Plugins

Read-only Git panel for the current workspace — branch, changed files, diffs and image before/after compare — plus three capsules above the composer (Git status, tool and skill activity, session running time) and per-session change attribution with review progress.

Hold-to-talk dictation in the composer that ships no recognizer of its own and reuses the speech service the official voice-input bundle already mounts - long-press the input box with mouse or touch, release to write the transcript into the draft, slide up to cancel, and it never sends.

In-session cd for DeepSeek Harness: re-base relative paths on the fly (the file tools and the bash/pwsh default workdir follow) or move the session to another workspace for real — a `cd {"workspace": true, "confirmed": true}` call the user has agreed to, or the user's own `/cd <directory>` command, relocates the session's stored log, sandbox root, AGENTS.md and skill discovery and sidebar grouping. Per-session, persisted across restarts, without moving the session for a plain re-base.

Full upstream REA 6.4.0 integration over the official DSH MCP bridge: all 170 tools, the version-matched reverse-engineering skill, and the six original MCP prompts with argument completions reachable from the composer / menu, all sharing one REA process and complete structured Evidence. External analysis engines are bring-your-own.

Keeps project decisions in plain markdown instead of chat history: one main document plus per-module documents, every entry carrying a file:line citation. The agent interviews you to turn open questions into settled decisions, and a five-dimension score (task complexity, extensibility, maintainability, code quality, reusability) is derived from the documents and shown on a button beside the model picker. A session can bind several projects; projects are sized small/medium/large, which widens the entry limits, and a reusable-pipeline section in the main document is injected when its trigger words appear.

Hierarchical workspace tree plus browser-style session tabs for the DSH sidebar: a "/" in a workspace or session title creates a virtual folder, with sections, pinning, time buckets, drag ordering, unified 6px status dots, per-row appearance customization (colour, glow, weight, icon) and a floating full-text search over session titles and message bodies. Several settings switches restore any behaviour to the host default, and a host-side route deletes sessions permanently (DSH ships archive only). Fork of KannaKuron/dsh-better-workspace.

Adaptive topology multi-agent preset for DeepSeek Harness with peer messaging, task handoff and live network visualization.

Injects a small continuity pointer at the start of a new session, naming the previous session and any handoff file, and reuses DSH's own compaction summary when there is no handoff file.

Heads-up Texas Hold'em training with an independent AI opponent, persistent public-action memory, and decision reviews.

Discovers rule files from every convention OMP supports and injects them into the system prompt as an always-apply layer plus a rulebook index, then enforces them with time-traveling stream rules that abort violating output mid-turn, deny a matching tool call, fold a reminder into that call's result, or ask a judge model about the finished reply. The same tool lets the model write new rules, and an audit panel on the Plugins page says why each rule is in force.

Chinese multi-agent workflow with per-role model fallback, versioned Mermaid task plans, independent Agent and Jev reviews, persistent expert collaboration, and pure-function calculation tools.

Browse, search and install skills from the public SkillHub catalogue, then enable, disable, update or remove them without leaving Harness. Category chips carry the upstream total for each category; the details drawer has tabs for the file tree, version history, permissions, third-party security-scan results and upstream metrics. An installed skill is written into the harness skill root as an ordinary local skill, and disabling one moves its directory out of that root rather than flagging it.

Video editing toolset for DSH: probe, trim, concat, audio handling, subtitle burn-in, transform, transcode and frame grabbing, powered by ffmpeg downloaded on first use.

Model failover and turn keep-alive for DeepSeek Harness: a request that fails with a model error before any visible output falls through the models of the configured provider groups (then the next provider) until one streams; transient failures retry with backoff under a liveness watchdog, a dead turn self-resumes with templated 「继续」 wake-ups, and an optional full-auto mode auto-answers permission, question and plan approvals with every decision appended to an AUTO-MODE.md audit log.

Full-screen boot animation for the DSH web client: the boot HTML paints a cover-fit artwork on its first frame, adds a slow settle, a scanning light sweep and a progress HUD, then hands the viewport over when the app mounts. Click or press Esc / space / Enter to skip.

Turns each long dsh conversation into a three-level trail (topic to progress steps to milestone timeline) and shows it in a draggable overlay, where one click jumps back to the matching message in the transcript. Topics are distilled by the DeepSeek model with a zero-cost rule-based fallback, can be renamed, locked, merged by drag and drop, and support per-conversation notes plus a vector drawing board.

Engineering intelligence for coding agents — persistent, evidence-aware, project-isolated engineering memory with unified hybrid search (memory + RAG documentation) for DeepSeek Harness.

AI Look-Up: detects aimless grinding (repeated commands, failure loops, long runs with no output) and injects mid-run self-review nudges, plus a real local-clock anchor so the agent stops estimating elapsed time.

Native right-sidebar Markdown preview with Mermaid diagrams, KaTeX math, GFM tables and syntax highlighting — rendering engine bundled, fully offline.

Notifies you about 11 configurable DSH agent events (task completion, questions, denied approvals, background subagents/goals/jobs, team tasks, context compaction, triggered schedules, plugin startup and permission changes) as browser Web Notifications through a bundled service worker, falling back to Windows toast or Linux D-Bus, with three silence levels and click-to-open.

Exposes the models already configured in DeepSeek Harness through an OpenAI-compatible gateway, so other local projects can call them with any standard OpenAI client. Multiple provider candidates share one named group with ordered, balanced or random dispatch; upstream failures before any output switch to the next candidate transparently, and rate-limited requests are retried after the provider's backoff. Per-candidate call statistics (attempts, answers, failures, token/TTFT totals) appear as badges in the settings page, and daily aggregates persist to a local file with a 30-day heatmap and trend view. Until you create a key in the UI, the endpoint accepts calls from anyone who can reach it; keys (stored as SHA-256 hashes) then turn authentication on, and the endpoint stays locked even after the last key is revoked. Exposing the optional LAN listener without a key leaves the port open to the whole network. Runs on DSH 0.1.2-rc.1 through 0.1.7-alpha.1 and later.

Delete a session from the UI (session-header button or sidebar row menu) or with the session_delete tool: stops and releases a running agent and its live session first, then removes the log directory, projection cache and workspace accounting, and cascades into the subagent sessions it owns while leaving forked branches untouched.

Shows subscription quota and account balance beside the DeepSeek Harness model selector for 28 provider entries, with a shared settings page and a read-only quota tool.

Embeds an Overleaf site (overleaf.com or a self-hosted instance) into a conversation tab through a same-origin reverse proxy, with cookie or popup login, selection quoting, caret insertion, compile-log driven fixes, outline navigation, and .bib / .tex synchronization.