@qwen-code/qwen-code 0.19.8 → 0.19.9

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 (434) 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 +60 -51
  5. package/bundled/qc-helper/docs/features/_meta.ts +1 -0
  6. package/bundled/qc-helper/docs/features/channels/dingtalk.md +9 -2
  7. package/bundled/qc-helper/docs/features/channels/overview.md +71 -4
  8. package/bundled/qc-helper/docs/features/channels/wecom.md +6 -0
  9. package/bundled/qc-helper/docs/features/code-review.md +29 -5
  10. package/bundled/qc-helper/docs/features/commands.md +39 -38
  11. package/bundled/qc-helper/docs/features/computer-use.md +77 -0
  12. package/bundled/qc-helper/docs/features/tool-use-summaries.md +19 -23
  13. package/bundled/qc-helper/docs/integration-vscode.md +2 -2
  14. package/bundled/qc-helper/docs/qwen-serve.md +29 -12
  15. package/bundled/qc-helper/docs/reference/keyboard-shortcuts.md +1 -1
  16. package/bundled/review/DESIGN.md +93 -22
  17. package/bundled/review/SKILL.md +295 -86
  18. package/chunks/MaxSizedBox-6HYJ3ZPJ.js +70 -0
  19. package/chunks/{StandaloneSessionPicker-EYRGH6PJ.js → StandaloneSessionPicker-WS4GXYOG.js} +79 -79
  20. package/chunks/{acpAgent-GRFTTRHW.js → acpAgent-5FWSOZL5.js} +968 -200
  21. package/chunks/agent-HOLHB3RT.js +68 -0
  22. package/chunks/agent-headless-SXL6H56A.js +62 -0
  23. package/chunks/{anthropicContentGenerator-CPF22MA7.js → anthropicContentGenerator-L73TO3DB.js} +187 -31
  24. package/chunks/{artifact-tool-D233YJFH.js → artifact-tool-U7IRTLIV.js} +5 -5
  25. package/chunks/{askUserQuestion-MKL5ZTMC.js → askUserQuestion-2DLUUZZG.js} +6 -6
  26. package/chunks/bridge-BCJQ7BBB.js +78 -0
  27. package/chunks/{ca-MKD32FQL.js → ca-UJ6HC4H2.js} +64 -5
  28. package/chunks/{channel-worker-supervisor-NZQUOEFJ.js → channel-worker-supervisor-WSOAAYUO.js} +137 -13
  29. package/chunks/{chunk-QQDPRDVW.js → chunk-2HRYPZT5.js} +1 -1
  30. package/chunks/{chunk-2PSWA5ID.js → chunk-2X56YUSZ.js} +1 -1
  31. package/chunks/{chunk-DIWVZ3VM.js → chunk-34MW4KTI.js} +5 -5
  32. package/chunks/{chunk-IBY3Q3HG.js → chunk-34Z3U5RQ.js} +508 -126
  33. package/chunks/{chunk-UXEW557D.js → chunk-3AHXV67U.js} +3 -3
  34. package/chunks/{chunk-O2YT7VB4.js → chunk-3BTRNWWD.js} +1 -1
  35. package/chunks/chunk-3G7CIHVV.js +71 -0
  36. package/chunks/{chunk-FBET5XZ2.js → chunk-3SJSQXNS.js} +20 -5
  37. package/chunks/{chunk-BUZ6HGL4.js → chunk-3VAGG5T5.js} +248 -55
  38. package/chunks/{chunk-M7S4GK5Z.js → chunk-4C5BQ2D2.js} +74 -27
  39. package/chunks/{chunk-5MBO76SL.js → chunk-4GORAUCN.js} +3 -3
  40. package/chunks/{chunk-55ZMG67I.js → chunk-4LD5APFL.js} +4 -4
  41. package/chunks/{chunk-TLWA7TPR.js → chunk-4QLQE5WJ.js} +2 -2
  42. package/chunks/{chunk-UIDXQNMV.js → chunk-4WGODMVR.js} +1 -1
  43. package/chunks/{chunk-E6US47KI.js → chunk-4WKAA4KS.js} +1 -1
  44. package/chunks/{chunk-H6EMK6QK.js → chunk-4ZVWQHEQ.js} +11913 -5207
  45. package/chunks/{chunk-HW4N45EE.js → chunk-524RQP4Q.js} +29 -8
  46. package/chunks/{chunk-3GONHQOA.js → chunk-57OAHC2Y.js} +1 -1
  47. package/chunks/{chunk-JZSY4WP3.js → chunk-5DTTYNB7.js} +1 -1
  48. package/chunks/{chunk-YDOXPLYL.js → chunk-5HOMWMCL.js} +1147 -738
  49. package/chunks/{chunk-A4BMJM77.js → chunk-5O2XNYP6.js} +1 -0
  50. package/chunks/{chunk-ZL5HN75Q.js → chunk-5SFOMFG4.js} +2 -2
  51. package/chunks/{chunk-2EM7ECZD.js → chunk-5U27BZ72.js} +179 -63
  52. package/chunks/{chunk-JRQ7EVGE.js → chunk-5VXNZWGF.js} +2 -2
  53. package/chunks/{chunk-QYNNN7BK.js → chunk-5XUCZNSY.js} +2 -2
  54. package/chunks/{chunk-GO6LNQXT.js → chunk-6AM5D4ME.js} +1 -1
  55. package/chunks/{chunk-BJBWRCSK.js → chunk-6H67XLET.js} +1 -1
  56. package/chunks/{chunk-PUVCVELY.js → chunk-6PESIEKJ.js} +4 -4
  57. package/chunks/{chunk-3UP777ZS.js → chunk-6RLROE6G.js} +1 -1
  58. package/chunks/{chunk-ZERZSAZL.js → chunk-75DOP5OR.js} +2 -2
  59. package/chunks/{chunk-RMLZAUWH.js → chunk-77XJ3SWN.js} +10 -12
  60. package/chunks/{chunk-L46XKEGM.js → chunk-7PU4FYLG.js} +5 -8
  61. package/chunks/{chunk-NQKLOAVJ.js → chunk-7R3CZA3Q.js} +2 -2
  62. package/chunks/{chunk-SAIILPQ3.js → chunk-7X7TEQNX.js} +5 -3
  63. package/chunks/{chunk-OQXDAMKY.js → chunk-A3XKDTSH.js} +8 -8
  64. package/chunks/{chunk-IRJWHZWU.js → chunk-A4UCTEB5.js} +2 -2
  65. package/chunks/{chunk-TSPB77TG.js → chunk-AKIVHSJR.js} +923 -2892
  66. package/chunks/{chunk-FQNC62B2.js → chunk-ATAKVRIF.js} +11 -11
  67. package/chunks/{chunk-GSHQYYIV.js → chunk-AURZZYMD.js} +6 -26
  68. package/chunks/{chunk-CHB5SLZZ.js → chunk-B4G2WOFA.js} +3 -3
  69. package/chunks/{chunk-X3YGAX7V.js → chunk-B5ORX3FG.js} +4 -2
  70. package/chunks/chunk-BAPGSC7U.js +239 -0
  71. package/chunks/{chunk-UX6OTBVD.js → chunk-BMGVRZN4.js} +2 -2
  72. package/chunks/{chunk-ZN5T4BHI.js → chunk-BPZALHVR.js} +2 -2
  73. package/chunks/{chunk-IJRL2S3D.js → chunk-BZIFY5TF.js} +6 -6
  74. package/chunks/{chunk-OFEVLU4C.js → chunk-CARU2RR2.js} +1 -1
  75. package/chunks/chunk-CC2ITGCF.js +176 -0
  76. package/chunks/{chunk-HDOH3QYE.js → chunk-CCDMCZPP.js} +2 -2
  77. package/chunks/{chunk-FV7425LN.js → chunk-CEA3E3JB.js} +18 -5
  78. package/chunks/{chunk-BOBOCR5H.js → chunk-CLFKOZEK.js} +4 -4
  79. package/chunks/{chunk-P3XEEI3X.js → chunk-CNEIYWSA.js} +38 -9
  80. package/chunks/{chunk-GLE2YUPU.js → chunk-COH43MRJ.js} +1 -1
  81. package/chunks/{chunk-E5A7LHNN.js → chunk-CPBF7KYF.js} +1 -1
  82. package/chunks/{chunk-UWCTAVOD.js → chunk-CR3C7WXL.js} +1 -1
  83. package/chunks/{chunk-5P5XGNYH.js → chunk-CU3L64TP.js} +1 -1
  84. package/chunks/{chunk-CD6USWHZ.js → chunk-CUMMSHH6.js} +2 -2
  85. package/chunks/{chunk-IWKSG2AR.js → chunk-CXAOG665.js} +1 -1
  86. package/chunks/{chunk-WQTHLB5T.js → chunk-D2GFWEXB.js} +7 -7
  87. package/chunks/{chunk-I6WGFJJ3.js → chunk-D5SKC4YG.js} +38 -12
  88. package/chunks/{chunk-MZ7BABX3.js → chunk-DC5Z3DU6.js} +2 -2
  89. package/chunks/{chunk-64WXLC72.js → chunk-DJ2GSRLV.js} +1 -1
  90. package/chunks/{chunk-QN5NZ3UQ.js → chunk-DMTGGOSA.js} +2 -2
  91. package/chunks/{chunk-A5JOJ77H.js → chunk-E2IY465S.js} +38 -15
  92. package/chunks/{chunk-KHDZHZMH.js → chunk-E5Z2AVNV.js} +1 -1
  93. package/chunks/{chunk-SQ2UATK7.js → chunk-EAXLGSFP.js} +11 -11
