@draht/coding-agent 2026.10.20 → 2026.10.23

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 (726) hide show
  1. package/CHANGELOG.md +138 -0
  2. package/agents/advisor.md +2 -2
  3. package/agents/architect.md +11 -33
  4. package/agents/debugger.md +13 -54
  5. package/agents/git-committer.md +18 -42
  6. package/agents/implementer.md +14 -36
  7. package/agents/investigator.md +12 -63
  8. package/agents/reviewer.md +16 -44
  9. package/agents/security-auditor.md +22 -56
  10. package/agents/spec-reviewer.md +13 -53
  11. package/agents/verifier.md +14 -33
  12. package/bin/drahtbank.mjs +4 -0
  13. package/dist/agents/advisor.md +2 -2
  14. package/dist/agents/architect.md +11 -33
  15. package/dist/agents/debugger.md +13 -54
  16. package/dist/agents/git-committer.md +18 -42
  17. package/dist/agents/implementer.md +14 -36
  18. package/dist/agents/investigator.md +12 -63
  19. package/dist/agents/reviewer.md +16 -44
  20. package/dist/agents/security-auditor.md +22 -56
  21. package/dist/agents/spec-reviewer.md +13 -53
  22. package/dist/agents/verifier.md +14 -33
  23. package/dist/bundle/chunks/anthropic-messages-VEMVBETR.js +6 -0
  24. package/dist/bundle/chunks/anthropic.js +1 -1
  25. package/dist/bundle/chunks/azure-openai-responses-EXUP6SLM.js +2 -0
  26. package/dist/bundle/chunks/bedrock-converse-stream.js +23 -20
  27. package/dist/bundle/chunks/chunk-2MJ6J5N2.js +6 -0
  28. package/dist/bundle/chunks/chunk-2RI4GIFP.js +166 -0
  29. package/dist/bundle/chunks/chunk-57PET6SW.js +82 -0
  30. package/dist/bundle/chunks/chunk-76YNMQ57.js +2 -0
  31. package/dist/bundle/chunks/chunk-AACPRSR2.js +9 -0
  32. package/dist/bundle/chunks/chunk-CHRFWNPF.js +1424 -0
  33. package/dist/bundle/chunks/chunk-CI37W6HM.js +2 -0
  34. package/dist/bundle/chunks/chunk-CMKX4CSI.js +6 -0
  35. package/dist/bundle/chunks/chunk-DHZBWXZK.js +16 -0
  36. package/dist/bundle/chunks/{chunk-D6TMD5Q2.js → chunk-DLVZ3EK7.js} +4 -4
  37. package/dist/bundle/chunks/chunk-DQ4G4IS4.js +20 -0
  38. package/dist/bundle/chunks/chunk-FXCTQRNN.js +2 -0
  39. package/dist/bundle/chunks/chunk-FXLM6UQV.js +2 -0
  40. package/dist/bundle/chunks/chunk-ITP6IDBA.js +20 -0
  41. package/dist/bundle/chunks/chunk-JRHPLIE5.js +11 -0
  42. package/dist/bundle/chunks/chunk-KINQOWAP.js +4 -0
  43. package/dist/bundle/chunks/{chunk-IWTUBX6V.js → chunk-LK54N67E.js} +5 -2
  44. package/dist/bundle/chunks/chunk-MBFTIGLS.js +2 -0
  45. package/dist/bundle/chunks/chunk-QG2WW2SA.js +2 -0
  46. package/dist/bundle/chunks/{chunk-KPO5375S.js → chunk-RCRGGYLW.js} +1 -1
  47. package/dist/bundle/chunks/chunk-RGI7SF5G.js +2 -0
  48. package/dist/bundle/chunks/{chunk-6ZJKIMU7.js → chunk-SYRVFGYE.js} +1 -1
  49. package/dist/bundle/chunks/chunk-UQSONZLL.js +479 -0
  50. package/dist/bundle/chunks/chunk-USCN7R2E.js +2 -0
  51. package/dist/bundle/chunks/chunk-XB4F3WGD.js +132 -0
  52. package/dist/bundle/chunks/chunk-YSIQCH4Z.js +2 -0
  53. package/dist/bundle/chunks/chunk-ZRPAOMVB.js +2 -0
  54. package/dist/bundle/chunks/{cli-PYJB6AQ3.js → cli-LGOE6EXL.js} +6 -6
  55. package/dist/bundle/chunks/cloudflare-workers-ai-system-one-47PK45EQ.js +2 -0
  56. package/dist/bundle/chunks/codemode-worker.js +188 -21
  57. package/dist/bundle/chunks/execute-ZVQ7ITER.js +31 -0
  58. package/dist/bundle/chunks/github-copilot.js +1 -1
  59. package/dist/bundle/chunks/google-generative-ai-PBPH45HB.js +2 -0
  60. package/dist/bundle/chunks/google-vertex-ZPCFQNU6.js +2 -0
  61. package/dist/bundle/chunks/image-resize-worker.js +1 -1
  62. package/dist/bundle/chunks/{llama-cpp-classify-EJ5XMSQL.js → llama-cpp-classify-MWIQKGBR.js} +3 -3
  63. package/dist/bundle/chunks/mistral-conversations-7ODWQ37T.js +5 -0
  64. package/dist/bundle/chunks/node-BZAVEWJ3.js +16 -0
  65. package/dist/bundle/chunks/openai-chatgpt.js +1 -1
  66. package/dist/bundle/chunks/openai-codex-responses-7Y2SP2GS.js +10 -0
  67. package/dist/bundle/chunks/openai-codex.js +1 -1
  68. package/dist/bundle/chunks/openai-completions-QNWYJ4H4.js +7 -0
  69. package/dist/bundle/chunks/openai-decisions-4PKBAPR3.js +5 -0
  70. package/dist/bundle/chunks/openai-responses-73WU3TQM.js +4 -0
  71. package/dist/bundle/chunks/opencode-go.js +1 -1
  72. package/dist/bundle/chunks/openrouter-images-IMWDSQ5F.js +2 -0
  73. package/dist/bundle/chunks/pi-messages-AMNZ7HKZ.js +8 -0
  74. package/dist/bundle/chunks/runtime-7BIFTREJ.js +3 -0
  75. package/dist/bundle/chunks/runtime-MZVF4MP6.js +2 -0
  76. package/dist/bundle/chunks/settings-manager-QF6DRH5C.js +2 -0
  77. package/dist/bundle/chunks/typesafe-system-one-AXQRIVVX.js +2 -0
  78. package/dist/bundle/chunks/virtual-modules-Z4F3ZUX3.js +2 -0
  79. package/dist/bundle/cli-runtime.js +1 -1
  80. package/dist/bundle/index.js +1 -1
  81. package/dist/bundle/rpc-entry.js +1 -1
  82. package/dist/cli/args.d.ts +2 -1
  83. package/dist/cli/args.d.ts.map +1 -1
  84. package/dist/cli/args.js +30 -8
  85. package/dist/cli/args.js.map +1 -1
  86. package/dist/cli/credential-print.d.ts.map +1 -1
  87. package/dist/cli/credential-print.js +4 -4
  88. package/dist/cli/credential-print.js.map +1 -1
  89. package/dist/config.d.ts +18 -1
  90. package/dist/config.d.ts.map +1 -1
  91. package/dist/config.js +44 -6
  92. package/dist/config.js.map +1 -1
  93. package/dist/core/agent-session.d.ts +65 -8
  94. package/dist/core/agent-session.d.ts.map +1 -1
  95. package/dist/core/agent-session.js +240 -102
  96. package/dist/core/agent-session.js.map +1 -1
  97. package/dist/core/auth-storage.d.ts.map +1 -1
  98. package/dist/core/auth-storage.js +20 -13
  99. package/dist/core/auth-storage.js.map +1 -1
  100. package/dist/core/bash-executor.d.ts.map +1 -1
  101. package/dist/core/bash-executor.js +42 -52
  102. package/dist/core/bash-executor.js.map +1 -1
  103. package/dist/core/bug-report.d.ts +9 -1
  104. package/dist/core/bug-report.d.ts.map +1 -1
  105. package/dist/core/builtins/completion-checks.d.ts +3 -0
  106. package/dist/core/builtins/completion-checks.d.ts.map +1 -0
  107. package/dist/core/builtins/completion-checks.js +142 -0
  108. package/dist/core/builtins/completion-checks.js.map +1 -0
  109. package/dist/core/builtins/duet.d.ts.map +1 -1
  110. package/dist/core/builtins/duet.js +7 -5
  111. package/dist/core/builtins/duet.js.map +1 -1
  112. package/dist/core/builtins/git-safety.d.ts +3 -0
  113. package/dist/core/builtins/git-safety.d.ts.map +1 -0
  114. package/dist/core/builtins/git-safety.js +34 -0
  115. package/dist/core/builtins/git-safety.js.map +1 -0
  116. package/dist/core/builtins/index.d.ts.map +1 -1
  117. package/dist/core/builtins/index.js +4 -0
  118. package/dist/core/builtins/index.js.map +1 -1
  119. package/dist/core/client-identity.d.ts +8 -0
  120. package/dist/core/client-identity.d.ts.map +1 -0
  121. package/dist/core/client-identity.js +15 -0
  122. package/dist/core/client-identity.js.map +1 -0
  123. package/dist/core/compaction/branch-summarization.d.ts.map +1 -1
  124. package/dist/core/compaction/branch-summarization.js +1 -2
  125. package/dist/core/compaction/branch-summarization.js.map +1 -1
  126. package/dist/core/compaction/compaction.d.ts +2 -2
  127. package/dist/core/compaction/compaction.d.ts.map +1 -1
  128. package/dist/core/compaction/compaction.js +20 -15
  129. package/dist/core/compaction/compaction.js.map +1 -1
  130. package/dist/core/compaction/utils.d.ts +6 -0
  131. package/dist/core/compaction/utils.d.ts.map +1 -1
  132. package/dist/core/compaction/utils.js +7 -8
  133. package/dist/core/compaction/utils.js.map +1 -1
  134. package/dist/core/export-html/index.d.ts.map +1 -1
  135. package/dist/core/export-html/index.js +2 -0
  136. package/dist/core/export-html/index.js.map +1 -1
  137. package/dist/core/export-html/template.html +1 -0
  138. package/dist/core/export-html/template.js +23 -17
  139. package/dist/core/export-html/tool-renderer.d.ts +3 -3
  140. package/dist/core/export-html/tool-renderer.d.ts.map +1 -1
  141. package/dist/core/export-html/tool-renderer.js +5 -3
  142. package/dist/core/export-html/tool-renderer.js.map +1 -1
  143. package/dist/core/export-html/vendor/marked-cjk-friendly.min.js +6 -0
  144. package/dist/core/export-html/vendor/marked.min.js +30 -29
  145. package/dist/core/extensions/index.d.ts +1 -1
  146. package/dist/core/extensions/index.d.ts.map +1 -1
  147. package/dist/core/extensions/index.js.map +1 -1
  148. package/dist/core/extensions/loader.d.ts.map +1 -1
  149. package/dist/core/extensions/loader.js +7 -0
  150. package/dist/core/extensions/loader.js.map +1 -1
  151. package/dist/core/extensions/runner.d.ts +6 -2
  152. package/dist/core/extensions/runner.d.ts.map +1 -1
  153. package/dist/core/extensions/runner.js +16 -4
  154. package/dist/core/extensions/runner.js.map +1 -1
  155. package/dist/core/extensions/types.d.ts +61 -7
  156. package/dist/core/extensions/types.d.ts.map +1 -1
  157. package/dist/core/extensions/types.js.map +1 -1
  158. package/dist/core/extensions/virtual-modules.d.ts.map +1 -1
  159. package/dist/core/extensions/virtual-modules.js +2 -0
  160. package/dist/core/extensions/virtual-modules.js.map +1 -1
  161. package/dist/core/key-id-schema.d.ts +6 -0
  162. package/dist/core/key-id-schema.d.ts.map +1 -0
  163. package/dist/core/key-id-schema.js +16 -0
  164. package/dist/core/key-id-schema.js.map +1 -0
  165. package/dist/core/keybindings-schema.d.ts +4 -0
  166. package/dist/core/keybindings-schema.d.ts.map +1 -0
  167. package/dist/core/keybindings-schema.js +16 -0
  168. package/dist/core/keybindings-schema.js.map +1 -0
  169. package/dist/core/keybindings.d.ts +242 -75
  170. package/dist/core/keybindings.d.ts.map +1 -1
  171. package/dist/core/keybindings.js +30 -23
  172. package/dist/core/keybindings.js.map +1 -1
  173. package/dist/core/mcp-servers.d.ts +22 -0
  174. package/dist/core/mcp-servers.d.ts.map +1 -1
  175. package/dist/core/mcp-servers.js +72 -11
  176. package/dist/core/mcp-servers.js.map +1 -1
  177. package/dist/core/model-config.d.ts +1623 -74
  178. package/dist/core/model-config.d.ts.map +1 -1
  179. package/dist/core/model-config.js +70 -184
  180. package/dist/core/model-config.js.map +1 -1
  181. package/dist/core/model-registry.d.ts +3 -1
  182. package/dist/core/model-registry.d.ts.map +1 -1
  183. package/dist/core/model-registry.js +4 -0
  184. package/dist/core/model-registry.js.map +1 -1
  185. package/dist/core/model-resolver.d.ts +56 -43
  186. package/dist/core/model-resolver.d.ts.map +1 -1
  187. package/dist/core/model-resolver.js +253 -358
  188. package/dist/core/model-resolver.js.map +1 -1
  189. package/dist/core/model-runtime.d.ts.map +1 -1
  190. package/dist/core/model-runtime.js +19 -10
  191. package/dist/core/model-runtime.js.map +1 -1
  192. package/dist/core/nested-tool-calls.d.ts +1 -0
  193. package/dist/core/nested-tool-calls.d.ts.map +1 -1
  194. package/dist/core/nested-tool-calls.js +1 -0
  195. package/dist/core/nested-tool-calls.js.map +1 -1
  196. package/dist/core/package-manager.js +3 -3
  197. package/dist/core/package-manager.js.map +1 -1
  198. package/dist/core/polyphase/keyword.js +1 -1
  199. package/dist/core/polyphase/keyword.js.map +1 -1
  200. package/dist/core/polyphase/model-selection.d.ts.map +1 -1
