Plugins

This plugin exports a reusable function that takes a file path or a Buffer, extracts the content via @firecrawl/anydoc, and returns GitHub‑Flavored Markdown (GFM). It also includes configuration options and an example usage.

模型回合结束后用 LLM 生成 3 条批判性跟进建议，点击即发送 | After a model turn, an LLM generates 3 critical follow-up suggestions shown as click-to-send chips

Vector + graph memory backend: observe/remember/search/recall tools against a local memoria server, fusing HNSW semantic recall, FTS5 keyword search, and knowledge-graph signals via RRF ranking, with automatic turn-end persistence and per-agent namespace isolation.

Per-message delete for DSH: remove a user message, one reply step, or a whole assistant reply from the derived model context through the official surface-replace contract, and hide it from the visible transcript without rewriting the append-only log.

Host-level proactive wake-ups for DeepSeek Harness: the model schedules its own alarms (once, recurring interval, or cron, with optional random jitter), cold sessions are woken on time by session resume, model-initiated follow-ups are gated by quiet hours and a daily delivery budget, silent wake turns end with proactive_reclaim and fold out of model context as tombstones, declared schedule files glob-sync JSON schedules into host alarms idempotently, min_idle_seconds defers wakes until the destination session quiets down, and a web panel (settings section plus per-session tab, SSE live refresh) manages alarms and wake history — the heartbeat engine for AI companions and roleplay characters with their own daily routines and world evolution.

Turns the MacBook keyboard Caps Lock light into an agent status light: on while the agent works, flashing when it waits for your approval or answer, off when idle.

Feeds every dsh prompt into the local agent-feedback-loop feedback-memory pipeline — captures dissatisfaction, reviews it offline into reflections, and attaches the compiled recurrence-rule context back to the turn, never blocking a prompt. Requires the agent-feedback-loop runtime; running agent-feedback-loop install afterwards wires existing dsh profiles automatically.

Shows a DSH session as a conversation canvas — every turn is a node, any turn forks a real child session, and a compacted context folds into one green node you can keep talking from; the left rail groups canvases by DSH workspace and renames them in step with the session titles.

Turns a plain-browser DSH session into the WhaleHarbor lite client: a standalone browser --app window with a client-style top bar and task notifications, while the full desktop installer downloads in the background (multi-source, SHA-256 verified) and an install prompt appears when ready.

Peak/off-peak billing clock with a provider-neutral account readout (DeepSeek balance, subscription plan windows, relay credits), per-turn spend measured from the provider's own counter, and a /hist token-history scene split per provider for dsh-tui

Pairs the running executor with a stronger reviewer model through zero-parameter advisor() calls and step-based patrol checks, returning plan, correction, or stop guidance.

Removes the queued prompts a DSH fork child inherits from its parent, so the first turn in a new branch runs the prompt typed there instead of the parent's next one.

L-clone 记忆钩子：DSH 每轮结束(turn/end)自动 capture 到外置大脑；Web GUI 侧边栏「大脑看板」按钮一键打开记忆工作台。

Windows-native tools for DSH agents: clipboard read and write, system notifications, hosts file inspection and network diagnostics, each returning structured data with UI cards from injection-safe PowerShell.

Settings section for archived sessions: browse by workspace, search, batch unarchive with the sidebar updating live, and optional auto-archive rules (idle days, keep-last-N per workspace) with a dry-run preview — plus a left-edge turn rail for jumping between turns of long conversations and ↑/↓ input history in the composer.

Resumes an agent turn that ended after narrating its next action without calling a tool: the guard replays the turn log on agent/turn-stopping, asks a judge model one true/false question, and steers the same turn to run one more step.

Per-turn file-change card for DSH Desktop: +N −M badges, aligned diffs, and Mac/Windows file open (system app, Finder/Explorer, VS Code).

Audit each finished assistant turn with an independent reviewer model and steer the agent to fix failed output, with at most 2 review rounds per turn and SOP-folder standards injected as an extra review dimension.

Watches agent execution traces and fires an LLM review at every successful turn end when signals trip, crystallizing reusable workflows into registered skills that improve progressively with later runs.

Adds a Reading tab to the DSH web client that shows process steps and live reasoning in source order, collapses successful turns to the final answer, and keeps the original tabs, composer, and tooling intact.

Per-model capability profiling for DSH: turns local session history into per-model dashboards of session counts, tool usage, error rates, and top error signatures, with time-range filters and multi-model comparison.

Desktop notifications for DeepSeek Harness approvals, questions, and turn completion — so neither DSH nor you end up waiting while you browse another tab.

Five casual mini-games (sliding-number puzzle, Sudoku, snake, Schulte grid, number memory) that pop up when a turn starts, with auto-saved progress across sessions.

Plays a short synthesized ding in the browser tab the moment an agent finishes a turn, built entirely with the Web Audio API; no backend audio and no OS notification.