  94. package/chunks/{chunk-JCH35JB3.js → chunk-ECNYL4AA.js} +2 -2
  95. package/chunks/{chunk-E7EMCSUG.js → chunk-EGYZ275M.js} +64 -42
  96. package/chunks/{chunk-6VK6FIMQ.js → chunk-EMDMPBJ4.js} +415 -379
  97. package/chunks/{chunk-5IFG2VC4.js → chunk-FCMNKVXT.js} +1 -1
  98. package/chunks/{chunk-V35MD7KN.js → chunk-GRC5HGPI.js} +1 -1
  99. package/chunks/{chunk-WMPVYQ4P.js → chunk-GWHYEOV2.js} +2 -2
  100. package/chunks/{chunk-27BHARDE.js → chunk-GWLSNBG4.js} +2103 -13
  101. package/chunks/chunk-GZRTYZ2R.js +292 -0
  102. package/chunks/{chunk-A2X3KLC3.js → chunk-GZXCZHCT.js} +3 -3
  103. package/chunks/{chunk-K5PGHDBN.js → chunk-H6XPXXMH.js} +1 -1
  104. package/chunks/{chunk-DICGXFAI.js → chunk-HKMAENAO.js} +8 -8
  105. package/chunks/{chunk-ZE6E424U.js → chunk-HPDUL5MF.js} +2 -2
  106. package/chunks/{chunk-KYMBIKIW.js → chunk-HTHUX2T5.js} +1 -1
  107. package/chunks/{chunk-LQ7TMOCE.js → chunk-HTO4JFDZ.js} +1 -1
  108. package/chunks/{chunk-ON3JA3RU.js → chunk-HVY356M2.js} +7 -9
  109. package/chunks/{chunk-GGQQA4JW.js → chunk-IAVB3HM3.js} +2 -2
  110. package/chunks/{chunk-FEJ2FZ3U.js → chunk-J3JA76CF.js} +2 -2
  111. package/chunks/{chunk-4CGOWHKM.js → chunk-J4MOFEOK.js} +2 -2
  112. package/chunks/{chunk-22MNNNXE.js → chunk-J4TSQ5EQ.js} +3 -2
  113. package/chunks/{chunk-22IFUCVR.js → chunk-JESCGQM3.js} +1 -1
  114. package/chunks/{chunk-CCGOFQV3.js → chunk-JSG7ZSBC.js} +8 -7
  115. package/chunks/{chunk-WF4FAXDL.js → chunk-JZETEN3Z.js} +62 -62
  116. package/chunks/{chunk-GN3F6PIU.js → chunk-K434OPES.js} +5 -5
  117. package/chunks/{chunk-YKZIAK7C.js → chunk-KHUQZZJ6.js} +66 -16
  118. package/chunks/{chunk-X2XNQQJI.js → chunk-KKNMOEZH.js} +4 -4
  119. package/chunks/{chunk-MRO43B25.js → chunk-KW7NOTN6.js} +1 -1
  120. package/chunks/{chunk-6IAWPIQ6.js → chunk-L36P3NBD.js} +3 -3
  121. package/chunks/{chunk-54YZOP7P.js → chunk-L573Z2QZ.js} +11894 -5190
  122. package/chunks/{chunk-DHOLNQLC.js → chunk-L6P4KPHR.js} +12 -12
  123. package/chunks/{chunk-E7KNELIZ.js → chunk-LK7KUE55.js} +2 -2
  124. package/chunks/{chunk-W7EEOR7D.js → chunk-LUODI7WD.js} +5 -5
  125. package/chunks/{chunk-CSOTA7KX.js → chunk-LXNEJD34.js} +2 -2
  126. package/chunks/{chunk-HLKG6CZN.js → chunk-M5GB774H.js} +1 -1
  127. package/chunks/{chunk-3B26UVCX.js → chunk-MC23XKFE.js} +39 -10
  128. package/chunks/{chunk-PC4ZXHU2.js → chunk-MXL5UP4X.js} +3 -3
  129. package/chunks/{chunk-BVYU3ZTI.js → chunk-N3EMS75V.js} +73 -30
  130. package/chunks/{chunk-332PWN27.js → chunk-NHDKSOEY.js} +1 -1
  131. package/chunks/{chunk-3GNOQZDC.js → chunk-NVYTCB5Z.js} +4797 -2620
  132. package/chunks/{chunk-P7M4GA57.js → chunk-OCPBI7J5.js} +1 -1
  133. package/chunks/chunk-OQ4DRIOA.js +296 -0
  134. package/chunks/{chunk-42XGFRJS.js → chunk-ORBGV7NJ.js} +5 -5
  135. package/chunks/{chunk-AYNCLGTW.js → chunk-P67PFTUT.js} +8 -51
  136. package/chunks/{chunk-VGGOPZUL.js → chunk-PDZ7MBDG.js} +12 -5
  137. package/chunks/{chunk-WHJQ3JUS.js → chunk-PODM4SZ4.js} +12 -12
  138. package/chunks/{chunk-JPALE3PA.js → chunk-PVZM22CK.js} +6 -6
  139. package/chunks/{chunk-AGHU5VRK.js → chunk-PZL23GTM.js} +1 -1
  140. package/chunks/{chunk-L4AMBVQG.js → chunk-Q4YQW46J.js} +31 -17
  141. package/chunks/{chunk-XYR5RUA5.js → chunk-Q6I5QHMH.js} +10 -3
  142. package/chunks/{chunk-FXGLL2HL.js → chunk-Q7YDKOGY.js} +1 -1
  143. package/chunks/{chunk-LGFAYIKX.js → chunk-QHTIBUWB.js} +1 -1
  144. package/chunks/{chunk-P3MYAZBY.js → chunk-QMGX2KO2.js} +1 -1
  145. package/chunks/{chunk-Z3I3QJK3.js → chunk-QRUIS3DN.js} +1 -1
  146. package/chunks/{chunk-ITOGNELQ.js → chunk-QSWDGAIC.js} +2 -2
  147. package/chunks/{chunk-GHOTR7HL.js → chunk-QUPXZXLV.js} +1 -1
  148. package/chunks/{chunk-XOHNA2S6.js → chunk-QYMQSECS.js} +3 -3
  149. package/chunks/{chunk-QYUE6W3T.js → chunk-RDJSGHZE.js} +1 -1
  150. package/chunks/{chunk-TLRYABYP.js → chunk-RKUWKYED.js} +1 -1
  151. package/chunks/{chunk-RNBYOUGV.js → chunk-RXFQM6FQ.js} +1 -1
  152. package/chunks/{chunk-QXPI7FEC.js → chunk-S3TWXGKA.js} +4 -4
  153. package/chunks/{chunk-BOBRZZKD.js → chunk-SCGXUJBT.js} +5 -5
  154. package/chunks/{chunk-44NROQYV.js → chunk-SJHDYNHF.js} +4 -4
  155. package/chunks/{chunk-MLZQVCF3.js → chunk-SZRN75WQ.js} +1 -1
  156. package/chunks/{chunk-7RYW5LQV.js → chunk-T2NCM2ET.js} +2 -2
  157. package/chunks/{chunk-Z2Z3GUXZ.js → chunk-TB6UDU4T.js} +1 -1
  158. package/chunks/{chunk-SUAKHHK7.js → chunk-TDEXZKMT.js} +3 -3
  159. package/chunks/{chunk-EXPMGZZV.js → chunk-TEGEBB2I.js} +1 -1
  160. package/chunks/{chunk-MX2YXRER.js → chunk-TJTKSVIV.js} +1 -1
  161. package/chunks/chunk-TO6QE22P.js +444 -0
  162. package/chunks/{chunk-H6BD2ELD.js → chunk-TYAMGABM.js} +2 -2
  163. package/chunks/chunk-U2NNEY4R.js +38 -0
  164. package/chunks/{chunk-VRDMOSQS.js → chunk-UDXSXLER.js} +2 -2
  165. package/chunks/{chunk-AHNJGLFV.js → chunk-UOZWKTQG.js} +3 -3
  166. package/chunks/{chunk-CJCKDMWO.js → chunk-URK542T4.js} +1 -1
  167. package/chunks/{chunk-AHNXYU4O.js → chunk-V6WHFGST.js} +1 -1
  168. package/chunks/{chunk-DCZWC4PF.js → chunk-VA4KQY6V.js} +5 -5
  169. package/chunks/{chunk-ZTQ26VBE.js → chunk-VDDGDZMA.js} +1 -1
  170. package/chunks/{chunk-OMX7CUOE.js → chunk-VGC4I5JJ.js} +1 -1
  171. package/chunks/{chunk-43W4YSO6.js → chunk-VJNBRRZG.js} +2 -2
  172. package/chunks/{chunk-J7RCB6N5.js → chunk-VTU57BWZ.js} +2 -2
  173. package/chunks/{chunk-LAXNEOBG.js → chunk-VWPVHAMO.js} +15 -3
  174. package/chunks/{chunk-VZ7HY3YU.js → chunk-W2UIXQDL.js} +3 -3
  175. package/chunks/{chunk-JZHIQJOE.js → chunk-W3JHSWRP.js} +6 -6
  176. package/chunks/{chunk-ER3BKOLB.js → chunk-W7FJ3N32.js} +1 -1
  177. package/chunks/{chunk-3HX5LZ6R.js → chunk-WBL3FJEU.js} +2 -2
  178. package/chunks/{chunk-BMFMJINR.js → chunk-WL4L7EZH.js} +1 -1
  179. package/chunks/{chunk-PMFULMLX.js → chunk-WQUQVGTF.js} +2057 -266
  180. package/chunks/chunk-X4NKFGFJ.js +81 -0
  181. package/chunks/{chunk-YHKAK72D.js → chunk-X6TJ3YZV.js} +102 -16
  182. package/chunks/{chunk-3RW4AZJV.js → chunk-XFSFZCM5.js} +1 -1
  183. package/chunks/{chunk-O7FIRWJV.js → chunk-XLA62MYB.js} +3 -3
  184. package/chunks/{chunk-2MPVVENX.js → chunk-XU457J4V.js} +2 -2
  185. package/chunks/{chunk-EEN2TKST.js → chunk-XUOOWUZS.js} +2 -2
