Skip to Content
BlogFeature Updates11-19 Product Update

Qwen Code Weekly: New Flagship Qwen4-Max Is Available, Parallel Sessions Work in Their Own Worktrees, Task Results Go Straight to Feishu/WeCom/DingTalk Groups

Qwen Team
2026-11-19

Qwen Code shipped three stable releases this week — v0.27.3 through v0.28.0.

New flagship Qwen4-Max is available. Qwen’s new flagship model, wired into the latest Qwen Code.

New sessions work in their own copy by default. Run several sessions on one project in parallel — each edits its own worktree, and the branch and files in your hands stay untouched.

Task results go straight to Feishu, WeCom, and DingTalk groups. Add a custom bot to the group, paste its webhook URL into Web Shell, and notifications and scheduled-task results land in the group.

✨ New Features

New Flagship Qwen4-Max Is Available

Qwen4-Max is Qwen’s new-generation flagship model. The official release went live on November 16; it handles text, images, and video, and targets complex reasoning, coding, and agent tasks.

Qwen Code completed the integration this week. Qwen4-Max is available whether you connect through Model Studio (Bailian), QwenCloud, a Qwen subscription, or another channel. Thinking depth comes in three tiers — low, high, and xhigh — defaulting to high, and you can turn thinking off.

Send images and video straight into the conversation for it to understand. The Model Studio (Bailian) and QwenCloud channels add two token-saving settings: cache retention can extend from the default 5 minutes to 1 hour, and image detail can be turned down.

What you can do:

  • Attach a design screenshot and have it build the page
  • Send a screen recording and have it lay out the bug’s reproduction steps
  • Raise the thinking effort when a test failure is hard to pin down

See PR #17513 

Qwen4-Max in the model list and the thinking depth tiers

New Sessions Run in Their Own Worktree by Default

New Web Shell sessions in a trusted Git workspace work in their own worktree by default. A worktree is another working copy of the same repository: commit history is shared, files are separate. Run several sessions on one project in parallel — each edits its own copy, nothing overwrites anything else, and the files you’re editing stay untouched.

When the work is done, collect the results two ways: click “Create branch here” in the branch menu to turn it into a regular branch, or click “Hand off to local” to bring the changes back to your original directory.

Prefer the current branch? Set worktree.defaultForNewSessions to false and new sessions work there directly.

What you can do:

  • Open a session per feature and work on several at once — no overwrites
  • Keep coding locally while the AI edits its own copy — the two never collide
  • Try two refactoring approaches in two sessions and compare them

See PR #17228 

Worktree mode for new Web Shell sessions and the branch menu

Send Task Results Straight to Feishu, WeCom, and DingTalk Groups

Feishu, WeCom, and DingTalk each gain a Webhook (send only) connection type. Add a custom bot to the group, paste its webhook URL into channel management in Web Shell, and notifications, task results, and scheduled-task results land in the group as Markdown messages.

This connection sends one way — it does not receive group messages. To chat with the AI in a group, use the platform’s existing bot connection type.

What you can do:

  • Schedule a task to summarize yesterday’s merged PRs at 9 every morning — the result posts to your Feishu project group automatically
  • Have the AI run regression tests every night and post the results to a WeCom group — read them as you start work
  • Set a completion notification on a long task — it posts to the DingTalk group when done, so teammates see the progress too

See PR #16804 , #17013 , #17224 

The Feishu Webhook setup page in Web Shell and the message in the group

Web Shell: Review Changes Before Delivery, Watch Background Tasks Run

A Change Overview shows how much a session changed. When the work is done and you’re ready to deliver, the right-side panel’s new Change Overview lists files and added/deleted lines in three groups: uncommitted changes, each bound PR, and the remaining commits. See PR #17378 

Click a badge to open a background task. Small badges sit above the input box — one each for running workflows, shells, monitors, and background agents. Click one to jump to its execution view. See PR #16813 

Filter sidebar sessions by workspace and date. The sidebar filters by workspace, and sessions group by activity date — narrow the range first, then find the session. See PR #17244 , #17447 

Other improvements. Each reply shows how many hooks fired, how many were blocked, and how long they took (#17015 , #17327 ); the Russian interface translation is complete (#17414 ); session search results are clearer, with up/down keyboard selection (#16779 ).

The Change Overview panel and background task badges in Web Shell

📊 More New Features

Sessions can hand work to another workspace. With Web Shell managing several workspaces, a session can delegate a task to another workspace, run it under that workspace’s instructions and settings, and bring the result back — you can keep asking follow-ups. The first delegation needs your confirmation. See PR #17454 , #17484 

Bind a PR by hand, and offline comments merge into one summary. When auto-binding misses a PR, type /pr <number or link> to bind it — a Bind PR button also sits in the Web Shell session overview and the sidebar menu. If the service was down for a while, comments that piled up on bound PRs arrive as a single merged summary when it starts again. See PR #16877 , #17199 

The /memory panel edits settings. In the terminal’s /memory panel, toggle auto-save and periodic cleanup directly, and open user-level and project-level memory files for editing. See PR #17213 

