Plugins

dsh-ecolink DSH 适配层:直读本地记忆池、pre-step 注入(打分+预算+会话去重)、#记忆名 过滤,打通网页端记忆生态

The Mayfly terminal UI bundle for DeepSeek Harness

Persistent, cross-session multi-agent team rooms for DeepSeek Harness — members, a message bus, a shared task board, and a shared timeline that survive restarts.

Lifecycle orchestration engine for AI agent teams with task-scoped Git worktree isolation, state-gated delivery transitions, and off-context memory.

Agentic answer reviewer for DeepSeek Harness: each final assistant turn is re-reviewed by a separate LLM graded 1-100; below-threshold scores steer the agent back with concrete feedback. The score is shown as a chip on the answer's action row (green pass / red needs-work, with retry count and reason on hover). Live gate config over a 127.0.0.1 HTTP server, plus a collapsed dock above the composer and an optional right-sidebar tab via dsh-better-sidebar.

DeepSeek Harness 数据源连接插件，支持数据库元数据发现、AI 语义建模、只读 SQL 查询和固定 HTTP API 调用

Smart session titles for DSH: after each conversation turn an independent auxiliary LLM call summarizes the full user+assistant transcript into a title that follows the session's real topic instead of echoing the first message; the first message is titled instantly, failed built-in titles auto-retry on later turns, manual renames are never overwritten, and subagent/fork sessions are skipped.

Remote development over SSH: pick a directory on a registered machine as the session workspace and the file, shell, bash, and search tools run on the remote host — the agent works there with the same local tools, and no extra model-facing tools are added.

Multi-model orchestrator: the main brain decomposes complex tasks and dispatches subtasks to GLM / Kimi / Qwen sub-agents by each model's strengths, with per-model token usage.

Runs one-time and RFC 5545 recurring Agent tasks in fresh DSH sessions, with visual schedule editing and session-linked history.

Governed long-term memory for DeepSeek Harness: append-only evidence ledger with write guards, 7-tier authority claims, supersede chains, and budgeted pre-step injection with per-domain quotas.

DeepSeek Harness plugin that aggressively saves tokens without affecting task quality: lossless head/tail truncation of tool results (default), grep-result folding, pressure-triggered dsh-compaction-basic delegation, and an LLM-summary CompactionEngine subclass for the aggressive mode. Saves 97.6% of input tokens on an 8-scenario synthetic suite, with all reductions routed through dsh event flow so model-visible = logged stays intact.

Personalization for the agent: a Web UI panel (about-you, reply style & tone, traits for headings/lists and emoji, output language, custom instructions) and `/soul` commands, with nickname/occupation/bio/style/traits/language compiled into a system prompt and re-injected into active sessions. Exposes `soulConfig` for other plugins and a `set_persona` tool the agent can call.

Switch the language of the agent's thinking/reasoning process (chain-of-thought): 简体中文, English, Русский, Français, Deutsch, Español, 日本語, 한국어 and more, or auto-follow the system locale. Adds a Settings → General row, a system-prompt instruction (per-prompt assembly, applies to new sessions), and the /thinking-language command.

Give DeepSeek (text-only) models vision in Claude Code, Codex, and Agent Plugins clients: describe images via any OpenAI-compatible vision endpoint.

Research-debt guard for DeepSeek Harness: nudges coding agents to search docs, GitHub and the web before repeated local trial-and-error.

Learns what you leave unsaid in your prompts from messy turns and your own corrections, and injects the learned directives into the system prompt of every new conversation; the directives are editable in Settings and a composer button rewrites the current draft with them.

Rate-limits LLM requests per provider and per model using a reservation-based token bucket, with queue or reject modes, plus gateway identity rules that rewrite user-agent and inject custom headers.

Search, monitor, interrupt, and batch-archive workspace subagents, featuring real-time activity streaming and an active-agent floating panel.

Commander mode for the dsh web GUI: a one-click session header button injects a protocol brief into the session, then parses and auto-executes task blocks in the model reply — separating the strategist loop from worker loops via a visible badge.

Recall, edit-and-resend and regenerate, plus in-conversation versioning: a timeline of every rewind, artifact rollback (git-first, snapshot fallback), a fork map of explored paths, session lineage, and a real-time watchdog that snapshots the log at the first sign of concurrent writes. Edits auto-stop the running agent (official cancel/whenIdle) so rewinds never corrupt the durable log or break /compact.

Register locally-defined custom agents as callable subagents in dsh: the main conversation invokes any agent by name via use_agent, each running as a real dsh subagent with its own persona. Supports breakpoint resume for interrupted runs.

Let your AI agent see and operate a real Android phone: phone_look (vision + UI-tree fusion), tap/swipe/type, screenshot — over adb, for any MCP client.

A content-aware PDF reading plugin for vision models: profiles each page for figures (vector and raster), tables, formula risk and double-column layout, then applies content-aware hybrid extraction, rendering figure/table/formula pages as high-DPI region crops. Provides a low-resolution preview to understand the page layout, and renders a specified region at high resolution. Packaged as multiple tools for agents.