  186. package/chunks/{chunk-SIUQ3YYX.js → chunk-XVNQMZ2I.js} +1 -1
  187. package/chunks/{chunk-SYCJMSIJ.js → chunk-XWRJCPHC.js} +1 -1
  188. package/chunks/{chunk-TI3BWD4D.js → chunk-XYQSMABS.js} +39 -19
  189. package/chunks/chunk-YAF2MQZ6.js +19 -0
  190. package/chunks/{chunk-O33TBKDC.js → chunk-YAUFFXDS.js} +154 -19
  191. package/chunks/{chunk-OACJLMLD.js → chunk-YLV3XXFB.js} +2 -2
  192. package/chunks/{chunk-BR4QREVK.js → chunk-YQ3U5MUC.js} +1 -1
  193. package/chunks/{chunk-Y6Z2O3WR.js → chunk-YUZI3WAC.js} +1 -1
  194. package/chunks/{chunk-II73RK2S.js → chunk-YVEDCAUE.js} +1 -1
  195. package/chunks/{chunk-SKAZWEV5.js → chunk-ZJE7NSL3.js} +1 -1
  196. package/chunks/{chunk-7LTB54MK.js → chunk-ZLXQN2QS.js} +2 -2
  197. package/chunks/cli-entry-path-4VJ3Y6T2.js +10 -0
  198. package/chunks/{computer-use-WMY3UOBX.js → computer-use-HM37RX6A.js} +50 -50
  199. package/chunks/config-utils-NV2SVGPB.js +23 -0
  200. package/chunks/contextCommand-OF5SFGH2.js +68 -0
  201. package/chunks/create-sub-session-INX7TXJI.js +207 -0
  202. package/chunks/create-sub-session-KPRT7ECJ.js +375 -0
  203. package/chunks/{cron-create-JSXEIPVS.js → cron-create-AMBKGZX6.js} +9 -9
  204. package/chunks/{cron-delete-OIFVEPGU.js → cron-delete-LRU4OJYG.js} +7 -7
  205. package/chunks/{cron-list-D4ZX4IOE.js → cron-list-WVP2JXER.js} +14 -10
  206. package/chunks/{daemon-WPAENEBW.js → daemon-ARHTSTXP.js} +478 -6
  207. package/chunks/daemon-status-provider-B2UTZUJ2.js +76 -0
  208. package/chunks/{de-ZFPPQVSF.js → de-EBJN3OVN.js} +64 -5
  209. package/chunks/{devtools-FM6GJPYG.js → devtools-4QFYJT6U.js} +3 -3
  210. package/chunks/{dist-Z34QPAQW.js → dist-PNVLTKTL.js} +374 -78
  211. package/chunks/{dist-63IS3ZMI.js → dist-PZV5RKM6.js} +4 -4
  212. package/chunks/{dist-BEXOZXLQ.js → dist-QYCAEZIT.js} +32 -15
  213. package/chunks/{dist-H2AEJCZ5.js → dist-R7LN5AZE.js} +5 -5
  214. package/chunks/{dist-E6UANPIM.js → dist-VHV4EVHG.js} +1011 -197
  215. package/chunks/{dist-O2IRTRPP.js → dist-WKPOYU7O.js} +10 -10
  216. package/chunks/{dist-SCFLLYMK.js → dist-XKU3ABM5.js} +12 -11
  217. package/chunks/earlyInputCapture-3VTHRC4C.js +69 -0
  218. package/chunks/{edit-OTYWAXGP.js → edit-VNI4NJ73.js} +51 -51
  219. package/chunks/{en-N4EPZAQI.js → en-5A6LA7RK.js} +74 -6
  220. package/chunks/{enter-worktree-HNYBDVCX.js → enter-worktree-IYYBKPZT.js} +50 -50
  221. package/chunks/{enterPlanMode-CJCNGT63.js → enterPlanMode-GMC5FD5A.js} +50 -50
  222. package/chunks/environment-5HSSRMJ7.js +88 -0
  223. package/chunks/errors-HMFCJJ7P.js +75 -0
  224. package/chunks/{exit-worktree-DUUKOE3X.js → exit-worktree-6BHCMP5G.js} +50 -50
  225. package/chunks/{exitPlanMode-AMMSXOAJ.js → exitPlanMode-CJW7G74W.js} +51 -51
  226. package/chunks/{fast-path-OV6NIP3K.js → fast-path-FRDMDVHG.js} +8 -8
  227. package/chunks/{fast-path-settings-7RIFI3PK.js → fast-path-settings-5QZE64HR.js} +6 -6
  228. package/chunks/{fileFromPath-IBEHA3CO.js → fileFromPath-UDALK7FM.js} +3 -3
  229. package/chunks/{fr-5WWMY53B.js → fr-YXRABLYZ.js} +64 -5
  230. package/chunks/{gemini-NQ3WWBKB.js → gemini-QYSEGHAX.js} +119 -111
  231. package/chunks/{geminiContentGenerator-CDUNEJQE.js → geminiContentGenerator-J7YNZDYP.js} +9 -9
  232. package/chunks/{getMachineId-bsd-4CASPIU4.js → getMachineId-bsd-EXV7SWPA.js} +3 -3
  233. package/chunks/{getMachineId-darwin-HPQPEMZR.js → getMachineId-darwin-IUOMFXU3.js} +3 -3
  234. package/chunks/{getMachineId-linux-AUARKYHL.js → getMachineId-linux-K7XJYFHL.js} +2 -2
  235. package/chunks/{getMachineId-unsupported-S32ZDA2T.js → getMachineId-unsupported-EA5FDRJ6.js} +2 -2
  236. package/chunks/{getMachineId-win-4EFLHYIJ.js → getMachineId-win-KBA6RAI5.js} +3 -3
  237. package/chunks/{glob-ROV3YS4R.js → glob-BRCSGFOT.js} +95 -74
  238. package/chunks/{grep-NRITKDCD.js → grep-EE2DUOSY.js} +50 -50
  239. package/chunks/handleAutoUpdate-5NWTLR67.js +69 -0
  240. package/chunks/i18n-BASPENNQ.js +84 -0
  241. package/chunks/initializer-UTQ7FB7G.js +71 -0
  242. package/chunks/installationInfo-W6V4DT7W.js +65 -0
  243. package/chunks/{ja-CUHZOLEJ.js → ja-7VQOANVG.js} +64 -5
  244. package/chunks/{keychain-token-storage-UJV5XP4Z.js → keychain-token-storage-VKUBNCP4.js} +4 -4
  245. package/chunks/{kittyProtocolDetector-OJRCJLIU.js → kittyProtocolDetector-HCNNKJTI.js} +2 -2
  246. package/chunks/list-DEICDL65.js +74 -0
  247. package/chunks/loadedSettingsAdapter-NOWEGDYJ.js +68 -0
  248. package/chunks/{loop-wakeup-OHWEMFP5.js → loop-wakeup-WX7BLWWP.js} +10 -10
  249. package/chunks/{lowlight-FYAAUU5J.js → lowlight-J2OZNPCA.js} +1 -1
  250. package/chunks/{ls-7MFU2QYW.js → ls-ZB2BDP6T.js} +6 -6
  251. package/chunks/{lsp-XHDTPTGV.js → lsp-V5DN4YUJ.js} +4 -4
  252. package/chunks/mcp-L5JXEEIA.js +68 -0
  253. package/chunks/{monitor-FL2ZO33W.js → monitor-X5Z3H4FY.js} +50 -50
  254. package/chunks/{multipart-parser-AJ4WASWR.js → multipart-parser-AWZKXSQN.js} +3 -3
  255. package/chunks/nonInteractiveCli-LS2K4X6A.js +124 -0
  256. package/chunks/{notebook-edit-6PULTHL5.js → notebook-edit-TRM2QIJK.js} +51 -51
  257. package/chunks/openaiContentGenerator-AAYONPMF.js +56 -0
  258. package/chunks/pidfile-D4I4FTVA.js +73 -0
  259. package/chunks/{pt-OLYN42DS.js → pt-2C6YCSHL.js} +64 -5
  260. package/chunks/{qwenContentGenerator-NX2E7PB7.js → qwenContentGenerator-K3HZ2H76.js} +52 -52
  261. package/chunks/{qwenOAuth2-ZV7YLMND.js → qwenOAuth2-PJQ27GSO.js} +9 -9
  262. package/chunks/read-file-7SZSIZOL.js +30 -0
  263. package/chunks/{read-mcp-resource-CNQHBSJM.js → read-mcp-resource-SM5DA4RG.js} +5 -5
  264. package/chunks/{read-package-up-ER5OJUGP.js → read-package-up-TCM6I7S2.js} +2 -2
  265. package/chunks/{record-artifact-SQ2OKRJW.js → record-artifact-4XKZX3UW.js} +4 -4
  266. package/chunks/ripGrep-YNPFVCZP.js +60 -0
  267. package/chunks/{ru-LDM3GWVQ.js → ru-6BBHVZZV.js} +64 -5
  268. package/chunks/{run-qwen-serve-JK2DL7PI.js → run-qwen-serve-DMWV5N6L.js} +395 -74
  269. package/chunks/runtime-57WWRVHN.js +94 -0
  270. package/chunks/{scheduler-O4IGVZKK.js → scheduler-YBLGWSIL.js} +51 -51
  271. package/chunks/{send-message-76GT3JMC.js → send-message-F36YD6KQ.js} +7 -7
  272. package/chunks/serve-R63NK3CV.js +74 -0
