pi-agent-browser-native 0.9.2 → 0.9.4

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 (392) hide show
  1. package/CHANGELOG.md +91 -5
  2. package/README.md +120 -86
  3. package/dist/extensions/agent-browser/index.js +43065 -2016
  4. package/dist/extensions/agent-browser/lib/argv-descriptor.js +49 -26
  5. package/dist/extensions/agent-browser/lib/argv-grammar.js +82 -93
  6. package/dist/extensions/agent-browser/lib/bash-guard.js +129 -126
  7. package/dist/extensions/agent-browser/lib/batch-lifecycle.js +113 -49
  8. package/dist/extensions/agent-browser/lib/browser-execution-claim-codec.js +61 -0
  9. package/dist/extensions/agent-browser/lib/browser-execution-claim-storage.js +232 -0
  10. package/dist/extensions/agent-browser/lib/browser-execution-claims.js +202 -0
  11. package/dist/extensions/agent-browser/lib/browser-execution-identity.js +77 -0
  12. package/dist/extensions/agent-browser/lib/browser-journal-branch.js +98 -0
  13. package/dist/extensions/agent-browser/lib/browser-journal-contracts.js +1 -0
  14. package/dist/extensions/agent-browser/lib/browser-journal-projection.js +221 -0
  15. package/dist/extensions/agent-browser/lib/browser-journal-reader.js +89 -0
  16. package/dist/extensions/agent-browser/lib/browser-journal-replay.js +246 -0
  17. package/dist/extensions/agent-browser/lib/browser-journal.js +103 -394
  18. package/dist/extensions/agent-browser/lib/browser-legacy-pages.js +220 -0
  19. package/dist/extensions/agent-browser/lib/browser-legacy-projection.js +282 -0
  20. package/dist/extensions/agent-browser/lib/browser-legacy-types.js +1 -0
  21. package/dist/extensions/agent-browser/lib/browser-session-conversion-stream.js +217 -0
  22. package/dist/extensions/agent-browser/lib/browser-session-conversion.js +80 -335
  23. package/dist/extensions/agent-browser/lib/browser-transcript-contracts.js +35 -0
  24. package/dist/extensions/agent-browser/lib/browser-transcript-validation.js +166 -0
  25. package/dist/extensions/agent-browser/lib/browser-transcript.js +137 -81
  26. package/dist/extensions/agent-browser/lib/browser-value-parsing.js +15 -0
  27. package/dist/extensions/agent-browser/lib/command-capabilities.js +340 -0
  28. package/dist/extensions/agent-browser/lib/command-policy.js +107 -88
  29. package/dist/extensions/agent-browser/lib/command-taxonomy.js +49 -322
  30. package/dist/extensions/agent-browser/lib/config-policy.js +138 -343
  31. package/dist/extensions/agent-browser/lib/config-providers.js +71 -0
  32. package/dist/extensions/agent-browser/lib/config-validation.js +218 -0
  33. package/dist/extensions/agent-browser/lib/config.js +19 -7
  34. package/dist/extensions/agent-browser/lib/electron/cdp.js +15 -7
  35. package/dist/extensions/agent-browser/lib/electron/cleanup.js +134 -55
  36. package/dist/extensions/agent-browser/lib/electron/discovery-darwin.js +109 -0
  37. package/dist/extensions/agent-browser/lib/electron/discovery-desktop.js +136 -0
  38. package/dist/extensions/agent-browser/lib/electron/discovery-evidence.js +89 -0
  39. package/dist/extensions/agent-browser/lib/electron/discovery-linux.js +93 -0
  40. package/dist/extensions/agent-browser/lib/electron/discovery-packages.js +162 -0
  41. package/dist/extensions/agent-browser/lib/electron/discovery-types.js +2 -0
  42. package/dist/extensions/agent-browser/lib/electron/discovery.js +140 -549
  43. package/dist/extensions/agent-browser/lib/electron/launch-monitor.js +102 -0
  44. package/dist/extensions/agent-browser/lib/electron/launch-process.js +209 -0
  45. package/dist/extensions/agent-browser/lib/electron/launch-types.js +2 -0
  46. package/dist/extensions/agent-browser/lib/electron/launch.js +249 -354
  47. package/dist/extensions/agent-browser/lib/executable-path.js +21 -12
  48. package/dist/extensions/agent-browser/lib/execution-cwd.js +35 -18
  49. package/dist/extensions/agent-browser/lib/input-modes/electron.js +162 -121
  50. package/dist/extensions/agent-browser/lib/input-modes/job.js +116 -313
  51. package/dist/extensions/agent-browser/lib/input-modes/lookup-network-evidence.js +104 -0
  52. package/dist/extensions/agent-browser/lib/input-modes/lookup-plan.js +132 -0
  53. package/dist/extensions/agent-browser/lib/input-modes/lookup-redaction.js +57 -0
  54. package/dist/extensions/agent-browser/lib/input-modes/lookup-source-evidence.js +151 -0
  55. package/dist/extensions/agent-browser/lib/input-modes/lookup-workspace.js +142 -0
  56. package/dist/extensions/agent-browser/lib/input-modes/lookups.js +57 -412
  57. package/dist/extensions/agent-browser/lib/input-modes/params.js +63 -17
  58. package/dist/extensions/agent-browser/lib/input-modes/qa-analysis.js +268 -0
  59. package/dist/extensions/agent-browser/lib/input-modes/qa-presentation.js +117 -0
  60. package/dist/extensions/agent-browser/lib/input-modes/script-child.js +396 -0
  61. package/dist/extensions/agent-browser/lib/input-modes/script-protocol.js +86 -0
  62. package/dist/extensions/agent-browser/lib/input-modes/script-types.js +1 -0
  63. package/dist/extensions/agent-browser/lib/input-modes/script-validation.js +60 -0
  64. package/dist/extensions/agent-browser/lib/input-modes/script.js +60 -409
  65. package/dist/extensions/agent-browser/lib/input-modes/semantic-action.js +218 -128
  66. package/dist/extensions/agent-browser/lib/input-modes/shared.js +15 -4
  67. package/dist/extensions/agent-browser/lib/input-modes/types.js +56 -7
  68. package/dist/extensions/agent-browser/lib/json-schema.js +22 -10
  69. package/dist/extensions/agent-browser/lib/launch-scoped-flags.js +17 -5
  70. package/dist/extensions/agent-browser/lib/managed-session-policy-lock.js +92 -425
  71. package/dist/extensions/agent-browser/lib/managed-session-posix-storage.js +58 -0
  72. package/dist/extensions/agent-browser/lib/managed-session-project-identity.js +244 -0
  73. package/dist/extensions/agent-browser/lib/managed-session-restore-context.js +84 -0
  74. package/dist/extensions/agent-browser/lib/managed-session-restore-policy.js +119 -0
  75. package/dist/extensions/agent-browser/lib/managed-session-restore-state.js +83 -0
  76. package/dist/extensions/agent-browser/lib/managed-session-restore.js +168 -300
  77. package/dist/extensions/agent-browser/lib/managed-session-snapshot-records.js +277 -0
  78. package/dist/extensions/agent-browser/lib/managed-session-snapshots.js +128 -305
  79. package/dist/extensions/agent-browser/lib/managed-session-storage.js +56 -253
  80. package/dist/extensions/agent-browser/lib/native-confirmation.js +140 -0
  81. package/dist/extensions/agent-browser/lib/native-output.js +44 -9
  82. package/dist/extensions/agent-browser/lib/orchestration/batch-stdin.js +107 -66
  83. package/dist/extensions/agent-browser/lib/orchestration/browser-run/artifact-merge.js +14 -6
  84. package/dist/extensions/agent-browser/lib/orchestration/browser-run/artifact-paths.js +109 -57
  85. package/dist/extensions/agent-browser/lib/orchestration/browser-run/browser-observation-result.js +82 -0
  86. package/dist/extensions/agent-browser/lib/orchestration/browser-run/click-dispatch.js +171 -57
  87. package/dist/extensions/agent-browser/lib/orchestration/browser-run/diagnostic-values.js +31 -0
  88. package/dist/extensions/agent-browser/lib/orchestration/browser-run/diagnostics.js +152 -781
  89. package/dist/extensions/agent-browser/lib/orchestration/browser-run/electron-observation.js +202 -0
  90. package/dist/extensions/agent-browser/lib/orchestration/browser-run/electron-text-diagnostics.js +109 -0
  91. package/dist/extensions/agent-browser/lib/orchestration/browser-run/fill-diagnostics.js +119 -0
  92. package/dist/extensions/agent-browser/lib/orchestration/browser-run/final-result-action-recovery.js +147 -0
  93. package/dist/extensions/agent-browser/lib/orchestration/browser-run/final-result-actions.js +144 -0
  94. package/dist/extensions/agent-browser/lib/orchestration/browser-run/final-result-content.js +123 -0
  95. package/dist/extensions/agent-browser/lib/orchestration/browser-run/final-result-contracts.js +1 -0
  96. package/dist/extensions/agent-browser/lib/orchestration/browser-run/final-result-details.js +156 -0
  97. package/dist/extensions/agent-browser/lib/orchestration/browser-run/final-result-electron.js +179 -0
  98. package/dist/extensions/agent-browser/lib/orchestration/browser-run/final-result-evidence.js +39 -0
  99. package/dist/extensions/agent-browser/lib/orchestration/browser-run/final-result-missing-binary.js +89 -0
  100. package/dist/extensions/agent-browser/lib/orchestration/browser-run/final-result-recovery.js +97 -0
  101. package/dist/extensions/agent-browser/lib/orchestration/browser-run/final-result-redaction.js +106 -0
  102. package/dist/extensions/agent-browser/lib/orchestration/browser-run/final-result-timeout.js +110 -0
  103. package/dist/extensions/agent-browser/lib/orchestration/browser-run/final-result.js +41 -538
  104. package/dist/extensions/agent-browser/lib/orchestration/browser-run/index.js +204 -108
  105. package/dist/extensions/agent-browser/lib/orchestration/browser-run/interaction-diagnostics.js +290 -0
  106. package/dist/extensions/agent-browser/lib/orchestration/browser-run/managed-session-close.js +167 -0
  107. package/dist/extensions/agent-browser/lib/orchestration/browser-run/managed-session-daemon-inspection.js +108 -0
  108. package/dist/extensions/agent-browser/lib/orchestration/browser-run/managed-session-daemon-policy.js +127 -199
  109. package/dist/extensions/agent-browser/lib/orchestration/browser-run/native-helper-observation.js +65 -0
  110. package/dist/extensions/agent-browser/lib/orchestration/browser-run/observation-types.js +1 -0
  111. package/dist/extensions/agent-browser/lib/orchestration/browser-run/overlay-diagnostics.js +120 -0
  112. package/dist/extensions/agent-browser/lib/orchestration/browser-run/prepare/network-page-filter.js +113 -30
  113. package/dist/extensions/agent-browser/lib/orchestration/browser-run/prepare/scroll-shims.js +109 -28
  114. package/dist/extensions/agent-browser/lib/orchestration/browser-run/prepare/snapshot-filter-data.js +150 -0
  115. package/dist/extensions/agent-browser/lib/orchestration/browser-run/prepare/snapshot-filter.js +138 -253
  116. package/dist/extensions/agent-browser/lib/orchestration/browser-run/prepare/snapshot-rendered-text.js +147 -0
  117. package/dist/extensions/agent-browser/lib/orchestration/browser-run/prepare/wait-timeouts.js +59 -24
  118. package/dist/extensions/agent-browser/lib/orchestration/browser-run/prepare-artifacts.js +159 -0
  119. package/dist/extensions/agent-browser/lib/orchestration/browser-run/prepare-command.js +131 -0
  120. package/dist/extensions/agent-browser/lib/orchestration/browser-run/prepare-contracts.js +1 -0
  121. package/dist/extensions/agent-browser/lib/orchestration/browser-run/prepare-daemon.js +93 -0
  122. package/dist/extensions/agent-browser/lib/orchestration/browser-run/prepare-failure.js +42 -0
  123. package/dist/extensions/agent-browser/lib/orchestration/browser-run/prepare-guards.js +242 -0
  124. package/dist/extensions/agent-browser/lib/orchestration/browser-run/prepare-input.js +75 -0
  125. package/dist/extensions/agent-browser/lib/orchestration/browser-run/prepare-observations.js +92 -0
  126. package/dist/extensions/agent-browser/lib/orchestration/browser-run/prepare-page-selection.js +254 -0
  127. package/dist/extensions/agent-browser/lib/orchestration/browser-run/prepare-page-state.js +121 -0
  128. package/dist/extensions/agent-browser/lib/orchestration/browser-run/prepare-refs.js +130 -0
  129. package/dist/extensions/agent-browser/lib/orchestration/browser-run/prepare-resources.js +114 -0
  130. package/dist/extensions/agent-browser/lib/orchestration/browser-run/prepare-semantic.js +121 -0
  131. package/dist/extensions/agent-browser/lib/orchestration/browser-run/prepare-session-plan.js +222 -0
  132. package/dist/extensions/agent-browser/lib/orchestration/browser-run/prepare-timeouts.js +68 -0
  133. package/dist/extensions/agent-browser/lib/orchestration/browser-run/prepare.js +176 -1114
  134. package/dist/extensions/agent-browser/lib/orchestration/browser-run/process-output-analysis.js +191 -0
  135. package/dist/extensions/agent-browser/lib/orchestration/browser-run/process-output-confirmation.js +152 -0
  136. package/dist/extensions/agent-browser/lib/orchestration/browser-run/process-output-diagnostics.js +182 -0
  137. package/dist/extensions/agent-browser/lib/orchestration/browser-run/process-output-electron.js +150 -0
  138. package/dist/extensions/agent-browser/lib/orchestration/browser-run/process-output-lifecycle-contracts.js +1 -0
  139. package/dist/extensions/agent-browser/lib/orchestration/browser-run/process-output-lifecycle-phase-contracts.js +1 -0
  140. package/dist/extensions/agent-browser/lib/orchestration/browser-run/process-output-lifecycle-phase.js +115 -0
  141. package/dist/extensions/agent-browser/lib/orchestration/browser-run/process-output-lifecycle.js +256 -0
  142. package/dist/extensions/agent-browser/lib/orchestration/browser-run/process-output-managed-contracts.js +1 -0
  143. package/dist/extensions/agent-browser/lib/orchestration/browser-run/process-output-managed.js +256 -0
  144. package/dist/extensions/agent-browser/lib/orchestration/browser-run/process-output-native-phase-contracts.js +1 -0
  145. package/dist/extensions/agent-browser/lib/orchestration/browser-run/process-output-native-phase.js +93 -0
  146. package/dist/extensions/agent-browser/lib/orchestration/browser-run/process-output-native.js +113 -0
  147. package/dist/extensions/agent-browser/lib/orchestration/browser-run/process-output-navigation-contracts.js +1 -0
  148. package/dist/extensions/agent-browser/lib/orchestration/browser-run/process-output-navigation.js +316 -0
  149. package/dist/extensions/agent-browser/lib/orchestration/browser-run/process-output-ownership.js +28 -0
  150. package/dist/extensions/agent-browser/lib/orchestration/browser-run/process-output-page-phase-contracts.js +1 -0
  151. package/dist/extensions/agent-browser/lib/orchestration/browser-run/process-output-page-phase.js +142 -0
  152. package/dist/extensions/agent-browser/lib/orchestration/browser-run/process-output-presentation-contracts.js +1 -0
  153. package/dist/extensions/agent-browser/lib/orchestration/browser-run/process-output-presentation.js +333 -0
  154. package/dist/extensions/agent-browser/lib/orchestration/browser-run/process-output-publication-phase-contracts.js +1 -0
  155. package/dist/extensions/agent-browser/lib/orchestration/browser-run/process-output-publication-phase.js +71 -0
  156. package/dist/extensions/agent-browser/lib/orchestration/browser-run/process-output-publication.js +201 -0
  157. package/dist/extensions/agent-browser/lib/orchestration/browser-run/process-output-receipts.js +183 -0
  158. package/dist/extensions/agent-browser/lib/orchestration/browser-run/process-output-refs.js +200 -0
  159. package/dist/extensions/agent-browser/lib/orchestration/browser-run/process-output-tabs.js +142 -0
  160. package/dist/extensions/agent-browser/lib/orchestration/browser-run/process-output.js +18 -910
  161. package/dist/extensions/agent-browser/lib/orchestration/browser-run/prompt-guards.js +23 -13
  162. package/dist/extensions/agent-browser/lib/orchestration/browser-run/recording-receipt-reconciliation.js +198 -0
  163. package/dist/extensions/agent-browser/lib/orchestration/browser-run/recording-recovery-contracts.js +1 -0
  164. package/dist/extensions/agent-browser/lib/orchestration/browser-run/recording-recovery-presentation.js +154 -0
  165. package/dist/extensions/agent-browser/lib/orchestration/browser-run/recording-recovery.js +68 -151
  166. package/dist/extensions/agent-browser/lib/orchestration/browser-run/screenshot-capture.js +14 -0
  167. package/dist/extensions/agent-browser/lib/orchestration/browser-run/screenshot-observation.js +169 -46
  168. package/dist/extensions/agent-browser/lib/orchestration/browser-run/session-state-commands.js +130 -0
  169. package/dist/extensions/agent-browser/lib/orchestration/browser-run/session-state-electron.js +210 -0
  170. package/dist/extensions/agent-browser/lib/orchestration/browser-run/session-state-observations.js +61 -0
  171. package/dist/extensions/agent-browser/lib/orchestration/browser-run/session-state-outcomes.js +187 -0
  172. package/dist/extensions/agent-browser/lib/orchestration/browser-run/session-state-refs.js +171 -0
  173. package/dist/extensions/agent-browser/lib/orchestration/browser-run/session-state-tabs.js +228 -0
  174. package/dist/extensions/agent-browser/lib/orchestration/browser-run/session-state.js +77 -753
  175. package/dist/extensions/agent-browser/lib/orchestration/browser-run/text-visibility-diagnostics.js +182 -0
  176. package/dist/extensions/agent-browser/lib/orchestration/browser-run/timeout-diagnostics.js +256 -0
  177. package/dist/extensions/agent-browser/lib/orchestration/browser-run/timeout-progress.js +108 -0
  178. package/dist/extensions/agent-browser/lib/orchestration/code-artifact-observation.js +39 -0
  179. package/dist/extensions/agent-browser/lib/orchestration/code-image-observation.js +119 -0
  180. package/dist/extensions/agent-browser/lib/orchestration/electron-host/branch.js +92 -0
  181. package/dist/extensions/agent-browser/lib/orchestration/electron-host/cleanup-result.js +58 -0
  182. package/dist/extensions/agent-browser/lib/orchestration/electron-host/cleanup.js +78 -0
  183. package/dist/extensions/agent-browser/lib/orchestration/electron-host/contracts.js +1 -0
  184. package/dist/extensions/agent-browser/lib/orchestration/electron-host/discovery.js +106 -0
