Qwen Code cua-driver-rs-v0.7.0 预发布

cua-driver prebuilt binaries — relative-coordinate fork (vendored under `packages/cua-driver`). - **macOS**: codesigned + notarized universal binary + `QwenCuaDriver.app` - **Linux**: unsigned (x86_64 + arm64, glibc 2.31 floor) - **Windows**: unsigned (x86_64 + arm64) Enable relative coordinates: `CUA_DRIVER_RS_COORDINATE_SPACE=1` (default `0` = off; optional `CUA_DRIVER_RS_COORDINATE_SCALE=1000`). <!-- Release notes generated using configuration in .github/release.yml at cua-driver-rs-v0.7.0 --> ## What's Changed * feat(web-shell): polish chat UI by @ytahdn in https://github.com/QwenLM/qwen-code/pull/5893 * feat(telemetry): wire recordApiRequestBreakdown into endLLMRequestSpan (Phase 4c) by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5904 * feat(web-shell): browse MCP server resources in the /mcp dialog by @wenshao in https://github.com/QwenLM/qwen-code/pull/5879 * feat(web-shell): allow host to override streaming loading phrases by @carffuca in https://github.com/QwenLM/qwen-code/pull/5900 * fix(core): tree-kill PTY shell tree on Windows to stop pwsh leak (#5873) by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5892 * [codex] test(ci): cover post-merge review follow-ups by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5899 * fix(core): ignore IDE configs from other workspaces by @seekskyworld in https://github.com/QwenLM/qwen-code/pull/5807 * fix(cli): wrap tool call descriptions instead of truncating by @Alex-ai-future in https://github.com/QwenLM/qwen-code/pull/5891 * fix(serve): reject negative cleanupPeriodDays values by @russeell in https://github.com/QwenLM/qwen-code/pull/5906 * fix(desktop): reject unsafe source slugs before deletion by @VectorPeak in https://github.com/QwenLM/qwen-code/pull/5829 * feat(web-shell): stream-highlight code blocks and fix fence-language aliases by @carffuca in https://github.com/QwenLM/qwen-code/pull/5869 * fix(core): clear tool display after completion errors by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5916 * fix(desktop): harden remaining source path validation by @VectorPeak in https://github.com/QwenLM/qwen-code/pull/5914 * fix(core): preserve rewind parents after resume by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5923 * Fix mid-input skill command completion by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5898 * fix(core): parse workflow stall env as decimal seconds by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5930 * fix(cli): align MCP dialog border by @shenyankm in https://github.com/QwenLM/qwen-code/pull/5935 * fix(core): improve cron tool search intents by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5927 * fix(core): silence unknown schema format warnings by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5915 * fix(core): stop computer use driver when idle by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5925 * feat(core): warn before foreground shell timeout by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5918 * feat(web-shell): add manual toggle for enhanced markdown tables by @ytahdn in https://github.com/QwenLM/qwen-code/pull/5917 * fix(core): stop repeated truncated write_file/edit retries from looping by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5934 * refactor(cli): Split serve server assembly by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5937 * feat(memory): add a git-shared team memory tier by @qqqys in https://github.com/QwenLM/qwen-code/pull/5886 * feat(web-shell): add workspace session sidebar by @ytahdn in https://github.com/QwenLM/qwen-code/pull/5931 * feat(cli): add /model --vision for a fallback vision model by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5778 * feat(cli): show scheduled task count in footer by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5921 * perf(cli): enable compile cache and defer getCliVersion for serve by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5938 * docs: add provider preset governance policy to CONTRIBUTING.md by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/5631 * feat(acp): support /cd command in ACP sessions by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5903 * Upgrade GitHub Actions to latest versions by @salmanmkc in https://github.com/QwenLM/qwen-code/pull/3683 * feat(channels): register Telegram bot command menu by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5919 * fix(core): preserve the selected model when re-applying a provider install plan by @lcheng321 in https://github.com/QwenLM/qwen-code/pull/5835 * fix(serve): reject non-positive sessionRecapAwayThresholdMinutes values by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5945 * feat(web-shell): add error boundaries so a render crash can't white-screen the embed by @carffuca in https://github.com/QwenLM/qwen-code/pull/5943 * feat(web-shell): add mobile responsive view for TodoPanel by @ytahdn in https://github.com/QwenLM/qwen-code/pull/5948 * feat(web-shell): add 'voice' to ComposerToolbarAction for external visibility control by @ytahdn in https://github.com/QwenLM/qwen-code/pull/5947 * fix(core): isolate Anthropic SDK abort listener leak with per-request child controllers by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5946 * fix(desktop): normalize source slug validation errors by @VectorPeak in https://github.com/QwenLM/qwen-code/pull/5911 * docs(daemon): refresh daemon docs for recent PRs (wave 2) by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5954 * feat(core): add configurable auto-compact threshold and Stop hook context usage (#4025) by @ZijianZhang989 in https://github.com/QwenLM/qwen-code/pull/5868 * ci(review): increase PR review timeout from 90 to 120 minutes by @wenshao in https://github.com/QwenLM/qwen-code/pull/5959 * fix(core): halt repeated shell inspection variants by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5944 * refactor(cli): Remove serve bridge re-export shims by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5955 * feat(core,cli,sdk): resume an interrupted turn without a synthetic "continue" message by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5030 * ci: allow longer PR review timeout retries by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5961 * feat(desktop): voice dictation in the desktop app by @qqqys in https://github.com/QwenLM/qwen-code/pull/5856 * feat(browser-ext): revive Chrome extension via daemon-direct architecture by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5777 * docs(telemetry): comprehensive documentation update to match current implementation by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5960 * ci(autofix): loosen issue candidate filters so the agent finds work by @qqqys in https://github.com/QwenLM/qwen-code/pull/5860 * feat(loop): inject a .qwen/loop.md task file at fire time via sentinels by @qqqys in https://github.com/QwenLM/qwen-code/pull/5890 * fix(cli): auto-select custom input on Enter in multi-select questions by @Alex-ai-future in https://github.com/QwenLM/qwen-code/pull/5791 * fix(core): only spawn memory recall when auto-memory is enabled by @Minerest in https://github.com/QwenLM/qwen-code/pull/5963 * fix(release): use relative postinstall patch dir by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5973 * docs(qc-helper): add daemon mode docs and fix system settings path by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/5981 * fix(standalone): Route serve shim through cli-entry by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5977 * feat(channels): qwen tag — RFC + Phase 0 (multiplayer channel-resident agent) by @qqqys in https://github.com/QwenLM/qwen-code/pull/5888 * fix(ui): display output tokens instead of cumulative API throughput for subagents by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5972 * fix(cli): Avoid ACP runtime preload on serve fast path by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5989 * fix(web-shell): prefer raw file diffs in tool output by @ytahdn in https://github.com/QwenLM/qwen-code/pull/5992 * [codex] fix daemon specialized model filtering by @callmeYe in https://github.com/QwenLM/qwen-code/pull/5993 * feat(channels): Add channel agent bridge abstraction by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5978 * fix(web-shell): improve follow-up suggestion handling by @ytahdn in https://github.com/QwenLM/qwen-code/pull/5996 * fix(ci): cover release integration regressions by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5994 * feat(core): add --insecure flag to skip TLS verification for self-signed endpoints (#3535) by @TianYuan1024 in https://github.com/QwenLM/qwen-code/pull/5962 * fix(core): filter thought parts from Stop hook last_assistant_message by @DennisYu07 in https://github.com/QwenLM/qwen-code/pull/6009 * feat(cli): add --safe-mode flag to disable all customizations for troubleshooting by @DennisYu07 in https://github.com/QwenLM/qwen-code/pull/4943 * fix(cli): fix thought viewer truncation, layout gaps, and choppy scrolling in VP mode by @chiga0 in https://github.com/QwenLM/qwen-code/pull/6002 * fix(cli): Guard serve fast-path bundle closure by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5995 * feat(daemon): support @extension mentions by @callmeYe in https://github.com/QwenLM/qwen-code/pull/6008 * test(ci): stabilize cron interactive release check