@xagent-ai/cli 1.0.1

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 (537) hide show
  1. package/.eslintrc.js +25 -0
  2. package/.gitmodules +3 -0
  3. package/.prettierrc.json +8 -0
  4. package/CONTRIBUTING.md +167 -0
  5. package/LICENSE +21 -0
  6. package/README.md +280 -0
  7. package/README_CN.md +280 -0
  8. package/dist/agents.d.ts +21 -0
  9. package/dist/agents.d.ts.map +1 -0
  10. package/dist/agents.js +463 -0
  11. package/dist/agents.js.map +1 -0
  12. package/dist/ai-client.d.ts +83 -0
  13. package/dist/ai-client.d.ts.map +1 -0
  14. package/dist/ai-client.js +1280 -0
  15. package/dist/ai-client.js.map +1 -0
  16. package/dist/auth.d.ts +25 -0
  17. package/dist/auth.d.ts.map +1 -0
  18. package/dist/auth.js +573 -0
  19. package/dist/auth.js.map +1 -0
  20. package/dist/cancellation.d.ts +46 -0
  21. package/dist/cancellation.d.ts.map +1 -0
  22. package/dist/cancellation.js +154 -0
  23. package/dist/cancellation.js.map +1 -0
  24. package/dist/checkpoint.d.ts +28 -0
  25. package/dist/checkpoint.d.ts.map +1 -0
  26. package/dist/checkpoint.js +186 -0
  27. package/dist/checkpoint.js.map +1 -0
  28. package/dist/cli.d.ts +3 -0
  29. package/dist/cli.d.ts.map +1 -0
  30. package/dist/cli.js +364 -0
  31. package/dist/cli.js.map +1 -0
  32. package/dist/config.d.ts +49 -0
  33. package/dist/config.d.ts.map +1 -0
  34. package/dist/config.js +205 -0
  35. package/dist/config.js.map +1 -0
  36. package/dist/context-compressor.d.ts +51 -0
  37. package/dist/context-compressor.d.ts.map +1 -0
  38. package/dist/context-compressor.js +231 -0
  39. package/dist/context-compressor.js.map +1 -0
  40. package/dist/conversation.d.ts +34 -0
  41. package/dist/conversation.d.ts.map +1 -0
  42. package/dist/conversation.js +221 -0
  43. package/dist/conversation.js.map +1 -0
  44. package/dist/gui-subagent/action-parser/actionParser.d.ts +19 -0
  45. package/dist/gui-subagent/action-parser/actionParser.d.ts.map +1 -0
  46. package/dist/gui-subagent/action-parser/actionParser.js +203 -0
  47. package/dist/gui-subagent/action-parser/actionParser.js.map +1 -0
  48. package/dist/gui-subagent/action-parser/constants.d.ts +8 -0
  49. package/dist/gui-subagent/action-parser/constants.d.ts.map +1 -0
  50. package/dist/gui-subagent/action-parser/constants.js +12 -0
  51. package/dist/gui-subagent/action-parser/constants.js.map +1 -0
  52. package/dist/gui-subagent/action-parser/index.d.ts +3 -0
  53. package/dist/gui-subagent/action-parser/index.d.ts.map +1 -0
  54. package/dist/gui-subagent/action-parser/index.js +6 -0
  55. package/dist/gui-subagent/action-parser/index.js.map +1 -0
  56. package/dist/gui-subagent/action-parser/types.d.ts +24 -0
  57. package/dist/gui-subagent/action-parser/types.d.ts.map +1 -0
  58. package/dist/gui-subagent/action-parser/types.js +12 -0
  59. package/dist/gui-subagent/action-parser/types.js.map +1 -0
  60. package/dist/gui-subagent/agent/gui-agent.d.ts +126 -0
  61. package/dist/gui-subagent/agent/gui-agent.d.ts.map +1 -0
  62. package/dist/gui-subagent/agent/gui-agent.js +820 -0
  63. package/dist/gui-subagent/agent/gui-agent.js.map +1 -0
  64. package/dist/gui-subagent/agent/index.d.ts +5 -0
  65. package/dist/gui-subagent/agent/index.d.ts.map +1 -0
  66. package/dist/gui-subagent/agent/index.js +5 -0
  67. package/dist/gui-subagent/agent/index.js.map +1 -0
  68. package/dist/gui-subagent/index.d.ts +43 -0
  69. package/dist/gui-subagent/index.d.ts.map +1 -0
  70. package/dist/gui-subagent/index.js +96 -0
  71. package/dist/gui-subagent/index.js.map +1 -0
  72. package/dist/gui-subagent/operator/base-operator.d.ts +108 -0
  73. package/dist/gui-subagent/operator/base-operator.d.ts.map +1 -0
  74. package/dist/gui-subagent/operator/base-operator.js +172 -0
  75. package/dist/gui-subagent/operator/base-operator.js.map +1 -0
  76. package/dist/gui-subagent/operator/browser-operator.d.ts +36 -0
  77. package/dist/gui-subagent/operator/browser-operator.d.ts.map +1 -0
  78. package/dist/gui-subagent/operator/browser-operator.js +306 -0
  79. package/dist/gui-subagent/operator/browser-operator.js.map +1 -0
  80. package/dist/gui-subagent/operator/computer-operator.d.ts +31 -0
  81. package/dist/gui-subagent/operator/computer-operator.d.ts.map +1 -0
  82. package/dist/gui-subagent/operator/computer-operator.js +441 -0
  83. package/dist/gui-subagent/operator/computer-operator.js.map +1 -0
  84. package/dist/gui-subagent/operator/desktop-operator.d.ts +55 -0
  85. package/dist/gui-subagent/operator/desktop-operator.d.ts.map +1 -0
  86. package/dist/gui-subagent/operator/desktop-operator.js +527 -0
  87. package/dist/gui-subagent/operator/desktop-operator.js.map +1 -0
  88. package/dist/gui-subagent/operator/index.d.ts +7 -0
  89. package/dist/gui-subagent/operator/index.d.ts.map +1 -0
  90. package/dist/gui-subagent/operator/index.js +6 -0
  91. package/dist/gui-subagent/operator/index.js.map +1 -0
  92. package/dist/gui-subagent/types/actions.d.ts +108 -0
  93. package/dist/gui-subagent/types/actions.d.ts.map +1 -0
  94. package/dist/gui-subagent/types/actions.js +39 -0
  95. package/dist/gui-subagent/types/actions.js.map +1 -0
  96. package/dist/gui-subagent/types/index.d.ts +6 -0
  97. package/dist/gui-subagent/types/index.d.ts.map +1 -0
  98. package/dist/gui-subagent/types/index.js +6 -0
  99. package/dist/gui-subagent/types/index.js.map +1 -0
  100. package/dist/gui-subagent/types/operator.d.ts +95 -0
  101. package/dist/gui-subagent/types/operator.d.ts.map +1 -0
  102. package/dist/gui-subagent/types/operator.js +16 -0
  103. package/dist/gui-subagent/types/operator.js.map +1 -0
  104. package/dist/gui-subagent/utils.d.ts +19 -0
  105. package/dist/gui-subagent/utils.d.ts.map +1 -0
  106. package/dist/gui-subagent/utils.js +42 -0
  107. package/dist/gui-subagent/utils.js.map +1 -0