  185. package/dist/extensions/agent-browser/lib/orchestration/electron-host/index.js +48 -816
  186. package/dist/extensions/agent-browser/lib/orchestration/electron-host/policy.js +86 -0
  187. package/dist/extensions/agent-browser/lib/orchestration/electron-host/probe-collection.js +69 -0
  188. package/dist/extensions/agent-browser/lib/orchestration/electron-host/probe-data.js +167 -0
  189. package/dist/extensions/agent-browser/lib/orchestration/electron-host/probe-presentation.js +164 -0
  190. package/dist/extensions/agent-browser/lib/orchestration/electron-host/probe.js +161 -0
  191. package/dist/extensions/agent-browser/lib/orchestration/electron-host/status.js +165 -0
  192. package/dist/extensions/agent-browser/lib/orchestration/execution-queue.js +21 -9
  193. package/dist/extensions/agent-browser/lib/orchestration/extension-artifact-preflight.js +211 -0
  194. package/dist/extensions/agent-browser/lib/orchestration/extension-artifacts.js +23 -0
  195. package/dist/extensions/agent-browser/lib/orchestration/extension-attachment-replay.js +99 -0
  196. package/dist/extensions/agent-browser/lib/orchestration/extension-branch-restore.js +275 -0
  197. package/dist/extensions/agent-browser/lib/orchestration/extension-code.js +280 -0
  198. package/dist/extensions/agent-browser/lib/orchestration/extension-command-admission.js +303 -0
  199. package/dist/extensions/agent-browser/lib/orchestration/extension-command-output.js +36 -0
  200. package/dist/extensions/agent-browser/lib/orchestration/extension-command-result.js +335 -0
  201. package/dist/extensions/agent-browser/lib/orchestration/extension-command-run.js +227 -0
  202. package/dist/extensions/agent-browser/lib/orchestration/extension-command-state.js +1 -0
  203. package/dist/extensions/agent-browser/lib/orchestration/extension-electron-ownership.js +204 -0
  204. package/dist/extensions/agent-browser/lib/orchestration/extension-execution-locks.js +139 -0
  205. package/dist/extensions/agent-browser/lib/orchestration/extension-execution-queue.js +24 -0
  206. package/dist/extensions/agent-browser/lib/orchestration/extension-host-coordination.js +98 -0
  207. package/dist/extensions/agent-browser/lib/orchestration/extension-host-run.js +295 -0
  208. package/dist/extensions/agent-browser/lib/orchestration/extension-intent-replay.js +41 -0
  209. package/dist/extensions/agent-browser/lib/orchestration/extension-invocation.js +7 -0
  210. package/dist/extensions/agent-browser/lib/orchestration/extension-lifecycle.js +102 -0
  211. package/dist/extensions/agent-browser/lib/orchestration/extension-managed-ownership.js +133 -0
  212. package/dist/extensions/agent-browser/lib/orchestration/extension-observation.js +120 -0
  213. package/dist/extensions/agent-browser/lib/orchestration/extension-prompt.js +180 -0
  214. package/dist/extensions/agent-browser/lib/orchestration/extension-recording.js +290 -0
  215. package/dist/extensions/agent-browser/lib/orchestration/extension-resource-contracts.js +1 -0
  216. package/dist/extensions/agent-browser/lib/orchestration/extension-resource-replay.js +269 -0
  217. package/dist/extensions/agent-browser/lib/orchestration/extension-result-state.js +113 -0
  218. package/dist/extensions/agent-browser/lib/orchestration/extension-runtime.js +146 -0
  219. package/dist/extensions/agent-browser/lib/orchestration/extension-script-leases.js +58 -0
  220. package/dist/extensions/agent-browser/lib/orchestration/extension-tool-boundary.js +62 -0
  221. package/dist/extensions/agent-browser/lib/orchestration/extension-version-check.js +54 -0
  222. package/dist/extensions/agent-browser/lib/orchestration/input-plan-types.js +1 -0
  223. package/dist/extensions/agent-browser/lib/orchestration/input-plan.js +261 -185
  224. package/dist/extensions/agent-browser/lib/orchestration/input-redaction.js +62 -0
  225. package/dist/extensions/agent-browser/lib/orchestration/native-config.js +144 -0
  226. package/dist/extensions/agent-browser/lib/orchestration/native-root-launch.js +77 -0
  227. package/dist/extensions/agent-browser/lib/orchestration/native-session-defaults.js +210 -139
  228. package/dist/extensions/agent-browser/lib/orchestration/operation-paths.js +124 -58
  229. package/dist/extensions/agent-browser/lib/orchestration/output-file.js +198 -98
  230. package/dist/extensions/agent-browser/lib/orchestration/script-mode.js +199 -96
  231. package/dist/extensions/agent-browser/lib/owned-managed-session-context.js +55 -0
  232. package/dist/extensions/agent-browser/lib/page-target-batch.js +118 -0
  233. package/dist/extensions/agent-browser/lib/page-target-guards.js +50 -0
  234. package/dist/extensions/agent-browser/lib/page-target-navigation.js +104 -0
  235. package/dist/extensions/agent-browser/lib/page-target-validation.js +59 -243
  236. package/dist/extensions/agent-browser/lib/parsing.js +13 -4
  237. package/dist/extensions/agent-browser/lib/pi-tool-rendering.js +134 -68
  238. package/dist/extensions/agent-browser/lib/playbook.js +18 -14
  239. package/dist/extensions/agent-browser/lib/process-child.js +284 -0
  240. package/dist/extensions/agent-browser/lib/process-environment.js +22 -6
  241. package/dist/extensions/agent-browser/lib/process-errors.js +23 -0
  242. package/dist/extensions/agent-browser/lib/process-identity.js +47 -15
  243. package/dist/extensions/agent-browser/lib/process-socket-storage.js +256 -0
  244. package/dist/extensions/agent-browser/lib/process-stdout.js +74 -0
  245. package/dist/extensions/agent-browser/lib/process.js +146 -537
  246. package/dist/extensions/agent-browser/lib/prompt-artifacts.js +287 -0
  247. package/dist/extensions/agent-browser/lib/prompt-policy.js +15 -194
  248. package/dist/extensions/agent-browser/lib/read-command.js +41 -0
  249. package/dist/extensions/agent-browser/lib/read-confirmation.js +138 -35
  250. package/dist/extensions/agent-browser/lib/recording-reservations.js +118 -45
  251. package/dist/extensions/agent-browser/lib/redaction-fields.js +75 -0
  252. package/dist/extensions/agent-browser/lib/redaction-json.js +149 -0
  253. package/dist/extensions/agent-browser/lib/redaction-url.js +88 -0
  254. package/dist/extensions/agent-browser/lib/results/action-contracts.js +1 -0
  255. package/dist/extensions/agent-browser/lib/results/action-recommendations.js +28 -271
  256. package/dist/extensions/agent-browser/lib/results/artifact-contracts.js +1 -0
  257. package/dist/extensions/agent-browser/lib/results/artifact-manifest-validation.js +133 -0
  258. package/dist/extensions/agent-browser/lib/results/artifact-manifest.js +96 -94
  259. package/dist/extensions/agent-browser/lib/results/artifact-recommendations.js +73 -0
  260. package/dist/extensions/agent-browser/lib/results/categories.js +111 -54
  261. package/dist/extensions/agent-browser/lib/results/confirmation.js +29 -10
  262. package/dist/extensions/agent-browser/lib/results/editable-ref-evidence.js +62 -27
  263. package/dist/extensions/agent-browser/lib/results/electron-recommendations.js +83 -0
  264. package/dist/extensions/agent-browser/lib/results/envelope-decoding.js +48 -0
  265. package/dist/extensions/agent-browser/lib/results/envelope.js +93 -66
  266. package/dist/extensions/agent-browser/lib/results/evidence-contracts.js +1 -0
  267. package/dist/extensions/agent-browser/lib/results/failure-recommendations.js +180 -0
  268. package/dist/extensions/agent-browser/lib/results/network-routes.js +86 -45
  269. package/dist/extensions/agent-browser/lib/results/network.js +35 -12
  270. package/dist/extensions/agent-browser/lib/results/next-actions.js +49 -19
  271. package/dist/extensions/agent-browser/lib/results/presentation/artifact-files.js +320 -0
  272. package/dist/extensions/agent-browser/lib/results/presentation/artifact-format.js +138 -0
  273. package/dist/extensions/agent-browser/lib/results/presentation/artifact-images.js +113 -0
  274. package/dist/extensions/agent-browser/lib/results/presentation/artifact-verification.js +145 -0
  275. package/dist/extensions/agent-browser/lib/results/presentation/artifacts.js +99 -552
  276. package/dist/extensions/agent-browser/lib/results/presentation/batch-contracts.js +1 -0
  277. package/dist/extensions/agent-browser/lib/results/presentation/batch-recording.js +118 -0
  278. package/dist/extensions/agent-browser/lib/results/presentation/batch-redaction.js +68 -0
  279. package/dist/extensions/agent-browser/lib/results/presentation/batch-rendering.js +135 -0
  280. package/dist/extensions/agent-browser/lib/results/presentation/batch-step.js +227 -0
  281. package/dist/extensions/agent-browser/lib/results/presentation/batch-summary.js +91 -0
  282. package/dist/extensions/agent-browser/lib/results/presentation/batch.js +91 -460
  283. package/dist/extensions/agent-browser/lib/results/presentation/browser-profile-recovery.js +9 -5
  284. package/dist/extensions/agent-browser/lib/results/presentation/command-presenters.js +216 -0
  285. package/dist/extensions/agent-browser/lib/results/presentation/common.js +26 -9
  286. package/dist/extensions/agent-browser/lib/results/presentation/content.js +86 -29
  287. package/dist/extensions/agent-browser/lib/results/presentation/diagnostic-a11y.js +67 -0
  288. package/dist/extensions/agent-browser/lib/results/presentation/diagnostic-health.js +79 -0
  289. package/dist/extensions/agent-browser/lib/results/presentation/diagnostic-identity.js +199 -0
  290. package/dist/extensions/agent-browser/lib/results/presentation/diagnostic-logs.js +75 -0
  291. package/dist/extensions/agent-browser/lib/results/presentation/diagnostic-network-actions.js +216 -0
  292. package/dist/extensions/agent-browser/lib/results/presentation/diagnostic-network.js +124 -0
  293. package/dist/extensions/agent-browser/lib/results/presentation/diagnostic-redaction.js +64 -0
  294. package/dist/extensions/agent-browser/lib/results/presentation/diagnostic-storage.js +209 -0
  295. package/dist/extensions/agent-browser/lib/results/presentation/diagnostic-stream.js +69 -0
  296. package/dist/extensions/agent-browser/lib/results/presentation/diagnostic-summary.js +222 -0
  297. package/dist/extensions/agent-browser/lib/results/presentation/diagnostics.js +103 -1019
  298. package/dist/extensions/agent-browser/lib/results/presentation/early-result.js +70 -0
  299. package/dist/extensions/agent-browser/lib/results/presentation/errors.js +130 -60
  300. package/dist/extensions/agent-browser/lib/results/presentation/input-contracts.js +1 -0
  301. package/dist/extensions/agent-browser/lib/results/presentation/large-output.js +60 -145
  302. package/dist/extensions/agent-browser/lib/results/presentation/navigation.js +147 -88
  303. package/dist/extensions/agent-browser/lib/results/presentation/notices.js +75 -0
  304. package/dist/extensions/agent-browser/lib/results/presentation/observation-contracts.js +1 -0
  305. package/dist/extensions/agent-browser/lib/results/presentation/observation-rendering.js +127 -0
  306. package/dist/extensions/agent-browser/lib/results/presentation/outcomes.js +120 -0
  307. package/dist/extensions/agent-browser/lib/results/presentation/output-completion.js +77 -0
  308. package/dist/extensions/agent-browser/lib/results/presentation/output-spill.js +51 -0
  309. package/dist/extensions/agent-browser/lib/results/presentation/registry.js +117 -237
  310. package/dist/extensions/agent-browser/lib/results/presentation/semantic-action.js +35 -21
  311. package/dist/extensions/agent-browser/lib/results/presentation/skills.js +104 -73
  312. package/dist/extensions/agent-browser/lib/results/presentation/source.js +109 -0
  313. package/dist/extensions/agent-browser/lib/results/presentation.js +17 -248
  314. package/dist/extensions/agent-browser/lib/results/recommendation-contracts.js +1 -0
  315. package/dist/extensions/agent-browser/lib/results/recording.js +52 -14
  316. package/dist/extensions/agent-browser/lib/results/recovery-actions.js +14 -5
  317. package/dist/extensions/agent-browser/lib/results/recovery-next-actions.js +30 -22
  318. package/dist/extensions/agent-browser/lib/results/selector-recovery-target.js +83 -0
  319. package/dist/extensions/agent-browser/lib/results/selector-recovery.js +123 -123
  320. package/dist/extensions/agent-browser/lib/results/snapshot-compact.js +266 -0
  321. package/dist/extensions/agent-browser/lib/results/snapshot-content.js +32 -0
  322. package/dist/extensions/agent-browser/lib/results/snapshot-high-value-controls.js +104 -71
  323. package/dist/extensions/agent-browser/lib/results/snapshot-refs.js +31 -11
  324. package/dist/extensions/agent-browser/lib/results/snapshot-segments.js +125 -66
  325. package/dist/extensions/agent-browser/lib/results/snapshot-spill.js +26 -7
  326. package/dist/extensions/agent-browser/lib/results/snapshot.js +28 -248
  327. package/dist/extensions/agent-browser/lib/results/text.js +16 -5
  328. package/dist/extensions/agent-browser/lib/runtime-args-validation.js +133 -0
  329. package/dist/extensions/agent-browser/lib/runtime-compatibility.js +81 -0
  330. package/dist/extensions/agent-browser/lib/runtime-contracts.js +1 -0
  331. package/dist/extensions/agent-browser/lib/runtime-redaction.js +118 -0
  332. package/dist/extensions/agent-browser/lib/runtime-replay-events.js +144 -0
  333. package/dist/extensions/agent-browser/lib/runtime-session-identity.js +76 -0
  334. package/dist/extensions/agent-browser/lib/runtime-session-plan.js +114 -0
  335. package/dist/extensions/agent-browser/lib/runtime-session-replay.js +123 -0
  336. package/dist/extensions/agent-browser/lib/runtime-tab-correction.js +65 -0
  337. package/dist/extensions/agent-browser/lib/runtime-timeouts.js +28 -0
  338. package/dist/extensions/agent-browser/lib/runtime.js +137 -1037
  339. package/dist/extensions/agent-browser/lib/session-identity.js +51 -0
  340. package/dist/extensions/agent-browser/lib/session-page-observation.js +357 -0
  341. package/dist/extensions/agent-browser/lib/session-page-state.js +188 -324
  342. package/dist/extensions/agent-browser/lib/session-page-types.js +1 -0
  343. package/dist/extensions/agent-browser/lib/temp-artifact-budget.js +78 -0
  344. package/dist/extensions/agent-browser/lib/temp-mutation-queue.js +7 -0
  345. package/dist/extensions/agent-browser/lib/temp-root-ownership.js +234 -0
  346. package/dist/extensions/agent-browser/lib/temp-root.js +207 -0
  347. package/dist/extensions/agent-browser/lib/temp.js +33 -446
  348. package/dist/extensions/agent-browser/lib/tool-surface.js +94 -24
  349. package/dist/extensions/agent-browser/lib/upstream-version.js +3 -2
  350. package/dist/extensions/agent-browser/lib/web-search-providers.js +229 -0
  351. package/dist/extensions/agent-browser/lib/web-search-request.js +108 -0
  352. package/dist/extensions/agent-browser/lib/web-search-results.js +281 -0
  353. package/dist/extensions/agent-browser/lib/web-search-schema.js +82 -0
  354. package/dist/extensions/agent-browser/lib/web-search.js +109 -617
  355. package/dist/extensions/agent-browser/lib/webmcp-observation.js +13 -6
  356. package/dist/extensions/agent-browser/lib/windows-stock-launcher.js +63 -37
  357. package/dist/extensions/agent-browser/script-worker.js +80 -43
  358. package/dist/scripts/agent-browser-target.mjs +4 -2
  359. package/docs/ARCHITECTURE.md +22 -10
  360. package/docs/CODE_QUALITY.md +242 -0
  361. package/docs/COMMAND_REFERENCE.md +264 -229
  362. package/docs/ELECTRON.md +53 -44
  363. package/docs/RELEASE.md +21 -17
  364. package/docs/REQUIREMENTS.md +2 -0
  365. package/docs/SESSION_STORAGE.md +1 -1
  366. package/docs/SUPPORT_MATRIX.md +84 -77
  367. package/docs/TOOL_CONTRACT.md +165 -130
  368. package/docs/platform-smoke.md +5 -5
  369. package/package.json +143 -120
  370. package/scripts/agent-browser-capability-baseline.mjs +361 -957
  371. package/scripts/agent-browser-target.mjs +6 -2
  372. package/scripts/build.mjs +37 -8
  373. package/scripts/capability-core-commands.mjs +193 -0
  374. package/scripts/capability-options.mjs +283 -0
  375. package/scripts/capability-samples.mjs +133 -0
  376. package/scripts/capability-section.mjs +11 -0
  377. package/scripts/config.mjs +213 -114
  378. package/scripts/convert-browser-session.mjs +30 -9
  379. package/scripts/doctor-sources.mjs +195 -0
  380. package/scripts/doctor.mjs +92 -247
  381. package/scripts/platform-smoke/artifacts.mjs +38 -11
  382. package/scripts/platform-smoke/commands.mjs +104 -0
  383. package/scripts/platform-smoke/crabbox-runner.mjs +167 -80
  384. package/scripts/platform-smoke/doctor-support.mjs +157 -0
  385. package/scripts/platform-smoke/doctor-windows.mjs +230 -0
  386. package/scripts/platform-smoke/doctor.mjs +212 -320
  387. package/scripts/platform-smoke/lease-evidence.mjs +134 -0
  388. package/scripts/platform-smoke/suite-checks.mjs +98 -0
  389. package/scripts/platform-smoke/suite-evidence.mjs +281 -0
  390. package/scripts/platform-smoke/targets.mjs +158 -472
  391. package/scripts/platform-smoke.mjs +55 -40
  392. package/scripts/prepare.mjs +16 -7
@@ -3,6 +3,7 @@
3
3
  Root browser groups use native named sessions plus per-root restore, with scoped Chrome profile-name bootstrap from existing package config. `test/agent-browser.shared-defaults.test.ts` covers root separation, descendant routing, exact root-name follow-ups, helper launch consistency, explicit overrides, and quit ownership; the companion pi-subagents tests cover foreground/detached launch and saved revive identity. Native JSON restore supports cookies and web storage, not new IndexedDB-only or memory credentials. Real SDK/native-browser restart and concurrency evidence is required for this boundary; a profile metadata match alone is not login proof.
4
4
 