by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/6016 * fix(cli): make the non-VP transcript scrollable during multi-agent runs by @chiga0 in https://github.com/QwenLM/qwen-code/pull/6015 * feat(web-shell): friendlier Esc interruption + queued-prompt UX by @carffuca in https://github.com/QwenLM/qwen-code/pull/6025 * feat(daemon,sdk): resumable /acp session stream (Last-Event-ID) + opt-in SDK transports export by @chiga0 in https://github.com/QwenLM/qwen-code/pull/5852 * fix(core): Allow subagents to exit plan mode by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/6026 * feat(ui): add ui.history.collapsePreviewCount to show last N turns when resuming collapsed sessions by @mvanhorn in https://github.com/QwenLM/qwen-code/pull/5848 * feat(core): support glob patterns in mcp.allowed and mcp.excluded by @DennisYu07 in https://github.com/QwenLM/qwen-code/pull/6012 * fix(ci): stabilize merge queue checks by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/6056 * feat(loop): add autonomous mode for a bare /loop by @qqqys in https://github.com/QwenLM/qwen-code/pull/5991 * fix(cli): Keep serve health responsive before runtime load by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/6013 * fix(cli): Handle ACP read_file for managed local paths by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/6021 * Sanitize subagent result tags by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/6027 * Avoid full-history clones in OOM-prone paths by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/6018 * fix(ci): create isolated home before tests by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/6071 * fix(channels): structure DingTalk stream logs by @qqqys in https://github.com/QwenLM/qwen-code/pull/5998 * fix(cli): Support Windows-style tilde paths by @VectorPeak in https://github.com/QwenLM/qwen-code/pull/6029 * Stop repeated invalid tool parameter loops in ACP by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/6076 * feat(web-shell): queue prompts while turns are running by @ytahdn in https://github.com/QwenLM/qwen-code/pull/6005 * ci(workflows): remind authors not to force-push active PRs by @wenshao in https://github.com/QwenLM/qwen-code/pull/6035 * fix(cli): replace all emoji with Unicode text symbols in TUI rendering by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/5999 * feat(web-shell): add mobile sidebar drawer with session list by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/6003 * fix(daemon): resolve ACP permission votes across connections by @chiga0 in https://github.com/QwenLM/qwen-code/pull/5912 * fix(cli): switch TUI prefix ✦→◆ to fix glyph overflow on some terminals by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/5974 * feat(cli): support inline one-shot model override in /model (#5967) by @TianYuan1024 in https://github.com/QwenLM/qwen-code/pull/6022 * fix(core): Parse tagged thinking for GLM responses by @VectorPeak in https://github.com/QwenLM/qwen-code/pull/6033 * feat(cli): Add daemon-managed channel worker for serve --channel by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/6031 * Fix ACP daemon loop review follow-ups by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/6085 * feat(serve): add sessionless workspace remember by @callmeYe in https://github.com/QwenLM/qwen-code/pull/5884 * feat(ui): add mouse click & hover in alternate-screen mode by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/6011 * feat(web-shell): add browser tab favicon by @wenshao in https://github.com/QwenLM/qwen-code/pull/6091 * feat(cli): add /config key=value slash command to set any setting from the prompt by @DennisYu07 in https://github.com/QwenLM/qwen-code/pull/5773 * fix(core): subtract reserved output tokens from context window for compression thresholds by @kagura-agent in https://github.com/QwenLM/qwen-code/pull/5957 * feat(core): Disallow plan lifecycle tools in subagents by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/6087 * fix(cli): validate ask_user_question TUI option input by @russeell in https://github.com/QwenLM/qwen-code/pull/6042 * fix(core): keep plan mode and require approval when plan gate is unavailable by @mvanhorn in https://github.com/QwenLM/qwen-code/pull/6046 * feat(channel): add channel loop support by @qqqys in https://github.com/QwenLM/qwen-code/pull/6073 * fix(deps): clear critical runtime audit findings by @gauravyad86 in https://github.com/QwenLM/qwen-code/pull/6065 * docs: refresh settings, MCP glob, auth alias, and autonomous loop docs by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/6090 * feat(web-shell): polish chat UI and table rendering by @ytahdn in https://github.com/QwenLM/qwen-code/pull/6099 * fix: remove