@qwen-code/qwen-code 0.19.7 → 0.19.8-nightly.20260710.205430235

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 (292) hide show
  1. package/bundled/qc-helper/SKILL.md +1 -0
  2. package/bundled/qc-helper/docs/configuration/auth.md +40 -55
  3. package/bundled/qc-helper/docs/configuration/model-providers.md +224 -218
  4. package/bundled/qc-helper/docs/configuration/settings.md +43 -36
  5. package/bundled/qc-helper/docs/features/_meta.ts +1 -0
  6. package/bundled/qc-helper/docs/features/channels/overview.md +20 -12
  7. package/bundled/qc-helper/docs/features/channels/plugins.md +1 -0
  8. package/bundled/qc-helper/docs/features/code-review.md +2 -1
  9. package/bundled/qc-helper/docs/features/commands.md +39 -38
  10. package/bundled/qc-helper/docs/features/computer-use.md +77 -0
  11. package/bundled/qc-helper/docs/features/hooks.md +36 -34
  12. package/bundled/qc-helper/docs/features/memory.md +1 -1
  13. package/bundled/qc-helper/docs/features/tool-use-summaries.md +19 -23
  14. package/bundled/qc-helper/docs/qwen-serve.md +22 -12
  15. package/bundled/qc-helper/docs/reference/keyboard-shortcuts.md +1 -1
  16. package/bundled/review/DESIGN.md +14 -13
  17. package/bundled/review/SKILL.md +38 -61
  18. package/chunks/{MaxSizedBox-XY5LIO5O.js → MaxSizedBox-LOFYQFYJ.js} +13 -14
  19. package/chunks/{StandaloneSessionPicker-APISIRJZ.js → StandaloneSessionPicker-U5OQBGEB.js} +31 -29
  20. package/chunks/{acpAgent-MMOSC2YA.js → acpAgent-SDIFRIED.js} +637 -131
  21. package/chunks/{agent-TKIBLLQT.js → agent-JIBBVHNQ.js} +10 -10
  22. package/chunks/{agent-headless-VLX4C7KX.js → agent-headless-6LGZYJYU.js} +10 -10
  23. package/chunks/{anthropicContentGenerator-AKYPSZIV.js → anthropicContentGenerator-55REPTTF.js} +30 -3
  24. package/chunks/{artifact-tool-D233YJFH.js → artifact-tool-EIN46DPM.js} +1 -1
  25. package/chunks/{askUserQuestion-MKL5ZTMC.js → askUserQuestion-6YX6ZRX7.js} +1 -1
  26. package/chunks/{bridge-BCU73DZO.js → bridge-HVPFYNM4.js} +17 -16
  27. package/chunks/{ca-HCMB2I54.js → ca-MULEGDVS.js} +89 -5
  28. package/chunks/{channel-worker-supervisor-CRCVYQIE.js → channel-worker-supervisor-OPXXT4JK.js} +20 -3
  29. package/chunks/{chunk-DGHJTO2K.js → chunk-2AF26HVM.js} +31 -2
  30. package/chunks/{chunk-3B26UVCX.js → chunk-2GUVUHJY.js} +6 -4
  31. package/chunks/{chunk-FV7425LN.js → chunk-2SZOMGOR.js} +4 -1
  32. package/chunks/{chunk-CNSF3WO5.js → chunk-32KS5XSX.js} +3 -3
  33. package/chunks/{chunk-4UCTWSTP.js → chunk-34UUM3IN.js} +1 -1
  34. package/chunks/{chunk-G7ZG7CA6.js → chunk-3UP777ZS.js} +8 -7
  35. package/chunks/{chunk-MIG5SQNL.js → chunk-4CSVIZLT.js} +4 -4
  36. package/chunks/{chunk-GD236YPV.js → chunk-4ONWIT5C.js} +1 -1
  37. package/chunks/{chunk-4ZJIPVPB.js → chunk-4XK7TNBP.js} +8 -8
  38. package/chunks/{chunk-I4A4K72C.js → chunk-5F2H3PXG.js} +446 -232
  39. package/chunks/chunk-5HOF2K5U.js +19 -0
  40. package/chunks/{chunk-GMOWQOQQ.js → chunk-5ZVIYNLN.js} +228 -36
  41. package/chunks/chunk-6O6Z2I5Q.js +292 -0
  42. package/chunks/{chunk-RYFZCUJO.js → chunk-6QKT5VNZ.js} +14 -6
  43. package/chunks/{chunk-SD4N3QJ2.js → chunk-6ZPSVWLF.js} +61 -17
  44. package/chunks/{chunk-X265R5C6.js → chunk-7YGSDQ5J.js} +2 -2
  45. package/chunks/{chunk-PRDFOIZF.js → chunk-A6KEUFJO.js} +32 -5
  46. package/chunks/{chunk-OWVIH4HY.js → chunk-B5OAMPJ5.js} +389 -87
  47. package/chunks/{chunk-ME3YSROJ.js → chunk-CV2AT2WJ.js} +22 -10
  48. package/chunks/{chunk-U4FRHCLA.js → chunk-DDKUYKHA.js} +1912 -201
  49. package/chunks/{chunk-YDSYD7UI.js → chunk-E3SA2LY4.js} +2 -2
  50. package/chunks/{chunk-6IAWPIQ6.js → chunk-EDM5O3SX.js} +2 -2
  51. package/chunks/{chunk-CISB3IQF.js → chunk-FONJQQWI.js} +65 -6
  52. package/chunks/{chunk-FRFFNYUY.js → chunk-G3WIMNL4.js} +3 -3
  53. package/chunks/{chunk-B34OV7K2.js → chunk-GGQQA4JW.js} +13 -0
  54. package/chunks/chunk-GLE2YUPU.js +34 -0
  55. package/chunks/{chunk-MJI36HER.js → chunk-GOTMC3BX.js} +1 -1
  56. package/chunks/{chunk-RFIL6REB.js → chunk-GRB4QSBD.js} +168 -31
  57. package/chunks/chunk-GVVY7GSP.js +38 -0
  58. package/chunks/{chunk-7JGISHHZ.js → chunk-HDEUQRAR.js} +14 -156
  59. package/chunks/{chunk-NZEGNV4V.js → chunk-HPRI22FZ.js} +6 -6
  60. package/chunks/{chunk-STAZRKOT.js → chunk-I34IHZFJ.js} +117 -459
  61. package/chunks/{chunk-JF7DFPQ5.js → chunk-I3MBKL6Z.js} +12 -2
  62. package/chunks/{chunk-DNV4FSN5.js → chunk-I5XN6KDI.js} +21 -4
  63. package/chunks/{chunk-VZ7HY3YU.js → chunk-IAMRWMFU.js} +1 -1
  64. package/chunks/{chunk-44NROQYV.js → chunk-JOQMY62N.js} +1 -1
  65. package/chunks/{chunk-VQWAZSXN.js → chunk-JW4IKIZ2.js} +57 -35
  66. package/chunks/{chunk-SAIILPQ3.js → chunk-KJMYXFUR.js} +3 -1
  67. package/chunks/{chunk-AFOLR6YL.js → chunk-KQ6MKCFE.js} +102 -16
  68. package/chunks/{chunk-X3YGAX7V.js → chunk-KS2FRTYI.js} +2 -0
  69. package/chunks/{chunk-IUE7YWC3.js → chunk-LE7EF36E.js} +7 -7
  70. package/chunks/{chunk-B4U2M63D.js → chunk-LRY7HD3Q.js} +2101 -11
  71. package/chunks/{chunk-PUQLHSQ2.js → chunk-ME7E6WZB.js} +6 -8
  72. package/chunks/{chunk-LEIJKM7Q.js → chunk-MEK7ZRJ3.js} +1 -1
  73. package/chunks/{chunk-AJBEAUIS.js → chunk-MG2TNCRX.js} +4 -3
  74. package/chunks/{chunk-GL5TV7B5.js → chunk-MSMQURDV.js} +21 -5
  75. package/chunks/{chunk-6BN7NZ5Z.js → chunk-NXDJLKKX.js} +4 -6
  76. package/chunks/{chunk-FEJ2FZ3U.js → chunk-NY2ZOFMM.js} +1 -1
  77. package/chunks/{chunk-QZF5U5KA.js → chunk-NY5BE643.js} +8 -8
  78. package/chunks/{chunk-4RQIB5UZ.js → chunk-O2YT7VB4.js} +0 -34
  79. package/chunks/{chunk-4KJ2BPIT.js → chunk-OACJLMLD.js} +2 -38
  80. package/chunks/chunk-PCWSPWXZ.js +168 -0
  81. package/chunks/{chunk-XPJH4PKR.js → chunk-PJ74K3DH.js} +1 -1
  82. package/chunks/{chunk-FTFXDZYI.js → chunk-PW7VWRLX.js} +45 -29
  83. package/chunks/chunk-R3SLDK6Y.js +468 -0
  84. package/chunks/{chunk-4O344UEE.js → chunk-SDJOZOYY.js} +38 -18
  85. package/chunks/{chunk-ALZ75L2X.js → chunk-SMYIBRAA.js} +412 -376
  86. package/chunks/{chunk-CCGOFQV3.js → chunk-SS5P6JM6.js} +6 -5
  87. package/chunks/{chunk-AIY5UTFI.js → chunk-T3XHYGMG.js} +925 -2872
  88. package/chunks/{chunk-Q6OEPOOC.js → chunk-TB6GWNV4.js} +1 -1
  89. package/chunks/{chunk-24XYI5EI.js → chunk-TERKDCOZ.js} +3 -3
  90. package/chunks/chunk-TVO5C767.js +159 -0
  91. package/chunks/{chunk-TBAZMRW3.js → chunk-TVW53EK7.js} +1 -1
  92. package/chunks/chunk-TX5QZYK6.js +296 -0
  93. package/chunks/{chunk-JD33UY7E.js → chunk-TZRVTPJ6.js} +15 -9
  94. package/chunks/{chunk-65CFHNSE.js → chunk-UAFB2DNB.js} +59 -59
  95. package/chunks/{chunk-QAKFYMJI.js → chunk-UOXLB2LY.js} +152 -17
  96. package/chunks/chunk-V35MD7KN.js +13 -0
  97. package/chunks/{chunk-XSAFNANZ.js → chunk-VWDJHVXM.js} +12 -12
  98. package/chunks/{chunk-XISQIIT7.js → chunk-W77ZLCSX.js} +1 -1
  99. package/chunks/{chunk-BWVQN2HV.js → chunk-WTEIUA2V.js} +4 -4
  100. package/chunks/{chunk-TDGF35EN.js → chunk-XOHNA2S6.js} +1 -1
  101. package/chunks/{chunk-HJ3GX3Y3.js → chunk-XZVUZSDG.js} +25 -11
  102. package/chunks/{chunk-ADZG46HR.js → chunk-YHGCTQG3.js} +1 -1
  103. package/chunks/{chunk-2NPS2UDH.js → chunk-YUNPEB3Q.js} +478 -43
  104. package/chunks/chunk-Z3I3QJK3.js +47 -0
  105. package/chunks/{chunk-P7I3D7FM.js → chunk-Z466FBSA.js} +1 -1
  106. package/chunks/{chunk-YEGT55NW.js → chunk-ZDAZSR2O.js} +3009 -1220
  107. package/chunks/{chunk-VEB3NYSO.js → chunk-ZJQBTFJ6.js} +6 -1
  108. package/chunks/chunk-ZL5HN75Q.js +61 -0
  109. package/chunks/{computer-use-X4KUU3NM.js → computer-use-IW5XBECT.js} +10 -10
  110. package/chunks/{contextCommand-LAYJZF7H.js → contextCommand-4QPLK2SH.js} +14 -14