  273. package/chunks/{server-SGNPKX2O.js → server-Z22GCAXP.js} +3956 -869
  274. package/chunks/{session-5BNM25EZ.js → session-HKAAI7BN.js} +117 -112
  275. package/chunks/settings-3EYN66GK.js +118 -0
  276. package/chunks/shell-6YXINTWJ.js +68 -0
  277. package/chunks/{skill-I22QK5XS.js → skill-OO57P4X6.js} +24 -24
  278. package/chunks/spawnChannel-JD7G4VU6.js +70 -0
  279. package/chunks/{src-BBQSM46M.js → src-G5UPLZSZ.js} +122 -52
  280. package/chunks/{src-7XL4G4DC.js → src-VLI3TKEY.js} +4 -4
  281. package/chunks/standalone-update-OB7F4JPZ.js +79 -0
  282. package/chunks/{startInteractiveUI-JII36UGN.js → startInteractiveUI-73EGLIIH.js} +1775 -1663
  283. package/chunks/stdioHelpers-UMY72QRP.js +14 -0
  284. package/chunks/{syntheticOutput-F7LSDCAR.js → syntheticOutput-34H7LGA7.js} +5 -5
  285. package/chunks/task-create-FRGOEIKY.js +22 -0
  286. package/chunks/{task-list-TGGJX7EA.js → task-list-OW766BXZ.js} +10 -10
  287. package/chunks/{task-stop-W7NGTMYQ.js → task-stop-SIR5SNBN.js} +4 -4
  288. package/chunks/{task-update-XYWMHJGJ.js → task-update-YRA532MT.js} +12 -12
  289. package/chunks/{team-create-A7NUU5AQ.js → team-create-PECAAPXK.js} +50 -50
  290. package/chunks/{team-delete-UHQQ2QQX.js → team-delete-6OSECUZC.js} +10 -10
  291. package/chunks/{team-plan-approval-TOQRJ2KI.js → team-plan-approval-L6F434RY.js} +50 -50
  292. package/chunks/theme-manager-ZG4RY6GU.js +64 -0
  293. package/chunks/{todoWrite-C4ZAMSR3.js → todoWrite-YDMFEV4G.js} +6 -6
  294. package/chunks/{tool-search-SZ4EFS2T.js → tool-search-THVIWAPB.js} +24 -24
  295. package/chunks/total-session-admission-JOKNRIIA.js +72 -0
  296. package/chunks/trustedFolders-EOGT3UVS.js +79 -0
  297. package/chunks/{types-QX5C3CHJ.js → types-JNKGKUJT.js} +2 -2
  298. package/chunks/updateCheck-2KYEYVSB.js +69 -0
  299. package/chunks/updateEventEmitter-5MKC7BLQ.js +10 -0
  300. package/chunks/validateNonInterActiveAuth-EN6ZQSR2.js +190 -0
  301. package/chunks/{version-NO2XSNNP.js → version-3UEA6ZIR.js} +3 -3
  302. package/chunks/{web-fetch-UYGMOHW4.js → web-fetch-PAAEQKBW.js} +8 -8
  303. package/chunks/{workflow-WO2H6NRI.js → workflow-QCCCMYP3.js} +51 -51
  304. package/chunks/workspace-providers-status-4KMGETOJ.js +71 -0
  305. package/chunks/workspace-registry-24QFLQYH.js +76 -0
  306. package/chunks/workspace-service-RVLBMSMZ.js +80 -0
  307. package/chunks/workspace-skills-status-DS4ZVFTO.js +70 -0
  308. package/chunks/{write-file-PX2Z7IBE.js → write-file-I3MUDRIE.js} +51 -51
  309. package/chunks/{yargs-B64EYTCF.js → yargs-6H2AUULL.js} +2 -2
  310. package/chunks/{zh-J4F6QWQV.js → zh-RQE7I22T.js} +74 -6
  311. package/chunks/{zh-TW-XVDWOLSW.js → zh-TW-TBPQGHKH.js} +74 -6
  312. package/cli.js +18 -17
  313. package/locales/ca.js +85 -7
  314. package/locales/de.js +84 -7
  315. package/locales/en.js +101 -7
  316. package/locales/fr.js +85 -7
  317. package/locales/ja.js +86 -6
  318. package/locales/pt.js +84 -7
  319. package/locales/ru.js +84 -7
  320. package/locales/zh-TW.js +97 -6
  321. package/locales/zh.js +97 -6
  322. package/package.json +3 -6
  323. package/web-shell/assets/{arc-BWyoJpY2.js → arc-C15hqnJe.js} +1 -1
  324. package/web-shell/assets/{architectureDiagram-3BPJPVTR-BT0mGrz2.js → architectureDiagram-3BPJPVTR-B-At37J_.js} +1 -1
  325. package/web-shell/assets/{blockDiagram-GPEHLZMM-BLgUWvyf.js → blockDiagram-GPEHLZMM-B51wjcU7.js} +1 -1
  326. package/web-shell/assets/{c4Diagram-AAUBKEIU-DYx9M7oU.js → c4Diagram-AAUBKEIU-xBK7BAwN.js} +1 -1
  327. package/web-shell/assets/channel-CLiQD50f.js +1 -0
  328. package/web-shell/assets/{chunk-2J33WTMH-CfMHWbuZ.js → chunk-2J33WTMH-xKmLg7Yr.js} +1 -1
  329. package/web-shell/assets/{chunk-4BX2VUAB-B1URoqEV.js → chunk-4BX2VUAB-BfkdKZCM.js} +1 -1
  330. package/web-shell/assets/{chunk-55IACEB6-DAIaM4QF.js → chunk-55IACEB6-DT713sZf.js} +1 -1
  331. package/web-shell/assets/{chunk-727SXJPM-B2X34knw.js → chunk-727SXJPM-CYEeAamv.js} +1 -1
  332. package/web-shell/assets/{chunk-AQP2D5EJ-Cif-zLTQ.js → chunk-AQP2D5EJ-DBN-5CFd.js} +1 -1
  333. package/web-shell/assets/{chunk-FMBD7UC4-H18WCXdY.js → chunk-FMBD7UC4-CGZKk4PH.js} +1 -1
  334. package/web-shell/assets/{chunk-ND2GUHAM-YFtetHi0.js → chunk-ND2GUHAM-qQbC2O-y.js} +1 -1
  335. package/web-shell/assets/{chunk-QZHKN3VN-By2hiH3r.js → chunk-QZHKN3VN-B3zeXwsX.js} +1 -1
  336. package/web-shell/assets/classDiagram-4FO5ZUOK-D3sYqow5.js +1 -0
  337. package/web-shell/assets/classDiagram-v2-Q7XG4LA2-D3sYqow5.js +1 -0
  338. package/web-shell/assets/{cose-bilkent-S5V4N54A-VrcnnLZu.js → cose-bilkent-S5V4N54A-BKsl1Wvy.js} +1 -1
  339. package/web-shell/assets/{dagre-BM42HDAG-CGo-IaVV.js → dagre-BM42HDAG-CuuuLiBK.js} +1 -1
  340. package/web-shell/assets/{diagram-2AECGRRQ-Dl4QjzIB.js → diagram-2AECGRRQ-CG4_eKiV.js} +1 -1
  341. package/web-shell/assets/{diagram-5GNKFQAL-qMLmsO0u.js → diagram-5GNKFQAL-DSFTmZB1.js} +1 -1
  342. package/web-shell/assets/{diagram-KO2AKTUF-CHlmuxPI.js → diagram-KO2AKTUF-BxwlEHn8.js} +1 -1
  343. package/web-shell/assets/{diagram-LMA3HP47-BUwU3GwT.js → diagram-LMA3HP47-BUAg-jMG.js} +1 -1
  344. package/web-shell/assets/{diagram-OG6HWLK6-HEhwPDUM.js → diagram-OG6HWLK6-BFM2jlO5.js} +1 -1
  345. package/web-shell/assets/{erDiagram-TEJ5UH35-1n0llBmM.js → erDiagram-TEJ5UH35-CerbFPa2.js} +1 -1
  346. package/web-shell/assets/{flowDiagram-I6XJVG4X-BN74uMnt.js → flowDiagram-I6XJVG4X-BNeZz5Zz.js} +1 -1
  347. package/web-shell/assets/{ganttDiagram-6RSMTGT7-BoOq78i3.js → ganttDiagram-6RSMTGT7-CTOogLaM.js} +1 -1
  348. package/web-shell/assets/{gitGraphDiagram-PVQCEYII-CN8b00c8.js → gitGraphDiagram-PVQCEYII-yxSFkXPj.js} +1 -1
  349. package/web-shell/assets/index-D5IWFVk1.css +5 -0
  350. package/web-shell/assets/index-KFJRDhX7.js +783 -0
  351. package/web-shell/assets/{infoDiagram-5YYISTIA-CCurnIna.js → infoDiagram-5YYISTIA-DYdAUevm.js} +1 -1
  352. package/web-shell/assets/{ishikawaDiagram-YF4QCWOH-AwuRqdUP.js → ishikawaDiagram-YF4QCWOH-CNuijZ90.js} +1 -1
  353. package/web-shell/assets/{journeyDiagram-JHISSGLW-B7IICk-E.js → journeyDiagram-JHISSGLW-BTyiuonf.js} +1 -1
  354. package/web-shell/assets/{kanban-definition-UN3LZRKU-BYF0OKhx.js → kanban-definition-UN3LZRKU-DPJo0Uow.js} +1 -1
