dsh-qwen38-local-qol：DeepSeek Harness 插件

概览

dsh-qwen38-local-qol

DeepSeek Harness QoL plugin for the local Qwen3.8 line (27B, Flash-Next): per-request thinking budgets on both llama.cpp and NInfer dialects, vision + tools, and a compaction backend whose summaries stop burning the output cap on thinking.

README / ZH

插件文档

目录摘要

DeepSeek Harness QoL plugin for the local Qwen3.8 line (27B, Flash-Next): per-request thinking budgets on both llama.cpp and NInfer dialects, vision + tools, and a compaction backend whose summaries stop burning the output cap on thinking.

dsh.pub 核对固定版本的组合包契约、运行时事实与分发语义；完整 README 请查看源仓库。

在 GitHub 阅读完整 README

LIMITATIONS

已知限制

- **Flash-Next has a fast line and a compat line** — the ExLlamaV3/TabbyAPI dialect (EXL3 quant, 256K context) is the fast path; the llama.cpp dialect still runs it at its own window/budget values. - **The TabbyAPI line's vision token count is not pinned** — the token meter reports image capacity as unknown on that line until the ExLlamaV3 image-processor formula is measured (the request itself works; only the pre-flight capacity projection is affected). - **The preset seam is a web-surface feature** — headless profiles do not mount `agent-presets` rows; the provider route (thinking budgets) works on both surfaces. - **Summarizer internals depend on the engine version** — the wire rules (thinking off, full output cap) hold for every engine version; engine internals are outside the plugin's control.

dsh-qwen38-local-qol