Plugins

Subtitle-first video transcription with SRT export, cancellable job controls, and a faster-whisper large-v3 fallback when subtitles are unavailable.

A phone shell for the web GUI - the sidebar becomes an overlay drawer that closes when a session is tapped, the settings sheet goes full-screen single column, and the transcript is retuned for phone reading.

A full-screen terminal workbench for DeepSeek Harness with a durable assistant, workspace-grouped project sessions, transcript-only scrolling, and structured thinking, tool, diff, plan, and subagent views.

Shrinks the first history page of long DSH sessions to at most 100 messages, targeting the latest two turns, and fills the viewport in the background with the built-in load-earlier control when the trimmed transcript is shorter than the window.

The row that is running expands itself and folds back when it settles. A running turn keeps its whole procedure in one height-capped window that scrolls itself; a finished turn merges into the built-in finished header, leaving only the final answer. It works by driving the official disclosure rows rather than drawing its own panel, leaves rows you opened by hand alone, and restores the official settings on uninstall.

Download watermark-free Douyin and Xiaohongshu videos, transcribe them with local or cloud speech recognition, proofread the text against a term list, and export Markdown, DOCX, SRT, VTT and other formats from a settings panel or agent tools. Needs Python 3.10+ with pip packages (playwright, python-docx, numpy, and sherpa-onnx for the default local SenseVoice engine, which also downloads a ~228 MB model on first use), ffmpeg on PATH, and Chrome or Edge.

Conversation memory behind a 20-letter recovery code: /recovery create packs the current conversation into one local record, and /recovery memory <code> injects it into a new conversation, where the model first summarises the recovered session and ends its reply with 记忆已恢复. Records are plain JSON under $DSH_HOME/recovery (mode 0600) with no network calls; the restored transcript is complete unless it exceeds the configured character budget, and /recovery where plus the dir option or DSH_RECOVERY_DIR move the directory to shared storage or a synced folder.

Pulls your chat.deepseek.com conversations into a local knowledge base — one Markdown file per conversation, a JSONL transcript and a catalog — and searches them from a control page inside DSH. Daily increments plus a full-history backfill from the official export, an integrity check, and an optional model step that runs through the host llm service and writes only after its JSON passes validation. Reads the web userToken from the DSH credential store and calls chat.deepseek.com only; no install scripts, no runtime dependencies.

Recap a session from dsh, Claude Code, Codex or OpenCode saved on this machine: the intent, key decisions and why, what changed, open threads and where to resume. Adds the session_recap tool, the /recap command and a right-sidebar panel that lists a project's sessions across agents. Uses the session's own model route, removes keys and tokens from transcripts before sending, and caches recaps locally. Needs python3 and zstd.

Clamps the session history page request to 120 messages and replaces request/header tool schemas larger than 200k characters with an empty array before React renders them, so long sessions open without freezing the transcript.

Adds an /if slash command to DSH: the first line is a condition and the remaining lines are an instruction. A fork subagent that inherits the session tools, system prompt and message history judges the condition and answers YES or NO, and only on YES is the instruction sent to the main agent as an ordinary user message, while a NO sends nothing. The condition, judge prompt and verdict never enter the main transcript. While the agent is busy the command queues with ordinary messages, editable, removable and steerable from the queue panel, and a setting switches to the 0.2.x background mode. The judge runs read-only, and falls back to a one-shot model call over a plain transcript when the host has no context-inheriting fork provider. Supports DSH 0.2.1-rc.5 and later (verified on 0.2.1-rc.5 and 0.2.2-rc.1) and Node.js 20.3 or later.

Audio tools for DSH: inspect audio/video files, transcode or extract the audio track from a video, trim and normalize, and transcribe speech with local whisper.cpp or an OpenAI-compatible API. Requires ffmpeg and ffprobe on PATH (not bundled); local transcription also needs a whisper-cli binary and a ggml model.

