-dCg2_HVB.js +0 -1
  385. package/dist/apps/context-files-ui/assets/fortran-3ZpXLFh1.js +0 -1
  386. package/dist/apps/context-files-ui/assets/gas-DMmxLZRI.js +0 -1
  387. package/dist/apps/context-files-ui/assets/gherkin-DUSFg2R6.js +0 -1
  388. package/dist/apps/context-files-ui/assets/groovy-Cmduloe1.js +0 -1
  389. package/dist/apps/context-files-ui/assets/haskell-Cyr255R9.js +0 -1
  390. package/dist/apps/context-files-ui/assets/haxe-BJVKtprM.js +0 -1
  391. package/dist/apps/context-files-ui/assets/http-DszHFpc-.js +0 -1
  392. package/dist/apps/context-files-ui/assets/idl-Cati9Nrv.js +0 -1
  393. package/dist/apps/context-files-ui/assets/index-B92tL3Pp.css +0 -1
  394. package/dist/apps/context-files-ui/assets/index-BhAWD3dv.js +0 -202
  395. package/dist/apps/context-files-ui/assets/javascript-C5pDVaoP.js +0 -1
  396. package/dist/apps/context-files-ui/assets/julia-DlqY1cTU.js +0 -1
  397. package/dist/apps/context-files-ui/assets/livescript-C6p8-2W1.js +0 -1
  398. package/dist/apps/context-files-ui/assets/lua-BxuTHaF7.js +0 -1
  399. package/dist/apps/context-files-ui/assets/mathematica-nDHZUMJT.js +0 -1
  400. package/dist/apps/context-files-ui/assets/mbox-DAaR0Hcz.js +0 -1
  401. package/dist/apps/context-files-ui/assets/mirc-CCA0FRfl.js +0 -1
  402. package/dist/apps/context-files-ui/assets/mllike-Cw3Iccsb.js +0 -1
  403. package/dist/apps/context-files-ui/assets/modelica-Czx80fNR.js +0 -1
  404. package/dist/apps/context-files-ui/assets/mscgen-BmfuTbzG.js +0 -1
  405. package/dist/apps/context-files-ui/assets/mumps-Ds_ZaumL.js +0 -1
  406. package/dist/apps/context-files-ui/assets/nginx-D9M2PQ4U.js +0 -1
  407. package/dist/apps/context-files-ui/assets/nsis-DOo3SJmd.js +0 -1
  408. package/dist/apps/context-files-ui/assets/ntriples-DLHGTvHs.js +0 -1
  409. package/dist/apps/context-files-ui/assets/octave-8jj96JiC.js +0 -1
  410. package/dist/apps/context-files-ui/assets/oz-BmMq7iC4.js +0 -1
  411. package/dist/apps/context-files-ui/assets/pascal-BgMr6XpT.js +0 -1
  412. package/dist/apps/context-files-ui/assets/perl-D6YJObi_.js +0 -1
  413. package/dist/apps/context-files-ui/assets/pig-nx7uchs8.js +0 -1
  414. package/dist/apps/context-files-ui/assets/powershell-B4IPkVxR.js +0 -1
  415. package/dist/apps/context-files-ui/assets/properties-CoavQdLC.js +0 -1
  416. package/dist/apps/context-files-ui/assets/protobuf-D5EWhcmc.js +0 -1
  417. package/dist/apps/context-files-ui/assets/pug-QU72BPAa.js +0 -1
  418. package/dist/apps/context-files-ui/assets/puppet-B_0GFuyD.js +0 -1
  419. package/dist/apps/context-files-ui/assets/python-Cs7sNzy_.js +0 -1
  420. package/dist/apps/context-files-ui/assets/q-BIB9pPtI.js +0 -1
  421. package/dist/apps/context-files-ui/assets/r-CN5s4f3o.js +0 -1
  422. package/dist/apps/context-files-ui/assets/rpm-Ct_Ck8mQ.js +0 -1
  423. package/dist/apps/context-files-ui/assets/ruby-BVPradRk.js +0 -1
  424. package/dist/apps/context-files-ui/assets/sas-DN4j74IF.js +0 -1
  425. package/dist/apps/context-files-ui/assets/scheme-CvNgHAnh.js +0 -1
  426. package/dist/apps/context-files-ui/assets/shell-BjiMLAaM.js +0 -1
  427. package/dist/apps/context-files-ui/assets/sieve-C2U1O5Z4.js +0 -1
  428. package/dist/apps/context-files-ui/assets/simple-mode-DnMbQuKW.js +0 -1
  429. package/dist/apps/context-files-ui/assets/smalltalk-DkYwYufV.js +0 -1
  430. package/dist/apps/context-files-ui/assets/solr-BopnSD-v.js +0 -1
  431. package/dist/apps/context-files-ui/assets/sparql-Cpg3YQfd.js +0 -1
  432. package/dist/apps/context-files-ui/assets/spreadsheet-kRxtVt9J.js +0 -1
  433. package/dist/apps/context-files-ui/assets/sql-DYI2GwJR.js +0 -1
  434. package/dist/apps/context-files-ui/assets/stex-BCRT8IJ3.js +0 -1
  435. package/dist/apps/context-files-ui/assets/stylus-CARoeVE9.js +0 -1
  436. package/dist/apps/context-files-ui/assets/swift-DKNaLAK6.js +0 -1
  437. package/dist/apps/context-files-ui/assets/tcl-CQyXkgMH.js +0 -1
  438. package/dist/apps/context-files-ui/assets/textile-Yg_UWn-t.js +0 -1
  439. package/dist/apps/context-files-ui/assets/tiddlywiki-dqVbkfX4.js +0 -1
  440. package/dist/apps/context-files-ui/assets/tiki-CC_ic8g0.js +0 -1
  441. package/dist/apps/context-files-ui/assets/toml-B7gGzVkJ.js +0 -1
  442. package/dist/apps/context-files-ui/assets/troff-Bq3z6oAu.js +0 -1
  443. package/dist/apps/context-files-ui/assets/ttcn-GvRgs2AT.js +0 -1
  444. package/dist/apps/context-files-ui/assets/ttcn-cfg-CGCXz7Vo.js +0 -1
  445. package/dist/apps/context-files-ui/assets/turtle-CwIpz2yy.js +0 -1
  446. package/dist/apps/context-files-ui/assets/vb-BmcHUM2C.js +0 -1
  447. package/dist/apps/context-files-ui/assets/vbscript-Cs9dylre.js +0 -1
  448. package/dist/apps/context-files-ui/assets/velocity-CBWU0VCy.js +0 -1
  449. package/dist/apps/context-files-ui/assets/verilog-DVCHmufx.js +0 -1
  450. package/dist/apps/context-files-ui/assets/vhdl-BGDk4f1d.js +0 -1
  451. package/dist/apps/context-files-ui/assets/webidl-egXQEWlC.js +0 -1
  452. package/dist/apps/context-files-ui/assets/xquery-5f0hn7cg.js +0 -1
  453. package/dist/apps/context-files-ui/assets/yacas-DNs9XkmQ.js +0 -1
  454. package/dist/apps/context-files-ui/assets/z80-B7Dfb4UO.js +0 -1
  455. package/dist/apps/context-files-ui/index.html +0 -14
  456. package/dist/auth/better-auth.js +0 -130
  457. package/dist/auth/login-actions.js +0 -251
  458. package/dist/auth/openai-codex-usage.js +0 -147
  459. package/dist/auth/types.js +0 -14
  460. package/dist/bin/pibo.js +0 -3
  461. package/dist/bin/rg.js +0 -15
  462. package/dist/channels/types.js +0 -1
  463. package/dist/cli-errors.js +0 -18
  464. package/dist/cli-session/fakeSessionSource.js +0 -804
  465. package/dist/cli-session/index.js +0 -3
  466. package/dist/cli-session/localSessionSource.js +0 -1144
  467. package/dist/cli-session/sessionSource.js +0 -13
  468. package/dist/cli.js +0 -491
  469. package/dist/compute/cli.js +0 -415
  470. package/dist/compute/docker.js +0 -835
  471. package/dist/compute/resource-health.js +0 -334
  472. package/dist/compute/resource-policy.js +0 -98
  473. package/dist/config/config.js +0 -180
  474. package/dist/core/base-prompt.js +0 -104
  475. package/dist/core/codex-compat.js +0 -44
  476. package/dist/core/compaction-prompt.js +0 -293
  477. package/dist/core/context-build.js +0 -711
  478. package/dist/core/context-guard.js +0 -293
  479. package/dist/core/events.js +0 -1
  480. package/dist/core/gateway-resource-guard.js +0 -215
  481. package/dist/core/model-defaults.js +0 -95
  482. package/dist/core/pibo-home.js +0 -8
  483. package/dist/core/profiles.js +0 -210
  484. package/dist/core/provider-recovery.js +0 -64
  485. package/dist/core/provider-telemetry.js +0 -353
  486. package/dist/core/routed-session.js +0 -1179
  487. package/dist/core/runtime-telemetry.js +0 -1059
  488. package/dist/core/runtime.js +0 -529
  489. package/dist/core/session-errors.js +0 -76
  490. package/dist/core/session-model.js +0 -39
  491. package/dist/core/session-router.js +0 -850
  492. package/dist/core/skill-expansion.js +0 -43
  493. package/dist/core/system-prompt-template.js +0 -56
  494. package/dist/core/telemetry-retention-settings.js +0 -34
  495. package/dist/core/telemetry-staleness.js +0 -128
  496. package/dist/core/test-output-compaction.js +0 -145
  497. package/dist/core/thinking.js +0 -9
  498. package/dist/core/user-settings.js +0 -84
  499. package/dist/core/workspace.js +0 -5
  500. package/dist/core/wsl.js +0 -100
  501. package/dist/cron/channel.js +0 -28
  502. package/dist/cron/cli.js +0 -230
  503. package/dist/cron/plugin.js +0 -11
  504. package/dist/cron/schedule.js +0 -214
  505. package/dist/cron/service.js +0 -177
  506. package/dist/cron/store.js +0 -349
  507. package/dist/cron/types.js +0 -1
  508. package/dist/data/cli.js +0 -184
  509. package/dist/data/event-log.js +0 -106
  510. package/dist/data/ingest-service.js +0 -389
  511. package/dist/data/message-store.js +0 -62
  512. package/dist/data/navigation-store.js +0 -75
  513. package/dist/data/observation-store.js +0 -46
  514. package/dist/data/payload-store.js +0 -153
  515. package/dist/data/pibo-store.js +0 -59
  516. package/dist/data/schema.js +0 -436
  517. package/dist/data/session-store.js +0 -63
  518. package/dist/data/sqlite-schema.js +0 -12
  519. package/dist/data/telemetry-preview.js +0 -65
  520. package/dist/data/telemetry-queries.js +0 -212
  521. package/dist/data/telemetry-retention.js +0 -50
  522. package/dist/data/telemetry-rows.js +0 -158
  523. package/dist/data/telemetry-writer.js +0 -114
  524. package/dist/data/telemetry.js +0 -471
  525. package/dist/debug/delta-compaction.js +0 -99
  526. package/dist/debug/detail-format.js +0 -86
  527. package/dist/debug/events.js +0 -212
  528. package/dist/debug/failures.js +0 -162
  529. package/dist/debug/index.js +0 -1296
  530. package/dist/debug/messages.js +0 -185
  531. package/dist/debug/next-commands.js +0 -6
  532. package/dist/debug/payloads.js +0 -123
  533. package/dist/debug/pty.js +0 -924
  534. package/dist/debug/session.js +0 -230
  535. package/dist/debug/sql.js +0 -238
  536. package/dist/debug/stores.js +0 -54
  537. package/dist/debug/summary.js +0 -72
  538. package/dist/debug/telemetry.js +0 -649
  539. package/dist/debug/tools.js +0 -168
  540. package/dist/debug/trace-render-check.js +0 -151
  541. package/dist/debug/trace.js +0 -370
  542. package/dist/debug/web-artifacts.js +0 -63
  543. package/dist/debug/web-options.js +0 -313
  544. package/dist/debug/web-render-analysis.js +0 -310
  545. package/dist/debug/web-snapshot-browser-scripts.js +0 -303
  546. package/dist/debug/web-streaming-benchmark-analysis.js +0 -605
  547. package/dist/debug/web-streaming-browser-library.js +0 -928
  548. package/dist/debug/web-streaming-browser-scripts.js +0 -242
  549. package/dist/debug/web-streaming-provider-telemetry.js +0 -194
  550. package/dist/debug/web-streaming-report.js +0 -493
  551. package/dist/debug/web-streaming-types.js +0 -1
  552. package/dist/debug/web.js +0 -574
  553. package/dist/gateway/backup.js +0 -83
  554. package/dist/gateway/cli.js +0 -632
  555. package/dist/gateway/client.js +0 -200
  556. package/dist/gateway/fallback.js +0 -155
  557. package/dist/gateway/pidfile.js +0 -130
  558. package/dist/gateway/protocol.js +0 -62
  559. package/dist/gateway/request.js +0 -155
  560. package/dist/gateway/server.js +0 -397
  561. package/dist/gateway/tool.js +0 -72
  562. package/dist/gateway/web.js +0 -224
  563. package/dist/index.js +0 -25
  564. package/dist/local/client.js +0 -77
  565. package/dist/local/extension.js +0 -551
  566. package/dist/local/tui.js +0 -25
  567. package/dist/mcp/agent-context.js +0 -127
  568. package/dist/mcp/client.js +0 -332
  569. package/dist/mcp/commands/call.js +0 -146
  570. package/dist/mcp/commands/grep.js +0 -145
  571. package/dist/mcp/commands/info.js +0 -83
  572. package/dist/mcp/commands/list.js +0 -94
  573. package/dist/mcp/config-command.js +0 -217
  574. package/dist/mcp/config.js +0 -473
  575. package/dist/mcp/daemon-client.js +0 -266
  576. package/dist/mcp/daemon.js +0 -327
  577. package/dist/mcp/errors.js +0 -287
  578. package/dist/mcp/index.js +0 -431
  579. package/dist/mcp/output.js +0 -226
  580. package/dist/mcp/python-runtime.js +0 -131
  581. package/dist/mcp/registry.js +0 -116
  582. package/dist/mcp/version.js +0 -5
  583. package/dist/pi-packages/cli.js +0 -92
  584. package/dist/pi-packages/installer.js +0 -70
  585. package/dist/pi-packages/metadata.js +0 -231
  586. package/dist/pi-packages/runtime.js +0 -61
  587. package/dist/pi-packages/store.js +0 -175
  588. package/dist/pi-packages/types.js +0 -1
  589. package/dist/plugins/better-auth.js +0 -11
  590. package/dist/plugins/builtin.js +0 -478
  591. package/dist/plugins/chat-custom-agents.js +0 -20
  592. package/dist/plugins/chat-user-skills.js +0 -41
  593. package/dist/plugins/chat-vscode-web.js +0 -28
  594. package/dist/plugins/chat-web.js +0 -11
  595. package/dist/plugins/codex-compat.js +0 -33
  596. package/dist/plugins/context-files-store.js +0 -354
  597. package/dist/plugins/context-files.js +0 -1081
  598. package/dist/plugins/dev-auth.js +0 -202
  599. package/dist/plugins/native-tooling.js +0 -15
  600. package/dist/plugins/registry.js +0 -436
  601. package/dist/plugins/types.js +0 -1
