fix: show custom vision models in LLM selector and model list

Expose user-added imageToText custom models as vision-capable chat
models in the default LLM selector and /v1/models, map custom service
kinds to runtime capabilities, and keep typed filtering for
/v1/models/{kind}.

Co-authored-by: Cursor <cursoragent@cursor.com>

tests/unit/capabilities-service-kind.test.js

@@ -0,0 +1,15 @@
+import { describe, expect, it } from "vitest";
+
+import { capabilitiesFromServiceKind } from "../../open-sse/providers/capabilities.js";
+
+describe("capabilitiesFromServiceKind", () => {
+  it("maps imageToText custom models to vision-capable runtime models", () => {
+    expect(capabilitiesFromServiceKind("imageToText")).toMatchObject({ vision: true });
+  });
+
+  it("maps media output/input custom model kinds to runtime capabilities", () => {
+    expect(capabilitiesFromServiceKind("image")).toMatchObject({ imageOutput: true });
+    expect(capabilitiesFromServiceKind("stt")).toMatchObject({ audioInput: true });
+    expect(capabilitiesFromServiceKind("tts")).toMatchObject({ audioOutput: true });
+  });
+});