  201. package/dist/core/polyphase/model-selection.js +15 -7
  202. package/dist/core/polyphase/model-selection.js.map +1 -1
  203. package/dist/core/polyphase/workflow/prelude.d.ts +2 -0
  204. package/dist/core/polyphase/workflow/prelude.d.ts.map +1 -1
  205. package/dist/core/polyphase/workflow/prelude.js +12 -16
  206. package/dist/core/polyphase/workflow/prelude.js.map +1 -1
  207. package/dist/core/polyphase/workflow/runtime.d.ts.map +1 -1
  208. package/dist/core/polyphase/workflow/runtime.js +2 -1
  209. package/dist/core/polyphase/workflow/runtime.js.map +1 -1
  210. package/dist/core/project-trust.d.ts.map +1 -1
  211. package/dist/core/project-trust.js +2 -1
  212. package/dist/core/project-trust.js.map +1 -1
  213. package/dist/core/prompt-templates.d.ts.map +1 -1
  214. package/dist/core/prompt-templates.js +7 -2
  215. package/dist/core/prompt-templates.js.map +1 -1
  216. package/dist/core/provider-composer.d.ts +2 -1
  217. package/dist/core/provider-composer.d.ts.map +1 -1
  218. package/dist/core/provider-composer.js +13 -0
  219. package/dist/core/provider-composer.js.map +1 -1
  220. package/dist/core/radius.d.ts +2 -0
  221. package/dist/core/radius.d.ts.map +1 -1
  222. package/dist/core/radius.js +2 -0
  223. package/dist/core/radius.js.map +1 -1
  224. package/dist/core/remote-catalog-provider.d.ts +12 -1
  225. package/dist/core/remote-catalog-provider.d.ts.map +1 -1
  226. package/dist/core/remote-catalog-provider.js +84 -24
  227. package/dist/core/remote-catalog-provider.js.map +1 -1
  228. package/dist/core/resource-loader.d.ts +3 -0
  229. package/dist/core/resource-loader.d.ts.map +1 -1
  230. package/dist/core/resource-loader.js +7 -4
  231. package/dist/core/resource-loader.js.map +1 -1
  232. package/dist/core/sdk.d.ts +13 -4
  233. package/dist/core/sdk.d.ts.map +1 -1
  234. package/dist/core/sdk.js +27 -15
  235. package/dist/core/sdk.js.map +1 -1
  236. package/dist/core/settings-defaults.d.ts +65 -0
  237. package/dist/core/settings-defaults.d.ts.map +1 -0
  238. package/dist/core/settings-defaults.js +66 -0
  239. package/dist/core/settings-defaults.js.map +1 -0
  240. package/dist/core/settings-manager.d.ts +17 -178
  241. package/dist/core/settings-manager.d.ts.map +1 -1
  242. package/dist/core/settings-manager.js +86 -57
  243. package/dist/core/settings-manager.js.map +1 -1
  244. package/dist/core/settings-schema.d.ts +269 -0
  245. package/dist/core/settings-schema.d.ts.map +1 -0
  246. package/dist/core/settings-schema.js +318 -0
  247. package/dist/core/settings-schema.js.map +1 -0
  248. package/dist/core/skills.d.ts +4 -1
  249. package/dist/core/skills.d.ts.map +1 -1
  250. package/dist/core/skills.js +6 -1
  251. package/dist/core/skills.js.map +1 -1
  252. package/dist/core/system-prompt.d.ts +6 -0
  253. package/dist/core/system-prompt.d.ts.map +1 -1
  254. package/dist/core/system-prompt.js +10 -5
  255. package/dist/core/system-prompt.js.map +1 -1
  256. package/dist/core/tools/bash.d.ts.map +1 -1
  257. package/dist/core/tools/bash.js +3 -5
  258. package/dist/core/tools/bash.js.map +1 -1
  259. package/dist/core/tools/grep.d.ts +8 -0
  260. package/dist/core/tools/grep.d.ts.map +1 -1
  261. package/dist/core/tools/grep.js +19 -7
  262. package/dist/core/tools/grep.js.map +1 -1
  263. package/dist/core/tools/index.d.ts +2 -0
  264. package/dist/core/tools/index.d.ts.map +1 -1
  265. package/dist/core/tools/index.js +2 -0
  266. package/dist/core/tools/index.js.map +1 -1
  267. package/dist/core/tools/output-accumulator.d.ts.map +1 -1
  268. package/dist/core/tools/output-accumulator.js +4 -10
  269. package/dist/core/tools/output-accumulator.js.map +1 -1
  270. package/dist/core/tools/path-utils.d.ts +1 -1
  271. package/dist/core/tools/path-utils.d.ts.map +1 -1
  272. package/dist/core/tools/path-utils.js +6 -6
  273. package/dist/core/tools/path-utils.js.map +1 -1
  274. package/dist/core/tools/read.d.ts +13 -0
  275. package/dist/core/tools/read.d.ts.map +1 -1
  276. package/dist/core/tools/read.js +32 -2
  277. package/dist/core/tools/read.js.map +1 -1
  278. package/dist/core/tools/render-utils.d.ts +20 -0
  279. package/dist/core/tools/render-utils.d.ts.map +1 -1
  280. package/dist/core/tools/render-utils.js +67 -0
  281. package/dist/core/tools/render-utils.js.map +1 -1
  282. package/dist/core/tools/renderers/bash.d.ts.map +1 -1
  283. package/dist/core/tools/renderers/bash.js +7 -35
  284. package/dist/core/tools/renderers/bash.js.map +1 -1
  285. package/dist/core/tools/renderers/edit.d.ts.map +1 -1
  286. package/dist/core/tools/renderers/edit.js +5 -4
  287. package/dist/core/tools/renderers/edit.js.map +1 -1
  288. package/dist/core/tools/renderers/index.d.ts +2 -2
  289. package/dist/core/tools/renderers/index.d.ts.map +1 -1
  290. package/dist/core/tools/renderers/index.js.map +1 -1
  291. package/dist/core/tools/renderers/read.d.ts.map +1 -1
  292. package/dist/core/tools/renderers/read.js +7 -11
  293. package/dist/core/tools/renderers/read.js.map +1 -1
  294. package/dist/extensions/codemode/execute.d.ts.map +1 -1
  295. package/dist/extensions/codemode/execute.js +391 -80
  296. package/dist/extensions/codemode/execute.js.map +1 -1
  297. package/dist/extensions/codemode/index.d.ts.map +1 -1
  298. package/dist/extensions/codemode/index.js +3 -1
  299. package/dist/extensions/codemode/index.js.map +1 -1
  300. package/dist/extensions/codemode/renderer.d.ts +2 -2
  301. package/dist/extensions/codemode/renderer.d.ts.map +1 -1
  302. package/dist/extensions/codemode/renderer.js +9 -3
  303. package/dist/extensions/codemode/renderer.js.map +1 -1
  304. package/dist/extensions/codemode/tool.d.ts +22 -21
  305. package/dist/extensions/codemode/tool.d.ts.map +1 -1
  306. package/dist/extensions/codemode/tool.js +96 -123
  307. package/dist/extensions/codemode/tool.js.map +1 -1
  308. package/dist/extensions/llama/provider.d.ts.map +1 -1
  309. package/dist/extensions/llama/provider.js +34 -11
  310. package/dist/extensions/llama/provider.js.map +1 -1
  311. package/dist/extensions/mcp/cli.d.ts.map +1 -1
  312. package/dist/extensions/mcp/cli.js +27 -33
  313. package/dist/extensions/mcp/cli.js.map +1 -1
  314. package/dist/extensions/mcp/config.d.ts +15 -3
  315. package/dist/extensions/mcp/config.d.ts.map +1 -1
  316. package/dist/extensions/mcp/config.js +49 -12
  317. package/dist/extensions/mcp/config.js.map +1 -1
  318. package/dist/extensions/mcp/index.d.ts +4 -1
  319. package/dist/extensions/mcp/index.d.ts.map +1 -1
  320. package/dist/extensions/mcp/index.js +279 -129
  321. package/dist/extensions/mcp/index.js.map +1 -1
  322. package/dist/extensions/mcp/oauth.d.ts +21 -11
  323. package/dist/extensions/mcp/oauth.d.ts.map +1 -1
  324. package/dist/extensions/mcp/oauth.js +166 -45
  325. package/dist/extensions/mcp/oauth.js.map +1 -1
  326. package/dist/extensions/mcp/resources.d.ts +3 -10
  327. package/dist/extensions/mcp/resources.d.ts.map +1 -1
  328. package/dist/extensions/mcp/resources.js +4 -5
  329. package/dist/extensions/mcp/resources.js.map +1 -1
  330. package/dist/extensions/mcp/runtime.d.ts +7 -7
  331. package/dist/extensions/mcp/runtime.d.ts.map +1 -1
  332. package/dist/extensions/mcp/runtime.js +31 -45
  333. package/dist/extensions/mcp/runtime.js.map +1 -1
  334. package/dist/extensions/mcp/tools.d.ts +7 -5
  335. package/dist/extensions/mcp/tools.d.ts.map +1 -1
  336. package/dist/extensions/mcp/tools.js +87 -29
  337. package/dist/extensions/mcp/tools.js.map +1 -1
  338. package/dist/extensions/mcp/ui.d.ts +3 -3
  339. package/dist/extensions/mcp/ui.d.ts.map +1 -1
  340. package/dist/extensions/mcp/ui.js +18 -6
  341. package/dist/extensions/mcp/ui.js.map +1 -1
  342. package/dist/extensions/tool-search/tool.d.ts +0 -2
  343. package/dist/extensions/tool-search/tool.d.ts.map +1 -1
  344. package/dist/extensions/tool-search/tool.js +2 -4
  345. package/dist/extensions/tool-search/tool.js.map +1 -1
  346. package/dist/hooks/checks/checks-runtime.cjs +215 -0
  347. package/dist/hooks/checks/git-safety.cjs +198 -0
  348. package/dist/hooks/checks/git-safety.d.cts +1 -0
  349. package/dist/hooks/gsd/draht-post-task.js +78 -39
  350. package/dist/hooks/gsd/draht-quality-gate.js +210 -122
  351. package/dist/hooks/gsd/package.json +3 -0
  352. package/dist/index.d.ts +5 -4
  353. package/dist/index.d.ts.map +1 -1
  354. package/dist/index.js +3 -2
  355. package/dist/index.js.map +1 -1
  356. package/dist/main.d.ts.map +1 -1
  357. package/dist/main.js +11 -3
  358. package/dist/main.js.map +1 -1
  359. package/dist/modes/interactive/components/auth-url.d.ts +14 -0
  360. package/dist/modes/interactive/components/auth-url.d.ts.map +1 -0
  361. package/dist/modes/interactive/components/auth-url.js +37 -0
  362. package/dist/modes/interactive/components/auth-url.js.map +1 -0
  363. package/dist/modes/interactive/components/bash-execution.d.ts +5 -1
  364. package/dist/modes/interactive/components/bash-execution.d.ts.map +1 -1
  365. package/dist/modes/interactive/components/bash-execution.js +17 -14
  366. package/dist/modes/interactive/components/bash-execution.js.map +1 -1
  367. package/dist/modes/interactive/components/branch-summary-message.d.ts +2 -1
  368. package/dist/modes/interactive/components/branch-summary-message.d.ts.map +1 -1
  369. package/dist/modes/interactive/components/branch-summary-message.js +5 -2
  370. package/dist/modes/interactive/components/branch-summary-message.js.map +1 -1
  371. package/dist/modes/interactive/components/compaction-summary-message.d.ts +2 -1
  372. package/dist/modes/interactive/components/compaction-summary-message.d.ts.map +1 -1
  373. package/dist/modes/interactive/components/compaction-summary-message.js +5 -2
  374. package/dist/modes/interactive/components/compaction-summary-message.js.map +1 -1
  375. package/dist/modes/interactive/components/custom-entry.d.ts +3 -1
  376. package/dist/modes/interactive/components/custom-entry.d.ts.map +1 -1
  377. package/dist/modes/interactive/components/custom-entry.js +8 -2
  378. package/dist/modes/interactive/components/custom-entry.js.map +1 -1
  379. package/dist/modes/interactive/components/custom-message.d.ts.map +1 -1
  380. package/dist/modes/interactive/components/custom-message.js +1 -0
  381. package/dist/modes/interactive/components/custom-message.js.map +1 -1
  382. package/dist/modes/interactive/components/login-dialog.d.ts +3 -0
  383. package/dist/modes/interactive/components/login-dialog.d.ts.map +1 -1
  384. package/dist/modes/interactive/components/login-dialog.js +38 -10
  385. package/dist/modes/interactive/components/login-dialog.js.map +1 -1
  386. package/dist/modes/interactive/components/oauth-selector.d.ts +8 -2
  387. package/dist/modes/interactive/components/oauth-selector.d.ts.map +1 -1
  388. package/dist/modes/interactive/components/oauth-selector.js +24 -21
  389. package/dist/modes/interactive/components/oauth-selector.js.map +1 -1
  390. package/dist/modes/interactive/components/radius-login-selector.d.ts +15 -0
  391. package/dist/modes/interactive/components/radius-login-selector.d.ts.map +1 -0
  392. package/dist/modes/interactive/components/radius-login-selector.js +85 -0
