dsh-vision-opencode
DeepSeek Harness plugin: configurable vision model with vision_read_image tool, composer-bar vision-model selector, and automatic image-to-text conversion for text-only main models.
796 results
DeepSeek Harness plugin: configurable vision model with vision_read_image tool, composer-bar vision-model selector, and automatic image-to-text conversion for text-only main models.
Drop or paste images, PDFs, office docs, zips, videos and audio into the DSH composer as workspace file paths instead of model attachments — lets a text-only model agent read them via vision tools.
DeepSeek Harness plugin: paragraph-batched streaming reveals with 8 designed animations, smooth scroll-follow and a settings panel.
Expose DeepSeek Harness agent capabilities as an MCP server, so an external MCP client (e.g. Hermes) can drive Harness to execute coding tasks. Hermes = brain, Harness = arms.
A live context-window donut for DeepSeek Harness: token usage, compaction savings, and cost at a glance
Per-model capability declaration for DeepSeek Harness: reasoning-effort levels (with wire spellings) and request modalities (text/image) for OpenAI-compatible providers — one settings section, no YAML hand-editing.
Generate complete AI songs, instrumentals, and BGM with YinChao, including lyrics-to-song, reference-audio creation, and song extension.
Give DeepSeek (text-only) models vision in Claude Code, Codex, and Agent Plugins clients: describe images via any OpenAI-compatible vision endpoint.
OpenViking retrieval, resource management, auto-recall and session memory for DeepSeek Harness.
Reduce large agent tool output by what it means, not by where it was cut.
A DeepSeek-style paperclip attach button in the DSH web composer; uploads files to the DSH host (model-aware: native image blocks for multimodal models, file paths for text-only models).
DeepSeek Harness plugin that connects to a PowerContext Server over HTTP for recall, memory, handoff, experience, and skills.
Make your AI harness speak — voice announcements for DSH and other AI coding harnesses (Windows SAPI5 + macOS system voices)
DeepSeek Harness Telegram mobile remote: workspace→session, /last context, /model — dsh-plugin
Transient /btw side questions for DeepSeek Harness: immediate while the main agent is busy, context-sharing, tool-free, one-shot, cache-aware, and invisible to the main session catalog.
Headroom-inspired automatic context compression plugin for DeepSeek Harness (dsh): compresses tool outputs before they reach the model and keeps every lossy compression reversible via CCR retrieval tools.
Voice-first session loop for DeepSeek Harness: a composer microphone button with browser/local speech-to-text (Web Speech, FunASR, whisper.cpp), a speak tool for text-to-speech replies (browser, edge-tts, piper), event announcements with mute, and speak-to-interrupt.
Search large MCP catalogs in DeepSeek Harness with two tools, on-demand schemas, and structured results for multi-step workflows
Image2 (gpt-image-2) generation plugin for DeepSeek Harness with simple relay settings and in-conversation image previews
CodeGraph for DSH — registers native `codegraph_*` tools (core surface: status/init/sync/explore; full surface adds query/node/files/callers/callees/impact/affected/index/uninit) wrapping the `codegraph` CLI, plus a prompt front-load hook that steers structural CodeGraph context into structural prompts, so the DSH agent can bootstrap, maintain, and query a pre-indexed code knowledge graph without grepping files.
PDF toolbox for DeepSeek Harness: extract text, metadata, and page ranges from PDF files (local parsing, no API key).
Persistent project memory for dsh agents: index docs (PDF/Markdown/text) and code symbols into a searchable per-workspace store, recall them with cited sources, and keep experience entries (problems -> solutions) searchable on demand.
造书工作台:把教材 PDF 加工成「AI 教学蓝本」的 6 阶段流水线(dsh 插件包)。主 AI 统筹跑流水线(亲自做或派小助手分头干),用户只做四件事:上传材料、确认探查结果、在关卡拍板、抽查提意见。全程中文,无需技术知识。
会话级自动上下文压缩插件:回合中每步前 + 回合结束检测上下文用量,超过会话阈值自动 compact,摘要注入上下文后自然继续(DeepSeek Harness / DSH)