The Goals page shows goals from every workspace. With several workspaces registered, goals from all trusted workspaces gather on one page, sorted by time, each card labeled with its workspace. When you create a goal, pick which workspace it goes into. See PR #17230 

Mods plugins can rewrite thinking content. A plugin can rewrite expanded thinking blocks the same way it rewrites reply text in the terminal — say, translating the thinking into Chinese. Both terminal UIs support it. See PR #16873 , #17443 

Web Shell works over plain HTTP. Open Web Shell from another computer at http://<computer-IP>:<port> and the terminal tab, web preview, and local commands all work. See PR #17196 

GitLab channels can be set up in Web Shell. The repository whitelist supports multi-level project paths like group/subgroup/project. See PR #16845 

👏 Experience Improvements

Compaction keeps the latest full operation intact. When a long conversation triggers compaction, the most recent operation and its result stay verbatim; only earlier history gets summarized. See PR #17141 

Stash or discard uncommitted changes without leaving the page. When a branch switch hits uncommitted changes, choose to stash or discard them right there and continue. See PR #17364 

Goal card states read at a glance. Running shows blue; waiting on you shows amber. Goals with limits get progress bars for turns, tokens, and time, and long goal text in a session collapses to one line. See PR #17349 , #17133 

The usage dashboard opens faster. It lives on the Web Shell status page. See PR #17239 

Selection popups highlight the current tier. The thinking-depth popup shows at a glance which tier is selected; the model list and the execution-mode picker do the same. See PR #16622 

Session renames take effect immediately. Confirm, and the new title shows right away. See PR #17006 

🔧 Important Fixes

FixWhat it means for youPR
Auto mode treated “looks related” as “you agreed” and auto-approved dangerous operationsDeleting results, discarding changes, and rewriting shared history now pass only on your explicit request; under auto-edit, permissions.ask rules apply to subagents too; git commit --amend opens a dialog for your approval; Full Access shows red both in the approval panel and after selection#16858 , #16932 , #16075 , #16874 , #17100 
Edit’s recovery matching broke syntax on non-ASCII text and escapesRecovery matching works and leaves escape sequences intact#17096 , #17152 
An unconfirmed message from another session locked the input boxThe input box stays editable, and that message can be retried or discarded#17140 
Buffered output was lost when a command process endedThe output is kept#17112 
The execution approval dialog showed commands incompletelyThe full command is kept#17361 
AUTO mode looked up links as local filesHTTP(S) links no longer trigger file lookups, and the network-lookup delay on Windows is gone#17127 
WeChat QR sign-in aborted when QR generation was slowSign-in uses a longer timeout, so login completes even when the QR code takes 30 seconds to generate#16838 
Grep didn’t recognize ripgrep regex syntaxNative ripgrep syntax works directly#14315 
The CLI crashed on startup in Docker/PodmanThe sandbox home directory is created automatically, so startup works even without $HOME#16878 
The process lingered after /quitThe exit command completes cleanly#17148 
Voice input sent before dictation finishedDictation finishes first, then the message sends#17331 
GitHub channel replies queued after rate limiting retried only at startupRetries also run in the background while the channel is running#16839 
Subagent context usage was measured against the main session’s windowIt’s measured against the subagent’s own model window, so the percentage is accurate#13614 
/effort listed tiers the current model doesn’t supportOnly tiers the current model supports are shown#17425 

👥 Contributors

ContributorContributionsPR Links
🆕 @Afloat16 🎉 First contribution: Java SDK error correlation and transcription performance, SDK timeout and reconnect fixes, CLI task selection, todo snapshots, auth dialogs, shell output retention, and other hardening#17103 , #17106 , #17107 , #17109 , #17110 , #17111 , #17112 , #17113 , #17115 , #17118 , #17121 , #17122 , #17124 , #17125 , #17126 
@2SinceJuly Agent loop switch supports force-off, lazy-fetch tests for the managed runtime#17048 , #16492 
@521Peter Docs for the Skill endpoint that updates workspace settings by name#16833 
@dakjdakd Grep supports native ripgrep regex syntax#14315 
@MohammedAlkindi Acceptance tests for managed hook descriptions and status messages#17393 
@now-ing Cleanup of remaining CVE audit issues in dependencies#10985 
@Shizoqua Subagent context usage measured against its own model window#13614 
@tonydzi Leader delivery and final-state characterization tests#14855 
@yanyukang2003-ux AUTO mode judges by explicit user authorization#16858 
🆕 @0xvincent 🎉 First contribution: Qwen Code 1.0 Preview entry added to the README#16872 
🆕 @EminBudak 🎉 First contribution: Wiro AI integration docs#16850 
🆕 @LubabaKhalid 🎉 First contribution: vulnerable dependencies updated#13169 
🆕 @pranavshankar1221 🎉 First contribution: current tier highlighted in selection popups#16622 

Upgrade: Run npm i @qwen-code/qwen-code@latest -g to upgrade to the latest version.

If you have questions or feedback, feel free to open an issue on GitHub Issues !

Last updated on