  108. package/dist/hook.d.ts +73 -0
  109. package/dist/hook.d.ts.map +1 -0
  110. package/dist/hook.js +156 -0
  111. package/dist/hook.js.map +1 -0
  112. package/dist/index.d.ts +19 -0
  113. package/dist/index.d.ts.map +1 -0
  114. package/dist/index.js +19 -0
  115. package/dist/index.js.map +1 -0
  116. package/dist/input-history.d.ts +24 -0
  117. package/dist/input-history.d.ts.map +1 -0
  118. package/dist/input-history.js +94 -0
  119. package/dist/input-history.js.map +1 -0
  120. package/dist/input-processor.d.ts +31 -0
  121. package/dist/input-processor.d.ts.map +1 -0
  122. package/dist/input-processor.js +233 -0
  123. package/dist/input-processor.js.map +1 -0
  124. package/dist/keyboard-manager.d.ts +151 -0
  125. package/dist/keyboard-manager.d.ts.map +1 -0
  126. package/dist/keyboard-manager.js +396 -0
  127. package/dist/keyboard-manager.js.map +1 -0
  128. package/dist/logger.d.ts +75 -0
  129. package/dist/logger.d.ts.map +1 -0
  130. package/dist/logger.js +339 -0
  131. package/dist/logger.js.map +1 -0
  132. package/dist/mcp.d.ts +57 -0
  133. package/dist/mcp.d.ts.map +1 -0
  134. package/dist/mcp.js +483 -0
  135. package/dist/mcp.js.map +1 -0
  136. package/dist/memory.d.ts +25 -0
  137. package/dist/memory.d.ts.map +1 -0
  138. package/dist/memory.js +250 -0
  139. package/dist/memory.js.map +1 -0
  140. package/dist/print-system-prompt.d.ts +2 -0
  141. package/dist/print-system-prompt.d.ts.map +1 -0
  142. package/dist/print-system-prompt.js +40 -0
  143. package/dist/print-system-prompt.js.map +1 -0
  144. package/dist/session-manager.d.ts +41 -0
  145. package/dist/session-manager.d.ts.map +1 -0
  146. package/dist/session-manager.js +234 -0
  147. package/dist/session-manager.js.map +1 -0
  148. package/dist/session.d.ts +77 -0
  149. package/dist/session.d.ts.map +1 -0
  150. package/dist/session.js +1081 -0
  151. package/dist/session.js.map +1 -0
  152. package/dist/skill-invoker.d.ts +177 -0
  153. package/dist/skill-invoker.d.ts.map +1 -0
  154. package/dist/skill-invoker.js +1643 -0
  155. package/dist/skill-invoker.js.map +1 -0
  156. package/dist/skill-loader.d.ts +76 -0
  157. package/dist/skill-loader.d.ts.map +1 -0
  158. package/dist/skill-loader.js +407 -0
  159. package/dist/skill-loader.js.map +1 -0
  160. package/dist/slash-commands.d.ts +60 -0
  161. package/dist/slash-commands.d.ts.map +1 -0
  162. package/dist/slash-commands.js +1021 -0
  163. package/dist/slash-commands.js.map +1 -0
  164. package/dist/smart-approval.d.ts +137 -0
  165. package/dist/smart-approval.d.ts.map +1 -0
  166. package/dist/smart-approval.js +512 -0
  167. package/dist/smart-approval.js.map +1 -0
  168. package/dist/system-prompt-generator.d.ts +35 -0
  169. package/dist/system-prompt-generator.d.ts.map +1 -0
  170. package/dist/system-prompt-generator.js +729 -0
  171. package/dist/system-prompt-generator.js.map +1 -0
  172. package/dist/test-boundary-conditions.d.ts.map +1 -0
  173. package/dist/test-boundary-conditions.js.map +1 -0
  174. package/dist/test-cancellation-fix.d.ts.map +1 -0
  175. package/dist/test-cancellation-fix.js.map +1 -0
  176. package/dist/test-input-history.d.ts.map +1 -0
  177. package/dist/test-input-history.js.map +1 -0
  178. package/dist/test-interaction-flow.d.ts.map +1 -0
  179. package/dist/test-interaction-flow.js.map +1 -0
  180. package/dist/test-quick.d.ts.map +1 -0
  181. package/dist/test-quick.js.map +1 -0
  182. package/dist/test-user-interaction.d.ts.map +1 -0
  183. package/dist/test-user-interaction.js.map +1 -0
  184. package/dist/theme.d.ts +353 -0
  185. package/dist/theme.d.ts.map +1 -0
  186. package/dist/theme.js +383 -0
  187. package/dist/theme.js.map +1 -0
  188. package/dist/tools.d.ts +373 -0
  189. package/dist/tools.d.ts.map +1 -0
  190. package/dist/tools.js +2906 -0
  191. package/dist/tools.js.map +1 -0
  192. package/dist/types.d.ts +180 -0
  193. package/dist/types.d.ts.map +1 -0
  194. package/dist/types.js +23 -0
  195. package/dist/types.js.map +1 -0
  196. package/dist/unified-session.d.ts +42 -0
  197. package/dist/unified-session.d.ts.map +1 -0
  198. package/dist/unified-session.js +271 -0
  199. package/dist/unified-session.js.map +1 -0
  200. package/dist/update.d.ts +30 -0
  201. package/dist/update.d.ts.map +1 -0
  202. package/dist/update.js +211 -0
  203. package/dist/update.js.map +1 -0
  204. package/dist/workflow.d.ts +53 -0
  205. package/dist/workflow.d.ts.map +1 -0
  206. package/dist/workflow.js +405 -0
  207. package/dist/workflow.js.map +1 -0
  208. package/docs/architecture/mcp-integration-guide.md +131 -0
  209. package/docs/architecture/overview.md +93 -0
  210. package/docs/architecture/tool-system-design.md +89 -0
  211. package/docs/cli/commands.md +189 -0
  212. package/docs/smart-mode.md +257 -0
  213. package/docs/third-party-models.md +449 -0
  214. package/package.json +85 -0
  215. package/scripts/init-skills-path.js +58 -0
  216. package/skills/.claude-plugin/marketplace.json +45 -0
  217. package/skills/README.md +94 -0
  218. package/skills/THIRD_PARTY_NOTICES.md +405 -0
  219. package/skills/skills/algorithmic-art/LICENSE.txt +202 -0
  220. package/skills/skills/algorithmic-art/SKILL.md +405 -0
  221. package/skills/skills/algorithmic-art/templates/generator_template.js +223 -0
  222. package/skills/skills/algorithmic-art/templates/viewer.html +599 -0
  223. package/skills/skills/brand-guidelines/LICENSE.txt +202 -0
  224. package/skills/skills/brand-guidelines/SKILL.md +73 -0
  225. package/skills/skills/canvas-design/LICENSE.txt +202 -0
  226. package/skills/skills/canvas-design/SKILL.md +130 -0
  227. package/skills/skills/canvas-design/canvas-fonts/ArsenalSC-OFL.txt +93 -0
  228. package/skills/skills/canvas-design/canvas-fonts/ArsenalSC-Regular.ttf +0 -0