  602. package/dist/plugins/web-annotations.js +0 -27
  603. package/dist/plugins/web.js +0 -11
  604. package/dist/providers/glm.js +0 -59
  605. package/dist/providers/minimax.js +0 -70
  606. package/dist/providers/openai-compat.js +0 -48
  607. package/dist/providers/openai-gpt56.js +0 -153
  608. package/dist/ralph/channel.js +0 -8
  609. package/dist/ralph/cli.js +0 -197
  610. package/dist/ralph/plugin.js +0 -14
  611. package/dist/ralph/service.js +0 -317
  612. package/dist/ralph/stopping.js +0 -151
  613. package/dist/ralph/store.js +0 -450
  614. package/dist/ralph/templates.js +0 -200
  615. package/dist/ralph/types.js +0 -1
  616. package/dist/reliability/store.js +0 -775
  617. package/dist/resources/cli.js +0 -135
  618. package/dist/resources/lifecycle.js +0 -353
  619. package/dist/resources/reaper-state.js +0 -94
  620. package/dist/resources/reaper.js +0 -145
  621. package/dist/runs/registry.js +0 -360
  622. package/dist/runs/tools.js +0 -185
  623. package/dist/session-ui/commandCatalog.js +0 -193
  624. package/dist/session-ui/commandResults.js +0 -95
  625. package/dist/session-ui/delegation.js +0 -89
  626. package/dist/session-ui/index.js +0 -8
  627. package/dist/session-ui/roomSessionViewModel.js +0 -69
  628. package/dist/session-ui/sessionActivity.js +0 -30
  629. package/dist/session-ui/statusViewModel.js +0 -127
  630. package/dist/session-ui/terminalCards.js +0 -210
  631. package/dist/session-ui/terminalRows.js +0 -1163
  632. package/dist/session-ui/terminalValue.js +0 -45
  633. package/dist/sessions/pibo-data-store.js +0 -178
  634. package/dist/sessions/sqlite-store.js +0 -220
  635. package/dist/sessions/store.js +0 -132
  636. package/dist/sessions/workflow-session-kind.js +0 -20
  637. package/dist/setup/cli.js +0 -619
  638. package/dist/shared/trace-async-agent-runs.js +0 -127
  639. package/dist/shared/trace-engine.js +0 -97
  640. package/dist/shared/trace-event-projection.js +0 -789
  641. package/dist/shared/trace-live-reducer.js +0 -191
  642. package/dist/shared/trace-nodes.js +0 -88
  643. package/dist/shared/trace-order.js +0 -84
  644. package/dist/shared/trace-page-merge.js +0 -40
  645. package/dist/shared/trace-patch-nodes.js +0 -83
  646. package/dist/shared/trace-run-notifications.js +0 -69
  647. package/dist/shared/trace-subagent-links.js +0 -46
  648. package/dist/shared/trace-transcript.js +0 -371
  649. package/dist/shared/trace-types.js +0 -1
  650. package/dist/signals/aggregate.js +0 -65
  651. package/dist/signals/events.js +0 -1
  652. package/dist/signals/projector.js +0 -205
  653. package/dist/signals/registry.js +0 -554
  654. package/dist/signals/store.js +0 -1
  655. package/dist/signals/types.js +0 -1
  656. package/dist/skills/cli.js +0 -151
  657. package/dist/subagents/tool.js +0 -63
  658. package/dist/tools/agent-browser-leases.js +0 -219
  659. package/dist/tools/agent-browser-wrapper.js +0 -99
  660. package/dist/tools/browser-pool.js +0 -623
  661. package/dist/tools/browser-use-cdp.js +0 -259
  662. package/dist/tools/browser-use-leases.js +0 -516
  663. package/dist/tools/browser-use-wrapper.js +0 -781
  664. package/dist/tools/cdp-client.js +0 -189
  665. package/dist/tools/codex-compat.js +0 -85
  666. package/dist/tools/codex-image-generation.js +0 -272
  667. package/dist/tools/desktop-env.js +0 -99
  668. package/dist/tools/guides.js +0 -563
  669. package/dist/tools/index.js +0 -1020
  670. package/dist/tools/linux-virtual-display.js +0 -58
  671. package/dist/tools/npm-runtime.js +0 -136
  672. package/dist/tools/python-runtime.js +0 -183
  673. package/dist/tools/registry.js +0 -237
  674. package/dist/tools/runtime/index.js +0 -3
  675. package/dist/tools/runtime/node-backend.js +0 -225
  676. package/dist/tools/runtime/node-worker-source.js +0 -206
  677. package/dist/tools/runtime/python-backend.js +0 -227
  678. package/dist/tools/runtime/python-worker-source.js +0 -178
  679. package/dist/tools/runtime/registry.js +0 -255
  680. package/dist/tools/runtime/tool.js +0 -168
  681. package/dist/tools/runtime/types.js +0 -1
  682. package/dist/tools/web-search.js +0 -138
  683. package/dist/user-skills/installer.js +0 -214
  684. package/dist/user-skills/manager.js +0 -133
  685. package/dist/user-skills/store.js +0 -267
  686. package/dist/user-skills/types.js +0 -1
  687. package/dist/vscode/cli.js +0 -90
  688. package/dist/vscode/code-cli.js +0 -119
  689. package/dist/vscode/install.js +0 -177
  690. package/dist/vscode/status.js +0 -80
  691. package/dist/vscode/types.js +0 -14
  692. package/dist/vscode/uninstall.js +0 -49
  693. package/dist/vscode/vsix-fetcher.js +0 -131
  694. package/dist/web/auth.js +0 -14
  695. package/dist/web/channel.js +0 -288
  696. package/dist/web/http.js +0 -195
  697. package/dist/web/types.js +0 -1
  698. package/dist/web-annotations/api.js +0 -348
  699. package/dist/web-annotations/attachments.js +0 -201
  700. package/dist/web-annotations/cdp.js +0 -1107
  701. package/dist/web-annotations/index.js +0 -7
  702. package/dist/web-annotations/store.js +0 -407
  703. package/dist/web-annotations/tools.js +0 -350
  704. package/dist/web-annotations/types.js +0 -34
  705. package/dist/web-annotations/validation.js +0 -288
@@ -1,1325 +1,1325 @@
1
- <!DOCTYPE html>
2
- <html lang="en">
3
- <head>
4
- <meta charset="UTF-8">
5
- <meta name="viewport" content="width=device-width, initial-scale=1.0">
6
- <title>Eval Review</title>
7
- <link rel="preconnect" href="https://fonts.googleapis.com">
8
- <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
9
- <link href="https://fonts.googleapis.com/css2?family=Poppins:wght@500;600&family=Lora:wght@400;500&display=swap" rel="stylesheet">
10
- <script src="https://cdn.sheetjs.com/xlsx-0.20.3/package/dist/xlsx.full.min.js" integrity="sha384-EnyY0/GSHQGSxSgMwaIPzSESbqoOLSexfnSMN2AP+39Ckmn92stwABZynq1JyzdT" crossorigin="anonymous"></script>
11
- <style>
12
- :root {
13
- --bg: #faf9f5;
14
- --surface: #ffffff;
15
- --border: #e8e6dc;
16
- --text: #141413;
17
- --text-muted: #b0aea5;
18
- --accent: #d97757;
19
- --accent-hover: #c4613f;
20
- --green: #788c5d;
21
- --green-bg: #eef2e8;
22
- --red: #c44;
23
- --red-bg: #fceaea;
24
- --header-bg: #141413;
25
- --header-text: #faf9f5;
26
- --radius: 6px;
27
- }
28
-
29
- * { box-sizing: border-box; margin: 0; padding: 0; }
30
-
31
- body {
32
- font-family: 'Lora', Georgia, serif;
33
- background: var(--bg);
34
- color: var(--text);
35
- height: 100vh;
36
- display: flex;
37
- flex-direction: column;
38
- }
39
-
40
- /* ---- Header ---- */
41
- .header {
42
- background: var(--header-bg);
43
- color: var(--header-text);
44
- padding: 1rem 2rem;
45
- display: flex;
46
- justify-content: space-between;
47
- align-items: center;
48
- flex-shrink: 0;
49
- }
50
- .header h1 {
51
- font-family: 'Poppins', sans-serif;
52
- font-size: 1.25rem;
53
- font-weight: 600;
54
- }
55
- .header .instructions {
56
- font-size: 0.8rem;
57
- opacity: 0.7;
58
- margin-top: 0.25rem;
59
- }
60
- .header .progress {
61
- font-size: 0.875rem;
62
- opacity: 0.8;
63
- text-align: right;
64
- }
65
-
66
- /* ---- Main content ---- */
67
- .main {
68
- flex: 1;
69
- overflow-y: auto;
70
- padding: 1.5rem 2rem;
71
- display: flex;
72
- flex-direction: column;
73
- gap: 1.25rem;
74
- }
75
-
76
- /* ---- Sections ---- */
77
- .section {
78
- background: var(--surface);
79
- border: 1px solid var(--border);
80
- border-radius: var(--radius);
81
- flex-shrink: 0;
82
- }
83
- .section-header {
84
- font-family: 'Poppins', sans-serif;
85
- padding: 0.75rem 1rem;
86
- font-size: 0.75rem;
87
- font-weight: 500;
88
- text-transform: uppercase;
89
- letter-spacing: 0.05em;
90
- color: var(--text-muted);
91
- border-bottom: 1px solid var(--border);
92
- background: var(--bg);
93
- }
94
- .section-body {
95
- padding: 1rem;
96
- }
97
-
98
- /* ---- Config badge ---- */
99
- .config-badge {
100
- display: inline-block;
101
- padding: 0.2rem 0.625rem;
102
- border-radius: 9999px;
103
- font-family: 'Poppins', sans-serif;
104
- font-size: 0.6875rem;
105
- font-weight: 600;
106
- text-transform: uppercase;
107
- letter-spacing: 0.03em;
108
- margin-left: 0.75rem;
109
- vertical-align: middle;
110
- }
111
- .config-badge.config-primary {
112
- background: rgba(33, 150, 243, 0.12);
113
- color: #1976d2;
114
- }
115
- .config-badge.config-baseline {
116
- background: rgba(255, 193, 7, 0.15);
117
- color: #f57f17;
118
- }
119
-
120
- /* ---- Prompt ---- */
121
- .prompt-text {
122
- white-space: pre-wrap;
123
- font-size: 0.9375rem;
124
- line-height: 1.6;
125
- }
126
-
127
- /* ---- Outputs ---- */
128
- .output-file {
129
- border: 1px solid var(--border);
130
- border-radius: var(--radius);
131
- overflow: hidden;
132
- }
133
- .output-file + .output-file {
134
- margin-top: 1rem;
135
- }
136
- .output-file-header {
137
- padding: 0.5rem 0.75rem;
138
- font-size: 0.8rem;
139
- font-weight: 600;
140
- color: var(--text-muted);
141
- background: var(--bg);
142
- border-bottom: 1px solid var(--border);
143
- font-family: 'SF Mono', SFMono-Regular, Consolas, 'Liberation Mono', Menlo, monospace;
144
- display: flex;
145
- justify-content: space-between;
146
- align-items: center;
147
- }
148
- .output-file-header .dl-btn {
149
- font-size: 0.7rem;
150
- color: var(--accent);
151
- text-decoration: none;
152
- cursor: pointer;
153
- font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', sans-serif;
154
- font-weight: 500;
155
- opacity: 0.8;
156
- }
157
- .output-file-header .dl-btn:hover {
158
- opacity: 1;
159
- text-decoration: underline;
160
- }
161
- .output-file-content {
162
- padding: 0.75rem;
163
- overflow-x: auto;
164
- }
165
- .output-file-content pre {
166
- font-size: 0.8125rem;
167
- line-height: 1.5;
168
- white-space: pre-wrap;
169
- word-break: break-word;
170
- font-family: 'SF Mono', SFMono-Regular, Consolas, 'Liberation Mono', Menlo, monospace;
171
- }
172
- .output-file-content img {
173
- max-width: 100%;
174
- height: auto;
175
- border-radius: 4px;
176
- }
177
- .output-file-content iframe {
178
- width: 100%;
179
- height: 600px;
180
- border: none;
181
- }
182
- .output-file-content table {
183
- border-collapse: collapse;
184
- font-size: 0.8125rem;
185
- width: 100%;
186
- }
187
- .output-file-content table td,
188
- .output-file-content table th {
189
- border: 1px solid var(--border);
190
- padding: 0.375rem 0.5rem;
191
- text-align: left;
192
- }
193
- .output-file-content table th {
194
- background: var(--bg);
195
- font-weight: 600;
196
- }
197
- .output-file-content .download-link {
198
- display: inline-flex;
199
- align-items: center;
200
- gap: 0.5rem;
201
- padding: 0.5rem 1rem;
202
- background: var(--bg);
203
- border: 1px solid var(--border);
204
- border-radius: 4px;
205
- color: var(--accent);
206
- text-decoration: none;
207
- font-size: 0.875rem;
208
- cursor: pointer;
209
- }
210
- .output-file-content .download-link:hover {
211
- background: var(--border);
212
- }
213
- .empty-state {
214
- color: var(--text-muted);
215
- font-style: italic;
216
- padding: 2rem;
217
- text-align: center;
218
- }
219
-
220
- /* ---- Feedback ---- */
221
- .prev-feedback {
222
- background: var(--bg);
223
- border: 1px solid var(--border);
224
- border-radius: 4px;
225
- padding: 0.625rem 0.75rem;
226
- margin-top: 0.75rem;
227
- font-size: 0.8125rem;
228
- color: var(--text-muted);
229
- line-height: 1.5;
230
- }
231
- .prev-feedback-label {
232
- font-size: 0.7rem;
233
- font-weight: 600;
234
- text-transform: uppercase;
235
- letter-spacing: 0.04em;
236
- margin-bottom: 0.25rem;
237
- color: var(--text-muted);
238
- }
239
- .feedback-textarea {
240
- width: 100%;
241
- min-height: 100px;
242
- padding: 0.75rem;
243
- border: 1px solid var(--border);
244
- border-radius: 4px;
245
- font-family: inherit;
246
- font-size: 0.9375rem;
247
- line-height: 1.5;
248
- resize: vertical;
249
- color: var(--text);
250
- }
251
- .feedback-textarea:focus {
252
- outline: none;
253
- border-color: var(--accent);
254
- box-shadow: 0 0 0 3px rgba(37, 99, 235, 0.1);
255
- }
256
- .feedback-status {
257
- font-size: 0.75rem;
258
- color: var(--text-muted);
259
- margin-top: 0.5rem;
260
- min-height: 1.1em;
261
- }
262
-
263
- /* ---- Grades (collapsible) ---- */
264
- .grades-toggle {
265
- display: flex;
266
- align-items: center;
267
