@chankov/agent-fleet 0.0.9 → 0.0.10

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 (354) hide show
  1. package/.claude/commands/doctor-agent-fleet.md +12 -7
  2. package/.claude/commands/setup-agent-fleet.md +7 -15
  3. package/.opencode/commands/af-doctor-agent-fleet.md +12 -7
  4. package/.opencode/commands/af-setup-agent-fleet.md +8 -6
  5. package/.pi/extensions/agent-fleet-update-check/README.md +2 -3
  6. package/.pi/extensions/btw/README.md +2 -2
  7. package/.pi/extensions/chrome-devtools-mcp/README.md +3 -6
  8. package/.pi/extensions/compact-and-continue/README.md +3 -3
  9. package/.pi/extensions/mcp-bridge/README.md +1 -1
  10. package/.pi/harnesses/agent-hub/README.md +139 -10
  11. package/.pi/harnesses/agent-hub/docs-lane.js +122 -0
  12. package/.pi/harnesses/agent-hub/external-blocker.js +85 -0
  13. package/.pi/harnesses/agent-hub/index.ts +448 -39
  14. package/.pi/harnesses/agent-hub/package.json +1 -1
  15. package/.pi/harnesses/agent-hub/review-findings.js +102 -0
  16. package/.pi/harnesses/agent-hub/run-budget.js +302 -4
  17. package/.pi/harnesses/agent-hub/run-namespace.js +87 -0
  18. package/.pi/harnesses/coms/package.json +1 -1
  19. package/.pi/harnesses/damage-control-continue/package.json +1 -1
  20. package/.pi/prompts/af-doctor-agent-fleet.md +13 -6
  21. package/.pi/prompts/af-setup-agent-fleet.md +7 -15
  22. package/.versions/0.0.10/.claude/commands/build.md +44 -0
  23. package/.versions/0.0.10/.claude/commands/code-simplify.md +22 -0
  24. package/.versions/0.0.10/.claude/commands/design-agent.md +14 -0
  25. package/.versions/0.0.10/.claude/commands/doctor-agent-fleet.md +22 -0
  26. package/.versions/0.0.10/.claude/commands/orchestrate.md +112 -0
  27. package/.versions/0.0.10/.claude/commands/plan.md +16 -0
  28. package/.versions/0.0.10/.claude/commands/prime.md +22 -0
  29. package/.versions/0.0.10/.claude/commands/review.md +16 -0
  30. package/.versions/0.0.10/.claude/commands/set-hermes-telegram.md +15 -0
  31. package/.versions/0.0.10/.claude/commands/set-hermes-watchdog.md +6 -0
  32. package/.versions/0.0.10/.claude/commands/setup-agent-fleet.md +17 -0
  33. package/.versions/0.0.10/.claude/commands/ship.md +72 -0
  34. package/.versions/0.0.10/.claude/commands/spec.md +15 -0
  35. package/.versions/0.0.10/.claude/commands/test.md +19 -0
  36. package/.versions/0.0.10/.claude/commands/webperf.md +32 -0
  37. package/.versions/0.0.10/.claude/orchestrate-teams.yaml +24 -0
  38. package/.versions/0.0.10/.opencode/commands/af-build.md +17 -0
  39. package/.versions/0.0.10/.opencode/commands/af-code-simplify.md +16 -0
  40. package/.versions/0.0.10/.opencode/commands/af-compound.md +16 -0
  41. package/.versions/0.0.10/.opencode/commands/af-design-agent.md +15 -0
  42. package/.versions/0.0.10/.opencode/commands/af-doctor-agent-fleet.md +22 -0
  43. package/.versions/0.0.10/.opencode/commands/af-orchestrate.md +112 -0
  44. package/.versions/0.0.10/.opencode/commands/af-plan.md +16 -0
  45. package/.versions/0.0.10/.opencode/commands/af-prime.md +22 -0
  46. package/.versions/0.0.10/.opencode/commands/af-review.md +15 -0
  47. package/.versions/0.0.10/.opencode/commands/af-set-hermes-telegram.md +15 -0
  48. package/.versions/0.0.10/.opencode/commands/af-set-hermes-watchdog.md +6 -0
  49. package/.versions/0.0.10/.opencode/commands/af-setup-agent-fleet.md +17 -0
  50. package/.versions/0.0.10/.opencode/commands/af-ship.md +16 -0
  51. package/.versions/0.0.10/.opencode/commands/af-spec.md +16 -0
  52. package/.versions/0.0.10/.opencode/commands/af-test.md +21 -0
  53. package/.versions/0.0.10/.opencode/commands/af-webperf.md +32 -0
  54. package/.versions/0.0.10/.opencode/orchestrate-teams.yaml +24 -0
  55. package/.versions/0.0.10/.pi/agents/dispatch-policy.yaml +32 -0
  56. package/.versions/0.0.10/.pi/agents/model-profiles.yaml +27 -0
  57. package/.versions/0.0.10/.pi/agents/peers.yaml +142 -0
  58. package/.versions/0.0.10/.pi/agents/teams.yaml +41 -0
  59. package/.versions/0.0.10/.pi/damage-control-rules.yaml +297 -0
  60. package/.versions/0.0.10/.pi/extensions/agent-fleet-update-check/README.md +57 -0
  61. package/.versions/0.0.10/.pi/extensions/agent-fleet-update-check/index.ts +161 -0
  62. package/.versions/0.0.10/.pi/extensions/agent-fleet-update-check/package.json +6 -0
  63. package/.versions/0.0.10/.pi/extensions/btw/README.md +118 -0
  64. package/.versions/0.0.10/.pi/extensions/btw/index.ts +917 -0
  65. package/.versions/0.0.10/.pi/extensions/btw/package.json +6 -0
  66. package/.versions/0.0.10/.pi/extensions/btw/state.js +179 -0
  67. package/.versions/0.0.10/.pi/extensions/chrome-devtools-mcp/README.md +55 -0
  68. package/.versions/0.0.10/.pi/extensions/chrome-devtools-mcp/index.ts +93 -0
  69. package/.versions/0.0.10/.pi/extensions/chrome-devtools-mcp/package.json +6 -0
  70. package/.versions/0.0.10/.pi/extensions/compact-and-continue/README.md +42 -0
  71. package/.versions/0.0.10/.pi/extensions/compact-and-continue/index.ts +120 -0
  72. package/.versions/0.0.10/.pi/extensions/compact-and-continue/package.json +6 -0
  73. package/.versions/0.0.10/.pi/extensions/mcp-bridge/README.md +46 -0
  74. package/.versions/0.0.10/.pi/extensions/mcp-bridge/index.ts +206 -0
  75. package/.versions/0.0.10/.pi/extensions/mcp-bridge/package.json +6 -0
  76. package/.versions/0.0.10/.pi/extensions/package-lock.json +1143 -0
  77. package/.versions/0.0.10/.pi/extensions/package.json +9 -0
  78. package/.versions/0.0.10/.pi/extensions/pi-voice-stt/README.md +201 -0
  79. package/.versions/0.0.10/.pi/extensions/pi-voice-stt/config.ts +198 -0
  80. package/.versions/0.0.10/.pi/extensions/pi-voice-stt/examples/stt.json +35 -0
  81. package/.versions/0.0.10/.pi/extensions/pi-voice-stt/index.ts +248 -0
  82. package/.versions/0.0.10/.pi/extensions/pi-voice-stt/package.json +6 -0
  83. package/.versions/0.0.10/.pi/extensions/pi-voice-stt/providers.ts +214 -0
  84. package/.versions/0.0.10/.pi/extensions/pi-voice-stt/recorder.ts +158 -0
  85. package/.versions/0.0.10/.pi/harnesses/agent-hub/README.md +1001 -0
  86. package/.versions/0.0.10/.pi/harnesses/agent-hub/access-approval.ts +135 -0
  87. package/.versions/0.0.10/.pi/harnesses/agent-hub/artifacts.js +146 -0
  88. package/.versions/0.0.10/.pi/harnesses/agent-hub/assertion-ledger.js +58 -0
  89. package/.versions/0.0.10/.pi/harnesses/agent-hub/backend-policy.js +153 -0
  90. package/.versions/0.0.10/.pi/harnesses/agent-hub/context-window.js +106 -0
  91. package/.versions/0.0.10/.pi/harnesses/agent-hub/delegate.ts +435 -0
  92. package/.versions/0.0.10/.pi/harnesses/agent-hub/docs-lane.js +122 -0
  93. package/.versions/0.0.10/.pi/harnesses/agent-hub/drift-watchdog.js +211 -0
  94. package/.versions/0.0.10/.pi/harnesses/agent-hub/evidence-rules.js +96 -0
  95. package/.versions/0.0.10/.pi/harnesses/agent-hub/external-blocker.js +85 -0
  96. package/.versions/0.0.10/.pi/harnesses/agent-hub/footer.ts +31 -0
  97. package/.versions/0.0.10/.pi/harnesses/agent-hub/helpers.ts +248 -0
  98. package/.versions/0.0.10/.pi/harnesses/agent-hub/index.ts +9111 -0
  99. package/.versions/0.0.10/.pi/harnesses/agent-hub/monitor-control.ts +9 -0
  100. package/.versions/0.0.10/.pi/harnesses/agent-hub/monitor-invoke-journal.ts +131 -0
  101. package/.versions/0.0.10/.pi/harnesses/agent-hub/monitor-invoke.ts +92 -0
  102. package/.versions/0.0.10/.pi/harnesses/agent-hub/monitor-lifecycle.ts +13 -0
  103. package/.versions/0.0.10/.pi/harnesses/agent-hub/monitor-publisher.ts +59 -0
  104. package/.versions/0.0.10/.pi/harnesses/agent-hub/monitor-recovery.ts +3 -0
  105. package/.versions/0.0.10/.pi/harnesses/agent-hub/monitor-runtime.ts +3 -0
  106. package/.versions/0.0.10/.pi/harnesses/agent-hub/monitor-session-bridge.ts +257 -0
  107. package/.versions/0.0.10/.pi/harnesses/agent-hub/package.json +7 -0
  108. package/.versions/0.0.10/.pi/harnesses/agent-hub/provider-semaphore.js +138 -0
  109. package/.versions/0.0.10/.pi/harnesses/agent-hub/research-retention.js +34 -0
  110. package/.versions/0.0.10/.pi/harnesses/agent-hub/research-watchdog.ts +40 -0
  111. package/.versions/0.0.10/.pi/harnesses/agent-hub/return-contract.js +293 -0
