Plugins

Ollama Cloud native chat adapter: direct NDJSON translation of the Ollama /api/chat wire format, model discovery with context windows and capabilities, and web search/fetch providers under the ollama-cloud id, plus a Web settings card.

Travel-planning agent mode: the full Travel Story app (map, timeline, playback) takes over the DSH page with chat as a floating panel — 18 agent tools for place search, weather, routing and itinerary editing, with live UI-context injection. Place searches go to AMap (Gaode) or LocationIQ, forecasts to Open-Meteo and routes to OSRM, and the map keys sit in $DSH_HOME/travel-agent.config.json; its HTTP route has no DSH access check.

Antu diagrams inside DeepSeek Harness: Host tools (antu_validate / antu_layout / antu_render) and an interactive chat card.

Session Manager for DSH (formerly Session Steward): one console over active and archived sessions — grouped by workspace, domain and title filters, favorites, and batch archive / unarchive / purge archived files (destructive steps ask twice) — plus a four-gate health checkup (log integrity, projection cache, lossless JSON, cold read) that ends in a reversible, backup-first prescription. Search and indexing live in dsh-search-index; this plugin builds no index and never rewrites session logs.

Drives the open-source ArtCraft studio suite (17 apps including PhotoCraft, FilmCraft and PdfCraft) from DeepSeek Harness: agent tools, a same-origin HTTP API, a bundled craft skill pack, and plugins-page status with self-update. The ArtCraft apps are not bundled: install them separately so the plugin can find their CLIs (auto-discovery, artcraft.config.json or PATH).

A2A protocol server for dsh agents, with JSON-RPC tasks, SSE streaming, cancellation, and an agent card.

Session deep links, full session export (markdown/JSON), approved cross-session messaging with pairing, and team roster, rotation and recovery tools for multi-session work.

Rewrites the Chinese copy of a market-installed plugin into English using a model already configured in the harness — automatically when the plugin is installed, then live-reloaded. Each file is translated in one whole-file pass, validated by a real parser where one exists (node --check for JavaScript, JSON and YAML parsers otherwise) and handed back to the model with the error for up to three repair attempts; files above 48 KB, or that never parse, fall back to a line-range pass that checks every returned line against the original for structure. Trigger phrases and locale tables can optionally be preserved rather than translated, and the untouched original is kept beside the file as a .zh.bak.

Load Claude Code assets into DSH at runtime — skills, slash commands, rules, permission rules (deny/ask/allow), subagents and hooks from .claude/, plus Claude Code plugins (plugin.json / marketplace / skills / agents / MCP), via an in-memory IR that keeps .claude as the source of truth and writes back only when you opt in. Also surfaces Claude Code auto-memory in the system prompt, read-only by default, with a write-back switch in the /cc-memory panel. Eight packages: one bundle that installs the whole set, plus the loader and six adapters (skills, permissions, agents, hooks, mcp, memory).

Four-module session companion: smart conversation export (Markdown/PDF/JSON/PNG long-image with privacy redaction and batch ZIP), context handoff summaries with template save/import, API cost optimization (live official pricing, peak/off-peak scheduling, daily/monthly budgets, model routing), and global conversation search with in-chat find (Ctrl+F, CSS Custom Highlight API).

Underground pipeline data quality inspection plugin — checks coverage, edge matching, flow direction, outputs quality score. Default rules follow Chinese standards and a Guangdong guideline (accepted SRIDs: CGCS2000 and 3° zones 38–40; gross-error threshold 5%); override via config JSON.

Run JSON workflows with /workflow, inspect progress, select Agent models, resume saved sessions, and run bounded review and repair loops.

