diff --git a/.github/workflows/python-integration-tests.yml b/.github/workflows/python-integration-tests.yml
index 9887b667a9..0d8ae36b8f 100644
--- a/.github/workflows/python-integration-tests.yml
+++ b/.github/workflows/python-integration-tests.yml
@@ -195,13 +195,19 @@ jobs:
           done
           # Pull models with retry for transient 429 rate limits
           for model in qwen2.5:1.5b nomic-embed-text; do
+            pulled=false
             for attempt in 1 2 3; do
               if ollama pull "$model"; then
+                pulled=true
                 break
               fi
               echo "Retry $attempt for $model (waiting 15s)..."
               sleep 15
             done
+            if [ "$pulled" != "true" ]; then
+              echo "ERROR: Failed to pull $model after 3 attempts"
+              exit 1
+            fi
           done
         working-directory: .
       - name: Start local MCP server
diff --git a/.github/workflows/python-merge-tests.yml b/.github/workflows/python-merge-tests.yml
index 2e6851e476..ea20ad06e8 100644
--- a/.github/workflows/python-merge-tests.yml
+++ b/.github/workflows/python-merge-tests.yml
@@ -313,13 +313,19 @@ jobs:
           done
           # Pull models with retry for transient 429 rate limits
           for model in qwen2.5:1.5b nomic-embed-text; do
+            pulled=false
             for attempt in 1 2 3; do
               if ollama pull "$model"; then
+                pulled=true
                 break
               fi
               echo "Retry $attempt for $model (waiting 15s)..."
               sleep 15
             done
+            if [ "$pulled" != "true" ]; then
+              echo "ERROR: Failed to pull $model after 3 attempts"
+              exit 1
+            fi
           done
         working-directory: .
       - name: Start local MCP server
diff --git a/python/packages/openai/tests/openai/test_openai_chat_client_azure.py b/python/packages/openai/tests/openai/test_openai_chat_client_azure.py
index b16fbd0f7f..fe25a7202d 100644
--- a/python/packages/openai/tests/openai/test_openai_chat_client_azure.py
+++ b/python/packages/openai/tests/openai/test_openai_chat_client_azure.py
@@ -2,6 +2,7 @@
 
 from __future__ import annotations
 
+import asyncio
 import os
 from functools import wraps
 from pathlib import Path
@@ -77,6 +78,15 @@ async def create_vector_store(client: OpenAIChatClient) -> tuple[str, Content]:
     if result.last_error is not None:
         raise RuntimeError(f"Vector store file processing failed with status: {result.last_error.message}")
 
+    # Wait for the vector store index to be fully searchable.
+    # create_and_poll confirms file processing, but the search index is eventually consistent.
+    for _ in range(10):
+        vs = await client.client.vector_stores.retrieve(vector_store.id)
+        if vs.file_counts.completed >= 1 and vs.file_counts.in_progress == 0:
+            break
+        await asyncio.sleep(1)
+    await asyncio.sleep(2)
+
     return file.id, Content.from_hosted_vector_store(vector_store_id=vector_store.id)