- cursor: pointer;
268
- user-select: none;
269
- }
270
- .grades-toggle:hover {
271
- color: var(--accent);
272
- }
273
- .grades-toggle .arrow {
274
- margin-right: 0.5rem;
275
- transition: transform 0.15s;
276
- font-size: 0.75rem;
277
- }
278
- .grades-toggle .arrow.open {
279
- transform: rotate(90deg);
280
- }
281
- .grades-content {
282
- display: none;
283
- margin-top: 0.75rem;
284
- }
285
- .grades-content.open {
286
- display: block;
287
- }
288
- .grades-summary {
289
- font-size: 0.875rem;
290
- margin-bottom: 0.75rem;
291
- display: flex;
292
- align-items: center;
293
- gap: 0.5rem;
294
- }
295
- .grade-badge {
296
- display: inline-block;
297
- padding: 0.125rem 0.5rem;
298
- border-radius: 9999px;
299
- font-size: 0.75rem;
300
- font-weight: 600;
301
- }
302
- .grade-pass { background: var(--green-bg); color: var(--green); }
303
- .grade-fail { background: var(--red-bg); color: var(--red); }
304
- .assertion-list {
305
- list-style: none;
306
- }
307
- .assertion-item {
308
- padding: 0.625rem 0;
309
- border-bottom: 1px solid var(--border);
310
- font-size: 0.8125rem;
311
- }
312
- .assertion-item:last-child { border-bottom: none; }
313
- .assertion-status {
314
- font-weight: 600;
315
- margin-right: 0.5rem;
316
- }
317
- .assertion-status.pass { color: var(--green); }
318
- .assertion-status.fail { color: var(--red); }
319
- .assertion-evidence {
320
- color: var(--text-muted);
321
- font-size: 0.75rem;
322
- margin-top: 0.25rem;
323
- padding-left: 1.5rem;
324
- }
325
-
326
- /* ---- View tabs ---- */
327
- .view-tabs {
328
- display: flex;
329
- gap: 0;
330
- padding: 0 2rem;
331
- background: var(--bg);
332
- border-bottom: 1px solid var(--border);
333
- flex-shrink: 0;
334
- }
335
- .view-tab {
336
- font-family: 'Poppins', sans-serif;
337
- padding: 0.625rem 1.25rem;
338
- font-size: 0.8125rem;
339
- font-weight: 500;
340
- cursor: pointer;
341
- border: none;
342
- background: none;
343
- color: var(--text-muted);
344
- border-bottom: 2px solid transparent;
345
- transition: all 0.15s;
346
- }
347
- .view-tab:hover { color: var(--text); }
348
- .view-tab.active {
349
- color: var(--accent);
350
- border-bottom-color: var(--accent);
351
- }
352
- .view-panel { display: none; }
353
- .view-panel.active { display: flex; flex-direction: column; flex: 1; overflow: hidden; }
354
-
355
- /* ---- Benchmark view ---- */
356
- .benchmark-view {
357
- padding: 1.5rem 2rem;
358
- overflow-y: auto;
359
- flex: 1;
360
- }
361
- .benchmark-table {
362
- border-collapse: collapse;
363
- background: var(--surface);
364
- border: 1px solid var(--border);
365
- border-radius: var(--radius);
366
- font-size: 0.8125rem;
367
- width: 100%;
368
- margin-bottom: 1.5rem;
369
- }
370
- .benchmark-table th, .benchmark-table td {
371
- padding: 0.625rem 0.75rem;
372
- text-align: left;
373
- border: 1px solid var(--border);
374
- }
375
- .benchmark-table th {
376
- font-family: 'Poppins', sans-serif;
377
- background: var(--header-bg);
378
- color: var(--header-text);
379
- font-weight: 500;
380
- font-size: 0.75rem;
381
- text-transform: uppercase;
382
- letter-spacing: 0.04em;
383
- }
384
- .benchmark-table tr:hover { background: var(--bg); }
385
- .benchmark-table tr.benchmark-row-with { background: rgba(33, 150, 243, 0.06); }
386
- .benchmark-table tr.benchmark-row-without { background: rgba(255, 193, 7, 0.06); }
387
- .benchmark-table tr.benchmark-row-with:hover { background: rgba(33, 150, 243, 0.12); }
388
- .benchmark-table tr.benchmark-row-without:hover { background: rgba(255, 193, 7, 0.12); }
389
- .benchmark-table tr.benchmark-row-avg { font-weight: 600; border-top: 2px solid var(--border); }
390
- .benchmark-table tr.benchmark-row-avg.benchmark-row-with { background: rgba(33, 150, 243, 0.12); }
391
- .benchmark-table tr.benchmark-row-avg.benchmark-row-without { background: rgba(255, 193, 7, 0.12); }
392
- .benchmark-delta-positive { color: var(--green); font-weight: 600; }
393
- .benchmark-delta-negative { color: var(--red); font-weight: 600; }
394
- .benchmark-notes {
395
- background: var(--surface);
396
- border: 1px solid var(--border);
397
- border-radius: var(--radius);
398
- padding: 1rem;
399
- }
400
- .benchmark-notes h3 {
401
- font-family: 'Poppins', sans-serif;
402
- font-size: 0.875rem;
403
- margin-bottom: 0.75rem;
404
- }
405
- .benchmark-notes ul {
406
- list-style: disc;
407
- padding-left: 1.25rem;
408
- }
409
- .benchmark-notes li {
410
- font-size: 0.8125rem;
411
- line-height: 1.6;
412
- margin-bottom: 0.375rem;
413
- }
414
- .benchmark-empty {
415
- color: var(--text-muted);
416
- font-style: italic;
417
- text-align: center;
418
- padding: 3rem;
419
- }
420
-
421
- /* ---- Navigation ---- */
422
- .nav {
423
- display: flex;
424
- justify-content: space-between;
425
- align-items: center;
426
- padding: 1rem 2rem;
427
- border-top: 1px solid var(--border);
428
- background: var(--surface);
429
- flex-shrink: 0;
430
- }
431
- .nav-btn {
432
- font-family: 'Poppins', sans-serif;
433
- padding: 0.5rem 1.25rem;
434
- border: 1px solid var(--border);
435
- border-radius: var(--radius);
436
- background: var(--surface);
437
- cursor: pointer;
438
- font-size: 0.875rem;
439
- font-weight: 500;
440
- color: var(--text);
441
- transition: all 0.15s;
442
- }
443
- .nav-btn:hover:not(:disabled) {
444
- background: var(--bg);
445
- border-color: var(--text-muted);
446
- }
447
- .nav-btn:disabled {
448
- opacity: 0.4;
449
- cursor: not-allowed;
450
- }
451
- .done-btn {
452
- font-family: 'Poppins', sans-serif;
453
- padding: 0.5rem 1.5rem;
454
- border: 1px solid var(--border);
455
- border-radius: var(--radius);
456
- background: var(--surface);
457
- color: var(--text);
458
- cursor: pointer;
459
- font-size: 0.875rem;
460
- font-weight: 500;
461
- transition: all 0.15s;
462
- }
463
- .done-btn:hover {
464
- background: var(--bg);
465
- border-color: var(--text-muted);
466
- }
467
- .done-btn.ready {
468
- border: none;
469
- background: var(--accent);
470
- color: white;
471
- font-weight: 600;
472
- }
473
- .done-btn.ready:hover {
474
- background: var(--accent-hover);
475
- }
476
- /* ---- Done overlay ---- */
477
- .done-overlay {
478
- display: none;
479
- position: fixed;
480
- inset: 0;
481
- background: rgba(0, 0, 0, 0.5);
482
- z-index: 100;
483
- justify-content: center;
484
- align-items: center;
485
- }
486
- .done-overlay.visible {
487
- display: flex;
488
- }
489
- .done-card {
490
- background: var(--surface);
491
- border-radius: 12px;
492
- padding: 2rem 3rem;
493
- text-align: center;
494
- box-shadow: 0 20px 60px rgba(0, 0, 0, 0.3);
495
- max-width: 500px;
496
- }
497
- .done-card h2 {
498
- font-size: 1.5rem;
499
- margin-bottom: 0.5rem;
500
- }
501
- .done-card p {
502
- color: var(--text-muted);
503
- margin-bottom: 1.5rem;
504
- line-height: 1.5;
505
- }
506
- .done-card .btn-row {
507
- display: flex;
508
- gap: 0.5rem;
509
- justify-content: center;
510
- }
511
- .done-card button {
512
- padding: 0.5rem 1.25rem;
513
- border: 1px solid var(--border);
514
- border-radius: var(--radius);
515
- background: var(--surface);
516
- cursor: pointer;
517
- font-size: 0.875rem;
518
- }
519
- .done-card button:hover {
520
- background: var(--bg);
521
- }
522
- /* ---- Toast ---- */
523
- .toast {
524
- position: fixed;
525
- bottom: 5rem;
526
- left: 50%;
527
- transform: translateX(-50%);
528
- background: var(--header-bg);
529
- color: var(--header-text);
530
- padding: 0.625rem 1.25rem;
531
- border-radius: var(--radius);
532
- font-size: 0.875rem;
533
- opacity: 0;
534
- transition: opacity 0.3s;
535
- pointer-events: none;
536
- z-index: 200;
537
- }
538
- .toast.visible {
539
- opacity: 1;
540
- }
541
- </style>
542
- </head>
543
- <body>
544
- <div id="app" style="height:100vh; display:flex; flex-direction:column;">
545
- <div class="header">
546
- <div>
547
- <h1>Eval Review: <span id="skill-name"></span></h1>
548
- <div class="instructions">Review each output and leave feedback below. Navigate with arrow keys or buttons. When done, copy feedback and paste into Claude Code.</div>
549
- </div>
550
- <div class="progress" id="progress"></div>
551
- </div>
552
-
553
- <!-- View tabs (only shown when benchmark data exists) -->
554
- <div class="view-tabs" id="view-tabs" style="display:none;">
555
- <button class="view-tab active" onclick="switchView('outputs')">Outputs</button>
556
- <button class="view-tab" onclick="switchView('benchmark')">Benchmark</button>
557
- </div>
558
-
559
- <!-- Outputs panel (qualitative review) -->
560
- <div class="view-panel active" id="panel-outputs">
561
- <div class="main">
562
- <!-- Prompt -->
563
- <div class="section">
564
- <div class="section-header">Prompt <span class="config-badge" id="config-badge" style="display:none;"></span></div>
565
- <div class="section-body">
566
- <div class="prompt-text" id="prompt-text"></div>
567
- </div>
568
- </div>
569
-
570
- <!-- Outputs -->
571
- <div class="section">
572
- <div class="section-header">Output</div>
573
- <div class="section-body" id="outputs-body">
574
- <div class="empty-state">No output files found</div>
575
- </div>
576
- </div>
577
-
578
- <!-- Previous Output (collapsible) -->
579
- <div class="section" id="prev-outputs-section" style="display:none;">
580
- <div class="section-header">
581
- <div class="grades-toggle" onclick="togglePrevOutputs()">
582
- <span class="arrow" id="prev-outputs-arrow">&#9654;</span>
583
- Previous Output
584
- </div>
585
- </div>
586
- <div class="grades-content" id="prev-outputs-content"></div>
587
- </div>
588
-
589
- <!-- Grades (collapsible) -->
590
- <div class="section" id="grades-section" style="display:none;">
591
- <div class="section-header">
592
- <div class="grades-toggle" onclick="toggleGrades()">
593
- <span class="arrow" id="grades-arrow">&#9654;</span>
594
- Formal Grades
595
- </div>
596
- </div>
597
- <div class="grades-content" id="grades-content"></div>
598
- </div>
599
-
600
- <!-- Feedback -->
601
- <div class="section">
602
- <div class="section-header">Your Feedback</div>
603
- <div class="section-body">
604
- <textarea
605
- class="feedback-textarea"
606
- id="feedback"
607
- placeholder="What do you think of this output? Any issues, suggestions, or things that look great?"
608
- ></textarea>
609
- <div class="feedback-status" id="feedback-status"></div>
610
- <div class="prev-feedback" id="prev-feedback" style="display:none;">
611
- <div class="prev-feedback-label">Previous feedback</div>
612
- <div id="prev-feedback-text"></div>
613
- </div>
614
- </div>
615
- </div>
616
- </div>
617
-
618
- <div class="nav" id="outputs-nav">
619
- <button class="nav-btn" id="prev-btn" onclick="navigate(-1)">&#8592; Previous</button>
620
- <button class="done-btn" id="done-btn" onclick="showDoneDialog()">Submit All Reviews</button>
621
- <button class="nav-btn" id="next-btn" onclick="navigate(1)">Next &#8594;</button>
622
- </div>
623
- </div><!-- end panel-outputs -->
624
-
625
- <!-- Benchmark panel (quantitative stats) -->
626
- <div class="view-panel" id="panel-benchmark">
627
- <div class="benchmark-view" id="benchmark-content">
628
- <div class="benchmark-empty">No benchmark data available. Run a benchmark to see quantitative results here.</div>
629
- </div>
630
- </div>
631
- </div>
632
-
633
- <!-- Done overlay -->
634
- <div class="done-overlay" id="done-overlay">
635
- <div class="done-card">
636
- <h2>Review Complete</h2>
637
- <p>Your feedback has been saved. Go back to your Claude Code session and tell Claude you're done reviewing.</p>
638
- <div class="btn-row">
639
- <button onclick="closeDoneDialog()">OK</button>
640
- </div>
641
- </div>
642
- </div>
643
-
644
- <!-- Toast -->
645
- <div class="toast" id="toast"></div>
646
-
647
- <script>
648
- // ---- Embedded data (injected by generate_review.py) ----
649
- /*__EMBEDDED_DATA__*/
650
-
651
- // ---- State ----
652
- let feedbackMap = {}; // run_id -> feedback text
653
- let currentIndex = 0;
654
- let visitedRuns = new Set();
655
-
656
- // ---- Init ----
657
- async function init() {
658
- // Load saved feedback from server — but only if this isn't a fresh
659
- // iteration (indicated by previous_feedback being present). When
660
- // previous feedback exists, the feedback.json on disk is stale from
661
- // the prior iteration and should not pre-fill the textareas.
