@a1exsun/dsh-council
DeepSeek Harness 的多模型委员会协商
插件会安装到这里；不确定时保持 web。
npx -y @deepseek-ai/dsh plugin --profile web add github:a1exsun/dsh-council#41b054f647d7d4902e62efac5872d6dba6e55d2aCouncil 以 @a1exsun/dsh-council 发布，当前版本为 0.1.0。Plugin Hub 会校验它的 manifest，并保存精确安装来源，便于复现安装结果。
点击下方 Badge 复制 Markdown，粘贴到 README 即可。
验证 package.json 声明的 GitHub 仓库，即可管理这个公开页面。认领后，Hub 会优先安排当前版本的安全扫描，并在通过后公开展示结果。
认领这个 Plugin →English · 简体中文
Independent answers. Anonymous reviews. One reasoned decision.
Multi-model deliberation inside DeepSeek Harness.
Installation · How it works · Configuration · Contributing
https://github.com/user-attachments/assets/e81dfa36-5d93-4efb-8c67-015a5e4d2179
01 · Answer2–8 models respond independently in parallel. |
02 · Review1–8 reviewers compare anonymous answers, identify gaps, and rank them. |
03 · DecideOne arbiter weighs the answers and reviews to produce a final recommendation. |
|
Your models. Use configured DSH providers and credentials. Choose models separately for each role, with reuse across roles. English and Chinese follow DSH's language setting. Inspectable results. Confidence notes, consensus, disagreements, blind spots, model identities, and average rankings. Original answers and reviews remain in DSH's child sessions. | ||
Install DeepSeek Harness (dsh) by following the official installation guide.
| Node.js | pnpm | DeepSeek Harness |
|---|---|---|
^22.19.0 || >=24.0.0 | 11.7.0 | At least two configured, authenticated models |
Install the prebuilt package from npm:
npx --yes @deepseek-ai/dsh@latest plugin --profile web add @a1exsun/dsh-council@0.1.0
npx --yes @deepseek-ai/dsh@latest web
Restart DSH Web if it is already running.
No source checkout or compilation is required. See Contributing for development setup.
When registering, enter invitation code: RA3Z7CMJW2SS
Enter this command in a DSH Web conversation:
/council
Choose your panelSelect answerers, reviewers, and an arbiter. Selections apply to one run. |
Ask your questionEach participant starts with fresh context. Include the information it needs in your question. |
Compare PostgreSQL leasing with a managed message queue for three workers. Explain how each recovers when a worker crashes after an external side effect but before acknowledging the job. Recommend one design and state its assumptions.
|
Cost 4–17 model participants per run. Each may make multiple requests and use Web tools. |
Privacy Your question and intermediate answers go to selected providers. See Security. |
Accuracy Model agreement does not guarantee correctness. Review the evidence and confidence notes. |
The defaults work without additional configuration. To adjust limits, set config on the dsh-council entry in your DSH profile:
- id: dsh-council
config:
answerMaxTokens: 16384
reviewMaxTokens: 16384
arbiterMaxTokens: 16384
childTimeoutMs: 300000
runTimeoutMs: 900000
subagentProvider: spawn
Token limits apply per model request. Timeouts are in milliseconds; runTimeoutMs must be at least childTimeoutMs.
Development setup · Tests · Bug reports →
Thanks to Andrej Karpathy for llm-council, which inspired this project.
Review dimensions also draw on OpenRouter Fusion.