150 results
Image auto-describe provider for the DeepSeek Harness apiproxy admission seam: transcribes pasted images through configurable vision routes (Qwen first, GLM fallback) so text-only session models still receive image prompts.
个人投研方法论（A股/美股/港股）：五维分析框架（估值/资金面/财报质量/行业景气/事件催化与风险）、多空辩论（事实底稿→多方/空方→中立主持归纳分歧）、反思审计（揪出无数据支撑的脑补结论）。受 simonlin1212/Vibe-Research（2.1k★ MIT）启发。
给 DeepSeek Harness 加视觉能力：可视化设置页选视觉厂商（Kimi/智谱/通义/OpenAI/Gemini/豆包/MiniMax/阶跃星辰）并粘贴 API Key，聊天里即可拖图识别——图片走视觉模型、文字走 DeepSeek 推理。
A project-scoped multimodal video director plugin for DeepSeek Harness.
Request image optimization, intelligent retention, and observability for DeepSeek Harness (DSH)
Xiaomi MiMo v2.5 adapter for DeepSeek Harness LLM seam with thinking chain support
DSH 插件：提供文本 / 图像 / 视频 / 语音 / 音乐 五个生成工具，模型从 llm-pi-ai 自动发现，含 Settings UI (llm-multimodal namespace)。
Automatic reasoning and image capability detection for custom DeepSeek Harness models
DeepSeek Harness 视觉助手插件：给没有视觉能力的模型配一个可随时切换的多模态识别模型。输入框图片自动落盘并改写为文本提示，主模型调用 vision_recognize 工具即可完成看图；识别模型在 settings 的 vision-assist 命名空间热更新切换。
The see tool for the DeepSeek Harness: offline OCR with positions (macOS Vision) + ASCII layout art (PIL) + vision-model semantic description (mimo-v2.5 via the opencode-go gateway). Works with any model, including text-only ones.
DSH bundle: Qwen multimodal bridge — vision (qwen3-vl), speech-to-text (qwen3-asr), text-to-image (qwen-image), via the deepseek-vision skill scripts
Vision bundle + plugin for DeepSeek Harness: the describe_image tool reads local images and asks any configured multimodal route, with zero core changes
DSH plugin: keep text-only models (deepseek-v4-flash / deepseek-v4-pro) as the session default, and automatically route requests that carry image content to a configured vision-capable model (deepseek-v4-flash-vision-exp) 鈥?no manual model switching (periscope).
Zero-config local vision and realtime audio routing for DeepSeek Harness
Windows computer-use bundle for DeepSeek Harness: screenshots, window enumeration, and mouse/keyboard control with approval gates.
DSH 图片插件，三个工具覆盖三种场景：ask_user_choice 图片/图文混合选择卡（Web GUI 渲染，可放大查看）+ show_images 回复内嵌图片（图文混排）+ save_received_images 盲模型收图存为工作区文件；聊天栏所有图片点击放大，支持滚轮缩放与拖拽平移。来源支持本地路径 / http(s) URL / base64 data URI。零 token 本地渲染，纯插件实现不改核心包。
Image translation for non-multimodal models via GLM-4V-Flash: intercepts images, generates descriptions, injects as text.
Bring ChatGPT-like image generation to DeepSeek Harness — Gemini, OpenAI, Seedream, DashScope, local ComfyUI & more.
dsh-voice — turn-based voice loop for DeepSeek Harness: pluggable Qwen / MiMo / local ASR+TTS engines, agent-driven speak/listen tools and browser PTT UI, built for interviewer presets
DSH skill bundle: competition math (IMO/Putnam/USAMO/AIME) solved with a pure-reasoning pass, an adversarial verifier in a fresh subagent context attacking concrete failure modes, and calibrated confidence output (high / medium / honest "no confident solution"); optional LaTeX→PDF rendering.
DSH 视觉桥接插件：复用 DSH Provider 或 OpenAI 兼容直连，支持可视化配置与图片粘贴
Automatic per-task model hot-switching for DeepSeek Harness (dsh): image-aware tasks route to the vision model automatically, every other task keeps your default model. Zero extra tokens, no context disturbance.
DSH plugin: auto-detect and configure model capabilities (reasoningEfforts + input modalities) for llm-pi-ai. Successor to dsh-reasoning-efforts.
DSH 模型视觉开关：设置页「模型视觉」行，为 llm-pi-ai 自定义路由下手写声明的模型切换 input 视觉模态（settings.mutate 官方通道，热生效）。