creatixchu ba30b73f7b refactor(attachment): 求解器留在 llm-deepseek,存储层只接收目标尺寸
ImageRequestPolicy 改为 ImageRequestTarget,只含目标宽、高和字节目标;dsh-attachment 删除 token-grid 投影联合和 tokenGridProjection,只保留提供方无关的 requestImageDimensions 与 longEdgeDimensions。v41 求解器回到 llm-deepseek 的 image-tokens.ts,新增 deepSeekRequestImageDimensions,resolveRequestImageTarget 为每张图算出目标并加 4096 单边上限;pi-ai 路由按自身像素预算推导目标。

按 review 意见修正:v41 计价 Note 里已删除常量的过期句子就地改写;ProjectedDimensions 登记到 attachment 子系统页与 type-equiv 清单;Note 区分发送尺寸与提供方补齐后的网格;短边取整的措辞改为「按路由预测」。
2026-09-10 16:46:28 +08:00
…
…
…
2026-09-10 11:49:17 +08:00
…

DeepSeek Harness

English | 中文

DeepSeek Harness (dsh) is an open-source agent harness developed by DeepSeek AI.

It is built on an everything-is-a-plugin architecture and powered by Cordis, whose design is described in A Programming Paradigm for Spatiotemporal Composability.

Documentation: https://deepseek-harness.github.io/deepseek-harness/

Developer preview

DeepSeek Harness is in developer preview and iterating rapidly. THERE WILL BE COMPATIBILITY-BREAKING CHANGES.

Review the safety notice before running the project.

Run

Run from npm

Install Node.js, then run:

npx @deepseek-ai/dsh web

The command starts the Web UI at http://127.0.0.1:3080 by default and opens it in the default browser for a local launch. An SSH launch only prints the host URL because the SSH client or editor owns the local forwarded address. Pass --no-open to run the server without opening a browser. See Web UI guide.

Run from source

To run from a repository checkout:

git clone https://github.com/deepseek-ai/deepseek-harness.git
cd deepseek-harness
pnpm install
pnpm run build
pnpm dsh web

pnpm run build prepares the repository artifacts. pnpm dsh web uses those built artifacts without rebuilding.

Community and support

Contributing

See CONTRIBUTING.md.

Development

Start with the development guide and architecture documentation.

For agents, follow AGENTS.md.

Citation

@misc{deepseek-harness2026,
  title={DeepSeek Harness: Everything is a Plugin},
  author={DeepSeek-AI},
  year={2026},
  publisher={GitHub},
  howpublished={\url{https://github.com/deepseek-ai/deepseek-harness}},
}

License

MIT

Third-party dependencies and their licenses are disclosed in THIRD_PARTY_NOTICES.md.

S
Description
Trusted, immutable container builds of DeepSeek Harness (dsh) from the official npm release. Upstream mirror + scheduled CI.
https://github.com/deepseek-ai/deepseek-harness Readme MIT
568 MiB
0 Stars 1 Watchers 0 Forks
v0.2.1-rc.4
Latest
2026-10-28 03:37:33 -04:00
Languages
JavaScript 60.4%
Shell 27.4%
Dockerfile 12.2%