Plugins

DeepSeek brain + automatic image transcription: attach images in the GUI and each one is transcribed via the official deepseek-v4-flash-vision-exp by default (a pure-text V4-Pro brain can see images), with any OpenAI-compatible VLM or local Ollama as alternatives.

Multi-platform API balance and usage dashboard for the DSH web GUI: balances for DeepSeek, Zhipu GLM, Kimi, StepFun, SiliconFlow, MiniMax, OpenRouter, Novita and xAI under the composer, estimated per-session and per-subagent cost with DeepSeek peak/off-peak pricing, automatic discovery of relays configured in DSH settings, and an optional draggable whale widget.

Match your models and token budgets to each role, then let DSH delegate specialized subagents by task type. Covers architecture analysis, UI/UX, code implementation, codebase exploration, and documentation research, with automatic setup plus per-role reasoning effort and tool permissions.

Restart recovery for DeepSeek Harness web: after a crash or restart, an interrupted agent turn continues automatically (host-side agent/created listener, no browser timing races).

Cross-session long-term memory under the "memory palace" metaphor: dual-scope SQLite stores (user + per-git-origin project), hybrid FTS5 + local-vector retrieval with RRF fusion and recency/proof ranking boost, automatic capture from the session log (including the final turn), provenance audit chains, consolidation distillation and decay forgetting, and a settings-page Memory Library panel with corridor topology, tour butler, and refurb list.

Expert-mode agent preset for DeepSeek Harness (v0.9.2, npm dsh-expert-mode, bilingual EN/ZH): a chief coordinator plus 17 domain-expert subagents with automatic task delegation. Features: taskboard scheduler (file-system task state machine pending/ready/running/done/failed, dependency DAG, atomic claim, retry, crash recovery), quality gates (5-stage pipeline for high-risk tasks: requirement clarity, implementation, verification, independent review, integration, with 2-round rework limit), Five-Anchor constraint (review/convergence/anti-drift/collaboration-check/resource-awareness per turn), Near-distance Guidance (identity/task/output template per expert), progressive disclosure (~28% token savings), expert persistence, inter-expert file message bus (direct P2P comm, zero coordinator relay), cross review, experience pool, fast-track for simple tasks, fault recovery with auto-retry. Experts: data analyst, copywriter, legal review, product manager, frontend, UI/UX, architect, social media ops, growth hacker, quant finance, finance, backend, DevOps, database, QA, security.

Adds a configurable vision model to text-only main models: a vision_read_image tool, a composer-bar vision-model selector, and automatic image-to-text conversion for text-only routes.

DeepSeek Harness plugin that turns Jev judgments into three automatic actions — pruning oversized tool output to the segments relevant to the request, screening fetched pages for instructions aimed at the model, and picking which skill fits the next step — plus the jev_ask and jev_gate tools, a judgment ledger that survives restarts, and a /jev-status report. Needs a TypeSafe API key; without one it is inert and sends nothing.

Rule-gated automatic approval for DeepSeek Harness sandbox escalations with an optional LLM reviewer and native human fallback.

A better fold bar: automatically folds tool calls and Think segments into step fold bars, and collapses each finished turn into a single turn header with live metrics (duration, TTFT, token, tok/s, cache hit) — only the final summary stays visible; customizable leading icons with animated poker cards built in (suit-cycling card animation while running, a deck when collapsed, a fan when expanded), a settings row for the official fold mode, compatible with both new and old DSH versions. Zero intrusion into DSH source.

Per-call cache billing inside the context-meter popover: current step, round and session totals with hit/miss/output tokens and amounts, automatic Beijing working-hour peak/off-peak pricing, per-model rates, and third-party relays billed too.

Computer use through an external USB HID device: name a target in plain language, a vision model locates it in a cropped window screenshot, and a Raspberry Pi Pico 2 moves the real mouse and types on the real keyboard. 7 tools. Windows has window listing, per-window cropping and automatic window raising; macOS needs pyobjc and has neither; Linux is unsupported.