  393. package/dist/modes/interactive/components/radius-login-selector.js.map +1 -0
  394. package/dist/modes/interactive/components/settings-selector.d.ts +3 -3
  395. package/dist/modes/interactive/components/settings-selector.d.ts.map +1 -1
  396. package/dist/modes/interactive/components/settings-selector.js +9 -8
  397. package/dist/modes/interactive/components/settings-selector.js.map +1 -1
  398. package/dist/modes/interactive/components/skill-invocation-message.d.ts +2 -1
  399. package/dist/modes/interactive/components/skill-invocation-message.d.ts.map +1 -1
  400. package/dist/modes/interactive/components/skill-invocation-message.js +5 -2
  401. package/dist/modes/interactive/components/skill-invocation-message.js.map +1 -1
  402. package/dist/modes/interactive/components/status-indicator.d.ts +1 -1
  403. package/dist/modes/interactive/components/status-indicator.d.ts.map +1 -1
  404. package/dist/modes/interactive/components/status-indicator.js +2 -2
  405. package/dist/modes/interactive/components/status-indicator.js.map +1 -1
  406. package/dist/modes/interactive/components/tool-execution.d.ts +12 -13
  407. package/dist/modes/interactive/components/tool-execution.d.ts.map +1 -1
  408. package/dist/modes/interactive/components/tool-execution.js +32 -45
  409. package/dist/modes/interactive/components/tool-execution.js.map +1 -1
  410. package/dist/modes/interactive/components/tree-selector.d.ts.map +1 -1
  411. package/dist/modes/interactive/components/tree-selector.js +2 -9
  412. package/dist/modes/interactive/components/tree-selector.js.map +1 -1
  413. package/dist/modes/interactive/components/user-message.d.ts.map +1 -1
  414. package/dist/modes/interactive/components/user-message.js +5 -4
  415. package/dist/modes/interactive/components/user-message.js.map +1 -1
  416. package/dist/modes/interactive/interactive-mode.d.ts +43 -48
  417. package/dist/modes/interactive/interactive-mode.d.ts.map +1 -1
  418. package/dist/modes/interactive/interactive-mode.js +362 -278
  419. package/dist/modes/interactive/interactive-mode.js.map +1 -1
  420. package/dist/modes/interactive/program-status-reporter.d.ts +34 -0
  421. package/dist/modes/interactive/program-status-reporter.d.ts.map +1 -0
  422. package/dist/modes/interactive/program-status-reporter.js +110 -0
  423. package/dist/modes/interactive/program-status-reporter.js.map +1 -0
  424. package/dist/modes/interactive/theme/dark.json +1 -1
  425. package/dist/modes/interactive/theme/light.json +1 -1
  426. package/dist/modes/interactive/theme/system-theme.d.ts +2 -1
  427. package/dist/modes/interactive/theme/system-theme.d.ts.map +1 -1
  428. package/dist/modes/interactive/theme/system-theme.js +16 -5
  429. package/dist/modes/interactive/theme/system-theme.js.map +1 -1
  430. package/dist/modes/interactive/theme/theme-schema.d.ts +28 -0
  431. package/dist/modes/interactive/theme/theme-schema.d.ts.map +1 -0
  432. package/dist/modes/interactive/theme/theme-schema.js +105 -0
  433. package/dist/modes/interactive/theme/theme-schema.js.map +1 -0
  434. package/dist/modes/interactive/theme/theme-tokens.d.ts +257 -0
  435. package/dist/modes/interactive/theme/theme-tokens.d.ts.map +1 -0
  436. package/dist/modes/interactive/theme/theme-tokens.js +94 -0
  437. package/dist/modes/interactive/theme/theme-tokens.js.map +1 -0
  438. package/dist/modes/interactive/theme/theme.d.ts +13 -16
  439. package/dist/modes/interactive/theme/theme.d.ts.map +1 -1
  440. package/dist/modes/interactive/theme/theme.js +22 -29
  441. package/dist/modes/interactive/theme/theme.js.map +1 -1
  442. package/dist/modes/print-mode.d.ts.map +1 -1
  443. package/dist/modes/print-mode.js +4 -0
  444. package/dist/modes/print-mode.js.map +1 -1
  445. package/dist/package-manager-cli.d.ts.map +1 -1
  446. package/dist/package-manager-cli.js +26 -1
  447. package/dist/package-manager-cli.js.map +1 -1
  448. package/dist/prompts/commands/atomic-commit.md +8 -6
  449. package/dist/prompts/commands/brainstorm.md +5 -149
  450. package/dist/prompts/commands/create-verification-skill.md +8 -48
  451. package/dist/prompts/commands/discuss-phase.md +6 -10
  452. package/dist/prompts/commands/execute-phase.md +18 -45
  453. package/dist/prompts/commands/fix.md +16 -128
  454. package/dist/prompts/commands/grill.md +6 -53
  455. package/dist/prompts/commands/init-project.md +13 -18
  456. package/dist/prompts/commands/map-codebase.md +3 -3
  457. package/dist/prompts/commands/new-project.md +12 -17
  458. package/dist/prompts/commands/next-milestone.md +4 -8
  459. package/dist/prompts/commands/orchestrate-loop.md +12 -12
  460. package/dist/prompts/commands/orchestrate.md +12 -11
  461. package/dist/prompts/commands/pause-work.md +1 -1
  462. package/dist/prompts/commands/plan-phase.md +15 -37
  463. package/dist/prompts/commands/quick.md +11 -64
  464. package/dist/prompts/commands/resolve-conflicts.md +2 -15
  465. package/dist/prompts/commands/triage.md +3 -14
  466. package/dist/prompts/commands/verify-work.md +15 -63
  467. package/dist/prompts/commands/why.md +18 -118
  468. package/dist/skills/atomic-reasoning/SKILL.md +6 -105
  469. package/dist/skills/blast-radius/SKILL.md +1 -1
  470. package/dist/skills/epistemics/SKILL.md +12 -87
  471. package/dist/skills/explainers/SKILL.md +1 -1
  472. package/dist/skills/typescript-discipline/SKILL.md +12 -42
  473. package/dist/skills/typescript-discipline/references/patterns.md +25 -266
  474. package/dist/skills/unslop/SKILL.md +14 -105
  475. package/dist/utils/ansi.d.ts +8 -0
  476. package/dist/utils/ansi.d.ts.map +1 -1
  477. package/dist/utils/ansi.js +30 -11
  478. package/dist/utils/ansi.js.map +1 -1
  479. package/dist/utils/clipboard-command.d.ts.map +1 -1
  480. package/dist/utils/clipboard-command.js +3 -0
  481. package/dist/utils/clipboard-command.js.map +1 -1
  482. package/dist/utils/clipboard.d.ts.map +1 -1
  483. package/dist/utils/clipboard.js +18 -12
  484. package/dist/utils/clipboard.js.map +1 -1
  485. package/dist/utils/draht-user-agent.d.ts +1 -0
  486. package/dist/utils/draht-user-agent.d.ts.map +1 -1
  487. package/dist/utils/draht-user-agent.js +3 -2
  488. package/dist/utils/draht-user-agent.js.map +1 -1
  489. package/dist/utils/image-convert.d.ts +12 -0
  490. package/dist/utils/image-convert.d.ts.map +1 -1
  491. package/dist/utils/image-convert.js +45 -6
  492. package/dist/utils/image-convert.js.map +1 -1
  493. package/dist/utils/image-resize-core.d.ts +12 -0
  494. package/dist/utils/image-resize-core.d.ts.map +1 -1
  495. package/dist/utils/image-resize-core.js +5 -0
  496. package/dist/utils/image-resize-core.js.map +1 -1
  497. package/dist/utils/image-resize-worker.js +3 -2
  498. package/dist/utils/image-resize-worker.js.map +1 -1
  499. package/dist/utils/image-resize.d.ts.map +1 -1
  500. package/dist/utils/image-resize.js +9 -10
  501. package/dist/utils/image-resize.js.map +1 -1
  502. package/dist/utils/output-files.d.ts +15 -0
  503. package/dist/utils/output-files.d.ts.map +1 -0
  504. package/dist/utils/output-files.js +30 -0
  505. package/dist/utils/output-files.js.map +1 -0
  506. package/dist/utils/shell.d.ts.map +1 -1
  507. package/dist/utils/shell.js +43 -13
  508. package/dist/utils/shell.js.map +1 -1
  509. package/dist/utils/syntax-highlight.d.ts.map +1 -1
  510. package/dist/utils/syntax-highlight.js +6 -1
  511. package/dist/utils/syntax-highlight.js.map +1 -1
  512. package/dist/utils/tools-manager.d.ts.map +1 -1
  513. package/dist/utils/tools-manager.js +4 -3
  514. package/dist/utils/tools-manager.js.map +1 -1
  515. package/docs/cli-integration.md +1 -1
  516. package/docs/cli.md +30 -26
  517. package/docs/codemode.md +230 -0
  518. package/docs/compaction.md +5 -5
  519. package/docs/containerization.md +1 -1
  520. package/docs/custom-provider.md +53 -1
  521. package/docs/docs.json +17 -1
  522. package/docs/drahtbank.md +163 -0
  523. package/docs/environment-variables.md +5 -2
  524. package/docs/extensions.md +143 -13
  525. package/docs/index.md +1 -1
  526. package/docs/json.md +3 -3
  527. package/docs/keybindings.md +9 -5
  528. package/docs/llama-cpp.md +9 -2
  529. package/docs/mcp.md +59 -3
  530. package/docs/message-types.md +22 -4
  531. package/docs/models-configuration.md +187 -0
  532. package/docs/models.md +67 -4
  533. package/docs/nvidia-rtx-llama-cpp.md +96 -0
  534. package/docs/providers.md +70 -5
  535. package/docs/sdk.md +1 -1
  536. package/docs/settings.md +10 -8
  537. package/docs/terminal-setup.md +14 -0
  538. package/docs/themes.md +4 -2
  539. package/docs/tui.md +71 -1
  540. package/docs/usage.md +1 -1
  541. package/docs/windows.md +16 -2
  542. package/eval/drahtbank/adapters.d.mts +35 -0
  543. package/eval/drahtbank/adapters.mjs +192 -0
  544. package/eval/drahtbank/bank.d.mts +141 -0
  545. package/eval/drahtbank/bank.mjs +515 -0
  546. package/eval/drahtbank/cases-v2.d.mts +28 -0
  547. package/eval/drahtbank/cases-v2.mjs +164 -0
  548. package/eval/drahtbank/cases.d.mts +17 -0
  549. package/eval/drahtbank/cases.mjs +198 -0
  550. package/eval/drahtbank/cli.mjs +120 -0
  551. package/eval/drahtbank/grading-v2.d.mts +26 -0
  552. package/eval/drahtbank/grading-v2.mjs +227 -0
  553. package/eval/drahtbank/isolated-tools.ts +223 -0
  554. package/eval/drahtbank/isolation-worker.mjs +53 -0
  555. package/eval/drahtbank/isolation.d.mts +52 -0
  556. package/eval/drahtbank/isolation.mjs +345 -0
  557. package/eval/drahtbank/runtime-checks.d.mts +15 -0
  558. package/eval/drahtbank/runtime-checks.mjs +187 -0
  559. package/examples/extensions/dynamic-resources/dynamic.json +1 -1
  560. package/examples/extensions/minimal-mode.ts +4 -5
  561. package/examples/extensions/overlay-test.ts +2 -2
  562. package/examples/extensions/plan-mode/index.ts +6 -2
  563. package/examples/extensions/subagent/index.ts +4 -6
  564. package/hooks/checks/checks-runtime.cjs +215 -0
  565. package/hooks/checks/git-safety.cjs +198 -0
  566. package/hooks/checks/git-safety.d.cts +1 -0
  567. package/hooks/gsd/draht-post-task.js +78 -39
  568. package/hooks/gsd/draht-quality-gate.js +210 -122
  569. package/hooks/gsd/package.json +3 -0
  570. package/package.json +21 -16
  571. package/prompts/commands/atomic-commit.md +8 -6
  572. package/prompts/commands/brainstorm.md +5 -149
  573. package/prompts/commands/create-verification-skill.md +8 -48
  574. package/prompts/commands/discuss-phase.md +6 -10
  575. package/prompts/commands/execute-phase.md +18 -45
  576. package/prompts/commands/fix.md +16 -128
  577. package/prompts/commands/grill.md +6 -53
  578. package/prompts/commands/init-project.md +13 -18
  579. package/prompts/commands/map-codebase.md +3 -3
  580. package/prompts/commands/new-project.md +12 -17
  581. package/prompts/commands/next-milestone.md +4 -8
  582. package/prompts/commands/orchestrate-loop.md +12 -12
  583. package/prompts/commands/orchestrate.md +12 -11
  584. package/prompts/commands/pause-work.md +1 -1
  585. package/prompts/commands/plan-phase.md +15 -37
  586. package/prompts/commands/quick.md +11 -64
  587. package/prompts/commands/resolve-conflicts.md +2 -15
  588. package/prompts/commands/triage.md +3 -14
  589. package/prompts/commands/verify-work.md +15 -63