  111. package/chunks/create-sub-session-7JK3EYWA.js +212 -0
  112. package/chunks/create-sub-session-EVYZYAE3.js +364 -0
  113. package/chunks/{cron-create-JSXEIPVS.js → cron-create-2CCO2PW6.js} +2 -2
  114. package/chunks/{cron-delete-OIFVEPGU.js → cron-delete-ETVTP5IV.js} +2 -2
  115. package/chunks/{cron-list-D4ZX4IOE.js → cron-list-FS3KWOY5.js} +2 -2
  116. package/chunks/{daemon-F3I2RXP6.js → daemon-NNUYIBWA.js} +461 -0
  117. package/chunks/{daemon-status-provider-XSAFKVDS.js → daemon-status-provider-3EPG6BXX.js} +21 -19
  118. package/chunks/{de-PLLFDERI.js → de-QRG6J2CM.js} +89 -5
  119. package/chunks/{dist-YTRKAVUB.js → dist-3EIIFOJV.js} +1 -1
  120. package/chunks/{dist-PKFTNUHO.js → dist-7F5GWZDZ.js} +2 -1
  121. package/chunks/{dist-FQ5WRJPL.js → dist-CBJ7OJ5R.js} +2 -2
  122. package/chunks/{dist-OT7G2WNM.js → dist-LIFJ2YAI.js} +1 -1
  123. package/chunks/{dist-573HNSVO.js → dist-OKXOQ63L.js} +2 -1
  124. package/chunks/{dist-IMFFBMAT.js → dist-SU5LY5R4.js} +3 -1
  125. package/chunks/{earlyInputCapture-AERYYGXE.js → earlyInputCapture-HP5XAS7A.js} +10 -10
  126. package/chunks/{edit-WZTZDGCI.js → edit-MDICC6KH.js} +11 -11
  127. package/chunks/{en-GA2RMXY5.js → en-HF3KFWZG.js} +91 -5
  128. package/chunks/{enter-worktree-DEPXBJEL.js → enter-worktree-JWTRNEN4.js} +10 -10
  129. package/chunks/{enterPlanMode-JFGXZHHJ.js → enterPlanMode-GMRZMTBQ.js} +10 -10
  130. package/chunks/environment-2CJAFOFN.js +88 -0
  131. package/chunks/{errors-GMZL4QV7.js → errors-UZOVFD2U.js} +13 -13
  132. package/chunks/{exit-worktree-Y7XBK3VV.js → exit-worktree-QQGEG343.js} +10 -10
  133. package/chunks/{exitPlanMode-WQQER65F.js → exitPlanMode-YK2JVAAB.js} +10 -10
  134. package/chunks/{fast-path-W2U6XDNO.js → fast-path-6SD4JNQW.js} +12 -3
  135. package/chunks/{fast-path-settings-RCRXH2JG.js → fast-path-settings-RAQGCIT7.js} +3 -2
  136. package/chunks/{fr-GWNQG4XH.js → fr-RSCO6HHD.js} +89 -5
  137. package/chunks/{gemini-T4WX6SRW.js → gemini-TFQXPUZB.js} +436 -140
  138. package/chunks/{geminiContentGenerator-MKQACXEJ.js → geminiContentGenerator-LJ2BNXHX.js} +1 -1
  139. package/chunks/{glob-4KKSHZDF.js → glob-3IJ6JR5W.js} +10 -10
  140. package/chunks/{grep-GHRYXSLZ.js → grep-UFZ2RFQZ.js} +10 -10
  141. package/chunks/{handleAutoUpdate-HN7ZOSXY.js → handleAutoUpdate-TEZC5ZIR.js} +17 -13
  142. package/chunks/i18n-5QEODTJV.js +84 -0
  143. package/chunks/{initializer-SRN3IM42.js → initializer-222MPCLQ.js} +18 -16
  144. package/chunks/installationInfo-OZ62OHZ2.js +65 -0
  145. package/chunks/{ja-2HOTA47X.js → ja-RRFGG2DC.js} +89 -5
  146. package/chunks/{list-INTVXUPA.js → list-BN5VBIIE.js} +20 -18
  147. package/chunks/{loadedSettingsAdapter-QVHHQPGM.js → loadedSettingsAdapter-EHTUJRFB.js} +18 -16
  148. package/chunks/{loop-wakeup-OHWEMFP5.js → loop-wakeup-SR2KWT4B.js} +3 -3
  149. package/chunks/{ls-L654WOAT.js → ls-RUBQK5Q2.js} +2 -2
  150. package/chunks/{lsp-M35KE54Y.js → lsp-DUTVY2ZA.js} +3 -5
  151. package/chunks/{mcp-7V4T46RG.js → mcp-OPGHD26Y.js} +18 -16
  152. package/chunks/{monitor-464OY2UE.js → monitor-WXBDVYYV.js} +10 -10
  153. package/chunks/{nonInteractiveCli-LJEEODU2.js → nonInteractiveCli-CWIBGJ4U.js} +54 -49
  154. package/chunks/{notebook-edit-BLJYCNDO.js → notebook-edit-T7P7M73F.js} +11 -11
  155. package/chunks/{openaiContentGenerator-PFF6HYB2.js → openaiContentGenerator-OES264C3.js} +7 -7
  156. package/chunks/{pidfile-LIBUENIV.js → pidfile-LJ3NLS2P.js} +10 -10
  157. package/chunks/{pt-2THT3YHA.js → pt-D4CG46JM.js} +89 -5
  158. package/chunks/{qwenContentGenerator-SUUHZ6CR.js → qwenContentGenerator-QJ67LAJ5.js} +12 -12
  159. package/chunks/{read-file-L7TBQVX7.js → read-file-KZD7TLU7.js} +5 -5
  160. package/chunks/{read-mcp-resource-CNQHBSJM.js → read-mcp-resource-Q56IMYOH.js} +1 -1
  161. package/chunks/{record-artifact-PP3LKHTS.js → record-artifact-GZ5D5HZX.js} +4 -4
  162. package/chunks/{ripGrep-CKKX3GRB.js → ripGrep-KUJLX75U.js} +10 -10
  163. package/chunks/{ru-Z67YJHBG.js → ru-O2QUEL22.js} +89 -5
  164. package/chunks/{run-qwen-serve-5OKADVLE.js → run-qwen-serve-M52KVRGI.js} +664 -153
  165. package/chunks/{scheduler-ZRW3AIDU.js → scheduler-FFATTAYZ.js} +10 -10
  166. package/chunks/{send-message-OA6MV4EU.js → send-message-HAGK3VTV.js} +2 -2
  167. package/chunks/{serve-36WS32W6.js → serve-B5S32524.js} +21 -18
  168. package/chunks/{server-M372UENX.js → server-6HK5FJMR.js} +3301 -665
  169. package/chunks/{session-F5KSNP2N.js → session-3WB76VTQ.js} +55 -50
  170. package/chunks/{settings-WFLNS3WT.js → settings-W3IX7NHK.js} +27 -23
  171. package/chunks/{shell-DEDSWN56.js → shell-HZIU2ZG7.js} +10 -10
  172. package/chunks/{skill-A2TL2NPC.js → skill-34OUFB65.js} +5 -5
  173. package/chunks/{spawnChannel-RQHUWTCL.js → spawnChannel-FTZJ3I5O.js} +12 -12
  174. package/chunks/{src-XKZMNHXS.js → src-NELBIIGI.js} +48 -10
  175. package/chunks/standalone-update-LICI2VSK.js +79 -0
  176. package/chunks/{startInteractiveUI-REKSTOHU.js → startInteractiveUI-LZEV5YI2.js} +2203 -1764
  177. package/chunks/stdioHelpers-CA7MG65Z.js +14 -0
  178. package/chunks/{syntheticOutput-F7LSDCAR.js → syntheticOutput-XFFJVCGV.js} +2 -2
  179. package/chunks/{task-create-RPFZNB4B.js → task-create-VINUSVBF.js} +3 -3
  180. package/chunks/{task-list-TGGJX7EA.js → task-list-YZ2AWQEG.js} +1 -1
  181. package/chunks/{task-stop-W7NGTMYQ.js → task-stop-PEXPKUW3.js} +1 -1
  182. package/chunks/{task-update-5WUG5MVQ.js → task-update-BHIX57YH.js} +3 -3
  183. package/chunks/{team-create-TBQVWAG7.js → team-create-2JS2OYSF.js} +10 -10
  184. package/chunks/{team-delete-UHQQ2QQX.js → team-delete-2OHXSBVS.js} +1 -1
  185. package/chunks/{team-plan-approval-FZPGUSHJ.js → team-plan-approval-PHLGYUY7.js} +10 -10
  186. package/chunks/{theme-manager-DQZVNSOC.js → theme-manager-UYXLX37P.js} +10 -10
  187. package/chunks/{todoWrite-C4ZAMSR3.js → todoWrite-7Q4ELT4F.js} +1 -1
  188. package/chunks/{tool-search-FDQ3SLNJ.js → tool-search-2MWA3GWE.js} +6 -6
  189. package/chunks/total-session-admission-PRZK35X4.js +72 -0
  190. package/chunks/{trustedFolders-Z475EIHL.js → trustedFolders-IT4JBNPG.js} +12 -12
  191. package/chunks/{updateCheck-E2ZX7RL7.js → updateCheck-X3ZWDO3Z.js} +17 -13
  192. package/chunks/updateEventEmitter-NXWTRHXY.js +10 -0
  193. package/chunks/{validateNonInterActiveAuth-O4ECBHQL.js → validateNonInterActiveAuth-IAOL7CM3.js} +51 -45
  194. package/chunks/{version-CEDD6ZZR.js → version-25QF6A5H.js} +1 -1
  195. package/chunks/{web-fetch-UYGMOHW4.js → web-fetch-I7FOWHGA.js} +2 -2
  196. package/chunks/{workflow-CQQ4J4I6.js → workflow-LZZ5U3IT.js} +11 -11
  197. package/chunks/{workspace-providers-status-MVYXMYDG.js → workspace-providers-status-7DTOAWEL.js} +21 -18
  198. package/chunks/workspace-registry-BBIPESIZ.js +76 -0
  199. package/chunks/{workspace-service-OMBR6ZLG.js → workspace-service-SY3P3FUY.js} +25 -23
  200. package/chunks/{workspace-skills-status-IMMQ7CAY.js → workspace-skills-status-GTT2A4WN.js} +20 -18
  201. package/chunks/{write-file-VWGY7AJP.js → write-file-M6IHNW3V.js} +11 -11
  202. package/chunks/{zh-7XVVRTDH.js → zh-K2EH6BDD.js} +91 -5
  203. package/chunks/{zh-TW-DPH554OG.js → zh-TW-4GPXJ7ZY.js} +91 -5
  204. package/cli.js +13 -12
  205. package/locales/ca.js +115 -7
  206. package/locales/de.js +114 -7
  207. package/locales/en.js +118 -7
  208. package/locales/fr.js +115 -7
  209. package/locales/ja.js +116 -6
  210. package/locales/pt.js +114 -7
  211. package/locales/ru.js +114 -7
  212. package/locales/zh-TW.js +114 -6
