72 results
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.
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.
Argo 阿尔戈 — 统一搜索与证据核验。多语言检测与跨语言回退；约 120+ 引擎 TF-IDF 路由 + RRF；影视/体育/地理/组织/媒体/金融/宏观/化学等垂直源；垂直结构化模态卡（火车票/油价/贵金属/万年历/星座/手机/汽车/挂号）；日常 combo 预算与深度研究 boost；recovery 防污染；Selection×Absorption；MCP（含 argo_local_search）。入口：install.sh / npx github:taxueseek/argo / mcp_server.py。
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.
ChatGPT-style text selection helper for DeepSeek Harness: select text in a conversation and a floating 「询问 DeepSeek」 button appears; click it to quote the selection into the composer.
API Key rotation pool for DeepSeek Harness: multiple keys per provider, weighted round-robin selection, automatic failover on 401/429/403, cooldown and recovery probing, usage statistics.
选区引用与锚点批注：在 DSH 会话中选中文字 → 批注 → 引用锚点 chip（点击跳回原文、悬停显示原文）→ 提交序列化为结构化引用块。
DSH composer model seat with accessible per-provider collapsible groups.
DSH web client plugin: select text in a chat message and quote it into the composer as an inline reference chip; the full text materializes on submit via the input-trigger reference codec.
Aggregate and natively control DeepSeek Harness sessions across multiple remote dsh web servers from one pane: server registry, merged session list, history, prompt, cancel, rename, fork, model selection and approval/question answering.
A DeepSeek Harness (DSH) agent preset for institutional multi-factor stock-selection research: methodology knowledge base + zero-dependency factor statistics.
A searchable, sortable model picker for the DeepSeek Harness Web UI — provider groups, favorites, live per-task cost, prices and context windows.
Claude Code integration plugin for DeepSeek Harness, providing native Claude conversations powered by the Claude Agent SDK, with model selection, approvals, questions, tools, and session continuation.
Codex-style multiple independent selection comments for DeepSeek Harness (DSH).
Best-of-3/5 orchestration and LLM-as-a-Verifier selection for DeepSeek Harness
Web-switchable agent loop engine selection for the DeepSeek Harness - out-of-tree plugin (Claude Code / Codex / Pi / Kimi Code drivers) maintained by @kuun993, zero main-repo changes
Selection quoting for the dsh web GUI: a toolbar over selected assistant text that attaches the selection to the composer as a removable quote banner, prepended to the outgoing message at send
dsh plugin + agent preset that replicates opencode + oh-my-openagent (omo): opencode's toolchain and system prompt, omo's multi-role subagent orchestration, and browser-side omo role selection + per-role model/fallback settings.
Selection annotations for DeepSeek Harness assistant replies, sent through the official composer
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.
GPU-aware execution layer for DeepSeek Harness: gpu_status / gpu_exec / gpu_run_bg tools, per-step GPU context injection, automatic CUDA_VISIBLE_DEVICES card selection
Select text in a conversation to get a floating toolbar: copy, quote-reply, ask/explain/translate/summarize, and a /btw side-question console (context-only answers that never enter the conversation). AI actions reuse the current session by default, with a per-action main-thread/side-channel destination switch.
Explicit model input-modality selection for the DeepSeek Harness Web UI
DSH plugin: start/stop a local llama.cpp llama-server from the settings → plugins page — two model slots (A/B) with per-slot model-file selection, eight editable launch-parameter groups (text/vision × fast/long × 2 slots), and one shared DSH provider carrying both slots' models with four thinking-effort levels.