  112. package/.versions/0.0.10/.pi/harnesses/agent-hub/return-extract.js +75 -0
  113. package/.versions/0.0.10/.pi/harnesses/agent-hub/review-findings.js +102 -0
  114. package/.versions/0.0.10/.pi/harnesses/agent-hub/run-budget.js +479 -0
  115. package/.versions/0.0.10/.pi/harnesses/agent-hub/run-namespace.js +87 -0
  116. package/.versions/0.0.10/.pi/harnesses/agent-hub/safety-routing.ts +22 -0
  117. package/.versions/0.0.10/.pi/harnesses/agent-hub/scope-gate.js +103 -0
  118. package/.versions/0.0.10/.pi/harnesses/agent-hub/session-health.js +110 -0
  119. package/.versions/0.0.10/.pi/harnesses/agent-hub/spawn.ts +354 -0
  120. package/.versions/0.0.10/.pi/harnesses/agent-hub/version.ts +42 -0
  121. package/.versions/0.0.10/.pi/harnesses/ask-user-remote/README.md +19 -0
  122. package/.versions/0.0.10/.pi/harnesses/ask-user-remote/index.ts +321 -0
  123. package/.versions/0.0.10/.pi/harnesses/ask-user-remote/race-core.js +106 -0
  124. package/.versions/0.0.10/.pi/harnesses/coms/README.md +100 -0
  125. package/.versions/0.0.10/.pi/harnesses/coms/index.ts +1767 -0
  126. package/.versions/0.0.10/.pi/harnesses/coms/package.json +7 -0
  127. package/.versions/0.0.10/.pi/harnesses/coms/version.ts +42 -0
  128. package/.versions/0.0.10/.pi/harnesses/damage-control-continue/README.md +124 -0
  129. package/.versions/0.0.10/.pi/harnesses/damage-control-continue/index.ts +536 -0
  130. package/.versions/0.0.10/.pi/harnesses/damage-control-continue/package.json +7 -0
  131. package/.versions/0.0.10/.pi/harnesses/damage-control-continue/version.ts +42 -0
  132. package/.versions/0.0.10/.pi/harnesses/lib/coms-registry-entry.ts +94 -0
  133. package/.versions/0.0.10/.pi/harnesses/lib/damage-control-shared.ts +197 -0
  134. package/.versions/0.0.10/.pi/harnesses/lib/herdr-client.ts +472 -0
  135. package/.versions/0.0.10/.pi/harnesses/lib/herdr-presence.ts +399 -0
  136. package/.versions/0.0.10/.pi/harnesses/lib/hermes-monitor-events.ts +136 -0
  137. package/.versions/0.0.10/.pi/harnesses/lib/hermes-monitor-herdr.ts +28 -0
  138. package/.versions/0.0.10/.pi/harnesses/lib/hermes-monitor-model.ts +18 -0
  139. package/.versions/0.0.10/.pi/harnesses/lib/hermes-monitor-registry.ts +6 -0
  140. package/.versions/0.0.10/.pi/harnesses/lib/hermes-monitor-socket.ts +163 -0
  141. package/.versions/0.0.10/.pi/harnesses/lib/hermes-monitor-store.ts +31 -0
  142. package/.versions/0.0.10/.pi/harnesses/lib/spawned-peers.js +190 -0
  143. package/.versions/0.0.10/.pi/harnesses/package-lock.json +35 -0
  144. package/.versions/0.0.10/.pi/harnesses/package.json +9 -0
  145. package/.versions/0.0.10/.pi/prompts/af-build.md +24 -0
  146. package/.versions/0.0.10/.pi/prompts/af-code-simplify.md +22 -0
  147. package/.versions/0.0.10/.pi/prompts/af-doctor-agent-fleet.md +22 -0
  148. package/.versions/0.0.10/.pi/prompts/af-plan.md +16 -0
  149. package/.versions/0.0.10/.pi/prompts/af-review.md +16 -0
  150. package/.versions/0.0.10/.pi/prompts/af-set-hermes-telegram.md +15 -0
  151. package/.versions/0.0.10/.pi/prompts/af-set-hermes-watchdog.md +6 -0
  152. package/.versions/0.0.10/.pi/prompts/af-setup-agent-fleet.md +19 -0
  153. package/.versions/0.0.10/.pi/prompts/af-ship.md +17 -0
  154. package/.versions/0.0.10/.pi/prompts/af-spec.md +15 -0
  155. package/.versions/0.0.10/.pi/prompts/af-test.md +19 -0
  156. package/.versions/0.0.10/.pi/skills/bowser/SKILL.md +145 -0
  157. package/.versions/0.0.10/.version +1 -0
  158. package/.versions/0.0.10/agents/architect.md +24 -0
  159. package/.versions/0.0.10/agents/bowser.md +27 -0
  160. package/.versions/0.0.10/agents/builder.md +54 -0
  161. package/.versions/0.0.10/agents/code-reviewer.md +208 -0
  162. package/.versions/0.0.10/agents/deep-researcher.md +32 -0
  163. package/.versions/0.0.10/agents/documenter.md +18 -0
  164. package/.versions/0.0.10/agents/orchestrator.md +72 -0
  165. package/.versions/0.0.10/agents/plan-reviewer.md +83 -0
  166. package/.versions/0.0.10/agents/planner.md +70 -0
  167. package/.versions/0.0.10/agents/releaser.md +24 -0
  168. package/.versions/0.0.10/agents/researcher.md +28 -0
  169. package/.versions/0.0.10/agents/security-auditor.md +167 -0
  170. package/.versions/0.0.10/agents/test-engineer.md +153 -0
  171. package/.versions/0.0.10/agents/web-debugger.md +43 -0
  172. package/.versions/0.0.10/agents/web-performance-auditor.md +193 -0
  173. package/.versions/0.0.10/codex/CONDUCTOR.md +148 -0
  174. package/.versions/0.0.10/docs/ARCHITECTURE.md +303 -0
  175. package/.versions/0.0.10/docs/agent-fleet-setup.md +377 -0
  176. package/.versions/0.0.10/docs/claude-code-coms-bridge.md +109 -0
  177. package/.versions/0.0.10/docs/codex-remote-conductor.md +170 -0
  178. package/.versions/0.0.10/docs/coms-hermes-bridge.md +189 -0
  179. package/.versions/0.0.10/docs/getting-started.md +254 -0
  180. package/.versions/0.0.10/docs/npm-install.md +514 -0
  181. package/.versions/0.0.10/docs/opencode-setup.md +281 -0
  182. package/.versions/0.0.10/docs/pi-extensions.md +363 -0
  183. package/.versions/0.0.10/docs/pi-setup.md +571 -0
  184. package/.versions/0.0.10/docs/skill-anatomy.md +150 -0
  185. package/.versions/0.0.10/hermes/README.md +347 -0
  186. package/.versions/0.0.10/hermes/desktop-plugins/agent-fleet-herdr/plugin.js +1291 -0
  187. package/.versions/0.0.10/hermes/desktop-plugins/agent-fleet-herdr/presentation.js +672 -0
  188. package/.versions/0.0.10/hermes/desktop-plugins/agent-fleet-monitor/plugin.js +19 -0
  189. package/.versions/0.0.10/hermes/desktop-plugins/agent-fleet-monitor/state.js +10 -0
  190. package/.versions/0.0.10/hermes/gates/gate-o-capability.md +8 -0
  191. package/.versions/0.0.10/hermes/gates/gate-o-validator-fixtures.json +1 -0
  192. package/.versions/0.0.10/hermes/plugins/agent-fleet-herdr/dashboard/activity.py +770 -0
  193. package/.versions/0.0.10/hermes/plugins/agent-fleet-herdr/dashboard/coms_registry.py +134 -0
  194. package/.versions/0.0.10/hermes/plugins/agent-fleet-herdr/dashboard/coms_send.py +350 -0
  195. package/.versions/0.0.10/hermes/plugins/agent-fleet-herdr/dashboard/herdr_source.py +193 -0
  196. package/.versions/0.0.10/hermes/plugins/agent-fleet-herdr/dashboard/manifest.json +4 -0
  197. package/.versions/0.0.10/hermes/plugins/agent-fleet-herdr/dashboard/plugin_api.py +444 -0
  198. package/.versions/0.0.10/hermes/plugins/agent-fleet-herdr/dashboard/sessions.py +205 -0
  199. package/.versions/0.0.10/hermes/plugins/agent-fleet-herdr/dashboard/tasks.py +300 -0
  200. package/.versions/0.0.10/hermes/plugins/agent-fleet-herdr/dashboard/watch.py +819 -0
  201. package/.versions/0.0.10/hermes/plugins/agent-fleet-herdr/plugin.yaml +8 -0
  202. package/.versions/0.0.10/hermes/plugins/agent-fleet-monitor/dashboard/adapter.py +139 -0
  203. package/.versions/0.0.10/hermes/plugins/agent-fleet-monitor/dashboard/manifest.json +11 -0
  204. package/.versions/0.0.10/hermes/plugins/agent-fleet-monitor/dashboard/plugin_api.py +50 -0
  205. package/.versions/0.0.10/hermes/skills/hub-conductor/SKILL.md +84 -0
  206. package/.versions/0.0.10/hermes/skills/hub-liaison/SKILL.md +84 -0
  207. package/.versions/0.0.10/hermes/skills/hub-watchdog/SKILL.md +76 -0
  208. package/.versions/0.0.10/hermes/skills/hub-watchdog/manifest.json +1 -0
  209. package/.versions/0.0.10/hermes/skills/hub-watchdog/scripts/watchdog.py +249 -0
  210. package/.versions/0.0.10/hermes/skills/hub-watchdog/scripts/watchdog_actions.py +124 -0
  211. package/.versions/0.0.10/hermes/skills/hub-watchdog/scripts/watchdog_contract.py +76 -0
  212. package/.versions/0.0.10/hermes/skills/hub-watchdog/scripts/watchdog_delivery.py +10 -0
  213. package/.versions/0.0.10/hermes/skills/hub-watchdog/scripts/watchdog_engine.py +128 -0
  214. package/.versions/0.0.10/hermes/skills/hub-watchdog/scripts/watchdog_judgment.py +41 -0
  215. package/.versions/0.0.10/hermes/skills/hub-watchdog/scripts/watchdog_recovery.py +103 -0
  216. package/.versions/0.0.10/hermes/skills/hub-watchdog/scripts/watchdog_state.py +163 -0
  217. package/.versions/0.0.10/hermes/skills/hub-watchdog/scripts/watchdog_transport.py +138 -0
  218. package/.versions/0.0.10/hermes/watchdog-tests/__init__.py +0 -0
  219. package/.versions/0.0.10/hooks/SIMPLIFY-IGNORE.md +90 -0