  213. package/locales/zh.js +114 -6
  214. package/package.json +3 -6
  215. package/web-shell/assets/{arc-C7hjaa7g.js → arc-G3HZaqaL.js} +1 -1
  216. package/web-shell/assets/{architectureDiagram-3BPJPVTR-pm9KtMZY.js → architectureDiagram-3BPJPVTR-DhBrwwch.js} +1 -1
  217. package/web-shell/assets/{blockDiagram-GPEHLZMM-CApElKsU.js → blockDiagram-GPEHLZMM-16JbbF0N.js} +1 -1
  218. package/web-shell/assets/{c4Diagram-AAUBKEIU-BeDe0-9N.js → c4Diagram-AAUBKEIU-DQ3-pKgc.js} +1 -1
  219. package/web-shell/assets/channel-CX7ZHuuL.js +1 -0
  220. package/web-shell/assets/{chunk-2J33WTMH-DJEkmLdl.js → chunk-2J33WTMH-ERCn30sp.js} +1 -1
  221. package/web-shell/assets/{chunk-4BX2VUAB-DXX8gdpe.js → chunk-4BX2VUAB-DTysfbFi.js} +1 -1
  222. package/web-shell/assets/{chunk-55IACEB6-DORmk1kQ.js → chunk-55IACEB6-BFGrbTBi.js} +1 -1
  223. package/web-shell/assets/{chunk-727SXJPM-DWmO4mCZ.js → chunk-727SXJPM-DCX4Oar-.js} +1 -1
  224. package/web-shell/assets/{chunk-AQP2D5EJ-C7LRaYw2.js → chunk-AQP2D5EJ-CgT6sBr3.js} +1 -1
  225. package/web-shell/assets/{chunk-FMBD7UC4-CCdXgyC5.js → chunk-FMBD7UC4-C1Uuk1KV.js} +1 -1
  226. package/web-shell/assets/{chunk-ND2GUHAM-SyL_xvWc.js → chunk-ND2GUHAM-DajgESiu.js} +1 -1
  227. package/web-shell/assets/{chunk-QZHKN3VN-BzOuCKxa.js → chunk-QZHKN3VN-DLJSvy9X.js} +1 -1
  228. package/web-shell/assets/classDiagram-4FO5ZUOK-B-oT3UI8.js +1 -0
  229. package/web-shell/assets/classDiagram-v2-Q7XG4LA2-B-oT3UI8.js +1 -0
  230. package/web-shell/assets/{cose-bilkent-S5V4N54A-BMPWyDKc.js → cose-bilkent-S5V4N54A-CH3w3qs7.js} +1 -1
  231. package/web-shell/assets/{dagre-BM42HDAG-B_GnPWik.js → dagre-BM42HDAG-BloXan9B.js} +1 -1
  232. package/web-shell/assets/{diagram-2AECGRRQ-fJqMc3S_.js → diagram-2AECGRRQ-BbZiGcmK.js} +1 -1
  233. package/web-shell/assets/{diagram-5GNKFQAL-ximV3O9D.js → diagram-5GNKFQAL-GQlYvLJv.js} +1 -1
  234. package/web-shell/assets/{diagram-KO2AKTUF-2vVyjzqw.js → diagram-KO2AKTUF-CtIBvVq3.js} +1 -1
  235. package/web-shell/assets/{diagram-LMA3HP47-Dckcx1sT.js → diagram-LMA3HP47-D5TBo9a2.js} +1 -1
  236. package/web-shell/assets/{diagram-OG6HWLK6-BAVv47ga.js → diagram-OG6HWLK6-N0gQhw6R.js} +1 -1
  237. package/web-shell/assets/{erDiagram-TEJ5UH35-Bn3nf5J0.js → erDiagram-TEJ5UH35-zab9vDj3.js} +1 -1
  238. package/web-shell/assets/{flowDiagram-I6XJVG4X-BIbGF9JT.js → flowDiagram-I6XJVG4X-BnnjtWJa.js} +1 -1
  239. package/web-shell/assets/{ganttDiagram-6RSMTGT7-CDbhb3AH.js → ganttDiagram-6RSMTGT7-2T0SQU4f.js} +1 -1
  240. package/web-shell/assets/{gitGraphDiagram-PVQCEYII-CbKG1a_w.js → gitGraphDiagram-PVQCEYII-DAD6_que.js} +1 -1
  241. package/web-shell/assets/index-XLkWfLja.css +5 -0
  242. package/web-shell/assets/index-srlTR1Jg.js +786 -0
  243. package/web-shell/assets/{infoDiagram-5YYISTIA-DUFxTy8m.js → infoDiagram-5YYISTIA-C-j8d0xO.js} +1 -1
  244. package/web-shell/assets/{ishikawaDiagram-YF4QCWOH-D69hrBG8.js → ishikawaDiagram-YF4QCWOH-D97bAKoT.js} +1 -1
  245. package/web-shell/assets/{journeyDiagram-JHISSGLW-DsvEw51Y.js → journeyDiagram-JHISSGLW-BJAHfJmm.js} +1 -1
  246. package/web-shell/assets/{kanban-definition-UN3LZRKU-lFFjZEYd.js → kanban-definition-UN3LZRKU-CZgR5aac.js} +1 -1
  247. package/web-shell/assets/{linear-Bo5bWzvo.js → linear-DOd4kYhA.js} +1 -1
  248. package/web-shell/assets/{mermaid.core-C_HKMJx5.js → mermaid.core-BBaplnXA.js} +5 -5
  249. package/web-shell/assets/{mindmap-definition-RKZ34NQL-DlV-NUTs.js → mindmap-definition-RKZ34NQL-IhBF_BR5.js} +1 -1
  250. package/web-shell/assets/{pieDiagram-4H26LBE5-B2e6FH2a.js → pieDiagram-4H26LBE5-B4R4sYyH.js} +1 -1
  251. package/web-shell/assets/{quadrantDiagram-W4KKPZXB-D75kSk-b.js → quadrantDiagram-W4KKPZXB-DKd1SJ61.js} +1 -1
  252. package/web-shell/assets/{requirementDiagram-4Y6WPE33-CQ6xakhM.js → requirementDiagram-4Y6WPE33-Cw96V0Xb.js} +1 -1
  253. package/web-shell/assets/{sankeyDiagram-5OEKKPKP-J_XTKrcY.js → sankeyDiagram-5OEKKPKP-C6ne_yWi.js} +1 -1
  254. package/web-shell/assets/{sequenceDiagram-3UESZ5HK-D7jTcBtf.js → sequenceDiagram-3UESZ5HK-CCyp4PDp.js} +1 -1
  255. package/web-shell/assets/{stateDiagram-AJRCARHV-CrlM_OT3.js → stateDiagram-AJRCARHV-DHvIqTmx.js} +1 -1
  256. package/web-shell/assets/stateDiagram-v2-BHNVJYJU-DvFhmpwA.js +1 -0
  257. package/web-shell/assets/{timeline-definition-PNZ67QCA-5oZi76Ef.js → timeline-definition-PNZ67QCA-amb3n9zH.js} +1 -1
  258. package/web-shell/assets/{vennDiagram-CIIHVFJN-DO5YptPK.js → vennDiagram-CIIHVFJN-Abf2qRFJ.js} +1 -1
  259. package/web-shell/assets/{wardley-L42UT6IY-4t1eJDvM.js → wardley-L42UT6IY-BBlOp1av.js} +1 -1
  260. package/web-shell/assets/{wardleyDiagram-YWT4CUSO-DKZc661S.js → wardleyDiagram-YWT4CUSO-gE_sZ0Ak.js} +1 -1
  261. package/web-shell/assets/{xychartDiagram-2RQKCTM6-su9hp08G.js → xychartDiagram-2RQKCTM6-BwOni53i.js} +1 -1
  262. package/web-shell/index.html +16 -4
  263. package/chunks/chunk-6SHO7WFF.js +0 -79
  264. package/chunks/chunk-IFEWJXFS.js +0 -37
  265. package/node_modules/@qwen-code/audio-capture/dist/index.d.ts +0 -35
  266. package/node_modules/@qwen-code/audio-capture/dist/index.js +0 -48
  267. package/node_modules/@qwen-code/audio-capture/dist/index.js.map +0 -1
  268. package/node_modules/@qwen-code/audio-capture/dist/platform.d.ts +0 -7
  269. package/node_modules/@qwen-code/audio-capture/dist/platform.js +0 -18
  270. package/node_modules/@qwen-code/audio-capture/dist/platform.js.map +0 -1
  271. package/node_modules/@qwen-code/audio-capture/node_modules/node-gyp-build/LICENSE +0 -21
  272. package/node_modules/@qwen-code/audio-capture/node_modules/node-gyp-build/README.md +0 -58
  273. package/node_modules/@qwen-code/audio-capture/node_modules/node-gyp-build/SECURITY.md +0 -5
  274. package/node_modules/@qwen-code/audio-capture/node_modules/node-gyp-build/bin.js +0 -84
  275. package/node_modules/@qwen-code/audio-capture/node_modules/node-gyp-build/build-test.js +0 -19
  276. package/node_modules/@qwen-code/audio-capture/node_modules/node-gyp-build/index.js +0 -6
  277. package/node_modules/@qwen-code/audio-capture/node_modules/node-gyp-build/node-gyp-build.js +0 -207
  278. package/node_modules/@qwen-code/audio-capture/node_modules/node-gyp-build/optional.js +0 -7
  279. package/node_modules/@qwen-code/audio-capture/node_modules/node-gyp-build/package.json +0 -43
  280. package/node_modules/@qwen-code/audio-capture/package.json +0 -30
  281. package/node_modules/@qwen-code/audio-capture/prebuilds/darwin-arm64/@qwen-code+audio-capture.node +0 -0
  282. package/node_modules/@qwen-code/audio-capture/prebuilds/darwin-x64/@qwen-code+audio-capture.node +0 -0
  283. package/node_modules/@qwen-code/audio-capture/prebuilds/linux-arm64/@qwen-code+audio-capture.node +0 -0
  284. package/node_modules/@qwen-code/audio-capture/prebuilds/linux-x64/@qwen-code+audio-capture.node +0 -0
  285. package/node_modules/@qwen-code/audio-capture/prebuilds/win32-x64/@qwen-code+audio-capture.node +0 -0
  286. package/web-shell/assets/channel-BNf1dW-j.js +0 -1
  287. package/web-shell/assets/classDiagram-4FO5ZUOK-uOIGlzgi.js +0 -1
  288. package/web-shell/assets/classDiagram-v2-Q7XG4LA2-uOIGlzgi.js +0 -1
  289. package/web-shell/assets/index-CnE2ur2L.js +0 -779
  290. package/web-shell/assets/index-hSKXrlSE.css +0 -5
  291. package/web-shell/assets/stateDiagram-v2-BHNVJYJU-Bs4TK_84.js +0 -1
  292. /package/chunks/{chunk-Y6Z2O3WR.js → chunk-JM7BYJO5.js} +0 -0
package/bundled/qc-helper/docs/configuration/settings.md CHANGED
@@ -77,28 +77,28 @@ Settings are organized into categories. Most settings should be placed within th
77
77
 
