523 results
DeepSeek Harness LLM adapter plugin for locally deployed Qwen models behind a vLLM OpenAI-compatible endpoint: per-model multimodal switch, fully configurable reasoning efforts, and a web settings page (client plugin) for editing the deployment from the frontend
Ctrl+click file paths and links in DeepSeek Harness chat: paths open their folder in the OS file manager, links open in a new browser tab.
DeepSeek Harness workspace & session enhancement plugin: recycle bin, cross-workspace session drag, ungrouped sessions, multi-folder workspace roots, in-app directory picker, session merge, folder/file sections, multi-select picker, session files & drag-drop upload, file preview — shipped as an overlay patch-set with install scripts
DeepSeek Harness plugin: display-layer translation of reasoning and answers via Chrome Translator or an OpenAI-compatible API
Native knowledge context for DeepSeek Harness
Record & Replay for the dsh web GUI: (1) replay every automatically recorded session as a readable timeline, export/import shareable replay packs, re-run a recorded conversation; (2) Codex-style screen recording -> skill generation - record a computer-use session in the browser (getDisplayMedia -> webm + sampled frames), replay it, and have an agent analyze the frames and install a generated SKILL.md into ~/.dsh/skills. Hot-pluggable - mounted via the profile patch layer, no dsh source changes.
Eyes for text-only DeepSeek: view_image tool (any OpenAI-compatible VLM, local Ollama or cloud) + chat image-attachment bridge that rewrites pasted/dropped images into view_image path markers
OCR via OpenAI/Anthropic vision APIs for dsh: ocr_recognize tool (percent coords + two-diagonal-point boxes, auto region re-read on low confidence), a collapsible settings card in Settings → Plugins (API format / URL / Key / Model, fetch model list, test connection). Hot-pluggable — mounted via ~/.dsh/profiles/web/cordis.patch.yml + a profile node_modules symlink, no dsh source changes.
Private, per-project system-prompt rules for DeepSeek Harness — matched by git remote URL, repo path, or cwd prefix; worktree-aware; never committed to the repository.
DeepSeek Harness 插件：一键配置任意 OpenAI 兼容 API 并自动带思考模式，同时规避 developer 角色被第三方端点拒绝（content_filter）的问题。
External vision proxy plugin for DeepSeek Harness, enabling text-only models (DeepSeek-V3 / R1) to analyze and understand images via OpenAI-compatible vision APIs.
Renders edit and write tool calls as always-expanded side-by-side diffs styled like git diff, with optional syntax coloring and word-level highlighting.
DSH skill_manage: agent-managed procedural memory. Create/patch/edit/disable/delete skills in ~/.dsh/skills (user scope) or <projectRoot>/.dsh/skills (project scope), with validation, delete guards (agent-created marker, pin, path confinement), disable/enable via disable-model-invocation, and an English trigger-discipline system prompt section. Built on top of skill-filesystem's hot-reload watcher.
Karpathy 编码方法论：先想后写、简单优先、外科手术式改动、目标驱动验证。受 andrej-karpathy-skills（203k★）启发的 DSH 原创改编。
DSH Web profile 模组管理器：在设置页里开关第三方插件，通过改写 profile 的 cordis.patch.yml 并由 patch watcher 热生效，无需手动改文件、无需重启。
Give text-only models eyes: an analyze_image tool for DeepSeek Harness, backed by free Chinese vision APIs (GLM-4V-Flash / Qwen-VL) or any OpenAI-compatible vision endpoint. 给纯文本模型装上眼睛。
Universal local vision bridge tool for DSH: describe/answer questions about images via any OpenAI-compatible local inference framework (llama.cpp / Ollama / LM Studio / vLLM), vision models auto-detected
FFF (Fast File Finder) tools for DeepSeek Harness — fffind (fuzzy path search) and ffgrep (content grep) backed by a resident @ff-labs/fff-node index that follows the current session workspace, with a runtime watch toggle on the web settings page.
Claude Code-style `paths:` rule injection for DeepSeek Harness (DSH): inject rules from ~/.dsh/rules, <project>/.dsh/rules and <project>/.claude/rules into the model context.
Hover file paths / URLs in the DSH Web UI to open them in the file manager (Explorer) or in the default browser.
deepseek-eyes：给 DeepSeek Harness 的纯文本模型装上眼睛——把粘贴的图片经 OpenAI 兼容视觉 API 转成文字描述，再转发给真实的文本模型（Give text-only models in DeepSeek Harness eyes: describe pasted images via an OpenAI-compatible vision API, then forward to the real provider. Not affiliated with DeepSeek.）
Manage DeepSeek Harness plugins from the web GUI and CLI: install, enable/disable, uninstall — no manual config-file editing. Writes your profile's cordis.patch.yml for you and applies changes live through HMR.
自包含的 DeepSeek Harness 视觉系统：DeepSeek 视觉孪生路由（原生图片体验 + 视觉桥请求层拦截）+ 本地 Ollama Agentic Vision 工具（describe/OCR/结构化扫描/区域查询/元素定位/双图对比/剪贴板）+ 粘贴分流（paste-to-path）。安装即用，无本机路径依赖。
On-demand image generation for DeepSeek Harness (DSH): a generate_image tool that calls your own OpenAI-compatible image URL + API key and delivers the image into the session