dsh-agent-context
上下文治理一体化插件:/context 命令 + ctx.contextMeter 服务 + 剪枝工具(prune_candidates/apply/expand/guard/stats)+ 两条提醒通道(上下文提醒 / 压缩告警,状态落盘跨重启去重)
857 results
上下文治理一体化插件:/context 命令 + ctx.contextMeter 服务 + 剪枝工具(prune_candidates/apply/expand/guard/stats)+ 两条提醒通道(上下文提醒 / 压缩告警,状态落盘跨重启去重)
DeepSeek Harness (dsh) plugin — read_pdf tool for PDF text extraction. Read and extract text from PDF files with AI agents / LLM tools, built on PDF.js (unpdf).
Focus board for DeepSeek Harness agents: durable, model-maintained notes in the session workspace that pin the objective, constraints, and decisions across compaction and sessions — with structured entry tags (kind/status), a grouped summary view, automatic context injection, an archive on clear, and an optional read-only web panel
MCP 服务器可视化配置插件:在 DSH Web 设置界面管理 MCP 服务器(stdio / streamable-http / SSE),保存即生效,无需手改配置文件。| Visual MCP server management for DeepSeek Harness: configure stdio / HTTP / SSE servers from the settings UI, hot-synced without editing config files.
MindsEye: model-driven vision tools, structured evidence, and exact cache for DeepSeek Harness
DSH File Explorer: workspace file tree + Monaco editor with real VS Code TextMate grammars, in the DSH Web GUI
LLM pre-review for sandbox-escalation approvals: an independent-context LLM gate answers sandbox escalation requests before they reach the user, falling back to the user on any failure.
Text-to-speech for DeepSeek Harness: speak agent replies in the Web UI with a provider fallback chain (OpenAI, ElevenLabs, Google, Azure, Groq, Deepgram, OpenRouter, Edge, Piper, eSpeak).
MCP management panel for DeepSeek Harness: connection status (green dot), pip/npx local-server upgrade detection & one-click upgrade, add-server form writing cordis.patch.yml, connectivity probe, and usage help.
Deterministic, recoverable tool-result compression and cache-aware compaction for DeepSeek Harness
DSH better-sidebar plugin: read paper PDFs and translate a selection with the LLM, contextual and isolated from the main conversation.
DeepSeek Harness live voice preview with exact-session consent, a local synthetic demo, and one bounded manual turn
DeepSeek Harness plugin: multi-tier memory management, semantic retrieval, structured memory, and model-context awareness for infinite context.
Auto-expand composer for DeepSeek Harness: a ⤢ button appears at the top-right of the composer card when the text wraps to 3+ visual lines, stretching the input to near-fullscreen height on click.
DeepSeek Harness 语音输入插件:在输入框加入麦克风按钮,用浏览器 Web Speech API 把语音实时转成文字填入输入框。
Hybrid memory plugin for DeepSeek Harness: L1 snapshot memory (MEMORY.md/USER.md, read on demand, zero context cost) + L2 searchable knowledge base (one-fact-per-file, SQLite FTS5) + L3 import from Hermes/Claude Code/Codex/WorkBuddy and approved Agent Hub documents. No automatic injection. Data lives on D drive, never C.
Noteboard for the dsh web GUI: a workspace-wide infinite canvas of Markdown sticky notes (.noteboard/), with multi-canvas layouts, tag rearrange, conversation text capture, and an AI distill path.
Memory plugin with built-in governance for DeepSeek Harness
dsh 插件 · 团队知识库:离线知识共享(FDE 盒子场景),浏览/全文检索/加工入口;raw 入料自动入队、bot 会话串行蒸馏成文(Karpathy LLM Wiki 模式:raw 不可变 / 两步加工 / log 流水 / 月度 lint)。
DSH Web 输入体验增强插件:可配置发送/换行键位 + 自定义输入框右键菜单 + 面板尺寸记忆 + OpenCode 会话请求头(含设置页)
Version-pinned live library docs for DeepSeek Harness — kill hallucinated APIs.
DSH 上下文管理插件:任务边界、项目帧、自动判别与上下文优化(开发中,R2 判别域 P8–P14b1 已施工)
Give the DSH agent a clock: injects the current date/time into the runtime context on every turn. · 给 agent 一块表:每一轮把当前时间注入运行上下文。
dsh 插件 · 上下文剃刀:把当前会话上下文逐条列出(角色/预览/≈token,cl100k 估算),超阈值标红,勾选后精确裁剪——不经 LLM 总结,删了什么一目了然。