review comments

Author: davidkyle

x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/elasticsearch/ElasticsearchInternalService.java

@@ -1041,7 +1041,7 @@ private void inferBatchAndRunAfter(EmbeddingRequestChunker.BatchRequestAndListen
             });
 
             var maybeDeployListener = runNextListener.delegateResponse(
-                (l, exception) -> maybeStartDeployment(esModel, exception, inferenceRequest, runNextListener)
+                (l, exception) -> maybeStartDeployment(esModel, exception, inferenceRequest, l)
             );
 
             client.execute(InferModelAction.INSTANCE, inferenceRequest, maybeDeployListener);

x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/elasticsearch/ElasticsearchInternalServiceTests.java

@@ -1283,10 +1283,7 @@ public void testChunkingLargeDocument() throws InterruptedException {
 
         // build a doc with enough words to make numChunks of chunks
         int numWords = numChunks * wordsPerChunk;
-        var docBuilder = new StringBuilder();
-        for (int i = 0; i < numWords; i++) {
-            docBuilder.append("word ");
-        }
+        var input = "word ".repeat(numWords);
 
         // how many response objects to return in each batch
         int[] numResponsesPerBatch = new int[numBatches];
@@ -1341,7 +1338,7 @@ public void testChunkingLargeDocument() throws InterruptedException {
         service.chunkedInfer(
             model,
             null,
-            List.of(docBuilder.toString()),
+            List.of(input),
             Map.of(),
             InputType.SEARCH,
             new ChunkingOptions(null, null),