Qwen Code v0.19.4

<!-- Release notes generated using configuration in .github/release.yml at release/v0.19.4 --> ## What's Changed * 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 ## New Contributors * @Minerest made their first contribution in https://github.com/QwenLM/qwen-code/pull/5963 * @TianYuan1024 made their first contribution in https://github.com/QwenLM/qwen-code/pull/5962 * @gauravyad86 made their first contribution in https://github.com/QwenLM/qwen-code/pull/6065 **Full Changelog**: https://github.com/QwenLM/qwen-code/compare/v0.19.3...v0.19.4