test: fix generation/conversation e2e (model id -> mistral plain FM, error/null guards)

Two Gen2-cdk e2e suites (generation, conversation) were failing for
reasons unrelated to product code. This change fixes the test fixtures
and adds fail-fast hygiene guards. Test-side only; no product behavior
changes.

Model ids
  The fixtures invoked anthropic.claude-3-haiku-20240307-v1:0, a legacy
  Bedrock model that has been auto-revoked in the e2e account; invoking
  it returned ResourceNotFoundException, AppSync resolved null, and the
  tests crashed on a null-deref.

  - generation: the @generation transformer's AppSync->Bedrock IAM role
    grants bedrock:InvokeModel only on the foundation-model ARN, so a
    cross-region inference profile fails with AccessDenied. The
    generation fixture is switched to the active on-demand foundation
    model mistral.mistral-large-2407-v1:0, which the e2e account can
    invoke under the existing IAM and which satisfies the basic
    text/scalar assertions.

  - conversation: routes via @aws-amplify/ai-constructs, which handles
    inference-profile IAM, so the conversation fixture uses the active
    inference profile us.anthropic.claude-haiku-4-5-20251001-v1:0.

Fail-fast guards
  generation.test.ts: assert the GraphQL response has no errors and that
  the generated recipe is not null before dereferencing, so a
  Bedrock/GraphQL error is printed instead of a TypeError.

  conversation.test.ts: replace the ineffective toBeDefined() check on
  the stream part with not.toBeNull(), guard the .length read when the
  part is null, and add a max-iteration / overall-timeout guard inside
  the subscription for-await loop so a non-streaming assistant fails
  fast with a descriptive message instead of cascading into the jest
  timeout.

---
Prompt: Split the mixed e2e/CI branch into a clean draft PR off main
containing only the generation/conversation e2e test fixes: switch the
dead legacy claude-3-haiku model id to a working model (generation ->
mistral plain on-demand FM, conversation -> working inference profile)
and add the error/null fail-fast guards. tsc the construct-tests
package and commit (no --no-verify).

Author: sarayev

packages/amplify-graphql-api-construct-tests/src/__tests__/conversations/conversation.test.ts

@@ -111,14 +111,34 @@ describe('conversation', () => {
         expect(message.conversationId).toEqual(conversationId);
 
         const events: AmplifyAIConversationMessageStreamPart[] = [];
+        // Guard against a non-streaming assistant: fail fast with a clear message instead of
+        // hanging on the subscription until the surrounding 20-minute jest timeout cascades.
+        const MAX_STREAM_EVENTS = 1000;
+        const streamDeadline = Date.now() + ONE_MINUTE;
         // expect to receive the assistant response in the subscription
         for await (const event of subscription) {
-          events.push(event.onCreateAssistantResponsePirateChat);
+          if (Date.now() > streamDeadline) {
+            throw new Error(
+              `Timed out waiting for a streamed assistant response with a stopReason after ${ONE_MINUTE}ms ` +
+                `(received ${events.length} events). The assistant may not be streaming a response.`,
+            );
+          }
+          if (events.length >= MAX_STREAM_EVENTS) {
+            throw new Error(
+              `Received ${events.length} stream events without a stopReason; aborting to avoid an unbounded loop. ` +
+                `The assistant may not be terminating its response.`,
+            );
+          }
+
+          const streamPart = event.onCreateAssistantResponsePirateChat;
+          events.push(streamPart);
           // expect event to contain `p`
-          expect(event.onCreateAssistantResponsePirateChat.p).toBeDefined();
-          expect(event.onCreateAssistantResponsePirateChat.p.length).toBeGreaterThanOrEqual(0);
+          expect(streamPart.p).not.toBeNull();
+          if (streamPart.p != null) {
+            expect(streamPart.p.length).toBeGreaterThanOrEqual(0);
+          }
 
-          if (event.onCreateAssistantResponsePirateChat.stopReason) break;
+          if (streamPart.stopReason) break;
         }
         const accumulatedP = events.map((messageStreamPart) => messageStreamPart.p).join('');
         expect(accumulatedP.length).toBeGreaterThan(0);

packages/amplify-graphql-api-construct-tests/src/__tests__/conversations/graphql/schema-conversation.graphql

@@ -6,7 +6,7 @@ type Mutation {
     toolConfiguration: AmplifyAIToolConfigurationInput
   ): AmplifyAIConversationMessage
     @conversation(
-      aiModel: "anthropic.claude-3-haiku-20240307-v1:0"
+      aiModel: "us.anthropic.claude-haiku-4-5-20251001-v1:0"
       systemPrompt: "You are a helpful chatbot that responds in the voice and tone of a pirate. Respond in 20 words or less."
       auth: { strategy: owner, provider: userPools }
     )

packages/amplify-graphql-api-construct-tests/src/__tests__/generations/generation.test.ts

@@ -63,7 +63,9 @@ describe('generation', () => {
         };
 
         const generateRecipeResult = await doAppSyncGraphqlQuery({ ...args, query: generateRecipe, variables });
+        expect(generateRecipeResult.body.errors).toBeUndefined();
         const recipe = generateRecipeResult.body.data.generateRecipe;
+        expect(recipe).not.toBeNull();
         expect(recipe.name).toBeDefined();
       });
     });

packages/amplify-graphql-api-construct-tests/src/__tests__/generations/graphql/schema-generation.graphql

@@ -6,14 +6,14 @@ type Recipe {
 type Query {
   summarize(input: String): String
     @generation(
-      aiModel: "anthropic.claude-3-haiku-20240307-v1:0"
+      aiModel: "mistral.mistral-large-2407-v1:0"
       systemPrompt: "summarize the input."
       inferenceConfiguration: { temperature: 0.5 }
     )
 
   generateRecipe(description: String): Recipe
-    @generation(aiModel: "anthropic.claude-3-haiku-20240307-v1:0", systemPrompt: "You are a 3 star michelin chef that generates recipes.")
+    @generation(aiModel: "mistral.mistral-large-2407-v1:0", systemPrompt: "You are a 3 star michelin chef that generates recipes.")
 
   solveEquation(equation: String): Int
-    @generation(aiModel: "anthropic.claude-3-haiku-20240307-v1:0", systemPrompt: "Solve the equation and return the result.")
+    @generation(aiModel: "mistral.mistral-large-2407-v1:0", systemPrompt: "Solve the equation and return the result.")
 }