DSH插件商店

dsh-argp

yoza10635

Guarded context compaction for DeepSeek Harness (dsh): the LLM proposes, deterministic guards dispose — eager per-atom shrink (extract/summary/false under verbatim guards) + lazy reference-graph eviction (0-LLM) + byte-exact recall from an append-only log. 守卫式上下文压缩：LLM 只提议、确定性守卫裁决——逐原子缩放 + 惰性引用图剪枝（0-LLM）+ 追加式日志逐字节召回；压缩率精确兑现，历史永不销毁。

dsh-context-lens

1014029855

Inspect, measure, search, and compare the exact provider-neutral context assembled by DeepSeek Harness.

dsh-session-drafts

ne-ilyxa

Cursor-style draft chats for DeepSeek Harness (DSH): New Session reuses the empty draft — and only mints a fresh one when every draft has unsent text — so empty placeholders never stack, exactly like Cursor's (or Telegram's) chat list.

dsh-legion

wxxb789

Multi-agent orchestration and LLM model routing for DeepSeek Harness (DSH): semantic AI agent profiles, exact model routes, declarative teams and strategies, and bounded subagent delegation - a TypeScript plugin that adds no second runtime.

dsh-context-tree

wr-web

Reusable trajectory-tree context, exact-turn forks, and bounded cross-session recall for DeepSeek Harness

dsh-moe-plugin

nataliwhite20534-droid

10 preset moe character cards for DSH - freely combinable, editable, persistable. Real outputs in docs/usage-examples.md.