  220. package/.versions/0.0.10/hooks/coms-stop-hook.mjs +84 -0
  221. package/.versions/0.0.10/hooks/hooks.json +14 -0
  222. package/.versions/0.0.10/hooks/session-start.sh +74 -0
  223. package/.versions/0.0.10/hooks/simplify-ignore.sh +302 -0
  224. package/.versions/0.0.10/install-manifest.json +3615 -0
  225. package/.versions/0.0.10/justfile +254 -0
  226. package/.versions/0.0.10/manifest-meta.json +472 -0
  227. package/.versions/0.0.10/references/accessibility-checklist.md +160 -0
  228. package/.versions/0.0.10/references/definition-of-done.md +67 -0
  229. package/.versions/0.0.10/references/fleet-coordination-patterns.md +151 -0
  230. package/.versions/0.0.10/references/observability-checklist.md +91 -0
  231. package/.versions/0.0.10/references/orchestration-patterns.md +370 -0
  232. package/.versions/0.0.10/references/performance-checklist.md +153 -0
  233. package/.versions/0.0.10/references/prompting-patterns.md +380 -0
  234. package/.versions/0.0.10/references/security-checklist.md +179 -0
  235. package/.versions/0.0.10/references/testing-patterns.md +236 -0
  236. package/.versions/0.0.10/scripts/codex-conductor.ts +41 -0
  237. package/.versions/0.0.10/scripts/codex-remote-control.ts +167 -0
  238. package/.versions/0.0.10/scripts/coms-claude-bridge.ts +401 -0
  239. package/.versions/0.0.10/scripts/coms-cli.ts +484 -0
  240. package/.versions/0.0.10/scripts/coms-hermes-bridge.ts +413 -0
  241. package/.versions/0.0.10/scripts/fleet.ts +168 -0
  242. package/.versions/0.0.10/scripts/hermes-monitor-capability-runner.ts +25 -0
  243. package/.versions/0.0.10/scripts/hermes-monitor-scenario.ts +474 -0
  244. package/.versions/0.0.10/scripts/hermes-watchdog-capability-probe.ts +45 -0
  245. package/.versions/0.0.10/scripts/install-hermes-plugin.sh +180 -0
  246. package/.versions/0.0.10/scripts/lib/claude-bridge-core.ts +165 -0
  247. package/.versions/0.0.10/scripts/lib/codex-conductor.ts +88 -0
  248. package/.versions/0.0.10/scripts/lib/codex-remote-control.ts +480 -0
  249. package/.versions/0.0.10/scripts/lib/coms-envelope.ts +582 -0
  250. package/.versions/0.0.10/scripts/lib/fake-herdr-server.ts +88 -0
  251. package/.versions/0.0.10/scripts/lib/fleet-command.ts +111 -0
  252. package/.versions/0.0.10/scripts/lib/herdr-layout.ts +281 -0
  253. package/.versions/0.0.10/scripts/lib/hermes-bridge-core.ts +241 -0
  254. package/.versions/0.0.10/scripts/lib/hermes-monitor-events.ts +1 -0
  255. package/.versions/0.0.10/scripts/lib/hermes-monitor-herdr.ts +2 -0
  256. package/.versions/0.0.10/scripts/lib/hermes-monitor-model.ts +3 -0
  257. package/.versions/0.0.10/scripts/lib/hermes-monitor-registry.ts +2 -0
  258. package/.versions/0.0.10/scripts/lib/hermes-monitor-socket.ts +2 -0
  259. package/.versions/0.0.10/scripts/lib/hermes-monitor-store.ts +2 -0
  260. package/.versions/0.0.10/scripts/lib/monitor-env.ts +120 -0
  261. package/.versions/0.0.10/scripts/lib/peer-launch.ts +314 -0
  262. package/.versions/0.0.10/scripts/lib/persona-banner.ts +62 -0
  263. package/.versions/0.0.10/scripts/lib/spawn-stagger.ts +101 -0
  264. package/.versions/0.0.10/scripts/lib/team-project.ts +193 -0
  265. package/.versions/0.0.10/scripts/lib/team-snapshot.ts +147 -0
  266. package/.versions/0.0.10/scripts/peer-banner.ts +40 -0
  267. package/.versions/0.0.10/scripts/peer-launch.ts +259 -0
  268. package/.versions/0.0.10/scripts/team-snapshot.ts +237 -0
  269. package/.versions/0.0.10/scripts/team-up.ts +360 -0
  270. package/.versions/0.0.10/skills/_internal/grilling.md +11 -0
  271. package/.versions/0.0.10/skills/browser-testing-with-devtools/SKILL.md +351 -0
  272. package/.versions/0.0.10/skills/code-review-and-quality/SKILL.md +381 -0
  273. package/.versions/0.0.10/skills/compound-learning/SKILL.md +137 -0
  274. package/.versions/0.0.10/skills/context-engineering/SKILL.md +291 -0
  275. package/.versions/0.0.10/skills/deprecation-and-migration/SKILL.md +206 -0
  276. package/.versions/0.0.10/skills/designing-agents/SKILL.md +394 -0
  277. package/.versions/0.0.10/skills/designing-agents/pi-harness-authoring.md +222 -0
  278. package/.versions/0.0.10/skills/frontend-ui-engineering/SKILL.md +328 -0
  279. package/.versions/0.0.10/skills/git-workflow-and-versioning/SKILL.md +316 -0
  280. package/.versions/0.0.10/skills/guided-workspace-setup/SKILL.md +226 -0
  281. package/.versions/0.0.10/skills/guided-workspace-setup/companion-manifest.json +38 -0
  282. package/.versions/0.0.10/skills/idea-refine/SKILL.md +182 -0
  283. package/.versions/0.0.10/skills/idea-refine/examples.md +238 -0
  284. package/.versions/0.0.10/skills/idea-refine/frameworks.md +99 -0
  285. package/.versions/0.0.10/skills/idea-refine/refinement-criteria.md +113 -0
  286. package/.versions/0.0.10/skills/idea-refine/scripts/idea-refine.sh +15 -0
  287. package/.versions/0.0.10/skills/incremental-implementation/SKILL.md +287 -0
  288. package/.versions/0.0.10/skills/interview-me/SKILL.md +226 -0
  289. package/.versions/0.0.10/skills/orchestration-verification/SKILL.md +181 -0
  290. package/.versions/0.0.10/skills/peer-coms/SKILL.md +90 -0
  291. package/.versions/0.0.10/skills/performance-optimization/SKILL.md +350 -0
  292. package/.versions/0.0.10/skills/planning-and-task-breakdown/SKILL.md +254 -0
  293. package/.versions/0.0.10/skills/security-and-hardening/SKILL.md +461 -0
  294. package/.versions/0.0.10/skills/spec-driven-development/SKILL.md +257 -0
  295. package/.versions/0.0.10/skills/using-agent-skills/SKILL.md +199 -0
  296. package/.versions/0.0.10/systemd/user/agent-fleet-codex-remote-control.service.in +23 -0
  297. package/.versions/0.0.10/vendor/agent-skills-upstream/LICENSE +21 -0
  298. package/.versions/0.0.10/vendor/agent-skills-upstream/README.md +11 -0
  299. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/api-and-interface-design/SKILL.md +294 -0
  300. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/browser-testing-with-devtools/SKILL.md +317 -0
  301. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/ci-cd-and-automation/SKILL.md +390 -0
  302. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/code-review-and-quality/SKILL.md +396 -0
  303. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/code-simplification/SKILL.md +331 -0
  304. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/context-engineering/SKILL.md +289 -0
  305. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/debugging-and-error-recovery/SKILL.md +300 -0
  306. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/deprecation-and-migration/SKILL.md +247 -0
  307. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/documentation-and-adrs/SKILL.md +278 -0
  308. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/doubt-driven-development/SKILL.md +243 -0
  309. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/frontend-ui-engineering/SKILL.md +328 -0
  310. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/git-workflow-and-versioning/SKILL.md +355 -0
  311. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/idea-refine/SKILL.md +178 -0
  312. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/idea-refine/examples.md +238 -0
  313. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/idea-refine/frameworks.md +99 -0
  314. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/idea-refine/refinement-criteria.md +113 -0
  315. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/idea-refine/scripts/idea-refine.sh +15 -0
  316. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/incremental-implementation/SKILL.md +249 -0
  317. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/interview-me/SKILL.md +225 -0
  318. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/observability-and-instrumentation/SKILL.md +203 -0
  319. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/performance-optimization/SKILL.md +350 -0
  320. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/planning-and-task-breakdown/SKILL.md +234 -0
  321. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/security-and-hardening/SKILL.md +467 -0
  322. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/shipping-and-launch/SKILL.md +310 -0