From chat to canvas to artwork — drive ComfyUI as a visual workflow IDE inside DSH. Embed ComfyUI (local or cloud) as a split-screen canvas in DeepSeek Harness Web: the agent sparks ideas, writes prompts and scripts right in the chat, applies them live to the canvas in front of you, and produces images, music, video, and 3D. From idea to finished output without ever leaving the conversation or switching front-ends: Canvas ops — compose and arrange pipelines, read/write workflows, edit nodes, wire links, run, tune parameters, and debug errors, all live and WYSIWYG on the exact canvas you are looking at; Production tasks — batch parameter sweeps (batch_run) and automatic output-image retrieval back into the chat (get_outputs), powering multi-modal creative and batch generation across images, music, video, and 3D; Environment upkeep — one-click launch of ComfyUI and one-click upgrade of the core plus every custom node (upgrade), keeping the stack healthy without interruption. This package is the DSH-side plugin, and it ships the ComfyUI-side bridge node too.

GitHub Copilot LLM adapter: OAuth device-flow sign-in, live model discovery from the Copilot API, vision support for image-capable models (gpt-4.1, gpt-4o), and two wire protocols (Chat Completions and Responses API) with automatic endpoint routing per model.

Pending-change review for DeepSeek Harness: every `edit`, `write` and `str_replace_editor` change is collected automatically into the file list, where a single change block, the blocks within a selection, or the whole file can be kept or reverted, and undo/redo is supported. It imports the workspace's version-control changes, shows the diff in a single-column or side-by-side view, and provides a Markdown preview in which changes can also be kept or reverted, in-file search, block jumping and copyable line references; the diff data is stored persistently, so the review continues after a restart.

Connect a ChatGPT account to Codex models in DeepSeek Harness through browser PKCE or device-code OAuth, with automatic token refresh and Web or headless login.

Analyze usage across models, providers, workspaces, and time ranges — including custom start/end dates over the full retained history — with live cache-hit visibility and separate model and provider breakdowns. Includes hourly single-day trends, daily cross-day trends, a 53-week GitHub-style heatmap, usage streaks, model and workspace Token-share donut charts with Token, cost, and percentage details, independent combinable filters, cache-efficiency trends, DeepSeek account balance, workspace aliases, CSV export, and a durable ledger that preserves successfully flushed usage after session deletion — and after a workspace is deleted, where its recorded usage is summed into one Deleted row — and rebuilds incrementally — on restart, unchanged sessions are applied from the ledger without re-reading their logs (a per-session log revision is the change signal), and only changed/new events are folded. The workspace registry is kept fresh automatically through the DSH domain/changed probe: only added/removed workspaces are reprocessed incrementally, unchanged workspaces reuse their computed aggregates and ledger with zero rescan, and usage is strictly limited to DSH-registered workspaces (unregistered cwds are ignored). After a scan, lightweight revision status fetches full history only when the Host/data state changes and exposes non-sensitive sync health (revision reuse, rereads, ledger recovery, and failures). Token accounting is explicit: input is fresh (cache read/write and reasoning are separate buckets) and zero-usage replays never overwrite recorded usage. Chinese uses local time, English uses UTC; API access is loopback-only.

Plugin marketplace in Settings that targets any local profile, not just the running one: install, update and remove across web, headless and other profiles, with install-script warnings, an installed view that also covers non-catalog profile dependencies, and an automatic DSH restart when the current profile changes.

Continual self-refinement loop: persistent memory, periodic review-and-refine, cross-session shared knowledge, and automatic rollback through a model-callable harness_refine tool.

Enhances data visualization in DeepSeek Harness by automatically selecting chart types from user input and generating images for trends, comparisons, proportions, relationships, and flows.

Settings card for the DSH LLM auto-retry engine: tune retry count, backoff and jitter live from Settings -> General, with configurable retryableCodes chips - defaults add INVALID_REQUEST so OpenAI-style HTTP 400 reasoning_text errors in thinking mode get retried automatically.

Automatically and intelligently routes each delegated task to the best configured model using aliases, capability tags, and usage guidance—keeping routine work fast and affordable while sending complex work to stronger specialists. Configure your model team in the Web UI or guided setup, run specialists in parallel with reliable result joining, and see the chosen model at a glance in subagent views and inline in Better Sidebar's Tasks tree.

Talk to Excel in DeepSeek Harness: create, edit, repair, and verify spreadsheets by conversation, with automatic formula health checks after every edit.