Plugins

One leader, many sessions: tell the leader the goal and it splits the work into cards, runs persistent worker sessions in the background, collects their reports, and keeps the facts on a per-project board in the right sidebar, so several features move in parallel instead of one at a time. Project-level LEADER.md and SLOTS.md prompts shape every request, and `read_worker_session` replays a worker transcript read-only without waking it.

A Phone tab in dsh-better-sidebar: SMS and calls over Twilio and SIP lines bridged through Asterisk, call audio through your server, Live, Voicemail and Do not disturb modes with live voicemail transcripts, a Telegram account with chats, voice messages and calls, and phone_* and telegram_* agent tools. Requires dsh-better-sidebar, Node 22.5+, a Twilio account with a voice and SMS number, a public HTTPS host for provider webhooks, and the bundled Go daemons built from a checkout (Telegram also needs your own api_id/api_hash).

Obsidian-compatible Markdown notes in the DSH sidebar with search, tags, backlinks, graph, audio notes with transcription, a paint canvas, OCR (needs tesseract), client-side encryption and notes_* agent tools; the release tarball and the npm package carry a prebuilt Linux x64 daemon, other platforms build it from source with Go.

One dedicated folder per conversation: archives the transcript, auto-categorizes research output by type once the conversation has been idle for 10 minutes, adds a delete action to the session menu, and permanently removes the folder with the conversation.

Actually delete DSH sessions instead of archiving them (Windows only). Clears all six on-disk locations (transcript, title cache, billion-context SQLite index with VACUUM, workspace registry, cost-meter ledger, bridge logs) with a dry run, a backup, byte-for-byte rollback, and an automatic quit-delete-relaunch flow.

Injects a Chinese-thinking reminder around the system prompt and the per-step runtime snapshot, so the agent reasons in Simplified Chinese instead of drifting back to English as the transcript grows.

A Settings page for the memo plugin suite in DSH Web: edits the memo Host's AI route, archived-session summary language, length, transcript budget, template and prompt, and repository URL, adds a GitHub intake section for the claim label, per-run issue cap, autopilot switch and its working directory, preset, time zone and dispatch prompt, with per-field reset and saves that reach the running services without a restart, and carries an update entry that checks the npm registry and can install a newer release through the deployment's plugin manager.

Fully local push-to-talk voice input for macOS: hold a global hotkey, speak, release — transcription is pasted at your cursor. Local-first STT (Qwen3-ASR 0.6B 4bit on MLX/Metal by default, SenseVoice and mlx-whisper fallbacks), zero external APIs, launchd self-healing service and an 8-point diagnose script. The bundled skill lets the agent install, configure (Karabiner hotkey wiring, launchd, engine switching) and troubleshoot the whole toolchain for you.

Select text in the chat transcript, right-click, and quote it into the composer. The quote travels as an atomic chip and renders as a collapsible card, while the model receives the full block with message role, turn, block index and character range.

Real-time speech-to-text inside the DeepSeek Harness composer: a live transcript while you speak, inserted at the caret when you stop, with a microphone picker. Local sherpa-onnx inference, so audio never leaves the machine.

Read a video with a text-only model: with ffmpeg installed, sample frames at a 0.1-10 second interval into contact sheets where every frame carries its real timecode, extract the audio track and send it to iTingnao (needs an ITINGNAO_API_KEY) for a timestamped transcript, and describe each sheet with an image-capable model in the host, so the plugin works on its own without any other vision plugin. A composer slider sets the sampling interval, and pure audio files are transcribed without frame sampling.

Import Codex and Claude Code session history into DeepSeek Harness: merges same-project sessions into existing workspaces by cwd, offers handoff summaries or full transcripts, and keeps a rollback ledger.

Adds four tools to a Session. create_session opens a new Session in a named workspace or in any existing folder and delivers one prompt into it; session_message adds one more message to a Session that is still running — the host is asked to splice it into that turn at once, instead of queueing it until the turn ends; a Session that has gone idle is refused, pointing back to create_session; read_session_transcript reads back what a Session said and whether its current turn has finished; list_dispatched_sessions lists what this plugin dispatched and each one's state right now. Host-half plugin, no UI — it calls the host's own session primitives rather than reimplementing them. Restart DSH after installing.

When a live session's context passes a threshold, append older messages to a per-conversation folder on disk, then release the oldest finished turns from the model-visible context; the chat transcript and the session log stay untouched.

Read-only viewer for archived DSH sessions: browse the archive with workspace filtering and title/ID search, and read the transcript folded from the durable log — including messages from before a context compaction — without unarchiving.

Reorganizes a DeepSeek Harness session transcript into a structured Markdown document with an outline and a table of contents instead of exporting the chat in chronological order. Exposed three ways: a model tool session_to_doc, a composer button, and a loopback-only Web endpoint.

Automatically archives idle DSH conversations after a configurable number of days and clears the projection cache of archived sessions, without deleting transcripts or attachments.

A session-header 3-dots menu: download the session log, switch each chat's transcript between Normal and Verbose, and define what Verbose expands (thinking blocks, tool calls, terminal output).

DSH plugin: delete an archived session's local files — transcript, projection cache, and its subagent sessions — after a two-step confirmation.

Sticker and emoji reactions for the DeepSeek Harness Web/Desktop chat: a composer sticker picker, agent stickers that render as images while the transcript keeps the pack tag, emoji reactions under the user bubble, and an emoji-rain effect.

DSH side chat: fork the current session into an ephemeral side conversation that can really edit files, without polluting the main transcript.

Cross-device conversation and task sync for DSH: one machine generates a relay station and the others join with its invite link; every frame is end-to-end encrypted, so the relay routes a hashed channel it cannot read. Peers read each other's full transcripts and task boards, interject into a turn that is running on the owning machine, send a work command that runs in a workspace of the target machine with the model strength chosen by the sender, and can copy a conversation into a new local session and keep working on it here. Ships a token-gated phone page for listing devices, reading tasks and sending a command.

Dictation that ends up in the repository instead of the chat log: hold the button (or import a WAV), and the plugin archives voice-memos/<id>/ with audio.wav, a rendered waveform.png, memo.md (frontmatter, per-segment timestamps, ready-to-paste quote blocks) and meta.json. Audio is resampled to 16 kHz mono in the browser before it is sent. Transcription stays local — the harness speechToText service with silence-split windows, or a command worker such as faster-whisper — and when no engine is available the memo is still filed with an explicit status and reason rather than a fabricated transcript. Ships a conversation-view 口述 tab with click-to-seek playback and per-segment quote copy, three agent tools (voice_memo_save / voice_memo_list / voice_memo_read) and HTTP routes. Zero runtime dependencies, 52 node:test cases, real screenshots in docs/.

/cmd <command> in the composer runs that shell command in the session working directory, sends the command and its output to the model as a user message, and renders the input as a terminal card with exit status, expandable output and copy buttons; a bare /cmd opens an interactive terminal whose transcript is sent to the model with Ctrl+Enter. Runs with its own terminal permissions (danger-full-access) by default; set useSessionPolicy: true to use the session sandbox.