662
- const hasPrevious = Object.keys(EMBEDDED_DATA.previous_feedback || {}).length > 0
663
- || Object.keys(EMBEDDED_DATA.previous_outputs || {}).length > 0;
664
- if (!hasPrevious) {
665
- try {
666
- const resp = await fetch("/api/feedback");
667
- const data = await resp.json();
668
- if (data.reviews) {
669
- for (const r of data.reviews) feedbackMap[r.run_id] = r.feedback;
670
- }
671
- } catch { /* first run, no feedback yet */ }
672
- }
673
-
674
- document.getElementById("skill-name").textContent = EMBEDDED_DATA.skill_name;
675
- showRun(0);
676
-
677
- // Wire up feedback auto-save
678
- const textarea = document.getElementById("feedback");
679
- let saveTimeout = null;
680
- textarea.addEventListener("input", () => {
681
- clearTimeout(saveTimeout);
682
- document.getElementById("feedback-status").textContent = "";
683
- saveTimeout = setTimeout(() => saveCurrentFeedback(), 800);
684
- });
685
- }
686
-
687
- // ---- Navigation ----
688
- function navigate(delta) {
689
- const newIndex = currentIndex + delta;
690
- if (newIndex >= 0 && newIndex < EMBEDDED_DATA.runs.length) {
691
- saveCurrentFeedback();
692
- showRun(newIndex);
693
- }
694
- }
695
-
696
- function updateNavButtons() {
697
- document.getElementById("prev-btn").disabled = currentIndex === 0;
698
- document.getElementById("next-btn").disabled =
699
- currentIndex === EMBEDDED_DATA.runs.length - 1;
700
- }
701
-
702
- // ---- Show a run ----
703
- function showRun(index) {
704
- currentIndex = index;
705
- const run = EMBEDDED_DATA.runs[index];
706
-
707
- // Progress
708
- document.getElementById("progress").textContent =
709
- `${index + 1} of ${EMBEDDED_DATA.runs.length}`;
710
-
711
- // Prompt
712
- document.getElementById("prompt-text").textContent = run.prompt;
713
-
714
- // Config badge
715
- const badge = document.getElementById("config-badge");
716
- const configMatch = run.id.match(/(with_skill|without_skill|new_skill|old_skill)/);
717
- if (configMatch) {
718
- const config = configMatch[1];
719
- const isBaseline = config === "without_skill" || config === "old_skill";
720
- badge.textContent = config.replace(/_/g, " ");
721
- badge.className = "config-badge " + (isBaseline ? "config-baseline" : "config-primary");
722
- badge.style.display = "inline-block";
723
- } else {
724
- badge.style.display = "none";
725
- }
726
-
727
- // Outputs
728
- renderOutputs(run);
729
-
730
- // Previous outputs
731
- renderPrevOutputs(run);
732
-
733
- // Grades
734
- renderGrades(run);
735
-
736
- // Previous feedback
737
- const prevFb = (EMBEDDED_DATA.previous_feedback || {})[run.id];
738
- const prevEl = document.getElementById("prev-feedback");
739
- if (prevFb) {
740
- document.getElementById("prev-feedback-text").textContent = prevFb;
741
- prevEl.style.display = "block";
742
- } else {
743
- prevEl.style.display = "none";
744
- }
745
-
746
- // Feedback
747
- document.getElementById("feedback").value = feedbackMap[run.id] || "";
748
- document.getElementById("feedback-status").textContent = "";
749
-
750
- updateNavButtons();
751
-
752
- // Track visited runs and promote done button when all visited
753
- visitedRuns.add(index);
754
- const doneBtn = document.getElementById("done-btn");
755
- if (visitedRuns.size >= EMBEDDED_DATA.runs.length) {
756
- doneBtn.classList.add("ready");
757
- }
758
-
759
- // Scroll main content to top
760
- document.querySelector(".main").scrollTop = 0;
761
- }
762
-
763
- // ---- Render outputs ----
764
- function renderOutputs(run) {
765
- const container = document.getElementById("outputs-body");
766
- container.innerHTML = "";
767
-
768
- const outputs = run.outputs || [];
769
- if (outputs.length === 0) {
770
- container.innerHTML = '<div class="empty-state">No output files</div>';
771
- return;
772
- }
773
-
774
- for (const file of outputs) {
775
- const fileDiv = document.createElement("div");
776
- fileDiv.className = "output-file";
777
-
778
- // Always show file header with download link
779
- const header = document.createElement("div");
780
- header.className = "output-file-header";
781
- const nameSpan = document.createElement("span");
782
- nameSpan.textContent = file.name;
783
- header.appendChild(nameSpan);
784
- const dlBtn = document.createElement("a");
785
- dlBtn.className = "dl-btn";
786
- dlBtn.textContent = "Download";
787
- dlBtn.download = file.name;
788
- dlBtn.href = getDownloadUri(file);
789
- header.appendChild(dlBtn);
790
- fileDiv.appendChild(header);
791
-
792
- const content = document.createElement("div");
793
- content.className = "output-file-content";
794
-
795
- if (file.type === "text") {
796
- const pre = document.createElement("pre");
797
- pre.textContent = file.content;
798
- content.appendChild(pre);
799
- } else if (file.type === "image") {
800
- const img = document.createElement("img");
801
- img.src = file.data_uri;
802
- img.alt = file.name;
803
- content.appendChild(img);
804
- } else if (file.type === "pdf") {
805
- const iframe = document.createElement("iframe");
806
- iframe.src = file.data_uri;
807
- content.appendChild(iframe);
808
- } else if (file.type === "xlsx") {
809
- renderXlsx(content, file.data_b64);
810
- } else if (file.type === "binary") {
811
- const a = document.createElement("a");
812
- a.className = "download-link";
813
- a.href = file.data_uri;
814
- a.download = file.name;
815
- a.textContent = "Download " + file.name;
816
- content.appendChild(a);
817
- } else if (file.type === "error") {
818
- const pre = document.createElement("pre");
819
- pre.textContent = file.content;
820
- pre.style.color = "var(--red)";
821
- content.appendChild(pre);
822
- }
823
-
824
- fileDiv.appendChild(content);
825
- container.appendChild(fileDiv);
826
- }
827
- }
828
-
829
- // ---- XLSX rendering via SheetJS ----
830
- function renderXlsx(container, b64Data) {
831
- try {
832
- const raw = Uint8Array.from(atob(b64Data), c => c.charCodeAt(0));
833
- const wb = XLSX.read(raw, { type: "array" });
834
-
835
- for (let i = 0; i < wb.SheetNames.length; i++) {
836
- const sheetName = wb.SheetNames[i];
837
- const ws = wb.Sheets[sheetName];
838
-
839
- if (wb.SheetNames.length > 1) {
840
- const sheetLabel = document.createElement("div");
841
- sheetLabel.style.cssText =
842
- "font-weight:600; font-size:0.8rem; color:#b0aea5; margin-top:0.5rem; margin-bottom:0.25rem;";
843
- sheetLabel.textContent = "Sheet: " + sheetName;
844
- container.appendChild(sheetLabel);
845
- }
846
-
847
- const htmlStr = XLSX.utils.sheet_to_html(ws, { editable: false });
848
- const wrapper = document.createElement("div");
849
- wrapper.innerHTML = htmlStr;
850
- container.appendChild(wrapper);
851
- }
852
- } catch (err) {
853
- container.textContent = "Error rendering spreadsheet: " + err.message;
854
- }
855
- }
856
-
857
- // ---- Grades ----
858
- function renderGrades(run) {
859
- const section = document.getElementById("grades-section");
860
- const content = document.getElementById("grades-content");
861
-
862
- if (!run.grading) {
863
- section.style.display = "none";
864
- return;
865
- }
866
-
867
- const grading = run.grading;
868
- section.style.display = "block";
869
- // Reset to collapsed
870
- content.classList.remove("open");
871
- document.getElementById("grades-arrow").classList.remove("open");
872
-
873
- const summary = grading.summary || {};
874
- const expectations = grading.expectations || [];
875
-
876
- let html = '<div style="padding: 1rem;">';
877
-
878
- // Summary line
879
- const passRate = summary.pass_rate != null
880
- ? Math.round(summary.pass_rate * 100) + "%"
881
- : "?";
882
- const badgeClass = summary.pass_rate >= 0.8 ? "grade-pass" : summary.pass_rate >= 0.5 ? "" : "grade-fail";
883
- html += '<div class="grades-summary">';
884
- html += '<span class="grade-badge ' + badgeClass + '">' + passRate + '</span>';
885
- html += '<span>' + (summary.passed || 0) + ' passed, ' + (summary.failed || 0) + ' failed of ' + (summary.total || 0) + '</span>';
886
- html += '</div>';
887
-
888
- // Assertions list
889
- html += '<ul class="assertion-list">';
890
- for (const exp of expectations) {
891
- const statusClass = exp.passed ? "pass" : "fail";
892
- const statusIcon = exp.passed ? "\u2713" : "\u2717";
893
- html += '<li class="assertion-item">';
894
- html += '<span class="assertion-status ' + statusClass + '">' + statusIcon + '</span>';
895
- html += '<span>' + escapeHtml(exp.text) + '</span>';
896
- if (exp.evidence) {
897
- html += '<div class="assertion-evidence">' + escapeHtml(exp.evidence) + '</div>';
898
- }
899
- html += '</li>';
900
- }
901
- html += '</ul>';
902
-
903
- html += '</div>';
904
- content.innerHTML = html;
905
- }
906
-
907
- function toggleGrades() {
908
- const content = document.getElementById("grades-content");
909
- const arrow = document.getElementById("grades-arrow");
910
- content.classList.toggle("open");
911
- arrow.classList.toggle("open");
912
- }
913
-
914
- // ---- Previous outputs (collapsible) ----
915
- function renderPrevOutputs(run) {
916
- const section = document.getElementById("prev-outputs-section");
917
- const content = document.getElementById("prev-outputs-content");
918
- const prevOutputs = (EMBEDDED_DATA.previous_outputs || {})[run.id];
919
-
920
- if (!prevOutputs || prevOutputs.length === 0) {
921
- section.style.display = "none";
922
- return;
923
- }
924
-
925
- section.style.display = "block";
926
- // Reset to collapsed
927
- content.classList.remove("open");
928
- document.getElementById("prev-outputs-arrow").classList.remove("open");
929
-
930
- // Render the files into the content area
931
- content.innerHTML = "";
932
- const wrapper = document.createElement("div");
933
- wrapper.style.padding = "1rem";
934
-
935
- for (const file of prevOutputs) {
936
- const fileDiv = document.createElement("div");
937
- fileDiv.className = "output-file";
938
-
939
- const header = document.createElement("div");
940
- header.className = "output-file-header";
941
- const nameSpan = document.createElement("span");
942
- nameSpan.textContent = file.name;
943
- header.appendChild(nameSpan);
944
- const dlBtn = document.createElement("a");
945
- dlBtn.className = "dl-btn";
946
- dlBtn.textContent = "Download";
947
- dlBtn.download = file.name;
948
- dlBtn.href = getDownloadUri(file);
949
- header.appendChild(dlBtn);
950
- fileDiv.appendChild(header);
951
-
952
- const fc = document.createElement("div");
953
- fc.className = "output-file-content";
954
-
955
- if (file.type === "text") {
956
- const pre = document.createElement("pre");
957
- pre.textContent = file.content;
958
- fc.appendChild(pre);
959
- } else if (file.type === "image") {
960
- const img = document.createElement("img");
961
- img.src = file.data_uri;
962
- img.alt = file.name;
963
- fc.appendChild(img);
964
- } else if (file.type === "pdf") {
965
- const iframe = document.createElement("iframe");
966
- iframe.src = file.data_uri;
967
- fc.appendChild(iframe);
968
- } else if (file.type === "xlsx") {
969
- renderXlsx(fc, file.data_b64);
970
- } else if (file.type === "binary") {
971
- const a = document.createElement("a");
972
- a.className = "download-link";
973
- a.href = file.data_uri;
974
- a.download = file.name;
975
- a.textContent = "Download " + file.name;
976
- fc.appendChild(a);
977
- }
978
-
979
- fileDiv.appendChild(fc);
980
- wrapper.appendChild(fileDiv);
981
- }
982
-
983
- content.appendChild(wrapper);
984
- }
985
-
986
- function togglePrevOutputs() {
987
- const content = document.getElementById("prev-outputs-content");
988
- const arrow = document.getElementById("prev-outputs-arrow");
989
- content.classList.toggle("open");
990
- arrow.classList.toggle("open");
991
- }
992
-
993
- // ---- Feedback (saved to server -> feedback.json) ----
994
- function saveCurrentFeedback() {
995
- const run = EMBEDDED_DATA.runs[currentIndex];
996
- const text = document.getElementById("feedback").value;
997
-
998
- if (text.trim() === "") {
999
- delete feedbackMap[run.id];
1000
- } else {
1001
- feedbackMap[run.id] = text;
1002
- }
1003
-
1004
- // Build reviews array from map
1005
- const reviews = [];
1006
- for (const [run_id, feedback] of Object.entries(feedbackMap)) {
1007
- if (feedback.trim()) {
1008
- reviews.push({ run_id, feedback, timestamp: new Date().toISOString() });
1009
- }
1010
- }
1011
-
1012
- fetch("/api/feedback", {
1013
- method: "POST",
1014
- headers: { "Content-Type": "application/json" },
1015
- body: JSON.stringify({ reviews, status: "in_progress" }),
1016
- }).then(() => {
1017
- document.getElementById("feedback-status").textContent = "Saved";
1018
- }).catch(() => {
1019
- // Static mode or server unavailable — no-op on auto-save,
1020
- // feedback will be downloaded on final submit
1021
- document.getElementById("feedback-status").textContent = "Will download on submit";
1022
- });
1023
- }
1024
-
1025
- // ---- Done ----
1026
- function showDoneDialog() {
1027
- // Save current textarea to feedbackMap (but don't POST yet)
1028
- const run = EMBEDDED_DATA.runs[currentIndex];
1029
- const text = document.getElementById("feedback").value;
1030
- if (text.trim() === "") {
1031
- delete feedbackMap[run.id];
1032
- } else {
1033
- feedbackMap[run.id] = text;
1034
- }
1035
-
1036
- // POST once with status: complete — include ALL runs so the model
1037
- // can distinguish "no feedback" (looks good) from "not reviewed"
1038
- const reviews = [];
1039
- const ts = new Date().toISOString();
1040
- for (const r of EMBEDDED_DATA.runs) {
1041
- reviews.push({ run_id: r.id, feedback: feedbackMap[r.id] || "", timestamp: ts });
1042
- }
1043
- const payload = JSON.stringify({ reviews, status: "complete" }, null, 2);
1044
- fetch("/api/feedback", {
1045
- method: "POST",
1046
- headers: { "Content-Type": "application/json" },
1047
- body: payload,
1048
- }).then(() => {
1049
- document.getElementById("done-overlay").classList.add("visible");
1050
- }).catch(() => {
1051
- // Server not available (static mode) — download as file
1052
- const blob = new Blob([payload], { type: "application/json" });
1053
- const url = URL.createObjectURL(blob);
1054
- const a = document.createElement("a");
1055
- a.href = url;
1056
- a.download = "feedback.json";
1057
- a.click();
1058
- URL.revokeObjectURL(url);
1059
- document.getElementById("done-overlay").classList.add("visible");