5
5
  Related docs:
6
+
6
7
  - [`../README.md`](../README.md)
7
8
  - [`../AGENTS.md`](https://github.com/fitchmultz/pi-agent-browser-native/blob/main/AGENTS.md) (rebaselining and verification stack)
8
9
  - [`COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md)
@@ -28,21 +29,23 @@ When upstream ships a new `agent-browser` or the inventory changes:
28
29
 
29
30
  ## Current browser contract
30
31
 
32
+ Native text and artifact ownership: the registered artifact owner covers empty-row screenshot alignment, nonscreenshot placeholders and bail truncation; the upgrade owner covers one-copy failed explicit text. The text/presentation owners cover cookie/storage format redaction across content, details, complete spills and exports, effective raw/stdin batch intent and native JSON all-entry maps. Real-native cases exercise screenshot paths, explicit/shorthand sensitive-key storage reads, empty-name cookies and CLI true/false helper continuity over opposite env/config defaults. Debug false creates no native log with clean or opposite defaults; later calls retain native inheritance. Native unescaped multiline all-entry/raw-batch text retains the documented heuristic ceiling; structured JSON provides the unambiguous storage boundary.
33
+
31
34
  The compact direct/code/loader surface replaces public multimode inputs while retaining native commands and advanced outcomes. This section describes the implementation contract; dated evidence below does not qualify new Pi 1.0 code.
32
35
 
33
- | Area | Contract and verification target |
34
- | --- | --- |
35
- | RQ-0064 fixed workflows | Public job DSL removed; native `batch --bail` preserves fixed ordering, waits, explicit assertions, paced keyboard/wait rows, and timeout partial progress. Code handles branches/loops. |
36
- | RQ-0065 QA | Flat `agent_browser_qa` preserves visible assertions, attached-buffer scope, diagnostic residue ambiguity, actionable/benign classification, and actual pass/fail. Fail-fast receipts separate failed checks from later `notRunChecks`; incomplete/timeout evidence stays unverified and execution counts without receipts remain unknown. |
37
- | RQ-0066 / RQ-0067 source | Flat source/network tools retain bounded host scans and candidates-only semantics even in browser-only hosts. |
38
- | RQ-0068 recipes | No recipe registry, persistent JavaScript, second driver, or interpreter dependency. |
39
- | RQ-0096 Electron | Flat lifecycle tool preserves app/process/profile ownership and cancellation; native browser/code operations reuse its returned session. |
40
- | RQ-0142 code | Fresh permissioned Node child over persistent parent-selected browser; explicit JSON/current-cell image output, visible failures/counts, ordinary auth/config/environment, ordered Pi intent/completion transitions, child cancellation/reaping, no legacy public execution. |
41
- | Hotpath boundaries | Unrelated tools/harmless Bash return before prompt policy. Latest raw user intent is seeded on start/tree, updated by `message_end` and refreshed after native content replacement. Captured admission uses a validated append-only prefix; one queued replay restores branch/lease state and folds per-session launch settings once. Per-row renderer memoization skips unchanged formatting. No broad config/trust/history cache, new wait/timer or budget increase. |
42
- | Shared ordering | Actual socket/namespace/session lock spans helper/action or entire cell; sorted identity sets for replacement/cleanup and namespace barrier for direct close-all. Requires every participating Pi to run the updated package; no human/third-party/older-version guarantee or transaction. |
43
- | Lightpanda engine | Chrome remains default; separately installed Lightpanda is opt-in. `--engine` uses existing managed fresh-launch recovery; effective CLI/env/config Lightpanda omits wrapper Chrome profile/executable defaults while preserving native choices. Positively identified images are text-rendered with unknown geometry, not visual/coordinate parity. No automatic fallback. `test/agent-browser.runtime.test.ts`, `test/agent-browser.shared-defaults.test.ts`, and `test/agent-browser.screenshot-geometry.test.ts` own the regressions; [limits](COMMAND_REFERENCE.md#lightpanda-engine). |
44
- | Observation and geometry | Canonical bounded JSON/prose/code/native `structuredContent` observations expose exact recovery and receipts, with native namespace/output-schema metadata and canonical returned `isError`; complete observation spills preserve large output. Image dimensions/CSS viewport/DPR/crop/scroll/frame evidence is measured or explicitly unknown; no viewport-coordinate assumptions for full-page/element images. |
45
- | Pi integration | Pi 1.0 floor with independently qualified official/fork graphs. Five advanced direct tools use native `defaultActive: false`; a narrow additive initial-resume fallback preserves available transcript selections without overriding explicit/defaultTools/filtered host selection. Loader/tree/reload retain native history; public `pi:instruction-groups` registration supplies one full `browser` instruction source. Managed hosts own deferred delivery; unmanaged/stock hosts receive identical full eager guidance even for generic prompts. No permission widening or legacy discovery metadata. `test/agent-browser.discovery.test.ts` covers full-text parity, dynamic ownership, and startup/late registration; tool-surface tests preserve host selections, with pipeline coverage in `test/agent-browser.pi-pipeline.test.ts`. No checkpoint or fork metadata/revision APIs, provider payload edits or image-detail overrides. |
36
+ | Area | Contract and verification target |
37
+ | ------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
38
+ | RQ-0064 fixed workflows | Public job DSL removed; native `batch --bail` preserves fixed ordering, waits, explicit assertions, paced keyboard/wait rows, and timeout partial progress. Code handles branches/loops. |
39
+ | RQ-0065 QA | Flat `agent_browser_qa` preserves visible assertions, attached-buffer scope, diagnostic residue ambiguity, actionable/benign classification, and actual pass/fail. Fail-fast receipts separate failed checks from later `notRunChecks`; incomplete/timeout evidence stays unverified and execution counts without receipts remain unknown. |
40
+ | RQ-0066 / RQ-0067 source | Flat source/network tools retain bounded host scans and candidates-only semantics even in browser-only hosts. |
41
+ | RQ-0068 recipes | No recipe registry, persistent JavaScript, second driver, or interpreter dependency. |
42
+ | RQ-0096 Electron | Flat lifecycle tool preserves app/process/profile ownership and cancellation; native browser/code operations reuse its returned session. |
43
+ | RQ-0142 code | Fresh permissioned Node child over persistent parent-selected browser; explicit JSON/current-cell image output, visible failures/counts, ordinary auth/config/environment, ordered Pi intent/completion transitions, child cancellation/reaping, no legacy public execution. |
44
+ | Hotpath boundaries | Unrelated tools/harmless Bash return before prompt policy. Latest raw user intent is seeded on start/tree, updated by `message_end` and refreshed after native content replacement. Captured admission uses a validated append-only prefix; one queued replay restores branch/lease state and folds per-session launch settings once. Per-row renderer memoization skips unchanged formatting. No broad config/trust/history cache, new wait/timer or budget increase. |
45
+ | Shared ordering | Actual socket/namespace/session lock spans helper/action or entire cell; sorted identity sets for replacement/cleanup and namespace barrier for direct close-all. Requires every participating Pi to run the updated package; no human/third-party/older-version guarantee or transaction. |
46
+ | Lightpanda engine | Chrome remains default; separately installed Lightpanda is opt-in. `--engine` uses existing managed fresh-launch recovery; effective CLI/env/config Lightpanda omits wrapper Chrome profile/executable defaults while preserving native choices. Positively identified images are text-rendered with unknown geometry, not visual/coordinate parity. No automatic fallback. `test/agent-browser.runtime.test.ts`, `test/agent-browser.shared-defaults.test.ts`, and `test/agent-browser.screenshot-geometry.test.ts` own the regressions; [limits](COMMAND_REFERENCE.md#lightpanda-engine). |
47
+ | Observation and geometry | Canonical bounded JSON/prose/code/native `structuredContent` observations expose exact recovery and receipts, with native namespace/output-schema metadata and canonical returned `isError`; complete observation spills preserve large output. Image dimensions/CSS viewport/DPR/crop/scroll/frame evidence is measured or explicitly unknown; no viewport-coordinate assumptions for full-page/element images. |
48
+ | Pi integration | Pi 1.0 floor with independently qualified official/fork graphs. Five advanced direct tools use native `defaultActive: false`; a narrow additive initial-resume fallback preserves available transcript selections without overriding explicit/defaultTools/filtered host selection. Loader/tree/reload retain native history; public `pi:instruction-groups` registration supplies one full `browser` instruction source. Managed hosts own deferred delivery; unmanaged/stock hosts receive identical full eager guidance even for generic prompts. No permission widening or legacy discovery metadata. `test/agent-browser.discovery.test.ts` covers full-text parity, dynamic ownership, and startup/late registration; tool-surface tests preserve host selections, with pipeline coverage in `test/agent-browser.pi-pipeline.test.ts`. No checkpoint or fork metadata/revision APIs, provider payload edits or image-detail overrides. |
46
49
 
47
50
  See [migration](TOOL_CONTRACT.md#07-migration), [canonical observations](TOOL_CONTRACT.md#canonical-observation), and [release qualification/rollback](RELEASE.md#07-upgrade-and-rollback). Routine GitHub Actions runs official/fork Linux compatibility, a macOS packed-Pi smoke, and Native lifecycle Linux qualification on PRs to `main`; Windows CI is excluded. Release/platform evidence and review remain separate from these focused checks.
48
51
 
@@ -60,42 +63,44 @@ Closed feedback decisions map to their canonical contracts in [`docs/support-not
60
63
 
