54 results
DeepSeek Harness plugin: model-facing image_describe (识图) tool over the DashScope OpenAI-compatible API (qwen3.7-flash), plus a paste bridge that turns pasted images into file paths on text-only sessions and renders them back in the transcript. Bring your own DASHSCOPE_API_KEY.
DeepSeek Harness plugin: run subagents on a local llama.cpp model via the OpenAI Responses (/v1/responses) protocol, with a subagent delegation skill
DSH 计费统计插件：自动识别模型、实时展示会话/今日/本月消费、余额查询、预算告警，内置 16 家厂商价格目录（DeepSeek/豆包/腾讯混元/阿里千问/OpenAI/Anthropic/Kimi/智谱 等），中英双语
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
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。
Durable coding-agent orchestrator as a DeepSeek Harness plugin: dispatch tasks to codebuddy/opencode/omp/cline/qwen with persistent jobs, queue, review, and rollback.
明眸 VisionBridge - 自研视觉桥：瞎子模型收图时自动调用视觉模型识别，把识别文字喂回主模型，无感、可配置、升级不丢
DSH 本地视觉能力：macOS Vision OCR + ollama qwen3-vl 语义描述 + 上传图片桥接（图片块转文本，text-only 通道可用）
DSH plugin: fixes compaction failure on local qwen3.8-27b gateways — xhigh thinking burns the entire output token budget, so thinking is off for compaction-only, with the model's non-thinking sampling parameters
Stop runaway agent loops in DeepSeek Harness: denies repeated identical tool calls and enforces a per-agent call cap, outside the model where instructions cannot reach.
A DeepSeek Harness plugin that lets an AI agent live and act autonomously in Minecraft — mineflayer service + MC tools, driven by a local Qwen3.8 model.
Text-to-image for DeepSeek Harness: a `draw_image` model tool, an input-bar 生图 button with a prompt popup (async generation, 4-grid results, download / keep / delete), an /imgdraw image route, and persisted history. Backends: DashScope wan2.7-image (free default) and SiliconFlow Qwen-Image.
DeepSeek Harness Web 插件：输入框工具行的额度徽标，跟随当前模型供应商切换，零配置按在用路由自动开源。官方真值来源：DeepSeek /user/balance、Moonshot 开放平台、OpenRouter credits、阿里云 BssOpenApi（AK/SK）、千问 Token Plan 控制台网关（Cookie）；官方无额度接口的供应商显示明确标注「实测」的本实例窗口。含模型工具 token_plan_quota。
DSH vision bridge (DSH >= 0.1.2-rc.1): when the selected chat model is text-only, attached images are described by a local Ollama VL model (qwen3-vl:8b) with keep_alive VRAM cooling. Install-time patch of dsh-api-session-controller prompt admission + runtime status companion.
图片转文字输入插件：给无视觉能力的纯文本 LLM（DeepSeek 等）提供图片输入接管。输入框粘贴/拖拽图片后一键转为结构化文字描述；视觉 API 配置在设置页填写，支持任意 OpenAI 兼容视觉模型（qwen-vl / gpt-4o / glm-4v 等）。多模态模型下自动让位，不劫持原生图片通道。
DeepSeek Harness 视觉桥：自动发现你已配置的多模态模型，给纯文本主模型装上 vision 工具，识别结果以纯文本返回。零配置，一条命令安装。
DeepSeek VisionPlus — official-grade vision extension for DeepSeek Harness. Routes image understanding to a free vision-model pool (Zhipu GLM, SiliconFlow Qwen) with automatic fallback, rate limiting, one-click platform tests and live status lines; text stays on DeepSeek. One-command install. MIT.
On-demand vision for text-only LLMs in DeepSeek Harness: keep pasted/attached images in the backend, and let the model call view_image to look at them anytime via any OpenAI-compatible vision endpoint — as if the model were natively multimodal.
Hot-disposable realtime voice Agent plugin for DeepSeek Harness WebUI and future WeChat Mini Program clients
Model-facing analyze_image tool for the DeepSeek Harness: multi-modal image understanding via any OpenAI- or Anthropic-compatible vision API, with 8 analysis modes, local path / http(s) URL / data URL input, and a Web UI hint that guides image-incapable models to the reliable local-path route.
Image generation tool for DeepSeek Harness — Doubao Seedream 5.0 Pro / qwen-image-3.0-pro, watermark-free, inline in-chat display.
DeepSeek Harness live voice preview with exact-session consent, a local synthetic demo, and one bounded manual turn
DSH plugin: OAuth sign-in for Claude, Codex, Grok, Antigravity, OpenRouter, Agnes AI, Qwen, Spark, ERNIE — expose subscription LLMs as DeepSeek Harness providers
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.