1060
- });
1061
- }
1062
-
1063
- function closeDoneDialog() {
1064
- // Reset status back to in_progress
1065
- saveCurrentFeedback();
1066
- document.getElementById("done-overlay").classList.remove("visible");
1067
- }
1068
-
1069
- // ---- Toast ----
1070
- function showToast(message) {
1071
- const toast = document.getElementById("toast");
1072
- toast.textContent = message;
1073
- toast.classList.add("visible");
1074
- setTimeout(() => toast.classList.remove("visible"), 2000);
1075
- }
1076
-
1077
- // ---- Keyboard nav ----
1078
- document.addEventListener("keydown", (e) => {
1079
- // Don't capture when typing in textarea
1080
- if (e.target.tagName === "TEXTAREA") return;
1081
-
1082
- if (e.key === "ArrowLeft" || e.key === "ArrowUp") {
1083
- e.preventDefault();
1084
- navigate(-1);
1085
- } else if (e.key === "ArrowRight" || e.key === "ArrowDown") {
1086
- e.preventDefault();
1087
- navigate(1);
1088
- }
1089
- });
1090
-
1091
- // ---- Util ----
1092
- function getDownloadUri(file) {
1093
- if (file.data_uri) return file.data_uri;
1094
- if (file.data_b64) return "data:application/octet-stream;base64," + file.data_b64;
1095
- if (file.type === "text") return "data:text/plain;charset=utf-8," + encodeURIComponent(file.content);
1096
- return "#";
1097
- }
1098
-
1099
- function escapeHtml(text) {
1100
- const div = document.createElement("div");
1101
- div.textContent = text;
1102
- return div.innerHTML;
1103
- }
1104
-
1105
- // ---- View switching ----
1106
- function switchView(view) {
1107
- document.querySelectorAll(".view-tab").forEach(t => t.classList.remove("active"));
1108
- document.querySelectorAll(".view-panel").forEach(p => p.classList.remove("active"));
1109
- document.querySelector(`[onclick="switchView('${view}')"]`).classList.add("active");
1110
- document.getElementById("panel-" + view).classList.add("active");
1111
- }
1112
-
1113
- // ---- Benchmark rendering ----
1114
- function renderBenchmark() {
1115
- const data = EMBEDDED_DATA.benchmark;
1116
- if (!data) return;
1117
-
1118
- // Show the tabs
1119
- document.getElementById("view-tabs").style.display = "flex";
1120
-
1121
- const container = document.getElementById("benchmark-content");
1122
- const summary = data.run_summary || {};
1123
- const metadata = data.metadata || {};
1124
- const notes = data.notes || [];
1125
-
1126
- let html = "";
1127
-
1128
- // Header
1129
- html += "<h2 style='font-family: Poppins, sans-serif; margin-bottom: 0.5rem;'>Benchmark Results</h2>";
1130
- html += "<p style='color: var(--text-muted); font-size: 0.875rem; margin-bottom: 1.25rem;'>";
1131
- if (metadata.skill_name) html += "<strong>" + escapeHtml(metadata.skill_name) + "</strong> &mdash; ";
1132
- if (metadata.timestamp) html += metadata.timestamp + " &mdash; ";
1133
- if (metadata.evals_run) html += "Evals: " + metadata.evals_run.join(", ") + " &mdash; ";
1134
- html += (metadata.runs_per_configuration || "?") + " runs per configuration";
1135
- html += "</p>";
1136
-
1137
- // Summary table
1138
- html += '<table class="benchmark-table">';
1139
-
1140
- function fmtStat(stat, pct) {
1141
- if (!stat) return "—";
1142
- const suffix = pct ? "%" : "";
1143
- const m = pct ? (stat.mean * 100).toFixed(0) : stat.mean.toFixed(1);
1144
- const s = pct ? (stat.stddev * 100).toFixed(0) : stat.stddev.toFixed(1);
1145
- return m + suffix + " ± " + s + suffix;
1146
- }
1147
-
1148
- function deltaClass(val) {
1149
- if (!val) return "";
1150
- const n = parseFloat(val);
1151
- if (n > 0) return "benchmark-delta-positive";
1152
- if (n < 0) return "benchmark-delta-negative";
1153
- return "";
1154
- }
1155
-
1156
- // Discover config names dynamically (everything except "delta")
1157
- const configs = Object.keys(summary).filter(k => k !== "delta");
1158
- const configA = configs[0] || "config_a";
1159
- const configB = configs[1] || "config_b";
1160
- const labelA = configA.replace(/_/g, " ").replace(/\b\w/g, c => c.toUpperCase());
1161
- const labelB = configB.replace(/_/g, " ").replace(/\b\w/g, c => c.toUpperCase());
1162
- const a = summary[configA] || {};
1163
- const b = summary[configB] || {};
1164
- const delta = summary.delta || {};
1165
-
1166
- html += "<thead><tr><th>Metric</th><th>" + escapeHtml(labelA) + "</th><th>" + escapeHtml(labelB) + "</th><th>Delta</th></tr></thead>";
1167
- html += "<tbody>";
1168
-
1169
- html += "<tr><td><strong>Pass Rate</strong></td>";
1170
- html += "<td>" + fmtStat(a.pass_rate, true) + "</td>";
1171
- html += "<td>" + fmtStat(b.pass_rate, true) + "</td>";
1172
- html += '<td class="' + deltaClass(delta.pass_rate) + '">' + (delta.pass_rate || "—") + "</td></tr>";
1173
-
1174
- // Time (only show row if data exists)
1175
- if (a.time_seconds || b.time_seconds) {
1176
- html += "<tr><td><strong>Time (s)</strong></td>";
1177
- html += "<td>" + fmtStat(a.time_seconds, false) + "</td>";
1178
- html += "<td>" + fmtStat(b.time_seconds, false) + "</td>";
1179
- html += '<td class="' + deltaClass(delta.time_seconds) + '">' + (delta.time_seconds ? delta.time_seconds + "s" : "—") + "</td></tr>";
1180
- }
1181
-
1182
- // Tokens (only show row if data exists)
1183
- if (a.tokens || b.tokens) {
1184
- html += "<tr><td><strong>Tokens</strong></td>";
1185
- html += "<td>" + fmtStat(a.tokens, false) + "</td>";
1186
- html += "<td>" + fmtStat(b.tokens, false) + "</td>";
1187
- html += '<td class="' + deltaClass(delta.tokens) + '">' + (delta.tokens || "—") + "</td></tr>";
1188
- }
1189
-
1190
- html += "</tbody></table>";
1191
-
1192
- // Per-eval breakdown (if runs data available)
1193
- const runs = data.runs || [];
1194
- if (runs.length > 0) {
1195
- const evalIds = [...new Set(runs.map(r => r.eval_id))].sort((a, b) => a - b);
1196
-
1197
- html += "<h3 style='font-family: Poppins, sans-serif; margin-bottom: 0.75rem;'>Per-Eval Breakdown</h3>";
1198
-
1199
- const hasTime = runs.some(r => r.result && r.result.time_seconds != null);
1200
- const hasErrors = runs.some(r => r.result && r.result.errors > 0);
1201
-
1202
- for (const evalId of evalIds) {
1203
- const evalRuns = runs.filter(r => r.eval_id === evalId);
1204
- const evalName = evalRuns[0] && evalRuns[0].eval_name ? evalRuns[0].eval_name : "Eval " + evalId;
1205
-
1206
- html += "<h4 style='font-family: Poppins, sans-serif; margin: 1rem 0 0.5rem; color: var(--text);'>" + escapeHtml(evalName) + "</h4>";
1207
- html += '<table class="benchmark-table">';
1208
- html += "<thead><tr><th>Config</th><th>Run</th><th>Pass Rate</th>";
1209
- if (hasTime) html += "<th>Time (s)</th>";
1210
- if (hasErrors) html += "<th>Crashes During Execution</th>";
1211
- html += "</tr></thead>";
1212
- html += "<tbody>";
1213
-
1214
- // Group by config and render with average rows
1215
- const configGroups = [...new Set(evalRuns.map(r => r.configuration))];
1216
- for (let ci = 0; ci < configGroups.length; ci++) {
1217
- const config = configGroups[ci];
1218
- const configRuns = evalRuns.filter(r => r.configuration === config);
1219
- if (configRuns.length === 0) continue;
1220
-
1221
- const rowClass = ci === 0 ? "benchmark-row-with" : "benchmark-row-without";
1222
- const configLabel = config.replace(/_/g, " ").replace(/\b\w/g, c => c.toUpperCase());
1223
-
1224
- for (const run of configRuns) {
1225
- const r = run.result || {};
1226
- const prClass = r.pass_rate >= 0.8 ? "benchmark-delta-positive" : r.pass_rate < 0.5 ? "benchmark-delta-negative" : "";
1227
- html += '<tr class="' + rowClass + '">';
1228
- html += "<td>" + configLabel + "</td>";
1229
- html += "<td>" + run.run_number + "</td>";
1230
- html += '<td class="' + prClass + '">' + ((r.pass_rate || 0) * 100).toFixed(0) + "% (" + (r.passed || 0) + "/" + (r.total || 0) + ")</td>";
1231
- if (hasTime) html += "<td>" + (r.time_seconds != null ? r.time_seconds.toFixed(1) : "—") + "</td>";
1232
- if (hasErrors) html += "<td>" + (r.errors || 0) + "</td>";
1233
- html += "</tr>";
1234
- }
1235
-
1236
- // Average row
1237
- const rates = configRuns.map(r => (r.result || {}).pass_rate || 0);
1238
- const avgRate = rates.reduce((a, b) => a + b, 0) / rates.length;
1239
- const avgPrClass = avgRate >= 0.8 ? "benchmark-delta-positive" : avgRate < 0.5 ? "benchmark-delta-negative" : "";
1240
- html += '<tr class="benchmark-row-avg ' + rowClass + '">';
1241
- html += "<td>" + configLabel + "</td>";
1242
- html += "<td>Avg</td>";
1243
- html += '<td class="' + avgPrClass + '">' + (avgRate * 100).toFixed(0) + "%</td>";
1244
- if (hasTime) {
1245
- const times = configRuns.map(r => (r.result || {}).time_seconds).filter(t => t != null);
1246
- html += "<td>" + (times.length ? (times.reduce((a, b) => a + b, 0) / times.length).toFixed(1) : "—") + "</td>";
1247
- }
1248
- if (hasErrors) html += "<td></td>";
1249
- html += "</tr>";
1250
- }
1251
- html += "</tbody></table>";
1252
-
1253
- // Per-assertion detail for this eval
1254
- const runsWithExpectations = {};
1255
- for (const config of configGroups) {
1256
- runsWithExpectations[config] = evalRuns.filter(r => r.configuration === config && r.expectations && r.expectations.length > 0);
1257
- }
1258
- const hasAnyExpectations = Object.values(runsWithExpectations).some(runs => runs.length > 0);
1259
- if (hasAnyExpectations) {
1260
- // Collect all unique assertion texts across all configs
1261
- const allAssertions = [];
1262
- const seen = new Set();
1263
- for (const config of configGroups) {
1264
- for (const run of runsWithExpectations[config]) {
1265
- for (const exp of (run.expectations || [])) {
1266
- if (!seen.has(exp.text)) {
1267
- seen.add(exp.text);
1268
- allAssertions.push(exp.text);
1269
- }
1270
- }
1271
- }
1272
- }
1273
-
1274
- html += '<table class="benchmark-table" style="margin-top: 0.5rem;">';
1275
- html += "<thead><tr><th>Assertion</th>";
1276
- for (const config of configGroups) {
1277
- const label = config.replace(/_/g, " ").replace(/\b\w/g, c => c.toUpperCase());
1278
- html += "<th>" + escapeHtml(label) + "</th>";
1279
- }
1280
- html += "</tr></thead><tbody>";
1281
-
1282
- for (const assertionText of allAssertions) {
1283
- html += "<tr><td>" + escapeHtml(assertionText) + "</td>";
1284
-
1285
- for (const config of configGroups) {
1286
- html += "<td>";
1287
- for (const run of runsWithExpectations[config]) {
1288
- const exp = (run.expectations || []).find(e => e.text === assertionText);
1289
- if (exp) {
1290
- const cls = exp.passed ? "benchmark-delta-positive" : "benchmark-delta-negative";
1291
- const icon = exp.passed ? "\u2713" : "\u2717";
1292
- html += '<span class="' + cls + '" title="Run ' + run.run_number + ': ' + escapeHtml(exp.evidence || "") + '">' + icon + "</span> ";
1293
- } else {
1294
- html += "— ";
1295
- }
1296
- }
1297
- html += "</td>";
1298
- }
1299
- html += "</tr>";
1300
- }
1301
- html += "</tbody></table>";
1302
- }
1303
- }
1304
- }
1305
-
1306
- // Notes
1307
- if (notes.length > 0) {
1308
- html += '<div class="benchmark-notes">';
1309
- html += "<h3>Analysis Notes</h3>";
1310
- html += "<ul>";
1311
- for (const note of notes) {
1312
- html += "<li>" + escapeHtml(note) + "</li>";
1313
- }
1314
- html += "</ul></div>";
1315
- }
1316
-
1317
- container.innerHTML = html;
1318
- }
1319
-
1320
- // ---- Start ----
1321
- init();
1322
- renderBenchmark();
1323
- </script>
1324
- </body>
1325
- </html>
1
+ <!DOCTYPE html>
2
+ <html lang="en">
3
+ <head>
4
+ <meta charset="UTF-8">
5
+ <meta name="viewport" content="width=device-width, initial-scale=1.0">
6
+ <title>Eval Review</title>
7
+ <link rel="preconnect" href="https://fonts.googleapis.com">
8
+ <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
9
+ <link href="https://fonts.googleapis.com/css2?family=Poppins:wght@500;600&family=Lora:wght@400;500&display=swap" rel="stylesheet">
10
+ <script src="https://cdn.sheetjs.com/xlsx-0.20.3/package/dist/xlsx.full.min.js" integrity="sha384-EnyY0/GSHQGSxSgMwaIPzSESbqoOLSexfnSMN2AP+39Ckmn92stwABZynq1JyzdT" crossorigin="anonymous"></script>
11
+ <style>
12
+ :root {
13
+ --bg: #faf9f5;
14
+ --surface: #ffffff;
15
+ --border: #e8e6dc;
16
+ --text: #141413;
17
+ --text-muted: #b0aea5;
18
+ --accent: #d97757;
19
+ --accent-hover: #c4613f;
20
+ --green: #788c5d;
21
+ --green-bg: #eef2e8;
22
+ --red: #c44;
23
+ --red-bg: #fceaea;
24
+ --header-bg: #141413;
25
+ --header-text: #faf9f5;
26
+ --radius: 6px;
27
+ }
28
+
29
+ * { box-sizing: border-box; margin: 0; padding: 0; }
30
+
31
+ body {
32
+ font-family: 'Lora', Georgia, serif;
33
+ background: var(--bg);
34
+ color: var(--text);
35
+ height: 100vh;
36
+ display: flex;
37
+ flex-direction: column;
38
+ }
39
+
40
+ /* ---- Header ---- */
41
+ .header {
42
+ background: var(--header-bg);
43
+ color: var(--header-text);
44
+ padding: 1rem 2rem;
45
+ display: flex;
46
+ justify-content: space-between;
47
+ align-items: center;
48
+ flex-shrink: 0;
49
+ }
50
+ .header h1 {
51
+ font-family: 'Poppins', sans-serif;
52
+ font-size: 1.25rem;
53
+ font-weight: 600;
54
+ }
55
+ .header .instructions {
56
+ font-size: 0.8rem;
57
+ opacity: 0.7;
58
+ margin-top: 0.25rem;
59
+ }
60
+ .header .progress {
61
+ font-size: 0.875rem;
62
+ opacity: 0.8;
63
+ text-align: right;
64
+ }
65
+
66
+ /* ---- Main content ---- */
67
+ .main {
68
+ flex: 1;
69
+ overflow-y: auto;
70
+ padding: 1.5rem 2rem;
71
+ display: flex;
72
+ flex-direction: column;
73
+ gap: 1.25rem;
74
+ }
75
+
76
+ /* ---- Sections ---- */
77
+ .section {
78
+ background: var(--surface);
79
+ border: 1px solid var(--border);
80
+ border-radius: var(--radius);
81
+ flex-shrink: 0;
82
+ }
83
+ .section-header {
84
+ font-family: 'Poppins', sans-serif;
85
+ padding: 0.75rem 1rem;
86
+ font-size: 0.75rem;
87
+ font-weight: 500;
88
+ text-transform: uppercase;
89
+ letter-spacing: 0.05em;
90
+ color: var(--text-muted);
91
+ border-bottom: 1px solid var(--border);
92
+ background: var(--bg);
93
+ }
94
+ .section-body {
95
+ padding: 1rem;
96
+ }
97
+
98
+ /* ---- Config badge ---- */
99
+ .config-badge {
100
+ display: inline-block;
101
+ padding: 0.2rem 0.625rem;
102
+ border-radius: 9999px;
103
+ font-family: 'Poppins', sans-serif;
104
+ font-size: 0.6875rem;
105
+ font-weight: 600;
106
+ text-transform: uppercase;
107
+ letter-spacing: 0.03em;
108
+ margin-left: 0.75rem;
109
+ vertical-align: middle;
110
+ }
111
+ .config-badge.config-primary {
112
+ background: rgba(33, 150, 243, 0.12);