Windows Computer Use for DeepSeek Harness with 21 tools and verified targeting: controls are addressed through their UI Automation identity and patterns, and numbered marks are checked against the live window before input, so a stale target is refused instead of clicked. A known sequence runs in one computer_batch call, one model round trip; incremental observations, compact receipts (normally no more than about 6 KiB extra), bounded handoff waits (HANDOFF_WAIT_TIMEOUT/HANDOFF_HELD_TIMEOUT as continuations), the desktop-block cycle boundary and a deterministic 100 s owner-scoped leave backstop keep context small and prevent a stuck handoff from waiting out the tool deadline. Approval modes settle an unanswerable ask honestly: in a danger-full-access session with no approval card the action runs under that grant, every other sandbox — and every delegated subagent session — refuses and names the unavailable channel instead of reporting a user rejection, and gate diagnostics land in policy.jsonl. Human handoff, a model-visible stop brake and prebuilt native workers.

Deterministic project actions shared by people and agents: one actions.json, a right-sidebar run panel, and agent tools.

Configurable send and newline keys, a composer context menu with three sources (leave it to DSH and other plugins / browser menu / plugin-styled custom menu), a quick-command panel with categorized prompt lists where each prompt can append on every send or only on the first message of a session, a create-and-move row at the bottom of each category, a prompt optimizer that rewrites the draft with a separate model call, settings-panel size memory, and automatic x-opencode-session header injection for OpenCode routes. Prompt lists live in a global ~/.dsh/quick-prompts.json that is independent of the session and the project.

Cross-session plaintext memory: deterministic BM25 keyword recall (no embeddings), memory_save/list/search/confirm/forget tools behind a human-confirm gate, and global + project-scoped JSON stores that follow your git repo.

Batch pseudonymization for medical text, CSV, JSON, and XLSX in DeepSeek Harness. Deterministic identifier rules run first; an optional OpenAI-compatible model pass adds discovery and verification. Exact-span replacement preserves file structure, tokens stay stable per value, and each batch produces an audit report plus a re-identification vault. DICOM images get header-only de-identification based on PS3.15 Annex E, with pixel data left byte-identical.

Registers DeepSeek Search and Fetch API providers for the ctx.web seam, replacing both the web_search and web_fetch backends with DeepSeek's Search and Fetch JSON APIs, with configurable retries and backoff, settings that apply to the next call, and a configuration page on the bundle page. Requires DSH 0.2.1-rc.5+ and a DeepSeek API key with access to /v1/tools/search and /v1/tools/fetch (calls are billed by DeepSeek; account sign-in is not supported).

Injects a per-turn skill-selection preface chosen by the local JEV model of the jev-decision-kit workspace, so the agent loads exactly those skills instead of browsing. Requires a separately set-up jev-decision-kit workspace (Python .venv, host/preface_worker.py, models/jev/head.json); without it the plugin injects nothing.

Role-play plugin for DeepSeek Harness: imports SillyTavern character cards (JSON/PNG) and world books (lorebooks), binds DSH skills to a character, and registers the combination as a native agent preset.

Database explorer panel for DeepSeek Harness: connect SQLite, MySQL/MariaDB, PostgreSQL, SQL Server, MongoDB, ClickHouse, Redis, Elasticsearch and Qdrant from a third Conversation tab — browse schemas, page through data, edit cells, insert rows, design and drop tables, run SQL, import/export CSV/JSON/SQL/Markdown, and draw editable E-R diagrams. Read-only connections enforce statement-level allowlists, agent tools ship read-only by default with an opt-in write flag, and every write (including refused attempts) lands in an auditable log. Ships an MCP stdio server exposing the same connections to external AI clients.

Prompt library above the DSH composer — a 📚 button expands a searchable panel to insert saved prompts into the draft with one click (appends, never overwrites), persisted in a host-side JSON file.

Browses checkpoints produced by dsh-checkpoint-rewind as a timeline of time nodes and shows per-file line diffs between any two of them, with trace replay from session logs (no snapshot producer needed) and preview-first workspace rollback with single-shot undo, via /diff and /rollback commands, a JSON HTTP API, and a GUI panel.