  590. package/prompts/commands/why.md +18 -118
  591. package/schemas/keybindings.schema.json +433 -0
  592. package/schemas/models.schema.json +1190 -0
  593. package/schemas/settings.schema.json +849 -0
  594. package/schemas/theme.schema.json +365 -0
  595. package/skills/atomic-reasoning/SKILL.md +6 -105
  596. package/skills/blast-radius/SKILL.md +1 -1
  597. package/skills/epistemics/SKILL.md +12 -87
  598. package/skills/explainers/SKILL.md +1 -1
  599. package/skills/typescript-discipline/SKILL.md +12 -42
  600. package/skills/typescript-discipline/references/patterns.md +25 -266
  601. package/skills/unslop/SKILL.md +14 -105
  602. package/dist/bundle/chunks/anthropic-messages-GAKYXF65.js +0 -6
  603. package/dist/bundle/chunks/azure-openai-responses-ZIXMK6JO.js +0 -2
  604. package/dist/bundle/chunks/chunk-2E5VODES.js +0 -2
  605. package/dist/bundle/chunks/chunk-2VAF4XJI.js +0 -146
  606. package/dist/bundle/chunks/chunk-4TVQYRQY.js +0 -2
  607. package/dist/bundle/chunks/chunk-7TYCZN4Z.js +0 -137
  608. package/dist/bundle/chunks/chunk-BXSHCX3G.js +0 -11
  609. package/dist/bundle/chunks/chunk-GVXA72ZA.js +0 -2
  610. package/dist/bundle/chunks/chunk-I5OKY6RH.js +0 -11
  611. package/dist/bundle/chunks/chunk-KU5HAKZL.js +0 -4
  612. package/dist/bundle/chunks/chunk-MO3SCGBN.js +0 -18
  613. package/dist/bundle/chunks/chunk-N2QZNJT6.js +0 -65
  614. package/dist/bundle/chunks/chunk-PGJAHC3R.js +0 -107
  615. package/dist/bundle/chunks/chunk-QVFELZW2.js +0 -312
  616. package/dist/bundle/chunks/chunk-RZKPFWMH.js +0 -42
  617. package/dist/bundle/chunks/chunk-SDRCE6OP.js +0 -2
  618. package/dist/bundle/chunks/chunk-SVNWI7EV.js +0 -8
  619. package/dist/bundle/chunks/chunk-TOWVIJ2O.js +0 -1623
  620. package/dist/bundle/chunks/chunk-XBUEMKIY.js +0 -2
  621. package/dist/bundle/chunks/chunk-ZA4QNPJY.js +0 -82
  622. package/dist/bundle/chunks/cloudflare-workers-ai-system-one-MJKOAE5S.js +0 -2
  623. package/dist/bundle/chunks/execute-6N7T7VLY.js +0 -18
  624. package/dist/bundle/chunks/google-generative-ai-RPUPQ6PM.js +0 -2
  625. package/dist/bundle/chunks/google-vertex-EZES5QVQ.js +0 -2
  626. package/dist/bundle/chunks/mistral-conversations-AOYGU43Y.js +0 -5
  627. package/dist/bundle/chunks/node-LQ52KV6B.js +0 -16
  628. package/dist/bundle/chunks/openai-codex-responses-M2Y77JEQ.js +0 -10
  629. package/dist/bundle/chunks/openai-completions-A4OKYOYV.js +0 -7
  630. package/dist/bundle/chunks/openai-responses-6IXV53T3.js +0 -3
  631. package/dist/bundle/chunks/openrouter-images-LYV4NKFM.js +0 -2
  632. package/dist/bundle/chunks/pi-messages-KKMEUT3Z.js +0 -8
  633. package/dist/bundle/chunks/runtime-363BOYEO.js +0 -3
  634. package/dist/bundle/chunks/runtime-D3KV73AE.js +0 -2
  635. package/dist/bundle/chunks/settings-manager-GEOZJXFQ.js +0 -2
  636. package/dist/bundle/chunks/typesafe-system-one-YBEEY5XU.js +0 -2
  637. package/dist/bundle/chunks/virtual-modules-RLC4Y5MX.js +0 -2
  638. package/dist/core/provider-attribution.d.ts +0 -4
  639. package/dist/core/provider-attribution.d.ts.map +0 -1
  640. package/dist/core/provider-attribution.js +0 -72
  641. package/dist/core/provider-attribution.js.map +0 -1
  642. package/dist/experimental/micro/api.d.ts +0 -81
  643. package/dist/experimental/micro/api.d.ts.map +0 -1
  644. package/dist/experimental/micro/api.js +0 -2
  645. package/dist/experimental/micro/api.js.map +0 -1
  646. package/dist/experimental/micro/main.d.ts +0 -3
  647. package/dist/experimental/micro/main.d.ts.map +0 -1
  648. package/dist/experimental/micro/main.js +0 -21
  649. package/dist/experimental/micro/main.js.map +0 -1
  650. package/dist/experimental/micro/models.d.ts +0 -11
  651. package/dist/experimental/micro/models.d.ts.map +0 -1
  652. package/dist/experimental/micro/models.js +0 -95
  653. package/dist/experimental/micro/models.js.map +0 -1
  654. package/dist/experimental/micro/runtime.d.ts +0 -12
  655. package/dist/experimental/micro/runtime.d.ts.map +0 -1
  656. package/dist/experimental/micro/runtime.js +0 -465
  657. package/dist/experimental/micro/runtime.js.map +0 -1
  658. package/dist/experimental/micro/sessions.d.ts +0 -10
  659. package/dist/experimental/micro/sessions.d.ts.map +0 -1
  660. package/dist/experimental/micro/sessions.js +0 -41
  661. package/dist/experimental/micro/sessions.js.map +0 -1
  662. package/dist/experimental/micro/tools.d.ts +0 -10
  663. package/dist/experimental/micro/tools.d.ts.map +0 -1
  664. package/dist/experimental/micro/tools.js +0 -96
  665. package/dist/experimental/micro/tools.js.map +0 -1
  666. package/dist/experimental/micro/tui.d.ts +0 -3
  667. package/dist/experimental/micro/tui.d.ts.map +0 -1
  668. package/dist/experimental/micro/tui.js +0 -510
  669. package/dist/experimental/micro/tui.js.map +0 -1
  670. package/dist/experimental/mini/main.d.ts +0 -7
  671. package/dist/experimental/mini/main.d.ts.map +0 -1
  672. package/dist/experimental/mini/main.js +0 -21
  673. package/dist/experimental/mini/main.js.map +0 -1
  674. package/dist/experimental/mini/server/entry.d.ts +0 -3
  675. package/dist/experimental/mini/server/entry.d.ts.map +0 -1
  676. package/dist/experimental/mini/server/entry.js +0 -11
  677. package/dist/experimental/mini/server/entry.js.map +0 -1
  678. package/dist/experimental/mini/server/run.d.ts +0 -13
  679. package/dist/experimental/mini/server/run.d.ts.map +0 -1
  680. package/dist/experimental/mini/server/run.js +0 -150
  681. package/dist/experimental/mini/server/run.js.map +0 -1
  682. package/dist/experimental/mini/shared/protocol.d.ts +0 -127
  683. package/dist/experimental/mini/shared/protocol.d.ts.map +0 -1
  684. package/dist/experimental/mini/shared/protocol.js +0 -13
  685. package/dist/experimental/mini/shared/protocol.js.map +0 -1
  686. package/dist/experimental/mini/shared/rpc.d.ts +0 -49
  687. package/dist/experimental/mini/shared/rpc.d.ts.map +0 -1
  688. package/dist/experimental/mini/shared/rpc.js +0 -171
  689. package/dist/experimental/mini/shared/rpc.js.map +0 -1
  690. package/dist/experimental/mini/shared/transport.d.ts +0 -35
  691. package/dist/experimental/mini/shared/transport.d.ts.map +0 -1
  692. package/dist/experimental/mini/shared/transport.js +0 -94
  693. package/dist/experimental/mini/shared/transport.js.map +0 -1
  694. package/dist/experimental/mini/tui/run.d.ts +0 -9
  695. package/dist/experimental/mini/tui/run.d.ts.map +0 -1
  696. package/dist/experimental/mini/tui/run.js +0 -62
  697. package/dist/experimental/mini/tui/run.js.map +0 -1
  698. package/dist/experimental/mini/tui/session.d.ts +0 -26
  699. package/dist/experimental/mini/tui/session.d.ts.map +0 -1
  700. package/dist/experimental/mini/tui/session.js +0 -94
  701. package/dist/experimental/mini/tui/session.js.map +0 -1
  702. package/dist/experimental/mini/tui/view.d.ts +0 -10
  703. package/dist/experimental/mini/tui/view.d.ts.map +0 -1
  704. package/dist/experimental/mini/tui/view.js +0 -461
  705. package/dist/experimental/mini/tui/view.js.map +0 -1
  706. package/dist/experimental/mini/worker/entry.d.ts +0 -3
  707. package/dist/experimental/mini/worker/entry.d.ts.map +0 -1
  708. package/dist/experimental/mini/worker/entry.js +0 -10
  709. package/dist/experimental/mini/worker/entry.js.map +0 -1
  710. package/dist/experimental/mini/worker/lane-service.d.ts +0 -44
  711. package/dist/experimental/mini/worker/lane-service.d.ts.map +0 -1
  712. package/dist/experimental/mini/worker/lane-service.js +0 -97
  713. package/dist/experimental/mini/worker/lane-service.js.map +0 -1
  714. package/dist/experimental/mini/worker/models-service.d.ts +0 -19
  715. package/dist/experimental/mini/worker/models-service.d.ts.map +0 -1
  716. package/dist/experimental/mini/worker/models-service.js +0 -136
  717. package/dist/experimental/mini/worker/models-service.js.map +0 -1
  718. package/dist/experimental/mini/worker/run.d.ts +0 -14
  719. package/dist/experimental/mini/worker/run.d.ts.map +0 -1
  720. package/dist/experimental/mini/worker/run.js +0 -88
  721. package/dist/experimental/mini/worker/run.js.map +0 -1
  722. package/dist/modes/interactive/theme/theme-json.d.ts +0 -85
  723. package/dist/modes/interactive/theme/theme-json.d.ts.map +0 -1
  724. package/dist/modes/interactive/theme/theme-json.js +0 -132
  725. package/dist/modes/interactive/theme/theme-json.js.map +0 -1
  726. package/dist/modes/interactive/theme/theme-schema.json +0 -361
@@ -21,7 +21,7 @@ Decompose the work into independently verifiable units before acting; the `atomi
21
21
  1. Run `draht-tools map-codebase $1` (graph artifacts are always whole-repo — see below)
22
22
  2. Tool generates: STACK.md, ARCHITECTURE.md, CONVENTIONS.md, CONCERNS.md
23
23
  2a. Run `draht-tools map-graph` to produce the **living architecture map**. The graph always maps the whole repository from the git root, regardless of any directory argument — the tool enforces this deterministically; a directory argument only scopes the narrative analysis in step 3, not the graph itself.
24
- - `.planning/codebase/MAP.json` — machine-readable map with **entry points** (CLI bins, HTTP routes, library main exports), **sinks** (FS / net / DB / stdout / exec calls), **bounded contexts** (packages), **cross-package dataflow edges**, **symbol-resolved call edges**, **flows** (which sinks each entry point reaches and through which intermediate module), per-module **layer** (presentation / application / domain / infrastructure / support), and exports/imports per file. Agents starting a new task should read MAP.json first instead of re-scanning the tree.
24
+ - `.planning/codebase/MAP.json` — machine-readable map with **entry points** (CLI bins, HTTP routes, library main exports), **sinks** (FS / net / DB / stdout / exec calls), **bounded contexts** (packages), **cross-package dataflow edges**, **symbol-resolved call edges**, **flows** (which sinks each entry point reaches and through which intermediate module), per-module **layer** (presentation / application / domain / infrastructure / support), and exports/imports per file. Orient with `GRAPH_REPORT.md` and focused `graph-*` queries; load only relevant map slices into context.
25
25
  - `.planning/codebase/MAP.html` — interactive visualization with three tabs:
26
26
  - **Graph** — the primary interactive force-directed knowledge graph: nodes colored by cluster and sized by degree; click a node for an inspector (file, symbols, importers, callers); search plus filters for layer / cluster / edge-confidence (EXTRACTED/INFERRED/AMBIGUOUS); legend; PNG/SVG export; double-click a cluster to expand/collapse it.
27
27
  - **Architecture** — package containers in layer bands with cross-package dataflow arrows.
@@ -45,11 +45,11 @@ Decompose the work into independently verifiable units before acting; the `atomi
45
45
  - `## Coverage Goals` — target coverage percentage and which paths are critical
46
46
  - `## Testing Levels` — what is tested at unit level vs integration vs e2e, with examples
47
47
  - `## Excluded` — what is explicitly not tested and why
48
- 7. Commit: `draht-tools commit-docs "map existing codebase"`
48
+ 7. If committing is authorized: `draht-tools commit-docs "map existing codebase"`
49
49
 
