diff --git a/extensions/qa-lab/src/providers/image-generation.test.ts b/extensions/qa-lab/src/providers/image-generation.test.ts
index a775e26713a..6077021d376 100644
--- a/extensions/qa-lab/src/providers/image-generation.test.ts
+++ b/extensions/qa-lab/src/providers/image-generation.test.ts
@@ -2,16 +2,18 @@ import { describe, expect, it } from "vitest";
 import { buildQaImageGenerationConfigPatch } from "./image-generation.js";
 
 describe("QA provider image generation config", () => {
-  it("uses the selected mock provider for mock-openai image generation", () => {
+  it("uses the OpenAI image provider against the selected mock-openai endpoint", () => {
     const patch = buildQaImageGenerationConfigPatch({
       providerMode: "mock-openai",
       providerBaseUrl: "http://127.0.0.1:44080/v1",
       requiredPluginIds: ["qa-channel"],
     });
 
-    expect(patch.plugins.allow).toEqual(["acpx", "memory-core", "qa-channel"]);
-    expect(patch.agents.defaults.imageGenerationModel.primary).toBe("mock-openai/gpt-image-1");
+    expect(patch.plugins.allow).toEqual(["acpx", "memory-core", "openai", "qa-channel"]);
+    expect(patch.plugins.entries?.openai).toEqual({ enabled: true });
+    expect(patch.agents.defaults.imageGenerationModel.primary).toBe("openai/gpt-image-1");
     expect(patch.models?.providers["mock-openai"]?.baseUrl).toBe("http://127.0.0.1:44080/v1");
+    expect(patch.models?.providers.openai?.baseUrl).toBe("http://127.0.0.1:44080/v1");
   });
 
   it("preserves already-allowed plugins when configuring image generation", () => {
diff --git a/extensions/qa-lab/src/providers/image-generation.ts b/extensions/qa-lab/src/providers/image-generation.ts
index 5606db95e07..acbe2d7343e 100644
--- a/extensions/qa-lab/src/providers/image-generation.ts
+++ b/extensions/qa-lab/src/providers/image-generation.ts
@@ -22,9 +22,12 @@ function uniqueNonEmpty(values: readonly (string | null | undefined)[]) {
 
 export function buildQaImageGenerationConfigPatch(input: QaImageGenerationPatchInput) {
   const provider = getQaProvider(input.providerMode);
-  const imageModelRef = provider.defaultImageGenerationModel({
-    modelProviderIds: provider.defaultImageGenerationProviderIds,
-  });
+  const usesOpenAiMockImageProvider = input.providerMode === "mock-openai";
+  const imageModelRef = usesOpenAiMockImageProvider
+    ? "openai/gpt-image-1"
+    : provider.defaultImageGenerationModel({
+        modelProviderIds: provider.defaultImageGenerationProviderIds,
+      });
   if (!imageModelRef) {
     throw new Error(
       `QA provider "${input.providerMode}" does not expose an image generation model`,
@@ -42,7 +45,8 @@ export function buildQaImageGenerationConfigPatch(input: QaImageGenerationPatchI
       providerBaseUrl: input.providerBaseUrl,
     });
   })();
-  const providerPluginIds = provider.usesModelProviderPlugins ? [imageProviderId] : [];
+  const providerPluginIds =
+    provider.usesModelProviderPlugins || usesOpenAiMockImageProvider ? [imageProviderId] : [];
   const enabledPluginIds = uniqueNonEmpty(providerPluginIds);
 
   return {