59 results
Repository-root manifest for the DeepSeek Harness plugin that lives in extensions/dsh — the same package published to npm as dsh-deja. It re-exports the subdirectory so the plugin installs from a bare git URL or from github:vshulcz/deja-vu#path:extensions/dsh; the npm package is the shorter path. The repository itself is the Go project behind the deja binary.
让 DeepSeek Harness 里任何纯文本模型都能读图。识图是按需调用的 tool —— 图片不进主模型上下文，不看就不花钱；附 23 处缺陷的评测集，换模型可自测。
DeepSeek Harness plugin bundle: qwen_vision (Qwen-VL image understanding) and qwen_generate (Qwen-Image text-to-image and image editing) tools for text-only models
Free vision plugin for DeepSeek Harness (dsh): image understanding for text-only models with free-tier providers (Qwen3-VL-Flash / DeepSeek-OCR / Doubao). 免费视觉插件：纯文本模型看图能力，优先免费模型（通义千问 / 硅基流动 / 豆包）。
Voice AI girlfriend for DeepSeek Harness: FunASR mic input, Qwen3-TTS voice replies, companion animation window, QQ two-way chat. Needs the repo's voice bridge + NapCat.
DeepSeek Harness QoL plugin for the local Qwen3.8 line (27B, Flash-Next): per-request thinking budgets on both llama.cpp and NInfer dialects, vision + tools, and a compaction backend whose summaries stop burning the output cap on thinking.
In-session cross-agent dispatch for DeepSeek Harness: a zero-dependency skill and a host-only bundle that send self-contained tasks to 11 external agent CLIs (Codex, Claude Code, TraeCode, OpenCode, Gemini, Cursor, Kimi, Qwen, Copilot, WorkBuddy, Grok).
DeepSeek Harness 全能插件：识别/生图/改图一体化，无需切换模型——用常规 DeepSeek 模型即可自动调用视觉与生图模型（gemini_vision / gemini_generate_image / gemini_optimize_image）。多后端：Gemini 原生 + 任意 OpenAI 兼容服务（GPT-4o、Qwen-VL、GLM-4V、Moonshot、gpt-image、DALL-E、Flux、Stable Diffusion、OpenRouter、硅基流动、各类中转等），生成后自动视觉自检反馈，优于 modlens。
A DeepSeek Harness (dsh) plugin: orchestrates complex tasks across multiple models — a 'main brain' decomposes the task and dispatches subtasks to GLM / Kimi / Qwen etc. sub-agents by each model's strengths, with per-model token usage.
DSH plugin: image understanding via any OpenAI-compatible vision API, paste-to-describe, and an animated whale-buddy desktop pet with status bubbles and a floating settings panel
DSH plugin: renders images inline in DeepSeek Harness Web chat and gives text-only models vision — cloud multimodal API first, local Qwen3-VL fallback.
DSH plugin: start/stop a local llama.cpp llama-server from the settings → plugins page — two model slots (A/B) with per-slot model-file selection, eight editable launch-parameter groups (text/vision × fast/long × 2 slots), and one shared DSH provider carrying both slots' models with four thinking-effort levels.
Voice control and multi-session task dispatch for DeepSeek Harness, powered by Qwen Audio Agent
DeepSeek vision bridge for the dsh web GUI: route image attachments to a vision model (pi-ai / llama.cpp Qwen3-VL) and continue the conversation with the text description on a text-only LLM (DeepSeek)
DeepSeek Harness (DSH) 识图插件：为不具备原生识图能力的模型提供识图能力，把图片发送给阿里云百炼/智谱多模态模型并返回文字描述。由 claude-vision-skill 移植适配。
Local multi-plan bridge for DeepSeek Harness: use your existing ChatGPT Codex, Claude, ZCode (GLM) and Qwen subscriptions through one loopback proxy, with a settings-page status card and one-click provisioning. No dsh core changes.
DSH standard vision skill: Qwen dynamic-resolution preprocessing + OpenAI-compatible VLM chain with failover/429 backoff, structured evidence mode, local tesseract-first long-screenshot OCR, paste-to-path (no framework patch). 8 tools + runtime skill.
多个可选择的 DeepSeek Harness Agent Presets 集合
DSH plugin (NInfer engine only): fixes compaction failure on local qwen3.8-27b gateways served by NInfer — xhigh thinking burns the entire output token budget, so thinking is off for compaction-only, with the model's non-thinking sampling parameters; the same idea applies to other launch methods
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。
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）
DeepSeek Harness 原生插件：让纯文本模型（如 DeepSeek）经 agent/pre-step 劫持 + resolveModelInfo 包装自动识别上传图片（qwen-vl），使纯文本对话也能“看见”图片。