lanyun077/dsh-project

Image "reading" for text-only models: downscale + reduce color depth + structure/color fingerprints into text grids fed back to the conversation, letting the model zoom, sample and OCR autonomously like a multimodal model; fully local with zero external model dependency, ships an image-reading methodology skill and optional PaddleOCR.

A DeepSeek Harness bundle plugin that lets a text-only main agent (DeepSeek) read images in the same session: when a task needs vision, the main agent delegates to a fresh subagent routed to a vision-capable model you pick in the settings (configured under SettingsModels, chosen under Settings视觉处理模型; the factory default is qwen3.8-max — see Configure), and the child's text result is merged back. Pasting or dropping an image just works: intake stays native (thumbnail rail, remove/undo); when you

Every DSH session starts from zero. dsh-memory gives your agents a persistent second brain: facts, preferences, decisions, and project notes survive across sessions and are recalled automatically.

Bounded local memory with CBDC authority gating: SQLite + FTS5 claims, scoped recall with explainable use/verify/ignore decisions and a full audit trail, /memory commands, ≤3-claim/1200-char injection per call, no extra model call.

Failure-recovery memory: search and record failure-recovery lessons from real engineering sessions, with BM25 + semantic RAG retrieval and a lessons knowledge base.

Automatic conversation distillation: background subagent reflection + skill create/update.