61
64
  Current summary:
62
65
 
63
- | Range | Status | Source of truth |
64
- | --- | --- | --- |
65
- | RQ-0110–RQ-0120 | Agent feedback triage resolved or documented; remaining unsupported areas are environment/upstream-owned. | [`docs/support-notes.md`](https://github.com/fitchmultz/pi-agent-browser-native/blob/main/docs/support-notes.md) |
66
- | RQ-0123–RQ-0127 | Stress-report wrapper fixes shipped; prompt-derived business-action blocking remains intentionally out of scope. | [`docs/support-notes.md`](https://github.com/fitchmultz/pi-agent-browser-native/blob/main/docs/support-notes.md) |
67
- | `agent-browser 0.27.2` baseline | Historical upstream rebaseline shipped; `RQ-0101` remains the compact-snapshot high-value-controls decision. | [`docs/support-notes.md`](https://github.com/fitchmultz/pi-agent-browser-native/blob/main/docs/support-notes.md) |
68
- | RQ-0128 | Upstream `agent-browser 0.27.3` install-only rebaseline shipped; no new wrapper capability adopted. | [`docs/support-notes.md`](https://github.com/fitchmultz/pi-agent-browser-native/blob/main/docs/support-notes.md) |
69
- | RQ-0129 | Upstream `agent-browser 0.29.1` rebaseline shipped; sandbox helpers are documented upstream package guidance, not a wrapper runtime. | [`docs/support-notes.md`](https://github.com/fitchmultz/pi-agent-browser-native/blob/main/docs/support-notes.md) |
70
- | RQ-0130 | Upstream `agent-browser 0.30.1` rebaseline shipped; `wait --url` glob support replaces the wrapper `job.assertUrl` predicate workaround. | [`docs/support-notes.md`](https://github.com/fitchmultz/pi-agent-browser-native/blob/main/docs/support-notes.md) |
71
- | RQ-0131 | Upstream `agent-browser 0.31.0` rebaseline shipped; restore workflow and namespace/session lifecycle globals are parsed, documented, and carried through wrapper-managed probes/state. | [`docs/COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#upstream-0310-rebaseline) |
72
- | RQ-0132 | Upstream `agent-browser 0.31.1` rebaseline shipped; React renderer selection is upstream-fixed for `react tree`, `react inspect`, and `react suspense`, with no wrapper CLI/schema changes. | [`docs/COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#upstream-0311-rebaseline) |
73
- | RQ-0133 | Upstream `agent-browser 0.31.2` rebaseline adds WebGPU launch/doctor/MCP surfaces and periodic restore-state autosaves; wrapper launch parsing/policy and docs now cover both. | [`docs/COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#upstream-0312-rebaseline) |
74
- | RQ-0134 | Upstream `agent-browser 0.32.0` rebaseline hardens domain containment, fixes completed-page waits, and adds a separate eve extension package; wrapper launch policy and docs cover the relevant behavior. | [`docs/COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#upstream-0320-rebaseline) |
75
- | RQ-0135 | Upstream `agent-browser 0.32.2` rebaseline updates eve packaging only and closes the wrapper's prior missing `read [url]` inventory/presentation contract. | [`docs/COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#upstream-0322-rebaseline) |
76
- | RQ-0136 | Wrapper regression fix keeps helper subprocess launch environments stable, refreshes active tab state after `tab close`, and makes ordinary document-direction scrolling deterministic before upstream fallback. | [`docs/ARCHITECTURE.md`](ARCHITECTURE.md), [`docs/TOOL_CONTRACT.md`](TOOL_CONTRACT.md#details) |
77
- | RQ-0137 | Upstream `agent-browser 0.32.4` rebaseline adds HAR `--content` body modes, the `derive-client` skill, and fixed `find role` implicit-ARIA/name matching with locator-detail misses; wrapper classifier/argv/docs cover those surfaces. | [`docs/COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#upstream-0330-rebaseline) |
78
- | RQ-0138 | Upstream `agent-browser 0.33.0` rebaseline adds `a11y` axe-core audits and discarded-tab revival on tab switch; wrapper documents/presents `a11y` and samples the new help surface. | [`docs/COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#upstream-0330-rebaseline) |
79
- | RQ-0139 | Upstream `agent-browser 0.33.2` rebaseline documents daemon idle timeout, streaming controls, and tab recovery. Wrapper-owned implicit sessions add transcript/checkout-scoped automatic restore with current v4 set-valued ticket-claim daemon coordination, eight-candidate opportunistic cleanup with randomized first windows and in-process rotation, verified snapshot retention, and page-target verification after ambiguous transitions. Explicit sessions, state/restore paths, config, file access, launch environment, local pages, output paths, and close arguments pass through unchanged; session/state lists keep all rows and identifiers visible. | [`docs/COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#upstream-0332-rebaseline), [`docs/ARCHITECTURE.md`](ARCHITECTURE.md) |
80
- | RQ-0140 | Successful CDP/auto-connect and Electron sessions preserve one attached browser across native-tool follow-ups and cleanup by omitting wrapper local-launch defaults, with environment support, branch replay, first-use content blocking, live URL gates against external drift, and close cleanup. | [`docs/ARCHITECTURE.md`](ARCHITECTURE.md), [`docs/TOOL_CONTRACT.md`](TOOL_CONTRACT.md), `test/agent-browser.extension-passthrough-validation.test.ts` |
81
- | RQ-0141 | Headed managed sessions avoid upstream 0.33.2 visible autosave targets by default and retain that daemon environment across helpers, still-owned off-current follow-ups, failed-replacement ownership, Electron cleanup, and reload/resume; slow daemon-policy inspection uses a 35-second budget; headed mode is launch-scoped; the effective launch interval persists across resume and changes in either direction require close plus a fresh daemon; and bare, review-only, fenced-reference, conditional, directly negated, or reference attachment paths do not become close-blocking output requirements while explicit contiguous output path lists, per-clause availability, duplicate precedence, and Markdown destinations are handled conservatively and linearly. | [`docs/ARCHITECTURE.md`](ARCHITECTURE.md), [`docs/TOOL_CONTRACT.md`](TOOL_CONTRACT.md), `test/agent-browser.managed-session-daemon-policy.test.ts`, `test/agent-browser.process.test.ts`, `test/agent-browser.prompt-policy.test.ts` |
82
- | RQ-0142 | Persistent `agent_browser_code` uses the retained permissioned child and the same native executor as direct calls. Browser/auth state persists; JS state resets. Selected JSON/images, handled-failure receipts/counts, bounded IPC/deadline, shared whole-cell ordering, and ordered Pi transition replay replace isolated finally-close execution. The optional host `beforeExecute` callback retains outer call identity and serial dispatch. Strict old lease readers exist only for upgrade cleanup. | [`TOOL_CONTRACT.md`](TOOL_CONTRACT.md#agent_browser_code), [`ARCHITECTURE.md`](ARCHITECTURE.md#persistent-browser-code), `test/agent-browser.script.test.ts`, `test/agent-browser.tool-surface.test.ts`, `test/agent-browser.execution-lock.test.ts`, `test/agent-browser.execution-order.test.ts` |
83
- | RQ-0143 | Browser-backed calls require a stable upstream version at or above the configured 0.35.0 floor, report minimum/observed version mismatch before launch, and keep stateless/local diagnostics available; the recommended target and minimum are shared by runtime, docs verification, and package contents. | [`scripts/agent-browser-target.mjs`](../scripts/agent-browser-target.mjs), [`docs/COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#upstream-0360-rebaseline), `test/agent-browser.upstream-version.test.ts` |
84
- | RQ-0144 | Managed restore keys are scoped to both checkout generation and Pi transcript so upstream 0.33.2's newest-file-wins loading cannot let concurrent chats clobber or inherit cookies/storage. Fresh rotations, reload, restart, and `/resume` of one transcript retain continuity; after a confirmed inactive daemon, a branch-restored compatible owned session retains its pending reopen through daemon-starting non-page calls and transcript replay, then reopens the complete recorded URL (including its fragment) before current-page operations such as `get url` or `reload`, verifies the actual target and invalidates old refs. This reloads a URL, not forms, JavaScript memory, or history; live wrong-tab recovery never auto-navigates. Passive and explicit upstream configs pass through, while explicit config selection suppresses the wrapper's automatic restore injection. | [`docs/ARCHITECTURE.md`](ARCHITECTURE.md), [`docs/TOOL_CONTRACT.md`](TOOL_CONTRACT.md), `test/agent-browser.managed-session-restore.test.ts`, `test/agent-browser.real-upstream-contract.test.ts` |
85
- | RQ-0145 | Mega-dogfood correctness closes false-positive success paths: URL QA makes matched post-clear page-error evidence non-pass as unverified, counts definitely new errors separately, and waits 150 ms for immediate post-load diagnostics, stale pre-existing artifacts and missing/stale recordings finalized by restart fail verification, aliased destinations (including dangling symlinks, full macOS/Windows Unicode folds, final short/long diff output flags, and same-call `outputPath` aliases) and active recording-path reuse through artifacts, path-bearing HAR stops, long/short or reordered explicit download waits, interspersed-global command forms, Electron cleanup output, or normalized output writes is rejected through an atomic process-wide, transcript-backed namespace/session reservation index independent of bounded manifest eviction; cross-branch close tombstones survive reload and each direct or ordered nested close retires exact identity at that lifecycle point while terminal closes clear attached/ref/page/route state, later lifecycle-proven browser launches—including failed post-close rows and `record stop`—can reactivate/rebuild it without stale pre-close `about:blank` recovery while bounded launch evidence survives failed-step presentation and transcript replay, explicitly non-launching diagnostics preserve the close, missing evidence stays conservatively active even on the first managed call, every successful direct/nested close clears wrapper trace/profiler ownership before later successful rows can rebuild it, and namespace-scoped `close --all` clears all matching managed/attached/page/ref/route/trace/recording ownership, only the newest pending recording path remains authoritative even across same-timestamp restart rows, current recording transitions replay directly without artifact-manifest compatibility inference, definitive direct/batch no-recording stop failures retire stale state at their ordered step, recording starts after nested close are rejected, pending rows coalesce into terminal batch outcomes without retaining an intermediate close-abandoned duplicate after a later saved stop, and any later same-session failure retains exact cleanup actions, same-page getter refs are refreshed, locator select resolves exact current native controls, no-movement scroll fails honestly, and existing owned cleanup preserves failure evidence. | [`docs/TOOL_CONTRACT.md`](TOOL_CONTRACT.md#details), [`docs/COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md), `test/agent-browser.extension-input-modes.test.ts`, `test/agent-browser.extension-ref-guards.test.ts`, `test/agent-browser.presentation.test.ts`, `test/agent-browser.presentation-artifacts-batch.test.ts`, `test/agent-browser.recording-reservations.test.ts`, `test/agent-browser.extension-validation.test.ts`, `test/agent-browser.script.test.ts` |
86
- | RQ-0146 | Upstream `agent-browser 0.34.0` rebaseline adds sticky `--pin-tab` / `--no-pin-tab` (`AGENT_BROWSER_PIN_TAB`) for shared CDP/auto-connect sessions, CDP target ids as tab refs, and `tab_gone` recovery data (`data.targetId`, optional `data.lastUrl`). The wrapper parses those flags as optional global booleans rather than launch-scoped, classifies `tab_gone` as `failureCategory: "tab-gone"` with `list-tabs-after-tab-gone` / `open-tab-after-tab-gone`, and shows `targetId` in `tab list` presentation. | [`docs/COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#upstream-0340-rebaseline), [`docs/TOOL_CONTRACT.md`](TOOL_CONTRACT.md#details), `test/agent-browser.results.test.ts`, `test/agent-browser.runtime.test.ts` |
87
- | RQ-0147 | Local Chrome composes stock `--no-startup-window` with native launch defaults while headless remains the default; URL-less open uses native lazy URL reads across direct/batch/code paths. Existing root/owned daemon probes and explicit-local session info gate bootstrap, without tab cleanup or a launcher/state journal. See `test/agent-browser.stock-startup.test.ts` for stock browser PID/page/storage checks. Native follow-ups preserve profiled and other launch-configured browser pages by omitting wrapper compatibility launch arguments while the daemon is active; daemon inspection reapplies the retained compatibility user agent only when relaunch is required. Caller `--args` retain their values after the startup default and native precedence; config, file access, and explicit local navigation remain native-owned, and cancellation wins over policy validation before spawn. | [`docs/ARCHITECTURE.md`](ARCHITECTURE.md), [`docs/TOOL_CONTRACT.md`](TOOL_CONTRACT.md), `test/agent-browser.runtime.test.ts`, `test/agent-browser.process.test.ts`, `test/agent-browser.real-upstream-contract.test.ts` |
88
- | RQ-0148 | Upstream 0.35.0 adds Linux Chromium private CA trust and the `protected-vercel-deployments` skill. The wrapper parses CA set/clear globals, requires fresh managed launches, suppresses automatic managed restore for CA-enabled sessions, passes caller certificate paths upstream unchanged, and uses 0.35.0 as its runtime floor. | [`docs/COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#upstream-0350-rebaseline), [`docs/TOOL_CONTRACT.md`](TOOL_CONTRACT.md), `test/agent-browser.runtime.test.ts`, `test/agent-browser.managed-session-restore.test.ts`, `test/agent-browser.page-target-validation.test.ts` |
89
- | RQ-0149 | Upstream 0.35.1 fixes snapshot-diff ref lifecycle, active-main-frame stream URL updates, and Windows ARM64 launcher selection without adding commands or flags. The wrapper preserves the 0.35.0 stable floor and accepts newer stable versions without version-specific shims. | [`docs/COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#upstream-0351-rebaseline), [`scripts/agent-browser-target.mjs`](../scripts/agent-browser-target.mjs), `test/agent-browser.upstream-version.test.ts`, `test/agent-browser.real-upstream-contract.test.ts` |
90
- | RQ-0150 | Upstream 0.35.2 hardens standalone dashboard origin access and fixes root remote CDP WebSocket query URLs. The wrapper parses `--allowed-origins` as a value and keeps explicit or implicit dashboard-start lifecycle calls sessionless; upstream owns origin validation, tokens, and the CDP fix. | [`docs/COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#upstream-0352-rebaseline), [`docs/TOOL_CONTRACT.md`](TOOL_CONTRACT.md#dashboard-reverse-proxy-origins), `test/agent-browser.runtime.test.ts` |
91
- | RQ-0151 | Upstream 0.36.0 adds experimental WebMCP page tools, default local-Chrome enablement with launch-scoped `--no-webmcp`, an opt-in MCP profile, and the `webmcp-gen` skill. The wrapper passes list/invoke/result/cancel through, preserves params/frame/detach/timeout arguments, derives watchdogs from effective direct/raw/stdin commands, keeps pending detached targets unverified, and restores batch target/ref state only after URL verification and a fresh snapshot, while keeping 0.35.0 as the stable floor. | [`docs/COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#upstream-0360-rebaseline), [`docs/TOOL_CONTRACT.md`](TOOL_CONTRACT.md#experimental-webmcp), `test/agent-browser.runtime.test.ts`, `test/agent-browser.wait-timeouts.test.ts`, `test/agent-browser.process.test.ts`, `test/agent-browser.page-target-validation.test.ts`, `test/agent-browser.extension-ref-guards.test.ts`, `test/agent-browser.real-upstream-contract.test.ts` |
92
- | RQ-0153 | Browser storage retains native JSONL authority, once-stored ancestral ref definitions, small correlated begin/finish events, explicit uncertainty/reuse and native-generation validation, invocation-only artifact receipts and ordered row changes. Failed persistence never retries effects; ordinary forks retain facts without acquiring parent cleanup rights. Read-only token replay and stopped separate-copy conversion preserve all ancestry, explicit observations and original audit bytes. | [`docs/SESSION_STORAGE.md`](SESSION_STORAGE.md), `lib/browser-transcript.ts`, `lib/browser-journal.ts`, `lib/browser-session-conversion.ts`, `test/agent-browser.storage-growth.test.ts`, `test/agent-browser.storage-recovery.test.ts`, existing script/ref/confirmation/Electron lifecycle tests |
93
- | RQ-0152 | Agent feedback closes recovery and evidence gaps without a new runtime layer: unknown-target timeouts return a visibly executable `get url` → `snapshot -i` fail-fast action while dialog recovery remains allowed; successful tab creation/selection/close, including dispatched batch rows, live-verifies URL/fresh titles and retains new, selected, and post-close blank tabs; compacted direct or batched `outputPath` writes use only full command-redacted live wrapper spills and fail rather than save metadata; explicit URL reads/all-read batches avoid browser helpers and managed replacement, while proven native read confirmations preserve exact session routing and capability-gated browser independence; single session-info preflights distinguish daemon/browser/native/Pi ownership; native recording receipts expose capture versus encoded measurements and survive failure/timeout exports, with bounded identity-matched recovery and no file-only success; direct or batched first/fresh local headed launches expose an unverified `browserWindow` handoff while attachments do not; snapshot spills and SAML/OAuth URL values are redacted at model/persistence boundaries; unsupported direct/batch `scrollintoview text=...` fails before upstream false success with visible native recovery payloads while help passes through; and web search sends Exa primary/version guidance, removes exact normalized-URL duplicates without overfetch, and labels provider page dates without claiming crawl/version proof. | [`docs/TOOL_CONTRACT.md`](TOOL_CONTRACT.md), [`docs/COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md), [`docs/ARCHITECTURE.md`](ARCHITECTURE.md), `test/agent-browser.extension-errors-artifacts.test.ts`, `test/agent-browser.extension-tabs.test.ts`, `test/agent-browser.extension-validation.test.ts`, `test/agent-browser.page-target-validation.test.ts`, `test/agent-browser.runtime.test.ts`, `test/agent-browser.snapshot-presentation.test.ts`, `test/agent-browser.web-search.test.ts`, `test/agent-browser.real-upstream-contract.test.ts` |
66
+ | Range | Status | Source of truth |
67
+ | ------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
68
+ | RQ-0110–RQ-0120 | Agent feedback triage resolved or documented; remaining unsupported areas are environment/upstream-owned. | [`docs/support-notes.md`](https://github.com/fitchmultz/pi-agent-browser-native/blob/main/docs/support-notes.md) |
