JingzeChen/dsh-beacon0

@jingzechen/dsh-beacon

Attention and handoff workspace for concurrent DeepSeek Harness Sessions

AI 분석

核心用途是管理和协调多个并发运行的 DSH 会话,提供状态摘要与自动生成交接简报。适合需要同时处理多个复杂 AI 会话并进行上下文切换的用户。

패키지
@jingzechen/dsh-beacon
버전
0.1.0
라이선스
MIT
최근 업데이트
2026. 9. 2.

설치

$npx -p @deepseek-ai/dsh dsh plugin --profile web add github:JingzeChen/dsh-beacon

Configuration

The published cordis.patch.yml supplies conservative defaults:

FieldDefaultMeaning
sessionActivity.maxOpenTools3Maximum unmatched tool names projected into a Session summary
sessionActivity.maxErrorBytes64Maximum UTF-8 bytes retained from a provider-neutral error code
sessionBrief.automaticTriggersturn-end, goal-blocked, turn-errorStable checkpoints eligible for automatic generation
sessionBrief.minMeaningfulEvents2Required activity advance after the previous accepted brief
sessionBrief.maxBriefBytes4096Maximum complete accepted brief size
sessionBrief.maxItemsPerField8Maximum completed, blocker, and citation items
sessionBriefLlm.maxInputBytes32768Maximum exact JSON-framed model input
sessionBriefLlm.maxOutputTokens4096Auxiliary output token cap
sessionBriefLlm.timeoutMs30000End-to-end auxiliary request deadline

A profile patch can replace the complete dsh-beacon row to change these values. DSH patch rows replace config rather than deep-merging it, so restate every required field.

To pin generated briefs to a dedicated route, add both provider and model under sessionBriefLlm. If both are omitted, Beacon uses the latest eligible route recorded for the Session. Brief generation remains unavailable when neither route exists; deterministic activity and context continue to work.