Qwen Code Files

What's Changed

• fix(ci): make shared ECS Vitest concurrency tunable by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/10667
• feat(cli): OpenTUI migration batch 4 — dialogs, commands, and session-rewind by @chiga0 in https://github.com/QwenLM/qwen-code/pull/10383
• feat(goal): let the model propose a Goal the user approves in a dialog by @qqqys in https://github.com/QwenLM/qwen-code/pull/10171
• fix(web-shell): persist model reasoning preferences by @callmeYe in https://github.com/QwenLM/qwen-code/pull/10489
• feat(web-shell): Add standalone chats by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/10514
• fix(ci): keep web-shell visuals comment on upload failure by @AaronZ345 in https://github.com/QwenLM/qwen-code/pull/10253
• fix(permissions): never let the AUTO-mode classifier auto-approve out-of-workspace writes; always fall back to manual approval by @PratikWayase in https://github.com/QwenLM/qwen-code/pull/8744
• fix(review): gate decided stops on a composed re-rule verdict by @wenshao in https://github.com/QwenLM/qwen-code/pull/10310
• fix(sdk): stop emitting a duplicated hashbang in the serve-mcp bin by @wenshao in https://github.com/QwenLM/qwen-code/pull/10485
• feat(cli): hot-reload modelProviders without session restart by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/10582
• fix(cli): keep hardware cursor aligned after layout changes by @liujiayi771 in https://github.com/QwenLM/qwen-code/pull/10417
• test(integration): remove flaky ACP recall timing check by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/10703
• perf(ci): shard release quality checks by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/10619
• feat(web-shell): add an experimental session workflow cockpit by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/8583
• fix(cli): Defer provisional standalone reasoning options by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/10706
• feat(web-shell): search conversation content in the sidebar session search by @wenshao in https://github.com/QwenLM/qwen-code/pull/10612
• feat(opentui): Add the backend composition root (Batch 5) by @chiga0 in https://github.com/QwenLM/qwen-code/pull/10696
• docs(design): Align OpenTUI migration notes with the landed batches by @chiga0 in https://github.com/QwenLM/qwen-code/pull/10724
• fix(cli): abort subagent generation on unmount by @AaronZ345 in https://github.com/QwenLM/qwen-code/pull/9937
• feat(web-shell): add a Workspaces overview panel by @wenshao in https://github.com/QwenLM/qwen-code/pull/10589
• feat(review): prebuild the review worktree before any agent runs by @wenshao in https://github.com/QwenLM/qwen-code/pull/10423
• fix(web-shell): remove duplicate language declaration in ChatEditor.test.tsx by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/10729
• fix(autofix): clamp gate test load explicitly instead of via RUNNER_NAME by @qqqys in https://github.com/QwenLM/qwen-code/pull/10671
• ci(ecs): file an issue when the runner fleet update fails by @wenshao in https://github.com/QwenLM/qwen-code/pull/10445
• fix(java): make SDK worker threads daemon by @AaronZ345 in https://github.com/QwenLM/qwen-code/pull/9925
• feat(web-shell): declutter the workspace sidebar and add loopback open actions by @wenshao in https://github.com/QwenLM/qwen-code/pull/10606
• fix(core): support hybrid thinking streams for Qwen3 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/9607
• feat(external-context): Publish the Mem0 Extension package by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/10653
• fix(web-shell): reconcile queued prompts across clients by @ytahdn in https://github.com/QwenLM/qwen-code/pull/10704
• feat(core): bind PRs created via gh pr create in the session shell by @wenshao in https://github.com/QwenLM/qwen-code/pull/9739
• fix(ci): retry transient sandbox:none E2E shard failures once (#10566) by @qwen-code-dev-bot in https://github.com/QwenLM/qwen-code/pull/10572
• fix(web-shell): proxy standalone/live daemon routes in vite dev by @wenshao in https://github.com/QwenLM/qwen-code/pull/10748
• test(ci): make web-shell visuals publish stub module-safe (#10736) by @qwen-code-dev-bot in https://github.com/QwenLM/qwen-code/pull/10738
• feat(web-shell): group scheduled task run sessions by @qqqys in https://github.com/QwenLM/qwen-code/pull/10611
• feat(cli): add /output-style command with picker and mid-session switching by @qqqys in https://github.com/QwenLM/qwen-code/pull/10683
• feat(ipc): authenticate cross-session inbox connections with per-session tokens by @qqqys in https://github.com/QwenLM/qwen-code/pull/10636
• feat(qwen-live): ACP backend adaptor and multi-backend routing — M4 by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/10617
• feat(opentui): Activate the OpenTUI backend behind QWEN_TUI_RENDERER by @chiga0 in https://github.com/QwenLM/qwen-code/pull/10739
• fix(core): validate git pull option combinations and detached HEAD by @wenshao in https://github.com/QwenLM/qwen-code/pull/10752
• fix(channels): apply approval mode to standalone sessions by @qqqys in https://github.com/QwenLM/qwen-code/pull/10715
• fix(cli): route the /output-style dialog in the OpenTUI registry by @wenshao in https://github.com/QwenLM/qwen-code/pull/10763
• fix(serve): keep prompt-turn failure logs from degrading to [object Object] by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/10732
