Python: Add integration tests for durabletask package (#3317)

* Add integration tests

* Fix flaky test

* Fix env viz

* Fix tests and address feedback

python/samples/getting_started/durabletask/03_single_agent_streaming/worker.py

@@ -18,7 +18,7 @@ import os
 from datetime import timedelta
 
 import redis.asyncio as aioredis
-from agent_framework import AgentRunResponseUpdate
+from agent_framework import AgentResponseUpdate
 from agent_framework.azure import AzureOpenAIChatClient
 from agent_framework_durabletask import AgentCallbackContext, AgentResponseCallbackProtocol, DurableAIAgentWorker
 from azure.identity import AzureCliCredential, DefaultAzureCredential
@@ -66,7 +66,7 @@ class RedisStreamCallback(AgentResponseCallbackProtocol):
 
     async def on_streaming_response_update(
         self,
-        update: AgentRunResponseUpdate,
+        update: AgentResponseUpdate,
         context: AgentCallbackContext,
     ) -> None:
         """Write streaming update to Redis Stream.

python/samples/getting_started/durabletask/04_single_agent_orchestration_chaining/worker.py

@@ -15,7 +15,7 @@ from collections.abc import Generator
 import logging
 import os
 
-from agent_framework import AgentRunResponse
+from agent_framework import AgentResponse
 from agent_framework.azure import AzureOpenAIChatClient
 from agent_framework_durabletask import DurableAIAgentOrchestrationContext, DurableAIAgentWorker
 from azure.identity import AzureCliCredential, DefaultAzureCredential
@@ -61,7 +61,7 @@ def get_orchestration():
 
 def single_agent_chaining_orchestration(
     context: OrchestrationContext, _: str
-) -> Generator[Task[AgentRunResponse], AgentRunResponse, str]:
+) -> Generator[Task[AgentResponse], AgentResponse, str]:
     """Orchestration that runs the writer agent twice on the same thread.
     
     This demonstrates chaining behavior where the output of the first agent run

python/samples/getting_started/durabletask/07_single_agent_orchestration_hitl/worker.py

@@ -72,7 +72,7 @@ def create_writer_agent():
     )
 
 
-def notify_user_for_approval(context: ActivityContext, content: dict[str, str]) -> None:
+def notify_user_for_approval(context: ActivityContext, content: dict[str, str]) -> str:
     """Activity function to notify user for approval.
     
     Args:
@@ -84,8 +84,9 @@ def notify_user_for_approval(context: ActivityContext, content: dict[str, str])
     logger.info(f"Title: {model.title or '(untitled)'}")
     logger.info(f"Content: {model.content}")
     logger.info("Use the client to send approval or rejection.")
+    return "Notification sent to user for approval."
 
-def publish_content(context: ActivityContext, content: dict[str, str]) -> None:
+def publish_content(context: ActivityContext, content: dict[str, str]) -> str:
     """Activity function to publish approved content.
     
     Args:
@@ -96,6 +97,7 @@ def publish_content(context: ActivityContext, content: dict[str, str]) -> None:
     logger.info("PUBLISHING: Content has been published successfully:")
     logger.info(f"Title: {model.title or '(untitled)'}")
     logger.info(f"Content: {model.content}")
+    return "Published content successfully."
 
 
 def content_generation_hitl_orchestration(
@@ -230,6 +232,14 @@ def content_generation_hitl_orchestration(
             
             # Content rejected - incorporate feedback and regenerate
             logger.debug(f"[Orchestration] Content rejected. Feedback: {approval.feedback}")
+            
+            # Check if we've exhausted attempts
+            if attempt >= payload.max_review_attempts:
+                context.set_custom_status("Max review attempts exhausted.")
+                # Max attempts exhausted
+                logger.error(f"[Orchestration] Max attempts ({payload.max_review_attempts}) exhausted")
+                break
+            
             context.set_custom_status(f"Content rejected by human reviewer. Regenerating...")
             
             rewrite_prompt = (
@@ -262,7 +272,8 @@ def content_generation_hitl_orchestration(
                 f"Human approval timed out after {payload.approval_timeout_seconds} second(s)."
             )
     
-    # Max attempts exhausted
+    # If we exit the loop without returning, max attempts were exhausted
+    context.set_custom_status("Max review attempts exhausted.")
     raise RuntimeError(
         f"Content could not be approved after {payload.max_review_attempts} iteration(s)."
     )