Language models
Language models integrate with DSH's model router. They are not a single selected capability service: every configured route from every loaded provider is available at the same time. Chats select a model as route/model.
Configure a route
In Settings → AI Providers → Language models, create a route with a stable ID and display name, choose a reusable connection, then add its models. Model discovery uses GET /models; models can also be entered manually.
Each model can declare:
- display name and context window;
- default output-token limit;
- image input support;
- named reasoning levels and a default level;
- sampling overrides.
Route-level sampling applies to every model unless overridden at model or request level. Supported controls include temperature, top-p, top-k, min-p, frequency and presence penalties, repetition penalty, seed, stop strings, output limit, tool choice, and additional JSON body fields.
OpenAI-compatible behavior
The project-maintained OpenAI provider streams POST /chat/completions and translates DSH messages, images, tool definitions, tool calls, reasoning, usage, and finish reasons. Route options cover several compatibility differences:
| Setting | Purpose |
|---|---|
maxCompletionTokens | Send max_completion_tokens instead of max_tokens |
replayReasoning | Include earlier reasoning when sending history back |
reasoningTags | Read reasoning from separate fields, explicit tags, or an implicit prefix |
headers | Add route-specific request headers |
body | Add provider-specific top-level request fields |
Route, model, request, and registered policy settings are merged before the call. DSH request values remain the most specific.
Policies
A plugin that knows the purpose of a request can register an LlmPolicy through ctx.aiProviders.policy(). Policies can adjust sampling and concurrency priority without binding the caller to the OpenAI provider.
Anthropic-native behavior
The project-maintained Anthropic provider uses POST /messages with native system prompts, content blocks, tool declarations, tool use and tool results. It translates streamed text, thinking, tool-input JSON, usage, cache usage, and stop reasons into DSH chunks. Image blocks are read from DSH's attachment service and sent as base64 image sources; offloaded images remain text placeholders.
Anthropic supports language models only in this plugin. It does not register embedding, reranking, speech, or image-generation services.