生産性ツール · DeepSeek Harness プラグイン — 105 ページ

DSH plugin: owns the sidebar workspace browser (vendored from the official plugin) so project-grouping logic can be layered onto the real UI instead of a reimplementation.

Project board for DeepSeek Harness: kanban card groups, cards linked to landfill-project memory, mounted repos, a pinned 项目区 workspace, and project sessions that auto-load card memory.

Project Context Engineering for AI agents: turn messy project context into a clear, actionable workspace.

Local project, requirement-group, and conversation workbench for DeepSeek Harness Web and Desktop

DeepSeek Harness Web plugin for date-organized projectless sessions under Documents/DSH

Project-oriented workspace and session management for DeepSeek Harness.

PRO-LONG-style programmatic memory for DeepSeek Harness: appends every session event to a per-workspace log.txt that the agent retrieves with grep/python. Built-in write probe, /prolong status command and permission-deny counter.

Trae-style input booster for the dsh web GUI: a sparkle (✨) button beside the model selector optimizes the typed draft into a high-quality, faithful, directly executable prompt via the session's default model; after optimization the button becomes an undo (↩) icon that restores the original input. Zero-build pure-JS plugin: the host half serves /api/prompt-boost/optimize (llm.stream), the browser half registers the conversation.input.right slot.

DSH web plugin: a star button beside the composer that rewrites the current draft into a clearer prompt, combining PromptForge rule diagnosis with the session's own default model.

System-prompt template injection for DeepSeek Harness: manage named prompt templates and inject the selected one (global default plus per-workspace overrides) into every session's system prompt.

AI 提示词优化器 DSH 插件：/optimize 命令 + optimize_prompt 工具，按《提示词工程师规范》把口语化需求转为结构化提示词；上下文感知锚定、结果自动填入 harness 输入框（复用 DSH ctx.llm 模型路由，零密钥自管）

AI 提示词优化器 DSH 插件：/optimize 命令 + optimize_prompt 工具，按《提示词工程师规范》把口语化需求转为结构化提示词；上下文感知锚定、结果自动填入 harness 输入框（复用 DSH ctx.llm 模型路由，零密钥自管）

DeepSeek Harness 插件:在发送栏旁一键分析并优化提示词(复用当前会话模型)

Local, per-session prompt stash for DeepSeek Harness Web

A session-bound agent-native REPL for DeepSeek Harness PTC mode.

CodeAct agent loop for the DeepSeek Harness: a persistent IPython session as the model's action space, with harness tools bridged in as a virtual `__dsh__.tools` module.

Route allow-listed QQ private messages into an isolated dsh workspace through OneBot 11.

QQ ↔ DeepSeek Harness agent bridge over OneBot v11 (reverse WebSocket): per-group/per-user session grouping, @-quote voice speech-to-text (GLM-ASR / OpenAI-compatible), quote & image resolution, face/sticker tools, /new /status commands. Independent bundle; remove anytime: dsh plugin --profile web remove dsh-qq-onebot-bridge

Self-contained quant workspace for DeepSeek Harness: bundled Python engine (Yahoo data) with pluggable strategies — single-ticker signal card / backtest / review tools.

DSH plugin: a one-click archive button on every sidebar session row, beside the ⋯ menu / 给侧边栏每个会话行加一个一键归档按钮（在 ⋯ 旁边）

DSH web plugin: manageable quick-reply text chips in the current session input area; one tap sends the stored text as an ordinary user message (queue while idle, steer when the top-level session runs). Independent source, user data and DSH install stay separate for easy upgrade recovery.

dsh-cost-meter 的 fork:会话费用/Token 缓存统计 + 统一额度看板(DeepSeek 余额 / OpenCode GO / Kimi For Coding / GLM Coding Plan / 火山方舟)。Fork of dsh-cost-meter with a unified multi-provider quota dashboard.

Event-Driven Autonomous Agent Runtime for DeepSeek Harness. Watch any event source (HTTP/file/command/webhook), match conditions, and spawn an isolated ReAct Agent Session that autonomously achieves your goal — with budget gates, retry, deterministic verification, failure classification, run trace, and a floating widget UI.

Import Claude Code / Codex CLI conversation history into DeepSeek Harness (DSH): each conversation becomes a native DSH session under its original workspace.