dsh-advisor-group
DSH 插件：在复古群聊卡片中咨询多个专家顾问模型——支持自动深化咨询流程、真正的流式传输、SSE 重放和 26 个服务商预设。
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:xingzhen199186/dsh-advisor-group#aaeda39063103058ae6e604144ad67b0d4979c3d
Advisor Group 以 dsh-advisor-group 发布，当前版本为 0.0.1。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。
A DeepSeek Harness (DSH) plugin that lets the main model consult multiple expert advisor models in a retro chat-group card — for professional, long-tail world-knowledge, high-risk, or uncertain questions.
📖 中文文档 / Chinese: README.zh.md
ask_advisors call runs up to maxRounds rounds automatically: each round is a driver deep-question → advisor A → advisor B (sees A) → advisor C (sees A+B) → … sequential relay, closed by a driver-generated synthesis conclusion.discussion.driverModel when the session header is unavailable.@顾问群 mention (force-start), same question repeated 3 times without resolution, or main-model self-assessed confidence below the threshold.SecretField semantics (never returned to the browser; apiKeysByProvider key history is server-side only), SSRF-guarded diagnostics (https-only / loopback, no IP literals, no redirects), per-boot token auth on /advisor-group/* routes, and an atomic configurable daily consultation cap (default 50, can be disabled) persisted across restarts.toggle_advisor_group enables/disables the plugin and persists the flag to settings.| Surface | Status |
|---|---|
| Harness | DeepSeek Harness 0.1.2-rc.1 |
| Node | ^22.19.0 || >=24.0.0 |
| Platforms | DSH Web (client bundle) + headless host logic |
# 1. Install the plugin (one package, everything included)
dsh plugin --profile web add dsh-advisor-group
# 2. Restart DSH web
npx @deepseek-ai/dsh web
From source (development)
npm install --legacy-peer-deps --no-audit --no-fund npm run build dsh plugin --profile web add ./dsh-advisor-group-0.1.0.tgz # after npm pack
Ctrl+Shift+R).maxRounds, thresholds, and the UI theme.@顾问群 in your question to force a consultation, orask_advisors tools available to the model: ask_advisors, toggle_advisor_group.
| Key | Type | Default | Description |
|---|---|---|---|
enabled | boolean | true | Enable advisor group |
discussion.maxRounds | number | 2 | Total rounds of the auto-deepen pipeline (each round = driver question + all advisors in relay) |
discussion.maxAdvisorsPerCall | number | 3 | Max advisors per call (1–10) |
discussion.autoDeepen | boolean | true | Run the auto-deepen pipeline (driver follow-ups + final synthesis) |
discussion.driverModel | object | – | Fallback driver model {provider, model} when the session header cannot be read |
discussion.advisorTimeoutMs | number | 600000 | Per-advisor call timeout (ms, 1000–600000), applied to both channels |
quota.enabled | boolean | true | Enable the daily new-consultation cap (cost safety valve) |
quota.maxPerDay | number | 50 | Max new consultations per UTC day (1–100000); ignored when quota.enabled is false |
trigger.requireClassifier | boolean | true | Run the pre-classifier before starting |
trigger.allowWebFallback | boolean | true | Allow classifier to recommend web search |
trigger.confidenceThreshold | number | 0.6 | Escalate when main-model confidence is below this |
ui.theme | string | retro-green | Chat card theme (retro-green / retro-amber / retro-blue) |
ui.showTimestamps | boolean | true | Show timestamps |
discussion.parallelanddiscussion.stopOnConsensusare deprecated leftovers kept only for stored-config compatibility.
settings.yaml (marked secret, never returned to the browser by describe); prefer apiKeyEnv (env-var mode) if you don't want keys on disk./advisor-group/* routes use a per-boot shared token for local single-user use — not multi-user auth. Add a reverse-proxy auth layer before LAN exposure.quota.*; default 50; can be disabled) is persisted to $DSH_HOME/storages/advisor-group/daily-guard.json (UTC day key), so restarts don't reset it./advisor-group/shadow), used for threshold tuning only — never influences behavior.advisorTools: 'all' is an elevated-risk scope. It exposes every session-visible tool to the advisor models, including writable/execution ones (pwsh, bash, write, config/SSH tools), executed through the official guarded pipeline. Only enable it for advisors you trust (e.g., your own local models), keep them on the direct-http channel, and note that every non-read-only invocation is logged with console.warn for audit. Prefer the default readonly (read/grep/glob/web_search/web_fetch/scan_discover/list_imported_sessions) or off.npm install --legacy-peer-deps --no-audit --no-fund
npm run typecheck
npm test # 64 tests, incl. provider streaming contracts against a local fake LLM server
npm run build # tsdown; client bundle must NOT be built with minify: true
Apache License 2.0 © 2026 dsh-advisor-group contributors.
ui.autoExpand | boolean | true | Auto-expand card |
advisors | array | [] | Advisor list (provider/model/baseURL/apiKey/apiKeyEnv/protocol…, keys are role('secret')) |