50
50
  ## Living map for agents
51
51
 
52
52
  The `MAP.json` produced in step 2a is the single source of truth for "what's in this codebase". It is always the **whole-repo** map — `map-graph` maps from the git root regardless of where it's invoked or what directory argument is passed:
53
- - Subagents that need orientation should read `.planning/codebase/MAP.json` before walking the file tree, even when working from a subdirectory — they get the full map via the `graph-*` commands, not a scoped one.
53
+ - Orient with `.planning/codebase/GRAPH_REPORT.md` and focused `graph-*` queries before walking the tree. Pass relevant results to subagents that cannot run draht-tools. These queries use the whole-repo map even when invoked from a subdirectory.
54
54
  - It is regenerated every time `map-codebase`, `map-graph`, or `map-serve` runs, so it stays current with the code.
55
55
  - Developers can keep `draht-tools map-serve` running in a terminal — the HTML visualization updates live as files change, so architecture documentation is never stale.
@@ -13,14 +13,10 @@ Initialize a new project: questioning → research → requirements → roadmap.
13
13
 
14
14
  Description: $ARGUMENTS
15
15
 
16
- ## Atomic Reasoning
17
-
18
- Decompose the work into independently verifiable units before acting; the `atomic-reasoning` skill holds the full discipline — load it when the decomposition is not obvious.
19
-
20
16
  ## Steps
21
17
  1. Run `draht-tools init` to check preconditions
22
18
  2. If existing code detected, run `draht-tools map-codebase` first
23
- 3. Deep questioning phase (3-7 rounds — each round asks the whole frontier: every question whose prerequisites are settled, numbered, each with a recommended answer)
19
+ 3. Clarify material gaps in the problem, scope, constraints, and success criteria; use existing answers and repository evidence before asking:
24
20
  4. Run `draht-tools create-project` with gathered info
25
21
  5. Run `draht-tools create-domain-model` to define bounded contexts, entities, and ubiquitous language
26
22
  6. Create `.planning/DOMAIN.md` with:
@@ -35,31 +31,30 @@ Decompose the work into independently verifiable units before acting; the `atomi
35
31
  - `## Coverage Goals` — target coverage percentage and which paths are critical
36
32
  - `## Testing Levels` — what is tested at unit level vs integration vs e2e, with examples
37
33
  - `## Excluded` — what is explicitly not tested and why (config files, generated code, etc.)
38
- 8. Optional research phase via `draht-tools research`
34
+ 8. If research is needed before defining requirements, investigate the open questions and save findings with sources under `.planning/research/<topic>.md`
39
35
  9. Run `draht-tools create-requirements` with v1/v2/out-of-scope (map requirements to bounded contexts)
40
36
  10. Run `draht-tools create-roadmap` with phases
41
37
  11. Run `draht-tools init-state`
42
- 12. Git commit via `draht-tools commit-docs "initialize project planning"`
38
+ 12. If committing is authorized, use `draht-tools commit-docs "initialize project planning"`
43
39
 
44
40
  ## Workflow
45
- After project initialization, phases are executed one at a time in new sessions:
41
+ After project initialization, phases are executed one at a time in dependency order:
46
42
 
47
43
  ```
48
- /new-project → /new → /discuss-phase 1 → /new → /plan-phase 1 → /new → /execute-phase 1 → /new → /verify-work 1
49
- → /new → /discuss-phase 2 → /new → /plan-phase 2 → /new → /execute-phase 2 → /new → /verify-work 2
44
+ /new-project → /discuss-phase 1 → /plan-phase 1 → /execute-phase 1 → /verify-work 1
45
+ → /discuss-phase 2 → /plan-phase 2 → /execute-phase 2 → /verify-work 2
50
46
  → ... (repeat for all phases in the milestone)
51
- → /new → /next-milestone (only after ALL phases are complete)
47
+ → /next-milestone (only after ALL phases are complete)
52
48
  ```
53
49
 
