feat: add the dsh-superagent research prototype

This commit is contained in:
DeepSeek Harness Team
2026-10-31 20:05:39 +08:00
commit 6337fc823c
216 changed files with 37068 additions and 0 deletions
+39
View File
@@ -0,0 +1,39 @@
# dsh-superagent
> **Research prototype for reference only, not an official DeepSeek product.** This code grew out of our team's day-to-day development work, with much of the engineering done by coding agents. Treat it as research code, not production-ready software. It may still contain bugs, and its coding style and engineering practices may be inconsistent. Review and adapt it before using it in your own environment.
>
> We have adapted it for publication, so it is not identical to our internal version or the implementation described in *Exploring Super-agent Design: Towards a More Autonomous Agent System*. Some designs discussed in the article are directions for future development and are not implemented in this prototype.
dsh-superagent is a proactive coding agent for one GitHub repository, packaged as a bundle for [DeepSeek Harness](https://www.deepseek.com/en/harness/). It listens to GitHub and, optionally, Feishu. When someone allowed asks the agent for work, it opens a work item, works on it in its own agent session and directory, and answers in the original conversation, for example with a pull request. A web panel shows what needs a person.
It is also a way of working with an agent: **take as little human attention as possible, and give as much value as possible.** An agent that can act for a whole team can also waste a whole team's attention, so it acts only when asked or when a rule the team wrote allows it, and speaks only when someone must act or can use a result. [docs/000-philosophy.md](docs/000-philosophy.md) explains the principle and what it asks of the operator.
## Setup
Setup has many steps, so an agent does it with you. Ask your coding agent:
> Read SETUP.md in this repository and set up dsh-superagent with me.
It asks one short question at a time, shows the full plan once, and then installs and configures everything. [SETUP.md](SETUP.md) is what it follows.
## Documentation
Read the numbered documents in order; each builds only on the ones before it.
- [000 Philosophy](docs/000-philosophy.md)
- [001 Domain model](docs/001-domain.md)
- [002 Authorization](docs/002-authorization.md)
- [003 Execution](docs/003-execution.md)
- [004 Prompts](docs/004-prompts.md)
- [005 Panel](docs/005-panel.md)
- [006 Deployment](docs/006-deployment.md): manual setup, configuration, upgrades and troubleshooting
- [007 Architecture](docs/007-architecture.md)
- [008 Cookbook](docs/008-cookbook.md): adding a Source
## Development
`pnpm check` runs the typecheck, the tests and the build.
## License
[MIT](LICENSE)