  323. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/source-driven-development/SKILL.md +194 -0
  324. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/spec-driven-development/SKILL.md +206 -0
  325. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/test-driven-development/SKILL.md +383 -0
  326. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/using-agent-skills/SKILL.md +191 -0
  327. package/CHANGELOG.md +103 -0
  328. package/README.md +22 -5
  329. package/agents/code-reviewer.md +4 -0
  330. package/agents/orchestrator.md +7 -1
  331. package/agents/plan-reviewer.md +22 -1
  332. package/bin/build-manifest.js +68 -0
  333. package/bin/cli.js +679 -49
  334. package/bin/lib/apply.js +641 -0
  335. package/bin/lib/manifest.js +731 -0
  336. package/bin/lib/merge-forms.js +106 -0
  337. package/bin/lib/plan.js +569 -0
  338. package/bin/lib/state.js +213 -0
  339. package/bin/lib/verify.js +576 -0
  340. package/bin/snapshot-version.js +5 -0
  341. package/docs/ARCHITECTURE.md +52 -11
  342. package/docs/agent-fleet-setup.md +59 -48
  343. package/docs/getting-started.md +29 -6
  344. package/docs/npm-install.md +208 -31
  345. package/docs/opencode-setup.md +32 -0
  346. package/docs/pi-extensions.md +17 -10
  347. package/docs/pi-setup.md +164 -69
  348. package/install-manifest.json +3615 -0
  349. package/manifest-meta.json +472 -0
  350. package/package.json +8 -3
  351. package/skills/browser-testing-with-devtools/SKILL.md +3 -4
  352. package/skills/guided-workspace-setup/SKILL.md +172 -490
  353. package/skills/planning-and-task-breakdown/SKILL.md +18 -0
  354. package/skills/spec-driven-development/SKILL.md +12 -0
@@ -3,5 +3,5 @@
3
3
  "private": true,
4
4
  "type": "module",
5
5
  "main": "index.ts",
6
- "version": "0.0.9"
6
+ "version": "0.0.10"
7
7
  }
@@ -0,0 +1,102 @@
1
+ // Review-finding accounting — counts what a review actually returned so the hub
2
+ // can say, in the dispatch result, whether the finding budget was honored.
3
+ //
4
+ // This module deliberately COUNTS and REPORTS; it never rewrites a review. The
5
+ // tempting version — cap the blocking findings and auto-relabel the overflow as
6
+ // non-blocking — is unsafe, and the reason is worth stating where it will be read
7
+ // before someone "fixes" it: no rule the hub can evaluate distinguishes "invents a
8
+ // manifest nobody asked for" from "this logs a connection string". Both are a
9
+ // heading and a bullet. Demoting the fifth Critical finding by position would, on
10
+ // the day it matters, move a real security finding into the section nobody acts
11
+ // on, and it would do so silently.
12
+ //
13
+ // So the enforcement lives where the hub has authority over its own behaviour —
14
+ // the review ROUND cap in run-budget.js — and this module supplies the visible
15
+ // accounting that makes an over-budget review obvious to the dispatcher and to
16
+ // the human reading the transcript.
17
+
18
+ // Heading forms the review personas emit: "### Critical Issues", "## Important",
19
+ // "#### Blocking findings". Also matches the bare label form ("**Critical:**").
20
+ const BLOCKING_HEADING = /^(#{1,6})\s*(?:\d+[.)]\s*)?\**\s*(critical|important|blocking)\b/i;
21
+ const NONBLOCKING_HEADING = /^(#{1,6})\s*\**\s*(non[- ]?blocking|suggestions?|nits?|minor|optional|what'?s done well|strengths)\b/i;
22
+ const ANY_HEADING = /^(#{1,6})\s/;
23
+
24
+ // A finding inside a section: a bullet, a numbered item, or a bolded lead-in.
25
+ const FINDING_ITEM = /^\s*(?:[-*+]\s+|\d+[.)]\s+)/;
26
+
27
+ // Inline forms used when a reviewer skips headings entirely:
28
+ // "CRITICAL: the token is logged", "- **Important** — retries are unbounded".
29
+ const INLINE_BLOCKING = /^\s*(?:[-*+]\s+|\d+[.)]\s+)?\**\s*(critical|important|blocker|blocking)\b\s*\**\s*[:—-]/i;
30
+
31
+ /**
32
+ * Count blocking vs non-blocking findings in a review's text.
33
+ * Returns { blocking, nonBlocking, sections, sawHeadings } — `sections` names the
34
+ * blocking headings that were found, for the notice.
35
+ */
36
+ export function countReviewFindings(text) {
37
+ const lines = String(text || "").split("\n");
38
+ let mode = "none"; // none | blocking | nonblocking
39
+ let blocking = 0;
40
+ let nonBlocking = 0;
41
+ let sawHeadings = false;
42
+ const sections = [];
43
+ let inFence = false;
44
+
45
+ for (const rawLine of lines) {
46
+ const line = rawLine.replace(/\r$/, "");
47
+ if (/^\s*(```|~~~)/.test(line)) {
48
+ inFence = !inFence;
49
+ continue;
50
+ }
51
+ if (inFence) continue;
52
+
53
+ if (ANY_HEADING.test(line)) {
54
+ sawHeadings = true;
55
+ if (BLOCKING_HEADING.test(line)) {
56
+ mode = "blocking";
57
+ sections.push(line.replace(/^#{1,6}\s*/, "").replace(/\**/g, "").trim());
58
+ } else if (NONBLOCKING_HEADING.test(line)) {
59
+ mode = "nonblocking";
60
+ } else {
61
+ mode = "none";
62
+ }
63
+ continue;
64
+ }
65
+
66
+ if (FINDING_ITEM.test(line)) {
67
+ if (mode === "blocking") blocking++;
68
+ else if (mode === "nonblocking") nonBlocking++;
69
+ else if (INLINE_BLOCKING.test(line)) blocking++;
70
+ continue;
71
+ }
72
+ // Un-bulleted inline label outside any section ("CRITICAL: ...").
73
+ if (mode === "none" && INLINE_BLOCKING.test(line)) blocking++;
74
+ }
75
+
76
+ return { blocking, nonBlocking, sections, sawHeadings };
77
+ }
78
+
79
+ /**
80
+ * The notice appended to a review dispatch's result when the return carried more
81
+ * blocking findings than the tier's cap. Instructional, never corrective: the
82
+ * dispatcher is told to rank and close, and told what NOT to do with the rest.
83
+ * Returns null when the review is within budget or there is nothing to judge.
84
+ */
85
+ export function findingBudgetNotice(agent, tierCap, counts, roundsSpent = null, roundCap = null) {
86
+ if (tierCap == null || !counts) return null;
87
+ if (counts.blocking <= tierCap) return null;
88
+ const roundLine = roundCap == null
89
+ ? ""
90
+ : `\nReview rounds on this task: ${roundsSpent ?? "?"}/${roundCap}. ` +
91
+ (roundsSpent != null && roundsSpent >= roundCap
92
+ ? "No further review dispatch will be accepted for this task — this IS the gate."
93
+ : "Spending the next round on the overflow is exactly the ratchet.");
94
+ return `\n\n⚠ FINDING BUDGET EXCEEDED — ${agent} returned ${counts.blocking} blocking finding(s) against a cap of ${tierCap}` +
95
+ (counts.sections.length > 0 ? ` (sections: ${counts.sections.slice(0, 4).join(", ")})` : "") + `.\n` +
96
+ `The hub does NOT reclassify findings — a cap cannot tell "invents a new manifest" from "this leaks a credential", ` +
97
+ `so you rank them, not a regex.\n` +
98
+ `Act on the ${tierCap} most severe as the gate. Treat the remainder as recommendations for the human: report them, ` +
99
+ `do NOT schedule them as work, and do NOT let them reopen an assertion that a named piece of evidence already closed. ` +
100
+ `A finding that asks for a NEW invariant, evidence artifact, script, manifest, or process step is scope growth — ` +
101
+ `surface it to the human as a choice rather than executing it.${roundLine}`;
102
+ }
@@ -14,7 +14,15 @@ export const DEFAULT_HUB_MODE = "standard";
14
14
  // must not burn a standard-mode budget on ceremony, while `project` defers
15
15
  // entirely to the mode. Unset tier is treated as "feature".
16
16
  export const TASK_TIERS = ["trivial", "small", "feature", "project"];
17
- export const DEFAULT_TASK_TIER = "feature";
17
+ // The tier ASSUMED when the dispatcher never called set_task_tier. It is
18
+ // deliberately not the middle of the range: the tier is task-scoped, so a skipped
19
+ // triage latches for the whole task, and skipped triage is exactly the case where
20
+ // the dispatcher was not thinking about proportionality. Assuming `feature` there
21
+ // unlocked planner/plan-reviewer/security-auditor, loosened the review cap, and
22
+ // handed out the full feature envelope — the over-apparatus failure mode, granted
23
+ // by forgetting a tool call. Assuming `small` costs an explicit escalation (with a
24
+ // reason) when the work really is bigger, which is the cheap direction to be wrong in.
25
+ export const DEFAULT_TASK_TIER = "small";
18
26
 
