222 results
Automatic model routing for DeepSeek Harness: a virtual `smart` model classifies every request by difficulty (hard / normal / easy) and by vision need, then delegates to the models you already configured in Settings → Models. 内置智能路由：三级难度 + 视觉自动路由，模型从「设置-模型」已配置模型中选取，虚拟 smart 模型零配置接入。
Use ZenMux models in DeepSeek Harness with OAuth login, model search, and protocol-aware routing
Grok (xAI) subscription OAuth provider for DeepSeek Harness: one-click login in Settings → Models, token refresh, live catalog, streaming over cli-chat-proxy.grok.com
Context compression for small-context models on the DeepSeek Harness Web GUI: one click condenses the whole conversation into a few sentences, opens a fresh session in the same workspace, and re-injects the summary as the first message so a small model keeps working with a clean, compact context.
Compare multiple coding models side by side in DeepSeek Harness with isolated Git worktrees
模型路由网关：一个端点连接 290+ AI 提供商（90+ 免费、1200+ 模型），Claude Code/Codex/Cursor/Cline/Copilot 全兼容——配额感知自动回退、19 种路由策略、RTK+Caveman 叠加压缩省 15-95% token、免费层聚合预算（~1.5B tokens/月）、MCP/A2A、本地优先。受 diegosouzapw/OmniRoute（51k★ MIT）启发。
Use OpenCode models inside DeepSeek Harness without a separate provider API key.
DSH 插件：给所有非官方（自定义）提供商的模型自动填充模型信息，包括：推理级别、最大上下文、输出上限与图片模态，数据来自 models.dev。
Registers generate_image and generate_video tools for Agnes AI media models (agnes-image-2.5-flash, agnes-video-2.5-flash) in DeepSeek Harness. Supports multi-image reference via reference_image_urls.
AI 模型
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.
88API Image Studio for DSH: six Image2, Image 2.5, and Nano Banana models for text-to-image, multi-reference editing, 2K/4K output, and sequential batches.
Single-model disable gate: hides denied models from every discovery path, blocks dispatch with an in-protocol error chunk, and exposes a settings-section UI for the denylist
DSH plugin: keyboard shortcuts to switch models and reasoning effort levels
DSH client plugin: collapsible model-provider groups in the composer model picker — click a provider row to fold or unfold its models
DeepSeek Harness plugin that enhances custom provider setup by auto-discovering models and auto-populating contextWindow, maxTokens, vision, and reasoning capabilities from models.dev
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.）
dsh-eye-vision: give text-only DeepSeek Harness models eyes — image understanding via any OpenAI-compatible multimodal API. Fork of dsh-free-vision with custom-provider fixes and an allowed-directories whitelist.
增强的模型设置页插件：为自定义模型提供每模型推理强度（reasoningEfforts）编辑，OpenAI 兼容网关可直接勾选 low/medium/high 等档位；聊天模型选择器随之显示 Effort 菜单。
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
DSH-native vision bridge for text-only models with native image attachments, multi-image evidence batching, and session-scoped validated Evidence caching.
Auto-switch DeepSeek models for DeepSeek Harness: routes every model request to the vision model when images are present, to the pro model for complex tasks, and to the fast model otherwise; includes a switch_model tool for manual per-session overrides.
DeepSeek Harness relay plugin for reasoning-effort autofill, /models sync, and a capability-aware Fast toggle.
DSH-native multi-AI group chat: the host (user) runs a chatroom of configurable AI agents with per-agent models, role cards, mute controls, and passive/active speaking modes — pure Node.js/Cordis, no Tauri/Rust