DeepSeek Harness releases v0.2.2-alpha.3 pre-release, expanding code review and automation tasks
DeepSeek Harness has updated its GitHub repository, launching the v0.2.2-alpha.3 pre-release version, expanding around code review, automated task management, the SDK, and the plugin ecosystem. It adds an experimental unified entry point for change requests and worktrees, allowing local code and PR diffs to be viewed in the file tree; after selecting a code snippet and adding a comment, it can be handed to the Agent for processing. It also adds a multi-file modification tool apply_patch, which is disabled by default and must be manually enabled. Automated task management has been moved up to the Host layer, supporting manual creation, direct editing, and executing tasks in newly created or reused sessions. This version is still a pre-release, and the official desktop installer package for it has not yet been provided.
Why read this
AI score 60
The original article breaks down item by item the specific changes in this pre-release version regarding code review, task scheduling, and the SDK, which can be used to assess how complete the Agent development workflow has become.
Topics
Body · AI translation
DeepSeek "Updates Whenever It Crashes": Harness Releases a New Version Again
Zhidongxi Download the App | Exclusive First Look November 4, 2026, 16:40:43 | From Beijing
Zhidongxi reported on November 4 that yesterday, DeepSeek Harness quietly updated its GitHub repository and released a v0.2.2-alpha.3 pre-release version.
This update expands on code review, automated task management, the SDK, and the plugin ecosystem.
Interestingly, just yesterday DeepSeek experienced partial outages of its web and API services.
Given DeepSeek's "glorious track record" of releasing an update every time it crashes, although there is no evidence directly linking the two events, netizens still speculated one after another about whether a new model was coming.
Sure enough, the "updates whenever it crashes" rule proved all too reliable.
In this update, DeepSeek Harness added an experimental unified entry point for "change requests and worktrees," allowing users to view local code and PR diffs through a file tree and hand selected code snippets and comments to the Agent for processing.
Automated tasks have also been upgraded to host-level unified management, supporting manual creation, direct editing, and task execution in both new and old sessions.
In addition, DeepSeek Harness added a multi-file modification tool, apply_patch, and further improved the capabilities of the Python and TypeScript SDKs.
1. More Convenient Code Review: DeepSeek Harness Optimizes Development Collaboration
In real software development, code generation is only one part of the process; developers also need to check modifications, handle code diffs, follow up on review comments, and ensure code can be merged smoothly.
In this update, DeepSeek Harness introduced an experimental unified entry point for "change requests and worktrees," integrating code review and Git Worktree-related operations together.
Specifically, developers can browse local code and PR diffs through a searchable file tree and view modifications file by file. After finding issues, they can select specific code snippets, add comments, and hand this information to the Agent for processing.
At the same time, this feature also supports tracking check and review status.
This allows developers to view code changes, raise modification suggestions, and let the Agent continue processing based on feedback, all within the same entry point, reducing the need to switch between different tools.
Another noteworthy update is the addition of the apply_patch tool.
In the past, when an Agent modified multiple files, it often had to perform file reading, editing, and other operations separately. The newly added apply_patch supports users in completing the addition, editing, deletion, and moving of multiple files through a single call, and the modification results can also be viewed in Review.
However, this tool is disabled by default and needs to be actively enabled by users.
These two updates mean that after an Agent modifies code, developers can directly check changes and raise comments in DeepSeek Harness, then let the Agent continue adjusting, making the connection between code modification and review smoother.
2. Unified Management of Automated Tasks Lets Agents Work Continuously Across Sessions
In addition to code development, DeepSeek Harness also made fairly noticeable adjustments to automated tasks in this update.
Previously, automated tasks were more closely associated with the execution process in specific sessions. In this update, DeepSeek Harness unified automated task management at the Host layer, supporting users in manually creating tasks or directly editing existing tasks, and users can also create tasks in sessions through prefilled prompts.
In terms of execution, users can choose to reuse an existing session or create a new session to execute tasks. In addition, when editing tasks, drafts and conflict review are supported to prevent content from being accidentally overwritten during editing.
This means automated task management is no longer limited to a single session; users can manage it from a higher level and arrange for Agents to execute work in different sessions as needed.
For development tasks that require repeated processing, this change can reduce the operations of repeatedly entering instructions and manually starting tasks.
3. SDK and Plugins Continue to Expand, Mobile Experience Optimized
The expansion of SDK and plugin capabilities mainly concerns how developers build their own Agent applications based on DeepSeek Harness.
In this update, DSH further improved the TypeScript and Python SDKs, completing native command and plugin management capabilities, including three functions: plan review, goal continuation, and operation approval.
Among them, plan review allows users to approve, modify, or cancel plans submitted by the Agent; goal continuation supports saving long-term goals and continuing to advance them after a session is restarted, resumed, or forked; and operation approval means the SDK receives approval requests from the Agent and then hands them to the integrated application to decide whether to approve.
On the plugin side, this update allows plugins to provide navigation icons for their own settings pages, and also supports dynamically providing API request headers based on session identity and request purpose.
In addition, when plugin installation fails, more complete diagnostic information and a Host log entry are now provided to help developers locate problems.
In addition to the developer ecosystem, DSH is also continuously improving the mobile experience, optimizing sidebar navigation and narrow-screen layouts. However, the "mobile" here is not a standalone App; it refers to accessing the Web GUI through a mobile browser.
In terms of interaction and file management, DSH has also made adjustments: it unified the right-click menus and keyboard menus for sessions, workspaces, and the sidebar, and opened up developer extension capabilities; file preview now adds a persistent directory tree, making it easier for users to quickly locate and switch files.
In addition to the above features, DSH also optimized the display of Trajectory call records this time, supporting independent collapsing of sub-calls, while improving the performance of streaming assembly for long replies.
In terms of bug fixes, the new version resolves issues such as historical sessions failing to open, session search failing, chat history loading getting stuck, and some models continuously failing requests when the number of images exceeds the request limit.
In addition, the new version also adjusted the file modification security policy: the read check before file modification and protection against external modifications are disabled by default, while sandbox restrictions and the Review mechanism remain in place.
Final Thoughts:
It should be noted that v0.2.2-alpha.3 is still a pre-release version, and the official corresponding desktop installation package has not yet been provided, so existing desktop App users cannot directly upgrade to this version for the time being.
Overall, this update shows that DSH is filling in multiple links needed for Agents to participate in software development, from code modification and diff review to task scheduling and plugin expansion, gradually forming a more complete development workflow.
"Special Statement: The above content (including videos, pictures, and audio if any) is uploaded and published by users of "Dafeng Hao," a self-media platform under Phoenix Net. This platform only provides information storage space services.
Notice: The content above (including the videos, pictures and audios if any) is uploaded and posted by the user of Dafeng Hao, which is a social media platform and merely provides information storage space services."