78
78
  #### general
79
79
 
80
- | Setting | Type | Description | Default |
81
- | ------------------------------------------ | ------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------- |
82
- | `general.preferredEditor` | string | The preferred editor to open files in. | `undefined` |
83
- | `general.vimMode` | boolean | Enable Vim keybindings. | `false` |
84
- | `general.enableAutoUpdate` | boolean | Enable automatic update checks and installations on startup. | `true` |
85
- | `general.showSessionRecap` | boolean | Auto-show a one-line "where you left off" recap when returning to the terminal after being away. Off by default. Use `/recap` to trigger manually regardless of this setting. | `false` |
86
- | `general.sessionRecapAwayThresholdMinutes` | number | Minutes the terminal must be blurred before an auto-recap fires on focus-in. Only used when `showSessionRecap` is enabled. | `5` |
87
- | `general.gitCoAuthor.commit` | boolean | Add a Co-authored-by trailer to git commit messages AND attach a per-file AI-attribution git note (`refs/notes/ai-attribution`) for commits made through Qwen Code. Disabling skips both. | `true` |
88
- | `general.gitCoAuthor.pr` | boolean | Append a Qwen Code attribution line to pull request descriptions when running `gh pr create`. | `true` |
89
- | `general.defaultFileEncoding` | enum | Default encoding for new files. Use `"utf-8"` (default) for UTF-8 without BOM, or `"utf-8-bom"` for UTF-8 with BOM. Only change this if your project specifically requires BOM. | `"utf-8"` |
90
- | `general.voice.enabled` | boolean | Enable voice dictation in the prompt input. Also togglable with the `/voice` command. Requires a transcription model (`voiceModel`) to be configured. | `false` |
91
- | `general.voice.mode` | enum | How push-to-talk behaves: `"hold"` to talk while the key is held, or `"tap"` to start and tap (or pause) to stop and submit. | `"hold"` |
92
- | `general.voice.language` | string | Preferred spoken language for voice transcription (e.g. `"english"`, `"chinese"`). Leave empty to auto-detect. | `""` |
80
+ | Setting | Type | Description | Default |
81
+ | ------------------------------------------ | ------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------- |
82
+ | `general.preferredEditor` | string | The preferred editor to open files in. | `undefined` |
83
+ | `general.vimMode` | boolean | Enable Vim keybindings. | `false` |
84
+ | `general.enableAutoUpdate` | boolean | Enable automatic update checks and installations on startup. | `true` |
85
+ | `general.showSessionRecap` | boolean | Auto-show a one-line "where you left off" recap when returning to the terminal after being away. Off by default. Use `/recap` to trigger manually regardless of this setting. | `false` |
86
+ | `general.sessionRecapAwayThresholdMinutes` | number | Minutes the terminal must be blurred before an auto-recap fires on focus-in. Only used when `showSessionRecap` is enabled. | `5` |
87
+ | `general.gitCoAuthor.commit` | boolean | Add a Co-authored-by trailer to git commit messages AND attach a per-file AI-attribution git note (`refs/notes/ai-attribution`) for commits made through Qwen Code. Disabling skips both. | `true` |
88
+ | `general.gitCoAuthor.pr` | boolean | Append a Qwen Code attribution line to pull request descriptions when running `gh pr create`. | `true` |
89
+ | `general.defaultFileEncoding` | enum | Default encoding for new files. Use `"utf-8"` (default) for UTF-8 without BOM, or `"utf-8-bom"` for UTF-8 with BOM. Only change this if your project specifically requires BOM. | `"utf-8"` |
90
+ | `general.voice.enabled` | boolean | Enable voice dictation in the prompt input. Also togglable with the `/voice` command. Requires a transcription model (`voiceModel`) to be configured. | `false` |
91
+ | `general.voice.mode` | enum | How push-to-talk behaves: `"hold"` to talk while the key is held, or `"tap"` to start and tap (or pause) to stop and submit. | `"hold"` |
92
+ | `general.voice.language` | string | Preferred spoken language for voice transcription (e.g. `"english"`, `"chinese"`). Leave empty to auto-detect. | `""` |
93
93
  | `general.voice.keytermsFile` | string | Path to a custom keyterms file (one term per line, `#` for comments) that biases voice transcription toward domain-specific terms. Relative paths resolve from the workspace root; defaults to `.qwen/voice-keyterms.txt` when present. Read only in trusted workspaces. Only applies to Qwen ASR models (`qwen3-asr-*`). | `""` |
94
- | `general.voice.refineTranscript` | boolean | Clean up voice transcripts with the fast model before inserting them — removes filler words and fixes recognition errors while preserving meaning. Falls back to the raw transcript on failure, and is skipped when no fast model is configured. | `true` |
95
- | `general.cleanupPeriodDays` | number | Days to retain `~/.qwen/file-history/` session backups used by `/rewind`. Backups older than this are removed by a background pass that runs at most once per day. `0` = minimum retention (~1 hour): keeps sessions touched in the last hour plus the currently active one. Changes take effect after restart. | `30` |
96
- | `general.language` | enum | Language for the user interface. Use `"auto"` to detect from system settings, or a language code (e.g. `"zh-CN"`, `"fr"`). Custom codes can be added by placing JS locale files in `~/.qwen/locales/`. See [i18n](../features/language). Requires restart. | `"auto"` |
97
- | `general.outputLanguage` | string | Language for model output. Use `"auto"` to detect from system settings, or set a specific language. Requires restart. | `"auto"` |
98
- | `general.dynamicCommandTranslation` | boolean | Enable AI translation of dynamic slash-command descriptions. When disabled, dynamic commands keep their original descriptions and skip translation model calls. | `false` |
99
- | `general.terminalBell` | boolean | Play a terminal bell sound when a response completes or needs approval. | `true` |
100
- | `general.preventSystemSleep` | boolean | Prevent the system from sleeping while Qwen Code is streaming a model response or executing tools. Idle prompt time and permission prompts do not inhibit sleep. Read once at startup, so changes take effect after restart. | `true` |
101
- | `general.chatRecording` | boolean | Save chat history to disk. Disabling this also prevents `--continue` and `--resume` from working. Requires restart. | `true` |
94
+ | `general.voice.refineTranscript` | boolean | Clean up voice transcripts with the fast model before inserting them — removes filler words and fixes recognition errors while preserving meaning. Falls back to the raw transcript on failure, and is skipped when no fast model is configured. | `true` |
95
+ | `general.cleanupPeriodDays` | number | Days to retain `~/.qwen/file-history/` session backups used by `/rewind`. Backups older than this are removed by a background pass that runs at most once per day. `0` = minimum retention (~1 hour): keeps sessions touched in the last hour plus the currently active one. Changes take effect after restart. | `30` |
96
+ | `general.language` | enum | Language for the user interface. Use `"auto"` to detect from system settings, or a language code (e.g. `"zh-CN"`, `"fr"`). Custom codes can be added by placing JS locale files in `~/.qwen/locales/`. See [i18n](../features/language). Requires restart. | `"auto"` |
97
+ | `general.outputLanguage` | string | Language for model output. Use `"auto"` to detect from system settings, or set a specific language. Requires restart. | `"auto"` |
98
+ | `general.dynamicCommandTranslation` | boolean | Enable AI translation of dynamic slash-command descriptions. When disabled, dynamic commands keep their original descriptions and skip translation model calls. | `false` |
99
+ | `general.terminalBell` | boolean | Play a terminal bell sound when a response completes or needs approval. | `true` |
100
+ | `general.preventSystemSleep` | boolean | Prevent the system from sleeping while Qwen Code is streaming a model response or executing tools. Idle prompt time and permission prompts do not inhibit sleep. Read once at startup, so changes take effect after restart. | `true` |
101
+ | `general.chatRecording` | boolean | Save chat history to disk. Disabling this also prevents `--continue` and `--resume` from working. Requires restart. | `true` |
102
102
 
