Merge remote-tracking branch 'origin/master' into task/command-feedback-master

docs/config-catalog.md

@@ -704,8 +704,34 @@ export interface PiAiProviderProfile {
   apiKey?: string
   /** Credential reference (environment-variable name) resolved per request through `ctx.credentials`. */
   apiKeyEnv?: string
-  /** Override the selected catalog model's endpoint without changing its protocol metadata. */
+  /** Name shown by configuration surfaces; defaults to the route key. */
+  displayName?: string
+  /**
+   * Wire protocol every model on this route speaks. Omission keeps each
+   * installed catalog model's own protocol, which is why a catalog route needs
+   * no protocol at all; a route the catalog does not ship must name one.
+   */
+  api?: string
+  /** Endpoint for this route's models; defaults to the installed catalog's endpoint. */
   baseURL?: string
+  /**
+   * This route's model catalog. Omission serves the installed catalog for the
+   * route unchanged; an explicit list replaces it, each entry defaulting its
+   * unset fields from the installed model of the same id.
+   */
+  models?: PiAiModelProfile[]
+  /**
+   * Context capacity for a model this route lists that neither the entry nor
+   * the installed catalog sizes (default 262,144). A guess by construction, so
+   * a deployment whose gateway serves smaller models corrects it here.
+   */
+  defaultContextWindow?: number
+  /**
+   * Output capability for a model this route lists that neither the entry nor
+   * the installed catalog sizes (default 32,768). This sizes the model; it
+   * never becomes a per-request cap on its own.
+   */
+  defaultMaxTokens?: number
   /** Provider request headers; Harness attribution wins reserved names. */
   headers?: Record<string, string>
   /** Provider-neutral pi-ai reasoning level. */
@@ -725,11 +751,28 @@ export interface PiAiProviderProfile {
   /** Provider-owned model-request retry policy; omission uses normal defaults. */
   retryPolicy?: RetryPolicyConfig
 }
+
+/** One configured model entry: an id plus the catalog fields it overrides. */
+export interface PiAiModelProfile {
+  /** Model id sent to the provider and accepted by {@link GenerateOptions.model}. */
+  id: string
+  /** Display name for selectors; defaults to the catalog name, then the id. */
+  name?: string
+  /** Maximum combined request and response context in tokens. */
+  contextWindow?: number
+  /**
+   * Maximum output tokens. Configuring one also makes it this model's
+   * per-request default; a value inherited from the installed catalog, or the
+   * route's fallback, is the model's capability and never becomes a request
+   * default on its own.
+   */
+  maxTokens?: number
+}
 ```
 
 Depends on: `CacheRetention` (`@earendil-works/pi-ai`) · `ModelThinkingLevel` (`@earendil-works/pi-ai`) · [`RetryPolicyConfig`](../packages/llm/llm/src/index.ts) · `ThinkingBudgets` (`@earendil-works/pi-ai`) · `Transport` (`@earendil-works/pi-ai`)
 
-Source: [`packages/llm/llm-pi-ai/src/config.ts:62`](../packages/llm/llm-pi-ai/src/config.ts)
+Source: [`packages/llm/llm-pi-ai/src/config.ts:122`](../packages/llm/llm-pi-ai/src/config.ts)
 
 ## `@deepseek-ai/dsh-llm-replay`