accidentally committed OpenClaw-Query-Submit submodule by @DennisYu07 in https://github.com/QwenLM/qwen-code/pull/6109 * fix(scripts): avoid shell injection in sandbox command detection by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/6108 * ci(autofix): fix scheduled and labeled issue triggers by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/6080 * feat(auto-mode): add classifyAllShell setting to route all shell commands through classifier by @DennisYu07 in https://github.com/QwenLM/qwen-code/pull/6040 * refactor(review): drop deterministic-analysis and autofix steps by @wenshao in https://github.com/QwenLM/qwen-code/pull/6092 * feat(channels): add group history backfill by @qqqys in https://github.com/QwenLM/qwen-code/pull/6074 * feat(daemon): Add session archive support by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/6058 * feat(cli): add tabbed Settings dialog with Status and Stats tabs by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/6044 * feat(core): add configurable idle timeout for MCP tool calls by @DennisYu07 in https://github.com/QwenLM/qwen-code/pull/6061 * fix(web-shell): fix InsightProgress layout and clean up UI elements by @yuanyuanAli in https://github.com/QwenLM/qwen-code/pull/6115 * ci: stabilize actionlint on self-hosted runners by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/6113 * fix(daemon): Route ACP images through the vision bridge by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/6111 * fix(ci): stabilize Windows loop tests by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/6082 * fix(cli): load browser MCP tools by default by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/6006 * fix(model): disambiguate vision model endpoints by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/6070 * [codex] Add explicit channel memory for messaging channels by @qqqys in https://github.com/QwenLM/qwen-code/pull/6051 * test(core): fix MCP idle timeout config stubs by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/6120 * feat(cli): Harden daemon-managed channel worker by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/6098 * fix(web-shell): defer session creation until first prompt by @ytahdn in https://github.com/QwenLM/qwen-code/pull/6066 * docs: document model/auth settings, /model --vision, and --safe-mode by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/6028 * fix(cli): clip live markdown to the viewport to stop non-VP scrollback replay by @chiga0 in https://github.com/QwenLM/qwen-code/pull/6081 * ci: add fork PR safety precheck by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5926 * feat(serve): support HTTPS/TLS via --tls-cert and --tls-key flags by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/6032 * fix(cli): yield to React after addItem to reduce input lag by @Alex-ai-future in https://github.com/QwenLM/qwen-code/pull/6059 * ci: persist npm cache on self-hosted runners by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/6130 * feat(cli): show description and level in /skills ACP output by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/6117 * fix(diff): show whitespace-only edits instead of 'No changes detected' by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/6141 * Add compact session timeline rail by @callmeYe in https://github.com/QwenLM/qwen-code/pull/6078 * feat(core,cli): unified reasoning effort with /effort command by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/6072 * feat(core): Add leader approval for plan-required teammates by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/6138 * fix(ci): grant PR review precheck permissions by @wenshao in https://github.com/QwenLM/qwen-code/pull/6147 * fix(ci): list workflow comments with GET by @wenshao in https://github.com/QwenLM/qwen-code/pull/6148 * fix(ci): use CI_BOT_PAT for precheck comment on fork PRs by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/6151 * fix(cli): Avoid blocking WebUI sessions on MCP readiness by @BZ-D in https://github.com/QwenLM/qwen-code/pull/6161 * fix(ci): allow prechecked fork PR automation by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/6160 * fix(ci): fall back to latest autofix sandbox image by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/6159 * fix(ci): create precheck comments via REST by @wenshao in https://github.com/QwenLM/qwen-code/pull/6156 * fix(web-shell): show skill slash commands (e.g. /review) before first prompt by @wenshao in https://github.com/QwenLM/qwen-code/pull/6153 * docs: document the /config slash command by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/6145 * fix(web-shell): only show scroll-to-bottom button when content overflows by @ytahdn