  229. package/skills/skills/canvas-design/canvas-fonts/BigShoulders-Bold.ttf +0 -0
  230. package/skills/skills/canvas-design/canvas-fonts/BigShoulders-OFL.txt +93 -0
  231. package/skills/skills/canvas-design/canvas-fonts/BigShoulders-Regular.ttf +0 -0
  232. package/skills/skills/canvas-design/canvas-fonts/Boldonse-OFL.txt +93 -0
  233. package/skills/skills/canvas-design/canvas-fonts/Boldonse-Regular.ttf +0 -0
  234. package/skills/skills/canvas-design/canvas-fonts/BricolageGrotesque-Bold.ttf +0 -0
  235. package/skills/skills/canvas-design/canvas-fonts/BricolageGrotesque-OFL.txt +93 -0
  236. package/skills/skills/canvas-design/canvas-fonts/BricolageGrotesque-Regular.ttf +0 -0
  237. package/skills/skills/canvas-design/canvas-fonts/CrimsonPro-Bold.ttf +0 -0
  238. package/skills/skills/canvas-design/canvas-fonts/CrimsonPro-Italic.ttf +0 -0
  239. package/skills/skills/canvas-design/canvas-fonts/CrimsonPro-OFL.txt +93 -0
  240. package/skills/skills/canvas-design/canvas-fonts/CrimsonPro-Regular.ttf +0 -0
  241. package/skills/skills/canvas-design/canvas-fonts/DMMono-OFL.txt +93 -0
  242. package/skills/skills/canvas-design/canvas-fonts/DMMono-Regular.ttf +0 -0
  243. package/skills/skills/canvas-design/canvas-fonts/EricaOne-OFL.txt +94 -0
  244. package/skills/skills/canvas-design/canvas-fonts/EricaOne-Regular.ttf +0 -0
  245. package/skills/skills/canvas-design/canvas-fonts/GeistMono-Bold.ttf +0 -0
  246. package/skills/skills/canvas-design/canvas-fonts/GeistMono-OFL.txt +93 -0
  247. package/skills/skills/canvas-design/canvas-fonts/GeistMono-Regular.ttf +0 -0
  248. package/skills/skills/canvas-design/canvas-fonts/Gloock-OFL.txt +93 -0
  249. package/skills/skills/canvas-design/canvas-fonts/Gloock-Regular.ttf +0 -0
  250. package/skills/skills/canvas-design/canvas-fonts/IBMPlexMono-Bold.ttf +0 -0
  251. package/skills/skills/canvas-design/canvas-fonts/IBMPlexMono-OFL.txt +93 -0
  252. package/skills/skills/canvas-design/canvas-fonts/IBMPlexMono-Regular.ttf +0 -0
  253. package/skills/skills/canvas-design/canvas-fonts/IBMPlexSerif-Bold.ttf +0 -0
  254. package/skills/skills/canvas-design/canvas-fonts/IBMPlexSerif-BoldItalic.ttf +0 -0
  255. package/skills/skills/canvas-design/canvas-fonts/IBMPlexSerif-Italic.ttf +0 -0
  256. package/skills/skills/canvas-design/canvas-fonts/IBMPlexSerif-Regular.ttf +0 -0
  257. package/skills/skills/canvas-design/canvas-fonts/InstrumentSans-Bold.ttf +0 -0
  258. package/skills/skills/canvas-design/canvas-fonts/InstrumentSans-BoldItalic.ttf +0 -0
  259. package/skills/skills/canvas-design/canvas-fonts/InstrumentSans-Italic.ttf +0 -0
  260. package/skills/skills/canvas-design/canvas-fonts/InstrumentSans-OFL.txt +93 -0
  261. package/skills/skills/canvas-design/canvas-fonts/InstrumentSans-Regular.ttf +0 -0
  262. package/skills/skills/canvas-design/canvas-fonts/InstrumentSerif-Italic.ttf +0 -0
  263. package/skills/skills/canvas-design/canvas-fonts/InstrumentSerif-Regular.ttf +0 -0
  264. package/skills/skills/canvas-design/canvas-fonts/Italiana-OFL.txt +93 -0
  265. package/skills/skills/canvas-design/canvas-fonts/Italiana-Regular.ttf +0 -0
  266. package/skills/skills/canvas-design/canvas-fonts/JetBrainsMono-Bold.ttf +0 -0
  267. package/skills/skills/canvas-design/canvas-fonts/JetBrainsMono-OFL.txt +93 -0
  268. package/skills/skills/canvas-design/canvas-fonts/JetBrainsMono-Regular.ttf +0 -0
  269. package/skills/skills/canvas-design/canvas-fonts/Jura-Light.ttf +0 -0
  270. package/skills/skills/canvas-design/canvas-fonts/Jura-Medium.ttf +0 -0
  271. package/skills/skills/canvas-design/canvas-fonts/Jura-OFL.txt +93 -0
  272. package/skills/skills/canvas-design/canvas-fonts/LibreBaskerville-OFL.txt +93 -0
  273. package/skills/skills/canvas-design/canvas-fonts/LibreBaskerville-Regular.ttf +0 -0
  274. package/skills/skills/canvas-design/canvas-fonts/Lora-Bold.ttf +0 -0
  275. package/skills/skills/canvas-design/canvas-fonts/Lora-BoldItalic.ttf +0 -0
  276. package/skills/skills/canvas-design/canvas-fonts/Lora-Italic.ttf +0 -0
  277. package/skills/skills/canvas-design/canvas-fonts/Lora-OFL.txt +93 -0
  278. package/skills/skills/canvas-design/canvas-fonts/Lora-Regular.ttf +0 -0
  279. package/skills/skills/canvas-design/canvas-fonts/NationalPark-Bold.ttf +0 -0
  280. package/skills/skills/canvas-design/canvas-fonts/NationalPark-OFL.txt +93 -0
  281. package/skills/skills/canvas-design/canvas-fonts/NationalPark-Regular.ttf +0 -0
  282. package/skills/skills/canvas-design/canvas-fonts/NothingYouCouldDo-OFL.txt +93 -0
  283. package/skills/skills/canvas-design/canvas-fonts/NothingYouCouldDo-Regular.ttf +0 -0
  284. package/skills/skills/canvas-design/canvas-fonts/Outfit-Bold.ttf +0 -0
  285. package/skills/skills/canvas-design/canvas-fonts/Outfit-OFL.txt +93 -0
  286. package/skills/skills/canvas-design/canvas-fonts/Outfit-Regular.ttf +0 -0
  287. package/skills/skills/canvas-design/canvas-fonts/PixelifySans-Medium.ttf +0 -0
  288. package/skills/skills/canvas-design/canvas-fonts/PixelifySans-OFL.txt +93 -0
  289. package/skills/skills/canvas-design/canvas-fonts/PoiretOne-OFL.txt +93 -0
  290. package/skills/skills/canvas-design/canvas-fonts/PoiretOne-Regular.ttf +0 -0
  291. package/skills/skills/canvas-design/canvas-fonts/RedHatMono-Bold.ttf +0 -0
  292. package/skills/skills/canvas-design/canvas-fonts/RedHatMono-OFL.txt +93 -0
  293. package/skills/skills/canvas-design/canvas-fonts/RedHatMono-Regular.ttf +0 -0
  294. package/skills/skills/canvas-design/canvas-fonts/Silkscreen-OFL.txt +93 -0
  295. package/skills/skills/canvas-design/canvas-fonts/Silkscreen-Regular.ttf +0 -0
  296. package/skills/skills/canvas-design/canvas-fonts/SmoochSans-Medium.ttf +0 -0
  297. package/skills/skills/canvas-design/canvas-fonts/SmoochSans-OFL.txt +93 -0
  298. package/skills/skills/canvas-design/canvas-fonts/Tektur-Medium.ttf +0 -0