19
27
  export const TIER_CAPS = {
20
28
  trivial: { maxDispatches: 1, maxResearch: 1 },
@@ -172,10 +180,300 @@ export function contextOverflowDiagnostic(runsSinceFresh, contextPct, { agent =
172
180
  );
173
181
  }
174
182
 
175
- /** One-line status chip: "Mode: standard·small · 1/2 disp · 0/2 res". */
176
- export function budgetStatusLine(mode, counters, budget, tier = null) {
183
+ /** One-line status chip: "Mode: standard·small · 1/2 disp · 0/2 res · task 4/6". */
184
+ export function budgetStatusLine(mode, counters, budget, tier = null, task = null) {
177
185
  const cap = (n) => (n == null ? "∞" : String(n));
178
186
  const tierSuffix = tier ? `·${tier}` : "";
187
+ const taskSuffix = task
188
+ ? ` · task ${task.counters.dispatches}/${cap(task.budget.maxDispatches)}`
189
+ : "";
179
190
  return `Mode: ${mode}${tierSuffix} · ${counters.dispatches}/${cap(budget.maxDispatches)} disp · ` +
180
- `${counters.research}/${cap(budget.maxResearch)} res`;
191
+ `${counters.research}/${cap(budget.maxResearch)} res${taskSuffix}`;
192
+ }
193
+
194
+ // ─────────────────────────────────────────────────────────────────────────────
195
+ // Tier ratchet (the tier is TASK-scoped, not turn-scoped)
196
+ // ─────────────────────────────────────────────────────────────────────────────
197
+ //
198
+ // Turn-scoped tiers cannot bind on a steered run: every follow-up message reset
199
+ // the tier to null, the next dispatch re-assumed `feature`, and a two-word
200
+ // correction ("no, only the one line") bought six fresh dispatches. Worse, the
201
+ // reset direction was always upward — nobody re-declares `trivial` after a
202
+ // steering message, so the effective tier drifted to the ceiling.
203
+ //
204
+ // The tier now survives the turn and moves by ratchet: DOWN is free (cheap and
205
+ // self-limiting), UP costs an explicit reason that is recorded and shown. Only
206
+ // an explicit new task (set_task_tier `new_task: true`, or /af-new-task) clears
207
+ // it.
208
+
209
+ export const TIER_RANK = { trivial: 0, small: 1, feature: 2, project: 3 };
210
+
211
+ /**
212
+ * Move the task tier from `current` to `next`.
213
+ * Returns { ok, tier, escalated, reason, message }: `tier` is always the tier
214
+ * that should be in force afterwards, so a refused escalation keeps the old one.
215
+ */
216
+ export function applyTierChange(current, next, reason = "") {
217
+ const target = normalizeTaskTier(next);
218
+ if (!target) {
219
+ return {
220
+ ok: false,
221
+ tier: current ?? null,
222
+ escalated: false,
223
+ reason: "unknown_tier",
224
+ message: `Unknown tier "${next}" — expected one of: ${TASK_TIERS.join(", ")}. ` +
225
+ `Tier unchanged (${current ?? "unset"}).`,
226
+ };
227
+ }
228
+ const from = normalizeTaskTier(current);
229
+ if (!from) {
230
+ return { ok: true, tier: target, escalated: false, reason: "initial", message: `Task tier: ${target}.` };
231
+ }
232
+ if (TIER_RANK[target] <= TIER_RANK[from]) {
233
+ return {
234
+ ok: true,
235
+ tier: target,
236
+ escalated: false,
237
+ reason: TIER_RANK[target] === TIER_RANK[from] ? "unchanged" : "lowered",
238
+ message: `Task tier: ${from} → ${target}.`,
239
+ };
240
+ }
241
+ if (!String(reason || "").trim()) {
242
+ return {
243
+ ok: false,
244
+ tier: from,
245
+ escalated: false,
246
+ reason: "raise_without_reason",
247
+ message: `⚠ Tier escalation ${from} → ${target} refused: raising the tier needs an explicit ` +
248
+ "`reason` naming what the ask turned out to contain that the lower tier does not cover. " +
249
+ `Tier stays ${from}. Lowering the tier never needs a reason.`,
250
+ };
251
+ }
252
+ return {
253
+ ok: true,
254
+ tier: target,
255
+ escalated: true,
256
+ reason: "raised",
257
+ message: `⚠ Task tier ESCALATED ${from} → ${target}: ${String(reason).trim()}`,
258
+ };
259
+ }
260
+
261
+ // ─────────────────────────────────────────────────────────────────────────────
262
+ // Task-scoped budget (the outer bound the turn budget never provided)
263
+ // ─────────────────────────────────────────────────────────────────────────────
264
+ //
265
+ // Turn budgets are a per-message allowance, and a per-message allowance cannot
266
+ // bound a task: the observed 47-hour run never hit one, because every steering
267
+ // message opened a fresh window of 8 dispatches and 60 minutes. The task budget
268
+ // is the same envelope multiplied once and NOT reset by a user message — only
269
+ // by an explicit new task. Exhaustion is a hard stop, not a "summarize and ask":
270
+ // continuing requires the human to open a new task window.
271
+
272
+ export const TASK_BUDGET_MULTIPLIER = 3;
273
+
274
+ /** Task envelope = turn envelope × multiplier; `null` (off) axes stay off. */
275
+ export function resolveTaskBudget(turnBudget, multiplier = TASK_BUDGET_MULTIPLIER) {
276
+ const scale = (value) => (value == null ? null : Math.max(1, Math.round(value * multiplier)));
277
+ return {
278
+ maxDispatches: scale(turnBudget.maxDispatches),
279
+ maxResearch: scale(turnBudget.maxResearch),
280
+ wallMs: scale(turnBudget.wallMs),
281
+ };
282
+ }
283
+
284
+ function taskRefusalTail() {
285
+ return "This is a HARD STOP for the current task, not a turn refusal — another user message does " +
286
+ "NOT reopen it. Summarize what is proven (with evidence and artifact paths), what is unproven, " +
287
+ "and what remains, then ask the human to either narrow the remaining work or open a fresh task " +
288
+ "window with `/af-new-task`. If the task genuinely grew, say what it grew INTO — a task that " +
289
+ "outgrew its envelope three times over is a re-scoping decision, not a budget problem.";
290
+ }
291
+
292
+ /**
293
+ * ACTIVE milliseconds in one turn: wall clock minus the time the human was away.
294
+ *
295
+ * The task clock must never charge for human time. A task's wall clock spans
296
+ * every message on it, so a lunch break, an overnight pause, or a long `ask_user`
297
+ * answer would all count as budget — and at `fast` mode's 45-minute task wall a
298
+ * single coffee break would hard-stop a task with two dispatches spent. That is a
299
+ * false positive that teaches people to reset the task window reflexively, which
300
+ * costs more than the guardrail buys. Dispatch/research counts stay the honest
301
+ * hard stops; the clock only bounds time the fleet actually spent working.
302
+ */
303
+ export function turnActiveMs(turnStartedAt, now, askUserWaitMs = 0) {
304
+ if (!turnStartedAt) return 0;
305
+ return Math.max(0, now - turnStartedAt - Math.max(0, askUserWaitMs || 0));
306
+ }
307
+
308
+ /**
309
+ * Gate one dispatcher tool call against the TASK budget (checked before the
310
+ * turn budget: it is the more severe stop).
311
+ * `activeTaskMs` is ACTIVE time (see turnActiveMs), never raw wall clock.
312
+ * kind: "dispatch" | "research". Returns null when allowed, else { reason, message }.
313
+ */
314
+ export function checkTaskBudget(kind, counters, taskBudget, activeTaskMs, tier = null) {
315
+ const label = tier ? `tier ${tier}` : "current tier";
316
+ if (taskBudget.wallMs != null && activeTaskMs >= taskBudget.wallMs) {
317
+ return {
318
+ reason: "task_wall",
319
+ message: `⛔ TASK budget exhausted: ${Math.round(activeTaskMs / 60_000)} min of ACTIVE time on this task ` +
320
+ `(limit ${Math.round(taskBudget.wallMs / 60_000)} min = ${TASK_BUDGET_MULTIPLIER}× the ${label} turn envelope; ` +
321
+ `time the human was away is not charged). ` +
322
+ taskRefusalTail(),
323
+ };
324
+ }
325
+ if (kind === "dispatch" && taskBudget.maxDispatches != null && counters.dispatches >= taskBudget.maxDispatches) {
326
+ return {
327
+ reason: "task_dispatches",
328
+ message: `⛔ TASK budget exhausted: ${counters.dispatches} of ${taskBudget.maxDispatches} ` +
329
+ `dispatch_agent calls used on this task (${TASK_BUDGET_MULTIPLIER}× the ${label} turn envelope). ` +
330
+ taskRefusalTail(),
331
+ };
332
+ }
333
+ if (kind === "research" && taskBudget.maxResearch != null && counters.research >= taskBudget.maxResearch) {
334
+ return {
335
+ reason: "task_research",
336
+ message: `⛔ TASK budget exhausted: ${counters.research} of ${taskBudget.maxResearch} ` +
337
+ `spawn_research calls used on this task (${TASK_BUDGET_MULTIPLIER}× the ${label} turn envelope). ` +
338
+ taskRefusalTail(),
339
+ };
340
+ }
341
+ return null;
342
+ }
343
+
344
+ /**
345
+ * How many research runs the TASK envelope still allows; null = unlimited.
346
+ * The auto-research pipe (specialist emits NEEDS_RESEARCH, the hub fans out
347
+ * read-only helpers in code) is exempt from the TURN budget on purpose — it is
348
+ * hub mechanics, not a dispatcher decision, and it must not steal the
349
+ * dispatcher's slots. It is NOT exempt from the TASK envelope: at 2 rounds × 4
350
+ * questions per dispatch and 18 dispatches per task, an uncounted pipe is 144
351
+ * research runs inside the bound that is supposed to be the outer one.
352
+ */
353
+ export function remainingTaskResearch(taskBudget, counters) {
354
+ if (taskBudget.maxResearch == null) return null;
355
+ return Math.max(0, taskBudget.maxResearch - (counters?.research ?? 0));
356
+ }
357
+
358
+ // ─────────────────────────────────────────────────────────────────────────────
359
+ // Tier persona gate (B3) — heavy apparatus is not available at low tiers
360
+ // ─────────────────────────────────────────────────────────────────────────────
361
+ //
362
+ // "A trivial ask gets one specialist" was prose in the system prompt, and prose
363
+ // lost: a one-line Azure permission change was routed through planner →
364
+ // plan-reviewer → security-auditor and grew a 1216-line plan. These personas
365
+ // each open a pipeline (plans, reviews, findings that ratchet back into the
366
+ // plan), so at trivial/small tiers they are refused in code. The escape hatch is
367
+ // the honest one: raise the tier with a reason.
368
+
369
+ export const HEAVY_PERSONAS = ["planner", "plan-reviewer", "architect", "security-auditor", "deep-researcher"];
370
+ export const REVIEW_PERSONAS = ["code-reviewer", "plan-reviewer", "security-auditor"];
371
+ const GATED_TIERS = new Set(["trivial", "small"]);
372
+
373
+ /**
374
+ * Refuse a heavy persona at a low tier. Returns null when allowed, else
375
+ * { reason, message }. Unknown/absent tier never gates (strict mode leaves the
376
+ * tier unset on purpose).
377
+ */
378
+ export function checkTierPersonaGate(tier, persona) {
379
+ const t = normalizeTaskTier(tier);
