feat: snip a region into chat, and make links clickable (#14)

src/lib/ollama.ts

@@ -219,6 +219,44 @@ export async function listModels(options: ListModelsOptions): Promise<ModelInfo[
     .sort((a, b) => a.name.localeCompare(b.name));
 }
 
+export interface ModelCapabilitiesOptions {
+  host: string;
+  apiKey: string;
+  model: string;
+  signal?: AbortSignal;
+}
+
+/**
+ * The features a model reports for itself, straight from `POST /api/show`.
+ *
+ * `GET /api/tags` is not enough here: it returns names, sizes and quantization
+ * levels and says nothing about what the model can actually do. The capability
+ * list is what turns "image input" from a guess about the model's name into a
+ * fact, so it is worth the extra request.
+ */
+export async function modelCapabilities(options: ModelCapabilitiesOptions): Promise<string[]> {
+  const host = normalizeHost(options.host);
+
+  const response = await fetch(`${host}/api/show`, {
+    method: "POST",
+    headers: { "Content-Type": "application/json", ...authHeaders(options.apiKey) },
+    body: JSON.stringify({ model: options.model }),
+    signal: options.signal,
+  });
+
+  if (!response.ok) {
+    throw describeHttpError(response.status, await safeText(response), host);
+  }
+
+  const payload = (await response.json()) as { capabilities?: string[] };
+  return payload.capabilities ?? [];
+}
+
+/** Ollama reports image input as the `vision` capability. */
+export function supportsVision(capabilities: string[]): boolean {
+  return capabilities.includes("vision");
+}
+
 export interface WebSearchResult {
   title: string;
   url: string;