  299. package/skills/skills/canvas-design/canvas-fonts/Tektur-OFL.txt +93 -0
  300. package/skills/skills/canvas-design/canvas-fonts/Tektur-Regular.ttf +0 -0
  301. package/skills/skills/canvas-design/canvas-fonts/WorkSans-Bold.ttf +0 -0
  302. package/skills/skills/canvas-design/canvas-fonts/WorkSans-BoldItalic.ttf +0 -0
  303. package/skills/skills/canvas-design/canvas-fonts/WorkSans-Italic.ttf +0 -0
  304. package/skills/skills/canvas-design/canvas-fonts/WorkSans-OFL.txt +93 -0
  305. package/skills/skills/canvas-design/canvas-fonts/WorkSans-Regular.ttf +0 -0
  306. package/skills/skills/canvas-design/canvas-fonts/YoungSerif-OFL.txt +93 -0
  307. package/skills/skills/canvas-design/canvas-fonts/YoungSerif-Regular.ttf +0 -0
  308. package/skills/skills/doc-coauthoring/SKILL.md +375 -0
  309. package/skills/skills/docx/LICENSE.txt +30 -0
  310. package/skills/skills/docx/SKILL.md +197 -0
  311. package/skills/skills/docx/docx-js.md +350 -0
  312. package/skills/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-chart.xsd +1499 -0
  313. package/skills/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-chartDrawing.xsd +146 -0
  314. package/skills/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-diagram.xsd +1085 -0
  315. package/skills/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-lockedCanvas.xsd +11 -0
  316. package/skills/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-main.xsd +3081 -0
  317. package/skills/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-picture.xsd +23 -0
  318. package/skills/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-spreadsheetDrawing.xsd +185 -0
  319. package/skills/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-wordprocessingDrawing.xsd +287 -0
  320. package/skills/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/pml.xsd +1676 -0
  321. package/skills/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-additionalCharacteristics.xsd +28 -0
  322. package/skills/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-bibliography.xsd +144 -0
  323. package/skills/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-commonSimpleTypes.xsd +174 -0
  324. package/skills/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-customXmlDataProperties.xsd +25 -0
  325. package/skills/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-customXmlSchemaProperties.xsd +18 -0
  326. package/skills/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd +59 -0
  327. package/skills/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd +56 -0
  328. package/skills/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesVariantTypes.xsd +195 -0
  329. package/skills/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-math.xsd +582 -0
  330. package/skills/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-relationshipReference.xsd +25 -0
  331. package/skills/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/sml.xsd +4439 -0
  332. package/skills/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/vml-main.xsd +570 -0
  333. package/skills/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/vml-officeDrawing.xsd +509 -0
  334. package/skills/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/vml-presentationDrawing.xsd +12 -0
  335. package/skills/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/vml-spreadsheetDrawing.xsd +108 -0
  336. package/skills/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/vml-wordprocessingDrawing.xsd +96 -0
  337. package/skills/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/wml.xsd +3646 -0
  338. package/skills/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/xml.xsd +116 -0
  339. package/skills/skills/docx/ooxml/schemas/ecma/fouth-edition/opc-contentTypes.xsd +42 -0
  340. package/skills/skills/docx/ooxml/schemas/ecma/fouth-edition/opc-coreProperties.xsd +50 -0
  341. package/skills/skills/docx/ooxml/schemas/ecma/fouth-edition/opc-digSig.xsd +49 -0
  342. package/skills/skills/docx/ooxml/schemas/ecma/fouth-edition/opc-relationships.xsd +33 -0
  343. package/skills/skills/docx/ooxml/schemas/mce/mc.xsd +75 -0
  344. package/skills/skills/docx/ooxml/schemas/microsoft/wml-2010.xsd +560 -0
  345. package/skills/skills/docx/ooxml/schemas/microsoft/wml-2012.xsd +67 -0
  346. package/skills/skills/docx/ooxml/schemas/microsoft/wml-2018.xsd +14 -0
  347. package/skills/skills/docx/ooxml/schemas/microsoft/wml-cex-2018.xsd +20 -0
  348. package/skills/skills/docx/ooxml/schemas/microsoft/wml-cid-2016.xsd +13 -0
  349. package/skills/skills/docx/ooxml/schemas/microsoft/wml-sdtdatahash-2020.xsd +4 -0
  350. package/skills/skills/docx/ooxml/schemas/microsoft/wml-symex-2015.xsd +8 -0
  351. package/skills/skills/docx/ooxml/scripts/pack.py +159 -0
  352. package/skills/skills/docx/ooxml/scripts/unpack.py +29 -0
  353. package/skills/skills/docx/ooxml/scripts/validate.py +69 -0
  354. package/skills/skills/docx/ooxml/scripts/validation/__init__.py +15 -0
  355. package/skills/skills/docx/ooxml/scripts/validation/base.py +951 -0
  356. package/skills/skills/docx/ooxml/scripts/validation/docx.py +274 -0
  357. package/skills/skills/docx/ooxml/scripts/validation/pptx.py +315 -0
  358. package/skills/skills/docx/ooxml/scripts/validation/redlining.py +279 -0
  359. package/skills/skills/docx/ooxml.md +610 -0
  360. package/skills/skills/docx/scripts/__init__.py +1 -0
  361. package/skills/skills/docx/scripts/document.py +1276 -0
  362. package/skills/skills/docx/scripts/templates/comments.xml +3 -0
  363. package/skills/skills/docx/scripts/templates/commentsExtended.xml +3 -0
  364. package/skills/skills/docx/scripts/templates/commentsExtensible.xml +3 -0
  365. package/skills/skills/docx/scripts/templates/commentsIds.xml +3 -0
  366. package/skills/skills/docx/scripts/templates/people.xml +3 -0
