Plugins

Session export and compliance archiving for DeepSeek Harness: deterministic redaction, Markdown/JSONL/PDF outputs, on-disk archive management, and a trend/audit view.

Self-update for the harness launcher; checks npm for a newer @deepseek-ai/dsh, stages the tarball, and applies it on harness exit or via update-and-restart from the web panel.

Windows desktop UI context picker for Codex, DeepSeek Harness, and MCP clients: select windows, UI elements, or screen regions with hover highlighting, UI Automation, screenshots, and local OCR, then review and approve Markdown/JSON context before output.

Cross-session memory for DeepSeek Harness via the official storage domain: memories persist through ctx.storage (storageDomain table) and are injected into the system prompt through a registered section (memory:recall), with memory_save / memory_forget tools so the agent reads and writes its own memory (maxMemories configurable).

Adds OpenAI Codex (ChatGPT) as a selectable DSH provider via the local Codex App Server.

Daily cost card for your local LLM gateway: /usage reads gateway_usage.jsonl and itemizes spend per model and per hour, covering official direct, OpenRouter relay, and in-plan metered pools.

Token attention management panel for DeepSeek Harness: per-task/day/week/month token usage and cost tracking (input hit/miss, output, reasoning), DeepSeek peak/off-peak pricing, task-type recognition, and advice on when to switch sessions, write a hand-off, or compact context.

DeepSeek Harness (dsh) plugin embedding the fin-trace agent loop — multi-hop relationship reasoning over a financial knowledge graph, exposed as async tools (start/status/cancel)

DeepSeek Harness plugin: Superself's `self` CLI as model-facing tools plus a /self command — cross-session, cross-project project state for agents.

Import, install and invoke Agent Skills in DeepSeek Harness from Codex, Claude Code, OpenCode, GitHub or npm — composer-side ⚡ picker inserts /skill-name into the draft, and a Skill 管理 settings page offers per-source/per-skill import, expandable source paths with skill counts, uninstall and one-click restore from .trash.

Windows minimal agent preset for DeepSeek Harness: fixed one-line persona, three tools, no runtime context.

Multi-backend web_search provider (Exa + Firecrawl) for the built-in web_search tool, with automatic failover, per-backend 429 cooldowns, and key-free anonymous access.

Reasoning-effort tier manager for custom API models plus cross-session preference memory: inline low/medium/high/max toggles inside Settings → Models, with atomic settings writes.

Draft polish for the DSH composer: one-click AI polish of the input draft (sparkles button next to send), with optional conversation context and a configurable model channel.

Matrix-style CLI chat page for the DSH web UI: the agent's thinking streams down the screen as green code rain while replies print normally in the terminal.

China-ready voice input for the composer. Requires a local Python bridge (pip install dashscope websockets, run bridge/voice-bridge.py) — the plugin alone does not work. Browser mic streams 16 kHz PCM to the bridge, which runs Alibaba Cloud DashScope ASR (paraformer-realtime-v2); interim text fills the draft at the cursor, silence auto-stop, optional auto-send.

Android client implementation for DeepSeek Harness: bridges local dsh web to the OneBox app with QR scan-to-pair and an end-to-end encrypted cloud relay tunnel.

Stages exact DSH tool calls without dispatch, presents complete canonical arguments in a durable Batch Review Inbox, invalidates approvals after edits or restarts, and commits only a matching SHA-256 digest plus single-use nonce through the normal DSH tool pipeline.

Pixel-art reasoning-effort slider for DSH Web with continuous 0–100 dragging, 16ms throttled writes, snap-to-level commits, and a WebGL ember fire that ignites as the slider moves.

DSH workspace hub: organize workspaces into color-coded folders in the sidebar (three-level drag reorder for folders/workspaces/sessions, inline edit, one-click expand/collapse, dual-channel search) with per-workspace and per-session token usage and cost stats from real session logs (official DeepSeek peak/off-peak pricing for any deepseek model, three spend calibers, hover detail cards, overview panel) plus OpenCode Go plan usage; data persists to host disk and refreshes live every 30 s.

X-ray for your DeepSeek Harness — see what's actually loaded, why, and what it costs you.

Desktop and webhook alerts on macOS, Linux and Windows when an agent finishes a turn, errors, or waits for approval — zero-dependency native notifications (osascript / notify-send / PowerShell toast) plus a Slack-compatible webhook, with a configurable minimum turn duration.

File-change monitor and code editor for the DSH Web UI. Agent edits appear beside your conversation as real-time line-by-line diffs, with a syntax-highlighted editor, one-click revert, change history, workspace switcher, and per-session isolation.

Remote-SSH-style workspaces: turn an SSH host and a remote directory into a native DSH workspace; the agent operates the remote filesystem directly via 12 rw_* tools (SFTP/exec), with workspace-confined paths and known_hosts verification.