69
+ | RQ-0123–RQ-0127 | Stress-report wrapper fixes shipped; prompt-derived business-action blocking remains intentionally out of scope. | [`docs/support-notes.md`](https://github.com/fitchmultz/pi-agent-browser-native/blob/main/docs/support-notes.md) |
70
+ | `agent-browser 0.27.2` baseline | Historical upstream rebaseline shipped; `RQ-0101` remains the compact-snapshot high-value-controls decision. | [`docs/support-notes.md`](https://github.com/fitchmultz/pi-agent-browser-native/blob/main/docs/support-notes.md) |
71
+ | RQ-0128 | Upstream `agent-browser 0.27.3` install-only rebaseline shipped; no new wrapper capability adopted. | [`docs/support-notes.md`](https://github.com/fitchmultz/pi-agent-browser-native/blob/main/docs/support-notes.md) |
72
+ | RQ-0129 | Upstream `agent-browser 0.29.1` rebaseline shipped; sandbox helpers are documented upstream package guidance, not a wrapper runtime. | [`docs/support-notes.md`](https://github.com/fitchmultz/pi-agent-browser-native/blob/main/docs/support-notes.md) |
73
+ | RQ-0130 | Upstream `agent-browser 0.30.1` rebaseline shipped; `wait --url` glob support replaces the wrapper `job.assertUrl` predicate workaround. | [`docs/support-notes.md`](https://github.com/fitchmultz/pi-agent-browser-native/blob/main/docs/support-notes.md) |
74
+ | RQ-0131 | Upstream `agent-browser 0.31.0` rebaseline shipped; restore workflow and namespace/session lifecycle globals are parsed, documented, and carried through wrapper-managed probes/state. | [`docs/COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#upstream-0310-rebaseline) |
75
+ | RQ-0132 | Upstream `agent-browser 0.31.1` rebaseline shipped; React renderer selection is upstream-fixed for `react tree`, `react inspect`, and `react suspense`, with no wrapper CLI/schema changes. | [`docs/COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#upstream-0311-rebaseline) |
76
+ | RQ-0133 | Upstream `agent-browser 0.31.2` rebaseline adds WebGPU launch/doctor/MCP surfaces and periodic restore-state autosaves; wrapper launch parsing/policy and docs now cover both. | [`docs/COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#upstream-0312-rebaseline) |
77
+ | RQ-0134 | Upstream `agent-browser 0.32.0` rebaseline hardens domain containment, fixes completed-page waits, and adds a separate eve extension package; wrapper launch policy and docs cover the relevant behavior. | [`docs/COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#upstream-0320-rebaseline) |
78
+ | RQ-0135 | Upstream `agent-browser 0.32.2` rebaseline updates eve packaging only and closes the wrapper's prior missing `read [url]` inventory/presentation contract. | [`docs/COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#upstream-0322-rebaseline) |
79
+ | RQ-0136 | Wrapper regression fix keeps helper subprocess launch environments stable, refreshes active tab state after `tab close`, and makes ordinary document-direction scrolling deterministic before upstream fallback. | [`docs/ARCHITECTURE.md`](ARCHITECTURE.md), [`docs/TOOL_CONTRACT.md`](TOOL_CONTRACT.md#details) |
80
+ | RQ-0137 | Upstream `agent-browser 0.32.4` rebaseline adds HAR `--content` body modes, the `derive-client` skill, and fixed `find role` implicit-ARIA/name matching with locator-detail misses; wrapper classifier/argv/docs cover those surfaces. | [`docs/COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#upstream-0330-rebaseline) |
81
+ | RQ-0138 | Upstream `agent-browser 0.33.0` rebaseline adds `a11y` axe-core audits and discarded-tab revival on tab switch; wrapper documents/presents `a11y` and samples the new help surface. | [`docs/COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#upstream-0330-rebaseline) |
82
+ | RQ-0139 | Upstream `agent-browser 0.33.2` rebaseline documents daemon idle timeout, streaming controls, and tab recovery. Wrapper-owned implicit sessions add transcript/checkout-scoped automatic restore with current v4 set-valued ticket-claim daemon coordination, eight-candidate opportunistic cleanup with randomized first windows and in-process rotation, verified snapshot retention, and page-target verification after ambiguous transitions. Explicit sessions, state/restore paths, config, file access, launch environment, local pages, output paths, and close arguments pass through unchanged; session/state lists keep all rows and identifiers visible. | [`docs/COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#upstream-0332-rebaseline), [`docs/ARCHITECTURE.md`](ARCHITECTURE.md) |
83
+ | RQ-0140 | Successful CDP/auto-connect and Electron sessions preserve one attached browser across native-tool follow-ups and cleanup by omitting wrapper local-launch defaults, with environment support, branch replay, first-use content blocking, live URL gates against external drift, and close cleanup. | [`docs/ARCHITECTURE.md`](ARCHITECTURE.md), [`docs/TOOL_CONTRACT.md`](TOOL_CONTRACT.md), `test/agent-browser.extension-passthrough-validation.test.ts` |
84
+ | RQ-0141 | Headed managed sessions avoid upstream 0.33.2 visible autosave targets by default and retain that daemon environment across helpers, still-owned off-current follow-ups, failed-replacement ownership, Electron cleanup, and reload/resume; slow daemon-policy inspection uses a 35-second budget; headed mode is launch-scoped; the effective launch interval persists across resume and changes in either direction require close plus a fresh daemon; and bare, review-only, fenced-reference, conditional, directly negated, or reference attachment paths do not become close-blocking output requirements while explicit contiguous output path lists, per-clause availability, duplicate precedence, and Markdown destinations are handled conservatively and linearly. | [`docs/ARCHITECTURE.md`](ARCHITECTURE.md), [`docs/TOOL_CONTRACT.md`](TOOL_CONTRACT.md), `test/agent-browser.managed-session-daemon-policy.test.ts`, `test/agent-browser.process.test.ts`, `test/agent-browser.prompt-policy.test.ts` |
85
+ | RQ-0142 | Persistent `agent_browser_code` uses the retained permissioned child and the same native executor as direct calls. Browser/auth state persists; JS state resets. Selected JSON/images, handled-failure receipts/counts, bounded IPC/deadline, shared whole-cell ordering, and ordered Pi transition replay replace isolated finally-close execution. The optional host `beforeExecute` callback retains outer call identity and serial dispatch. Strict old lease readers exist only for upgrade cleanup. | [`TOOL_CONTRACT.md`](TOOL_CONTRACT.md#agent_browser_code), [`ARCHITECTURE.md`](ARCHITECTURE.md#persistent-browser-code), `test/agent-browser.script.test.ts`, `test/agent-browser.tool-surface.test.ts`, `test/agent-browser.execution-lock.test.ts`, `test/agent-browser.execution-order.test.ts` |
86
+ | RQ-0143 | Browser-backed calls require a stable upstream version at or above the configured 0.35.0 floor, report minimum/observed version mismatch before launch, and keep stateless/local diagnostics available; the recommended target and minimum are shared by runtime, docs verification, and package contents. | [`scripts/agent-browser-target.mjs`](../scripts/agent-browser-target.mjs), [`docs/COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#upstream-0360-rebaseline), `test/agent-browser.upstream-version.test.ts` |
87
+ | RQ-0144 | Managed restore keys are scoped to both checkout generation and Pi transcript so upstream 0.33.2's newest-file-wins loading cannot let concurrent chats clobber or inherit cookies/storage. Fresh rotations, reload, restart, and `/resume` of one transcript retain continuity; after a confirmed inactive daemon, a branch-restored compatible owned session retains its pending reopen through daemon-starting non-page calls and transcript replay, then reopens the complete recorded URL (including its fragment) before current-page operations such as `get url` or `reload`, verifies the actual target and invalidates old refs. This reloads a URL, not forms, JavaScript memory, or history; live wrong-tab recovery never auto-navigates. Passive and explicit upstream configs pass through, while explicit config selection suppresses the wrapper's automatic restore injection. | [`docs/ARCHITECTURE.md`](ARCHITECTURE.md), [`docs/TOOL_CONTRACT.md`](TOOL_CONTRACT.md), `test/agent-browser.managed-session-restore.test.ts`, `test/agent-browser.real-upstream-contract.test.ts` |
88
+ | RQ-0145 | Mega-dogfood correctness closes false-positive success paths: URL QA makes matched post-clear page-error evidence non-pass as unverified, counts definitely new errors separately, and waits 150 ms for immediate post-load diagnostics, stale pre-existing artifacts and missing/stale recordings finalized by restart fail verification, aliased destinations (including dangling symlinks, full macOS/Windows Unicode folds, final short/long diff output flags, and same-call `outputPath` aliases) and active recording-path reuse through artifacts, path-bearing HAR stops, long/short or reordered explicit download waits, interspersed-global command forms, Electron cleanup output, or normalized output writes is rejected through an atomic process-wide, transcript-backed namespace/session reservation index independent of bounded manifest eviction; cross-branch close tombstones survive reload and each direct or ordered nested close retires exact identity at that lifecycle point while terminal closes clear attached/ref/page/route state, later lifecycle-proven browser launches—including failed post-close rows and `record stop`—can reactivate/rebuild it without stale pre-close `about:blank` recovery while bounded launch evidence survives failed-step presentation and transcript replay, explicitly non-launching diagnostics preserve the close, missing evidence stays conservatively active even on the first managed call, every successful direct/nested close clears wrapper trace/profiler ownership before later successful rows can rebuild it, and namespace-scoped `close --all` clears all matching managed/attached/page/ref/route/trace/recording ownership, only the newest pending recording path remains authoritative even across same-timestamp restart rows, current recording transitions replay directly without artifact-manifest compatibility inference, definitive direct/batch no-recording stop failures retire stale state at their ordered step, recording starts after nested close are rejected, rejected or pending restarts keep the active take's reservation and stop action unless a terminal previous-take receipt or native `restarted: true` acknowledges replacement, pending rows coalesce into terminal batch outcomes without retaining an intermediate close-abandoned duplicate after a later saved stop, and any later same-session failure retains exact cleanup actions, same-page getter refs are refreshed, locator select resolves exact current native controls, no-movement scroll fails honestly, and existing owned cleanup preserves failure evidence. | [`docs/TOOL_CONTRACT.md`](TOOL_CONTRACT.md#details), [`docs/COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md), `test/agent-browser.extension-input-modes.test.ts`, `test/agent-browser.extension-ref-guards.test.ts`, `test/agent-browser.presentation.test.ts`, `test/agent-browser.presentation-artifacts-batch.test.ts`, `test/agent-browser.recording-reservations.test.ts`, `test/agent-browser.extension-validation.test.ts`, `test/agent-browser.script.test.ts` |
89
+ | RQ-0146 | Upstream `agent-browser 0.34.0` rebaseline adds sticky `--pin-tab` / `--no-pin-tab` (`AGENT_BROWSER_PIN_TAB`) for shared CDP/auto-connect sessions, CDP target ids as tab refs, and `tab_gone` recovery data (`data.targetId`, optional `data.lastUrl`). The wrapper parses those flags as optional global booleans rather than launch-scoped, classifies `tab_gone` as `failureCategory: "tab-gone"` with `list-tabs-after-tab-gone` / `open-tab-after-tab-gone`, and shows `targetId` in `tab list` presentation. | [`docs/COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#upstream-0340-rebaseline), [`docs/TOOL_CONTRACT.md`](TOOL_CONTRACT.md#details), `test/agent-browser.results.test.ts`, `test/agent-browser.runtime.test.ts` |
90
+ | RQ-0147 | Local Chrome composes stock `--no-startup-window` with CLI arguments only when native environment/config does not own local launch defaults; otherwise startup arguments remain native-owned, and callers include that flag in native `args` when one headed window is required. Headless remains the default; URL-less open uses native lazy URL reads across direct/batch/code paths. Existing root/owned daemon probes and explicit-local session info gate bootstrap, without tab cleanup or a launcher/state journal. See `test/agent-browser.stock-startup.test.ts` for stock browser PID/page/storage checks. Native follow-ups preserve profiled and other launch-configured browser pages by omitting wrapper compatibility launch arguments while the daemon is active; daemon inspection reapplies the retained compatibility user agent only when relaunch is required. Caller `--args` retain their values and native precedence; eligible CLI-only launches place them after the startup default, while native config/environment defaults pass through without injected startup arguments. Config, file access, and explicit local navigation remain native-owned, and cancellation wins over policy validation before spawn. | [`docs/ARCHITECTURE.md`](ARCHITECTURE.md), [`docs/TOOL_CONTRACT.md`](TOOL_CONTRACT.md), `test/agent-browser.runtime.test.ts`, `test/agent-browser.process.test.ts`, `test/agent-browser.real-upstream-contract.test.ts` |
91
+ | RQ-0148 | Upstream 0.35.0 adds Linux Chromium private CA trust and the `protected-vercel-deployments` skill. The wrapper parses CA set/clear globals, requires fresh managed launches, suppresses automatic managed restore for CA-enabled sessions, passes caller certificate paths upstream unchanged, and uses 0.35.0 as its runtime floor. | [`docs/COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#upstream-0350-rebaseline), [`docs/TOOL_CONTRACT.md`](TOOL_CONTRACT.md), `test/agent-browser.runtime.test.ts`, `test/agent-browser.managed-session-restore.test.ts`, `test/agent-browser.page-target-validation.test.ts` |
92
+ | RQ-0149 | Upstream 0.35.1 fixes snapshot-diff ref lifecycle, active-main-frame stream URL updates, and Windows ARM64 launcher selection without adding commands or flags. The wrapper preserves the 0.35.0 stable floor and accepts newer stable versions without version-specific shims. | [`docs/COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#upstream-0351-rebaseline), [`scripts/agent-browser-target.mjs`](../scripts/agent-browser-target.mjs), `test/agent-browser.upstream-version.test.ts`, `test/agent-browser.real-upstream-contract.test.ts` |
93
+ | RQ-0150 | Upstream 0.35.2 hardens standalone dashboard origin access and fixes root remote CDP WebSocket query URLs. The wrapper parses `--allowed-origins` as a value and keeps explicit or implicit dashboard-start lifecycle calls sessionless; upstream owns origin validation, tokens, and the CDP fix. | [`docs/COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#upstream-0352-rebaseline), [`docs/TOOL_CONTRACT.md`](TOOL_CONTRACT.md#dashboard-reverse-proxy-origins), `test/agent-browser.runtime.test.ts` |
94
+ | RQ-0151 | Upstream 0.36.0 adds experimental WebMCP page tools, default local-Chrome enablement with launch-scoped `--no-webmcp`, an opt-in MCP profile, and the `webmcp-gen` skill. The wrapper passes list/invoke/result/cancel through, preserves params/frame/detach/timeout arguments, derives watchdogs from effective direct/raw/stdin commands, keeps pending detached targets unverified, and restores batch target/ref state only after URL verification and a fresh snapshot, while keeping 0.35.0 as the stable floor. | [`docs/COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#upstream-0360-rebaseline), [`docs/TOOL_CONTRACT.md`](TOOL_CONTRACT.md#experimental-webmcp), `test/agent-browser.runtime.test.ts`, `test/agent-browser.wait-timeouts.test.ts`, `test/agent-browser.process.test.ts`, `test/agent-browser.page-target-validation.test.ts`, `test/agent-browser.extension-ref-guards.test.ts`, `test/agent-browser.real-upstream-contract.test.ts` |
95
+ | RQ-0153 | Browser storage retains native JSONL authority, once-stored ancestral ref definitions, small correlated begin/finish events, explicit uncertainty/reuse and native-generation validation, invocation-only artifact receipts and ordered row changes. Failed persistence never retries effects; ordinary forks retain facts without acquiring parent cleanup rights. Read-only token replay and stopped separate-copy conversion preserve all ancestry, explicit observations and original audit bytes. | [`docs/SESSION_STORAGE.md`](SESSION_STORAGE.md), `lib/browser-transcript.ts`, `lib/browser-journal.ts`, `lib/browser-session-conversion.ts`, `test/agent-browser.storage-growth.test.ts`, `test/agent-browser.storage-recovery.test.ts`, existing script/ref/confirmation/Electron lifecycle tests |
96
+ | RQ-0152 | Agent feedback closes recovery and evidence gaps without a new runtime layer: unknown-target timeouts return a visibly executable `get url` → `snapshot -i` fail-fast action while dialog recovery remains allowed; successful tab creation/selection/close, including dispatched batch rows, live-verifies URL/fresh titles and retains new, selected, and post-close blank tabs; compacted direct or batched `outputPath` writes use only full command-redacted live wrapper spills and fail rather than save metadata; explicit URL reads/all-read batches avoid browser helpers and managed replacement, while proven native read confirmations preserve exact session routing and capability-gated browser independence; single session-info preflights distinguish daemon/browser/native/Pi ownership; native recording receipts expose capture versus encoded measurements and survive failure/timeout exports, with bounded identity-matched recovery and no file-only success; direct or batched first/fresh local headed launches expose an unverified `browserWindow` handoff while attachments do not; snapshot spills and SAML/OAuth URL values are redacted at model/persistence boundaries; unsupported direct/batch `scrollintoview text=...` fails before upstream false success with visible native recovery payloads while help passes through; and web search sends Exa primary/version guidance, removes exact normalized-URL duplicates without overfetch, and labels provider page dates without claiming crawl/version proof. | [`docs/TOOL_CONTRACT.md`](TOOL_CONTRACT.md), [`docs/COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md), [`docs/ARCHITECTURE.md`](ARCHITECTURE.md), `test/agent-browser.extension-errors-artifacts.test.ts`, `test/agent-browser.extension-tabs.test.ts`, `test/agent-browser.extension-validation.test.ts`, `test/agent-browser.page-target-validation.test.ts`, `test/agent-browser.runtime.test.ts`, `test/agent-browser.snapshot-presentation.test.ts`, `test/agent-browser.web-search.test.ts`, `test/agent-browser.real-upstream-contract.test.ts` |
94
97
 