54
- Each step runs in its own session (`/new` between steps). Do NOT suggest `/next-milestone` until every phase in the milestone is verified.
50
+ A fresh session between steps is optional. Do NOT suggest `/next-milestone` until every phase in the milestone is verified.
55
51
 
56
52
  ## Rules
57
- - Ask the whole frontier per round — numbered, each with a recommended answer; the user replies by number, and accepted-by-number counts as decided
53
+ - Group related questions and ask only those that change a material decision.
58
54
  - Questions that depend on still-open answers wait for a later round
59
- - Finding facts is your job, never the user's — dispatch a subagent for anything the environment can answer and keep asking the rest of the frontier while it runs
55
+ - Investigate repository facts directly; delegate independent research when useful.
60
56
  - Follow threads based on answers
61
57
  - Use examples ("Like Stripe Checkout, or custom?")
62
- - Confirm, don't assume
63
- - When the description names a solution ("an app with X"), ask what problem it solves — requirements record problems and outcomes; mechanisms stay candidates
64
- - 3-7 follow-up rounds typical
58
+ - Distinguish user decisions from reasonable implementation assumptions; clarify only blocking ambiguity
59
+ - Respect explicit requirements; clarify the intended outcome when it is unclear.
65
60
  - Stop when you have: problem, audience, MVP scope, constraints, success criteria
@@ -11,10 +11,6 @@ Plan the next milestone after ALL phases in the current one are complete.
11
11
  /next-milestone
12
12
  ```
13
13
 
14
- ## Atomic Reasoning
15
-
16
- Decompose the work into independently verifiable units before acting; the `atomic-reasoning` skill holds the full discipline — load it when the decomposition is not obvious.
17
-
18
14
  ## Prerequisites
19
15
  - `.planning/ROADMAP.md` must exist
20
16
  - ALL phases in the current milestone must be complete (verified via /verify-work)
@@ -37,17 +33,17 @@ Decompose the work into independently verifiable units before acting; the `atomi
37
33
  - Should any v2 requirements be promoted based on what we learned?
38
34
  - Are there new requirements discovered during implementation?
39
35
  4. Propose next milestone:
40
- - Define 3-5 phases, each with a clear goal (outcome, not activity)
36
+ - Define coherent phases, each with an observable goal
41
37
  - Order phases by dependency
42
38
  - Map each phase to specific requirements
43
39
  - Estimate relative complexity
44
- 5. Present the proposed milestone for user approval before writing files
45
- 6. After approval:
40
+ 5. Present the proposed milestone and resolve blocking scope decisions; use existing authorization for agreed work
41
+ 6. Record the agreed milestone (label any proposal or unresolved assumption):
46
42
  - Update `ROADMAP.md` with the new milestone and phases
47
43
  - Update `STATE.md` to reflect milestone transition
48
44
  - Update `REQUIREMENTS.md` if requirements changed
49
45
  - Update `DOMAIN.md` if domain model needs evolution
50
- - Commit: `draht-tools commit-docs "plan next milestone"`
46
+ - If committing is authorized: `draht-tools commit-docs "plan next milestone"`
51
47
 
52
48
  ## Rules
53
49
  - Always review what was actually built, not just what was planned
@@ -9,7 +9,7 @@ Run fresh-context worker iterations against a fixed goal until an independent ch
9
9
 
10
10
  Goal: $ARGUMENTS
11
11
 
12
- > **Tool note**: Use the `subagent` tool. Workers are `implementer` (or `debugger` for pure-diagnosis goals); the final gate is `spec-reviewer`. One worker per iteration — never parallel workers inside the loop.
12
+ > **Tool note**: Use the `subagent` tool. Workers are `implementer` (or `debugger` for pure-diagnosis goals); use `spec-reviewer` for acceptance criteria the check cannot establish. One worker per iteration — never parallel workers inside the loop.
13
13
 
14
14
  ## When to Loop vs Orchestrate
15
15
 
@@ -58,17 +58,17 @@ Each iteration dispatches ONE fresh worker whose prompt contains, in full (worke
58
58
  2. The last 3 entries of `PROGRESS.md` and the last 5 `git log --oneline` lines — the recoverable state
59
59
  3. The previous iteration's failure evidence, terse: the failing assertions or error lines, not full output
60
60
  4. Standing orders:
61
- - **Startup ritual** — read the progress log, run the CHECK first, observe the current failure before changing anything
61
+ - **Orient** — read the progress log and current check evidence; rerun if the evidence is missing or its inputs changed
62
62
  - **One increment** — the smallest change that moves the check toward passing; do not batch
63
- - **Commit the increment** even if the check still fails — state must survive context death
63
+ - **Preserve the increment** in the working tree and progress log; commit only when authorized
64
64
  - **Append one `PROGRESS.md` entry** — what changed / check result observed / suggested next step
65
65
  - Never edit or delete tests or the check to make it pass; never claim completion without quoting check output
66
66
 
67
67
  ## Independent Verification — the gate
68
68
 
69
- After EVERY iteration, re-run the CHECK yourself and read exit code and output. Completion is decided by this re-run, never by the worker's report — worker claims are inputs, not verdicts.
69
+ After each iteration, inspect the CHECK’s exit status, output, and input state. Reuse auditable successful evidence when the inputs are unchanged; otherwise run the CHECK. A worker’s unsupported completion claim is insufficient.
70
70
 
71
- - **Check passes** → dispatch `spec-reviewer` once over the full loop diff (contract vs everything changed since the loop started). Only a clean spec review ends the loop as DONE; concerns trigger one more targeted iteration.
71
+ - **Check passes** → compare the full diff with the contract. Use `spec-reviewer` when semantic acceptance criteria remain outside the check. Required findings trigger a targeted iteration within the existing cap.
72
72
  - **Check fails** → extract the terse failure evidence and feed it into the next iteration's prompt as guidance.
73
73
 
74
74
  ## Stall Detection
@@ -76,7 +76,7 @@ After EVERY iteration, re-run the CHECK yourself and read exit code and output.
76
76
  Stop early when the loop is running but not progressing:
77
77
 
78
78
  - Two consecutive iterations with the identical failure signature, or
79
- - An iteration that produced no commit
79
+ - An iteration that produced no relevant change or new diagnostic evidence
80
80
 
81
81
  On stall, do not dispatch the same input again — change something: decompose the goal, add context the workers were missing, switch worker (`implementer` → `debugger`), consult `advisor` for a course correction, or surface to the user with the evidence so far.
82
82
 
@@ -84,16 +84,16 @@ On stall, do not dispatch the same input again — change something: decompose t
84
84
 
85
85
  1. Parse `$ARGUMENTS` into GOAL and flags; derive the CHECK; refuse to loop without one
86
86
  2. Write `.planning/loop/LOOP.md` and `.planning/loop/PROGRESS.md`
87
- 3. Iterate: dispatch worker → re-run CHECK yourself → branch (pass → gate, fail → next iteration, stall / max / BLOCKED → hard stop)
88
- 4. On success: spec-review the full diff, then report — outcome first, check output quoted, iterations used
87
+ 3. Iterate: dispatch worker → validate current CHECK evidence → branch (pass → gate, fail → next iteration, stall / max / BLOCKED → hard stop)
88
+ 4. On success: resolve any required spec review, then report — outcome first, check output quoted, iterations used
89
89
  5. On any hard stop: append a handoff entry to `PROGRESS.md` (state observed, failure evidence, recommended next step) and report with observed / derived / assumed labels
90
90
  6. Leave `.planning/loop/` in place as the loop's record
91
91
 
92
92
  ## Rules
93
93
 
94
- - One worker, one increment, at least one commit per iteration
95
- - Loops are volume work — run workers on the executor tier and keep steering (this context, `advisor`, `spec-reviewer`) on the strongest tier
96
- - The worker never grades its own work — your re-run of the check plus a fresh-context spec review decide completion
94
+ - One worker and one verifiable increment per iteration; commits require authorization
95
+ - Choose available worker models that meet the task’s checks; change tiers only when evidence supports the tradeoff
96
+ - Completion requires current passing check evidence and any required review; an agent’s confidence is not a check
97
97
  - Never raise max iterations mid-loop without asking the user
98
- - Tests and the check are immutable inside the loop; tampering means revert and hard stop
98
+ - Tests and the check are immutable inside the loop; tampering means stop and report the affected changes; do not discard unrelated work
99
99
  - Evidence discipline applies to the loop verdict: label results observed / derived / assumed
@@ -34,7 +34,7 @@ Decompose the work into independently verifiable units before acting; the `atomi
34
34
  | Create atomic commits | `git-committer` |
35
35
  | Strategic steer at a decision point — rare, high-leverage | `advisor` |
36
36
 
37
- `spec-reviewer` and `reviewer` are distinct on purpose. Spec-reviewer ONLY checks "did the diff implement what the spec asked, no more no less". Reviewer evaluates quality. For any task with a written spec, run spec-reviewer **before** reviewer.
37
+ `spec-reviewer` and `reviewer` are distinct on purpose. Spec-reviewer ONLY checks "did the diff implement what the spec asked, no more no less". Reviewer evaluates quality. When both reviews are required, run spec-reviewer before reviewer. Select reviews for the task’s risk and acceptance criteria.
38
38
 
39
39
  ## Effort Scaling
40
40
 
@@ -43,16 +43,16 @@ Match orchestration weight to the task — over-orchestration burns tokens witho
43
43
  | Task shape | Dispatch |
44
44
  |---|---|
45
45
  | Single question or trivial fix | One agent, or handle it directly — no orchestration |
46
- | One change set to evaluate | 2–4 parallel evaluators (reviewer, security-auditor, verifier) |
46
+ | One change set to evaluate | Only the reviewers needed to resolve material risks or acceptance gaps |
47
47
  | Multi-part feature with known decomposition | Fan-out / fan-in |
48
48
  | Goal needing iteration until a measurable criterion holds | `/orchestrate-loop` |
49
49
 
50
50
  ## Model Tiering
51
51
 
52
- Bill volume tokens at the cheaper rate:
52
+ Choose available models from the current provider catalog and measure quality, latency, and cost on the workload:
53
53
 
54
- - **Orchestrator pattern** — run this command on the strongest tier (e.g. Claude Fable 5.1) and let workers execute on the executor tier (e.g. Claude Sonnet 5): planning quality where it matters, volume tokens at worker rates.
55
- - **Advisor pattern** — when the session runs on the executor tier, dispatch `advisor` sparingly: once after orientation before committing to an approach, again when stuck or before declaring a hard task done. ~1–3 consults per task; treat its guidance with serious weight.
54
+ - **Orchestrator pattern** — use a capable model for decomposition and assign bounded worker tasks to models that pass the relevant checks. Keep the same model when a cheaper or faster worker has not demonstrated acceptable results.
55
+ - **Advisor pattern** — consult `advisor` when a concrete unresolved decision benefits from another model. Provide the question and evidence; no fixed consultation count is required.
56
56
 
57
57
  ## Orchestration Modes
58
58
 
@@ -63,10 +63,10 @@ Use the `subagent` tool with `tasks: [...]` when sub-tasks don't depend on each
63
63
  Use the `subagent` tool with `chain: [...]` when later work depends on earlier output. Earlier output is interpolated via `{previous}` in the next task. Example: architect produces plan → implementer executes plan → verifier runs tests → reviewer audits the diff.
64
64
 
65
65
  ### Fan-out / Fan-in
66
- Architect decomposes into N independent plans → dispatch N implementers in parallel → collect all outputs → single verifier run → single reviewer audit. This is the standard pattern for `/execute-phase` work.
66
+ Architect decomposes independent work → dispatch implementers in parallel → collect results for verification and review. When both reviews are selected, spec review precedes quality review; `/execute-phase` keeps its explicit per-task sequence.
67
67
 
68
68
  ### Two-Stage Review (spec → quality)
69
- For any task that has a written spec, follow implementer with **spec-reviewer first, then reviewer**:
69
+ When the requested workflow needs separate spec and quality review, use this order:
70
70
 
71
71
  ```
72
72
  implementer → spec-reviewer → reviewer
@@ -81,12 +81,13 @@ When the work cannot land in one dispatch but success is provable by a determini
81
81
 
