Plugins

Token-cost pipeline for DeepSeek Harness: pressure-aware layered compaction (lossless projection below 40% context pressure, LLM summarization above), per-agent tool allowlisting, long-text-to-image with vision summarization, and a /token-status command tracking pressure, tiers, and saved tokens.

Reversible context slimming for DeepSeek Harness: TOON-style lossless tabular re-encoding of uniform JSON arrays, stride-sampled table windows with line numbers, and cross-turn dedup for repeated tool output; every replacement passes a byte-plus-token gate (≤72% bytes, strictly fewer estimated tokens) and the original is spilled to disk behind a `[save-token #id]` notice retrievable in one call via the `save_token_expand` tool, with billed and avoided token metering on a settings dashboard.

Layered token-optimization pipeline for DeepSeek Harness: output ladder, MCP lazy loading,compaction driver, cache-hit reporting. Built on real DSH plugin APIs; ~40-60% input saved in long sessions.

Wraps work in named tasks and, once a task closes, folds its whole span of messages into one summary at the next step boundary; the original content can be restored on demand.

Token-efficient persona runtime for DeepSeek Harness with local catgirl rendering and progressive tool-schema disclosure.

Route each task to one model and its review to a different one, with qualification evidence, failover and a durable journal.

Fronts stdio MCP servers with three router tools (list_capabilities, describe_tool, call_tool) so schemas load on demand instead of riding every request; shapes every tool result through a deterministic output ladder that archives the original first (retrieve_spill reads it back); prices tool groups in tokens and can hide built-in groups per agent. Bridges to a standard-library Python router, so Python 3.9+ is required.

Compaction fallback for compaction-basic: when its LLM summary throws, comes back empty or cannot fit the window, the span is compiled deterministically with a seq pointer on every line (vendored dsh-compaction-instant compiler). Adds recall and search tools, /recall and /context commands, an idle trigger at 45% of the window and an on-disk span archive. The engine mounts as one row in the agent preset (docs/dsh-integration.md).

One MCP tool instead of every schema you own — a lazy capability broker that cuts resident tool context by a measured 94.4%. Search, inspect, enable and call MCP servers and skills on demand.

DeepSeek Harness 动态上下文管理插件（Dynamic Context Pruning for dsh），对标 opencode-dcp

Sleev routing observability for DeepSeek Harness

把长文本渲染成图片发送，利用每图 384 token 封顶压缩 LLM 输入 token，专为DeepSeek Harness设计的插件；Pack long text into images to cut LLM input tokens (384/image cap) — a DeepSeek Harness plugin.