Plugins

Manages the MCP servers of a DeepSeek Harness profile: lists each server with its connection state and the tools it registers, preflights a configuration before saving it (a missing executable, an npm package name used as a command, an unexpanded variable that would reach the child literally, a URL with no path), and adds servers by pasting a dsh patch fragment or a Claude Code mcpServers block, converted to the dsh shape.

Read-only preview of SQLite files and MySQL / MariaDB / PostgreSQL / SQL Server connections in the right sidebar, with tables, paged rows, columns, indexes and draggable column widths, never writing to the database.

A session manager for the DeepSeek Harness sidebar: per-workspace category trees with drag-and-drop ordering, pinned sessions hoisted above the categories (or kept inside them, switchable from the view options), an archive partition, and a delete bin where removed sessions keep their logs and can be restored or purged in batches. The host half owns the category and recycle data, the web half renders it; both ship as one plugin. Maintained fork of ht719/dsh-session-categories ported to current DSH, with pinning, archive partition and delete bin added; it cannot be installed together with the original.

Floating DeepSeek account balance card for the dsh web UI: shows total, granted and topped-up balance per currency, refreshed every 60 seconds. Draggable and collapsible; the API key resolves from the card, the credentials service, or the DEEPSEEK_API_KEY environment variable, in that order.

Reasoning-effort slider for the DeepSeek Harness composer: drag through the thinking levels the current model declares and release to write the chosen level into the session. An auto band escalates one level after a tool error and another after two or more, and optional model routing picks a provider/model per task type.

Moves and resizes the DeepSeek Harness settings panel; its position and size are remembered per browser.

Adds a draggable off / low / high / max reasoning-effort slider to the composer model row and applies the selected level to the current DSH session. The slider only appears for models that offer all four effort levels.

Restores the DSH right sidebar divider drag after whole-interface zoom shifts the host handle off it, and widens the hit area to 12px with a hover affordance.

A collapsible "In Progress" group for the DSH Web sidebar: collect sessions from each session row's ... menu, pin the shortlist above the workspace list, reorder by dragging, and keep it across restarts.

Shortcut buttons in the composer row that send preset text into the current conversation in one click. Button label, size, opacity, shape and payload are editable in place, and the whole group moves left or right of the context meter by right-click dragging, persisted in localStorage. The group takes only the width it needs, so the context meter and the usage area stay clickable.

Whale-girl desktop pet for the DSH Web UI, drawn with hand-written SVG + CSS (no image or audio assets, zero runtime dependencies): swims while a turn runs, blows labeled bubbles on tool calls, taps the glass with an amber pulse when an approval is waiting, jumps with a turn duration/tool-count report on success and droops on failure, naps after dark or when idle. Click to poke, double-click to pet (affinity hearts), drag with remembered position, right-click menu (feed / mute / reset / hide), hover card with level, title, XP bar and per-turn stats. A `whale_say` tool lets the agent make her speak or act as a lightweight visible notification. Read-only over sessions and workspace; only ~/.dsh/whale-girl/state.json is written.

Draggable floating TES-gyro widget for the DSH Web UI: click to spin it with linear friction decay, tune the spin speed from a slider, and play the bundled track with its LRC lyrics scrolling in sync. Spin speed and position are remembered.

LAN co-op for the dsh-pet desktop pet: see colleagues' pets on the same network, wave at them, and drag their desktop windows anywhere; an optional included patch adds live animation, bubble and meme sync. Requires dsh-pet 0.3.7.

Compaction integrity: directive lines (never/must/必须 style markers) extracted from the compacted range are verified against the summary — verbatim or by content-word coverage — and every constraint the session silently forgot is reported and written to a JSONL ledger; pinned constraints from config are checked on every compaction.

Encrypted local credential vault for DeepSeek Harness: sidebar record management, an info_records tool for pre-sign-in lookups, opt-in chat capture, per-record manual-only mode, and AES-256-GCM storage protected by Windows DPAPI, the macOS Keychain, or the Linux Secret Service.