• fix(acp-bridge): backpressure ACP NDJSON queue saturation instead of tearing down the channel by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/10731
• fix(ci): isolate and bound release validation workloads by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/10765
• fix(workflow): tighten multi-workspace state boundaries by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/10772
• test(core): rescale the shell-safety CPU budget to the metric it measures by @TianYuan1024 in https://github.com/QwenLM/qwen-code/pull/10735
• fix(vscode): stop webview bundle test timing out under CI contention (#10665) by @qwen-code-dev-bot in https://github.com/QwenLM/qwen-code/pull/10672
• fix(release): raise prepared package size budget to 112 MiB (#10774) by @qwen-code-dev-bot in https://github.com/QwenLM/qwen-code/pull/10781
• fix(core): skip non-regular files in usage history transcript replay by @qqqys in https://github.com/QwenLM/qwen-code/pull/10681
• feat(ipc): give the session's own processes a child token the inbound gate recognizes by @qqqys in https://github.com/QwenLM/qwen-code/pull/10764
• feat(opentui): bundle assets, CI matrix and parity tooling (Batch 7) by @chiga0 in https://github.com/QwenLM/qwen-code/pull/10770
• fix(cli): stop the ctrl+s hint advertising shell-cap hidden lines by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/10657
• fix(web-shell): keep the sidebar New task on a workspace by @wenshao in https://github.com/QwenLM/qwen-code/pull/10777
• fix(serve): keep the Conversations runtime outside the workspace registration limit by @wenshao in https://github.com/QwenLM/qwen-code/pull/10759
• feat(daemon): name the saturated NDJSON budget in channel-teardown diagnostics by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/10727
• fix(cua): restore legacy Windows installer compatibility by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/10792
• fix(triage): make Stage 1-pre subsumption check large-file safe by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/10396
• fix(web-shell): Load models for fresh standalone sessions by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/10719
• fix(core): recover from gateway 400 on media-bearing OpenAI requests by degrading the media by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/10699
• fix(ci): keep worker tests responsive under ECS contention by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/10813
• fix(ci): classify the CI profile from the trusted base SHA by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/10799
• fix(cli): align OpenTUI output-style behavior by @qqqys in https://github.com/QwenLM/qwen-code/pull/10806
• feat(qwen-live): protocol v7 playback receipts and interactive init — M5 by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/10769
• docs(readme): add versioned SWE-bench scores by @DennisYu07 in https://github.com/QwenLM/qwen-code/pull/10808
• fix(cli): show active scheduled tasks at session start by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/10053
• fix(ci): stop stable releases from disabling per-workspace test retries by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/10803
• fix(release): stop hiding sandbox build failures and check the prepared package early by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/10784
• feat(release): add gated bun/OpenTUI preview flavor to standalone releases by @chiga0 in https://github.com/QwenLM/qwen-code/pull/10814
• fix(core): craft the hard-link tar fixture instead of packing it by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/10801
• fix(release): cap Vitest workers in the quality_scripts lane (#10755) by @qwen-code-dev-bot in https://github.com/QwenLM/qwen-code/pull/10760
• feat(channels): expose BTW through agent bridges by @qqqys in https://github.com/QwenLM/qwen-code/pull/10712
• fix(web-shell): keep a manual session name across /clear (#8977) by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/9260
• fix(ci): Take the OpenTUI interactive e2e leg out of CI by @chiga0 in https://github.com/QwenLM/qwen-code/pull/10829
• fix(live-host-release): correct setup-node action SHA by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/10827
• fix(web-shell): Reload models for repeated new tasks by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/10824
• fix(goal): stop exporting the unreachable propose_goal decline message by @qqqys in https://github.com/QwenLM/qwen-code/pull/10787
• fix(ci): stop heartbeat mint-skip test racing loop startup by @qwen-code-dev-bot in https://github.com/QwenLM/qwen-code/pull/10527
• fix(dws): isolate direct-message ingestion across conversations by @qqqys in https://github.com/QwenLM/qwen-code/pull/10691
• fix(web-shell): preserve slash command attachments by @ytahdn in https://github.com/QwenLM/qwen-code/pull/10730
• feat(serve): add workspace-scoped MCP management by @ytahdn in https://github.com/QwenLM/qwen-code/pull/10679
• fix(channels): prune selections when workspaces are removed by @qqqys in https://github.com/QwenLM/qwen-code/pull/10796

New Contributors

• @liujiayi771 made their first contribution in https://github.com/QwenLM/qwen-code/pull/10417

Full Changelog: https://github.com/QwenLM/qwen-code/compare/cua-driver-rs-v0.20.3...live-host-v0.2.0