95
98
  Browser journal storage (RQ-0153) uses one canonical small event/reducer, once-stored complete captures and journal-ordered artifact changes. `test/agent-browser.storage-growth.test.ts` protects the incident-sized map and ordinary-code growth; `test/agent-browser.storage-recovery.test.ts` covers actual append-fault dispatch counts, concurrent publication during captured-branch replay, unpublished selected-leaf refusal, unknown prefixes, same-URL generation replacement, branch conversion and strict token validation. Existing tab/ref, read-confirmation, recording, artifact and Electron lifecycle suites retain their contracts. The opt-in `test/helpers/large-browser-journal.mjs` exercises a >1 GiB original with a giant ignored value under a constrained V8 heap; it reports actual RSS separately. Official and fork load/restart qualification remains independent, and stock official 1.0.0's native eager loader is not repaired by the extension alone. Conversion is offline and source-retaining; see [`SESSION_STORAGE.md`](SESSION_STORAGE.md).
96
99
 
97
100
  QA truthfulness (#121, RQ-0145) is covered by the registered-tool controls in `test/agent-browser.extension-input-modes.test.ts` and the strict `contract suite matches QA non-pass after same-URL error-buffer rollover` case in `test/agent-browser.real-upstream-contract.test.ts`. The real fixture fills the native error FIFO with identical rows, then verifies that a new document actually throws again at the same URL and that QA is always non-pass. Matched rows fail as an unverified check, not an application-error assertion. Empty/cleared and explicit `checkErrors: false` controls preserve valid passes; the wrapper does not fix upstream `errors --clear` or accept a warning-only pass as resolution.
98
101
 
102
+ Explicit native text preserves standalone and compound/raw-or-stdin batch output without changing caller input. `test/agent-browser.text-output.test.ts` covers opaque JSON/confirmation-like page strings, complete whitespace-preserving stdout and redacted subprocess/presentation spills, text-only output export success/failure notices, nonzero failure and strict malformed JSON; the `real native explicit text` case in `test/agent-browser.real-upstream-contract.test.ts` proves native URL reads, both diff orders, row boolean operands and last-wins outer selection. The same native case protects empty stdin-row skipping, later successful rows, Unicode results, bail behavior and original row positions in text errors; malformed shapes still fail before dispatch. Failed-exit stderr is primary while zero-exit malformed JSON remains strict, covered by the registered `failed-json`/`strict-json` cases. Text contains no trusted row, confirmation, lifecycle, page-target or artifact receipts; use JSON for those fields. See [the output contract](TOOL_CONTRACT.md#wrapper-json).
103
+
99
104
  Browser evidence (RQ-0152) is covered by `test/agent-browser.browser-evidence.test.ts`, `test/agent-browser.read-confirmation.test.ts`, `test/agent-browser.recording-receipts.test.ts` and `test/agent-browser.recording-recovery.test.ts`, alongside existing presentation, reservation/replay and lifecycle checks. They cover cold/shared/unknown/invalid/timeout reads, native-default and shared confirmation routing, capability absence and script identity boundaries, separate daemon/browser/Pi identity, sparse/legacy capture metrics, native failure retention, stale/same-path mismatches, one-query stop recovery, error exports and artifact aliases. Full live identity, receipt lookup and browser-independent native read/confirm handling require companion upstream fixes; missing fields remain unknown, and native receipts do not survive daemon exit. These source checks do not replace paired native/Pi runtime verification.
100
105
 
101
106
  Contributor fixes #133/#152 remove unused prompt suffix entries without changing runtime guidance and diagnose bare `--no-sandbox` only in the command slot or navigation option positions. Native `--args` values and literal operands remain intact; batch checks use raw effective rows without treating row-local `--args` as a launch setting. `test/agent-browser.chromium-args.test.ts` covers pre-dispatch rejection, literal/flag-value controls, inspection, raw/stdin batch precedence and dispatcher outcomes. Existing prompt/grammar checks remain; source checks do not replace native-product gates.
@@ -118,6 +123,8 @@ Overlay recovery (RQ-0073, #147) recommends only `inspect-overlay-state` after a
118
123
 
119
124
  Lightpanda support preserves native command access rather than promising Chrome parity. Registered-tool image controls cover native metadata in direct/JSON, batch and selected code attachments plus standalone browser-brand evidence when legacy/attached native output omits or mislabels the engine. Verified image bytes remain unchanged and coordinate claims stay unknown even when dimensions match synthetic browser geometry. Root-default controls cover CLI/env/native-config precedence and untouched caller settings; engine planner controls preserve fresh/new/explicit launches. See [engine limits](COMMAND_REFERENCE.md#lightpanda-engine). Release evidence below remains separate from these focused regressions.
120
125
 
126
+ Confirmation-policy continuity uses existing canonical session page events, resolved before helpers. The focused native nextAction case proves exact denial, a useful confirmed audit followed immediately by title/body reads across resume, bare getter/PID continuity, and denied recording-restart sentinel/original-take preservation; the shared-defaults owner covers selected-string/empty/unset precedence, code/advanced routing, ordered pending-batch targets/replay with a gated URL helper, failed replacement cleanup/recovery, off-branch cleanup, close and identity isolation. Strict native guarded-control markers reuse the same transcript reducer with compact command/action provenance, not command replay; exact decisions avoid helper-slot replacement without claiming native ID validation or browser independence. Read-confirmation tests cover forged/foreign/first-nondecision controls, raw-argv-over-stdin decisions, later unknown-page checks, ordered confirmed batch effects, truthful requested/early-helper/post-command-helper pending copy, and completed click/tab/failed-inner/close reconciliation through real code intent/finish replay, cold-resume covers pending helper exposure/replay, and Electron host tests cover ambient/retained policy. Definite no-admission attempts restore prior policy while interrupted work retains intent. Pending close does not retire ownership or restore state. Native policy changes still restart normally; pending commands remain native-owned. Read-confirmation regressions also cover ordered confirmed snapshots, later pending/failed/invalidation rows, one-use freshness consumption through direct/code/batch resume, semantic role click/check/fill and unique role/label select after snapshot approval with unchanged payloads, absent/ambiguous select targets and drift, warm/no-resume direct and semantic select success on unchanged path/hash routes for caller-owned and freshly established wrapper-owned managed sessions versus refusal after a live-observed complete-URL change, including hash-only routes, without a gated-snapshot loop or changing ordinary fragment-insensitive ref/tab comparisons, plus live/resumed attachment retirement after confirmed close. Registered confirmation tests also cover direct/batch tab transport metadata, exact approval/denial, visible conditional continuation, malformed/mismatched extras and page/eval/HTTP provenance rejection; actual SDK/native proof uses the real authenticated-tab transport with a dummy loopback token. Presentation tests distinguish direct/nested pending snapshot controls from complete empty snapshots and preserve redacted recovery actions and explicit JSON. Click-dispatch owner tests and local native SDK proof cover timer cancellation, pending-safe marker/listener expiry without an extra helper, and native ref/XPath click dispatch when `evaluate` guards optional diagnostic probes. The patched recording-restart/navigation subcase has a separate test-only opt-in; stock upstream still runs the remaining confirmation checks. See [real upstream qualification](RELEASE.md#real-upstream-contract-validation).
127
+
121
128
  Shared native defaults are covered by `test/agent-browser.shared-defaults.test.ts`: environment/file/argv precedence, caller-owned reuse across independent Pi contexts, quit ownership, native helper idle settings, unchanged implicit cleanup, and an opt-in real local-profile fixture proving shared state and code follows the selected ordinary browser rather than a disposable isolated session. Code tests cover the fresh child language boundary and persistent browser behavior; the local Electron handoff regression in `test/agent-browser.extension-electron-lifecycle.test.ts` keeps generated launch ownership despite a native session environment default; native config validation uses upstream rather than a second schema. See [shared browser defaults](../README.md#shared-browser-defaults). These tests do not promise permanent third-party authentication.
122
129
 
123
130
  Browser correctness regressions cover credential-bearing filtered network details/exports, native generated-Blob downloads with actual saved bytes, accessible-name click target identity and abstention, smooth CSS-container movement, and parseable early-result JSON. Native fixture coverage complements deterministic dispatch/cleanup and output-shape checks; release qualification remains separate.
@@ -138,44 +145,44 @@ Linux/macOS, declared Node floors, official/fork host identities, required consu
138
145
 
139
146
  Re-run the gates below before each release. Dated outcomes in this table are historical evidence for their named source/version, not qualification of the current Pi 1.0 implementation. The earlier 0.36.0 rebaseline passed local pre-PR, real-upstream and deterministic dogfood on 2026-09-01; the 0.35.0 floor was last validated locally on 2026-08-26. The historical 0.38.1 PR qualification used local macOS and the hosted native-Windows gate. Current explicit owner waivers take precedence; neither historical passes nor failures qualify the new candidate. Release-only cross-platform/model/lifecycle and publication gates remain separate.
140
147
 
