@dsh-extension/dsh-vision-bridge
On-demand vision for text-only DSH sessions: images become markers, and a vision_describe tool sends only image + question to an OpenAI-compatible vision model
1103 results
On-demand vision for text-only DSH sessions: images become markers, and a vision_describe tool sends only image + question to an OpenAI-compatible vision model
dsh plugin: recognize attached images with the built-in Windows OCR engine (Windows.Media.Ocr) and send only the recognized text to the model. Text models never receive image bytes; vision passthrough is opt-in.
DeepSeek Harness usage dashboard with model, provider, workspace, cache, balance, and CSV insights
DeepSeek Harness(dsh)的 MCP / Skill / 记忆管理工具:写入前先连接自检,连不上不写;从 Claude Code / Codex 一键迁移;可装成 dsh 插件,在 Web 里用 /mcp 命令和卡片操作。
Codex-style reasoning-effort slider embedded in the DSH model selector
SHOPLINE AI Toolkit for DeepSeek Harness (DSH): bridges the official SHOPLINE Developer MCP server and ships SHOPLINE agent skills, mirroring the Shopify AI Toolkit architecture. dsh-plugin.
Auditable vision and cross-platform Computer Use runtime for DeepSeek Harness with source-preserving evidence.
Hook DeepSeek Harness into your Hermes pipeline: dispatch-spec template, model-tier routing, quality gates, git single-writer rule — as an installable skill pack.
DSH plugin: auto-fill metadata (context length, output cap, display name, input modalities) for custom-provider models from the Model Metadata Registry (models.dev).
Tuning Engines CLI, MCP server, and Python agent runtime adapters for governed model, agent, skill, and MCP workflows. Fine-tune open-source LLMs, run inference, manage datasets/evaluations, and connect LangGraph or Temporal while Tuning Engines handles policy, audit, usage, and token economics.
J-Space Cognition Suite V3.6 - Inference-time cognitive control and deep reasoning for DeepSeek models
PBR model preview for DeepSeek Harness: render GLB/GLTF game art with physically-based materials, textures, environment lighting, and orbit controls — fence language `pbr3d` + `pbr_render` tool.
Composer mic for DeepSeek Harness Web: tap-to-monitor live transcription and hold-to-talk, with host Edge TTS reply reading that streams while the model generates, echo-pause during reading, and tap-to-stop.
dsh plugin: register codex-web-search-mcp (model-independent OpenAI Codex / Grok web search & deep research MCP server) as a native dsh MCP tool set (mcp__codex-web-search__*).
Enhanced ACP server for DeepSeek Harness: block-level streaming, usage/stat telemetry (cache hit rate, token speed, input/output tokens, context length, turns, tool timing), model & reasoning-effort switching, and permission-preset control over the ACP wire (Zed-friendly)
Read-only CC Switch provider bridge for DeepSeek Harness
DSH plugin: run every agent shell command through Git for Windows bash on Windows instead of PowerShell. Replaces the pwsh executor with a Git Bash ctx.shell provider and materializes Git Bash variants of the standard/minimal/code/cordis agent presets into your user preset root at startup. On Windows it also adopts dsh-better-sidebar's terminal shell (UI tabs and the model-facing terminal_* tools) through the sidebar's official settings seam, and pairs with dsh-ptc-cordis-preset so the PTC Creation-mode preset materializes as its Git Bash variant. Ships both composition eras for dsh <= 0.1.1 (built-in preset id 'code') and dsh >= 0.1.2 (renamed id 'ptc') — the era is probed per boot and re-materialized automatically after a dsh upgrade, in either upgrade order; preset ids never change so pinned sessions stay valid.
Local OCR fallback for DeepSeek Harness (Web): when the routed model cannot accept image input, a pasted image is saved locally and its text read by PP-OCRv5 + ONNX Runtime — fully offline, no vision model required. / DeepSeek Harness 本地 OCR 兜底插件(Web):当接入的模型不支持图片输入时,自动把图片存到本地并用 PP-OCRv5 读出文字,完全离线。
LLM-as-a-Verifier for DeepSeek Harness: fine-grained reward, Probabilistic Pivot Tournament best-of-N selection, and per-step progress tracking as agent tools.
DeepSeek Harness LLM provider for Codex models using managed ChatGPT OAuth
Fully customizable keyboard shortcuts for the DeepSeek Harness WebUI — macOS-first defaults, 34 pre-registered features across session/view/clipboard/model/permission/system groups, one-click recording to add your own bindings, silent permission cycling with color feedback.
DeepSeek Harness bundle: oh-my-opencode-slim style Orchestrator agent preset with model-pinned specialist subagents (explorer/oracle/librarian/designer/fixer/council).
DeepSeek Harness plugin: 在侧边栏展示当前 DSH 中配置的所有模型 Provider 的账号余额(余额面板 + 底部快捷入口)
DSH Web plugin that lets text-only models see images: paste images in the chat and send without file paths; the model discovers its own vision tools. Multimodal models pass through natively.