in https://github.com/QwenLM/qwen-code/pull/6150 * fix(web-shell): improve disconnected composer handling by @ytahdn in https://github.com/QwenLM/qwen-code/pull/6166 * fix(ci): diagnose autofix publish credentials by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/6162 * fix(release): reduce npm package scan triggers by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/6164 * fix(channels): replace setTimeout(0) drain with turn_complete SSE barrier by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/6165 * feat(channels): add DingTalk proactive send for channel loops by @qqqys in https://github.com/QwenLM/qwen-code/pull/6174 * fix: lazy-load memory prompt when indexes are empty (#6097) by @kagura-agent in https://github.com/QwenLM/qwen-code/pull/6104 * feat(channels): add identity and task lifecycle metadata by @qqqys in https://github.com/QwenLM/qwen-code/pull/6105 * feat(core): add retry with backoff for MCP capability discovery by @DennisYu07 in https://github.com/QwenLM/qwen-code/pull/6158 * fix(cli): skip MCP approval dialogs in YOLO mode by @qwen-code-dev-bot in https://github.com/QwenLM/qwen-code/pull/6177 * feat(channels): add listSessions to ChannelAgentBridge by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/6182 * ci: Add prepare-pr skill for autofix PR bodies by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/6184 * feat(channels): show lifecycle status in adapters by @qqqys in https://github.com/QwenLM/qwen-code/pull/6114 * fix(serve): keep skill slash commands available when the ACP child is unavailable by @wenshao in https://github.com/QwenLM/qwen-code/pull/6169 * fix(web-shell): polish session timeline rail by @callmeYe in https://github.com/QwenLM/qwen-code/pull/6171 * test: stabilize plan mode tool-control E2E by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/6176 * fix(web-shell): mobile UX — safe areas, overscroll, native-app feel by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/6142 * feat(web-shell): overhaul list-dialog interaction, keyboard nav & a11y by @carffuca in https://github.com/QwenLM/qwen-code/pull/6128 * feat(cli): add credential redaction for worker stderr forwarding by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/6146 * fix(cli): drop /effort tier autocompletion for an argument-hint placeholder by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/6179 * fix(ci): limit fork PR precheck to safety signals by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/6178 * fix(web-shell): cut mobile session-switch jank (memoized timeline signature, replay-first dispatch) by @qqqys in https://github.com/QwenLM/qwen-code/pull/6183 * fix: resolve macOS seatbelt profile path from bundle dir, not chunks/ by @mvanhorn in https://github.com/QwenLM/qwen-code/pull/6172 * fix(cli): add bootstrap fast paths by @gauravyad86 in https://github.com/QwenLM/qwen-code/pull/6188 * fix(core): Reduce multimodal history payload size by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/6045 * fix(core): prevent subagent crash when ${hook_context} placeholder has no hook configured by @DennisYu07 in https://github.com/QwenLM/qwen-code/pull/6180 * ci(release): optimize validation steps by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/6133 * feat(core): add dataviz bundled skill by @qqqys in https://github.com/QwenLM/qwen-code/pull/6198 * docs: correct stale CLI flags/keybinding and document model.reasoningEffort by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/6219 * fix(scheduler): add opt-in per-tool-call execution timeout by @wenshao with @Copilot in https://github.com/QwenLM/qwen-code/pull/6136 * feat(core): allow sub-agents to spawn nested sub-agents up to a configurable depth by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/6189 * fix(web-shell): keep the user-selectable wrapper out of flex layout by @carffuca in https://github.com/QwenLM/qwen-code/pull/6229 * feat(web-shell): add daemon UI support for vision model selection by @AmariahAK in https://github.com/QwenLM/qwen-code/pull/6209 * fix(core): raise stream idle timeout default and hint the env knob by @mvanhorn in https://github.com/QwenLM/qwen-code/pull/6107 * feat(cua-driver): sync vendored cua-driver 0.6.8 → 0.7.0 by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/6212 ## New Contributors * @Minerest made their first contribution in https://github.com/QwenLM/qwen-code/pull/5963 * @gauravyad86 made their first contribution in https://github.com/QwenLM/qwen-code/pull/6065 * @AmariahAK made their first contribution in https://github.com/QwenLM/qwen-code/pull/6209 **Full Changelog**: https://github.com/QwenLM/qwen-code/compare/cua-driver-rs-v0.6.8...cua-driver-rs-v0.7.0