privacy 15

dsh plugin: recognize attached images with the built-in Windows OCR engine (Windows.Media.Ocr) and send only the recognized text to the model. Text models never receive image bytes; vision passthrough is opt-in.

Privacy-minimal heuristic per-turn execution summaries for DeepSeek Harness

PII masking middleware for DeepSeek Harness: anonymize names, phones, emails, ID cards, bank cards, keys, and addresses to placeholders before they reach the model, restore them at the display layer, keep the restore table only in memory and a controlled

dsh plugin: back the native web_search / web_fetch tools with your self-hosted SearXNG instance - keyless, private, no third-party search vendor.

Local-model (Ollama) integration for DeepSeek Harness: discover, pull, remove, and inspect local models, route requests to them by task type or keyword with automatic fallback to the cloud, and get a one-shot status overview via /ollama.

dsh plugin: recognize attached images locally with Tesseract OCR and send only the recognized text to the model. Text models never receive image bytes; vision passthrough is opt-in.

DeepSeek Harness chat history and session management: search archives, restore conversations, and delete safely

Fully-local OCR CLI for text-only LLMs: PaddleOCR-VL first-tier engine with tesseract fallback, dsh plugin included

Transport-layer data masking for deepseek-harness (dsh): sensitive values never leave the process — the model sees placeholders, you see real values restored live in the stream.

Select and locally share one or more DeepSeek Harness conversation turns as Markdown, self-contained HTML, or a long PNG, with privacy-first redaction and no uploads

DeepSeek Harness 社交插件：AI 代笔、默认匿名、逐条过审的观点交换网络。话题广场、话题内匿名对话。

Privacy-first Markdown and self-contained HTML sharing for DeepSeek Harness sessions

Local image understanding for the DeepSeek Harness: OCR, table-layout detection, and semantic description of textless images via macOS Vision, fully on-device (images never leave your Mac). 本地化识图，图片不出本机。

Bridge Apple's on-device Vision framework (macOS) into DeepSeek Harness: OCR, image classification, face detection, and document layout as local dsh tools. No network, no API key, no daemon.

Local-first vision for text-only DeepSeek Harness agents: route image understanding to a local OpenAI-compatible vision model, return structured JSON evidence (summary / OCR / layout / semantics / visual / uncertainty).