380
+ if (!t || !GATED_TIERS.has(t)) return null;
381
+ const name = String(persona || "").trim().toLowerCase();
382
+ if (!HEAVY_PERSONAS.includes(name)) return null;
383
+ return {
384
+ reason: "tier_persona_gate",
385
+ message: `⚠ ${name} is not available at tier "${t}" — and this dispatch was NOT counted against any budget.\n` +
386
+ `At trivial/small tiers the apparatus is one specialist plus its own evidence: no planning pipeline, ` +
387
+ `no plan review, no separate audit pass. Each of those personas opens a document/finding loop whose ` +
388
+ `output then has to be executed and re-reviewed.\n` +
389
+ `Either dispatch the specialist that does the actual work (builder, test-engineer, code-reviewer, ` +
390
+ `documenter), or — if the ask really is bigger than "${t}" — call set_task_tier with a higher tier ` +
391
+ `AND a reason naming what it turned out to contain. Do not raise the tier merely to unlock a persona.`,
392
+ };
393
+ }
394
+
395
+ // ─────────────────────────────────────────────────────────────────────────────
396
+ // Review finding budget (B6) — a review is a gate, and a gate has a size
397
+ // ─────────────────────────────────────────────────────────────────────────────
398
+ //
399
+ // Unbounded review authority is a ratchet: every round produced new blocking
400
+ // findings, each finding added an invariant to the plan, and the enlarged plan
401
+ // justified another round. PLAN37 recorded P37-001…011, R37-IMM-001 and six
402
+ // script-review remediations — none of which the user asked for. The cap is on
403
+ // BLOCKING findings only; everything else still gets reported, just not as a gate.
404
+
405
+ export const BLOCKING_FINDING_CAPS = { trivial: 1, small: 2, feature: 5, project: null };
406
+
407
+ // Review ROUNDS per task. The finding cap is an instruction to the reviewer, and
408
+ // an instruction is exactly what this whole change exists to stop relying on —
409
+ // but the finding cap is also the wrong thing to enforce mechanically: no rule
410
+ // the hub can evaluate distinguishes "invents a new manifest" from "this leaks a
411
+ // credential", and silently demoting the second is worse than tolerating the
412
+ // first. What the hub CAN own is its own action. The ratchet needs a second
413
+ // round to close, so the round count is where it is cut — deterministically,
414
+ // with no judgement about finding content.
415
+ export const REVIEW_ROUND_CAPS = { trivial: 1, small: 1, feature: 2, project: null };
416
+
417
+ /** Review rounds allowed on one task at this tier; null = uncapped. */
418
+ export function reviewRoundCap(tier) {
419
+ const t = normalizeTaskTier(tier);
420
+ if (!t) return null;
421
+ return REVIEW_ROUND_CAPS[t] ?? null;
422
+ }
423
+
424
+ /**
425
+ * Refuse an (N+1)-th review dispatch on the same task.
426
+ * Returns null when allowed, else { reason, message }.
427
+ */
428
+ export function checkReviewRoundCap(tier, persona, roundsSoFar) {
429
+ if (!isReviewPersona(persona)) return null;
430
+ const cap = reviewRoundCap(tier);
431
+ if (cap == null || roundsSoFar < cap) return null;
432
+ const t = normalizeTaskTier(tier);
433
+ return {
434
+ reason: "review_round_cap",
435
+ message: `⚠ Review round cap reached: ${roundsSoFar} of ${cap} review dispatch${cap === 1 ? "" : "es"} ` +
436
+ `already spent on this task at tier "${t}" — and this dispatch was NOT counted against any budget.\n` +
437
+ `A review is a GATE, not a loop. The findings from the round you already have are the gate: fix them, ` +
438
+ `re-verify only the assertions the fix touched, and close. Re-reviewing the same work to see whether ` +
439
+ `the fix produced new findings is the ratchet — each round's findings become requirements, and the ` +
440
+ `enlarged requirement set justifies the next round.\n` +
441
+ `If this genuinely is a different review (a different subsystem, or work the earlier round never saw), ` +
442
+ `raise the tier with a reason via set_task_tier, or open a new task window with /af-new-task.`,
443
+ };
444
+ }
445
+
446
+ /** Blocking-finding cap for a tier; null = uncapped (project / unset tier). */
447
+ export function blockingFindingCap(tier) {
448
+ const t = normalizeTaskTier(tier);
449
+ if (!t) return null;
450
+ return BLOCKING_FINDING_CAPS[t] ?? null;
451
+ }
452
+
453
+ /** Is this a review persona (gets the finding-budget clause)? */
454
+ export function isReviewPersona(persona) {
455
+ return REVIEW_PERSONAS.includes(String(persona || "").trim().toLowerCase());
456
+ }
457
+
458
+ /**
459
+ * The finding-budget clause appended to a review persona's task text.
460
+ * Returns null when the persona is not a reviewer or the tier is uncapped.
461
+ */
462
+ export function reviewBudgetClause(tier, persona) {
463
+ if (!isReviewPersona(persona)) return null;
464
+ const cap = blockingFindingCap(tier);
465
+ if (cap == null) return null;
466
+ return [
467
+ `## Finding budget (task tier: ${normalizeTaskTier(tier)})`,
468
+ ``,
469
+ `Report at most ${cap} BLOCKING finding${cap === 1 ? "" : "s"}. Rank by severity and put everything`,
470
+ `else under a "## Non-blocking (optional)" heading — non-blocking findings are advice, and must not`,
471
+ `gate the change or be re-raised as blockers in a later round.`,
472
+ ``,
473
+ `A blocking finding may only enforce an invariant the task, the plan, or the project rules ALREADY`,
474
+ `state. It may NOT introduce a new invariant, a new evidence artifact, a new script/manifest/fixture,`,
475
+ `or a new process requirement — that is scope growth wearing a reviewer's hat. If you believe a new`,
476
+ `invariant is genuinely needed, write it under "## Non-blocking (optional)" as a recommendation for`,
477
+ `the human to decide, and do not block on it.`,
478
+ ].join("\n");
181
479
  }
@@ -0,0 +1,87 @@
1
+ // Immutable per-run artifact namespaces — the pure policy core behind "a run's
2
+ // artifacts are never overwritten by the next run".
3
+ //
4
+ // The observed failure: `.pi/agent-sessions/artifacts/` was deleted at session
5
+ // start, and specialist returns were named by a per-session counter
6
+ // (`returns/builder-run1.md`). Two consequences, both hit at once: a later
7
+ // session's `builder-run1.md` occupied the same path as an earlier one, and the
8
+ // start-of-session wipe removed eleven implementation returns and two review
9
+ // artifacts that a post-mortem then had to record as NOT RECOVERABLE.
10
+ //
11
+ // The fix is not retention-by-luck: each session archives the previous session's
12
+ // artifacts into `runs/<runId>/`, a namespace that is written once and never
13
+ // reused, and records it in `runs/index.json`. Pruning is explicit and bounded,
14
+ // so the directory cannot grow without limit either.
15
+
16
+ export const DEFAULT_RUN_HISTORY_KEEP = 10;
17
+ export const RUNS_DIRNAME = "runs";
18
+ export const RUN_INDEX_FILENAME = "index.json";
19
+
20
+ /**
21
+ * Run id: sortable UTC timestamp + a short random suffix, so two sessions
22
+ * starting in the same second still get distinct namespaces.
23
+ * `2026-08-03T09-10-42-a3f9`
24
+ */
25
+ export function makeRunId(date = new Date(), suffix = null) {
26
+ const iso = new Date(date).toISOString().replace(/\.\d+Z$/, "").replace(/:/g, "-");
27
+ const tail = suffix ?? Math.random().toString(36).slice(2, 6);
28
+ return `${iso}-${tail}`;
29
+ }
30
+
31
+ /** A run id we generated (used to filter stray directories out of `runs/`). */
32
+ export function isRunId(name) {
33
+ return /^\d{4}-\d{2}-\d{2}T\d{2}-\d{2}-\d{2}-[a-z0-9]{2,8}$/.test(String(name || ""));
34
+ }
35
+
36
+ /**
37
+ * Which run directories to delete so at most `keep` survive.
38
+ * Run ids sort lexicographically by time, so newest = last. `keep: null`
39
+ * ("off") prunes nothing; non-run-id entries are never touched.
40
+ */
41
+ export function pruneRunDirs(names, keep = DEFAULT_RUN_HISTORY_KEEP) {
42
+ if (keep == null) return [];
43
+ const runs = (names || []).filter(isRunId).sort();
44
+ const limit = Math.max(0, keep);
45
+ if (runs.length <= limit) return [];
46
+ return runs.slice(0, runs.length - limit);
47
+ }
48
+
49
+ /**
50
+ * The metadata written once into `runs/<runId>/meta.json`. Carries the
51
+ * identifiers a post-mortem needs and could not previously recover: which
52
+ * workspace/project/repo the run belonged to, and when it started and ended.
53
+ */
54
+ export function buildRunMeta({ runId, startedAt = null, archivedAt = Date.now(), cwd = null, project = null, workspace = null, artifactCounts = null }) {
55
+ return {
56
+ runId,
57
+ startedAt: startedAt == null ? null : new Date(startedAt).toISOString(),
58
+ archivedAt: new Date(archivedAt).toISOString(),
59
+ cwd,
60
+ project,
61
+ workspace,
62
+ artifactCounts,
63
+ note: "Immutable archive of one agent-hub session's artifacts. Written once; never rewritten.",
64
+ };
65
+ }
66
+
67
+ /**
68
+ * Fold a run entry into `runs/index.json`, newest last, capped at `keep`.
69
+ * Re-indexing the same runId replaces its entry rather than duplicating it.
70
+ */
71
+ export function appendRunIndex(existing, entry, keep = DEFAULT_RUN_HISTORY_KEEP) {
72
+ const runs = Array.isArray(existing?.runs) ? existing.runs.filter((r) => r && r.runId !== entry.runId) : [];
73
+ runs.push(entry);
74
+ runs.sort((a, b) => String(a.runId).localeCompare(String(b.runId)));
75
+ const trimmed = keep == null ? runs : runs.slice(Math.max(0, runs.length - Math.max(0, keep)));
76
+ return { version: 1, updatedAt: new Date().toISOString(), runs: trimmed };
77
+ }
78
+
79
+ /** Parse the `run-history-keep:` overrides value → number, null ("off"), or undefined. */
80
+ export function normalizeRunHistoryKeep(value) {
81
+ const raw = String(value ?? "").trim().toLowerCase();
82
+ if (!raw) return undefined;
83
+ if (raw === "off" || raw === "none" || raw === "0") return null;
84
+ const n = Number(raw);
85
+ if (!Number.isFinite(n) || n < 1) return undefined;
86
+ return Math.floor(n);
87
+ }
@@ -3,5 +3,5 @@
3
3
  "private": true,
4
4
  "type": "module",
5
5
  "main": "index.ts",
6
- "version": "0.0.9"
6
+ "version": "0.0.10"
7
7
  }
@@ -3,5 +3,5 @@
3
3
  "private": true,
4
4
  "type": "module",
5
5
  "main": "index.ts",
6
- "version": "0.0.9"
6
+ "version": "0.0.10"
7
7
  }
@@ -2,14 +2,21 @@
2
2
  description: Scan agent-fleet install targets for broken symlinks, stale persona references, and overrides-file problems, then offer repairs
3
3
  ---
4
4
 
