taishan-vision
泰山识图 Taishan Vision - 让 DeepSeek Harness 纯文本模型也能识图:GLM 视觉识别 + 所选模型推理(静态插件包,重启永久生效)
279 results
泰山识图 Taishan Vision - 让 DeepSeek Harness 纯文本模型也能识图:GLM 视觉识别 + 所选模型推理(静态插件包,重启永久生效)
DeepSeek Harness web plugin: a Model Capabilities settings page for declaring model input modalities, context window, output cap and image budgets without hand-editing settings.yaml.
DeepSeek Harness plugin: analyse images out of band with a vision model — pasted images are digested into text before admission and a describe_image tool covers image paths, all without ever changing the session's model.
Give DeepSeek Harness agents eyes: local image analysis via vision models — um_analyze_img tool + model-capability recognition + hot-switch settings UI
Project PDF library with background indexing and cited page highlights for DeepSeek Harness Web
DSH 截图提问插件:输入框相机按钮或 Ctrl+Shift+A → 自动最小化窗口 → 原生全屏框选浮层(确认/取消按钮)→ 选区直接作为图片附件进入当前会话输入框,全程不落盘。Screenshot-to-ask for DeepSeek Harness: the window hides, a native region overlay covers every monitor, and the crop lands in the composer as an image attachment.
Local reverse proxy plugin for DeepSeek Harness that caps images per request to 1, for self-hosted vLLM backends that reject prompts with more than one image
DeepSeek Harness(DSH)对话互通插件:让同一进程里的对话互相发现、直接发消息、盯进度、设护栏——不用先绑定,也不用开子代理。Peer messaging, supervision, and tool guardrails between conversations.
Capability metadata for hand-declared gateway models, resolved at runtime by bare model name (context window, output cap, reasoning levels, vision) — matched against the official DeepSeek route's catalog, the installed pi-ai catalog, opencode and models.dev, without writing to your settings.
External vision model plugin for image recognition when the active model lacks vision
Automatic tier-based model routing for DeepSeek Harness: a virtual `smart` model classifies each request by difficulty (hard / normal / easy) and by vision need, then delegates it to the models you already configured. 三级难度 + 视觉自动路由,虚拟 smart 模型零配置接入。
Autonomous screen vision for DeepSeek Harness on macOS and Windows: the agent captures the screen and receives the image itself in one call.
Helper dispatch — a visible settings panel that decides whether the main agent may delegate work to helper agents, which helpers are allowed (free-lane models / subagents / experts / teams), and injects that division of labor into a systemPrompt section, taking effect on save.
DeepSeek Harness plugin that turns a local llama.cpp (llama-server) into a first-class model provider: process & router management, model catalog sync with mmproj vision pairing, auto-start on demand, stop-then-load model switching, and a sidebar terminal-output monitor panel.
Dedicated Git commit planning and execution agent for DSH: analyses status/diff, materialises an exact add/commit plan, binds user approval to a plan revision, and runs a restricted git CLI executor.