82
82
  ## Reading Subagent Status
83
83
 
84
- Every draht agent ends its response with one of four status lines. Branch on it:
84
+ Require each dispatched agent to end its response with exactly one of these status lines, then branch on it:
85
85
 
86
86
  - `STATUS: DONE` — check the evidence before proceeding: a `DONE` that quotes no verification output (test counts, command results) is treated as `DONE_WITH_CONCERNS` — re-run the decisive check yourself. Subagent claims are inputs, not verdicts.
87
87
  - `STATUS: DONE_WITH_CONCERNS` — note the concerns. If correctness-related, address before moving on; otherwise log and continue.
88
88
  - `STATUS: NEEDS_CONTEXT` — provide the missing info and re-dispatch the same agent. Do NOT skip ahead with a guess.
89
- - `STATUS: BLOCKED` — STOP. Report the blocker. Do not retry the same agent on the same input — adjust inputs (more context, decompose further, different agent) or surface to the user.
89
+ - `STATUS: BLOCKED` from a review agent (`spec-reviewer`, `reviewer`, or `security-auditor`) — send actionable required fixes to the implementer, then repeat the required reviews. Allow at most 3 implementer re-dispatches per task across review stages, or the active workflow's stricter cap. At the cap, stop and report the unresolved findings.
90
+ - `STATUS: BLOCKED` from an implementer or another non-review agent — stop and report the blocker to the user. Do not retry unchanged inputs.
90
91
 
91
92
  ## Steps
92
93
  1. Read the task description and identify sub-tasks
@@ -101,5 +102,5 @@ Every draht agent ends its response with one of four status lines. Branch on it:
101
102
  - Every dispatch is a complete brief: objective, expected output format, tool guidance, and task boundaries — subagents cannot see the main conversation
102
103
  - Do not nest delegations deeply — one level is usually enough
103
104
  - Never retry the same agent on the same input after `BLOCKED` — change something
104
- - For any spec-driven work, spec-reviewer runs before quality reviewer
105
- - The agent that produced work never evaluates it — completion verdicts come from a fresh-context evaluator plus your own re-run of the decisive check
105
+ - If both spec and quality review are required, spec-reviewer runs first
106
+ - Use a fresh reviewer for unresolved semantic risks. Reuse auditable check results for unchanged inputs; rerun when state changed or evidence cannot be verified. Required failed checks block completion.
@@ -15,4 +15,4 @@ Create a handoff document for session continuity.
15
15
  1. Run `draht-tools pause` — creates CONTINUE-HERE.md
16
16
  2. **Distill lessons before the context is lost**: for anything this session tried that failed, or an approach that worked against expectations, append one dated bullet to `.planning/STATE.md` under `## Lessons` (create the section before `## Blockers` if missing). Lessons name what to do differently — "runner hits TLS issue in PowerShell, use bash", not "had problems with tests".
17
17
  - Handoff and lesson prose follows the `unslop` skill — plain words, no filler, specifics over vibes; commands, paths, and quoted output stay verbatim.
18
- 3. Commit: `draht-tools commit-docs "pause work"`
18
+ 3. If committing is authorized: `draht-tools commit-docs "pause work"`
@@ -13,29 +13,11 @@ Create atomic execution plans for a roadmap phase, using subagents for parallel
13
13
 
14
14
  Phase: $1
15
15
 
16
- ## Red Flags — STOP
16
+ ## Planning constraints
17
17
 
18
- A plan is only as good as the tasks inside it. STOP and revise instead of saving if **any** of these is true:
18
+ Use coherent tasks with concrete files, behavior, and verification. Group dependent changes that need to land together; split unrelated outcomes. Task size follows the behavior and dependency structure, not a time limit or fixed count. Resolve uncertainty that could invalidate later work early, and state material assumptions and how to check them.
19
19
 
20
- - Any task contains placeholder text: `[TBD]`, `[files]`, `[description]`, "appropriate error handling", "similar to Task N", `...` in code positions
21
- - A task's `<test>` section names no concrete test cases (e.g., "test the function" with no inputs/outputs)
22
- - A task's `<files>` section lists no concrete file paths
23
- - A task takes more than ~5 minutes — break it down further
24
- - The plan introduces new domain terms that are NOT in `.planning/DOMAIN.md` — update DOMAIN.md first
25
- - A plan touches more than one bounded context without explicit ACL — split per context
26
- - The first plan is scaffolding/boilerplate while an unproven risk (new integration, unfamiliar API, untested pattern) sits in a later plan — reorder so the risk is proven first
27
-
28
- Run `draht-tools validate-plans $1` after saving. Fix any issues it reports before commit.
29
-
30
- ## Atomic Reasoning
31
-
32
- Decompose the work into independently verifiable units before acting; the `atomic-reasoning` skill holds the full discipline — load it when the decomposition is not obvious.
33
-
34
- **Atomicity test:** a task is atomic only if its `<verify>` can fail while every other task passes. If two tasks can only be checked together, they are one task.
35
-
36
- - **Order risk-first**: score each truth by uncertainty (has this codebase done it before?) × blast radius (how much becomes invalid if it's wrong?). The plan proving the highest-scoring truth executes first; boilerplate goes last. Boilerplate never invalidates a phase — the risky part regularly does.
37
-
38
- - Write every assumption a plan rests on as an explicit `Assumes:` line (with how to confirm it) in the plan header. Unwritten assumptions become the executor's bugs.
20
+ The `atomic-reasoning` skill can help with difficult decomposition. Respect existing domain vocabulary and architecture; do not require new DDD layers or events solely because a plan crosses directories. Validate the saved plan with `draht-tools validate-plans $1` and resolve its errors before execution.
39
21
 
40
22
  ## Steps
41
23
  1. Run `draht-tools load-phase-context $1` to gather all context
@@ -43,10 +25,10 @@ Decompose the work into independently verifiable units before acting; the `atomi
43
25
  2. Optional: `draht-tools research-phase $1` for domain research
44
26
  3. Goal-backward planning:
45
27
  a. State the goal (outcome, not activity)
46
- b. Derive observable truths (3-7 from user perspective)
28
+ b. Derive the observable outcomes required by the user
47
29
  c. From each observable truth, derive the test scenarios that would prove it (specific inputs → expected outputs or state changes)
48
30
  d. Map to required artifacts (files, endpoints, schemas)
49
- e. Break into plan groups of 2-5 tasks each
31
+ e. Group tasks according to dependencies and coherent outcomes
50
32
  4. Identify which plans are independent (no shared files, no dependency edges)
51
33
  5. **Delegate plan creation to subagents:**
52
34
  - For independent plans: use the `subagent` tool in **parallel mode** with `architect` agents, one per plan.
@@ -85,7 +67,7 @@ Decompose the work into independently verifiable units before acting; the `atomi
85
67
  The content must contain real task details (files, actions, tests) — NOT placeholder brackets. If `create-plan` is called without stdin, it writes a useless template.
86
68
 
87
69
  8. Validate: `draht-tools validate-plans $1` — if it exits non-zero, fix the offending plan before commit.
88
- 9. Commit: `draht-tools commit-docs "create phase $1 plans"`
70
+ 9. If committing is authorized: `draht-tools commit-docs "create phase $1 plans"`
89
71
  10. Show the user the execution order as a Mermaid `flowchart TD` per the `explainers` skill: one `subgraph` per wave, one node per plan, edges for the dependencies the saved plans declare. Draw it from the saved plan files, not from memory. It goes in your reply, not into the plan files.
90
72
 