113
+ color: #1976d2;
114
+ }
115
+ .config-badge.config-baseline {
116
+ background: rgba(255, 193, 7, 0.15);
117
+ color: #f57f17;
118
+ }
119
+
120
+ /* ---- Prompt ---- */
121
+ .prompt-text {
122
+ white-space: pre-wrap;
123
+ font-size: 0.9375rem;
124
+ line-height: 1.6;
125
+ }
126
+
127
+ /* ---- Outputs ---- */
128
+ .output-file {
129
+ border: 1px solid var(--border);
130
+ border-radius: var(--radius);
131
+ overflow: hidden;
132
+ }
133
+ .output-file + .output-file {
134
+ margin-top: 1rem;
135
+ }
136
+ .output-file-header {
137
+ padding: 0.5rem 0.75rem;
138
+ font-size: 0.8rem;
139
+ font-weight: 600;
140
+ color: var(--text-muted);
141
+ background: var(--bg);
142
+ border-bottom: 1px solid var(--border);
143
+ font-family: 'SF Mono', SFMono-Regular, Consolas, 'Liberation Mono', Menlo, monospace;
144
+ display: flex;
145
+ justify-content: space-between;
146
+ align-items: center;
147
+ }
148
+ .output-file-header .dl-btn {
149
+ font-size: 0.7rem;
150
+ color: var(--accent);
151
+ text-decoration: none;
152
+ cursor: pointer;
153
+ font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', sans-serif;
154
+ font-weight: 500;
155
+ opacity: 0.8;
156
+ }
157
+ .output-file-header .dl-btn:hover {
158
+ opacity: 1;
159
+ text-decoration: underline;
160
+ }
161
+ .output-file-content {
162
+ padding: 0.75rem;
163
+ overflow-x: auto;
164
+ }
165
+ .output-file-content pre {
166
+ font-size: 0.8125rem;
167
+ line-height: 1.5;
168
+ white-space: pre-wrap;
169
+ word-break: break-word;
170
+ font-family: 'SF Mono', SFMono-Regular, Consolas, 'Liberation Mono', Menlo, monospace;
171
+ }
172
+ .output-file-content img {
173
+ max-width: 100%;
174
+ height: auto;
175
+ border-radius: 4px;
176
+ }
177
+ .output-file-content iframe {
178
+ width: 100%;
179
+ height: 600px;
180
+ border: none;
181
+ }
182
+ .output-file-content table {
183
+ border-collapse: collapse;
184
+ font-size: 0.8125rem;
185
+ width: 100%;
186
+ }
187
+ .output-file-content table td,
188
+ .output-file-content table th {
189
+ border: 1px solid var(--border);
190
+ padding: 0.375rem 0.5rem;
191
+ text-align: left;
192
+ }
193
+ .output-file-content table th {
194
+ background: var(--bg);
195
+ font-weight: 600;
196
+ }
197
+ .output-file-content .download-link {
198
+ display: inline-flex;
199
+ align-items: center;
200
+ gap: 0.5rem;
201
+ padding: 0.5rem 1rem;
202
+ background: var(--bg);
203
+ border: 1px solid var(--border);
204
+ border-radius: 4px;
205
+ color: var(--accent);
206
+ text-decoration: none;
207
+ font-size: 0.875rem;
208
+ cursor: pointer;
209
+ }
210
+ .output-file-content .download-link:hover {
211
+ background: var(--border);
212
+ }
213
+ .empty-state {
214
+ color: var(--text-muted);
215
+ font-style: italic;
216
+ padding: 2rem;
217
+ text-align: center;
218
+ }
219
+
220
+ /* ---- Feedback ---- */
221
+ .prev-feedback {
222
+ background: var(--bg);
223
+ border: 1px solid var(--border);
224
+ border-radius: 4px;
225
+ padding: 0.625rem 0.75rem;
226
+ margin-top: 0.75rem;
227
+ font-size: 0.8125rem;
228
+ color: var(--text-muted);
229
+ line-height: 1.5;
230
+ }
231
+ .prev-feedback-label {
232
+ font-size: 0.7rem;
233
+ font-weight: 600;
234
+ text-transform: uppercase;
235
+ letter-spacing: 0.04em;
236
+ margin-bottom: 0.25rem;
237
+ color: var(--text-muted);
238
+ }
239
+ .feedback-textarea {
240
+ width: 100%;
241
+ min-height: 100px;
242
+ padding: 0.75rem;
243
+ border: 1px solid var(--border);
244
+ border-radius: 4px;
245
+ font-family: inherit;
246
+ font-size: 0.9375rem;
247
+ line-height: 1.5;
248
+ resize: vertical;
249
+ color: var(--text);
250
+ }
251
+ .feedback-textarea:focus {
252
+ outline: none;
253
+ border-color: var(--accent);
254
+ box-shadow: 0 0 0 3px rgba(37, 99, 235, 0.1);
255
+ }
256
+ .feedback-status {
257
+ font-size: 0.75rem;
258
+ color: var(--text-muted);
259
+ margin-top: 0.5rem;
260
+ min-height: 1.1em;
261
+ }
262
+
263
+ /* ---- Grades (collapsible) ---- */
264
+ .grades-toggle {
265
+ display: flex;
266
+ align-items: center;
267
+ cursor: pointer;
268
+ user-select: none;
269
+ }
270
+ .grades-toggle:hover {
271
+ color: var(--accent);
272
+ }
273
+ .grades-toggle .arrow {
274
+ margin-right: 0.5rem;
275
+ transition: transform 0.15s;
276
+ font-size: 0.75rem;
277
+ }
278
+ .grades-toggle .arrow.open {
279
+ transform: rotate(90deg);
280
+ }
281
+ .grades-content {
282
+ display: none;
283
+ margin-top: 0.75rem;
284
+ }
285
+ .grades-content.open {
286
+ display: block;
287
+ }
288
+ .grades-summary {
289
+ font-size: 0.875rem;
290
+ margin-bottom: 0.75rem;
291
+ display: flex;
292
+ align-items: center;
293
+ gap: 0.5rem;
294
+ }
295
+ .grade-badge {
296
+ display: inline-block;
297
+ padding: 0.125rem 0.5rem;
298
+ border-radius: 9999px;
299
+ font-size: 0.75rem;
300
+ font-weight: 600;
301
+ }
302
+ .grade-pass { background: var(--green-bg); color: var(--green); }
303
+ .grade-fail { background: var(--red-bg); color: var(--red); }
304
+ .assertion-list {
305
+ list-style: none;
306
+ }
307
+ .assertion-item {
308
+ padding: 0.625rem 0;
309
+ border-bottom: 1px solid var(--border);
310
+ font-size: 0.8125rem;
311
+ }
312
+ .assertion-item:last-child { border-bottom: none; }
313
+ .assertion-status {
314
+ font-weight: 600;
315
+ margin-right: 0.5rem;
316
+ }
317
+ .assertion-status.pass { color: var(--green); }
318
+ .assertion-status.fail { color: var(--red); }
319
+ .assertion-evidence {
320
+ color: var(--text-muted);
321
+ font-size: 0.75rem;
322
+ margin-top: 0.25rem;
323
+ padding-left: 1.5rem;
324
+ }
325
+
326
+ /* ---- View tabs ---- */
327
+ .view-tabs {
328
+ display: flex;
329
+ gap: 0;
330
+ padding: 0 2rem;
331
+ background: var(--bg);
332
+ border-bottom: 1px solid var(--border);
333
+ flex-shrink: 0;
334
+ }
335
+ .view-tab {
336
+ font-family: 'Poppins', sans-serif;
337
+ padding: 0.625rem 1.25rem;
338
+ font-size: 0.8125rem;
339
+ font-weight: 500;
340
+ cursor: pointer;
341
+ border: none;
342
+ background: none;
343
+ color: var(--text-muted);
344
+ border-bottom: 2px solid transparent;
345
+ transition: all 0.15s;
346
+ }
347
+ .view-tab:hover { color: var(--text); }
348
+ .view-tab.active {
349
+ color: var(--accent);
350
+ border-bottom-color: var(--accent);
351
+ }
352
+ .view-panel { display: none; }
353
+ .view-panel.active { display: flex; flex-direction: column; flex: 1; overflow: hidden; }
354
+
355
+ /* ---- Benchmark view ---- */
356
+ .benchmark-view {
357
+ padding: 1.5rem 2rem;
358
+ overflow-y: auto;
359
+ flex: 1;
360
+ }
361
+ .benchmark-table {
362
+ border-collapse: collapse;
363
+ background: var(--surface);
364
+ border: 1px solid var(--border);
365
+ border-radius: var(--radius);
366
+ font-size: 0.8125rem;
367
+ width: 100%;
368
+ margin-bottom: 1.5rem;
369
+ }
370
+ .benchmark-table th, .benchmark-table td {
371
+ padding: 0.625rem 0.75rem;
372
+ text-align: left;
373
+ border: 1px solid var(--border);
374
+ }
375
+ .benchmark-table th {
376
+ font-family: 'Poppins', sans-serif;
377
+ background: var(--header-bg);
378
+ color: var(--header-text);
379
+ font-weight: 500;
380
+ font-size: 0.75rem;
381
+ text-transform: uppercase;
382
+ letter-spacing: 0.04em;
383
+ }
384
+ .benchmark-table tr:hover { background: var(--bg); }
385
+ .benchmark-table tr.benchmark-row-with { background: rgba(33, 150, 243, 0.06); }
386
+ .benchmark-table tr.benchmark-row-without { background: rgba(255, 193, 7, 0.06); }
387
+ .benchmark-table tr.benchmark-row-with:hover { background: rgba(33, 150, 243, 0.12); }
388
+ .benchmark-table tr.benchmark-row-without:hover { background: rgba(255, 193, 7, 0.12); }
389
+ .benchmark-table tr.benchmark-row-avg { font-weight: 600; border-top: 2px solid var(--border); }
390
+ .benchmark-table tr.benchmark-row-avg.benchmark-row-with { background: rgba(33, 150, 243, 0.12); }
391
+ .benchmark-table tr.benchmark-row-avg.benchmark-row-without { background: rgba(255, 193, 7, 0.12); }
392
+ .benchmark-delta-positive { color: var(--green); font-weight: 600; }
393
+ .benchmark-delta-negative { color: var(--red); font-weight: 600; }
394
+ .benchmark-notes {
395
+ background: var(--surface);
396
+ border: 1px solid var(--border);
397
+ border-radius: var(--radius);
398
+ padding: 1rem;
399
+ }
400
+ .benchmark-notes h3 {
401
+ font-family: 'Poppins', sans-serif;
402
+ font-size: 0.875rem;
403
+ margin-bottom: 0.75rem;
404
+ }
405
+ .benchmark-notes ul {
406
+ list-style: disc;
407
+ padding-left: 1.25rem;
408
+ }
409
+ .benchmark-notes li {
410
+ font-size: 0.8125rem;
411
+ line-height: 1.6;
412
+ margin-bottom: 0.375rem;
413
+ }
414
+ .benchmark-empty {
415
+ color: var(--text-muted);
416
+ font-style: italic;
417
+ text-align: center;
418
+ padding: 3rem;
419
+ }
420
+
421
+ /* ---- Navigation ---- */
422
+ .nav {
423
+ display: flex;
424
+ justify-content: space-between;
425
+ align-items: center;
426
+ padding: 1rem 2rem;
427
+ border-top: 1px solid var(--border);
428
+ background: var(--surface);
429
+ flex-shrink: 0;
430
+ }
431
+ .nav-btn {
432
+ font-family: 'Poppins', sans-serif;
433
+ padding: 0.5rem 1.25rem;
434
+ border: 1px solid var(--border);
435
+ border-radius: var(--radius);
436
+ background: var(--surface);
437
+ cursor: pointer;
438
+ font-size: 0.875rem;
439
+ font-weight: 500;
440
+ color: var(--text);
441
+ transition: all 0.15s;
442
+ }
443
+ .nav-btn:hover:not(:disabled) {
444
+ background: var(--bg);
445
+ border-color: var(--text-muted);
446
+ }
447
+ .nav-btn:disabled {
448
+ opacity: 0.4;
449
+ cursor: not-allowed;
450
+ }
451
+ .done-btn {
452
+ font-family: 'Poppins', sans-serif;
453
+ padding: 0.5rem 1.5rem;
454
+ border: 1px solid var(--border);
455
+ border-radius: var(--radius);
456
+ background: var(--surface);
457
+ color: var(--text);
458
+ cursor: pointer;
459
+ font-size: 0.875rem;
460
+ font-weight: 500;
461
+ transition: all 0.15s;
462
+ }
463
+ .done-btn:hover {
464
+ background: var(--bg);
465
+ border-color: var(--text-muted);
466
+ }
467
+ .done-btn.ready {
468
+ border: none;
469
+ background: var(--accent);
470
+ color: white;
471
+ font-weight: 600;
472
+ }
473
+ .done-btn.ready:hover {
474
+ background: var(--accent-hover);
475
+ }
476
+ /* ---- Done overlay ---- */
477
+ .done-overlay {
478
+ display: none;
479
+ position: fixed;
480
+ inset: 0;
481
+ background: rgba(0, 0, 0, 0.5);
482
+ z-index: 100;
483
+ justify-content: center;
484
+ align-items: center;
485
+ }
486
+ .done-overlay.visible {
487
+ display: flex;
488
+ }
489
+ .done-card {
490
+ background: var(--surface);
491
+ border-radius: 12px;
492
+ padding: 2rem 3rem;
493
+ text-align: center;
494
+ box-shadow: 0 20px 60px rgba(0, 0, 0, 0.3);
495
+ max-width: 500px;
496
+ }
497
+ .done-card h2 {
498
+ font-size: 1.5rem;
499
+ margin-bottom: 0.5rem;
500
+ }
501
+ .done-card p {
502
+ color: var(--text-muted);
503
+ margin-bottom: 1.5rem;
504
+ line-height: 1.5;
505
+ }
506
+ .done-card .btn-row {
507
+ display: flex;
508
+ gap: 0.5rem;
509
+ justify-content: center;
510
+ }
511
+ .done-card button {
512
+ padding: 0.5rem 1.25rem;
513
+ border: 1px solid var(--border);
514
+ border-radius: var(--radius);
515
+ background: var(--surface);
516
+ cursor: pointer;
517
+ font-size: 0.875rem;
518
+ }
519
+ .done-card button:hover {
520
+ background: var(--bg);
521
+ }
522
+ /* ---- Toast ---- */
523
+ .toast {
524
+ position: fixed;
525
+ bottom: 5rem;
526
+ left: 50%;
527
+ transform: translateX(-50%);
528
+ background: var(--header-bg);
529
+ color: var(--header-text);
530
+ padding: 0.625rem 1.25rem;
531
+ border-radius: var(--radius);
532
+ font-size: 0.875rem;
533
+ opacity: 0;
534
+ transition: opacity 0.3s;
535
+ pointer-events: none;
536
+ z-index: 200;
537
+ }
538
+ .toast.visible {
539
+ opacity: 1;
540
+ }
541
+ </style>
542
+ </head>
543
+ <body>
544
+ <div id="app" style="height:100vh; display:flex; flex-direction:column;">
545
+ <div class="header">
546
+ <div>
547
+ <h1>Eval Review: <span id="skill-name"></span></h1>
548
+ <div class="instructions">Review each output and leave feedback below. Navigate with arrow keys or buttons. When done, copy feedback and paste into Claude Code.</div>
549
+ </div>
550
+ <div class="progress" id="progress"></div>
551
+ </div>
552
+
553
+ <!-- View tabs (only shown when benchmark data exists) -->
554
+ <div class="view-tabs" id="view-tabs" style="display:none;">
555
+ <button class="view-tab active" onclick="switchView('outputs')">Outputs</button>
556
+ <button class="view-tab" onclick="switchView('benchmark')">Benchmark</button>
557
+ </div>
558
+
559
+ <!-- Outputs panel (qualitative review) -->
560
+ <div class="view-panel active" id="panel-outputs">
561
+ <div class="main">
562
+ <!-- Prompt -->
563
+ <div class="section">
564
+ <div class="section-header">Prompt <span class="config-badge" id="config-badge" style="display:none;"></span></div>
565
+ <div class="section-body">
566
+ <div class="prompt-text" id="prompt-text"></div>
567
+ </div>
568
+ </div>
569
+
570
+ <!-- Outputs -->
571
+ <div class="section">
572
+ <div class="section-header">Output</div>
573
+ <div class="section-body" id="outputs-body">
574
+ <div class="empty-state">No output files found</div>
575
+ </div>
576
+ </div>
577
+
578
+ <!-- Previous Output (collapsible) -->
579
+ <div class="section" id="prev-outputs-section" style="display:none;">
580
+ <div class="section-header">
581
+ <div class="grades-toggle" onclick="togglePrevOutputs()">
582
+ <span class="arrow" id="prev-outputs-arrow">&#9654;</span>
583
+ Previous Output
584
+ </div>
585
+ </div>
586
+ <div class="grades-content" id="prev-outputs-content"></div>
587
+ </div>
588
+
589
+ <!-- Grades (collapsible) -->
590
+ <div class="section" id="grades-section" style="display:none;">
591
+ <div class="section-header">
592
+ <div class="grades-toggle" onclick="toggleGrades()">
593
+ <span class="arrow" id="grades-arrow">&#9654;</span>
594
+ Formal Grades
595
+ </div>
596
+ </div>
597
+ <div class="grades-content" id="grades-content"></div>
598
+ </div>
599
+
600
+ <!-- Feedback -->
601
+ <div class="section">
602
+ <div class="section-header">Your Feedback</div>
603
+ <div class="section-body">
604
+ <textarea
605
+ class="feedback-textarea"
606
+ id="feedback"
607
+ placeholder="What do you think of this output? Any issues, suggestions, or things that look great?"
