Plugins

A DeepL-style translation surface for dsh: replaces the shell's root frame with a two-pane translator driven by a tool-less agent preset, keeping the shipped settings panel (models, providers, plugins) intact

Voice-first session loop for DeepSeek Harness: a composer microphone button with browser/local speech-to-text (Web Speech, FunASR, whisper.cpp), a speak tool for text-to-speech replies (browser, edge-tts, piper), event announcements with mute, and speak-t

文件改动确认机制（双面插件）：write/edit/str_replace_editor 写入前弹出确认条，内嵌 GitHub 风格 diff（行号 + 红删绿增），允许本次 / 拒绝。File-change confirmation with inline diff for DeepSeek Harness.

The rich `edit` tool for DeepSeek Harness (replace / patch / apply_patch / hashline modes) with embedded format-on-write and diagnostics — a standalone plugin with no upstream harness changes required.

Minimal-anchored agent preset: request #1 keeps the real bash + str_replace_editor pair with auto-injected context stripped, then promotion unlocks the full Standard catalog and posts a one-shot background-jobs notice against sleep-polling habits.

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.

DingTalk IM channel via Stream-mode WebSocket: each chat drives its own tooled agent; replies stream back as messages, no public callback URL needed.

Two-way Feishu (Lark) chat bridge for DeepSeek Harness over the official WebSocket long connection: messages route to the bound workspace's latest session and replies return automatically; bot credentials and workspace routing are configurable from the settings page.

Feishu bridge for DeepSeek Harness (derived from dsh-im-bridge): WebSocket long connection, approval cards, group @-mention-only replies, streaming card updates, /stop command.

Real-time duplex voice over Volcengine streaming ASR/TTS: agent reply narration, barge-in, wake word, live captions, 30 Chinese voices and a reply-first acknowledgment; builds in the DSH monorepo.

Reads assistant replies aloud via Fish Audio API only (bring your own key): per-message read-aloud, auto-read toggle, and a settings page for model, voice reference_id, encrypted API key, and proxy.

Full-duplex voice mode for the Web UI: a composer mic (RMS endpoint detection) transcribes speech with whisper running locally in the browser, assistant replies stream back as spoken audio sentence-by-sentence, and speaking interrupts playback and the running turn (true barge-in). No API key.

Sound reminders with one-click jump for concurrent sessions: the current session gets crisp dang/dang-dang tones, other sessions a soft ding/ding-ding plus a top-right card that jumps straight to the replying conversation.

Voice AI girlfriend for the Web UI: FunASR mic input, Qwen3-TTS spoken replies, companion animation window, and two-way QQ chat (text/voice/image push) via NapCat.

Ecommerce operator workbench: CSV batch preview with marketplace column adapters, reproducible profit/six-dimension scoring, public product-page snapshots, Chinese skills, and a replaceable store-policy KB.

PLUR memory rendered into the system prompt on each assembly rather than exposed as a tool call, so the block is replaced instead of appended and context stays flat across a session. Fully local hybrid search (BM25 + BGE fused with RRF), plain YAML storage you can edit, per-workspace scoping, and a /plur-memory browser.

Compaction backend replacing LLM summarization with a deterministic semantic extractor (keeps code/paths/commands, drops chatter) plus 28.4x KV-compression accounting.

Weak-network adaptor: transparent long-backoff model-stream retries (10-min cap), local response replay cache, heartbeat auto-reconnect, and degraded-mode token economy, with a bilingual (zh/en) settings page.

Optimize Prompt button under the composer: one click rewrites your draft into a clearer, more executable prompt, with a before-and-after dialog and one-click replacement.

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

Sélectionnez du texte dans une conversation, puis citez-le dans le composeur ou répondez-y dans une nouvelle fenêtre.

Plugin passerelle de messagerie instantanée DeepSeek Harness : route les messages Telegram et WeChat vers des sessions d'agent par correspondant et renvoie les réponses.

Prompt système façon pi pour DeepSeek Harness (dsh-pi). Un bundle de plugin Cordis qui remplace le prompt système par le style minimal-core, listage d'outils et directives de pi.

Récupération de contexte fine à la demande : outils context_query / context_slice / context_grep qui relisent l'historique déjà persisté avec des citations sûres pour le replay.