Outbound route pool for DeepSeek Harness. Ships 15 seed routes plus a 20-entry candidate pool covering 7 target kinds (GitHub raw/codeload/main, npm registry, PyPI index, HuggingFace, general). Routes are verified before use: upstream IP lists go through a TLS handshake with full certificate-chain validation (a bare TCP check can be answered locally and report dead IPs as healthy), and failures advance a cooldown ladder of 2/5/15 minutes with the fastest healthy route picked per target kind. Routes are applied by rewriting the URL with one of four rules (prefix, registry, index, host-replace), reaching git, pip, npm, pnpm, gh, curl and wget through three paths: the shell seam (download commands the model runs through the bash tool are intercepted and rewritten automatically; commands wrapped by the pwsh tool, and fetches made by the host itself or the renderer, are not covered), two registered tools the model can call directly (line_pool_status, line_pool_run), and child-process spawn. Multi-line commands keep their line breaks and only the download segment is touched. URLs carrying credentials (user:token@host) are never rewritten, so tokens are not forwarded to third-party mirrors. No global config is modified. A sidebar panel lists every route with latency, failure reason and cooldown countdown, supports per-route retest and enable/disable, and shows live TUN/proxy status from network-adapter and loopback port checks. The candidate pool is re-verified every 24 hours so newly usable routes are added and dead ones dropped. 570 tests, 87% line coverage.

Move an entire dsh installation to another machine and check it item by item. Three layers go across: the declaration layer (settings, credentials, plugin declarations and vendored link: sources), the state layer (sessions, storages, skills, attachments) and, optionally, the workspace project code. Sessions are rewritten at the zstd header frame only, workspace paths are remapped through an explicit path mapping, and at the end 14 checks (I1–I13 plus I6b) report PASS / FAIL / WARN. A LAN route pairs two machines and pulls the bundle over directly; merge mode diffs a bundle against a machine that has already been in use and stops before writing anything while conflicts are undecided.

Inspects ONNX models (inputs/outputs, shapes, opset, operators, size) and benchmarks them with ONNX Runtime on the local machine or on a remote target over SSH, reporting average/P50/P95/P99 latency, FPS and the execution provider actually used, with PASS/FAIL gates for FPS, P95 latency and model size. Requires Python 3.10+ with numpy, onnx, onnxruntime, and psutil installed (pip install numpy onnx onnxruntime psutil); remote targets need python3, numpy, and onnxruntime.

Turns what a design, plan or document claims into a model and decides it: UML diagrams rendered, read and reviewed; state machines, protocols and data models checked as models; migrations tested for coverage and rollback symmetry; concurrency claims mined and routed to the checker that can decide them; dependency graphs audited; reports diffed.

A small dock in the DSH Web UI: restart the host or reload the page in one click. Restart asks first (now / 30s / 60s / 2min / cancel); the dock drags to any edge only after a 320ms hold, and stays anchored when the window resizes. Refresh refuses to run unless the plugin bundle is verifiably loadable (timestamp baseline + real bundle fetch + syntax compile), so a reload can never brick the app. Restart is Windows-only (PowerShell 5.1); the UI and page refresh work on all platforms.

Sorts every loaded skill into one or more user-owned workspaces in a right-sidebar tab: each workspace is its own category list plus where every skill sits, categories are created, renamed, reordered and deleted in place, and skills are dragged or picked between them. A first run can let the profile model build the first classification, or place skills into categories the user built first; clicking a row copies its /skill-name and hovering unfolds the description the skill ships.

Windows x64 only, 0.5.4 preview: two scoped tools (dragon_browser and dragon_desktop) that drive a visible browser through the DOM or CDP and Windows apps through UI Automation, with per-origin and per-executable read/control scopes, batch steps, a physical-Esc emergency stop and a redacted action log. 0.5.4 only widens the DSH compatibility range to 0.2.0-rc.2 through 0.2.1.x, because 0.5.3 pinned it to an exact DSH version and was silently skipped on DSH Desktop 0.2.1. Two long-lived native processes remove the per-action process spawn, so a single key step takes about 0.7 s on the same machine; when another window steals the foreground the step is aborted instead of typing into the wrong place. The browser side ships its own Edge/Chrome launcher and CDP client, so it no longer needs another browser plugin or the Electron runtime. It is not an OS sandbox; logins, admin windows and secure desktops stay with the user.

A persistent translate button lives in every page the browser opens: click it and every visible text node is replaced in place, click again to restore. Hold to drag, drop it near an edge and it tucks into a small handle; it is re-injected automatically after navigation. The host LLM service does the translation — the plugin holds no API key.

Registers one `principles_audit` tool for DeepSeek Harness: it reviews a principle library for principle_id collisions and legacy ids, missing causal statements, boundaries, counter-examples or evidence, duplicate and near-duplicate principles, status-versus-confidence inconsistencies, long-stale entries and dimension-coverage gaps. Findings are severity-ranked and a hard gate turns them into pass, warn or fail, where every critical finding must be covered by a valid, unexpired exemption. The library is only read.