103
103
  #### output
104
104
 
@@ -125,7 +125,7 @@ Settings are organized into categories. Most settings should be placed within th
125
125
  | `ui.showCitations` | boolean | Show citations for generated text in the chat. | `false` |
126
126
  | `ui.history.collapseOnResume` | boolean | Whether to collapse history by default when resuming a session. Can be toggled via `/history collapse-on-resume` and `/history expand-on-resume`. | `false` |
127
127
  | `ui.history.collapsePreviewCount` | number | Number of most recent user turns to keep visible when `ui.history.collapseOnResume` is enabled. `0` collapses all restored history by default; `-1` shows all restored history. | `0` |
128
- | `ui.compactMode` | boolean | Hide tool output and thinking for a cleaner view. Toggle with `Ctrl+O` during a session or via the Settings dialog. Tool approval prompts are never hidden, even in compact mode. The setting persists across sessions. | `false` |
128
+ | `ui.compactMode` | boolean | Retired in the terminal UI. The CLI now always shows the compact, type-based tool view in the main transcript; press `Ctrl+O` to open the full-detail transcript instead of toggling a mode. Still honored by the web shell. | `false` |
129
129
  | `ui.shellOutputMaxLines` | number | Max number of shell output lines shown inline. Set to `0` to disable the cap and show full output. Hidden lines are surfaced via the `+N lines` indicator. Errors, `!`-prefix user-initiated commands, confirming tools, and focused embedded shells always show full output. | `5` |
130
130
  | `ui.enableWelcomeBack` | boolean | Show welcome back dialog when returning to a project with conversation history. When enabled, Qwen Code will automatically detect if you're returning to a project with a previously generated project summary (`.qwen/PROJECT_SUMMARY.md`) and show a dialog allowing you to continue your previous conversation or start fresh. If you choose **Start new chat session**, that choice is remembered for the current project until the project summary changes. This feature integrates with the `/summary` command and quit confirmation dialog. | `true` |
131
131
  | `ui.accessibility.enableLoadingPhrases` | boolean | Enable loading phrases (disable for accessibility). | `true` |
@@ -172,7 +172,7 @@ Settings are organized into categories. Most settings should be placed within th
172
172
  | `model.chatCompression.maxRecentFilesToRetain` | number | Number of most-recently-touched files whose current content is restored (embedded if small, otherwise referenced by path) into history after auto-compaction. `0` restores none. Env override: `QWEN_COMPACT_MAX_RECENT_FILES`. | `5` |
173
173
  | `model.chatCompression.maxRecentImagesToRetain` | number | Number of most-recent images (tool screenshots / user pastes) restored into history after auto-compaction. `0` restores none. Env override: `QWEN_COMPACT_MAX_RECENT_IMAGES`. | `3` |
174
174
  | `model.chatCompression.enableScreenshotTrigger` | boolean | When `true`, auto-compaction also fires once the number of tool-returned images accumulated in history reaches `screenshotTriggerThreshold`, independent of token usage — aimed at computer-use sessions where frequent screenshots dilute model attention. Counts only images returned inside tool results, not user-pasted images. Env override: `QWEN_COMPACT_SCREENSHOT_TRIGGER` (`1`/`true`/`0`/`false`). | `true` |
175
- | `model.chatCompression.screenshotTriggerThreshold` | number | Tool-returned image count at or above which the screenshot trigger fires (only when `enableScreenshotTrigger`). Compaction resets the count — surviving images are re-embedded as top-level parts, which the trigger doesn't count — so it won't immediately re-fire. Env override: `QWEN_COMPACT_SCREENSHOT_THRESHOLD`. | `50` |
175
+ | `model.chatCompression.screenshotTriggerThreshold` | number | Tool-returned image count at or above which the screenshot trigger fires (only when `enableScreenshotTrigger`). Compaction resets the count — surviving images are re-embedded as top-level parts, which the trigger doesn't count — so it won't immediately re-fire. Env override: `QWEN_COMPACT_SCREENSHOT_THRESHOLD`. | `20` |
176
176
  | `model.skipNextSpeakerCheck` | boolean | Skip the next speaker check. | `true` |
177
177
  | `model.skipLoopDetection` | boolean | Disables streaming loop detection checks. Defaults to `true` (loop detection is skipped) to avoid false positives interrupting legitimate workflows. Set to `false` to re-enable streaming loop detection — useful as a guardrail in headless / non-interactive runs where stuck repetition can otherwise waste budget. | `true` |
178
178
  | `model.maxToolCallsPerTurn` | number | Hard cap on tool calls within a single turn (one model turn plus its tool-result continuations; blocking Stop-hook continuations such as `/goal` iterations start a fresh budget). Always-on circuit breaker against runaway turns, independent of `model.skipLoopDetection`; the pattern-based loop detectors fire long before this cap, which only bounds total volume. Set to `0` or a negative value to disable the cap. Choosing "Disable loop detection for this session" in the loop-detected dialog also suppresses it for the rest of the session. | `100` |
@@ -262,6 +262,12 @@ The `extra_body` field allows you to add custom parameters to the request body s
262
262
  | ------------- | ------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------- |
263
263
  | `visionModel` | string | Image-capable model used as the vision bridge: when a text-only main model receives an image, it is transcribed by this model first. Leave empty to auto-pick a same-provider vision model. Can also be set via `/model --vision`. | `""` |
264
264
 
265
+ #### visionBridgeTimeoutMs
266
+
267
+ | Setting | Type | Description | Default |
268
+ | ----------------------- | ------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------- |
269
+ | `visionBridgeTimeoutMs` | integer | Per-attempt timeout in milliseconds for the vision bridge image transcription call (positive integer up to 2147483647; the bridge retries a timed-out attempt once with a fresh timeout). Unset uses the built-in 30s. Raise for slow or proxied vision endpoints. | unset |
270
+
265
271
  #### voiceModel
266
272
 
267
273
  | Setting | Type | Description | Default |
@@ -270,14 +276,14 @@ The `extra_body` field allows you to add custom parameters to the request body s
270
276
 
271
277
  #### modelFallbacks
272
278
 
273
- | Setting | Type | Description | Default |
274
- | ---------------- | ------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------- |
279
+ | Setting | Type | Description | Default |
280
+ | ---------------- | ------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------- |
275
281
  | `modelFallbacks` | string | Ordered list of fallback model IDs (comma-separated, max 3) to try when the primary model hits capacity errors (429/503/529). Example: `"qwen-plus,qwen-turbo"`. Can also be set via the `--fallback-model` CLI flag. Requires restart. | `""` |
276
282
 
277
283
  #### modelPricing
278
284
 
279
- | Setting | Type | Description | Default |
280
- | -------------- | ------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------- |
285
+ | Setting | Type | Description | Default |
286
+ | -------------- | ------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ----------- |
281
287
  | `modelPricing` | object | Optional per-model pricing for cost estimation in `/stats model`. Example: `{ "qwen3-coder": { "inputPerMillionTokens": 0.30, "outputPerMillionTokens": 1.20 } }`. | `undefined` |
282
288
 
283
289
  #### context
@@ -325,7 +331,7 @@ If you are experiencing performance issues with file searching (e.g., with `@` c
325
331
  | `tools.truncateToolOutputLines` | number | Maximum lines or entries kept when truncating tool output. Applies to Shell, Grep, Glob, ReadFile and ReadManyFiles tools. | `1000` | Requires restart: Yes |
326
332
  | `tools.computerUse.enabled` | boolean | Enable the built-in Computer Use tools (cua-driver native desktop automation). When `true` (default), the `computer_use__*` tools are registered as deferred built-ins; the first invocation downloads the pinned, signed cua-driver binary into `~/.qwen/computer-use/` and walks through macOS Accessibility / Screen Recording permissions. | `true` | Requires restart: Yes |
327
333
  | `tools.computerUse.maxImageDimension` | number | Longest-edge pixel cap applied to cua-driver screenshots (via `set_config`'s `max_image_dimension`). `-1` (default) keeps cua-driver's built-in default (1568); `0` disables resizing (full resolution); a positive value caps the longest edge. Lower caps cut vision-token cost at the expense of fine detail. | `-1` | Requires restart: Yes. Env override: `QWEN_COMPUTER_USE_MAX_IMAGE_DIMENSION` (a non-negative integer; takes precedence over this setting) |
328
- | `tools.computerUse.idleTimeoutMs` | number | Milliseconds to keep the cua-driver process alive after the last `computer_use__*` call. The default is `300000` (5 minutes). Set to `0` to keep it running until Qwen Code exits. | `300000` | Requires restart: Yes |
334
+ | `tools.computerUse.idleTimeoutMs` | number | Milliseconds to keep the cua-driver process alive after the last `computer_use__*` call. The default is `300000` (5 minutes). Set to `0` to keep it running until Qwen Code exits. | `300000` | Requires restart: Yes |
329
335
  | `tools.toolSearch.enabled` | boolean | Load MCP tools on demand via ToolSearch to reduce prompt size. Disable this for models that rely on prefix-based KV caching (e.g. DeepSeek) to keep the prompt prefix stable and maximize cache hit rates. | `true` | Requires restart: Yes |
330
336
 
