Bundle
dsh-plugin-langfuse
Langfuse observability for DeepSeek Harness: OpenTelemetry traces, compaction, feedback Scores, and fork lineage
linyp14
Browse
28 results
Bundle
dsh-compaction-instant
VCC-style instant, near-lossless deterministic compaction engine for the DeepSeek Harness — a drop-in replacement for @deepseek-ai/dsh-compaction-basic
TsFreddie14
Bundle
auto-compact
会话级自动上下文压缩插件：回合中每步前 + 回合结束检测上下文用量，超过会话阈值自动 compact，摘要注入上下文后自然继续（DeepSeek Harness / DSH）
83
Bundle
dsh-minimal-mode-compaction
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。
wicm842669642
Bundle
@mimichunterz/agent-compact
Context compression tool (context_compact): the agent writes the replacement checkpoint itself and hands it to the host compaction engine, which skips the LLM summarizer call; automatic compaction stays on the official engine.
MimicHunterZ5
Bundle
dsh-compaction-meta
元压缩：模型自己决定何时、如何压缩自己的上下文——列 surface、选区间、以自写文本替换；替换走官方 compaction 事务（检查点、配对平衡、可重建）。Meta-compaction: the model directs its own context compaction through the official compaction seam.
DViridescent2
Bundle
dsh-qwen38-ninfer-compaction-fix
DSH plugin (NInfer engine only): fixes compaction failure on local qwen3.8-27b gateways served by NInfer — xhigh thinking burns the entire output token budget, so thinking is off for compaction-only, with the model's non-thinking sampling parameters; the same idea applies to other launch methods
zhubaohi2
Bundle
dsh-auto-compact
会话级自动上下文压缩插件：回合中每步前 + 回合结束检测上下文用量，超过会话阈值自动 compact，摘要注入上下文后自然继续（DeepSeek Harness / DSH）
JohnathonYe2
Bundle
dsh-compaction-cacheaware
Reasonix-style cache-aware compaction backend for DeepSeek Harness (DSH). Replaces/enhances compaction-basic with compact_ratio, one structured summary checkpoint, and a stable recent tail.
Zhuchen001232
Bundle
dsh-active-context-pruning
Model-authored context pruning for DeepSeek Harness through the official compaction API.
aerince2
Bundle
dsh-ledger-compact
dsh-plugin: OMP-style ingress shaping plus optional local /fast-compact. Can replace DSH /compact and auto-compaction with a mechanical fold.
telagod2
Bundle
dsh-compact
DeepSeek Harness 上下文自动压缩、手动压缩与溢出恢复插件
zixin9472
Bundle
@xiaobanli/dsh-compact-after-task
Auto-compact a DSH conversation after the current task finishes, at a user-set context threshold. Settings-page switch + slider included.
xiaoliang21
Bundle
dsh-qwen38-compaction-fix
DSH plugin: fixes compaction failure on local qwen3.8-27b gateways — xhigh thinking burns the entire output token budget, so thinking is off for compaction-only, with the model's non-thinking sampling parameters
zhubaohi1
Bundle
dsh-epoch-reanchor
Minimal epoch bootstrap, full-tool promotion, and hard handoff compaction for DeepSeek Harness
whycantiusemyname1
Bundle
dsh-context-guard
Token-efficient tool-result pruning policy for DeepSeek Harness presets.
kpl01111
Bundle
@helibeiqi/dsh-compaction-pro
High-fidelity, faithful, bilingual, recursive compaction backend for DeepSeek Harness — a drop-in upgrade over dsh-compaction-basic.
helibeiqi1
Bundle
@aiwayds/dsh-dcp
Deterministic context-pruning compaction backend for dsh (DeepSeek Harness) — zero-LLM summaries, /dcp command, works out of the box. Design references Opencode-DCP/opencode-dynamic-context-pruning.
fan561
Bundle
dsh-context-rollover
Model-driven context-window rollover bundle for the DeepSeek Harness: fresh working context, durable model-managed notes, a small verbatim recent tail, and targeted history recovery — no summarization.
athif231
Bundle
dsh-context-management
Windowed, reversible context management for DeepSeek Harness; replaces Basic compaction.
PlxloYzb1
Bundle
dsh-compaction-micro
Tiered micro-clear layer for DeepSeek Harness compaction: clears whitelisted re-runnable tool results to placeholders before the official summarization tier, freeing context with no model call.
Perfirstvito1
Bundle
dsh-squeeze-command
Manual budget-targeted context compression for DeepSeek Harness: the conversation model picks ranges, a cheap flash-tier route writes the checkpoint summaries.
hardes111
Bundle
dsh-context-budget
Keeps a local model's context at a size the GPU handles well: measured prefill speed, hard ceiling, early compaction for DeepSeek Harness
d3vmeh
Bundle
dsh-mindmap-chat
Chat branch tree plugin for DeepSeek Harness: mind-map of conversation branches, group folders, archiving and compaction preview.
DeepVite