xingzhen199186/dsh-advisor-group0

dsh-advisor-group

DSH plugin: consult multiple expert advisor models in a retro chat-group card — auto-deepen consultation pipeline with real streaming, SSE replay, and 26 provider presets.

包名
dsh-advisor-group
版本
0.0.1
许可证
NOASSERTION
最近更新
2026年9月6日

安装

$npx -p @deepseek-ai/dsh dsh plugin --profile web add github:xingzhen199186/dsh-advisor-group

⚙️ Configuration

KeyTypeDefaultDescription
enabledbooleantrueEnable advisor group
discussion.maxRoundsnumber2Total rounds of the auto-deepen pipeline (each round = driver question + all advisors in relay)
discussion.maxAdvisorsPerCallnumber3Max advisors per call (1–10)
discussion.autoDeepenbooleantrueRun the auto-deepen pipeline (driver follow-ups + final synthesis)
discussion.driverModelobjectFallback driver model {provider, model} when the session header cannot be read
discussion.advisorTimeoutMsnumber600000Per-advisor call timeout (ms, 1000–600000), applied to both channels
quota.enabledbooleantrueEnable the daily new-consultation cap (cost safety valve)
quota.maxPerDaynumber50Max new consultations per UTC day (1–100000); ignored when quota.enabled is false
trigger.requireClassifierbooleantrueRun the pre-classifier before starting
trigger.allowWebFallbackbooleantrueAllow classifier to recommend web search
trigger.confidenceThresholdnumber0.6Escalate when main-model confidence is below this
ui.themestringretro-greenChat card theme (retro-green / retro-amber / retro-blue)
ui.showTimestampsbooleantrueShow timestamps
ui.autoExpandbooleantrueAuto-expand card
advisorsarray[]Advisor list (provider/model/baseURL/apiKey/apiKeyEnv/protocol…, keys are role('secret'))

discussion.parallel and discussion.stopOnConsensus are deprecated leftovers kept only for stored-config compatibility.