  367. package/skills/skills/docx/scripts/utilities.py +374 -0
  368. package/skills/skills/frontend-design/LICENSE.txt +177 -0
  369. package/skills/skills/frontend-design/SKILL.md +42 -0
  370. package/skills/skills/internal-comms/LICENSE.txt +202 -0
  371. package/skills/skills/internal-comms/SKILL.md +32 -0
  372. package/skills/skills/internal-comms/examples/3p-updates.md +47 -0
  373. package/skills/skills/internal-comms/examples/company-newsletter.md +65 -0
  374. package/skills/skills/internal-comms/examples/faq-answers.md +30 -0
  375. package/skills/skills/internal-comms/examples/general-comms.md +16 -0
  376. package/skills/skills/mcp-builder/LICENSE.txt +202 -0
  377. package/skills/skills/mcp-builder/SKILL.md +236 -0
  378. package/skills/skills/mcp-builder/reference/evaluation.md +602 -0
  379. package/skills/skills/mcp-builder/reference/mcp_best_practices.md +249 -0
  380. package/skills/skills/mcp-builder/reference/node_mcp_server.md +970 -0
  381. package/skills/skills/mcp-builder/reference/python_mcp_server.md +719 -0
  382. package/skills/skills/mcp-builder/scripts/connections.py +151 -0
  383. package/skills/skills/mcp-builder/scripts/evaluation.py +373 -0
  384. package/skills/skills/mcp-builder/scripts/example_evaluation.xml +22 -0
  385. package/skills/skills/mcp-builder/scripts/requirements.txt +2 -0
  386. package/skills/skills/pdf/LICENSE.txt +30 -0
  387. package/skills/skills/pdf/SKILL.md +294 -0
  388. package/skills/skills/pdf/forms.md +205 -0
  389. package/skills/skills/pdf/reference.md +612 -0
  390. package/skills/skills/pdf/scripts/check_bounding_boxes.py +70 -0
  391. package/skills/skills/pdf/scripts/check_bounding_boxes_test.py +226 -0
  392. package/skills/skills/pdf/scripts/check_fillable_fields.py +12 -0
  393. package/skills/skills/pdf/scripts/convert_pdf_to_images.py +35 -0
  394. package/skills/skills/pdf/scripts/create_validation_image.py +41 -0
  395. package/skills/skills/pdf/scripts/extract_form_field_info.py +152 -0
  396. package/skills/skills/pdf/scripts/fill_fillable_fields.py +114 -0
  397. package/skills/skills/pdf/scripts/fill_pdf_form_with_annotations.py +108 -0
  398. package/skills/skills/pptx/LICENSE.txt +30 -0
  399. package/skills/skills/pptx/SKILL.md +484 -0
  400. package/skills/skills/pptx/html2pptx.md +625 -0
  401. package/skills/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/dml-chart.xsd +1499 -0
  402. package/skills/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/dml-chartDrawing.xsd +146 -0
  403. package/skills/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/dml-diagram.xsd +1085 -0
  404. package/skills/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/dml-lockedCanvas.xsd +11 -0
  405. package/skills/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/dml-main.xsd +3081 -0
  406. package/skills/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/dml-picture.xsd +23 -0
  407. package/skills/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/dml-spreadsheetDrawing.xsd +185 -0
  408. package/skills/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/dml-wordprocessingDrawing.xsd +287 -0
  409. package/skills/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/pml.xsd +1676 -0
  410. package/skills/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/shared-additionalCharacteristics.xsd +28 -0
  411. package/skills/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/shared-bibliography.xsd +144 -0
  412. package/skills/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/shared-commonSimpleTypes.xsd +174 -0
  413. package/skills/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/shared-customXmlDataProperties.xsd +25 -0
  414. package/skills/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/shared-customXmlSchemaProperties.xsd +18 -0
  415. package/skills/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd +59 -0
  416. package/skills/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd +56 -0
  417. package/skills/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesVariantTypes.xsd +195 -0
  418. package/skills/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/shared-math.xsd +582 -0
  419. package/skills/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/shared-relationshipReference.xsd +25 -0
  420. package/skills/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/sml.xsd +4439 -0
  421. package/skills/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/vml-main.xsd +570 -0
  422. package/skills/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/vml-officeDrawing.xsd +509 -0
  423. package/skills/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/vml-presentationDrawing.xsd +12 -0
  424. package/skills/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/vml-spreadsheetDrawing.xsd +108 -0
  425. package/skills/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/vml-wordprocessingDrawing.xsd +96 -0
  426. package/skills/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/wml.xsd +3646 -0
  427. package/skills/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/xml.xsd +116 -0
  428. package/skills/skills/pptx/ooxml/schemas/ecma/fouth-edition/opc-contentTypes.xsd +42 -0
  429. package/skills/skills/pptx/ooxml/schemas/ecma/fouth-edition/opc-coreProperties.xsd +50 -0
  430. package/skills/skills/pptx/ooxml/schemas/ecma/fouth-edition/opc-digSig.xsd +49 -0
  431. package/skills/skills/pptx/ooxml/schemas/ecma/fouth-edition/opc-relationships.xsd +33 -0
  432. package/skills/skills/pptx/ooxml/schemas/mce/mc.xsd +75 -0
  433. package/skills/skills/pptx/ooxml/schemas/microsoft/wml-2010.xsd +560 -0
  434. package/skills/skills/pptx/ooxml/schemas/microsoft/wml-2012.xsd +67 -0
  435. package/skills/skills/pptx/ooxml/schemas/microsoft/wml-2018.xsd +14 -0
  436. package/skills/skills/pptx/ooxml/schemas/microsoft/wml-cex-2018.xsd +20 -0
