Plugins

Leia o conteúdo de outra sessão (mensagens, chamadas/resultados de ferramentas, raciocínio) de dentro de uma sessão DSH

Edição de mensagens atômica por turno, nova tentativa, reroll e navegação em árvore de versões para conversas do DeepSeek Harness.

Lê em voz alta as respostas do assistente apenas via a API Fish Audio (traga sua própria chave): leitura por mensagem, alternância de leitura automática e uma página de configurações para modelo, reference_id da voz, chave de API criptografada e proxy.

Ponte de visão para rotas do DeepSeek apenas texto que analisa imagens anexadas e locais por endpoints configuráveis do OpenAI Responses, Chat Completions ou Anthropic Messages, enquanto mantém nativas as rotas com suporte a imagem.

Vigilantes persistentes em segundo plano que acordam o agente ao receber novas mensagens (caixa de entrada de arquivos ou delta de saída de comando) — o equivalente no harness da ferramenta Monitor do Claude Code.

Junte-se à ACN a partir do DeepSeek Harness: registre este agente, descubra outros, envie mensagens, leia a caixa de entrada. Usa a região da China por padrão

Ferramentas Git de primeira classe para o modelo: status / diff / log / commit / branch com mensagens e caminhos validados — sem chamadas diretas ao git via shell

Memória entre sessões com escopo por projeto: snapshot do PROJECT.md injetado na primeira mensagem do usuário, ferramenta memory_remember e autorreflexão após tarefas ReAct; cada projeto mantém seu próprio arquivo de memória

One private Feishu group per DSH workspace with real-time two-way message synchronization.

DeepSeek Harness plugin that fixes RTL/LTR bidi rendering in chat: per-block direction for Persian and Arabic messages with embedded English, plus list markers and quote bars that follow their text

IDE-style Git panel in the DSH Web GUI: a resident tab with a three-column overview (branch/tag list, searchable commit-history graph, commit detail with changed-file tree and message) and a changes page (stats bar, uncommitted list with per-file stage/unstage/discard, commit box with amend); side-by-side diffs carry lazy highlight.js syntax highlighting, on-demand between-hunk context expansion and word-level intra-line emphasis, with image files shown as before/after panes; plus a zsh-style branch marker in the input bar. Every git command runs as an argv array through the host subprocess service, cwd locked to the repo root.

Drive your local DSH from WeChat: a self-hosted iLink bridge over a persistent ACP session (context lives in DSH and is resumable), phone conversations grouped into the desktop workspace, with image recognition, file messages (Excel/Word/PDF, parsed by the agent itself) and voice transcripts. Access defaults to strict (only registered devices are served); the phone channel's permission preset is wide by design - see the README security section before sharing the bot.

Schedule a message into a dsh chat for later: a Schedule button in the message box with a date and time picker, a sidebar panel of pending messages across chats, delivery as a normal user message even with the browser closed, and schedule_message, list_scheduled_messages and cancel_scheduled_message tools so the model can come back to a chat on its own.

Folds long composer drafts into a compact summary card once a character threshold is reached, without changing message submission.

SMS forwarding webhook for DeepSeek Harness. Phone apps (SMS Forwarder, Tasker, or any HTTP POST) push messages to a local HTTP endpoint; the plugin stores them as JSONL and exposes sms_recent / sms_search tools so the agent can read SMS verification codes during tasks. Auto-extracts the first 4-8 digit OTP from each message, supports keyword filtering, and works over LAN or Tailscale.

Compresses older DSH context into a structured handoff, retains recent messages, and keeps session history searchable.

Discord-like communities in DSH with channels, roles and permissions, message search, and sharing or cloning of DSH sessions.

WeChat Official Account channel for DSH — WeChat messages run agent turns and the answers are pushed back through the customer-service message API, with signature-checked callbacks and an openid allowlist.

Conversation enhancements: a history-input overlay (Alt+Up with workspace/session/global/prompt scopes), recall of unapplied interjected messages, conversation forking with fork-family version switching, and optional auto-resend after forking (off by default).

Agent preset plugin for DeepSeek Harness that triages every request, delegates implementation to an expert, and schedules parallel work through a dependency-DAG taskboard and a file-based message bus before an independent review gate. Ships with only 11 core experts out of the box; more expert teams (Agency agents EN/ZH, classic collections) are one-click downloads from the settings page over dual GitHub/CDN channels with sha256 verification.

Global token totals across every local DSH conversation, de-duplicated by message id, with custom date ranges and per-provider monthly quota tracking.

Kaze Tachinu (The Wind Rises) skin for the DSH Web GUI: a full-screen film wallpaper behind glassmorphism surfaces, sky-blue interaction tokens, redrawn vector logos for the sidebar and home hero, a restyled composer card with themed placeholder text, and a bottom fade on the message list.

DeepSeek Harness peak-hour message queue: defer selected sends and deliver them to the original conversation off-peak. / DSH 高峰消息暂存与低谷自动投递。

Keeps one reasoning-only turn from making an entire session unusable. When a turn produces no visible text and no tool call, the assistant message is persisted empty, the gateway then rejects every later request in that session with 'content or tool_calls must be set', and the session is dead with no way back through chat. This plugin registers a single llm/stream waterfall listener and, only when the turn carried nothing visible, injects a small text block immediately before the terminal finish, so the persisted message is never empty. Ships the fixture DSH's own mock cannot express (a strictly reasoning-only SSE server, since llm-mock-server forbids an empty successText and always appends text after reasoning), plus an end-to-end reproduction that replays a real persisted session through DSH's own serializeMessages. Preventive, not a repair. Zero dependencies, one file, no process or filesystem access.