  355. package/web-shell/assets/{linear-GWWguGfD.js → linear-C8wKCbIC.js} +1 -1
  356. package/web-shell/assets/{mermaid.core-JqtkxvCl.js → mermaid.core-BV5o7nW5.js} +5 -5
  357. package/web-shell/assets/{mindmap-definition-RKZ34NQL-B0MmHsZ6.js → mindmap-definition-RKZ34NQL-BtLcBmSt.js} +1 -1
  358. package/web-shell/assets/{pieDiagram-4H26LBE5-DhImUZLQ.js → pieDiagram-4H26LBE5-C22J7A9Q.js} +1 -1
  359. package/web-shell/assets/{quadrantDiagram-W4KKPZXB-DGeSC3DT.js → quadrantDiagram-W4KKPZXB-DSL10wiL.js} +1 -1
  360. package/web-shell/assets/{requirementDiagram-4Y6WPE33-DkspY6Re.js → requirementDiagram-4Y6WPE33-feqh0UpX.js} +1 -1
  361. package/web-shell/assets/{sankeyDiagram-5OEKKPKP-CaOofS2x.js → sankeyDiagram-5OEKKPKP-Z4OVaWaZ.js} +1 -1
  362. package/web-shell/assets/{sequenceDiagram-3UESZ5HK-DFQ_kFnN.js → sequenceDiagram-3UESZ5HK-DIluIcb1.js} +1 -1
  363. package/web-shell/assets/{stateDiagram-AJRCARHV-D3snw0Tz.js → stateDiagram-AJRCARHV-hlhnuoYH.js} +1 -1
  364. package/web-shell/assets/stateDiagram-v2-BHNVJYJU-BhQMwgpl.js +1 -0
  365. package/web-shell/assets/{timeline-definition-PNZ67QCA-l4zH8nLM.js → timeline-definition-PNZ67QCA-Dqf_CqgL.js} +1 -1
  366. package/web-shell/assets/{vennDiagram-CIIHVFJN-BnRlA98M.js → vennDiagram-CIIHVFJN-DD2QhaTX.js} +1 -1
  367. package/web-shell/assets/{wardley-L42UT6IY-BS0xUdmd.js → wardley-L42UT6IY-B2uI85U_.js} +1 -1
  368. package/web-shell/assets/{wardleyDiagram-YWT4CUSO-DKGBUWyQ.js → wardleyDiagram-YWT4CUSO-U1aJX71g.js} +1 -1
  369. package/web-shell/assets/{xychartDiagram-2RQKCTM6-DVb2HuOB.js → xychartDiagram-2RQKCTM6-C0ODHUee.js} +1 -1
  370. package/web-shell/index.html +16 -4
  371. package/chunks/MaxSizedBox-5DT2SD7B.js +0 -71
  372. package/chunks/agent-H2DGKS77.js +0 -68
  373. package/chunks/agent-headless-KFMFIT6J.js +0 -62
  374. package/chunks/bridge-NA3ZQQKJ.js +0 -78
  375. package/chunks/chunk-6SHO7WFF.js +0 -79
  376. package/chunks/chunk-IFEWJXFS.js +0 -37
  377. package/chunks/chunk-S6RLAIUR.js +0 -23
  378. package/chunks/chunk-XNXVCNAT.js +0 -88
  379. package/chunks/contextCommand-LXFZRP4L.js +0 -68
  380. package/chunks/daemon-status-provider-GJRXY5EN.js +0 -76
  381. package/chunks/earlyInputCapture-KNOYZ4MJ.js +0 -69
  382. package/chunks/environment-ATFTYMLZ.js +0 -88
  383. package/chunks/errors-A54HAADA.js +0 -75
  384. package/chunks/handleAutoUpdate-CEZJAARW.js +0 -65
  385. package/chunks/initializer-BRFJKRRX.js +0 -71
  386. package/chunks/list-KVHF7O4X.js +0 -73
  387. package/chunks/loadedSettingsAdapter-LL5PSFKX.js +0 -68
  388. package/chunks/mcp-3GCXRTOQ.js +0 -68
  389. package/chunks/nonInteractiveCli-PTQI3DV6.js +0 -119
  390. package/chunks/openaiContentGenerator-YE42PKCY.js +0 -56
  391. package/chunks/pidfile-NZYSCFRK.js +0 -73
  392. package/chunks/read-file-33XGP5HF.js +0 -30
  393. package/chunks/ripGrep-QWZLGTAN.js +0 -60
  394. package/chunks/serve-JTMIGANH.js +0 -74
  395. package/chunks/settings-3MI4XXP6.js +0 -118
  396. package/chunks/shell-YJKBE67T.js +0 -68
  397. package/chunks/spawnChannel-UNV6W4DU.js +0 -70
  398. package/chunks/task-create-WCHTB435.js +0 -22
  399. package/chunks/theme-manager-WZ4RRMMB.js +0 -64
  400. package/chunks/total-session-admission-ULXJWXFV.js +0 -72
  401. package/chunks/trustedFolders-LAZZPZ3D.js +0 -79
  402. package/chunks/updateCheck-KONLM73X.js +0 -65
  403. package/chunks/validateNonInterActiveAuth-MPKSRCXD.js +0 -184
  404. package/chunks/workspace-providers-status-3W7E7DFW.js +0 -71
  405. package/chunks/workspace-registry-SXJZNN3O.js +0 -74
  406. package/chunks/workspace-service-CZRQZ4Q4.js +0 -80
  407. package/chunks/workspace-skills-status-K7WFREPD.js +0 -70
  408. package/node_modules/@qwen-code/audio-capture/dist/index.d.ts +0 -35
  409. package/node_modules/@qwen-code/audio-capture/dist/index.js +0 -48
  410. package/node_modules/@qwen-code/audio-capture/dist/index.js.map +0 -1
  411. package/node_modules/@qwen-code/audio-capture/dist/platform.d.ts +0 -7
  412. package/node_modules/@qwen-code/audio-capture/dist/platform.js +0 -18
  413. package/node_modules/@qwen-code/audio-capture/dist/platform.js.map +0 -1
  414. package/node_modules/@qwen-code/audio-capture/node_modules/node-gyp-build/LICENSE +0 -21
  415. package/node_modules/@qwen-code/audio-capture/node_modules/node-gyp-build/README.md +0 -58
  416. package/node_modules/@qwen-code/audio-capture/node_modules/node-gyp-build/SECURITY.md +0 -5
  417. package/node_modules/@qwen-code/audio-capture/node_modules/node-gyp-build/bin.js +0 -84
  418. package/node_modules/@qwen-code/audio-capture/node_modules/node-gyp-build/build-test.js +0 -19
  419. package/node_modules/@qwen-code/audio-capture/node_modules/node-gyp-build/index.js +0 -6
  420. package/node_modules/@qwen-code/audio-capture/node_modules/node-gyp-build/node-gyp-build.js +0 -207
  421. package/node_modules/@qwen-code/audio-capture/node_modules/node-gyp-build/optional.js +0 -7
  422. package/node_modules/@qwen-code/audio-capture/node_modules/node-gyp-build/package.json +0 -43
  423. package/node_modules/@qwen-code/audio-capture/package.json +0 -30
  424. package/node_modules/@qwen-code/audio-capture/prebuilds/darwin-arm64/@qwen-code+audio-capture.node +0 -0
  425. package/node_modules/@qwen-code/audio-capture/prebuilds/darwin-x64/@qwen-code+audio-capture.node +0 -0
  426. package/node_modules/@qwen-code/audio-capture/prebuilds/linux-arm64/@qwen-code+audio-capture.node +0 -0
  427. package/node_modules/@qwen-code/audio-capture/prebuilds/linux-x64/@qwen-code+audio-capture.node +0 -0
  428. package/node_modules/@qwen-code/audio-capture/prebuilds/win32-x64/@qwen-code+audio-capture.node +0 -0
  429. package/web-shell/assets/channel-wmPUGHtg.js +0 -1
  430. package/web-shell/assets/classDiagram-4FO5ZUOK-BA2ljEjW.js +0 -1
  431. package/web-shell/assets/classDiagram-v2-Q7XG4LA2-BA2ljEjW.js +0 -1
  432. package/web-shell/assets/index-CNwoO1Cn.js +0 -783
  433. package/web-shell/assets/index-CWQ0z6kZ.css +0 -5
  434. package/web-shell/assets/stateDiagram-v2-BHNVJYJU-BbSm_9d0.js +0 -1
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 |
@@ -270,33 +276,33 @@ 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
284
290
 
