token-optimization

A token-efficient persona runtime for DeepSeek Harness. 把人格留在界面，把智能留给模型。Measured: -67% input tokens, -66% cache reads, 0-token catgirl rendering.

A DeepSeek Harness (dsh) dynamic plugin that cuts token cost without cutting model intelligence

Off-peak task queue plugin for DeepSeek Harness — queue at peak price, drain at night, read the savings report

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

Memory and token-optimization plugin toolkit for DeepSeek Harness: cross-session knowledge graph memory + five-layer token-saving orchestration.

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

Evidence-preserving tool output compression for DeepSeek Harness — deterministic, local-first, and benchmarked.

Token-efficient tool-result pruning for DeepSeek Harness: compact previews, targeted recall, and long-session context control.

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.

轨迹省钱优化器：DSH 会话轨迹 token 浪费分析 + waterfall 执行层强制拦截/截断。Trajectory cost optimizer with enforcement layer for DeepSeek Harness.

Sleev integration for DeepSeek Harness with route-aware LLM telemetry and context-optimization observability