Plugins

Query Chinese Minecraft Wiki (MediaWiki API) and convert raw wiki text into clean AI-readable output — search, page intro, full-page Markdown, and random entry; templates, references, images and cross-language links are stripped before reaching the model.

Unified token quota and usage statistics for dsh: multi-vendor rolling/payg quota with sidebar cards and provider ops, plus session-log token aggregation with trends, heatmap, and per-model breakdown.

Local OCR fallback for text-only routes: when the session model declares it cannot accept images, the attached image is cached locally and its path injected so the model can call ocr_image — PP-OCRv5 + ONNX Runtime on CPU, no API key, images never leave the machine. Silent when the model can see images.

Free conversational ChatGPT Web (GPT 5.6 Luna) model provider for DeepSeek Harness with streaming Markdown.

Dispatch subagents with named profiles (model, reasoning effort, and tool scope per task), safety checks, cost estimation with savings comparison, and a full dispatch decision ledger.

Early-stage plugin connecting DeepSeek Harness to a separately deployed, self-hosted OwnDsh server for team identity, model access control, quotas, and usage auditing.

Model-facing display_file tool that renders 36 file extensions inline in the web UI: images with a click-to-zoom lightbox, seekable video, audio, PDF, Office and OpenDocument files converted to PDF on the host via LibreOffice, and local HTML in a sandboxed frame; bytes stream from a signed HTTP route with range support, and PNG/JPEG/WebP/GIF also enter model context on image-capable routes.

Evidence-driven goal verification plugin for DeepSeek Harness. Locks goals via /ultragoal and verifies completion against command exit codes and generated artifacts, preventing the model from falsely reporting task completion.

CLIProxyAPI quota for DeepSeek Harness: a ring beside the model picker plus a settings panel listing every account quota windows with plans and reset times.

Make your dsh ready for serious coding. (Tools x Schemas)^REPL. `skill://`, `ctx://`, `agent://`, `dvc://`, `dsh://`, IPython REPL, Context as Variables, cross compactions recallable, full context revive. `hash-edit`, `dvc://browser`, subagent as function, workflow as function.

Read-only trajectory review in a resizable conversation sidebar, with rule analysis, optional model explanations, evidence navigation, and same-range run comparison.

Authentication gate for the DeepSeek Harness Web UI: the login gate covers pages, /api, /plugins and WebSocket upgrades; PBKDF2 password hashing, HttpOnly SameSite session cookies and IP-based login lockout; invite-code registration; two-factor login with TOTP or passkeys (WebAuthn: several keys per account, phone enrolment by QR, username-less sign-in, and a password or second-factor step-up before any login factor is added or removed); a user-management settings panel (users edit their own profile and manage their own TOTP and passkeys, admins add or remove users, reset passwords, manage invites and clear the passkeys of a lost device); admin-only model and API-key configuration guards; per-user isolation on the REST/list APIs and on the WebSocket event streams; session persistence across restarts; a JSONL audit log; and a fail-closed gateway. Runs on both DSH transport lines (0.1.1-rc.2 legacy and 0.1.2+ modern) with no configuration; passkey login needs a localhost or HTTPS origin because browsers require a secure context.

Kiro model provider with Builder ID, Identity Center, Google, GitHub and credential-import sign-in, automatic token and profile refresh, account usage, live model discovery, selectable reasoning efforts, streaming tool calls, provider stop-reason and context-overflow handling, and token accounting that uses Kiro's exact counters when it sends them and otherwise scales the context-usage percentage it does send by the model's advertised window.

Identity-gated Tailscale access to the Web GUI with dsh still bound to loopback: a 127.0.0.1 proxy published by `tailscale serve` admits a request only when the Tailscale login it stamps is allowed, with an optional per-device allowlist, so the privileged /api methods behind the loopback check — Settings, Models, Plugins — answer without dsh being told to trust a remote host.

Provides the see_image tool for DSH: send an image file to a configurable OpenAI-compatible vision model and relay its description back to a text-only model.

Wraps globalThis.fetch to route DeepSeek Harness model-API requests through an HTTP/SOCKS proxy by target domain, leaving all other requests on the direct connection, without modifying Harness source.

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.

Deep research as an agent mode: one reviewed loop that plans, researches in adaptive parallel rounds driven by the gaps the researchers themselves declare, synthesises a cited report and then reviews it adversarially, instead of a script the model rewrites per call. Questions the round budget never reached are named in the report rather than dropped.

Config-driven lifecycle hooks, including context injection: declare event, handler and outcome in YAML, where the handler is an in-harness tool (MCP included), a shell command or an HTTP endpoint, and the outcome is model-visible context, a denied tool call, or fire-and-forget.

Claim-verification skill that checks design documents and plans against codebase facts, escalating behavioral claims to executable logic-primitive verification for state machines and data models, with before/after regression, domain constraints, and concurrency risk mining.

Progressive tool disclosure: a deferred tool group costs one catalog line instead of its full schemas until the model loads it with tool_search, with one switch per group in Settings and each group measured against the live registry.

A thinking level stored per provider and model, so reasoning effort outlives the session it was set in and also reaches subagents, which dsh never asks. The in-session picker still wins, and a model with no row keeps its provider default.

Per provider/model generation concurrency, with a settings card: a cap on how many sessions may stream at once, enforced at the stream and again at subagent spawn, where a fan-out past the cap waits in a FIFO queue instead of failing.

Large-image recognition for vision-exp models: lossless 800×800 tile recognition (smart/pipeline/full), local OCR with preprocessing & handwriting routing, optional multi-vendor GPU (DirectML/CUDA/OpenVINO) with auto CPU fallback.