285
- | Setting | Type | Description | Default |
286
- | ----------------------------------------------------------- | -------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------- |
287
- | `context.fileName` | string or array of strings | The name of the context file(s). | `undefined` |
288
- | `context.autoCompactThreshold` | number | Fraction of the context window at which auto-compaction triggers. Must be greater than 0 and at most 1. Default is `0.7` (70%). For large context windows (>110K tokens), the absolute branch of the three-tier threshold system dominates, so values below ~0.7 may have no visible effect. Custom thresholds primarily affect small-window models (≤128K). Replaces the old `model.chatCompression.contextPercentageThreshold`. | `undefined` (uses internal 0.7) |
289
- | `context.importFormat` | string | The format to use when importing memory. | `undefined` |
290
- | `context.includeDirectories` | array | Additional directories to include in the workspace context. Specifies an array of additional absolute or relative paths to include in the workspace context. Missing directories will be skipped with a warning by default. Paths can use `~` to refer to the user's home directory. This setting can be combined with the `--include-directories` command-line flag. | `[]` |
291
- | `context.loadFromIncludeDirectories` | boolean | Controls the behavior of the `/memory refresh` command. If set to `true`, `QWEN.md` files should be loaded from all directories that are added. If set to `false`, `QWEN.md` should only be loaded from the current directory. | `false` |
292
- | `context.fileFiltering.respectGitIgnore` | boolean | Respect .gitignore files when searching. | `true` |
293
- | `context.fileFiltering.respectQwenIgnore` | boolean | Respect .qwenignore and configured custom ignore files when searching. | `true` |
294
- | `context.fileFiltering.customIgnoreFiles` | array | Project-root-relative ignore files to use instead of the default compatibility files (`.agentignore`, `.aiignore`) when `respectQwenIgnore` is enabled. `.qwenignore` is always included. | `[".agentignore", ".aiignore"]` |
295
- | `context.fileFiltering.enableRecursiveFileSearch` | boolean | Whether to enable searching recursively for filenames under the current tree when completing `@` prefixes in the prompt. | `true` |
296
- | `context.fileFiltering.enableFuzzySearch` | boolean | When `true`, enables fuzzy search capabilities when searching for files. Set to `false` to improve performance on projects with a large number of files. | `true` |
297
- | `context.clearContextOnIdle.toolResultsThresholdMinutes` | number | Minutes of inactivity before clearing old tool result content. Use `-1` to disable the idle trigger. | `60` |
298
- | `context.clearContextOnIdle.toolResultsNumToKeep` | integer | Integer number of most-recent compactable tool results to preserve when clearing. Values below 1 are floored to 1. | `5` |
299
- | `context.clearContextOnIdle.toolResultsTotalCharsThreshold` | number | Total compactable tool result output characters allowed in history before clearing oldest results. Use `-1` to disable the size trigger. This is a soft threshold: protected recent tool results may keep the total above it. | `500000` |
291
+ | Setting | Type | Description | Default |
292
+ | ----------------------------------------------------------- | -------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | -------------------------------- |
293
+ | `context.fileName` | string or array of strings | The name of the context file(s). | `undefined` |
294
+ | `context.autoCompactThreshold` | number | Target fraction of the context window at which auto-compaction triggers. Must be greater than 0 and at most 1. Default is `0.85` (85%). Acts as a ceiling on the trigger: on large windows it is the effective trigger (~85%), while on smaller windows compaction may fire earlier to leave room to summarize. Replaces the old `model.chatCompression.contextPercentageThreshold`. | `undefined` (uses internal 0.85) |
295
+ | `context.importFormat` | string | The format to use when importing memory. | `undefined` |
296
+ | `context.includeDirectories` | array | Additional directories to include in the workspace context. Specifies an array of additional absolute or relative paths to include in the workspace context. Missing directories will be skipped with a warning by default. Paths can use `~` to refer to the user's home directory. This setting can be combined with the `--include-directories` command-line flag. | `[]` |
297
+ | `context.loadFromIncludeDirectories` | boolean | Controls the behavior of the `/memory refresh` command. If set to `true`, `QWEN.md` files should be loaded from all directories that are added. If set to `false`, `QWEN.md` should only be loaded from the current directory. | `false` |
298
+ | `context.fileFiltering.respectGitIgnore` | boolean | Respect .gitignore files when searching. | `true` |
299
+ | `context.fileFiltering.respectQwenIgnore` | boolean | Respect .qwenignore and configured custom ignore files when searching. | `true` |
300
+ | `context.fileFiltering.customIgnoreFiles` | array | Project-root-relative ignore files to use instead of the default compatibility files (`.agentignore`, `.aiignore`) when `respectQwenIgnore` is enabled. `.qwenignore` is always included. | `[".agentignore", ".aiignore"]` |
301
+ | `context.fileFiltering.enableRecursiveFileSearch` | boolean | Whether to enable searching recursively for filenames under the current tree when completing `@` prefixes in the prompt. | `true` |
302
+ | `context.fileFiltering.enableFuzzySearch` | boolean | When `true`, enables fuzzy search capabilities when searching for files. Set to `false` to improve performance on projects with a large number of files. | `true` |
303
+ | `context.clearContextOnIdle.toolResultsThresholdMinutes` | number | Minutes of inactivity before clearing old tool result content. Use `-1` to disable the idle trigger. | `60` |
304
+ | `context.clearContextOnIdle.toolResultsNumToKeep` | integer | Integer number of most-recent compactable tool results to preserve when clearing. Values below 1 are floored to 1. | `5` |
305
+ | `context.clearContextOnIdle.toolResultsTotalCharsThreshold` | number | Total compactable tool result output characters allowed in history before clearing oldest results. Use `-1` to disable the size trigger. This is a soft threshold: protected recent tool results may keep the total above it. | `500000` |
300
306
 