608
+ ></textarea>
609
+ <div class="feedback-status" id="feedback-status"></div>
610
+ <div class="prev-feedback" id="prev-feedback" style="display:none;">
611
+ <div class="prev-feedback-label">Previous feedback</div>
612
+ <div id="prev-feedback-text"></div>
613
+ </div>
614
+ </div>
615
+ </div>
616
+ </div>
617
+
618
+ <div class="nav" id="outputs-nav">
619
+ <button class="nav-btn" id="prev-btn" onclick="navigate(-1)">&#8592; Previous</button>
620
+ <button class="done-btn" id="done-btn" onclick="showDoneDialog()">Submit All Reviews</button>
621
+ <button class="nav-btn" id="next-btn" onclick="navigate(1)">Next &#8594;</button>
622
+ </div>
623
+ </div><!-- end panel-outputs -->
624
+
625
+ <!-- Benchmark panel (quantitative stats) -->
626
+ <div class="view-panel" id="panel-benchmark">
627
+ <div class="benchmark-view" id="benchmark-content">
628
+ <div class="benchmark-empty">No benchmark data available. Run a benchmark to see quantitative results here.</div>
629
+ </div>
630
+ </div>
631
+ </div>
632
+
633
+ <!-- Done overlay -->
634
+ <div class="done-overlay" id="done-overlay">
635
+ <div class="done-card">
636
+ <h2>Review Complete</h2>
637
+ <p>Your feedback has been saved. Go back to your Claude Code session and tell Claude you're done reviewing.</p>
638
+ <div class="btn-row">
639
+ <button onclick="closeDoneDialog()">OK</button>
640
+ </div>
641
+ </div>
642
+ </div>
643
+
644
+ <!-- Toast -->
645
+ <div class="toast" id="toast"></div>
646
+
647
+ <script>
648
+ // ---- Embedded data (injected by generate_review.py) ----
649
+ /*__EMBEDDED_DATA__*/
650
+
651
+ // ---- State ----
652
+ let feedbackMap = {}; // run_id -> feedback text
653
+ let currentIndex = 0;
654
+ let visitedRuns = new Set();
655
+
656
+ // ---- Init ----
657
+ async function init() {
658
+ // Load saved feedback from server — but only if this isn't a fresh
659
+ // iteration (indicated by previous_feedback being present). When
660
+ // previous feedback exists, the feedback.json on disk is stale from
661
+ // the prior iteration and should not pre-fill the textareas.
662
+ const hasPrevious = Object.keys(EMBEDDED_DATA.previous_feedback || {}).length > 0
663
+ || Object.keys(EMBEDDED_DATA.previous_outputs || {}).length > 0;
664
+ if (!hasPrevious) {
665
+ try {
666
+ const resp = await fetch("/api/feedback");
667
+ const data = await resp.json();
668
+ if (data.reviews) {
669
+ for (const r of data.reviews) feedbackMap[r.run_id] = r.feedback;
670
+ }
671
+ } catch { /* first run, no feedback yet */ }
672
+ }
673
+
674
+ document.getElementById("skill-name").textContent = EMBEDDED_DATA.skill_name;
675
+ showRun(0);
676
+
677
+ // Wire up feedback auto-save
678
+ const textarea = document.getElementById("feedback");
679
+ let saveTimeout = null;
680
+ textarea.addEventListener("input", () => {
681
+ clearTimeout(saveTimeout);
682
+ document.getElementById("feedback-status").textContent = "";
683
+ saveTimeout = setTimeout(() => saveCurrentFeedback(), 800);
684
+ });
685
+ }
686
+
687
+ // ---- Navigation ----
688
+ function navigate(delta) {
689
+ const newIndex = currentIndex + delta;
690
+ if (newIndex >= 0 && newIndex < EMBEDDED_DATA.runs.length) {
691
+ saveCurrentFeedback();
692
+ showRun(newIndex);
693
+ }
694
+ }
695
+
696
+ function updateNavButtons() {
697
+ document.getElementById("prev-btn").disabled = currentIndex === 0;
698
+ document.getElementById("next-btn").disabled =
699
+ currentIndex === EMBEDDED_DATA.runs.length - 1;
700
+ }
701
+
702
+ // ---- Show a run ----
703
+ function showRun(index) {
704
+ currentIndex = index;
705
+ const run = EMBEDDED_DATA.runs[index];
706
+
707
+ // Progress
708
+ document.getElementById("progress").textContent =
709
+ `${index + 1} of ${EMBEDDED_DATA.runs.length}`;
710
+
711
+ // Prompt
712
+ document.getElementById("prompt-text").textContent = run.prompt;
713
+
714
+ // Config badge
715
+ const badge = document.getElementById("config-badge");
716
+ const configMatch = run.id.match(/(with_skill|without_skill|new_skill|old_skill)/);
717
+ if (configMatch) {
718
+ const config = configMatch[1];
719
+ const isBaseline = config === "without_skill" || config === "old_skill";
720
+ badge.textContent = config.replace(/_/g, " ");
721
+ badge.className = "config-badge " + (isBaseline ? "config-baseline" : "config-primary");
722
+ badge.style.display = "inline-block";
723
+ } else {
724
+ badge.style.display = "none";
725
+ }
726
+
727
+ // Outputs
728
+ renderOutputs(run);
729
+
730
+ // Previous outputs
731
+ renderPrevOutputs(run);
732
+
733
+ // Grades
734
+ renderGrades(run);
735
+
736
+ // Previous feedback
737
+ const prevFb = (EMBEDDED_DATA.previous_feedback || {})[run.id];
738
+ const prevEl = document.getElementById("prev-feedback");
739
+ if (prevFb) {
740
+ document.getElementById("prev-feedback-text").textContent = prevFb;
741
+ prevEl.style.display = "block";
742
+ } else {
743
+ prevEl.style.display = "none";
744
+ }
745
+
746
+ // Feedback
747
+ document.getElementById("feedback").value = feedbackMap[run.id] || "";
748
+ document.getElementById("feedback-status").textContent = "";
749
+
750
+ updateNavButtons();
751
+
752
+ // Track visited runs and promote done button when all visited
753
+ visitedRuns.add(index);
754
+ const doneBtn = document.getElementById("done-btn");
755
+ if (visitedRuns.size >= EMBEDDED_DATA.runs.length) {
756
+ doneBtn.classList.add("ready");
757
+ }
758
+
759
+ // Scroll main content to top
760
+ document.querySelector(".main").scrollTop = 0;
761
+ }
762
+
763
+ // ---- Render outputs ----
764
+ function renderOutputs(run) {
765
+ const container = document.getElementById("outputs-body");
766
+ container.innerHTML = "";
767
+
768
+ const outputs = run.outputs || [];
769
+ if (outputs.length === 0) {
770
+ container.innerHTML = '<div class="empty-state">No output files</div>';
771
+ return;
772
+ }
773
+
774
+ for (const file of outputs) {
775
+ const fileDiv = document.createElement("div");
776
+ fileDiv.className = "output-file";
777
+
778
+ // Always show file header with download link
779
+ const header = document.createElement("div");
780
+ header.className = "output-file-header";
781
+ const nameSpan = document.createElement("span");
782
+ nameSpan.textContent = file.name;
783
+ header.appendChild(nameSpan);
784
+ const dlBtn = document.createElement("a");
785
+ dlBtn.className = "dl-btn";
786
+ dlBtn.textContent = "Download";
787
+ dlBtn.download = file.name;
788
+ dlBtn.href = getDownloadUri(file);
789
+ header.appendChild(dlBtn);
790
+ fileDiv.appendChild(header);
791
+
792
+ const content = document.createElement("div");
793
+ content.className = "output-file-content";
794
+
795
+ if (file.type === "text") {
796
+ const pre = document.createElement("pre");
797
+ pre.textContent = file.content;
798
+ content.appendChild(pre);
799
+ } else if (file.type === "image") {
800
+ const img = document.createElement("img");
801
+ img.src = file.data_uri;
802
+ img.alt = file.name;
803
+ content.appendChild(img);
804
+ } else if (file.type === "pdf") {
805
+ const iframe = document.createElement("iframe");
806
+ iframe.src = file.data_uri;
807
+ content.appendChild(iframe);
808
+ } else if (file.type === "xlsx") {
809
+ renderXlsx(content, file.data_b64);
810
+ } else if (file.type === "binary") {
811
+ const a = document.createElement("a");
812
+ a.className = "download-link";
813
+ a.href = file.data_uri;
814
+ a.download = file.name;
815
+ a.textContent = "Download " + file.name;
816
+ content.appendChild(a);
817
+ } else if (file.type === "error") {
818
+ const pre = document.createElement("pre");
819
+ pre.textContent = file.content;
820
+ pre.style.color = "var(--red)";
821
+ content.appendChild(pre);
822
+ }
823
+
824
+ fileDiv.appendChild(content);
825
+ container.appendChild(fileDiv);
826
+ }
827
+ }
828
+
829
+ // ---- XLSX rendering via SheetJS ----
830
+ function renderXlsx(container, b64Data) {
831
+ try {
832
+ const raw = Uint8Array.from(atob(b64Data), c => c.charCodeAt(0));
833
+ const wb = XLSX.read(raw, { type: "array" });
834
+
835
+ for (let i = 0; i < wb.SheetNames.length; i++) {
836
+ const sheetName = wb.SheetNames[i];
837
+ const ws = wb.Sheets[sheetName];
838
+
839
+ if (wb.SheetNames.length > 1) {
840
+ const sheetLabel = document.createElement("div");
841
+ sheetLabel.style.cssText =
842
+ "font-weight:600; font-size:0.8rem; color:#b0aea5; margin-top:0.5rem; margin-bottom:0.25rem;";
843
+ sheetLabel.textContent = "Sheet: " + sheetName;
844
+ container.appendChild(sheetLabel);
845
+ }
846
+
847
+ const htmlStr = XLSX.utils.sheet_to_html(ws, { editable: false });
848
+ const wrapper = document.createElement("div");
849
+ wrapper.innerHTML = htmlStr;
850
+ container.appendChild(wrapper);
851
+ }
852
+ } catch (err) {
853
+ container.textContent = "Error rendering spreadsheet: " + err.message;
854
+ }
855
+ }
856
+
857
+ // ---- Grades ----
858
+ function renderGrades(run) {
859
+ const section = document.getElementById("grades-section");
860
+ const content = document.getElementById("grades-content");
861
+
862
+ if (!run.grading) {
863
+ section.style.display = "none";
864
+ return;
865
+ }
866
+
867
+ const grading = run.grading;
868
+ section.style.display = "block";
869
+ // Reset to collapsed
870
+ content.classList.remove("open");
871
+ document.getElementById("grades-arrow").classList.remove("open");
872
+
873
+ const summary = grading.summary || {};
874
+ const expectations = grading.expectations || [];
875
+
876
+ let html = '<div style="padding: 1rem;">';
877
+
878
+ // Summary line
879
+ const passRate = summary.pass_rate != null
880
+ ? Math.round(summary.pass_rate * 100) + "%"
881
+ : "?";
882
+ const badgeClass = summary.pass_rate >= 0.8 ? "grade-pass" : summary.pass_rate >= 0.5 ? "" : "grade-fail";
883
+ html += '<div class="grades-summary">';
884
+ html += '<span class="grade-badge ' + badgeClass + '">' + passRate + '</span>';
885
+ html += '<span>' + (summary.passed || 0) + ' passed, ' + (summary.failed || 0) + ' failed of ' + (summary.total || 0) + '</span>';
886
+ html += '</div>';
887
+
888
+ // Assertions list
889
+ html += '<ul class="assertion-list">';
890
+ for (const exp of expectations) {
891
+ const statusClass = exp.passed ? "pass" : "fail";
892
+ const statusIcon = exp.passed ? "\u2713" : "\u2717";
893
+ html += '<li class="assertion-item">';
894
+ html += '<span class="assertion-status ' + statusClass + '">' + statusIcon + '</span>';
895
+ html += '<span>' + escapeHtml(exp.text) + '</span>';
896
+ if (exp.evidence) {
897
+ html += '<div class="assertion-evidence">' + escapeHtml(exp.evidence) + '</div>';
898
+ }
899
+ html += '</li>';
900
+ }
901
+ html += '</ul>';
902
+
903
+ html += '</div>';
904
+ content.innerHTML = html;
905
+ }
906
+
907
+ function toggleGrades() {
908
+ const content = document.getElementById("grades-content");
909
+ const arrow = document.getElementById("grades-arrow");
910
+ content.classList.toggle("open");
911
+ arrow.classList.toggle("open");
912
+ }
913
+
914
+ // ---- Previous outputs (collapsible) ----
915
+ function renderPrevOutputs(run) {
916
+ const section = document.getElementById("prev-outputs-section");
917
+ const content = document.getElementById("prev-outputs-content");
918
+ const prevOutputs = (EMBEDDED_DATA.previous_outputs || {})[run.id];
919
+
920
+ if (!prevOutputs || prevOutputs.length === 0) {
921
+ section.style.display = "none";
922
+ return;
923
+ }
924
+
925
+ section.style.display = "block";
926
+ // Reset to collapsed
927
+ content.classList.remove("open");
928
+ document.getElementById("prev-outputs-arrow").classList.remove("open");
929
+
930
+ // Render the files into the content area
931
+ content.innerHTML = "";
932
+ const wrapper = document.createElement("div");
933
+ wrapper.style.padding = "1rem";
934
+
935
+ for (const file of prevOutputs) {
936
+ const fileDiv = document.createElement("div");
937
+ fileDiv.className = "output-file";
938
+
939
+ const header = document.createElement("div");
940
+ header.className = "output-file-header";
941
+ const nameSpan = document.createElement("span");
942
+ nameSpan.textContent = file.name;
943
+ header.appendChild(nameSpan);
944
+ const dlBtn = document.createElement("a");
945
+ dlBtn.className = "dl-btn";
946
+ dlBtn.textContent = "Download";
947
+ dlBtn.download = file.name;
948
+ dlBtn.href = getDownloadUri(file);
949
+ header.appendChild(dlBtn);
950
+ fileDiv.appendChild(header);
951
+
952
+ const fc = document.createElement("div");
953
+ fc.className = "output-file-content";
954
+
955
+ if (file.type === "text") {
956
+ const pre = document.createElement("pre");
957
+ pre.textContent = file.content;
958
+ fc.appendChild(pre);
959
+ } else if (file.type === "image") {
960
+ const img = document.createElement("img");
961
+ img.src = file.data_uri;
962
+ img.alt = file.name;
963
+ fc.appendChild(img);
964
+ } else if (file.type === "pdf") {
965
+ const iframe = document.createElement("iframe");
966
+ iframe.src = file.data_uri;
967
+ fc.appendChild(iframe);
968
+ } else if (file.type === "xlsx") {
969
+ renderXlsx(fc, file.data_b64);
970
+ } else if (file.type === "binary") {
971
+ const a = document.createElement("a");
972
+ a.className = "download-link";
973
+ a.href = file.data_uri;
974
+ a.download = file.name;
975
+ a.textContent = "Download " + file.name;
976
+ fc.appendChild(a);
977
+ }
978
+
979
+ fileDiv.appendChild(fc);
980
+ wrapper.appendChild(fileDiv);
981
+ }
982
+
983
+ content.appendChild(wrapper);
984
+ }
985
+
986
+ function togglePrevOutputs() {
987
+ const content = document.getElementById("prev-outputs-content");
988
+ const arrow = document.getElementById("prev-outputs-arrow");
989
+ content.classList.toggle("open");
990
+ arrow.classList.toggle("open");
991
+ }
992
+
993
+ // ---- Feedback (saved to server -> feedback.json) ----
994