331
337
  > [!note]
@@ -342,6 +348,7 @@ If you are experiencing performance issues with file searching (e.g., with `@` c
342
348
  | `memory.autoSkillConfirm` | boolean | Ask for confirmation before auto-generated skills are added to the skill library. When off, auto-skills are saved immediately. | `true` |
343
349
  | `memory.enableTeamMemory` | boolean | Enable a project memory tier shared with collaborators via the git-tracked `.qwen/team-memory/` directory. Writes to it are secret-scanned and reviewable in the git diff. | `false` |
344
350
  | `memory.enableTeamMemorySync` | boolean | When team memory is enabled, automatically commit, fast-forward-pull, and push the `.qwen/team-memory/` directory at session start so collaborators stay in sync. Requires a configured git upstream. | `false` |
351
+ | `memory.agentTimeoutMinutes` | number | Max runtime in minutes for background memory agents (extraction, dream, remember, skill review). Unset uses each agent's built-in default (2–5 minutes); `0` disables the time limit. | unset |
345
352
 
346
353
  See [Memory](../features/memory) for details on how auto-memory works and how to use the `/memory`, `/remember`, and `/dream` commands.
347
354
 
@@ -477,18 +484,18 @@ execute when typed.
477
484
 
478
485
  Controls which [Skills](../features/skills) are exposed to the model.
479
486
 
480
- | Setting | Type | Description | Default |
481
- | ---------------- | ---------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------- |
487
+ | Setting | Type | Description | Default |
488
+ | ----------------- | ---------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------- |
482
489
  | `skills.disabled` | array of strings | Skill names to hide. Matched case-insensitively against the skill name. Hidden skills do not appear in `<available_skills>` or as `/<name>` slash commands. **Merged as a union** across user/project/system scopes, so a project cannot remove entries defined in user or system settings. | `undefined` |
483
490
 
484
491
  #### mcp
485
492
 
486
- | Setting | Type | Description | Default |
487
- | ------------------- | ---------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------- |
488
- | `mcp.serverCommand` | string | Command to start an MCP server. | `undefined` |
489
- | `mcp.allowed` | array of strings | An allowlist of MCP servers to allow. Allows you to specify a list of MCP server names that should be made available to the model. This can be used to restrict the set of MCP servers to connect to. Supports glob patterns (`*` matches any sequence, `?` matches a single character — e.g. `"*puppeteer*"`); entries without glob characters are matched exactly. Note that this will be ignored if `--allowed-mcp-server-names` is set. | `undefined` |
490
- | `mcp.excluded` | array of strings | A denylist of MCP servers to exclude. A server listed in both `mcp.excluded` and `mcp.allowed` is excluded. Supports glob patterns (`*`, `?`) the same way as `mcp.allowed`. Note that this will be ignored if `--allowed-mcp-server-names` is set. | `undefined` |
491
- | `mcp.toolIdleTimeoutMs` | number | Idle timeout in milliseconds for MCP tool calls. If the MCP server does not produce any response or progress update within this time, the call is aborted. Must be between `10000` and `3600000`. Can be overridden via the `QWEN_CODE_MCP_TOOL_IDLE_TIMEOUT_MS` environment variable. | `300000` |
493
+ | Setting | Type | Description | Default |
494
+ | ----------------------- | ---------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------- |
495
+ | `mcp.serverCommand` | string | Command to start an MCP server. | `undefined` |
496
+ | `mcp.allowed` | array of strings | An allowlist of MCP servers to allow. Allows you to specify a list of MCP server names that should be made available to the model. This can be used to restrict the set of MCP servers to connect to. Supports glob patterns (`*` matches any sequence, `?` matches a single character — e.g. `"*puppeteer*"`); entries without glob characters are matched exactly. Note that this will be ignored if `--allowed-mcp-server-names` is set. | `undefined` |
497
+ | `mcp.excluded` | array of strings | A denylist of MCP servers to exclude. A server listed in both `mcp.excluded` and `mcp.allowed` is excluded. Supports glob patterns (`*`, `?`) the same way as `mcp.allowed`. Note that this will be ignored if `--allowed-mcp-server-names` is set. | `undefined` |
498
+ | `mcp.toolIdleTimeoutMs` | number | Idle timeout in milliseconds for MCP tool calls. If the MCP server does not produce any response or progress update within this time, the call is aborted. Must be between `10000` and `3600000`. Can be overridden via the `QWEN_CODE_MCP_TOOL_IDLE_TIMEOUT_MS` environment variable. | `300000` |
492
499
 
493
500
  > [!note]
494
501
  >
package/bundled/qc-helper/docs/features/_meta.ts CHANGED
@@ -16,6 +16,7 @@ export default {
16
16
  worktree: 'Worktrees',
17
17
  mcp: 'MCP',
18
18
  lsp: 'LSP (Language Server Protocol)',
19
+ 'computer-use': 'Computer Use',
19
20
  'token-caching': 'Token Caching',
20
21
  sandbox: 'Sandboxing',
21
22
  language: 'i18n',
package/bundled/qc-helper/docs/features/channels/overview.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # Channels
2
2
 
3
- Channels let you interact with a Qwen Code agent from messaging platforms like Telegram, WeChat, QQ, DingTalk, or Feishu, instead of the terminal. You send messages from your phone or desktop chat app, and the agent responds just like it would in the CLI.
3
+ Channels let you interact with a Qwen Code agent from messaging platforms like Telegram, WeChat, QQ, DingTalk, WeCom, or Feishu, instead of the terminal. You send messages from your phone or desktop chat app, and the agent responds just like it would in the CLI.
4
4
 
5
5
  ## How It Works
6
6
 
@@ -15,7 +15,7 @@ All channels share one agent process with isolated sessions per user. Each chann
15
15
 
16
16
  ## Quick Start
17
17
 
18
- 1. Set up a bot on your messaging platform (see channel-specific guides: [Telegram](./telegram), [WeChat](./weixin), [QQ Bot](./qqbot), [DingTalk](./dingtalk), [Feishu](./feishu))
18
+ 1. Set up a bot on your messaging platform (see channel-specific guides: [Telegram](./telegram), [WeChat](./weixin), [QQ Bot](./qqbot), [DingTalk](./dingtalk), [WeCom](./wecom), [Feishu](./feishu))
19
19
  2. Add the channel configuration to `~/.qwen/settings.json`
20
20
  3. Run `qwen channel start` to start all channels, or `qwen channel start <name>` for a single channel
21
21
 
@@ -37,6 +37,7 @@ Channels are configured under the `channels` key in `settings.json`. Each channe
37
37
  "cwd": "/path/to/working/directory",
38
38
  "instructions": "Optional system instructions for the agent.",
39
39
  "groupPolicy": "disabled",
40
+ "dmPolicy": "open",
40
41
  "groups": {
41
42
  "*": { "requireMention": true }
42
43
  }
@@ -49,10 +50,12 @@ Channels are configured under the `channels` key in `settings.json`. Each channe
49
50
 
50
51
  | Option | Required | Description |
51
52
  | ------------------------ | ---------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
52
- | `type` | Yes | Channel type: `telegram`, `weixin`, `qq`, `dingtalk`, `feishu`, or a custom type from an extension (see [Plugins](./plugins)) |
53
- | `token` | Telegram | Bot token. Supports `$ENV_VAR` syntax to read from environment variables. Not needed for WeChat, DingTalk, or Feishu |
53
+ | `type` | Yes | Channel type: `telegram`, `weixin`, `qq`, `dingtalk`, `wecom`, `feishu`, or a custom type from an extension (see [Plugins](./plugins)) |
54
+ | `token` | Telegram | Bot token. Supports `$ENV_VAR` syntax to read from environment variables. Not needed for WeChat, DingTalk, WeCom, or Feishu |
54
55
  | `clientId` | DingTalk, Feishu | DingTalk AppKey or Feishu App ID. Supports `$ENV_VAR` syntax |
55
56
  | `clientSecret` | DingTalk, Feishu | DingTalk AppSecret or Feishu App Secret. Supports `$ENV_VAR` syntax |
57
+ | `botId` | WeCom | WeCom intelligent robot Bot ID. Supports `$ENV_VAR` syntax. See [WeCom](./wecom) |
58
+ | `secret` | WeCom | WeCom intelligent robot Secret. Supports `$ENV_VAR` syntax. See [WeCom](./wecom) |
56
59
  | `model` | No | Model to use for this channel (e.g., `qwen3.5-plus`). Overrides the default model. Useful for multimodal models that support image input |
57
60
  | `senderPolicy` | No | Who can talk to the bot: `allowlist` (default), `open`, or `pairing` |
58
61
  | `allowedUsers` | No | List of user IDs allowed to use the bot (used by `allowlist` and `pairing` policies) |
@@ -60,6 +63,7 @@ Channels are configured under the `channels` key in `settings.json`. Each channe
60
63
  | `cwd` | No | Working directory for the agent. Defaults to the current directory |
61
64
  | `instructions` | No | Custom instructions prepended to the first message of each session |
62
65
  | `groupPolicy` | No | Group chat access: `disabled` (default), `allowlist`, or `open`. See [Group Chats](#group-chats) |
66
+ | `dmPolicy` | No | Private/DM access: `open` (default) or `disabled` (silently drop all DMs). Useful for group-only bots |
63
67
  | `groupHistoryLimit` | No | Opt-in group history backfill. `0` or omitted disables it. A positive number persists that many authorized, unmentioned group messages for the next bot mention/reply. |
64
68
  | `groups` | No | Per-group settings. Keys are group chat IDs or `"*"` for defaults. See [Group Chats](#group-chats) |
65
69
  | `dispatchMode` | No | What happens when you send a message while the bot is busy: `steer` (default), `collect`, or `followup`. See [Dispatch Modes](#dispatch-modes) |
@@ -85,7 +89,7 @@ Controls how conversation sessions are managed:
85
89
 