91
73
  ## Plan Format
@@ -93,8 +75,8 @@ Plans use XML task format:
93
75
  ```xml
94
76
  <task type="auto">
95
77
  <n>Task name</n>
96
- <context>Bounded context this task belongs to</context>
97
- <domain>Aggregates, entities, value objects, or events touched</domain>
78
+ <context>Relevant project context or module boundary</context>
79
+ <domain>Existing domain concepts affected, if applicable</domain>
98
80
  <files>affected files</files>
99
81
  <test>
100
82
  RED phase: Write failing tests FIRST.
@@ -111,9 +93,7 @@ Plans use XML task format:
111
93
  </action>
112
94
  <refactor>
113
95
  REFACTOR phase: Improve structure while keeping tests green.
114
- - Extract value objects, push logic into domain layer
115
- - Ensure naming matches ubiquitous language
116
- - Remove duplication across bounded contexts (or make shared kernel explicit)
96
+ - Apply useful structural improvements within scope; preserve behavior
117
97
  </refactor>
118
98
  <verify>How to verify (tests pass + manual check if needed)</verify>
119
99
  <done>What "done" looks like — expressed as passing test assertions</done>
@@ -123,17 +103,15 @@ Plans use XML task format:
123
103
  Task types: `auto`, `checkpoint:human-verify`, `checkpoint:decision`
124
104
 
125
105
  ## Workflow
126
- This is one step in the per-phase cycle. Each step runs in its own session (`/new` between steps):
106
+ This is one step in the per-phase cycle. Start a fresh session when context limits make it useful:
127
107
 
128
108
  ```
129
- /discuss-phase N → /new → /plan-phase N → /new → /execute-phase N → /new → /verify-work N → /new → /discuss-phase N+1 → ...
109
+ /discuss-phase N → /plan-phase N → /execute-phase N → /verify-work N → /discuss-phase N+1 → ...
130
110
  ```
131
111
 
132
- After completing this command, tell the user to start a new session and run `/execute-phase $1`.
112
+ After completing this command, identify `/execute-phase $1` as the next step; a fresh session is optional.
133
113
  Do NOT suggest `/next-milestone` — that is only after ALL phases in the milestone are verified.
134
114
 
135
- ## Domain Rules for Plans
136
- - File/module structure should mirror bounded contexts (e.g., `src/billing/`, `src/catalog/`)
137
- - Never scatter one aggregate's logic across multiple contexts without an explicit ACL
138
- - If a plan introduces a new domain term, update `.planning/DOMAIN.md` first
139
- - Cross-context communication should use domain events, not direct imports
115
+ ## Domain context
116
+
117
+ Use established project terms and boundaries. Update an existing domain document when the plan changes the model; do not introduce DDD ceremony for unrelated work.
@@ -1,76 +1,23 @@
1
1
  ---
2
- description: "Execute a small ad-hoc task with tracking (implementer + TDD + optional spec-reviewer pass)"
2
+ description: "Complete an ad-hoc task directly with relevant verification and optional specialist help"
3
3
  ---
4
4
 
5
5
  # /quick
6
6
 
7
- Execute a small ad-hoc task with tracking.
8
-
9
- ## Usage
10
- ```
11
- /quick [description]
12
- ```
13
-
7
+ Usage: `/quick [description]`
14
8
  Task: $ARGUMENTS
15
9
 
16
- ## "Small" Is a Claim, Not a Fact
17
-
18
- Before planning, verify the task is actually quick: grep the blast radius (callers, imports, tests touching the target). If the change reaches further than the description implies, say so and recommend `/plan-phase`-level treatment instead of forcing it through. And if the description names a solution ("add a flag"), confirm the problem it solves — a smaller fix may exist. A "quick task" that silently grows is how untracked complexity enters a codebase.
19
-
20
- ## Atomic Reasoning
21
-
22
- Decompose the work into independently verifiable units before acting; the `atomic-reasoning` skill holds the full discipline — load it when the decomposition is not obvious.
23
-
24
- ## Steps
25
- 1. Run `draht-tools next-quick-number` to get task number
26
- 2. Analyze the task and write a concrete plan with actual task details (files, actions, verification). Pipe it into `draht-tools create-quick-plan`:
27
- ```
28
- echo 'plan content here' | draht-tools create-quick-plan NNN "$ARGUMENTS"
29
- ```
30
- The plan content must include: a `# Quick Task NNN: title` heading, a `## Tasks` section with one or more `<task>` XML blocks containing real file paths, real actions, and real verification steps — NOT placeholders like `[files]`.
31
-
32
- 3. **Stage 1 — Implementer.** Use the `subagent` tool in **single mode** with the `implementer` agent:
33
- ```
34
- Execute this task: $ARGUMENTS
35
-
36
- Follow the TDD cycle:
37
- - RED — Write a failing test that describes the desired behaviour
38
- - GREEN — Write the minimum implementation to make it pass
39
- - REFACTOR — Clean up while keeping the test green
40
- Exception: skip the TDD cycle only for pure config or documentation-only tasks that have no testable behaviour.
41
-
42
- Comment discipline: comments exist ONLY for constraints the code cannot express — a protocol quirk, a deliberate deviation, a non-obvious invariant. If code needs comments to be understood, rewrite the code until it doesn't. Never narrate steps, restate the diff, or leave "removed X" / "this handles Y" breadcrumbs. Comment density above the surrounding file's norm is a defect — fix it before committing. A heavily-commented solution signals the design is wrong: redesign, don't annotate.
43
-
44
- After completion, report: files changed, tests written, and verification results.
45
-
46
- End your response with `STATUS: DONE | DONE_WITH_CONCERNS | NEEDS_CONTEXT | BLOCKED` per the agent contract.
47
-
48
- Do NOT run draht, draht-tools, draht help, or pi commands — use only standard tools.
49
- ```
50
-
51
- Read the final `STATUS:` line:
52
- - `DONE` → go to Stage 2 (or skip Stage 2 for pure-config / pure-docs).
53
- - `DONE_WITH_CONCERNS` → log; if correctness, re-dispatch; otherwise continue.
54
- - `NEEDS_CONTEXT` → provide missing info and re-dispatch.
55
- - `BLOCKED` → STOP, report.
10
+ Complete the requested task directly, using an approach proportionate to its scope. Follow repository and user instructions. Ordinary work needs no numbered plan, XML, `.planning/` state, phase command, or session reset.
56
11
 
57
- 4. **Stage 2 — Spec-reviewer (skip for pure-config / pure-docs).** Use the `subagent` tool with the `spec-reviewer` agent. Prompt:
58
- ```
59
- Review the diff for quick task NNN against `.planning/quick/NNN-*-PLAN.md`. ONLY check spec compliance — does the diff implement exactly what the plan's <test>/<action>/<done> sections asked, no more, no less?
12
+ 1. Inspect the relevant code, callers, and tests; identify the observable result the user needs.
13
+ 2. Make the smallest complete change and preserve unrelated behavior. For behavior changes, add or update focused tests. Reproduce a bug before fixing it and demonstrate that the regression test detects it; skip tests for pure documentation or configuration changes with no testable behavior.
14
+ 3. Run the relevant project checks and any tests you created or changed, following repository command restrictions. A failed command, timeout, or unavailable required check is not a pass; do not weaken checks to obtain one.
15
+ 4. Report the result, changed files, and observed verification with decisive output. State what remains unverified. Do not commit unless requested.
60
16
 
61
- End with `STATUS: DONE | DONE_WITH_CONCERNS | NEEDS_CONTEXT | BLOCKED`.
62
- ```
63
- - `DONE` → go to Stage 3.
64
- - `BLOCKED` → re-dispatch implementer with Required Fixes. Repeat until `DONE`. **Hard cap: 3 re-dispatches total** — at the cap, STOP and report the disagreement to the user.
17
+ ## Optional delegation
65
18
 
66
- 5. **Stage 3 — Reviewer (optional code-quality pass).** For non-trivial quick tasks (more than one file, or domain code), use the `subagent` tool with the `reviewer` agent. Otherwise skip.
67
- - `DONE` → task complete.
68
- - `BLOCKED` → re-dispatch implementer with Must-fix list — same **hard cap of 3 re-dispatches**; at the cap, STOP and report.
19
+ Delegate when independent investigation, implementation, or fresh review materially helps. Give each agent the task, relevant context, scope, and expected evidence. Use the `implementer` agent for changes, the `spec-reviewer` agent for an explicit spec, and the `reviewer` agent for code quality; when both reviews are needed, check spec compliance first.
69
20
 
70
- 6. Write summary: `draht-tools write-quick-summary NNN`
71
- 7. Update state: `draht-tools update-state`
21
+ Require delegated reports to end with one `STATUS: DONE | DONE_WITH_CONCERNS | NEEDS_CONTEXT | BLOCKED`. Check evidence before accepting `DONE`; resolve correctness concerns before completion. Supply missing context for `NEEDS_CONTEXT`. An implementer blocker stops the task; a review blocker returns its required fixes for implementation and re-review. Allow at most **3 implementer re-dispatches total across review stages**, then report unresolved findings. Never claim completion while required checks or review findings remain unresolved.
72
22
 
73
- ## When to skip Stage 3
74
- - Pure config (tsconfig, biome, formatter)
75
- - Docs-only edits
76
- - Single-line obvious changes (typo, version bump)
23
+ Use the `subagent` tool for optional delegation. Subagents use standard tools only; the orchestrator runs any `draht`, `draht-tools`, `draht help`, or `pi` commands.
@@ -19,11 +19,7 @@ Context: $ARGUMENTS
19
19
  - `git status` reports unmerged paths — a merge, rebase, or cherry-pick is mid-flight.
20
20
  - The `subagent` tool reported a failed worktree merge-back (its failure notice points here): the agent's work sits on an unmerged `agent/<taskId>` branch. Run `git merge agent/<taskId>` first to enter the conflict, then continue here.
21
21
 
22
- ## The Iron Law
23
-
24
- > **EVERY HUNK RESOLUTION MUST BE JUSTIFIED BY THE RECOVERED INTENT OF BOTH SIDES. NO INTENT, NO RESOLUTION.**
25
-
26
- A conflict is two changes with a reason each. Until you can state both reasons, you are not resolving — you are guessing.
22
+ Resolve conflicts from both sides' intended behavior and the operation's goal. Preserve compatible changes; clarify an unresolved semantic conflict instead of choosing a side blindly.
27
23
 
28
24
  ## Phase 1 — Map the Conflict
29
25
 
@@ -53,19 +49,10 @@ Exit criterion: a one-sentence intent statement per side, per conflicted area. I
53
49
 
54
50
  ## Phase 4 — Run the Project's Checks
55
51
 
56
- Discover the project's own gates — package scripts, Makefile, CI config — and run them in order: typecheck, then tests, then lint/format. Fix what the merge broke, under the same rule: no invented behaviour.
52
+ Discover the project's own gates — package scripts, Makefile, CI config — and run the required checks for the merged state, respecting repository command restrictions. Fix what the merge broke, under the same rule: no invented behaviour.
57
53
 
58
54
  ## Phase 5 — Finish the Operation
59
55
 
60
56
  - Merge: stage the resolved files and commit. The merge commit message names each recorded trade-off — which intent won where, and why.
61
57
  - Rebase or cherry-pick: `git rebase --continue` / `git cherry-pick --continue` until every commit is replayed.
62
58
  - Never `--no-verify`.
63
-
64
- ## Red Flags — STOP
65
-
66
- Stop immediately if you catch yourself:
67
- - Resolving a hunk whose "why" you cannot state for both sides
68
- - Taking one side wholesale because it is newer, bigger, or yours
69
- - Introducing behaviour that exists on neither side
70
- - Finishing with failing checks, or reaching for `--no-verify`
71
- - Running `--abort` without explicit user sign-off
@@ -59,11 +59,11 @@ Bounded pass — report on each step:
59
59
  2. Check whether the visible symptom belongs to that code path or to a dependency below it.
60
60
  3. If the report looks like a regression: `git log --oneline -20` and recent diffs on the affected files — name candidate commits.
61
61
  4. Check whether a merged commit or open PR already addresses the same symptom.
62
- 5. Separate confirmed facts from hypotheses — label every statement observed, derived, or assumed.
62
+ 5. Separate confirmed facts from hypotheses — label the confidence of material findings as observed, derived, or assumed.
63
63
 
64
- Stop at diagnosis strength sufficient for routing — a complete root cause is /fix's job, not yours. Do not build a reproduction unless one command is already obvious from the report itself.
64
+ Stop at diagnosis strength sufficient for routing — a complete root cause is /fix's job, not yours. Do not build a reproduction unless one command is already obvious from the report itself; labeled hypotheses without a reproduction are a complete answer for this pass.
65
65
 
66
- End with STATUS: DONE | DONE_WITH_CONCERNS | NEEDS_CONTEXT | BLOCKED
66
+ End with STATUS: DONE | DONE_WITH_CONCERNS | NEEDS_CONTEXT | BLOCKED. DONE means the routing-strength diagnosis is done — no fix is expected.
67
67
  ```
68
68
 
69
69
  The pass does not need a complete root cause — it must be strong enough to avoid routing a visible symptom to the wrong component. A keyword match between the report and a module name is not a trace; a visible symptom alone is not enough when cause tracing points to a dependency below it. When the report smells like a regression and design intent matters ("was this behaviour a decision or an accident?"), a bounded `/why` consult can supplement the trace — not a full archaeology run.
@@ -146,14 +146,3 @@ End the report with exactly one marker line, the last line of the response:
146
146
  ```
147
147
 
148
148
  `bug` and `performance` carry `tracker=` only when this run matched or created a live issue. Everything else — feature request, question, feedback, reroute, unclear — closes with `[triage:other]`. Never emit two markers; never bury the marker mid-report. A follow-up `/fix` run takes the marker plus its tracker link as the issue input.
149
-
150
- ## Rationalization Table
151
-
152
- | Excuse | Reality |
153
- |---|---|
154
- | "The report names the component, route it there" | A keyword match is not a trace. Route on a confirmed code path or signature, or say the owner is unclear. |
155
- | "Probably a duplicate of #123" | Probably means possibly related: link it as uncertain and create nothing. |
156
- | "Filing a ticket is harmless" | A guessed or duplicate ticket costs a maintainer two triages. Prefer no ticket. |
157
- | "The old closed issue matches, done" | A long-closed issue is a regression lead — trace what re-broke it. |
158
- | "No repo access, but the cause is obvious" | Reading a report yields hypotheses. Classify conservatively and say the trace was unavailable. |
159
- | "I'll fix it while I'm here" | Triage ends at the verdict. Hand `[triage:bug]` to `/fix`. |