Plugins

Dual-model auto-routing plugin: low-cost direct / high-cost upgrade with an escape-learning closed loop (wrong direct answers auto-learn fingerprints, force-upgrading the same fingerprint next time), persisted and interoperable with the Python ModelRouter.

Free-tier model routing for the DeepSeek Harness (dsh) - discover OpenRouter free models, apply the best free model as agent default, auto-rotate on rate limits; paid config untouched unless asked.

Hybrid model router for DeepSeek Harness: declarative rules, user-configurable cost control (cost-first / quality-first / balanced), optional LLM task classifier, and failure fallback chains.

Multi-provider LLM API balances under the chat input, with presets for DeepSeek, OpenRouter and SiliconFlow.

Two-tier model router for DeepSeek Harness — LLM-Judge routing, multi-model fallback chains, exponential-backoff failover, and task-level orchestration (DSH adaptation of pi-shift-router)

DeepSeek Harness plugin: query AI Monitor balance / usage from local SQLite — cost-aware agent, auto bookkeeping with the AI Monitor proxy.

DSH Desktop toolkit with separate settings for each feature: a selection toolbar, a floating assistant, and screenshot, long screenshot and screen recording modes opened by global shortcuts from a toolbar at the top of the screen. Screenshots support shapes, pen, arrows, text and numbered markers, mosaic, pin to desktop, saving, and forwarding to a DSH conversation or the system share panel (Windows and macOS); recordings capture an area, a window or a full screen as MP4, GIF or WebM with optional system sound and microphone. Extract text, Translate and Knowledge graph on captures use the OCR tools of dsh-vision-router, which is installed separately (the settings page offers a one-click install). Requires DSH Desktop >=0.2.2-rc.1 <0.3.0-0. The features run in a separate Electron helper process and the plugin does not download Electron: with the installer build of DSH Desktop you must provide a standalone Electron through the electronExecutable setting, the DSH_DESKTOP_TOOLS_ELECTRON environment variable or $DSH_HOME/electron/; a DSH Desktop started from a bare Electron reuses it. System sound recording is not available on Linux.

Sidebar widget that follows the session's current service and shows its plan quota or balance — OpenCode GO rolling, weekly and monthly windows with time bars, MiniMax usage, and DeepSeek, OpenRouter or Moonshot balances.

Switches which assistant persona answers, based on how the message addresses it (alias matching, with names inside quotes and copula phrases such as "is/was" excluded); each persona is a folder holding its own prompt, aliases, colour, avatar and optional lore, several personas can answer one turn, and a settings panel plus a per-turn routing log make each switch checkable. Personas live under ~/.dsh/personas (deleting one in the panel removes its folder) and the routing log in ~/.dsh/persona-router keeps the first 60 characters of each message; its HTTP routes (/persona-router/…) have no DSH access check.

Provider-aware account balance chip for the DeepSeek Harness composer dock: DeepSeek, OpenRouter, Moonshot/Kimi, Zhipu/GLM, MiniMax and Alibaba Cloud Token Plan, with peak/off-peak and night-discount countdowns.

IPv6 remote-access gateway for DSH: PIN-protected HTTPS reverse proxy with a Let's Encrypt certificate (DNS-01 via DuckDNS), QR scan-to-connect and a settings page, no relay in the data path. Needs a public IPv6 address (detected on Windows and Linux only, not macOS), a free DuckDNS subdomain and token, and inbound ports 8787/8788 open on the router; the AAAA record is only auto-updated when the plugin config sets ddns or tls.

Serial model orchestration: a delegate tool over a built-in catalog of current Chinese-market models (DeepSeek, GLM, Doubao, Hunyuan, MiniMax, MiMo, Kimi, Qwen, GPT). The main agent splits work, picks a model per subtask with a required reason, waits for each result, and falls back to a default model; every route is checked against the Session model-selection policy before a child starts. Needs Plugins → Subagent → Model selection enabled for the routes you want (new sessions only) and each model's provider configured. Uses the same plugin id as other model-router plugins, so install only one of them.

Lists RouterAI prompt, completion and cache-read prices per million tokens for the models configured in this profile, highlighting the active one. Requires a model provider whose config key is `routerai`; without it the table shows no data.

Per-provider API key pool for DeepSeek Harness with manual switching, background reachability probing and plan-usage adapters for DeepSeek, Kimi, MiniMax, Zhipu, OpenRouter and other providers.

Shows the RouterAI credit balance in rubles and the spend since the session started in the sidebar footer (Web and Desktop, Russian-language labels). Requires a RouterAI API key stored in the harness credentials as ROUTERAI_API_KEY; without it the footer shows a "key not set" message instead of the balance.

Lists RouterAI prompt and completion prices for the profile models, highlighting the active one. Requires a model provider whose config key is `routerai`; without it the table shows no data.

Routes model and reasoning effort per turn: a cheap classifier reads each request and picks one of five tiers, a supervisor model re-routes on tool errors and checkpoints, and upgrading to the stronger model waits for confirmation.

Shows the RouterAI credit balance and the spend since the session started in the sidebar footer. Requires a RouterAI API key (`ROUTERAI_API_KEY`) and a model provider whose config key is `routerai`; without them it shows `--`.

Merges your configured, runtime-registered and locally cached models into one panel, probes and minimal-request tests them, pulls each channel's upstream /v1/models catalog, and chains the keepers into named schemes. A virtual ModelPool provider fails over at request time with per-model cooldowns, exponential backoff, image-request avoidance for text-only models, and a 10-minute memory for rejected reasoning levels. Adds a token ledger by day and model with CSV export, and 21 regression probes. Not a fork of dsh-llm-fallbacks.

Intercepts DSH tool results before the model reads them: dedupe cache for repeated calls, a declarative decision graph that replaces large outputs with structured digests, an injection gate, and an honest token ledger that includes a negative-return account for over-compression. Measured 1400-1600 tokens saved per hit; the cumulative ledger is currently negative and the README says why, including that it cannot skip model turns.

After user setup, guides native subagents toward model preferences by task type, using native model-selection permissions with no extra routing-model calls.

Replaces the full skill catalog with keyword-based discovery, per-skill enable/disable switches, and system-prompt section controls. Disabled skills are refused by the skill tool, and their slash-command invocations are blocked at pre-step.

Picks PTC or native tool presentation per task and switches it at runtime for the model or the user.

Routes DeepSeek models in dsh through an OpenCode Go subscription and falls back to the DeepSeek account per model when that model's allowance runs out; a plan-wide fallback covers bad credentials.