5
- Load and follow Step 5 (Doctor preflight) of the `guided-workspace-setup` skill — without running the rest of the install flow. Use this when the user wants the repair pass on its own; the full `/af-setup-agent-fleet` flow runs the same scan automatically as soon as it detects prior install state.
5
+ Load and follow the `guided-workspace-setup` skill's repair path — without running the rest of the install flow. Use this when the user wants the repair pass on its own; `/af-setup-agent-fleet` offers the same thing as soon as it finds prior install state.
6
6
 
7
- Walk every install-target directory the chosen coding agent uses (`agents/`, `.claude/agents/`, `.opencode/agent/` (+ legacy `.opencode/agents/`), `.pi/agents/`, `.claude/skills/`, `.opencode/skills/`, `.pi/skills/`, `.agents/skills`, `.claude/commands/`, `.opencode/commands/`, `.pi/prompts/`, `.claude/references/`, `.claude/hooks/`). For each broken symlink, resolve where it pointed, look for a canonical replacement in the source `agents/` and `skills/` trees, and offer to repair or delete (persona links under `.claude/agents/` and `.opencode/agent(s)/` are repaired by regenerating a transformed copy via `transform-persona`, not by re-symlinking the raw source). Common stale names from the pre-merge persona layout: `reviewer` → `code-reviewer`, `red-team` → `security-auditor`.
7
+ Run the CLI — do not walk directories or repair files yourself:
8
8
 
9
- Also flag and offer to rewrite any remaining YAML configs (`teams.yaml`, `peers.yaml`, etc.) that still reference removed persona names.
9
+ ```
10
+ node <source-root>/bin/cli.js doctor --workspace <workspace> [--agent <agent>] --json
11
+ ```
10
12
 
11
- Also validate `.ai/agent-fleet-overrides.md` when it exists, against the schema in `docs/agent-fleet-setup.md`: unknown sections, unknown keys in known sections, invalid values for the mechanically parsed `agent-hub` keys, missing `rules:` folders, and `## env` `required:` names that are neither set nor declared in the root `.env`. These findings are advisory only — report them with fix "edit by hand", never edit the overrides file.
13
+ Resolve `<source-root>` from `<workspace>/.ai/.agent-fleet-bootstrap.json`, or this prompt's realpath if it is a symlink, or by asking. Never scan the filesystem for agent-fleet clones.
12
14
 
13
- Present the findings per the skill's Step 1 interaction contract: print a short text summary (counts per kind, advisory findings as report-only text), then ask one `ask_user` multi-select — *"Which fixes should I apply now?"* — each option titled `<path> — <issue>` with the proposed fix as its description, chunked at ≤ 9 options; empty selection or cancel applies nothing. Without the widget, print a `# | Path | Issue | Suggested fix` table instead and take the picks as text.
15
+ The report has two halves, and they are repaired differently on purpose:
14
16
 
15
- Never overwrite a regular file — only act on symlinks whose target is missing. Report `repaired`, `deleted`, and `skipped` counts, and append a `## doctor-runs` line to `.ai/agent-fleet-setup.md` with the date, agent, phase (`standalone`), and counts.
17
+ - `repairs` — recorded items that are missing, dangling, or linked outside the source root. These are rebuilt through the same `apply()` path `install` writes with, so a repaired file is byte-identical to a freshly installed one.
18
+ - `findings` — what the install record cannot own: broken symlinks in a pre-engine workspace, stale persona names in `.pi/agents/*.yaml` (`reviewer` → `code-reviewer`, `red-team` → `security-auditor`), plus advisory ones. `overrides` and `yaml-shape` findings are **advisory**: report them with "edit by hand" and never fix them, because the fix is always a hand edit of the flagged file.
19
+
20
+ Print the two lists as text, then ask one `ask_user` single-select (or a plain text question without the widget) — *"Apply the suggested fixes?"* — and on yes re-run with `--fix`. An empty answer or a cancel applies nothing.
21
+
22
+ Exit codes: `0` nothing to repair, `2` repairable issues found (or advisories present, or a repair failed), `1` could not run. Report the counts the CLI returns; do not invent your own.
@@ -4,24 +4,16 @@ description: Guided setup — install agent-fleet artifacts into a workspace for
4
4
 
