dsh-umi-ocr-vision
Umi-OCR vision bridge for DeepSeek Harness: when the main model is text-only, OCR images with local Umi-OCR and let the original DeepSeek model answer.
909 results
Umi-OCR vision bridge for DeepSeek Harness: when the main model is text-only, OCR images with local Umi-OCR and let the original DeepSeek model answer.
每日财经日报:免费数据源(Yahoo Finance / CoinGecko / Google News)生成中文财经日报,按计划定时通过 WhatsApp 推送(依赖 dsh-im 的 bot.sendText 主动发送端点)。
MCP orchestration layer for DeepSeek Harness — multi-server routing, health monitoring, fallback, and tool aggregation
A vision bridge for text-only DeepSeek Harness models: registers an `analyze_image` tool that answers questions about images via ANY OpenAI-compatible vision/multimodal endpoint (SiliconFlow, DashScope, Zhipu, OpenRouter, Ollama, ...).
dsh-thesis governed local thesis context bundle for DeepSeek Harness
DSH plugin: convert user-sent non-text files (PDF/DOCX/XLSX/PPTX/HTML/CSV/EPUB/…) into LLM-friendly Markdown with Microsoft MarkItDown — composer file button + model-facing markitdown tool + send-time auto-convert.
Session ID footer for DeepSeek Harness: shows the current session id in small text under the composer, click to copy.
Turn a paper into an academic talk for DeepSeek Harness (dsh) — 论文转 PPT / 组会汇报 / 会议报告 / 答辩 / 开题. Reads the real full text, budgets the slot per venue, and builds the deck around the figures with the speaker notes written as the script. Drives dsh-ai4scholar and dsh-slides.
@-mention context references for DeepSeek Harness: workspace file search and cross-session references from the web composer.
DSH plugin: compress verbose voice-dictation text into token-efficient prompts, fully local.
Selection-based comments for the DeepSeek Harness Web UI: select text in the chat, comment on each selection, then submit all comments as one message.
DSH plugin: when a provider's model sync returns only ids, automatically fill display name, context window, max output tokens, reasoning efforts, and input modalities from the models.dev catalog (cached, TTL-refreshed), and surface a settings page with toggles, refresh, and a fill report.
Cross-session memory plugin for DSH — auto-extraction, semantic recall, scheduled maintenance, LLM-powered consolidation, context explosion prevention, global Soul identity
文本换行
Drag & drop anything into the DSH composer: local files upload to <workspace>/.dropped/<sessionId>/ and insert absolute-path references; web images / URLs download host-side then reference; plain text inserts into the composer (oversized text becomes a file).
LongCat (LongCat-2.0) model provider for DeepSeek Harness — 1M context, thinking mode, tool calling
Conversation branches: select main-conversation text to open IM-style Q&A branches in the right details column
小说写作助手插件(v5.1.1):句式/情感/意象分析、伏笔设定管理、本地语义检索、氛围光谱、风格画像报告、文笔六维基线带、原创模式与创作资料、写作哨兵(衔接/OOC/大纲);附 stdio MCP 服务器(Claude Desktop / Cursor 可用)。
查看、搜索和恢复已归档会话,支持按工作区批量归档、备份导入导出与回收站管理。
Lifecycle-safe Codex-style Session context actions for DeepSeek Harness.
Lightweight DSH upload bridge: images and common documents become workspace paths so a text-only DeepSeek model can read them with Qwen-MM-Plugins vision tools.
DSH WebUI 语音输入插件(火山引擎流式 ASR / 豆包 Seed ASR):输入框麦克风按钮(Alt+V)→ 浏览器采集 16kHz PCM → 经宿主 WebSocket 中继到豆包流式识别 → 实时回填(跟随光标/Proma 式输出,失败兜底剪贴板)。协议实现源自 Proma 桌面端调研复刻。
Quote-to-composer UI plugin for DeepSeek Harness Web: select conversation text in the chat and send it together with your next question
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.