Plugins

Off-peak message scheduler: turn on valley mode and the composer queues your messages until DeepSeek off-peak hours (half price), then auto-injects them into the session and gets replies. Native-look composer, hotkeys (Enter queue / ⌘+Enter send now / Esc exit), per-session toggle persisted across restarts.

Browses checkpoints produced by dsh-checkpoint-rewind as a timeline of time nodes and shows per-file line diffs between any two of them, with trace replay from session logs (no snapshot producer needed) and preview-first workspace rollback with single-shot undo, via /diff and /rollback commands, a JSON HTTP API, and a GUI panel.

A Chrome-dino-style runner for the DeepSeek Harness Web UI: play while the agent replies, score from 梁子 to 梁圣 on a persistent progress strip.

IM channel bridge: WeChat (ilinkai) / QQ / Feishu with proactive push — wake the channel bot from scheduled tasks and deliver AI replies to your phone.

Animated Claude-style reasoning-effort slider and model picker that replaces the native DSH model selector.

Replaces the Web GUI trajectory tab with a new-user-friendly round-by-round storyline, plain-language tool labels, category filters and fuzzy search.

DSH Web 工作区侧栏替代，顶部全局最近会话 + Workspace→Session 二级菜单 + 面包屑 | DSH Web workspace sidebar replacement: top global recent sessions + Workspace→Session two-level menu + breadcrumbs

Short-video sidebar: native player, series navigation, precise history replay.

DSH Desktop enhancement plugin: it puts verifiable facts on the table. Constraints are injected only when relevant, so idle chat costs no extra tokens; injection is layered (session-stable text in the system prompt, volatile content as a tail snapshot) and the prompt cache stays valid. Discipline: each turn is classified (question / research / discussion / diagnosis / execution) with boundaries enforced - no file edits on question turns, no unsolicited fixes on diagnosis turns; citing code lines not opened this session, negative claims about unseen symbols, requirements that do not match the deliverable, and dressing up “I did not check” as “waiting for your decision” are all called out; replies are written for humans - a code, field name or id must be explained in plain words the first time it appears. Memory and knowledge: 75%/90% context warnings plus an exported session recap (say "continue" in a new session); project knowledge accumulated across sessions by working directory, auto-captured and deletable by id. Inspectable artifacts: task contract / change record (auto-logged, unverified items flagged at delivery) / hypothesis record (conclusions must pass an evidence gate) / design decisions. Dashboard and personas: routing, trigger hits and block assembly are written to lume-metrics.jsonl and queryable via lume_metrics; personas are distilled from chat logs, novels, scripts or character sheets, with long-term and temporary memory, a memory star map and persona card export/import.

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.

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.

AgentDuel is a code-battle game. This plugin lets you complete the entire game loop inside DSH: manage deathmatch characters and capture-the-flag teams, submit agent code, start battles, watch replays, and use DSH conversations to keep improving agents based on battle results.

RLM mode for dsh: recursive sub-agents via a unified rlm() function — spawn, await, and chain child agents as first-class Python calls. Adds a persistent IPython kernel with tools.* bindings and context-as-variable.

Requires DSH 0.1.6-alpha.2. Annotate completed assistant replies, submit multiple drafts with official composer text and attachments as one Session message, navigate linked model replies, and use Settings to hide selected reasoning or tool details without changing stored events.

Chat with local DeepSeek Harness agents from iPhone iMessage: switch workspaces/sessions, start new sessions, and get replies in the Messages app — no extra apps, no servers, no cloud.

Codex-style `@file` mentions for the web GUI: search and reference workspace files of every format (.java, .vue, PDF, images, extension-less, hidden) with no index truncation. Replaces dsh-at-file.

Multi-channel IM bridge for DeepSeek Harness: route WeChat (ClawBot/iLink), QQ, and Feishu (Lark) chat messages to a DSH agent and relay its replies back, with per-channel sessions and reply dedup.

Full-duplex voice mode for the Web UI: tap-to-toggle or hold-to-talk dictation (send key or `Ctrl`) with a live caption, host-side SenseVoice ASR via sherpa-onnx, sentence-by-sentence spoken replies, and speaking interrupts playback and the running turn (true barge-in). No API key.

Free voice closed loop for the Web UI: browser SpeechRecognition mic input with live interim results plus read-aloud speaker buttons and auto-read for assistant replies, zero configuration and no API key.

Session timeline down the left of the conversation: every user message at a glance, current-message tracking, hover preview of the message and its reply, click to jump, collapsible.

Replace dsh's built-in web search with search MCP servers (Tavily/Brave/Exa/Perplexity/DuckDuckGo/custom), configured from the web Settings page. Disables the built-in DeepSeek search provider while enabled.

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.

Edit any user turn in DeepSeek Harness and re-run it: an inline editor on the message row rolls the conversation back to just before that turn through the official surface-replace contract, then re-prompts the agent with the revised text. The append-only

Persona engine for DeepSeek Harness: one config.json drives the AI's self-name (per model, per tier), how it addresses you, relationship stance, character text, per-item work contracts with individual toggles, thinking-chain language, appearance and reply tone (both opt-in and per-model overridable), and long-term memory gated by human confirmation - the AI can only append proposed candidates, a human confirm line flips them into effect, and the log is physically append-only and replayable. Confirmed entries are injected as a quoted data-not-instructions block; entries tagged with a kind can instead be routed to arbitrary files on confirmation and never reach the prompt. Three prompt sections re-evaluate from disk on every assembly, so edits apply on the next step with no restart. Persona presets are shareable JSON snapshots (imports and exports SillyTavern character cards, v2/v3 read, v2 written) and deliberately never carry memory. Zero runtime dependencies, no network, no shell; any error degrades to an empty section rather than a broken session. Ships blank - installing changes nothing until you write something.