5
5
  Load and follow the `guided-workspace-setup` skill before proceeding.
6
6
 
7
- Run the guided install for a target workspace. If the user passed a workspace path, use it; otherwise ask for it. Detect the running coding agent and confirm it with the user.
7
+ Run the guided install for a target workspace. If the user passed a workspace path, use it; otherwise ask. Confirm the coding agent (`pi` here unless the user says otherwise).
8
8
 
9
- Analyse the workspace. If prior install state is found (`.ai/agent-fleet-setup.md` or a populated agent directory), run the **Doctor preflight** first (Step 5) — scan for broken symlinks and stale persona references, present findings as a table, and apply the fixes the user picks before continuing.
9
+ The skill is a front-end over the `agent-fleet` CLI's installer engine: `verify --json` supplies the menu (groups, profiles, per-item state), and `install` / `upgrade` / `uninstall` / `doctor --fix` do every write. **Do not copy, symlink, or delete an install target yourself** — the CLI records ownership in `.ai/agent-fleet-state.json`, and anything written by hand is invisible to every later run. The harness/extension closures (Fleet Core, the `justfile` managed region, the `.pi/agents` configs, the runtime script closure) are manifest data, so the CLI already pulls them in; you do not restate or reassemble them. Artifacts install as copies; never ask copy-vs-symlink and never pass `--method`.
10
10
 
11
- **Bootstrap `pi-ask-user` first (Step 5b).** Before the install menu, check whether the `pi-ask-user` interaction package is available (bundled by `@chankov/agent-fleet`, recorded as a project package, or global). If it is missing, offer to install it project-scoped (`pi install -l npm:pi-ask-user`), record it as an external/project pi package, then **stop the pass** and ask the user to reload pi and re-run `/af-setup-agent-fleet`. The tool only becomes callable after reload, and on the re-run the menu uses its native multi-select widget. Only fall back to a text menu in this pass if the user *declines* the bootstrap.
11
+ Two things are yours rather than the CLI's: drafting `.ai/agent-fleet-overrides.md` from a scan of the project, and the `pi-voice-stt` provider Q&A (`.ai/stt.json` names env vars; the key goes in a gitignored `.env`).
12
12
 
13
- The Skills group draws from **two roots**: fleet-native `skills/` and the vendored upstream import `vendor/agent-skills-upstream/skills/` (see `docs/UPSTREAM-SKILLS.md`). On a name collision the native copy wins — never offer the vendored duplicate as a separate row.
13
+ **Bootstrap `pi-ask-user` first.** Before the menu, check whether the interaction package is available (bundled by `@chankov/agent-fleet`, recorded as a project package, or global). If it is missing, offer `pi install -l npm:pi-ask-user`, then **stop the pass** and ask the user to reload pi and re-run `/af-setup-agent-fleet` — the widget is not callable until then. Fall back to a text menu in this pass only if the user declines.
14
14
 
15
- Then present the install menu per the skill's Step 1 interaction contract — drive every decision through the `ask_user` widget, never a printed table awaiting a free-text reply (the table format is reserved for the no-widget fallback when the user declined the bootstrap). Open with the **Express question** (fresh workspace: `Recommended ★` / `Everything` / `Custom — group by group` / `Nothing`; existing: `Keep as-is` / `Apply updates` / `Keep + add recommended ★` / `Custom`) — any answer but `Custom` skips all group screens. On `Custom`, run the **7 groups** (4 shared: Skills, Agent personas, Commands/prompts, References & Hooks; 3 pi-only: pi extensions & runtime skills, pi harnesses, External pi packages): each opens as a single-select quick screen (`Recommended ★ (n)` / `Everything (m)` / `Customise` / `Skip group`, or the installed-state variants with `Remove some…`), and multi-select drill-ins appear only behind `Customise`, chunked by sub-category (lifecycle phase for Skills, `rw`/`ro`/`pi-only` for personas, harness category, …) at ≤ 9 options per call, ≤ 8 `context` lines. Option titles carry `name ★ [st]` (`ok`/`upd`/`mod`/`cflt`/`gone`/`new`/`pkg`/`—`/`brk`); descriptions carry the purpose plus the state in plain words (`mod` → warn that refreshing overwrites local edits). There is **no pre-checking** (`ask_user` has no preselect) — installed state shows as counts on quick screens and words in descriptions; leaving an installed item unselected in a drill-in keeps it as-is. Freeform stays on so `all` / `recommended` (adds `★` on top — never removes) / `none` / `keep` still work; cancel = keep-as-is/skip. `cflt` rows are resolved only by printing the three-way diff and asking per row with `displayMode: "inline"` — never by Express or `Apply updates`. The External pi packages group lists `pi-ask-user` and the optional suggested `pi-codex-image-gen`. After Step 5b, `pi-ask-user` normally counts toward `Keep as-is` (`pkg`, scope `project` / `bundled by @chankov/agent-fleet` / `global` — state it in the restate line, no duplicate entries). `pi-codex-image-gen` is not bundled or bootstrapped; offer `pi install -l npm:pi-codex-image-gen` only when the user selects it. Never offer `setup`, `doctor`, or `guided-workspace-setup` — those are installer-only and live in the source agent-fleet repo.
15
+ Drive every decision through the `ask_user` widget: ≤ 9 options and ≤ 8 `context` lines per call, options carrying the data (never a table in `context`). Open with the Express question backed by the manifest's profiles; group screens run only on `Custom`; drill-ins appear only behind `Customise`. Option titles carry `<name> ★ [state]`, descriptions say what picking it does in plain words. Leaving an installed item unpicked keeps it — removal is its own explicit screen and runs `uninstall`. Cancel is a no-op everywhere except the final confirmation.
16
16
 
17
- Removal happens **only** on an explicit `Remove some…` multi-select (empty selection = remove nothing), and it is scoped: the screen lists only items whose name is in the agent-fleet inventory **and** that are recorded in `## install-status` (or are symlinks resolving into the source repo). User-authored skills, custom commands, third-party plugins, external pi packages not recorded by this setup, and unrelated settings/env keys are left untouched and logged as "Skipped — not owned by agent-fleet".
17
+ If `verify` reports findings or broken items, offer `doctor --fix` before the menu — a broken workspace makes the menu lie about what is installed.
18
18
 
19
- **No cross-tool substitution.** Each row is offered only when the source file the chosen agent needs already exists — for `pi`, that means `.pi/prompts/<name>.md`, `.pi/extensions/<name>/`, etc. Never fall back to `.claude/commands/` (or another agent's tree) to satisfy a pi prompt request; items missing their per-agent source are filtered out of the menu entirely.
20
-
21
- **Personas are generated for non-pi targets.** The personas group lists the full availability roster from `node <source-root>/bin/cli.js transform-persona --list --agent <agent>`. For `pi` the canonical `agents/<name>.md` installs as-is (copy or symlink). For `claude-code`/`opencode` the apply step runs `transform-persona --agent <agent> --workspace <workspace> <name…>` instead — always a generated copy, even in symlink mode — and records the rows with `transformed: true`; status checks diff against the generated output, not the raw source.
22
-
23
- **pi harness companions.** Installing, refreshing, or removing any pi harness also refreshes its companions in the same pass — the `justfile` launch recipes, `scripts/team-up.ts`, the peer/team YAML and personas, `.pi/damage-control-rules.yaml`, and `.pi/harnesses/package.json`. When `agent-hub` is installed or kept, keep its required launch companions together: `damage-control-continue` and `ask-user-remote`; the managed `just hub` / `hub-solo` recipes load both before `agent-hub`, and every native child inherits continue. Treat the retired `damage-control` hard-stop directory as `gone`: remove it only when recorded and unchanged against the recorded snapshot, or when it is a symlink into the source root (including a broken retirement link); preserve every user-modified or unowned copy. Refresh the `justfile` from the **current** source so retired-harness recipes are pruned and new ones added, rewriting only the managed region between the `agent-fleet:harnesses` sentinels so any user recipes survive.
24
-
25
- **No mid-apply overwrite prompts.** The `mod` description already warns that refreshing overwrites local edits. The user's selection is the consent; the Step 9 confirmation is the single gate. During apply, refresh selected items unconditionally — never pause to ask "should I overwrite this file?". Genuine errors (permission denied, missing source) still stop and report.
26
-
27
- Offer override sections for the workspace's `.ai/agent-fleet-overrides.md` based on the analysis (print each draft, then `Accept` / `Edit` / `Skip` per section via `ask_user`), and record what was installed in `.ai/agent-fleet-setup.md`. Print the plan as compact action-grouped lines (Add / Refresh / Remove / Keep-count / Records / Method), then confirm with one `ask_user` single-select asked with `displayMode: "inline"` — `Apply — and remove the installer commands` (default) / `Apply — keep the installer commands` / `Adjust picks` / `Cancel` — and write nothing until an Apply is chosen. Then perform the setup, re-scan for any new breakage, and report what changed.
19
+ Print the plan as compact action-grouped lines before confirming, then confirm with one `displayMode: "inline"` single-select: `Apply — and remove the installer commands` (default) / `Apply — keep the installer commands` / `Adjust picks` / `Cancel`. Ask before passing `--allow-exec` (the `npm ci` steps). Exit `3` means conflicts: show the `.new` files the CLI wrote and let the user decide — never pick a side for them. Relay `operator` and `external` steps verbatim; the CLI performs neither, and neither do you.