141
- | Gate | Evidence | Status |
142
- | --- | --- | --- |
143
- | Native lifecycle Linux | Portable public SDK/native-browser lifecycle gate covers branch/reload, ordered code cancellation, ownership/routing, journal-begin failure and root save/reopen; see [native qualification](RELEASE.md#native-lifecycle-qualification). | Requalify the exact final source and host graph; no Pi 1.0 candidate pass is claimed by historical evidence below. |
144
- | Default local gate | `npm run verify` checks generated playbook drift, clean-builds generated `dist/`, runs `tsc --noEmit`, unit/fake tests, generated command-reference blocks, and live command-reference sampling. | **Earlier 0.36.0:** pass on 2026-09-01; 779 tests passed, two opt-in real-upstream tests skipped, and build/typecheck/docs/live command-reference gates passed. |
145
- | Pre-PR local gate | `npm run verify -- pre-pr` composes the default gate with package-content verification. Use before larger local handoffs or PR-ready claims when lifecycle/platform/live dogfood cost is not warranted. | **Earlier 0.36.0 / package 0.6.2:** pass on 2026-09-01; 779 tests passed, two opt-in tests skipped, and the 127-file tarball verified. |
146
- | Windows argument transport (#102/#131/#141) | `test/agent-browser.windows-argv.test.ts` exercises actual host argv, empty values, quotes, Unicode/spaces, stdin, custom shims and failure outcomes. `test/agent-browser.windows-stock-launcher.test.ts` covers the recognized global npm CMD template's direct-native path, command selection, fallback, literal LF/CRLF and cancellation. Custom or unrecognized batch launchers retain their existing newline limitation. POSIX keeps Node `spawn`. | Native Windows focused qualification on 2026-09-21 passed all seven stock-launcher controls, all 29 Chromium cases and 33 process/argv cases (two existing platform skips). Actual upstream Rust received all 12 expected operands; the original CMD path lost all four newline-bearing operands. These focused results do not replace full-suite, managed-browser, package or release gates. |
147
- | Real upstream contract | `npm run verify -- real-upstream` runs the localhost fixture matrix against a real stable `agent-browser` at or above the configured floor. | **Earlier recommended 0.36.0:** pass on 2026-09-01 (2/2 tests), including WebMCP and `--no-webmcp`; the 0.35.0 floor last passed on 2026-08-26 (2/2 tests). |
148
- | Packaged Pi smoke | `npm run verify -- package-pi` validates package contents, installs the extracted tarball's runtime dependencies without lifecycle scripts or host peers, loads the packaged `agent_browser` tool without requiring optional Brave config, and executes fake-upstream `--version`. | **Earlier package 0.6.2 / Pi 0.84.4:** pass on 2026-09-01; the 127-file tarball loaded exactly one packaged `agent_browser` and executed `--version`. |
149
- | Startup profile | `npm run verify -- startup-profile --samples <n>` clean-builds generated `dist/`, records direct package entrypoint import/factory timing in fresh Node processes using the same `scripts/startup-measurement.mjs` measurement and 250ms budget as the startup owner test (the test retains its Android-only 1000ms exception), and writes `.artifacts/startup-profile/latest.json`. It must not launch Pi, tmux, mise, npm, browsers, or `agent-browser`; full Pi TUI ready-prompt profiling is intentionally excluded after it proved too invasive for routine verification. Run this opt-in evidence when package layout, the compiled entrypoint, top-level imports, schema registration, or prompt/config startup logic changes. | **Earlier compiled 0.6.2 entrypoint:** pass on 2026-09-01 with three samples; median 104.9 ms and max 114.5 ms, below the 250 ms budget. |
150
- | Deterministic dogfood smoke | `npm run verify -- dogfood` clean-builds, then `scripts/verify-agent-browser-dogfood.ts` drives the native wrapper against a loopback HTTP fixture through persistent code aggregation, advanced QA/actions, native batch, screenshot artifact verification, and session close with the real `agent-browser` on `PATH`. | **Earlier 0.36.0 / package 0.6.2 / Pi 0.84.4:** pass on 2026-09-01; QA, script branching/cleanup, fresh/current opens, semantic clicks, job screenshot verification, and close all passed. |
151
- | WebGPU and restore autosave | Live 0.31.2 feature probes validate the new upstream paths independently from ordinary browser dogfood. | **macOS:** `doctor --webgpu` passed Apple Metal render/readback and headless red-pixel screenshot checks; the official Hello Triangle sample exposed the Metal adapter and produced a verified non-black screenshot. **Ubuntu image:** `doctor --webgpu --headed --json` passed SwiftShader render/readback and red-pixel screenshot checks with the baked Vulkan/Mesa/Xvfb dependencies. **Restore autosave:** an idle headless page timer changed localStorage and the namespaced restore file contained the new value before close; test state was removed. Wrapper-owned headed launches default periodic autosave off to avoid upstream 0.33.2 visible temporary collector tabs; native close still saves, direct window close can lose newer state because headed browsers are exempt from idle shutdown, and explicit `AGENT_BROWSER_AUTOSAVE_INTERVAL_MS` opts in at daemon launch; its effective value persists across resume, and changing a running wrapper-owned headed daemon in either direction requires close plus a fresh launch. On 2026-08-06, a headed checkout dogfood run crossed `react.dev` → `example.com` → `react.dev`, idled past the autosave interval while recording, showed no temporary page switch in frame/contact-sheet review, and closed both sessions successfully; disposable evidence was removed. **Windows interactive desktop:** post-release validation on 2026-07-15 used a disposable clone of snapshot `57cc3c0d-7d7c-4a4c-9c57-8270d4174679`, a logged-in console session, `agent-browser 0.31.2`, and Edge 150. The headed doctor WebGPU render/readback subcheck passed in 0.99s and its decoded screenshot subcheck passed with `rgb(255,0,0)`; a separate `--webgpu --headed` launch opened the proof page and the Parallels console capture visibly recorded the red triangle (553,500 bright-red pixels; SHA-256 `f5a28f5336cbdfeb0ff557af9425458bddc6b266d3cc6b946de7b101a0b43288`). The full doctor remained nonzero only for the unrelated absence of a separately installed Chrome binary; the explicit Edge executable completed the launch and both WebGPU probes. Local evidence is under `.artifacts/windows-webgpu-interactive/20260715T150903Z/summary.json`; the disposable clone and temporary account were deleted afterward. |
152
- | Android/Termux local bring-up | Non-release-blocking source validation uses Termux system Chromium through upstream's Linux `which chromium` discovery, the packaged Linux-musl arm64 CLI, real Pi managed-session smoke, deterministic dogfood, and the default unit/package gate. Electron desktop lifecycle is not applicable. | **Historical 0.6 local evidence (not 0.7 code qualification):** Android 17 / arm64 Termux passed implicit, explicit, and namespaced fresh sessions, managed restore, script, QA, semantic action, job, click, eval/batch stdin, screenshot attachment, recording dependencies, and cleanup; Android is not yet a Crabbox release target. |
153
- | Crabbox platform smoke | `npm run check:platform-smoke` syntax-checks the harness and cheap invariants. `npm run smoke:platform:ubuntu-image` builds the project-owned Linux image, `npm run smoke:platform:doctor` checks Crabbox 0.26.0+ and local target readiness, and `npm run smoke:platform:all` runs doctor first, then fast target-local `platform-build` (`npm run verify -- platform-target`, pack, clean Pi install) plus `browser-dogfood-smoke` on Crabbox `macos`, `ubuntu`, and `windows-native`; see [`platform-smoke.md`](platform-smoke.md). Target artifacts include Crabbox/provider/work-root metadata, and release review also checks provider-specific `crabbox list` commands for leftover leases/clones. | **Earlier 0.36.0 / package 0.6.2 / Pi 0.84.4:** Ubuntu `platform-build` and `browser-dogfood-smoke` passed with 11/11 assertions each on 2026-09-01, including complete artifact manifests and lease cleanup. Under explicit GitHub-only release waivers, macOS SSH and native Windows were not run because localhost SSH and `prlctl` were unavailable. |
154
- | `verify -- release` / `prepublishOnly` | `npm run verify -- release` chains the default gate with the configured-source lifecycle harness, packaged Pi smoke, and the release-blocking Crabbox platform matrix (`verifySteps` `release` in [`scripts/project.mjs`](https://github.com/fitchmultz/pi-agent-browser-native/blob/main/scripts/project.mjs)). `package.json` `prepublishOnly` runs that compose before `npm pack --dry-run` during `npm publish`. It intentionally omits standalone real-upstream and host-only dogfood modes—see [`RELEASE.md`](RELEASE.md#pre-release-checks). | **Package 0.6.2:** on 2026-09-01 the default, lifecycle, package-Pi, startup, real-upstream, deterministic dogfood, harness, Ubuntu image, and Ubuntu target gates passed individually. The canonical full composition was not reported as passed because macOS SSH and native Windows were explicitly waived after doctor confirmed localhost SSH and `prlctl` were unavailable. That historical release created GitHub artifacts only; it did not authorize npm publishing. |
155
- | Configured-source lifecycle | `npm run verify -- lifecycle` (`scripts/verify-lifecycle.mjs`) drives `/reload`, closes and relaunches Pi with the same exact `--session-id`, checks the JSONL session header id, session continuity, slash-command sentinel tokens (`v1` before reload and `v2` after full relaunch), persisted spill reachability, and native returned failure status and JSON preservation for a QA reclassification with a fake upstream on `PATH`. Default Pi model is `zai/glm-5.2`; default per-step wait is **180000 ms** (`DEFAULT_TIMEOUT_MS`); override model with `--model <id>` and waits with `--timeout-ms <ms>`. Passthrough flags in [`scripts/project.mjs`](https://github.com/fitchmultz/pi-agent-browser-native/blob/main/scripts/project.mjs): `--keep-artifacts`, `--model`, `--verbose`, and `--timeout-ms` plus a value (for example `npm run verify -- lifecycle --model openai-codex/gpt-5.5:minimal --keep-artifacts --verbose --timeout-ms 600000`). | **Pi 0.84.4 on 2026-09-01:** pass; `/reload`, exact-session relaunch, managed continuity, persisted spill reachability, and Pi failure status all verified. |
156
- | Quick isolated Pi smoke | `pi --approve --no-extensions --no-skills -e .` from trusted repo root; checkout-native browser tools only. | **Earlier 0.36.0 / package 0.6.2 / Pi 0.84.4:** isolated checkout tmux smoke passed on 2026-09-01; native `agent_browser` completed version, localhost open, WebMCP list/invoke, visible-text verification, and close. |
157
-
158
- Runtime floor note: package metadata requires Node 24.21.0 or newer, keeps optional Pi core package peer ranges wildcard per installed Pi package docs, pins direct Pi validation dependencies to 1.0.0, and makes `pi --version` below 1.0.0 a setup failure through `pi-agent-browser-doctor` / `npm run doctor`. The Pi floor follows the native tool-history/prompt APIs and includes no older-host compatibility shim.
148
+ | Gate | Evidence | Status |
149
+ | ------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
150
+ | Native lifecycle Linux | Portable public SDK/native-browser lifecycle gate covers branch/reload, ordered code cancellation, ownership/routing, journal-begin failure and root save/reopen; see [native qualification](RELEASE.md#native-lifecycle-qualification). | Requalify the exact final source and host graph; no Pi 1.0 candidate pass is claimed by historical evidence below. |
151
+ | Default local gate | `npm run verify` checks generated playbook drift, clean-builds generated `dist/`, runs `tsc --noEmit`, unit/fake tests, generated command-reference blocks, and live command-reference sampling. | **Earlier 0.36.0:** pass on 2026-09-01; 779 tests passed, two opt-in real-upstream tests skipped, and build/typecheck/docs/live command-reference gates passed. |
152
+ | Pre-PR local gate | `npm run verify -- pre-pr` composes the default gate with package-content verification. Use before larger local handoffs or PR-ready claims when lifecycle/platform/live dogfood cost is not warranted. | **Earlier 0.36.0 / package 0.6.2:** pass on 2026-09-01; 779 tests passed, two opt-in tests skipped, and the 127-file tarball verified. |
153
+ | Windows argument transport (#102/#131/#141) | `test/agent-browser.windows-argv.test.ts` exercises actual host argv, empty values, quotes, Unicode/spaces, stdin, custom shims and failure outcomes. `test/agent-browser.windows-stock-launcher.test.ts` covers the recognized global npm CMD template's direct-native path, command selection, fallback, literal LF/CRLF and cancellation. Custom or unrecognized batch launchers retain their existing newline limitation. POSIX keeps Node `spawn`. | Native Windows focused qualification on 2026-09-21 passed all seven stock-launcher controls, all 29 Chromium cases and 33 process/argv cases (two existing platform skips). Actual upstream Rust received all 12 expected operands; the original CMD path lost all four newline-bearing operands. These focused results do not replace full-suite, managed-browser, package or release gates. |
154
+ | Real upstream contract | `npm run verify -- real-upstream` runs the localhost fixture matrix against a real stable `agent-browser` at or above the configured floor. | **Earlier recommended 0.36.0:** pass on 2026-09-01 (2/2 tests), including WebMCP and `--no-webmcp`; the 0.35.0 floor last passed on 2026-08-26 (2/2 tests). |
155
+ | Packaged Pi smoke | `npm run verify -- package-pi` validates package contents, installs the extracted tarball's runtime dependencies without lifecycle scripts or host peers, loads the packaged `agent_browser` tool without requiring optional Brave config, and executes fake-upstream `--version`. | **Earlier package 0.6.2 / Pi 0.84.4:** pass on 2026-09-01; the 127-file tarball loaded exactly one packaged `agent_browser` and executed `--version`. |
156
+ | Startup profile | `npm run verify -- startup-profile --samples <n>` clean-builds generated `dist/`, records direct package entrypoint import/factory timing in fresh Node processes using the same `scripts/startup-measurement.mjs` measurement and 250ms budget as the startup owner test (the test retains its Android-only 1000ms exception), and writes `.artifacts/startup-profile/latest.json`. It must not launch Pi, tmux, mise, npm, browsers, or `agent-browser`; full Pi TUI ready-prompt profiling is intentionally excluded after it proved too invasive for routine verification. Run this opt-in evidence when package layout, the compiled entrypoint, top-level imports, schema registration, or prompt/config startup logic changes. | **Earlier compiled 0.6.2 entrypoint:** pass on 2026-09-01 with three samples; median 104.9 ms and max 114.5 ms, below the 250 ms budget. |
157
+ | Deterministic dogfood smoke | `npm run verify -- dogfood` clean-builds, then `scripts/verify-agent-browser-dogfood.ts` drives the native wrapper against a loopback HTTP fixture through persistent code aggregation, advanced QA/actions, native batch, screenshot artifact verification, and session close with the real `agent-browser` on `PATH`. | **Earlier 0.36.0 / package 0.6.2 / Pi 0.84.4:** pass on 2026-09-01; QA, script branching/cleanup, fresh/current opens, semantic clicks, job screenshot verification, and close all passed. |
158
+ | WebGPU and restore autosave | Live 0.31.2 feature probes validate the new upstream paths independently from ordinary browser dogfood. | **macOS:** `doctor --webgpu` passed Apple Metal render/readback and headless red-pixel screenshot checks; the official Hello Triangle sample exposed the Metal adapter and produced a verified non-black screenshot. **Ubuntu image:** `doctor --webgpu --headed --json` passed SwiftShader render/readback and red-pixel screenshot checks with the baked Vulkan/Mesa/Xvfb dependencies. **Restore autosave:** an idle headless page timer changed localStorage and the namespaced restore file contained the new value before close; test state was removed. Wrapper-owned headed launches default periodic autosave off to avoid upstream 0.33.2 visible temporary collector tabs; native close still saves, direct window close can lose newer state because headed browsers are exempt from idle shutdown, and explicit `AGENT_BROWSER_AUTOSAVE_INTERVAL_MS` opts in at daemon launch; its effective value persists across resume, and changing a running wrapper-owned headed daemon in either direction requires close plus a fresh launch. On 2026-08-06, a headed checkout dogfood run crossed `react.dev` → `example.com` → `react.dev`, idled past the autosave interval while recording, showed no temporary page switch in frame/contact-sheet review, and closed both sessions successfully; disposable evidence was removed. **Windows interactive desktop:** post-release validation on 2026-07-15 used a disposable clone of snapshot `57cc3c0d-7d7c-4a4c-9c57-8270d4174679`, a logged-in console session, `agent-browser 0.31.2`, and Edge 150. The headed doctor WebGPU render/readback subcheck passed in 0.99s and its decoded screenshot subcheck passed with `rgb(255,0,0)`; a separate `--webgpu --headed` launch opened the proof page and the Parallels console capture visibly recorded the red triangle (553,500 bright-red pixels; SHA-256 `f5a28f5336cbdfeb0ff557af9425458bddc6b266d3cc6b946de7b101a0b43288`). The full doctor remained nonzero only for the unrelated absence of a separately installed Chrome binary; the explicit Edge executable completed the launch and both WebGPU probes. Local evidence is under `.artifacts/windows-webgpu-interactive/20260715T150903Z/summary.json`; the disposable clone and temporary account were deleted afterward. |
159
+ | Android/Termux local bring-up | Non-release-blocking source validation uses Termux system Chromium through upstream's Linux `which chromium` discovery, the packaged Linux-musl arm64 CLI, real Pi managed-session smoke, deterministic dogfood, and the default unit/package gate. Electron desktop lifecycle is not applicable. | **Historical 0.6 local evidence (not 0.7 code qualification):** Android 17 / arm64 Termux passed implicit, explicit, and namespaced fresh sessions, managed restore, script, QA, semantic action, job, click, eval/batch stdin, screenshot attachment, recording dependencies, and cleanup; Android is not yet a Crabbox release target. |
160
+ | Crabbox platform smoke | `npm run check:platform-smoke` syntax-checks the harness and cheap invariants. `npm run smoke:platform:ubuntu-image` builds the project-owned Linux image, `npm run smoke:platform:doctor` checks Crabbox 0.26.0+ and local target readiness, and `npm run smoke:platform:all` runs doctor first, then fast target-local `platform-build` (`npm run verify -- platform-target`, pack, clean Pi install) plus `browser-dogfood-smoke` on Crabbox `macos`, `ubuntu`, and `windows-native`; see [`platform-smoke.md`](platform-smoke.md). Target artifacts include Crabbox/provider/work-root metadata, and release review also checks provider-specific `crabbox list` commands for leftover leases/clones. | **Earlier 0.36.0 / package 0.6.2 / Pi 0.84.4:** Ubuntu `platform-build` and `browser-dogfood-smoke` passed with 11/11 assertions each on 2026-09-01, including complete artifact manifests and lease cleanup. Under explicit GitHub-only release waivers, macOS SSH and native Windows were not run because localhost SSH and `prlctl` were unavailable. |
161
+ | `verify -- release` / `prepublishOnly` | `npm run verify -- release` chains the default gate with the configured-source lifecycle harness, packaged Pi smoke, and the release-blocking Crabbox platform matrix (`verifySteps` `release` in [`scripts/project.mjs`](https://github.com/fitchmultz/pi-agent-browser-native/blob/main/scripts/project.mjs)). `package.json` `prepublishOnly` runs that compose before `npm pack --dry-run` during `npm publish`. It intentionally omits standalone real-upstream and host-only dogfood modes—see [`RELEASE.md`](RELEASE.md#pre-release-checks). | **Package 0.6.2:** on 2026-09-01 the default, lifecycle, package-Pi, startup, real-upstream, deterministic dogfood, harness, Ubuntu image, and Ubuntu target gates passed individually. The canonical full composition was not reported as passed because macOS SSH and native Windows were explicitly waived after doctor confirmed localhost SSH and `prlctl` were unavailable. That historical release created GitHub artifacts only; it did not authorize npm publishing. |
162
+ | Configured-source lifecycle | `npm run verify -- lifecycle` (`scripts/verify-lifecycle.mjs`) drives `/reload`, closes and relaunches Pi with the same exact `--session-id`, checks the JSONL session header id, session continuity, slash-command sentinel tokens (`v1` before reload and `v2` after full relaunch), persisted spill reachability, and native returned failure status and JSON preservation for a QA reclassification with a fake upstream on `PATH`. Default Pi model is `zai/glm-5.2`; default per-step wait is **180000 ms** (`DEFAULT_TIMEOUT_MS`); override model with `--model <id>` and waits with `--timeout-ms <ms>`. Passthrough flags in [`scripts/project.mjs`](https://github.com/fitchmultz/pi-agent-browser-native/blob/main/scripts/project.mjs): `--keep-artifacts`, `--model`, `--verbose`, and `--timeout-ms` plus a value (for example `npm run verify -- lifecycle --model openai-codex/gpt-5.5:minimal --keep-artifacts --verbose --timeout-ms 600000`). | **Pi 0.84.4 on 2026-09-01:** pass; `/reload`, exact-session relaunch, managed continuity, persisted spill reachability, and Pi failure status all verified. |
163
+ | Quick isolated Pi smoke | `pi --approve --no-extensions --no-skills -e .` from trusted repo root; checkout-native browser tools only. | **Earlier 0.36.0 / package 0.6.2 / Pi 0.84.4:** isolated checkout tmux smoke passed on 2026-09-01; native `agent_browser` completed version, localhost open, WebMCP list/invoke, visible-text verification, and close. |
164
+
165
+ Runtime floor note: package metadata requires Node 24.21.0 or newer, keeps optional Pi core package peer ranges wildcard per installed Pi package docs, keeps direct Pi development dependencies locked as reproducible snapshots while qualification resolves the latest stable official Pi and maintained fork main independently, and makes `pi --version` below 1.0.0 a setup failure through `pi-agent-browser-doctor` / `npm run doctor`. The Pi floor follows the native tool-history/prompt APIs and includes no older-host compatibility shim.
159
166
 