  437. package/skills/skills/pptx/ooxml/schemas/microsoft/wml-cid-2016.xsd +13 -0
  438. package/skills/skills/pptx/ooxml/schemas/microsoft/wml-sdtdatahash-2020.xsd +4 -0
  439. package/skills/skills/pptx/ooxml/schemas/microsoft/wml-symex-2015.xsd +8 -0
  440. package/skills/skills/pptx/ooxml/scripts/pack.py +159 -0
  441. package/skills/skills/pptx/ooxml/scripts/unpack.py +29 -0
  442. package/skills/skills/pptx/ooxml/scripts/validate.py +69 -0
  443. package/skills/skills/pptx/ooxml/scripts/validation/__init__.py +15 -0
  444. package/skills/skills/pptx/ooxml/scripts/validation/base.py +951 -0
  445. package/skills/skills/pptx/ooxml/scripts/validation/docx.py +274 -0
  446. package/skills/skills/pptx/ooxml/scripts/validation/pptx.py +315 -0
  447. package/skills/skills/pptx/ooxml/scripts/validation/redlining.py +279 -0
  448. package/skills/skills/pptx/ooxml.md +427 -0
  449. package/skills/skills/pptx/scripts/html2pptx.js +979 -0
  450. package/skills/skills/pptx/scripts/inventory.py +1020 -0
  451. package/skills/skills/pptx/scripts/rearrange.py +231 -0
  452. package/skills/skills/pptx/scripts/replace.py +385 -0
  453. package/skills/skills/pptx/scripts/thumbnail.py +450 -0
  454. package/skills/skills/skill-creator/LICENSE.txt +202 -0
  455. package/skills/skills/skill-creator/SKILL.md +356 -0
  456. package/skills/skills/skill-creator/references/output-patterns.md +82 -0
  457. package/skills/skills/skill-creator/references/workflows.md +28 -0
  458. package/skills/skills/skill-creator/scripts/init_skill.py +303 -0
  459. package/skills/skills/skill-creator/scripts/package_skill.py +110 -0
  460. package/skills/skills/skill-creator/scripts/quick_validate.py +95 -0
  461. package/skills/skills/slack-gif-creator/LICENSE.txt +202 -0
  462. package/skills/skills/slack-gif-creator/SKILL.md +254 -0
  463. package/skills/skills/slack-gif-creator/core/easing.py +234 -0
  464. package/skills/skills/slack-gif-creator/core/frame_composer.py +176 -0
  465. package/skills/skills/slack-gif-creator/core/gif_builder.py +269 -0
  466. package/skills/skills/slack-gif-creator/core/validators.py +136 -0
  467. package/skills/skills/slack-gif-creator/requirements.txt +4 -0
  468. package/skills/skills/theme-factory/LICENSE.txt +202 -0
  469. package/skills/skills/theme-factory/SKILL.md +59 -0
  470. package/skills/skills/theme-factory/theme-showcase.pdf +0 -0
  471. package/skills/skills/theme-factory/themes/arctic-frost.md +19 -0
  472. package/skills/skills/theme-factory/themes/botanical-garden.md +19 -0
  473. package/skills/skills/theme-factory/themes/desert-rose.md +19 -0
  474. package/skills/skills/theme-factory/themes/forest-canopy.md +19 -0
  475. package/skills/skills/theme-factory/themes/golden-hour.md +19 -0
  476. package/skills/skills/theme-factory/themes/midnight-galaxy.md +19 -0
  477. package/skills/skills/theme-factory/themes/modern-minimalist.md +19 -0
  478. package/skills/skills/theme-factory/themes/ocean-depths.md +19 -0
  479. package/skills/skills/theme-factory/themes/sunset-boulevard.md +19 -0
  480. package/skills/skills/theme-factory/themes/tech-innovation.md +19 -0
  481. package/skills/skills/web-artifacts-builder/LICENSE.txt +202 -0
  482. package/skills/skills/web-artifacts-builder/SKILL.md +74 -0
  483. package/skills/skills/web-artifacts-builder/scripts/bundle-artifact.sh +54 -0
  484. package/skills/skills/web-artifacts-builder/scripts/init-artifact.sh +322 -0
  485. package/skills/skills/webapp-testing/LICENSE.txt +202 -0
  486. package/skills/skills/webapp-testing/SKILL.md +96 -0
  487. package/skills/skills/webapp-testing/examples/console_logging.py +35 -0
  488. package/skills/skills/webapp-testing/examples/element_discovery.py +40 -0
  489. package/skills/skills/webapp-testing/examples/static_html_automation.py +33 -0
  490. package/skills/skills/webapp-testing/scripts/with_server.py +106 -0
  491. package/skills/skills/xlsx/LICENSE.txt +30 -0
  492. package/skills/skills/xlsx/SKILL.md +289 -0
  493. package/skills/skills/xlsx/recalc.py +178 -0
  494. package/skills/spec/agent-skills-spec.md +3 -0
  495. package/skills/template/SKILL.md +6 -0
  496. package/src/agents.ts +504 -0
  497. package/src/ai-client.ts +1456 -0
  498. package/src/auth.ts +648 -0
  499. package/src/cancellation.ts +176 -0
  500. package/src/checkpoint.ts +219 -0
  501. package/src/cli.ts +384 -0
  502. package/src/config.ts +248 -0
  503. package/src/context-compressor.ts +290 -0
  504. package/src/conversation.ts +288 -0
  505. package/src/gui-subagent/action-parser/actionParser.ts +312 -0
  506. package/src/gui-subagent/action-parser/constants.ts +12 -0
  507. package/src/gui-subagent/action-parser/index.ts +6 -0
  508. package/src/gui-subagent/action-parser/types.ts +31 -0
  509. package/src/gui-subagent/agent/gui-agent.ts +982 -0
  510. package/src/gui-subagent/agent/index.ts +5 -0
  511. package/src/gui-subagent/index.ts +139 -0
  512. package/src/gui-subagent/operator/base-operator.ts +246 -0
  513. package/src/gui-subagent/operator/computer-operator.ts +520 -0
  514. package/src/gui-subagent/operator/index.ts +7 -0
  515. package/src/gui-subagent/types/actions.ts +263 -0
  516. package/src/gui-subagent/types/index.ts +6 -0
  517. package/src/gui-subagent/types/operator.ts +106 -0
  518. package/src/gui-subagent/utils.ts +51 -0
  519. package/src/index.ts +18 -0
  520. package/src/input-processor.ts +282 -0
  521. package/src/logger.ts +438 -0
  522. package/src/mcp.ts +563 -0
  523. package/src/memory.ts +303 -0
  524. package/src/session-manager.ts +308 -0
  525. package/src/session.ts +1280 -0
  526. package/src/skill-invoker.ts +1888 -0
  527. package/src/skill-loader.ts +476 -0
  528. package/src/slash-commands.ts +1150 -0
  529. package/src/smart-approval.ts +595 -0
