DSH插件商店

dsh-force-compact

falling-ts

Aggressive context compaction for local-first agents. Runs Qwen3.8‑27B on self‑hosted llama.cpp at low context, shrinking history so the live prompt stays small, fast, and private—delivering a big‑window experience without API cost or data egress. 面向本地的激进上下文压缩插件。自托管 llama.cpp 低上下文运行 Qwen3.8‑27B,不断收缩历史、保持常驻 prompt 小而快,兼顾隐私与大窗口体验,零 API 成本、数据不出本机。

dsh-ctxopt-compaction

chunsi-w

DeepSeek Harness 的上下文压缩插件

context-assembler-DSH

i1j

Context Assembler DSH — DeepSeek Harness 上下文汇编插件：按话题块编排上下文，最大化每 token 互信息密度

dsh-jev-prune

yangyu666

Jev-judged context compaction for DeepSeek Harness: semantic tool-result pruning + deterministic receipt compaction

dsh-token-optimizer

Snow-ea

Deterministic, recoverable tool-result compression and cache-aware compaction for DeepSeek Harness.

dsh-epistemic-fold

orangeofcarl0-sys

A contract-preserving context runtime for long-horizon agents on DeepSeek Harness

dsh-task-stack

Ray1270

Persistent per-session task stack for DeepSeek Harness agents - focus_task / focus_complete / read_focus + /focus, zero prompt injection

dsh-minimal-mode-compaction

wicm84266964

为 DeepSeek Harness 极简模式增加自动上下文压缩、/compact、/context 和模型主动压缩，解决极简模式长任务无法持续工作的问题。

dsh-clear-mind

john-walks-slow

Context compaction for DeepSeek Harness: mind_map and clear_mind agent tools turn selected history into self-written checkpoints, with auditable GUI tombstones and proactive threshold reminders.

dsh-handoff-compaction

knighthongyu

Context compression for DSH: visually configure summary and recent-context budgets (8k + 16k by default), keep tasks on track, and search full conversation history. Friendly to small-context models.