160
167
  ## Baseline checklist by inventory section
161
168
 
162
- | Baseline section | Baseline items | Documentation | Runtime handling | Test coverage | Validation status |
163
- | --- | --- | --- | --- | --- | --- |
164
- | Built-in skills | 19 canonical tokens from baseline section `skills`; see [`scripts/agent-browser-capability-baseline.mjs`](../scripts/agent-browser-capability-baseline.mjs) and generated [`COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#built-in-skills). | [`COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#built-in-skills), generated baseline block, README proof section, release docs. | `needsManagedSession` keeps read-only skills inspection sessionless while preserving thin upstream passthrough; upstream `@agent-browser/sandbox` remains external package guidance, not a bundled wrapper dependency. | Runtime and extension-validation skills/provider matrix; real-upstream inspection/skills group. | Supported. |
165
- | Core page, element, navigation, and extraction commands | Canonical tokens from baseline section `core-commands`; see [`scripts/agent-browser-capability-baseline.mjs`](../scripts/agent-browser-capability-baseline.mjs) and generated [`COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#core-page-and-element-commands). | [`COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#core-page-and-element-commands), [`TOOL_CONTRACT.md`](TOOL_CONTRACT.md), README quick start. | Thin passthrough with wrapper-owned JSON/session planning, ref guidance, artifact verification, page-change summaries, click-dispatch diagnostics only after native temporary-marker target identity readback (otherwise abstaining), inspection-only recovery for upstream overlay-blocked clicks, deterministic document scroll before wheel/no-op diagnostics and instant CSS-container movement, shorthand compilers, and redaction. | Real-upstream core matrix (including snapshot-ref select) plus fake core matrix for passthrough, ordering, diagnostics, and compiler validation. | Supported. Upstream semantics remain upstream-owned. |
166
- | Sessions, state, tabs, frames, dialogs, and windows | 28 canonical tokens from baseline section `state-tabs-frames-dialogs`; see [`scripts/agent-browser-capability-baseline.mjs`](../scripts/agent-browser-capability-baseline.mjs) and generated [`COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#session-state-frames-dialogs-windows-and-inspection-commands). | [`COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#session-state-frames-dialogs-windows-and-inspection-commands), stateful workflow notes, [`TOOL_CONTRACT.md`](TOOL_CONTRACT.md#details). | Stateful summaries redact credentials while preserving restore identifiers, every session/state list row, and ordinary `cookies set --curl` file operands in invocation echoes and failed batch diagnostics; explicit targets and paths pass through. Runtime retains state artifact verification, sessionless local command planning, automatic managed restore, native-CDP-ID tab recovery across duplicate URLs and transcript replay, reached failed-batch target invalidation/live verification, active-target refresh after tab close, and close alias cleanup. | Extension tab/ref tests, real-upstream stable-id/label tab lifecycle, runtime session/resume tests, presentation redaction tests, lifecycle harness. | Supported. External profile/auth state remains operator-owned. |
167
- | Network, storage, artifacts, diagnostics, and performance | Canonical tokens from baseline section `network-storage-artifacts-diagnostics`; see [`scripts/agent-browser-capability-baseline.mjs`](../scripts/agent-browser-capability-baseline.mjs) and generated [`COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#page-state-finding-mouse-settings-network-and-storage). | [`COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#page-state-finding-mouse-settings-network-and-storage), diagnostic sections, [`TOOL_CONTRACT.md`](TOOL_CONTRACT.md#details). | Thin passthrough plus native-owned click/download execution for all downloads (including loopback, Blob exports, and redirects), compact diagnostics with identical credential redaction for page/origin/URL-filtered details and exports, route-mock warnings, useful-but-redacted storage output, stream idempotency normalization, FPS/cursor/contact-sheet-aware recording destinations/pinning and contact-sheet image verification, truthful ref-refresh and missing-ffmpeg warnings, positive WebMCP navigation hints and catalog updates, sensitive-data redaction, timeout bounds, and cleanup-pair guidance. | Fake non-core matrix and safe real-upstream coverage for network/HAR, diff, trace/profiler, console/errors/highlight, stream, vitals, React missing-renderer, native FPS recording path/page checks and WebMCP navigation hints. | Supported. Environment-sensitive operations need suitable local/browser state. |
168
- | Batch, auth, confirmations, setup, dashboard, devices, and AI commands | Canonical tokens from baseline section `batch-auth-setup-ai`; see [`scripts/agent-browser-capability-baseline.mjs`](../scripts/agent-browser-capability-baseline.mjs) and generated [`COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#batch-auth-confirmations-sessions-chat-dashboard-devices-and-setup). | [`COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#batch-auth-confirmations-sessions-chat-dashboard-devices-and-setup), README security notes, release docs. | Native-tool batch stdin, generated QA/lookup batch plans, auth/confirmation redaction, sessionless local auth/setup/dashboard/doctor/plugin planning, upgrade-only native text normalization with error precedence and explicit-JSON results, plugin list/show JSON envelope normalization, bare-`mcp` validation with `mcp --help` preserved, timeout/cleanup guidance. | Parser/runtime plugin and MCP unit coverage; fake-upstream plugin list/show and MCP help/blocking coverage; registered upgrade text/success/nonzero/timeout/abort/JSON controls in `test/agent-browser.upgrade-output.test.ts`; real-upstream plugin list shape probe; structured input-mode tests. | Supported. Interactive side-effecting setup/auth/chat remains upstream-owned. `plugin` is local/sessionless; `mcp` is external-client-only except help; `auth login --credential-provider` resolves credentials via a plugin; `install --with-deps` failures remain upstream-owned. |
169
- | Global flags, config, providers, policy, and environment | Canonical tokens from baseline section `options-and-env`; see [`scripts/agent-browser-capability-baseline.mjs`](../scripts/agent-browser-capability-baseline.mjs) and generated [`COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#important-global-flags-config-and-environment). | [`COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#important-global-flags-config-and-environment), README provider/setup notes, [`TOOL_CONTRACT.md`](TOOL_CONTRACT.md#sessionmode), architecture/runtime docs. | Runtime preserves caller-requested JSON for early filters, scroll results, and preparation failures without output-file prose (help/version remains native text), and handles command discovery, value-flag prevalidation, launch-scoped flags, redacted echoes, fresh-session recovery hints, explicit sessions, provider/device launch-scoping, parent env forwarding with consistent managed idle-timeout/socket/operation-timeout overrides on top-level and helper subprocesses, subprocess completion, and package-owned Pi-scoped config for optional companion features. | Runtime tests for flags/planning/redaction/session behavior; process/ref tests for env consistency and stdio-linger completion; config/web-search/CLI tests; fake provider/specialized-skill matrix; package doctor. | Supported. Provider clouds, iOS/Appium, proxies, profiles, and credentials require external setup. |
169
+ | Baseline section | Baseline items | Documentation | Runtime handling | Test coverage | Validation status |
170
+ | ---------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
171
+ | Built-in skills | 19 canonical tokens from baseline section `skills`; see [`scripts/agent-browser-capability-baseline.mjs`](../scripts/agent-browser-capability-baseline.mjs) and generated [`COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#built-in-skills). | [`COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#built-in-skills), generated baseline block, README proof section, release docs. | `needsManagedSession` keeps read-only skills inspection sessionless while preserving thin upstream passthrough; upstream `@agent-browser/sandbox` remains external package guidance, not a bundled wrapper dependency. | Runtime and extension-validation skills/provider matrix; real-upstream inspection/skills group. | Supported. |
172
+ | Core page, element, navigation, and extraction commands | Canonical tokens from baseline section `core-commands`; see [`scripts/agent-browser-capability-baseline.mjs`](../scripts/agent-browser-capability-baseline.mjs) and generated [`COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#core-page-and-element-commands). | [`COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#core-page-and-element-commands), [`TOOL_CONTRACT.md`](TOOL_CONTRACT.md), README quick start. | Thin passthrough with wrapper-owned JSON/session planning, ref guidance, artifact verification, page-change summaries, click-dispatch diagnostics only after native temporary-marker target identity readback (otherwise abstaining), inspection-only recovery for upstream overlay-blocked clicks, deterministic document scroll before wheel/no-op diagnostics and instant CSS-container movement, shorthand compilers, and redaction. | Real-upstream core matrix (including snapshot-ref select) plus fake core matrix for passthrough, ordering, diagnostics, and compiler validation. | Supported. Upstream semantics remain upstream-owned. |
173
+ | Sessions, state, tabs, frames, dialogs, and windows | 28 canonical tokens from baseline section `state-tabs-frames-dialogs`; see [`scripts/agent-browser-capability-baseline.mjs`](../scripts/agent-browser-capability-baseline.mjs) and generated [`COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#session-state-frames-dialogs-windows-and-inspection-commands). | [`COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#session-state-frames-dialogs-windows-and-inspection-commands), stateful workflow notes, [`TOOL_CONTRACT.md`](TOOL_CONTRACT.md#details). | Stateful summaries redact credentials while preserving restore identifiers, every session/state list row, and ordinary `cookies set --curl` file operands in invocation echoes and failed batch diagnostics; explicit targets and paths pass through. Runtime retains state artifact verification, sessionless local command planning, automatic managed restore, native-CDP-ID tab recovery across duplicate URLs and transcript replay, reached failed-batch target invalidation/live verification, active-target refresh after tab close, and close alias cleanup. | Extension tab/ref tests, real-upstream stable-id/label tab lifecycle, runtime session/resume tests, presentation redaction tests, lifecycle harness. | Supported. External profile/auth state remains operator-owned. |
174
+ | Network, storage, artifacts, diagnostics, and performance | Canonical tokens from baseline section `network-storage-artifacts-diagnostics`; see [`scripts/agent-browser-capability-baseline.mjs`](../scripts/agent-browser-capability-baseline.mjs) and generated [`COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#page-state-finding-mouse-settings-network-and-storage). | [`COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#page-state-finding-mouse-settings-network-and-storage), diagnostic sections, [`TOOL_CONTRACT.md`](TOOL_CONTRACT.md#details). | Thin passthrough plus native-owned click/download execution for all downloads (including loopback, Blob exports, and redirects), compact diagnostics with identical credential redaction for page/origin/URL-filtered details and exports, route-mock warnings, useful-but-redacted storage output, stream idempotency normalization, FPS/cursor/contact-sheet-aware recording destinations/pinning and contact-sheet image verification, truthful ref-refresh and missing-ffmpeg warnings, positive WebMCP navigation hints and catalog updates, sensitive-data redaction, timeout bounds, and cleanup-pair guidance. | Fake non-core matrix and safe real-upstream coverage for network/HAR, diff, trace/profiler, console/errors/highlight, stream, vitals, React missing-renderer, native FPS recording path/page checks and WebMCP navigation hints. | Supported. Environment-sensitive operations need suitable local/browser state. |
175
+ | Batch, auth, confirmations, setup, dashboard, devices, and AI commands | Canonical tokens from baseline section `batch-auth-setup-ai`; see [`scripts/agent-browser-capability-baseline.mjs`](../scripts/agent-browser-capability-baseline.mjs) and generated [`COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#batch-auth-confirmations-sessions-chat-dashboard-devices-and-setup). | [`COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#batch-auth-confirmations-sessions-chat-dashboard-devices-and-setup), README security notes, release docs. | Native-tool batch stdin, generated QA/lookup batch plans, auth/confirmation redaction, sessionless local auth/setup/dashboard/doctor/plugin planning, upgrade-only native text normalization with error precedence and explicit-JSON results, plugin list/show JSON envelope normalization, bare-`mcp` validation with `mcp --help` preserved, timeout/cleanup guidance. | Parser/runtime plugin and MCP unit coverage; fake-upstream plugin list/show and MCP help/blocking coverage; registered upgrade text/success/nonzero/timeout/abort/JSON controls in `test/agent-browser.upgrade-output.test.ts`; real-upstream plugin list shape probe; structured input-mode tests. | Supported. Interactive side-effecting setup/auth/chat remains upstream-owned. `plugin` is local/sessionless; `mcp` is external-client-only except help; `auth login --credential-provider` resolves credentials via a plugin; `install --with-deps` failures remain upstream-owned. |
176
+ | Global flags, config, providers, policy, and environment | Canonical tokens from baseline section `options-and-env`; see [`scripts/agent-browser-capability-baseline.mjs`](../scripts/agent-browser-capability-baseline.mjs) and generated [`COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#important-global-flags-config-and-environment). | [`COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#important-global-flags-config-and-environment), README provider/setup notes, [`TOOL_CONTRACT.md`](TOOL_CONTRACT.md#sessionmode), architecture/runtime docs. | Runtime preserves caller-requested JSON for early filters, scroll results, and preparation failures without output-file prose (help/version remains native text), and handles command discovery, value-flag prevalidation, launch-scoped flags, redacted echoes, fresh-session recovery hints, explicit sessions, provider/device launch-scoping, parent env forwarding with consistent managed idle-timeout/socket/operation-timeout overrides and per-call explicit policy/confirmation context on top-level and helper subprocesses, subprocess completion, and package-owned Pi-scoped config for optional companion features. | Runtime tests for flags/planning/redaction/session behavior; process/ref tests for env consistency and stdio-linger completion; config/web-search/CLI tests; fake provider/specialized-skill matrix; package doctor. | Supported. Provider clouds, iOS/Appium, proxies, profiles, and credentials require external setup. |
170
177
 
171
178
  ## Follow-up decision after closure
172
179
 
173
180
  The compact decision index lives at [`docs/support-notes.md`](https://github.com/fitchmultz/pi-agent-browser-native/blob/main/docs/support-notes.md). Keep this section as the active index of shipped follow-up areas and their canonical contracts.
174
181
 
175
- | Area | Active contract | Decision index |
176
- | --- | --- | --- |
177
- | Compact direct/code tools and five discoverable flat advanced tools | [`TOOL_CONTRACT.md`](TOOL_CONTRACT.md), [`COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md) | [`docs/support-notes.md`](https://github.com/fitchmultz/pi-agent-browser-native/blob/main/docs/support-notes.md) |
178
- | Electron lifecycle, manual CDP attach, desktop readiness, and tab/surface recovery | [`ELECTRON.md`](ELECTRON.md), [`TOOL_CONTRACT.md`](TOOL_CONTRACT.md#agent_browser_electron), [`COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#electron-desktop-apps) | [`docs/support-notes.md`](https://github.com/fitchmultz/pi-agent-browser-native/blob/main/docs/support-notes.md) |
179
- | Ref lifecycle, click dispatch (eligible ref or XPath candidates require native marker identity readback; unproven identity abstains), selector recovery, rich inputs, and dense snapshots | [`TOOL_CONTRACT.md`](TOOL_CONTRACT.md#details), [`COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#selector-strategy), README pitfalls | [`docs/support-notes.md`](https://github.com/fitchmultz/pi-agent-browser-native/blob/main/docs/support-notes.md) |
180
- | Diagnostics, artifacts, QA/network classification, timeout recovery, scroll/combobox/recording guidance | [`TOOL_CONTRACT.md`](TOOL_CONTRACT.md#details), [`COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md), [`RELEASE.md`](RELEASE.md) | [`docs/support-notes.md`](https://github.com/fitchmultz/pi-agent-browser-native/blob/main/docs/support-notes.md) |
181
- | Package config and optional web search, including the default Exa mode and bounded filters | [`TOOL_CONTRACT.md`](TOOL_CONTRACT.md#optional-companion-web-search), README optional package config, [`COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#optional-package-config-and-companion-web-search) | [`docs/support-notes.md`](https://github.com/fitchmultz/pi-agent-browser-native/blob/main/docs/support-notes.md) |
182
+ | Area | Active contract | Decision index |
183
+ | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------- |
184
+ | Compact direct/code tools and five discoverable flat advanced tools | [`TOOL_CONTRACT.md`](TOOL_CONTRACT.md), [`COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md) | [`docs/support-notes.md`](https://github.com/fitchmultz/pi-agent-browser-native/blob/main/docs/support-notes.md) |
185
+ | Electron lifecycle, manual CDP attach, desktop readiness, and tab/surface recovery | [`ELECTRON.md`](ELECTRON.md), [`TOOL_CONTRACT.md`](TOOL_CONTRACT.md#agent_browser_electron), [`COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#electron-desktop-apps) | [`docs/support-notes.md`](https://github.com/fitchmultz/pi-agent-browser-native/blob/main/docs/support-notes.md) |
186
+ | Ref lifecycle, click dispatch (eligible ref or XPath candidates require native marker identity readback; unproven identity abstains), selector recovery, rich inputs, and dense snapshots | [`TOOL_CONTRACT.md`](TOOL_CONTRACT.md#details), [`COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#selector-strategy), README pitfalls | [`docs/support-notes.md`](https://github.com/fitchmultz/pi-agent-browser-native/blob/main/docs/support-notes.md) |
187
+ | Diagnostics, artifacts, QA/network classification, timeout recovery, scroll/combobox/recording guidance | [`TOOL_CONTRACT.md`](TOOL_CONTRACT.md#details), [`COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md), [`RELEASE.md`](RELEASE.md) | [`docs/support-notes.md`](https://github.com/fitchmultz/pi-agent-browser-native/blob/main/docs/support-notes.md) |
188
+ | Package config and optional web search, including the default Exa mode and bounded filters | [`TOOL_CONTRACT.md`](TOOL_CONTRACT.md#optional-companion-web-search), README optional package config, [`COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#optional-package-config-and-companion-web-search) | [`docs/support-notes.md`](https://github.com/fitchmultz/pi-agent-browser-native/blob/main/docs/support-notes.md) |