  530. package/src/system-prompt-generator.ts +786 -0
  531. package/src/theme.ts +455 -0
  532. package/src/tools.ts +3398 -0
  533. package/src/types.ts +198 -0
  534. package/src/update.ts +270 -0
  535. package/src/workflow.ts +508 -0
  536. package/tsconfig.json +22 -0
  537. package/vitest.config.ts +19 -0
@@ -0,0 +1,5 @@
1
+ /**
2
+ * Agent Index for gui-subagent
3
+ */
4
+
5
+ export { GUIAgent, type GUIAgentConfig, type GUIAgentData, type Conversation } from './gui-agent.js';
@@ -0,0 +1,139 @@
1
+ /**
2
+ * GUI Subagent - Computer Automation for xagent
3
+ *
4
+ * A powerful automation subagent that can:
5
+ * - Control the entire desktop via computer actions (ComputerOperator)
6
+ * - Perform clicks, typing, scrolling, drag operations
7
+ * - Execute complex automation workflows
8
+ *
9
+ * Based on UI-TARS architecture
10
+ */
11
+
12
+ export * from './types/index.js';
13
+ export * from './operator/index.js';
14
+ export * from './agent/index.js';
15
+
16
+ import { ComputerOperator, type ComputerOperatorOptions } from './operator/computer-operator.js';
17
+ import { GUIAgent, type GUIAgentConfig, type GUIAgentData, type Conversation, GUIAgentStatus } from './agent/gui-agent.js';
18
+ import type { Operator } from './operator/base-operator.js';
19
+ import { getCancellationManager } from '../cancellation.js';
20
+
21
+ /**
22
+ * GUI Subagent configuration
23
+ */
24
+ export interface GUISubAgentConfig {
25
+ model?: string;
26
+ modelBaseUrl?: string;
27
+ modelApiKey?: string;
28
+ headless?: boolean;
29
+ loopIntervalInMs?: number;
30
+ maxLoopCount?: number;
31
+ showAIDebugInfo?: boolean;
32
+ }
33
+
34
+ /**
35
+ * Default configuration values (aligned with UI-TARS)
36
+ */
37
+ export const DEFAULT_GUI_CONFIG: Required<GUISubAgentConfig> = {
38
+ model: 'gpt-4o',
39
+ modelBaseUrl: '',
40
+ modelApiKey: '',
41
+ headless: false,
42
+ loopIntervalInMs: 0,
43
+ maxLoopCount: 100,
44
+ showAIDebugInfo: false,
45
+ };
46
+
47
+ /**
48
+ * Create a GUI subagent with the specified configuration
49
+ */
50
+ export async function createGUISubAgent<T extends Operator>(
51
+ config: GUISubAgentConfig = {},
52
+ operator?: T
53
+ ): Promise<GUIAgent<T>> {
54
+ const mergedConfig = { ...DEFAULT_GUI_CONFIG, ...config };
55
+
56
+ // Default to ComputerOperator for initial screenshot
57
+ // The actual operator type will be determined by LLM in run()
58
+ const agentOperator = operator ?? new ComputerOperator({
59
+ config: {
60
+ headless: mergedConfig.headless,
61
+ },
62
+ }) as unknown as T;
63
+
64
+ // Create AbortController for cancellation support
65
+ const abortController = new AbortController();
66
+
67
+ // Listen to cancellationManager for ESC key
68
+ const cancellationManager = getCancellationManager();
69
+ const cancelHandler = () => {
70
+ abortController.abort();
71
+ };
72
+ cancellationManager.on('cancelled', cancelHandler);
73
+
74
+ const agentConfig: GUIAgentConfig<T> = {
75
+ operator: agentOperator,
76
+ model: mergedConfig.model,
77
+ modelBaseUrl: mergedConfig.modelBaseUrl,
78
+ modelApiKey: mergedConfig.modelApiKey,
79
+ loopIntervalInMs: mergedConfig.loopIntervalInMs,
80
+ maxLoopCount: mergedConfig.maxLoopCount,
81
+ showAIDebugInfo: mergedConfig.showAIDebugInfo,
82
+ signal: abortController.signal,
83
+ };
84
+
85
+ const agent = new GUIAgent<T>(agentConfig);
86
+
87
+ // Store cancel handler for cleanup
88
+ (agent as any)._cancelHandler = cancelHandler;
89
+ (agent as any)._cancellationManager = cancellationManager;
90
+
91
+ await agent.initialize();
92
+
93
+ return agent;
94
+ }
95
+
96
+ /**
97
+ * Create a GUI Agent with a specific operator
98
+ */
99
+ export async function createGUIAgent<T extends Operator>(
100
+ operator: T,
101
+ config?: Partial<GUIAgentConfig<T>>
102
+ ): Promise<GUIAgent<T>> {
103
+ // Create AbortController for cancellation support if not provided
104
+ const abortController = config?.signal ? undefined : new AbortController();
105
+
106
+ // Listen to cancellationManager for ESC key if no signal provided
107
+ let cancelHandler: (() => void) | undefined;
108
+ if (!config?.signal) {
109
+ const cancellationManager = getCancellationManager();
110
+ cancelHandler = () => {
111
+ abortController?.abort();
112
+ };
113
+ cancellationManager.on('cancelled', cancelHandler);
114
+ }
115
+
116
+ const agent = new GUIAgent<T>({
117
+ operator,
118
+ ...config,
119
+ signal: config?.signal ?? abortController?.signal,
120
+ });
121
+
122
+ // Store cancel handler for cleanup
123
+ if (cancelHandler) {
124
+ const cancellationManager = getCancellationManager();
125
+ (agent as any)._cancelHandler = cancelHandler;
126
+ (agent as any)._cancellationManager = cancellationManager;
127
+ }
128
+
129
+ await agent.initialize();
130
+ return agent;
131
+ }
132
+
133
+ export { ComputerOperator, GUIAgent, GUIAgentStatus };
134
+ export type {
135
+ ComputerOperatorOptions,
136
+ GUIAgentConfig,
137
+ GUIAgentData,
138
+ Conversation,
139
+ };
@@ -0,0 +1,246 @@
1
+ /**
2
+ * Base Operator for gui-subagent
3
+ * Abstract base class for browser/desktop automation operators
4
+ * Based on UI-TARS architecture (@ui-tars/sdk/core)
5
+ *
6
+ * This implementation is aligned with @ui-tars/sdk/core.ts Operator class
7
+ */
8
+
9
+ import type {
10
+ ScreenContext,
11
+ ScreenshotOutput,
12
+ ExecuteParams,
13
+ ExecuteOutput,
14
+ } from '../types/operator.js';
15
+
16
+ /**
17
+ * Operator manual configuration for AI agents
18
+ * Aligned with @ui-tars/sdk/core.ts Operator.MANUAL
19
+ */
20
+ export interface OperatorManual {
21
+ ACTION_SPACES: string[];
22
+ KEY_SPACE?: {
23
+ [key: string]: string;
24
+ };
25
+ KEY_DESCRIPTION?: {
26
+ [key: string]: string;
27
+ };
28
+ }
29
+
30
+ /**
31
+ * Abstract base Operator class
32
+ * Provides common functionality for all operators (browser, computer, etc.)
