플러그인

웹 UI 사이드바에 Quick Chat 항목을 추가해 자체 모델 및 추론 노력 선택기가 있는 떠 있는 채팅 창을 열고, 선택적으로 현재 세션의 기록을 시드로 받으며, 모든 사이드 대화를 재개·이름 변경·삭제 가능한 기록으로 유지합니다.

DeepSeek Harness용 메시지 단위 삭제 — 모든 채팅 메시지의 복사 버튼 옆에 휴지통 아이콘이 있어, 공식 surface-replace 계약을 통해 해당 메시지를 파생 모델 컨텍스트(및 표시된 대화 기록)에서 제거합니다.

자막 우선 비디오 전사로, SRT 내보내기, 취소 가능한 작업 제어, 자막을 사용할 수 없을 때 faster-whisper large-v3 폴백을 제공합니다.

지속되는 어시스턴트, 워크스페이스별로 그룹화된 프로젝트 세션, 트랜스크립트 전용 스크롤, 구조화된 생각·도구·diff·계획·서브에이전트 보기를 갖춘 DeepSeek Harness용 전체 화면 터미널 워크벤치.

Readable transcript export for DeepSeek Harness: turn any Session into a Markdown / HTML / ZIP transcript with reasoning blocks, tool calls and results, images and usage — from the Session header or the /export-md command.

QQ channel for dsh via OneBot 11 (NapCat and friends): reverse or forward WebSocket, DM and group chats, image and voice transcription, t2i text-image cards, merged forwards, and a settings page.

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.

Shows a Chinese translation under each English thinking block in the DSH web chat, without modifying the session transcript; per-chunk caching, a configurable translation model, and a settings panel.

Live token cost for every chat in the DSH Web UI: the chat, its subagents and the whole session tree, priced from a bundled models.dev snapshot of seven providers and 139 priced models, with cache read and write rates wherever the provider publishes them and DeepSeek from its own peak and off-peak table. Every finished answer carries its own price in the transcript, and a chat that is not currently open is priced from the log instead of disappearing. Spend is costed per interval from an append-only JSONL ledger in the project folder, so logged work keeps the tariff it was billed at. On top of it: budget-aware work plans packed against a money limit, routing scenarios that show which models are worth connecting, a generated plan document in English, Chinese or Russian, and a warning when spend belongs to no plan unit.

Answers hard questions by staging a formal debate: two adversarial subagents argue opposite sides with research, then the main agent rules on the transcript through the debate_open, debate_round, and debate_verdict tools.

Session handoff for DeepSeek Harness: the session menu creates a successor session that rebuilds the old session's memory, tasks and rules through an eight-section takeover packet, with light context via on-demand transcript readback.

Consent-bound one-turn voice preview for DSH Web with a credential-free local synthetic demo, optional Qwen Audio, exact Session isolation, and explicit transcript-to-draft handoff without automatic submission.

DeepSeek Harness plugin: Bilibili keyword video search, video metadata, subtitle transcripts, direct play URLs, and multimodal frame viewing (bilibili_search / bilibili_video / bilibili_subtitles / bilibili_playurl / bilibili_frames). Anonymous by default

DSH Web plugin for managing sessions: archive/unarchive, guaranteed physical deletion (transcript files + ~/storages/*.json sweep), drag-and-drop workspace reassignment, and branch-based message editing (edit/retry/reroll with reversible version timelines

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.

Named user credentials the model uses by reference: values are entered on a Settings → Credentials page and injected into each shell execution as DSH_CM_* variables instead of being printed into the transcript, with credential_read as the documented last resort.

Conversation-map rail down the left edge of the transcript: one tick per user turn, read from the full session log on the host rather than from the rendered page, so long sessions are covered end to end. Hovering fans the neighbouring ticks open by pixel distance and floats a scrollable preview of that turn prompt and its last reply; clicking scrolls to the turn, paging older history in first when it has not been rendered yet; the tick for the visible turn stays highlighted while you scroll.

DashScope OpenAI 호환 API(qwen3.7-flash) 기반의 모델용 image_describe(识图) 도구와 붙여넣기 브리지: 텍스트 전용 세션에서 붙여넣은 이미지가 전송 시 파일 경로로 자동 변환되고 트랜스크립트에 다시 렌더링되어 이미지 허용 단계에서 걸리지 않습니다. DASHSCOPE_API_KEY는 BYOK, 엔드포인트/모델/예산 설정 가능, 리다이렉트 방지 HTTP 클라이언트, 모든 agent preset에서 동작.

기존 Claude / ChatGPT 기록을 DSH로 가져오기: Claude 내보내기의 memories.json을 제로 토큰으로 즉시 가져오고, 로컬 Claude Code 트랜스크립트는 내보내기 없이 사용하며, 대화는 DSH에 이미 설정된 모델로 증류합니다. 모든 메모리는 코드로 소스와 대조된 축자적 증거를 동반하며, 의역은 폐기 후 집계되고 assistant 턴에서만 발견된 증거는 항상 저장이 아닌 검토로 보냅니다.

Deterministic cross-session transcript retrieval for DeepSeek Harness: the model-facing `recall` tool searches past session logs with explicit scope control

Deterministic session evidence reports for DeepSeek Harness: /transcript writes styled single-file HTML / Markdown / JSON reports from canonical session logs, /stats prints a terminal stats card, /archive writes per-session ZIPs

Chat agent for a DeepSeek Harness session: create characters and write their personas, keep several archive threads per character, undo or rewind the locally stored transcript, and record story beats in an event book.

Community ACP bridge for DeepSeek Harness that supports session/load by replaying a persisted session's transcript