billion-context-dsh
Active Context Pruning (ACP) for the DeepSeek Harness — model-driven context management as a CompactionEngine backend.
10 results
Active Context Pruning (ACP) for the DeepSeek Harness — model-driven context management as a CompactionEngine backend.
Deterministic context-pruning compaction backend for dsh (DeepSeek Harness) — zero-LLM summaries, /dcp command, works out of the box. Design references Opencode-DCP/opencode-dynamic-context-pruning.
Reasonix-style cache-aware compaction backend for DeepSeek Harness (DSH). Replaces/enhances compaction-basic with compact_ratio, one structured summary checkpoint, and a stable recent tail.
Riff winning short videos — give one source (a TikTok link, an uploaded video, or an analyzed template) and the backend riffs its emotion formula into your own AI video (post-ready short-form or UGC-style ad creative), with optional digital character, product placement, and language.
Text-to-image for DeepSeek Harness: a `draw_image` model tool, an input-bar 生图 button with a prompt popup (async generation, 4-grid results, download / keep / delete), an /imgdraw image route, and persisted history. Backends: DashScope wan2.7-image (free default) and SiliconFlow Qwen-Image.
Enhanced fork of dsh-clean-desktop-shell: auto-starts the local backend with --no-open, prompts before closing the backend on quit, and starts the backend in parallel with Electron for faster cold start. DSH 插件形态的桌面壳增强版:自动启动后端(不打开浏览器)、退出时询问是否关闭后端、后端与窗口并行启动加速冷启动。
为 DeepSeek Harness Web 页面左下角添加“重启后端”按钮,一键重启 dsh 后端进程。
S3-compatible spill backend for DeepSeek Harness: oversized tool output goes to object storage (AWS S3, MinIO, R2) instead of the agent's local disk
High-fidelity, faithful, bilingual, recursive compaction backend for DeepSeek Harness — a drop-in upgrade over dsh-compaction-basic.
High-fidelity, faithful, bilingual, recursive compaction backend for DeepSeek Harness — a drop-in upgrade over dsh-compaction-basic.