301
307
  #### Troubleshooting File Search Performance
302
308
 
@@ -315,6 +321,8 @@ If you are experiencing performance issues with file searching (e.g., with `@` c
315
321
  | `tools.shell.enableInteractiveShell` | boolean | Use `node-pty` for an interactive shell experience. Fallback to `child_process` still applies. | `true` | |
316
322
  | `tools.core` | array of strings | **Deprecated.** Will be removed in next version. Use `permissions.allow` + `permissions.deny` instead. Restricts built-in tools to an allowlist. All tools not in the list are disabled. | `undefined` | |
317
323
  | `tools.exclude` | array of strings | **Deprecated.** Use `permissions.deny` instead. Tool names to exclude from discovery. Automatically migrated to the `permissions` format on first load. | `undefined` | |
324
+ | `tools.disabled` | array of strings | Tool names hidden from the registry entirely. Unlike `permissions.deny` (which blocks calls at runtime), disabled tools are never registered, so they do not appear in `/tools` and cannot be discovered or called by the model. For example, `["enter_plan_mode"]` prevents the model from switching into plan mode on its own. Merged as a union across scopes. | `undefined` | |
325
+ | `tools.visible` | array of strings | Deferred tool names made visible at startup without requiring `tool_search`. Listed tools appear alongside core tools in the initial session. Merged as a union across scopes. | `undefined` | |
318
326
  | `tools.allowed` | array of strings | **Deprecated.** Use `permissions.allow` instead. Tool names that bypass the confirmation dialog. Automatically migrated to the `permissions` format on first load. | `undefined` | |
319
327
  | `tools.approvalMode` | string | Sets the default approval mode for tool usage. | `default` | Possible values: `plan` (analyze only, do not modify files or execute commands), `default` (require approval before file edits or shell commands run), `auto-edit` (automatically approve file edits), `auto` (LLM classifier auto-approves safe actions, blocks risky ones), `yolo` (automatically approve all tool calls) |
320
328
  | `tools.discoveryCommand` | string | Command to run for tool discovery. | `undefined` | |
@@ -325,7 +333,7 @@ If you are experiencing performance issues with file searching (e.g., with `@` c
325
333
  | `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
334
  | `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
335
  | `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 |
336
+ | `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
337
  | `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
338
 
331
339
  > [!note]
@@ -342,6 +350,7 @@ If you are experiencing performance issues with file searching (e.g., with `@` c
342
350
  | `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
351
  | `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
352
  | `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` |
353
+ | `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
354
 
346
355
  See [Memory](../features/memory) for details on how auto-memory works and how to use the `/memory`, `/remember`, and `/dream` commands.
347
356
 
@@ -477,18 +486,18 @@ execute when typed.
477
486
 
478
487
  Controls which [Skills](../features/skills) are exposed to the model.
479
488
 
480
- | Setting | Type | Description | Default |
481
- | ---------------- | ---------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------- |
489
+ | Setting | Type | Description | Default |
490
+ | ----------------- | ---------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------- |
482
491
  | `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
492
 
484
493
  #### mcp
485
494
 
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` |
495
+ | Setting | Type | Description | Default |
496
+ | ----------------------- | ---------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------- |
497
+ | `mcp.serverCommand` | string | Command to start an MCP server. | `undefined` |
498
+ | `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` |
499
+ | `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` |
500
+ | `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
501
 
493
502
  > [!note]
494
503
  >
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/dingtalk.md CHANGED
@@ -30,6 +30,7 @@ Add the channel to `~/.qwen/settings.json`:
30
30
  "type": "dingtalk",
31
31
  "clientId": "$DINGTALK_CLIENT_ID",
32
32
  "clientSecret": "$DINGTALK_CLIENT_SECRET",
33
+ "useConnectionManager": true,
33
34
  "senderPolicy": "open",
34
35
  "sessionScope": "user",
35
36
  "cwd": "/path/to/your/project",
@@ -61,6 +62,12 @@ Or define them in the `env` section of `settings.json`:
61
62
  }
62
63
  ```
63
64
 
65
+ ### Connection Recovery
66
+
67
+ `useConnectionManager` defaults to `true`. The connection manager monitors the Stream WebSocket and replaces the DingTalk SDK client when the connection stops responding. You should normally leave it enabled.
68
+
69
+ Set `"useConnectionManager": false` to disable Qwen Code's connection manager and fall back to the SDK's keepalive and automatic reconnect behavior.
70
+
64
71
  ## Running
65
72
 
66
73
  ```bash
@@ -99,14 +106,14 @@ You can send photos and documents to the bot, not just text.
99
106
 
100
107
  - **Authentication:** AppKey + AppSecret instead of a static bot token. The SDK manages access token refresh automatically.
101
108
  - **Connection:** WebSocket stream instead of polling — no public IP or webhook URL needed.
102
- - **Formatting:** Responses use DingTalk's markdown dialect (a limited subset). Tables are automatically converted to plain text since DingTalk doesn't render them. Long messages are split into chunks at ~3800 characters.
109
+ - **Formatting:** Responses use DingTalk's markdown dialect. Markdown tables are passed through to the DingTalk client; long messages are split into chunks at ~3800 characters.
103
110
  - **Working indicator:** A 👀 emoji reaction is added to the user's message while processing, then removed when the response is sent.
104
111
  - **Media download:** Two-step process — a `downloadCode` from the message is exchanged for a temporary download URL via DingTalk's API.
105
112
  - **Groups:** DingTalk uses `isInAtList` for @mention detection instead of parsing message entities.
106
113
 
107
114
  ## Tips
108
115
 
109
- - **Use DingTalk markdown-aware instructions** — DingTalk supports a limited markdown subset (headers, bold, links, code blocks, but not tables). Adding instructions like "Use DingTalk markdown. Avoid tables." helps the agent format responses correctly.
116
+ - **Use DingTalk markdown-aware instructions** — DingTalk supports headings, bold text, links, code blocks, and tables. Keep tables compact because narrow screens may scroll horizontally.
110
117
  - **Restrict access** — In an organization context, `senderPolicy: "open"` may be acceptable. For tighter control, use `"allowlist"` or `"pairing"`. See [DM Pairing](./overview#dm-pairing) for details.
111
118
  - **Referenced messages** — Quoting (replying to) a user message includes the quoted text as context for the agent. Quoting bot responses is not yet supported.
112
119
 
package/bundled/qc-helper/docs/features/channels/overview.md CHANGED
@@ -89,7 +89,7 @@ Controls how conversation sessions are managed:
89
89
 
90
90
  ### Channel Memory
91
91
 
92
- 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`.
93
93
 
94
94
  Natural-language examples:
95
95
 
@@ -98,10 +98,11 @@ Natural-language examples:
98
98
  - `你现在都记住了什么` shows saved memory for the current chat or thread.
99
99
  - `把这个聊天的记忆清空` starts the clear flow; `确认清空记忆` confirms it.
100
100
 
101
- Group chats can show saved memory, but writes and clears are blocked to avoid
102
- 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.
103
102
 
104
- 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.
105
106
 
106
107
  ### Token Security
107
108
 
@@ -388,6 +389,72 @@ This mode starts one channel worker process owned by `qwen serve`. The worker co
388
389
 
389
390
  When channels are serve-managed, `qwen channel status` shows the owner as `qwen serve`, and `qwen channel stop` tells you to stop the daemon instead of signaling the worker directly. If a ready worker exits unexpectedly, the daemon continues running and reports a channel-worker warning in `/daemon/status`.
390
391
 
392
+ ## Webhook-triggered tasks
393
+
394
+ Daemon-managed channels can also accept authenticated webhook events. Qwen receives the event as context, summarizes and decides what matters, and then delivers the final response to the configured chat target. This is not a raw notification relay.
395
+ Webhook tasks require `approvalMode: "yolo"` because they run without interactive approval. That setting applies to the whole channel, not only webhook turns, so use a dedicated webhook channel or tightly restrict normal chat senders for that channel.
396
+
397
+ Example channel config:
398
+
399
+ ```json
400
+ {
401
+ "channels": {
402
+ "dingtalk-main": {
403
+ "type": "dingtalk",
404
+ "clientId": "$DINGTALK_CLIENT_ID",
405
+ "clientSecret": "$DINGTALK_CLIENT_SECRET",
406
+ "cwd": "/repo",
407
+ "senderPolicy": "allowlist",
408
+ "allowedUsers": ["12345"],
409
+ "approvalMode": "yolo",
410
+ "sessionScope": "user",
411
+ "webhooks": {
412
+ "sources": {
413
+ "github-ci": {
414
+ "secretEnv": "QWEN_CHANNEL_GITHUB_CI_SECRET",
415
+ "targets": {
416
+ "default": {
417
+ "chatId": "OPEN_CONVERSATION_ID",
418
+ "senderId": "webhook:github-ci",
419
+ "isGroup": true
420
+ }
421
+ }
422
+ }
423
+ }
424
+ }
425
+ }
426
+ }
427
+ }
428
+ ```
429
+
430
+ For DingTalk, `chatId` must be the group `openConversationId`; other adapters may require their own proactive target shape.
431
+
432
+ Start `qwen serve` with the channel worker enabled:
433
+
434
+ ```bash
435
+ QWEN_SERVER_TOKEN="$QWEN_SERVER_TOKEN" qwen serve --require-auth --channel dingtalk-main
436
+ ```
437
+
438
+ Example request:
439
+
440
+ ```bash
441
+ curl -X POST "http://127.0.0.1:4170/channels/dingtalk-main/webhooks/github-ci" \
442
+ -H "x-qwen-webhook-secret: $QWEN_CHANNEL_GITHUB_CI_SECRET" \
443
+ -H "Content-Type: application/json" \
444
+ -d '{
445
+ "eventType": "push",
446
+ "targetRef": "default",
447
+ "title": "CI pipeline finished",
448
+ "payload": {
449
+ "targetRef": "refs/heads/main",
450
+ "repository": "qwen-code",
451
+ "status": "success"
452
+ }
453
+ }'
454
+ ```
455
+
456
+ Webhook routes authenticate with the webhook secret header, even when `qwen serve` is running with bearer auth enabled. Do not share the daemon bearer token with webhook providers. Webhook config and `secretEnv` values are loaded when the daemon starts; restart `qwen serve` after changing webhook sources or rotating secrets. A `202 {"accepted": true}` response means the channel worker accepted ownership of the task, not that the final response has already been delivered to chat. Check daemon and channel worker logs, plus `/daemon/status`, when troubleshooting delivery failures.
457
+
391
458
  ### Multi-Channel Mode
392
459
 
