Plugins

Opt-in HTTP proxy service for DSH plugins, with native address and port settings. Exposes scopedHttpProxy for explicit callers, applies address changes to subsequent requests, and leaves system proxies, environment variables and global network dispatchers unchanged.

Paints a colored counter badge (green = unread completed sessions, orange = pending question or approval) on the DeepSeek Harness taskbar icon on Windows, and plays a chime when a session finishes. Fork of dthcle/dsh-badge-notify (MIT) with a completion chime and green/orange state colors; both draw the same taskbar badge, so the two cannot be enabled together.

Cross-device notifications for DeepSeek Harness. While a long task runs unattended, a finished turn, a pending approval or a question reaches you through the enabled channels: desktop toast, browser tab, ntfy push or Feishu bot.

Windows-only DeepSeek Harness host plugin that shows bottom-right desktop cards: a notification when a turn completes or fails, and a choice popup for ask_user_question where clicking an option answers it. Card colours follow the current Harness theme, and the notification sound plus the always-notify / only-when-unfocused timing are configurable in the Harness settings page.

Plays a random chime when a reply finishes, a one-shot reminder chime if the conversation stays quiet for a configurable number of seconds afterwards, and a chime the moment DSH needs you to step in: an approval request, a question, or a plan confirmation. Three independent switches and sound pools, persisted on disk.

A lightweight, native and extensible Windows notification plugin for DSH: on-demand helper startup, sound, native toasts and a taskbar unread badge, covering roughly 90% of routine alert scenarios in our use (an empirical estimate). No resident background service; MIT-licensed, customizable, and maintained for DSH compatibility.

Event-driven trigger plugin (the doorbell beside dsh-proactive's alarm clock): recursive fs watchers with per-rule debounce windows and glob filters, plus a loopback-only local webhook endpoint with per-rule tokens, fire rules that wake a target session through the host agents service - live sessions get a direct follow-up, cold ones are resumed first - and inject a rendered prompt with template variables (paths, count, payload). Rules hot-reload from the event-gate rules file without restarting DSH, every trigger appends to an auditable JSONL history queryable via the trigger_list and trigger_history tools, and a loopback health route reports install and runtime status. Typical uses: auto-organizing a downloads folder, diagnosing CI or monitoring alarms posted from local scripts, and watching logs for errors. Pure JS, no build step, MIT.

To-do list panel for DeepSeek Harness: large task cards in collapsible sections, hour-precision due times, per-task reminder lead times, and DingTalk notifications through a group robot webhook or an enterprise-app work notice. Each task can bind to a workspace session and jump to it on click.

Manage subagents and Agent Teams teammates in DeepSeek Harness: stop running instances, then really remove them by retiring their catalog and roster records with seq-preserving log tombstones and moving their session directories to a recoverable trash; model tools, a conversation-header panel and an offline CLI.

Builds a per-project code wiki: README summary, docs tree, tech stack, git activity and language composition, cached locally and exportable as Markdown.

Adds a voice to the agent: emotional speech synthesis (ChatTTS when available, falling back to edge-tts) and a singing mode, with mp3 output and local playback over ffplay. Requires Python 3.10+ with edge-tts installed (ChatTTS and its model cache are optional), ffmpeg/ffplay, and the pythonPath/ffmpegPath/ffplayPath values in cordis.patch.yml pointed at your own installs.

Splits over-long screenshots into DSH-acceptable slices before prompt admission instead of letting them be rejected: vertical slices overlap so a line of text is never cut in half, and pure-JS codecs avoid native binaries. It wraps the existing attachment store instead of replacing it.

Read a video with a text-only model: with ffmpeg installed, sample frames at a 0.1-10 second interval into contact sheets where every frame carries its real timecode, extract the audio track and send it to iTingnao (needs an ITINGNAO_API_KEY) for a timestamped transcript, and describe each sheet with an image-capable model in the host, so the plugin works on its own without any other vision plugin. A composer slider sets the sampling interval, and pure audio files are transcribed without frame sampling.

Windows only (binds user32.dll via koffi; inert on macOS/Linux). Remembers the DeepSeek Harness main window's size AND position: restores both on every launch (re-asserted during a grace period to beat the default layout), saves stable manual moves/resizes as the new lock, never records minimized/maximized/fullscreen states, never adopts the default rect DSH itself places the window at (so the app's own layout resets can never poison the lock), and stays on-screen when monitors change. Compatible with DSH 0.2.1-rc.3+.

Windows x64 desktop tools for DeepSeek Harness to restore and foreground existing windows, observe screenshots and UI Automation elements, left-click, and type text or supported keys, with repeatable control sessions and physical Esc to stop.

Unity-MCP bridge for DSH: dormant from boot, /unity-mcp-tools connects the Unity editor MCP server (com.ivanmurzak.unity.mcp) and registers the tools currently enabled on the Unity side; ships a per-plugin-version command catalog plus /unity-mcp-install and /unity-mcp-check, and re-fetches tools/list itself after a tool-set change because DSH sessions never receive list_changed.

Rejects foreground waiting in DSH agents: waiting commands (sleep, wait, tail -f, watch, ping without -c, infinite loops), blocking wait tools (wait_agent, job_output with wait: true), progress polling (the same check command repeated within a window) and commands that need human input/confirmation (sudo without -n, ssh without BatchMode, login flows, interactive editors, docker -it) are refused with an actionable retry to run in the background or end the turn. Configurable budget and polling window, message language follows the system (zh/en), zero runtime dependencies.

Local document library for DSH Desktop (Windows only, installed with the bundled PowerShell script): upload files once, then every conversation can search and read them through four tools (library_list / library_search / library_read / library_save); upload, download and batch download live in the Settings panel. Files stay on the machine unless you enable the optional vision model, which sends images to the endpoint you configure.

Weather care for DeepSeek Harness: turns a forecast into one sentence you can send — clothing and umbrella advice from feels-like temperature, humidity and air quality, adjusted for how cold-sensitive the user is and how they commute. Also a switchable daily care push, extreme-weather alerts and reminders, evaluated when the agent wakes (a host such as qq-bridge can wake it on schedule). Preferences stay on the local machine.

Runs the local nanobot CLI agent as a DSH subagent through a nanobot_run tool: each call carries one self-contained task and returns only the agent's final answer, either as a fresh process or through a persistent OpenAI-compatible server.

Long-term memory kept as blocks: one event per block, written to a local append-only event log with a block view and derived indexes, so a full history stays recoverable while only the matching blocks reach the context. The model saves entries with memory_remember and pulls the relevant few with memory_recall, plus one automatic recall pass before each step. Data stays in ~/.beme; no external service and no API key.

Turns archived sessions into durable memory instead of dead disk. Distils each archive into reusable skills, a fact ledger with ADD/UPDATE/NOOP decisions plus validUntil and supersededBy so stale facts retire instead of piling up, and topic clusters by single-linkage similarity. Also digests sessions that are still in progress through a read-only seq watermark, leaving the session log byte-for-byte untouched, and can self-check the growing memory to merge duplicate facts, retire stale ones and consolidate duplicate skills — measuring only unless you opt in, and never hard-deleting, only superseding.

Distills daily chats into an updatable character card and a cross-session emotion module that trains the persona.

Local long-term memory for DeepSeek Harness with SQLite storage, automatic extraction, semantic recall, corrections, reliable forgetting, and an in-app summary dialog.