dsh-force-compact

Copy the command, or hand the whole task to your harness agent.

From the README

A cleaned excerpt from the project's own documentation.

dsh-force-compact Aggressive, local-first context compaction for DeepSeek Harness agents. A DSH Cordis function plugin that keeps the agent's working context lean by design: serve Qwen3.8‑27B on a self-hosted llama.cpp with a modest context, and the plugin shrinks the conversation itself — a large-window feel with no API cost and no data egress. 中文 --- Why - Self-hosted inference — the agent talks to a local OpenAI-compatible llama.cpp server through the standard DeepSeek adapter; no separate adapter needed. - Low context, high signal — instead of fighting a small cap, the plugin shrinks the conversation, so the agent reasons over a tight prompt while keeping deep memory in the compressed head. - Think off for compactions, passthrough everywhere else — disableThinking: true (default) turns thinking off on this plugin's own compaction summarization call only ; every other model request rides the machine's configuration unchanged. - Private & free — no per-token billing, no egress. --- What it does Two compaction engines coexist behind one facade ( resolveCompaction ), transparent to callers:…

Project details

Repository

falling-ts/dsh-force-compact

by

falling-ts

License

MIT

stars

10

Forks

2

Updated

Oct 24, 2026

Created

Aug 23, 2026

Language

JavaScript

Indexed from

topic