dsh-cross-session-agent
Unofficial bounded peer discovery, messaging, receipts, and safe context projection for DeepSeek Harness agents.
883 results
Unofficial bounded peer discovery, messaging, receipts, and safe context projection for DeepSeek Harness agents.
DeepSeek Harness plugin for inspecting live session system prompts and injected context
AntV AVA and GPT-Vis plugin for DeepSeek Harness: stream data-heavy answers as narrative text, charts, or both.
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.
Call a new-api (one-api style) relay station's video model from the conversation, with @-referenced image/video materials plus a prompt.
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)。
Static and runtime security guard for the DeepSeek Harness: scans plugins and workspaces for malicious code, context injection and token waste (block/warn/clean), intercepts dangerous runtime tool calls and prompt steps, and exposes /scan, plugin_scan, the scan web panel and a user-managed allowlist. Fully static analysis — never executes scanned code.
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。
DSH vision bridge (DSH >= 0.1.2-rc.1): when the selected chat model is text-only, attached images are described by a local Ollama VL model (qwen3-vl:8b) with keep_alive VRAM cooling. Install-time patch of dsh-api-session-controller prompt admission + runtime status companion.
A dsh policy plugin that gates kubectl writes by kubeconfig context: hard-deny irreversible verbs outside local clusters, ask for the rest.
Windowed, reversible context management for DeepSeek Harness; replaces Basic compaction.
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)
DSH 一次性只读旁问插件:基于当前上下文回答,独立气泡,不执行工具 · One-shot read-only side-ask plugin: answers from current context in an independent bubble, no tool execution
乔哈里认知四象限对话梳理工具 / Johari cognition-quadrant dialog prompt composer — adds a button above the composer that opens a 2×2 quadrant panel (我知道/不知道 × AI知道/不知道) to groom conversation context into a structured prompt written back into the draft.
Persistent project memory, context-safe agent handoffs, checkpointing, evidence tracking, and long-running task continuity for DeepSeek Harness
DeepSeek Harness host plugin: archive raw tool results into the session folder, clear them from the visible conversation at round boundaries, and let the model recall them through a read_tool_result_log tool.
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。
DSH better-sidebar plugin: read paper PDFs and translate a selection with the LLM, contextual and isolated from the main conversation.
Share a selected range of chat messages as Markdown, HTML, or plain text (Web /share command, Header button, sidebar ... menu, redaction, auto-save)
OpenViking memory & context bundle for DeepSeek Harness: auto-recall, session capture, threshold commit, offline outbox replay, self-contained MCP tool bridge, viking:// URI guard.
Manual budget-targeted context compression for DeepSeek Harness: the conversation model picks ranges, a cheap flash-tier route writes the checkpoint summaries.
Tiered micro-clear layer for DeepSeek Harness compaction: clears whitelisted re-runnable tool results to placeholders before the official summarization tier, freeing context with no model call.
Quote selected Web conversation text into the DeepSeek Harness composer for targeted follow-up turns.