dsh-context-console
DSH context console with trajectory, prompt/skill/MCP/tool inventory, message forging, and conservative session-log recovery.
848 results
DSH context console with trajectory, prompt/skill/MCP/tool inventory, message forging, and conservative session-log recovery.
Ask any line of code its backstory: what it does, and why it's here — grounded in git history and the agent's own session log. Ships a DeepSeek Harness plugin and a standalone MCP server.
Windows minimal agent preset for DeepSeek Harness: a one-line fixed persona, gitbash + str_replace_editor + web_search, no runtime context, no compaction. Installs the preset into the user's agent-presets root.
AI 生图 (image generation) plugin for the dsh web GUI: text-to-image and image-to-image through a configurable OpenAI-compatible endpoint, with multi-provider support, model discovery, and agent tool registration. 与 @xiaoyuink/dsh-image-vision 同系列的图像插件。
Labnana image generation for DeepSeek Harness: text-to-image / image-to-image / precise editing with credits estimation, subscription balance and web settings UI.
DSH plugin: 深海摸鱼 —— context 越深潜得越深,答完摸鱼集镭射生物卡 | Deep-sea slacking holo cards
Customizable theme plugin for DeepSeek Harness web UI. Ships with a Xiao-style jade palette by default; accent color, mascot badge text, injected voice and frosted background are all configurable. Built with TypeScript and pnpm.
GLM 视觉模型插件:注册 glm-vision 供应商路由(glm-4.6v 系列,image+text 输入声明)并提供 glm_vision 工具,让 DeepSeek 等文本主模型直接调用智谱视觉模型看图。
自然语言查询 + 商业智能报表插件 for DeepSeek Harness:在 dsh-mysql 连接底座之上,提供 Text2SQL 自然语言查库、15+ 图表类型、Dashboard 仪表盘、指标/维度管理、多维分析、自助分析、报表导出、审计日志与数据权限。Natural-language data queries + enterprise BI reports for DeepSeek Harness: Text2SQL, 15+ chart types, dashboards, metric management, multi-dimensional analysis, self-service analysis, export, audit log and data permissions.
Cross-session memory cue bank for DeepSeek Harness: builds a persistent event-cue library (keywords, user language idiosyncrasies) and re-activates remembered event details on topic switches, mirroring human episodic recall.
Mojibake interceptor for DeepSeek Harness: feature-based garbled-text detection that interrupts garbled writes and asks for review (an identical retry passes).
Message edit / regenerate for DSH Web: inline edit of assistant replies (text + reasoning), regenerate replies, and user-message edit — a Cordis host plugin serving /api/msg-edit/* plus a dsh.client UI plugin contributing to the assistant action strip.
DeepSeek Harness bundle for a Windows desktop UI context picker and MCP server for Codex, DeepSeek Harness, and AI agents
Vision sidecar for text-only coding agents.
Model-authored context pruning for DeepSeek Harness through the official compaction API.
Native knowledge context for DeepSeek Harness
Persistent vision plugin for DeepSeek Harness: registers the vision_analyze tool backed by a configurable multimodal model, with a settings-page UI. Zero dependencies.
Vision-augmented DeepSeek adapter plugin for DeepSeek Harness: a vision-capable model describes image input, then a text-only DeepSeek model reasons over the description
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)
VSCode-style file explorer for the DeepSeek Harness web client: a body-mounted, draggable right sidebar with virtualized lazy file tree and text / Markdown / image preview. Does not depend on the native details slot, so it works on blank sessions.
Voice input plugin for DeepSeek Harness
Host-level vision bridge for text-only models: analyze_image tool (Ollama local / Xiaomi MiMo cloud / any OpenAI-compatible endpoint) returning structured evidence.
Web-enhanced plugin for DeepSeek Harness: task board with cron scheduling, git graph, preview/files/SCM right panel, DeepSeek balance line, and image understanding for text-only models
DSH Web selection-annotation plugin: select assistant text, annotate (optional), and press Enter to send the annotation block with your message — the model replies to each annotation by number, with hoverable chips in the reply.