+ function saveCurrentFeedback() {
995
+ const run = EMBEDDED_DATA.runs[currentIndex];
996
+ const text = document.getElementById("feedback").value;
997
+
998
+ if (text.trim() === "") {
999
+ delete feedbackMap[run.id];
1000
+ } else {
1001
+ feedbackMap[run.id] = text;
1002
+ }
1003
+
1004
+ // Build reviews array from map
1005
+ const reviews = [];
1006
+ for (const [run_id, feedback] of Object.entries(feedbackMap)) {
1007
+ if (feedback.trim()) {
1008
+ reviews.push({ run_id, feedback, timestamp: new Date().toISOString() });
1009
+ }
1010
+ }
1011
+
1012
+ fetch("/api/feedback", {
1013
+ method: "POST",
1014
+ headers: { "Content-Type": "application/json" },
1015
+ body: JSON.stringify({ reviews, status: "in_progress" }),
1016
+ }).then(() => {
1017
+ document.getElementById("feedback-status").textContent = "Saved";
1018
+ }).catch(() => {
1019
+ // Static mode or server unavailable — no-op on auto-save,
1020
+ // feedback will be downloaded on final submit
1021
+ document.getElementById("feedback-status").textContent = "Will download on submit";
1022
+ });
1023
+ }
1024
+
1025
+ // ---- Done ----
1026
+ function showDoneDialog() {
1027
+ // Save current textarea to feedbackMap (but don't POST yet)
1028
+ const run = EMBEDDED_DATA.runs[currentIndex];
1029
+ const text = document.getElementById("feedback").value;
1030
+ if (text.trim() === "") {
1031
+ delete feedbackMap[run.id];
1032
+ } else {
1033
+ feedbackMap[run.id] = text;
1034
+ }
1035
+
1036
+ // POST once with status: complete — include ALL runs so the model
1037
+ // can distinguish "no feedback" (looks good) from "not reviewed"
1038
+ const reviews = [];
1039
+ const ts = new Date().toISOString();
1040
+ for (const r of EMBEDDED_DATA.runs) {
1041
+ reviews.push({ run_id: r.id, feedback: feedbackMap[r.id] || "", timestamp: ts });
1042
+ }
1043
+ const payload = JSON.stringify({ reviews, status: "complete" }, null, 2);
1044
+ fetch("/api/feedback", {
1045
+ method: "POST",
1046
+ headers: { "Content-Type": "application/json" },
1047
+ body: payload,
1048
+ }).then(() => {
1049
+ document.getElementById("done-overlay").classList.add("visible");
1050
+ }).catch(() => {
1051
+ // Server not available (static mode) — download as file
1052
+ const blob = new Blob([payload], { type: "application/json" });
1053
+ const url = URL.createObjectURL(blob);
1054
+ const a = document.createElement("a");
1055
+ a.href = url;
1056
+ a.download = "feedback.json";
1057
+ a.click();
1058
+ URL.revokeObjectURL(url);
1059
+ document.getElementById("done-overlay").classList.add("visible");
1060
+ });
1061
+ }
1062
+
1063
+ function closeDoneDialog() {
1064
+ // Reset status back to in_progress
1065
+ saveCurrentFeedback();
1066
+ document.getElementById("done-overlay").classList.remove("visible");
1067
+ }
1068
+
1069
+ // ---- Toast ----
1070
+ function showToast(message) {
1071
+ const toast = document.getElementById("toast");
1072
+ toast.textContent = message;
1073
+ toast.classList.add("visible");
1074
+ setTimeout(() => toast.classList.remove("visible"), 2000);
1075
+ }
1076
+
1077
+ // ---- Keyboard nav ----
1078
+ document.addEventListener("keydown", (e) => {
1079
+ // Don't capture when typing in textarea
1080
+ if (e.target.tagName === "TEXTAREA") return;
1081
+
1082
+ if (e.key === "ArrowLeft" || e.key === "ArrowUp") {
1083
+ e.preventDefault();
1084
+ navigate(-1);
1085
+ } else if (e.key === "ArrowRight" || e.key === "ArrowDown") {
1086
+ e.preventDefault();
1087
+ navigate(1);
1088
+ }
1089
+ });
1090
+
1091
+ // ---- Util ----
1092
+ function getDownloadUri(file) {
1093
+ if (file.data_uri) return file.data_uri;
1094
+ if (file.data_b64) return "data:application/octet-stream;base64," + file.data_b64;
1095
+ if (file.type === "text") return "data:text/plain;charset=utf-8," + encodeURIComponent(file.content);
1096
+ return "#";
1097
+ }
1098
+
1099
+ function escapeHtml(text) {
1100
+ const div = document.createElement("div");
1101
+ div.textContent = text;
1102
+ return div.innerHTML;
1103
+ }
1104
+
1105
+ // ---- View switching ----
1106
+ function switchView(view) {
1107
+ document.querySelectorAll(".view-tab").forEach(t => t.classList.remove("active"));
1108
+ document.querySelectorAll(".view-panel").forEach(p => p.classList.remove("active"));
1109
+ document.querySelector(`[onclick="switchView('${view}')"]`).classList.add("active");
1110
+ document.getElementById("panel-" + view).classList.add("active");
1111
+ }
1112
+
1113
+ // ---- Benchmark rendering ----
1114
+ function renderBenchmark() {
1115
+ const data = EMBEDDED_DATA.benchmark;
1116
+ if (!data) return;
1117
+
1118
+ // Show the tabs
1119
+ document.getElementById("view-tabs").style.display = "flex";
1120
+
1121
+ const container = document.getElementById("benchmark-content");
1122
+ const summary = data.run_summary || {};
1123
+ const metadata = data.metadata || {};
1124
+ const notes = data.notes || [];
1125
+
1126
+ let html = "";
1127
+
1128
+ // Header
1129
+ html += "<h2 style='font-family: Poppins, sans-serif; margin-bottom: 0.5rem;'>Benchmark Results</h2>";
1130
+ html += "<p style='color: var(--text-muted); font-size: 0.875rem; margin-bottom: 1.25rem;'>";
1131
+ if (metadata.skill_name) html += "<strong>" + escapeHtml(metadata.skill_name) + "</strong> &mdash; ";
1132
+ if (metadata.timestamp) html += metadata.timestamp + " &mdash; ";
1133
+ if (metadata.evals_run) html += "Evals: " + metadata.evals_run.join(", ") + " &mdash; ";
1134
+ html += (metadata.runs_per_configuration || "?") + " runs per configuration";
1135
+ html += "</p>";
1136
+
1137
+ // Summary table
1138
+ html += '<table class="benchmark-table">';
1139
+
1140
+ function fmtStat(stat, pct) {
1141
+ if (!stat) return "—";
1142
+ const suffix = pct ? "%" : "";
1143
+ const m = pct ? (stat.mean * 100).toFixed(0) : stat.mean.toFixed(1);
1144
+ const s = pct ? (stat.stddev * 100).toFixed(0) : stat.stddev.toFixed(1);
1145
+ return m + suffix + " ± " + s + suffix;
1146
+ }
1147
+
1148
+ function deltaClass(val) {
1149
+ if (!val) return "";
1150
+ const n = parseFloat(val);
1151
+ if (n > 0) return "benchmark-delta-positive";
1152
+ if (n < 0) return "benchmark-delta-negative";
1153
+ return "";
1154
+ }
1155
+
1156
+ // Discover config names dynamically (everything except "delta")
1157
+ const configs = Object.keys(summary).filter(k => k !== "delta");
1158
+ const configA = configs[0] || "config_a";
1159
+ const configB = configs[1] || "config_b";
1160
+ const labelA = configA.replace(/_/g, " ").replace(/\b\w/g, c => c.toUpperCase());
1161
+ const labelB = configB.replace(/_/g, " ").replace(/\b\w/g, c => c.toUpperCase());
1162
+ const a = summary[configA] || {};
1163
+ const b = summary[configB] || {};
1164
+ const delta = summary.delta || {};
1165
+
1166
+ html += "<thead><tr><th>Metric</th><th>" + escapeHtml(labelA) + "</th><th>" + escapeHtml(labelB) + "</th><th>Delta</th></tr></thead>";
1167
+ html += "<tbody>";
1168
+
1169
+ html += "<tr><td><strong>Pass Rate</strong></td>";
1170
+ html += "<td>" + fmtStat(a.pass_rate, true) + "</td>";
1171
+ html += "<td>" + fmtStat(b.pass_rate, true) + "</td>";
1172
+ html += '<td class="' + deltaClass(delta.pass_rate) + '">' + (delta.pass_rate || "—") + "</td></tr>";
1173
+
1174
+ // Time (only show row if data exists)
1175
+ if (a.time_seconds || b.time_seconds) {
1176
+ html += "<tr><td><strong>Time (s)</strong></td>";
1177
+ html += "<td>" + fmtStat(a.time_seconds, false) + "</td>";
1178
+ html += "<td>" + fmtStat(b.time_seconds, false) + "</td>";
1179
+ html += '<td class="' + deltaClass(delta.time_seconds) + '">' + (delta.time_seconds ? delta.time_seconds + "s" : "—") + "</td></tr>";
1180
+ }
1181
+
1182
+ // Tokens (only show row if data exists)
1183
+ if (a.tokens || b.tokens) {
1184
+ html += "<tr><td><strong>Tokens</strong></td>";
1185
+ html += "<td>" + fmtStat(a.tokens, false) + "</td>";
1186
+ html += "<td>" + fmtStat(b.tokens, false) + "</td>";
1187
+ html += '<td class="' + deltaClass(delta.tokens) + '">' + (delta.tokens || "—") + "</td></tr>";
1188
+ }
1189
+
1190
+ html += "</tbody></table>";
1191
+
1192
+ // Per-eval breakdown (if runs data available)
1193
+ const runs = data.runs || [];
1194
+ if (runs.length > 0) {
1195
+ const evalIds = [...new Set(runs.map(r => r.eval_id))].sort((a, b) => a - b);
1196
+
1197
+ html += "<h3 style='font-family: Poppins, sans-serif; margin-bottom: 0.75rem;'>Per-Eval Breakdown</h3>";
1198
+
1199
+ const hasTime = runs.some(r => r.result && r.result.time_seconds != null);
1200
+ const hasErrors = runs.some(r => r.result && r.result.errors > 0);
1201
+
1202
+ for (const evalId of evalIds) {
1203
+ const evalRuns = runs.filter(r => r.eval_id === evalId);
1204
+ const evalName = evalRuns[0] && evalRuns[0].eval_name ? evalRuns[0].eval_name : "Eval " + evalId;
1205
+
1206
+ html += "<h4 style='font-family: Poppins, sans-serif; margin: 1rem 0 0.5rem; color: var(--text);'>" + escapeHtml(evalName) + "</h4>";
1207
+ html += '<table class="benchmark-table">';
1208
+ html += "<thead><tr><th>Config</th><th>Run</th><th>Pass Rate</th>";
1209
+ if (hasTime) html += "<th>Time (s)</th>";
1210
+ if (hasErrors) html += "<th>Crashes During Execution</th>";
1211
+ html += "</tr></thead>";
1212
+ html += "<tbody>";
1213
+
1214
+ // Group by config and render with average rows
1215
+ const configGroups = [...new Set(evalRuns.map(r => r.configuration))];
1216
+ for (let ci = 0; ci < configGroups.length; ci++) {
1217
+ const config = configGroups[ci];
1218
+ const configRuns = evalRuns.filter(r => r.configuration === config);
1219
+ if (configRuns.length === 0) continue;
1220
+
1221
+ const rowClass = ci === 0 ? "benchmark-row-with" : "benchmark-row-without";
1222
+ const configLabel = config.replace(/_/g, " ").replace(/\b\w/g, c => c.toUpperCase());
1223
+
1224
+ for (const run of configRuns) {
1225
+ const r = run.result || {};
1226
+ const prClass = r.pass_rate >= 0.8 ? "benchmark-delta-positive" : r.pass_rate < 0.5 ? "benchmark-delta-negative" : "";
1227
+ html += '<tr class="' + rowClass + '">';
1228
+ html += "<td>" + configLabel + "</td>";
1229
+ html += "<td>" + run.run_number + "</td>";
1230
+ html += '<td class="' + prClass + '">' + ((r.pass_rate || 0) * 100).toFixed(0) + "% (" + (r.passed || 0) + "/" + (r.total || 0) + ")</td>";
1231
+ if (hasTime) html += "<td>" + (r.time_seconds != null ? r.time_seconds.toFixed(1) : "—") + "</td>";
1232
+ if (hasErrors) html += "<td>" + (r.errors || 0) + "</td>";
1233
+ html += "</tr>";
1234
+ }
1235
+
1236
+ // Average row
1237
+ const rates = configRuns.map(r => (r.result || {}).pass_rate || 0);
1238
+ const avgRate = rates.reduce((a, b) => a + b, 0) / rates.length;
1239
+ const avgPrClass = avgRate >= 0.8 ? "benchmark-delta-positive" : avgRate < 0.5 ? "benchmark-delta-negative" : "";
1240
+ html += '<tr class="benchmark-row-avg ' + rowClass + '">';
1241
+ html += "<td>" + configLabel + "</td>";
1242
+ html += "<td>Avg</td>";
1243
+ html += '<td class="' + avgPrClass + '">' + (avgRate * 100).toFixed(0) + "%</td>";
1244
+ if (hasTime) {
1245
+ const times = configRuns.map(r => (r.result || {}).time_seconds).filter(t => t != null);
1246
+ html += "<td>" + (times.length ? (times.reduce((a, b) => a + b, 0) / times.length).toFixed(1) : "—") + "</td>";
1247
+ }
1248
+ if (hasErrors) html += "<td></td>";
1249
+ html += "</tr>";
1250
+ }
1251
+ html += "</tbody></table>";
1252
+
1253
+ // Per-assertion detail for this eval
1254
+ const runsWithExpectations = {};
1255
+ for (const config of configGroups) {
1256
+ runsWithExpectations[config] = evalRuns.filter(r => r.configuration === config && r.expectations && r.expectations.length > 0);
1257
+ }
1258
+ const hasAnyExpectations = Object.values(runsWithExpectations).some(runs => runs.length > 0);
1259
+ if (hasAnyExpectations) {
1260
+ // Collect all unique assertion texts across all configs
1261
+ const allAssertions = [];
1262
+ const seen = new Set();
1263
+ for (const config of configGroups) {
1264
+ for (const run of runsWithExpectations[config]) {
1265
+ for (const exp of (run.expectations || [])) {
1266
+ if (!seen.has(exp.text)) {
1267
+ seen.add(exp.text);
1268
+ allAssertions.push(exp.text);
1269
+ }
1270
+ }
1271
+ }
1272
+ }
1273
+
1274
+ html += '<table class="benchmark-table" style="margin-top: 0.5rem;">';
1275
+ html += "<thead><tr><th>Assertion</th>";
1276
+ for (const config of configGroups) {
1277
+ const label = config.replace(/_/g, " ").replace(/\b\w/g, c => c.toUpperCase());
1278
+ html += "<th>" + escapeHtml(label) + "</th>";
1279
+ }
1280
+ html += "</tr></thead><tbody>";
1281
+
1282
+ for (const assertionText of allAssertions) {
1283
+ html += "<tr><td>" + escapeHtml(assertionText) + "</td>";
1284
+
1285
+ for (const config of configGroups) {
1286
+ html += "<td>";
1287
+ for (const run of runsWithExpectations[config]) {
1288
+ const exp = (run.expectations || []).find(e => e.text === assertionText);
1289
+ if (exp) {
1290
+ const cls = exp.passed ? "benchmark-delta-positive" : "benchmark-delta-negative";
1291
+ const icon = exp.passed ? "\u2713" : "\u2717";
1292
+ html += '<span class="' + cls + '" title="Run ' + run.run_number + ': ' + escapeHtml(exp.evidence || "") + '">' + icon + "</span> ";
1293
+ } else {
1294
+ html += "— ";
1295
+ }
1296
+ }
1297
+ html += "</td>";
1298
+ }
1299
+ html += "</tr>";
1300
+ }
1301
+ html += "</tbody></table>";
1302
+ }
1303
+ }
1304
+ }
1305
+
1306
+ // Notes
1307
+ if (notes.length > 0) {
1308
+ html += '<div class="benchmark-notes">';
1309
+ html += "<h3>Analysis Notes</h3>";
1310
+ html += "<ul>";
1311
+ for (const note of notes) {
1312
+ html += "<li>" + escapeHtml(note) + "</li>";
1313
+ }
1314
+ html += "</ul></div>";
1315
+ }
1316
+
1317
+ container.innerHTML = html;
1318
+ }
1319
+
1320
+ // ---- Start ----
1321
+ init();
1322
+ renderBenchmark();
1323
+ </script>
1324
+ </body>
1325
+ </html>