Native DSH /side conversation tabs with a clean transcript and inherited context, hidden from the main session list using independent Session forks and the official chat UI, with timestamps, token usage, streaming and the command menu. Extracted from dsh-better-sidebar 0.29.0 (MIT); do not enable it alongside dsh-better-sidebar's own /side entry — the two command entries conflict, so stop one before using the other. Requires Windows DSH Desktop 0.2.1-rc.5 and dsh-delete-session for confirmed permanent cleanup.

Turns real DSH crash logs into a short hard-constraint list: static preflight before a plugin installs, conflict check afterwards, controlled self-heal when the harness will not start — plus handing a huge session over to a fresh one, the brief written by a model that reads the original transcript.

Read, message and live-follow local DeepSeek Harness sessions from inside an agent: four tools (session_list, session_read, session_send, session_chat) plus a matching Python CLI, over the desktop app local RPC; transcripts also read offline. Requires Python 3.10+; offline transcript reads also need the zstd CLI.

Adds a terminology-aware correction pass to the built-in local speech-to-text: keeps DSH's own microphone and SenseVoice engine (audio never leaves the machine) and fixes homophones, domain terms and malformed numbers in the finished transcript.

Drives the Claude desktop app from DSH over its claude:// deep links: open a Claude Code session with a prompt and folders, a Cowork task with files, or push a CLI session id back into the app. Also presses Ctrl+Enter for you (SendKeys) and reads the reply back from the local Claude Code transcripts under ~/.claude/projects/<cwd-slug>/<session>.jsonl — seven tools: desktop_send, desktop_continue, desktop_open, desktop_sessions, desktop_read, desktop_wait, desktop_probe.

DeepSeek Harness conversation polish: message and step folding, composer and sidebar sizing, folded-content search, turn timing, and confirmed local conversation history deletion.

Standalone QQ-bot extension pack for DeepSeek Harness — fully independent, no other plugin required. Two-layer SQLite memory with hippocampal recall, a persona that keeps learning from daily chats, group tiers, local-model quick replies with a single-brain arbiter, TTS outbox, sticker library, an approval-gated video studio, and a four-form desktop pet (three custom characters plus the stock fish) playable over a public invite link with access-code login, single seat and brute-force protection. Chat bridging is deny-by-default: c2c/group access defaults to a care mode that only responds to the special-cared people and groups of the owner (shared with the persona system, zero extra config); allowlist, open and disabled modes remain available. First-run defaults (persistent inbound dedupe, configurable outbound-hook budget, optional default permission preset, extension seeding) are written only where nothing was configured and never overwrite user changes. Interview and quiz practice run inside chat with local scoring and configurable transcript retention. Requires QQBOT_APPID and QQBOT_SECRET, and Node.js 22.5 or newer.

Annotate quoted answer text in the transcript: each selection keeps its quote plus a note of your own, notes pile up as chips in the composer and travel with the message, and two or more also get a chip above the input to jump back or clear them. The chips need dsh-paste-chip installed; without it each note is a plain text line in the draft.

Reads a local video or page link with ffmpeg and Paraformer ASR, returning a timestamped transcript plus key-frame images the agent can open; finds candidate videos by keyword and installs its own runtime dependencies on first use. Requires Python 3.8+ on PATH; video_discover also needs a one-time douyin/xiaohongshu login.

Adds job-role prompts to the DSH composer: type - at the start of the input to pick a role, which becomes a reference chip in the draft and is then injected as a system prompt section on every turn of that conversation, so the instruction keeps applying without showing up in the transcript. Roles are added and edited on a Settings page and stored in ~/.dsh/dsh-role-prompts.md.

Adds two Volcengine Doubao cloud speech recognizers to the DeepSeek Harness voice-input picker, optionally rewriting the transcript with an LLM.

Add MiniMax image understanding, image generation, speech synthesis, and transcription tools to DeepSeek Harness.