393
460
  When you run `qwen channel start` without a name, all channels defined in `settings.json` start together sharing a single agent process. Each channel maintains its own sessions — a Telegram user and a WeChat user get separate conversations, even though they share the same agent.
package/bundled/qc-helper/docs/features/channels/wecom.md CHANGED
@@ -11,7 +11,13 @@ This guide covers setting up Qwen Code with a WeCom intelligent robot (企业微
11
11
  ## Creating the Robot
12
12
 
13
13
  1. Open the WeCom admin console and create an intelligent robot.
14
+
15
+ ![](https://gw.alicdn.com/imgextra/i2/O1CN017w1jWj1TTvNBcfya8_!!6000000002384-2-tps-2212-887.png)
16
+
14
17
  2. Choose API mode.
18
+
19
+ ![](https://gw.alicdn.com/imgextra/i3/O1CN01buuik0207paQUuLQW_!!6000000006803-1-tps-1276-720.gif)
20
+
15
21
  3. Copy the Bot ID and Secret.
16
22
  4. Add the robot to the direct chats or groups where it should be available.
17
23
 
package/bundled/qc-helper/docs/features/code-review.md CHANGED
@@ -27,8 +27,9 @@ The `/review` command runs a multi-stage pipeline:
27
27
 
28
28
  ```
29
29
  Step 1: Determine scope (local diff / PR worktree / file)
30
+ Capture the diff to a file + partition it into chunks
30
31
  Step 2: Load project review rules
31
- Step 3: 10 parallel review agents [10 LLM calls]
32
+ Step 3A: <=500 source lines: 10 parallel review agents [10 LLM calls]
32
33
  |-- Agent 0: Issue Fidelity & Root-Cause Ownership
33
34
  |-- Agent 1: Correctness
34
35
  |-- Agent 2: Security
@@ -37,8 +38,20 @@ Step 3: 10 parallel review agents [10 LLM calls]
37
38
  |-- Agent 5: Test Coverage
38
39
  |-- Agent 6: Undirected Audit (3 personas: 6a/6b/6c)
39
40
  '-- Agent 7: Build & Test (runs shell commands)
40
- Step 4: Deduplicate --> Batch verify --> Aggregate [1 LLM call]
41
- Step 5: Iterative reverse audit (1-3 rounds, gap finding) [1-3 LLM calls]
41
+ Step 3B: >500 source lines: territory x dimension fan-out [N+4+H calls]
42
+ |-- 1 chunk agent per ~400 diff lines (all dimensions,
43
+ | its territory only, returns a coverage receipt)
44
+ |-- 3 invariant agents per heavily-rewritten source
45
+ | file (whole file; state/timers, counters/
46
+ | returns/errors, config/early-returns)
47
+ |-- Agent 0: Issue Fidelity (whole diff)
48
+ |-- Agent 7: Build & Test (whole repo)
49
+ |-- Cross-file impact (whole diff)
50
+ '-- Test coverage matrix (whole diff)
51
+ Step 4: Deduplicate --> Sharded verify (<=8 findings each)
52
+ --> Aggregate [ceil(N/8) calls]
53
+ Step 5: Iterative reverse audit, fanned out per chunk;
54
+ stop after 2 consecutive dry rounds (cap 5)
42
55
  Step 6: Present findings + verdict
43
56
  Step 7: Submit PR review (inline comments, if requested)
44
57
  Step 8: Save report + incremental cache
@@ -58,7 +71,17 @@ Step 9: Clean up (remove worktree + temp files)
58
71
  | Agent 6: Undirected Audit | 3 parallel personas (attacker / 3am-oncall / maintainer) — catches cross-dimensional issues |
59
72
  | Agent 7: Build & Test | Runs build and test commands, reports failures |
60
73
 
61
- All agents run in parallel (Agent 6 launches 3 persona variants concurrently, totaling 10 parallel tasks for same-repo PR reviews; Agent 0 is skipped for local-diff and file-path reviews, which run 9). Findings from Agents 0-6 are verified in a **single batch verification pass** (one agent reviews all findings at once, keeping verification cost fixed regardless of finding count). After verification, **iterative reverse audit** runs 1-3 rounds of gap-finding — each round receives the cumulative finding list from prior rounds, so successive rounds focus on whatever's left undiscovered. The loop stops as soon as a round returns "No issues found", or after 3 rounds (hard cap). Reverse audit findings skip verification (the agent already has full context) and are included as high-confidence results.
74
+ All agents run in parallel (Agent 6 launches 3 persona variants concurrently, totaling 10 parallel tasks for same-repo PR reviews; Agent 0 is skipped for local-diff and file-path reviews, which run 9).
75
+
76
+ Once a PR carries more than 500 lines of **source** change — or more than 2 400 diff lines in total, past which chunking needs fewer agents than the ten-lens topology anyway — this dimension fan-out is replaced by a **territory × dimension** fan-out: the diff is split into ~400-line chunks — boundaries fall on hunk boundaries, and a hunk too large to fit is split only at a top-level declaration, never inside a function — and each chunk gets its own agent that applies every review dimension to that chunk alone.
77
+
78
+ The gate deliberately counts source lines rather than diff lines. Test code, prose and lockfiles dominate diff size — across this repo's last 40 merged PRs the median diff is 41% tests — so a gate on raw size would carve a 173-line production change into territories just because it shipped 489 lines of new tests, leaving that production code with one reviewer instead of eight lenses. Chunking still covers every line either way, tests included; what the gate decides is how many reviewers there are and what each is asked to do. Ten agents all reading one large diff read the same early hunks ten times; one agent per chunk means every line of the diff has exactly one accountable reviewer. Each chunk agent returns a `Covered:` receipt, and a chunk with no receipt is re-reviewed before the run proceeds — so "no blockers" can never be reported over code that nobody read.
79
+
80
+ A **source** file that is largely rewritten (an existing file of 300+ lines that is now 40%+ new, or has 800+ changed lines) also gets **three whole-file invariant agents**. Test and generated files never qualify — the checklist asks about fields, timers, and error taxonomies, which a rewritten test file does not have. Its bugs are usually not inside any one hunk but _between_ the new lines — a timer armed near the top of the file and a teardown path two thousand lines below. Each agent reads the whole post-change file and walks two or three items of a fixed checklist: mutable fields cleared on every exit path, timers cancelled on every close (and cancellation not discarding captured data), map inserts matched by deletes, retry counters incremented at every entry, status return values actually checked, error codes exhaustively classified permanent vs transient, config fields honoured on every path, and early returns that skip a required side effect.
81
+
82
+ The checklist is split three ways on purpose. Handing one agent all eight checks over a 2 400-line file gets one of them done properly; three agents with two or three checks each get all of them done. Chunk agents do not substitute for this — on PR #6457 they held every one of these defects inside their assigned territory and reported none. What they lacked was not the lines but the question.
83
+
84
+ Findings are verified in **sharded batches** (at most 8 findings per verification agent, all launched together). A verifier may downgrade a Critical to low confidence but may never delete one — a rejected Critical is invisible to every later stage, while a downgraded one still reaches a human. After verification, **iterative reverse audit** hunts for gaps, fanned out one auditor per chunk per round, each with the cumulative finding list. The loop stops after **two consecutive dry rounds** (or 5 rounds, hard cap — reported as such rather than as convergence). One dry round is not evidence of convergence, and reverse-audit findings are verified like any other.
62
85
 
63
86
  ## Severity Levels
64
87
 
@@ -112,7 +135,8 @@ Or, after running `/review 123`, type `post comments` to publish findings withou
112
135
 
113
136
  **What gets posted:**
114
137
 
115
- - High-confidence Critical and Suggestion findings as inline comments on specific lines
138
+ - High-confidence Critical and Suggestion findings as inline comments on specific lines, each prefixed with `**[Critical]**` or `**[Suggestion]**` so blockers are distinguishable from recommendations
139
+ - Where the fix is a single localized edit, a ` ```suggestion ` block you can apply in one click
116
140
  - For Approve/Request changes verdicts: a review summary with the verdict
117
141
  - For Comment verdict with all inline comments posted: no separate summary (inline comments are sufficient)
118
142
  - Model attribution footer on each comment (e.g., _— qwen3-coder via Qwen Code /review_)