33
+ */
34
+ export abstract class Operator {
35
+ protected _initialized = false;
36
+ protected _initializing = false;
37
+ protected _initPromise: Promise<void> | null = null;
38
+
39
+ constructor() {}
40
+
41
+ /**
42
+ * Static manual configuration for AI agents
43
+ * Override this in subclasses to provide custom action spaces
44
+ */
45
+ static get MANUAL(): OperatorManual {
46
+ return {
47
+ ACTION_SPACES: [
48
+ `click(start_box='[x1, y1, x2, y2]')`,
49
+ `left_double(start_box='[x1, y1, x2, y2]')`,
50
+ `right_single(start_box='[x1, y1, x2, y2]')`,
51
+ `drag(start_box='[x1, y1, x2, y2]', end_box='[x3, y3, x4, y4]')`,
52
+ `hotkey(key='')`,
53
+ `type(content='')`,
54
+ `scroll(start_box='[x1, y1, x2, y2]', direction='down or up or right or left')`,
55
+ `wait()`,
56
+ `finished()`,
57
+ `call_user()`,
58
+ ],
59
+ };
60
+ }
61
+
62
+ /**
63
+ * Get manual configuration from instance
64
+ */
65
+ protected get manual(): OperatorManual {
66
+ return (this.constructor as typeof Operator).MANUAL;
67
+ }
68
+
69
+ /**
70
+ * Initialize the operator
71
+ * Must be called before any other operations
72
+ */
73
+ async doInitialize(): Promise<void> {
74
+ if (this._initialized) {
75
+ return;
76
+ }
77
+
78
+ if (this._initializing && this._initPromise) {
79
+ return this._initPromise;
80
+ }
81
+
82
+ this._initializing = true;
83
+ const initPromise = (async () => {
84
+ try {
85
+ await this.initialize();
86
+ this._initialized = true;
87
+ } finally {
88
+ this._initializing = false;
89
+ }
90
+ })();
91
+
92
+ this._initPromise = initPromise;
93
+ return initPromise;
94
+ }
95
+
96
+ /**
97
+ * Internal initialize method - implement in subclass
98
+ */
99
+ protected abstract initialize(): Promise<void>;
100
+
101
+ /**
102
+ * Ensure operator is initialized
103
+ */
104
+ protected async ensureInitialized(): Promise<void> {
105
+ if (!this._initialized && !this._initializing) {
106
+ await this.doInitialize();
107
+ } else if (this._initializing && this._initPromise) {
108
+ await this._initPromise;
109
+ }
110
+ }
111
+
112
+ /**
113
+ * Get supported action types
114
+ */
115
+ abstract getSupportedActions(): string[];
116
+
117
+ /**
118
+ * Get screen context (width, height, scaleFactor)
119
+ */
120
+ async getScreenContext(): Promise<ScreenContext> {
121
+ await this.ensureInitialized();
122
+ return this.screenContext();
123
+ }
124
+
125
+ /**
126
+ * Internal screen context - implement in subclass
127
+ */
128
+ protected abstract screenContext(): ScreenContext;
129
+
130
+ /**
131
+ * Take a screenshot
132
+ * Returns base64 encoded image
133
+ */
134
+ async doScreenshot(): Promise<ScreenshotOutput> {
135
+ try {
136
+ await this.ensureInitialized();
137
+ return await this.screenshot();
138
+ } catch (error) {
139
+ return {
140
+ status: 'failed',
141
+ errorMessage: error instanceof Error ? error.message : 'Unknown error',
142
+ };
143
+ }
144
+ }
145
+
146
+ /**
147
+ * Internal screenshot method - implement in subclass
148
+ */
149
+ protected abstract screenshot(): Promise<ScreenshotOutput>;
150
+
151
+ /**
152
+ * Execute an action based on parsed prediction
153
+ * Aligned with @ui-tars/sdk/core.ts Operator.execute()
154
+ */
155
+ async doExecute(params: ExecuteParams): Promise<ExecuteOutput> {
156
+ try {
157
+ await this.ensureInitialized();
158
+ return await this.execute(params);
159
+ } catch (error) {
160
+ return {
161
+ status: 'failed',
162
+ errorMessage: error instanceof Error ? error.message : 'Unknown error',
163
+ };
164
+ }
165
+ }
166
+
167
+ /**
168
+ * Internal execute method - implement in subclass
169
+ */
170
+ protected abstract execute(params: ExecuteParams): Promise<ExecuteOutput>;
171
+
172
+ /**
173
+ * Cleanup resources
174
+ */
175
+ abstract cleanup(): Promise<void>;
176
+
177
+ /**
178
+ * Destroy operator instance
179
+ */
180
+ abstract destroyInstance(): Promise<void>;
181
+
182
+ /**
183
+ * Check if operator is initialized
184
+ */
185
+ isInitialized(): boolean {
186
+ return this._initialized;
187
+ }
188
+ }
189
+
190
+ /**
191
+ * Parse box string to screen coordinates
192
+ * Aligned with @ui-tars/sdk/core.ts parseBoxToScreenCoords()
193
+ */
194
+ export function parseBoxToScreenCoords(params: {
195
+ boxStr: string;
196
+ screenWidth: number;
197
+ screenHeight: number;
198
+ }): { x: number; y: number } {
199
+ const { boxStr, screenWidth, screenHeight } = params;
200
+
201
+ if (!boxStr) {
202
+ return { x: 0, y: 0 };
203
+ }
204
+
205
+ // Support multiple formats:
206
+ // [x1, y1, x2, y2], (x1,y1,x2,y2), "[x1, y1, x2, y2]", etc.
207
+ const numbers = boxStr
208
+ .replace(/[()[\]]/g, '')
209
+ .split(',')
210
+ .filter((n) => n.trim())
211
+ .map((n) => parseFloat(n.trim()));
212
+
213
+ if (numbers.length < 2 || numbers.some((n) => Number.isNaN(n))) {
214
+ return { x: 0, y: 0 };
215
+ }
216
+
217
+ // Calculate center of the box
218
+ const x1 = numbers[0];
219
+ const y1 = numbers[1];
220
+ const x2 = numbers.length > 2 ? numbers[2] : x1;
221
+ const y2 = numbers.length > 3 ? numbers[3] : y1;
222
+
223
+ // Normalize to screen coordinates
224
+ let normalizedX: number;
225
+ let normalizedY: number;
226
+
227
+ // Check if coordinates are normalized (0-1 range) or absolute pixels (> 1)
228
+ if (x1 >= 0 && x1 <= 1 && y1 >= 0 && y1 <= 1) {
229
+ // Already normalized coordinates (0-1 range)
230
+ normalizedX = (x1 + x2) / 2;
231
+ normalizedY = (y1 + y2) / 2;
232
+ } else if (x1 > 1 || y1 > 1) {
233
+ // Absolute pixel coordinates
234
+ normalizedX = x1 / screenWidth;
235
+ normalizedY = y1 / screenHeight;
236
+ } else {
237
+ // Fallback: treat as normalized
238
+ normalizedX = x1;
239
+ normalizedY = y1;
240
+ }
241
+
242
+ return {
243
+ x: Math.round(normalizedX * screenWidth),
244
+ y: Math.round(normalizedY * screenHeight),
245
+ };
246
+ }