dsh-plugin-save-token
Cut token cost without cutting model intelligence — a DeepSeek Harness (dsh) bundle plugin: structure-aware compression + TOON-style lossless encoding first + reversible spill-to-disk + real-time dashboard.
11 results
Cut token cost without cutting model intelligence — a DeepSeek Harness (dsh) bundle plugin: structure-aware compression + TOON-style lossless encoding first + reversible spill-to-disk + real-time dashboard.
Token-efficient catgirl persona runtime for DeepSeek Harness
Cache-stable progressive tool discovery and dispatch for DeepSeek Harness
Content-aware tool output compression for DeepSeek Harness.
DeepSeek Harness dynamic context pruning plugin (model-driven context management)
dsh third-party plugin: queue during peak hours, drain off-peak, report the savings.
把长文本渲染成图片发送来压缩 LLM 输入 token(DeepSeek 视觉模型、每图 384 token 封顶)— text-as-image token compression for DeepSeek Harness
Deterministic, recoverable tool-result compression and cache-aware compaction for DeepSeek Harness
Token-efficient tool-result pruning policy for DeepSeek Harness presets.
Keeps long coding-agent sessions lean: wrap work in named tasks and, when one is done, fold its whole span into a short titled summary. The conversation stays readable, context costs stay low, and every fold's original content can be read back on demand. For DeepSeek Harness.
Token optimizer for DeepSeek Harness — condense your context, keep the essence