86
90
  ### Channel Memory
87
91
 
88
- Channel memory lets an authorized channel member save stable context for one chat or thread. Qwen Code injects that memory when a fresh channel session starts, including after `/clear`.
92
+ Channel memory lets accepted channel senders save stable context for one chat or thread. Qwen Code injects that memory when a fresh channel session starts, including after `/clear`.
89
93
 
90
94
  Natural-language examples:
91
95
 
@@ -94,10 +98,11 @@ Natural-language examples:
94
98
  - `你现在都记住了什么` shows saved memory for the current chat or thread.
95
99
  - `把这个聊天的记忆清空` starts the clear flow; `确认清空记忆` confirms it.
96
100
 
97
- Group chats can show saved memory, but writes and clears are blocked to avoid
98
- turning shared memory into a prompt-injection path for other participants.
101
+ Channel memory follows the channel access gates. Any message accepted by `senderPolicy`, `dmPolicy`, `groupPolicy`, group settings, pairing, and mention requirements can read, write, or clear memory for that chat or thread.
99
102
 
100
- Only users listed in `allowedUsers` can read, write, or clear channel memory. If `allowedUsers` is empty, channel memory commands are disabled for everyone.
103
+ In open groups, any accepted member can update shared channel memory for that group. Use `allowlist` or `pairing` policies when memory should be limited to trusted senders.
104
+
105
+ Memory is keyed to the current chat or thread, so it is not injected into `single` session scope, where every chat shares one channel-wide agent session.
101
106
 
102
107
  ### Token Security
103
108
 
@@ -211,9 +216,10 @@ By default, Qwen ignores unmentioned group messages and does not store them as s
211
216
 
212
217
  ```
213
218
  1. groupPolicy — is this group allowed? (no → ignore)
214
- 2. requireMention — was the bot mentioned/replied to? (no → ignore)
215
- 3. senderPolicy — is this sender approved? (no → pairing flow)
216
- 4. Route to session
219
+ 2. dmPolicy — is this DM allowed? (disabled → ignore)
220
+ 3. requireMention — was the bot mentioned/replied to? (no → ignore)
221
+ 4. senderPolicy — is this sender approved? (no → pairing flow)
222
+ 5. Route to session
217
223
  ```
218
224
 
219
225
  ### Telegram Setup for Groups
@@ -273,6 +279,8 @@ Files work with any model — no multimodal support required.
273
279
  | Captions | Photo/file captions included as message text | Not applicable | Rich text: mixed text + images in one message | Rich text (`post`): text extracted; embedded images ignored |
274
280
 
275
281
  > QQ Bot does not process incoming media — image and sticker messages are ignored, so it has no media-handling row above.
282
+ >
283
+ > WeCom accepts text, images, mixed text plus images, files, videos, and voice messages (transcribed). Images are passed to the agent as attachments; files and videos are downloaded to temporary local paths. See [WeCom](./wecom#images-and-files) for details.
276
284
 
277
285
  ## Dispatch Modes
278
286
 
@@ -343,7 +351,7 @@ Channels support slash commands. These are handled locally (no agent round-trip)
343
351
 
344
352
  All other slash commands (e.g., `/compress`, `/summary`) are forwarded to the agent.
345
353
 
346
- These commands work on all channel types (Telegram, WeChat, QQ, DingTalk, Feishu).
354
+ These commands work on all channel types (Telegram, WeChat, QQ, DingTalk, WeCom, Feishu).
347
355
 
348
356
  ## Running
349
357
 
package/bundled/qc-helper/docs/features/channels/plugins.md CHANGED
@@ -55,6 +55,7 @@ All standard channel options work with custom channels:
55
55
  | `instructions` | Prepended to the first message of each session |
56
56
  | `model` | Model override for the channel |
57
57
  | `groupPolicy` | `disabled`, `allowlist`, or `open` |
58
+ | `dmPolicy` | `open` or `disabled` |
58
59
  | `groups` | Per-group settings |
59
60
 
60
61
  See [Overview](./overview) for details on each option.
package/bundled/qc-helper/docs/features/code-review.md CHANGED
@@ -112,7 +112,8 @@ Or, after running `/review 123`, type `post comments` to publish findings withou
112
112
 
113
113
  **What gets posted:**
114
114
 
115
- - High-confidence Critical and Suggestion findings as inline comments on specific lines
115
+ - High-confidence Critical and Suggestion findings as inline comments on specific lines, each prefixed with `**[Critical]**` or `**[Suggestion]**` so blockers are distinguishable from recommendations
116
+ - Where the fix is a single localized edit, a ` ```suggestion ` block you can apply in one click
116
117
  - For Approve/Request changes verdicts: a review summary with the verdict
117
118
  - For Comment verdict with all inline comments posted: no separate summary (inline comments are sufficient)
118
119
  - Model attribution footer on each comment (e.g., _— qwen3-coder via Qwen Code /review_)
package/bundled/qc-helper/docs/features/commands.md CHANGED
@@ -76,42 +76,43 @@ Commands specifically for controlling interface and output language.
76
76
 
77
77
  Commands for managing AI tools and models.
78
78
 
79
- | Command | Description | Usage Examples |
80
- | ----------------- | -------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------- |
81
- | `/mcp` | List configured MCP servers and tools | `/mcp`, `/mcp desc`, `/mcp nodesc`, `/mcp schema` |
82
- | `/import-config` | Import MCP servers from Claude configs | `/import-config all`, `/import-config claude-code`, `/import-config claude-desktop --scope user\|project` |
83
- | `/tools` | Display currently available tool list | `/tools`, `/tools desc` |
84
- | `/skills` | Open the Skills panel to browse, search, toggle, and launch skills | `/skills`, `/<skill-name>` |
85
- | `/plan` | Switch to plan mode or exit plan mode | `/plan`, `/plan <task>`, `/plan exit` |
86
- | `/approval-mode` | Change the tool-approval mode (current session only) | `/approval-mode`, `/approval-mode auto-edit` |
87
- | → `plan` | Analysis only, no execution (secure review) | `/approval-mode plan` |
88
- | → `default` | Require approval for edits (daily use) | `/approval-mode default` |
89
- | → `auto-edit` | Auto-approve edits (trusted environment) | `/approval-mode auto-edit` |
90
- | → `auto` | Classifier-evaluated approval (autonomous) | `/approval-mode auto` |
91
- | → `yolo` | Auto-approve everything (quick prototyping) | `/approval-mode yolo` |
92
- | `/model` | Switch model used in current session | `/model`, `/model <model-id>` (switch immediately) |
93
- | `/model --fast` | Set a lighter model for prompt suggestions | `/model --fast qwen3-coder-flash` |
94
- | `/model --voice` | Set the model used for voice transcription | `/model --voice <model-id>` |
95
- | `/model --vision` | Set the vision-bridge model used to transcribe images for a text-only main model | `/model --vision <model-id>` |
96
- | `/effort` | Set reasoning effort for thinking-capable models | `/effort` (opens picker), `/effort high` (low/medium/high/xhigh/max; mapped & clamped per provider) |
97
- | `/extensions` | Manage extensions | `/extensions list`, `/extensions manage` |
98
- | → `list` | List installed extensions | `/extensions list` |
99
- | → `manage` | Manage installed extensions (interactive) | `/extensions manage` |
100
- | → `explore` | Open extensions page in browser | `/extensions explore <Gemini\|ClaudeCode>` |
101
- | → `install` | Install an extension from a git repo or path | `/extensions install <repo-or-path>` |
102
- | `/memory` | Open the Memory Manager dialog | `/memory` |
103
- | `/remember` | Save a durable memory | `/remember Prefer terse responses` |
104
- | `/forget` | Remove matching entries from auto-memory | `/forget <query>` |
105
- | `/dream` | Manually run auto-memory consolidation | `/dream` |
106
- | `/hooks` | Manage Qwen Code hooks | `/hooks`, `/hooks list` |
107
- | `/permissions` | Manage permission rules | `/permissions` |
108
- | `/agents` | Manage subagents | `/agents manage`, `/agents create` |
109
- | `/arena` | Manage Arena sessions | `/arena start`, `/arena stop`, `/arena status`, `/arena select` (alias `choose`) |
110
- | `/goal` | Set a goal — keep working until condition met | `/goal <condition>`, `/goal clear` |
111
- | `/tasks` | List background tasks | `/tasks` |
112
- | `/workflows` | Inspect workflow runs | `/workflows`, `/workflows <runId>` |
113
- | `/lsp` | Show LSP server status | `/lsp` |
114
- | `/trust` | Manage folder trust settings | `/trust` |
79
+ | Command | Description | Usage Examples |
80
+ | ----------------- | ------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------- |
81
+ | `/mcp` | List configured MCP servers and tools | `/mcp`, `/mcp desc`, `/mcp nodesc`, `/mcp schema` |
82
+ | `/import-config` | Import MCP servers from Claude configs | `/import-config all`, `/import-config claude-code`, `/import-config claude-desktop --scope user\|project` |
83
+ | `/tools` | Display currently available tool list | `/tools`, `/tools desc` |
84
+ | `/skills` | Open the Skills panel to browse, search, toggle, and launch skills | `/skills`, `/<skill-name>` |
85
+ | `/plan` | Switch to plan mode or exit plan mode | `/plan`, `/plan <task>`, `/plan exit` |
86
+ | `/approval-mode` | Change the tool-approval mode (current session only) | `/approval-mode`, `/approval-mode auto-edit` |
87
+ | → `plan` | Analysis only, no execution (secure review) | `/approval-mode plan` |
88
+ | → `default` | Require approval for edits (daily use) | `/approval-mode default` |
89
+ | → `auto-edit` | Auto-approve edits (trusted environment) | `/approval-mode auto-edit` |
90
+ | → `auto` | Classifier-evaluated approval (autonomous) | `/approval-mode auto` |
91
+ | → `yolo` | Auto-approve everything (quick prototyping) | `/approval-mode yolo` |
92
+ | `/model` | Switch model used in current session | `/model`, `/model <model-id>` (switch immediately) |
93
+ | `/model --fast` | Set a lighter model for prompt suggestions | `/model --fast qwen3-coder-flash` |
94
+ | `/model --voice` | Set the model used for voice transcription | `/model --voice <model-id>` |
95
+ | `/model --vision` | Set the vision-bridge model used to transcribe images for a text-only main model | `/model --vision <model-id>` |
96
+ | `/effort` | Set reasoning effort for thinking-capable models | `/effort` (opens picker), `/effort high` (low/medium/high/xhigh/max; mapped & clamped per provider) |
97
+ | `/extensions` | Manage extensions | `/extensions list`, `/extensions manage` |
98
+ | → `list` | List installed extensions | `/extensions list` |
99
+ | → `manage` | Manage installed extensions (interactive) | `/extensions manage` |
100
+ | → `explore` | Open extensions page in browser | `/extensions explore <Gemini\|ClaudeCode>` |
101
+ | → `install` | Install an extension from a git repo or path | `/extensions install <repo-or-path>` |
102
+ | `/memory` | Open the Memory Manager dialog | `/memory` |
103
+ | `/remember` | Save a durable memory | `/remember Prefer terse responses` |
104
+ | `/forget` | Remove matching entries from auto-memory | `/forget <query>` |
105
+ | `/dream` | Manually run auto-memory consolidation | `/dream` |
106
+ | `/hooks` | Manage Qwen Code hooks | `/hooks`, `/hooks list` |
107
+ | `/reload-plugins` | Reload extension changes (commands, skills, agents, hooks, MCP/LSP servers) from disk | `/reload-plugins` |
108
+ | `/permissions` | Manage permission rules | `/permissions` |
109
+ | `/agents` | Manage subagents | `/agents manage`, `/agents create` |
110
+ | `/arena` | Manage Arena sessions | `/arena start`, `/arena stop`, `/arena status`, `/arena select` (alias `choose`) |
111
+ | `/goal` | Set a goal — keep working until condition met | `/goal <condition>`, `/goal clear` |
112
+ | `/tasks` | List background tasks | `/tasks` |
113
+ | `/workflows` | Inspect workflow runs | `/workflows`, `/workflows <runId>` |
114
+ | `/lsp` | Show LSP server status | `/lsp` |
115
+ | `/trust` | Manage folder trust settings | `/trust` |
115
116
 
