Plugins

Turn raw data (CSV / pasted table / SQL results / DuckDB) into a structured Markdown report with business conclusions, metrics and charts.

Agent-initiated voice calls: `offer_call` rings the human (接听/拒接/稍后再说); accepted calls synthesize and play locally via CrispASR + Qwen3-TTS (9 speakers, 2 Chinese dialects), rejected calls return the decision to the agent.

Session header badge showing DeepSeek peak/off-peak status, per-model token prices on hover, and real session/turn costs from actual usage.

Message recall (撤回) plugin for the DSH Web UI: one undo button on each user message that removes the turn and everything after it, durably, without reverting code changes.

向模型暴露 sleep 工具，按指定毫秒暂停执行后返回，支持取消/clamp | Exposes a sleep tool that pauses for specified ms then returns, with cancellation/clamping

Bridges session images to configurable vision providers and returns text-only analysis to eligible DeepSeek Harness model routes.

Writes local JSONL summaries of per-turn tool counts and coarse verification signals without storing prompts, tool arguments, or result text.

Fail-closed Feishu (Lark) channel bridge: chat with a bot, get dsh agent turns back — with opt-in human-in-the-loop tool approval (Allow/Deny cards before every bash call, fail-closed timeout). Official-Python-SDK-only integration (exact-pinned); deny-by-default allowlist, webhook signature/timestamp/replay verification, per-chat sticky sessions; daily latest-SDK compatibility canary; bilingual docs.

Bark push notifications to iPhone: turn completion, waiting-for-input, and approval events sent from the DSH Host.

Runtime policy guards that block repeated failing tool calls, oversized shell commands and network commands chained with local ones, composite batch tools (read_batch/edit_batch), a SYSTEM.md mode that replaces the official system-prompt sections with your own file, soft convergence notices, and turn telemetry for DeepSeek Harness.

Turns one journal paper PDF into three deliverables by default — a Chinese group-meeting literature report deck (.pptx) in the Nanyang Normal University physics template, a matching Word speaker script, and a two-colour defence-prediction Q&A HTML (ten-odd questions with short direct answers). Requires Python 3 with python-pptx, python-docx, Pillow and pymupdf (pypdf fallback); install them with pip install -r requirements.txt.

Session usage dashboard for DeepSeek Harness: price, tokens, per-turn curves, and per-answer cost badges.

Session handoff: `/handoff` summarizes recent turns with an LLM, opens a new session in the same workspace with the summary as its first message, and can trigger automatically when the context window or session size grows. Supports DSH `0.1.0-rc.5`–`rc.8`, `0.1.1-rc.2`, `0.2.0-rc.2` and `0.2.1-rc.2`.

Brings the rtk token-saving setup from Claude Code to DeepSeek Harness: commands rtk can rewrite are rewritten, and builds, tests and logs it cannot reach are compressed; git, cargo, npm and pytest are covered. Compressed output tells the model what was elided and how to recover it; when the sandbox cannot reach the rtk store the original is saved and its path given. Savings show without a command: a pill below the composer, with `/rtk stats` for detail. When a rewrite is unreliable the original command runs as usual: if rtk cannot run, or the returned command would drop arguments, nothing breaks. The rtk binary ships with the package, so mainstream platforms need no separate rtk install, unlike most other rtk plugins.

A bottom-right pixel-art basketball-chick desktop pet for the DSH Web GUI: sprite animations, drag with edge snapping, click sounds, waiting reminders when a session needs you, per-turn cost bubbles, a usage ledger, and a DeepSeek balance badge.

Image generation and editing for GPT Image, Gemini (Nano Banana) and Grok, with official, OpenAI-compatible, api.toolify-ai.com and custom HTTP providers. Text-to-image, reference-image editing, canvas annotation, mask editing and Agent multi-turn chat, with images and history kept on your machine. The workbench UI is the MIT-licensed GPT Image Playground v0.9.0 build by CookSleep, bundled unchanged; that upstream is a standalone web app, not a DSH plugin.

Fully local long-term memory for dsh: cross-conversation and cross-project, stored as a single JSON file on your machine with no network calls, no model calls and no API key. Ships memory_save, memory_search, memory_list, memory_forget and memory_review tools, keyword-and-tag recall injected before each turn with adjustable ranking weights, Markdown import (including Kun and Hermes Agent formats) and export (native and Hermes Agent formats), and a settings page to browse and edit memories.

A pannable conversation tree for DeepSeek Harness: inspect any turn in a side panel, return to its branch, and fork a new branch from any turn; continuous turns fold into a single node.

Local long-term memory for DSH sessions: archives older turns under context pressure, with a turn-summary index for faster turn lists, statistics, window probing and archive planning (rebuilt automatically when unavailable, with a manual full verification), four tiered hot-memory boards, project documents with enabled/disabled/archived filters and optional owner-controlled family sharing, project hot memory, dual user/assistant turn previews, memory families with editable names and root transfer, root-abdication recovery, orphan-family takeover, summary keyword locator with segment-level candidates and paging, manual injection, 20K segmented reads, and tag-related retrieval. Includes staged recall cues, automatic compatibility with older memory layouts, and post-install version verification. Off in each new session until you turn it on with `/palace on` or the Memory Palace tab. All data stays in the workspace.

QQ-style alert sounds for DSH: the QQ message tone when a turn finishes and the QQ system tone when approval or an answer is needed, reading your local QQ install on Windows and falling back to built-in tones.

Roleplay companion memory for DeepSeek Harness: per-conversation editable persona documents (1-100 weight per entry, AI may refine them in small story-driven steps), per-speaker favorability and bond in multi-person chats, active memories with AI-scored vectors, a nine-emotion table updated every turn, an AI self-evolution ledger, recent 48-hour transcript search, companion-style conversation compression, sleep-time compute that pre-guesses the next topics while a conversation is idle, per-conversation tone cards learned from its own past replies, a habit-hint small-model bridge that writes the user habits it extracts into this conversation memory, a date-archived local knowledge base with auto-packing by turns or tokens, and a unified integrations page that lists curated plugins and downloads their GitHub releases.

Adds edit and delete to your own message bubbles: editing truncates the following turns and resends the new text, deleting removes the message and those turns, and either can optionally roll back the recorded file changes of the removed turns (refusing when a file has changed since). The sidebar keeps a single conversation.

Ask about one sentence without derailing the chat: select a passage in a Web conversation, comment, and the session's own model answers in a small thread beside it while the main chat stays untouched. The replier can read the session, the working directory and, if you turn it on, the web, but changes nothing. Commented passages stay highlighted with a badge that shows unread replies, and Send to chat hands a thread to the agent when you want it acted on.

Shows per-turn and session costs, provider/model breakdowns, subscription usage and the signed-in DeepSeek account balance in the sidebar.