116
117
  > [!warning]
117
118
  >
@@ -123,7 +124,7 @@ Commands for managing AI tools and models.
123
124
 
124
125
  > [!note]
125
126
  >
126
- > `/workflows`, `/lsp`, and `/trust` are registered only when their feature is enabled — via the `QWEN_CODE_ENABLE_WORKFLOWS=1` env var, the `--experimental-lsp` CLI flag, and the `security.folderTrust.enabled` setting respectively. When disabled they won't appear and will report an unknown command.
127
+ > `/workflows`, `/lsp`, and `/trust` are registered only when their feature is enabled — via the `QWEN_CODE_ENABLE_WORKFLOWS=1` env var, the `--experimental-lsp` CLI flag, and the `security.folderTrust.enabled` setting respectively. When disabled they won't appear and will report an unknown command. Similarly, `/dream` and `/forget` are registered only when managed auto-memory is available; without it they won't appear.
127
128
 
128
129
  ### 1.5 Built-in Skills
129
130
 
@@ -326,7 +327,7 @@ Commands for obtaining information and performing system settings.
326
327
  | `/stats monthly` | Show monthly token usage statistics | `/stats monthly` (alias `month`), `/stats month [YYYY-MM]` |
327
328
  | `/stats export` | Export usage statistics to CSV or JSON | `/stats export <daily\|monthly> [date\|month] [--format csv\|json] [--output path]` |
328
329
  | `/settings` | Open settings editor | `/settings` |
329
- | `/config` | Get or set any setting by dot-path key (writes to user settings) | `/config` (list all), `/config <key>`, `/config <key>=<value>` |
330
+ | `/config` | Get or set any setting by dot-path key (writes to user settings) | `/config` (list all), `/config <key>`, `/config <key>=<value>` |
330
331
  | `/auth` | Change authentication method | `/auth`, `/connect`, `/login` |
331
332
  | `/doctor` | Run installation and environment diagnostics | `/doctor`, `/doctor memory` |
332
333
  | → `memory` | Show current process memory diagnostics | `/doctor memory [--json] [--sample] [--snapshot]` |
package/bundled/qc-helper/docs/features/computer-use.md ADDED
@@ -0,0 +1,77 @@
1
+ # Computer Use
2
+
3
+ Qwen Code ships built-in **Computer Use** tools that let the agent drive your desktop — clicking, typing, scrolling, launching apps, reading window contents, and taking screenshots. This turns Qwen Code into a general desktop automation agent, not just a coding assistant confined to the terminal.
4
+
5
+ Computer Use is powered by the [`cua-driver`](https://github.com/trycua/cua) native driver. The tools are registered as deferred (lazy-loaded) built-ins under the `computer_use__` prefix, so they only cost prompt space once the model actually reaches for them.
6
+
7
+ > [!warning]
8
+ >
9
+ > Computer Use gives the agent control of your mouse, keyboard, and windows, and lets it read the contents of your screen. Only use it with trusted prompts and, where possible, in a sandboxed or disposable environment. The action tools (click, type, drag, etc.) go through the normal [approval flow](./approval-mode.md); read-only tools such as listing windows may run without a prompt.
10
+
11
+ ## Enabling and disabling
12
+
13
+ Computer Use is **enabled by default**. The `computer_use__*` tools are registered automatically at startup.
14
+
15
+ To disable it entirely — which also prevents the native driver from being downloaded or spawned — set `tools.computerUse.enabled` to `false` in your `settings.json`:
16
+
17
+ ```jsonc
18
+ {
19
+ "tools": {
20
+ "computerUse": {
21
+ "enabled": false,
22
+ },
23
+ },
24
+ }
25
+ ```
26
+
27
+ This setting requires a restart to take effect.
28
+
29
+ ## First run and the native driver
30
+
31
+ The first time the agent invokes a Computer Use tool, Qwen Code downloads a pinned, signed `cua-driver` binary (~20 MB) into `~/.qwen/computer-use/` and spawns it as a local process. Prebuilt binaries are published for macOS (Apple Silicon and Intel), Linux (x86_64), and Windows (x86_64).
32
+
33
+ ### macOS permissions
34
+
35
+ On macOS, desktop automation requires two system permissions:
36
+
37
+ - **Accessibility** — to read window/UI state and synthesize input
38
+ - **Screen Recording** — to capture screenshots
39
+
40
+ On first use the driver walks you through granting these via the standard macOS system dialogs. The agent can also check permission status on demand (the `check_permissions` tool). Because macOS attributes permission grants to the _responsible_ process, grants may need to be given to the terminal or IDE that launched Qwen Code.
41
+
42
+ ## What the agent can do
43
+
44
+ The full `cua-driver` tool surface is exposed. Highlights:
45
+
46
+ | Category | Tools (a selection) |
47
+ | ------------- | ---------------------------------------------------------------------------------- |
48
+ | Mouse | `click`, `double_click`, `right_click`, `drag`, `move_cursor`, `scroll` |
49
+ | Keyboard | `type_text`, `press_key`, `hotkey` |
50
+ | Windows / UI | `list_windows`, `get_window_state`, `get_accessibility_tree`, `set_value`, `zoom` |
51
+ | Apps | `launch_app`, `list_apps`, `bring_to_front`, `kill_app` |
52
+ | Browser pages | `page` (execute JavaScript, read text, query the DOM, click elements) |
53
+ | Screenshots | `get_window_state` (captures a PNG), `page` |
54
+ | Recording | `start_recording`, `stop_recording`, `replay_trajectory` (record/replay a session) |
55
+ | Sessions | `start_session`, `end_session`, agent-cursor overlay controls |
56
+
57
+ Element-addressed actions are preferred over raw pixel coordinates: `get_window_state` returns a Markdown rendering of a window's accessibility tree with a stable `element_index` for each actionable element, which the input tools can target directly.
58
+
59
+ Support is most complete on macOS; some tools are platform-specific (for example, `bring_to_front` is Windows-only, and `launch_app` targets macOS apps).
60
+
61
+ ## Configuration
62
+
63
+ All Computer Use settings live under `tools.computerUse` in `settings.json`. See the [Settings reference](../configuration/settings.md) for the authoritative list.
64
+
65
+ | Setting | Type | Default | Description |
66
+ | ------------------------------------- | ------- | -------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
67
+ | `tools.computerUse.enabled` | boolean | `true` | Register the `computer_use__*` tools. When `false`, the driver is never downloaded or spawned. |
68
+ | `tools.computerUse.maxImageDimension` | number | `-1` | Longest-edge pixel cap for screenshots. `-1` keeps the driver's default (1568); `0` disables resizing (full resolution); a positive value caps the longest edge. Lower caps cut vision-token cost. Env override: `QWEN_COMPUTER_USE_MAX_IMAGE_DIMENSION`. |
69
+ | `tools.computerUse.idleTimeoutMs` | number | `300000` | Milliseconds to keep the driver process alive after the last `computer_use__*` call (default 5 minutes). `0` keeps it running until Qwen Code exits. |
70
+
71
+ All three settings require a restart to take effect.
72
+
73
+ ## See also
74
+
75
+ - [Approval Mode](./approval-mode.md) — how tool executions are gated
76
+ - [Sandboxing](./sandbox.md) — isolating what tools can touch
77
+ - [Settings reference](../configuration/settings.md) — the full `tools.computerUse.*` schema