Python: Address PR 5331 comments and track sesssion while calling Agent in email_security_example (#5446)

* Address PR review: fix paths and update FIDES implementation

* Address PR comments and add session tracking in email example in samples

* Fix session creation and resolve merge conflict in docstring example

* Resolve merge conflict in docstring example

python/samples/02-agents/security/FIDES_DEVELOPER_GUIDE.md

@@ -495,36 +495,9 @@ The instructions explain:
 - How to pass `variable_ids` to reference hidden content
 - Best practices for secure content handling
 
-### 9. Message-Level Label Tracking (Phase 1)
+### 9. LabeledMessage Class
 
-The middleware now tracks security labels at the **message level**, not just tool calls:
-
-```python
-from agent_framework.security import LabelTrackingFunctionMiddleware, LabeledMessage
-
-middleware = LabelTrackingFunctionMiddleware()
-
-# Label messages in a conversation
-messages = [
-    {"role": "user", "content": "Hello"},           # Auto-labeled TRUSTED
-    {"role": "assistant", "content": "Hi there"},   # Auto-labeled TRUSTED (no untrusted sources)
-    {"role": "tool", "content": "API response"},    # Auto-labeled UNTRUSTED
-]
-
-labeled_messages = middleware.label_messages(messages)
-# labeled_messages[0].security_label.integrity == TRUSTED
-# labeled_messages[2].security_label.integrity == UNTRUSTED
-
-# Individual message labeling
-middleware.label_message(message_index=5, label=custom_label)
-label = middleware.get_message_label(5)
-
-# Get all message labels
-all_labels = middleware.get_all_message_labels()
-```
-
-**LabeledMessage Class:**
-- Automatically infers labels based on message role
+**LabeledMessage** automatically infers security labels based on message role:
 - User/system messages → TRUSTED
 - Tool messages → UNTRUSTED
 - Assistant messages → Inherit from source_labels or TRUSTED
@@ -1108,18 +1081,6 @@ LabeledMessage.from_dict(data) -> LabeledMessage  # Deserialize
 LabeledMessage.from_message(msg, index) -> LabeledMessage  # Wrap standard message
 ```
 
-### LabelTrackingFunctionMiddleware Extensions
-
-```python
-middleware = LabelTrackingFunctionMiddleware(...)
-
-# Message-level label tracking (Phase 1)
-middleware.label_message(message_index, label, source_labels=None)  # Label a message
-middleware.get_message_label(message_index) -> ContentLabel | None  # Get message label
-middleware.label_messages(messages) -> List[LabeledMessage]         # Batch label messages
-middleware.get_all_message_labels() -> Dict[int, ContentLabel]      # Get all message labels
-```
-
 ### SecureAgentConfig
 
 ```python

python/samples/02-agents/security/email_security_example.py

@@ -278,7 +278,13 @@ async def run_scenarios(agent, config):
     print("- Injection attempts in emails are NOT followed")
     print()
 
-    response = await agent.run("Please fetch my recent emails and give me a brief summary of each one.")
+    # Use a shared session so conversation history persists across scenarios.
+    # Without this, each agent.run() starts a fresh conversation and the LLM
+    # won't know about the emails fetched in Scenario 1 — it would never
+    # attempt to call send_email, so the policy enforcer would never trigger.
+    session = agent.create_session()
+
+    response = await agent.run("Please fetch my recent emails and give me a brief summary of each one.", session=session)
     print(f"\n📋 Agent Response:\n{'-' * 40}")
     print(response.text)
 
@@ -295,7 +301,9 @@ async def run_scenarios(agent, config):
     print("- Agent should explain it cannot send email due to security policy")
     print()
 
-    response = await agent.run("Now please send an email to colleague@company.com summarizing what you found.")
+    response = await agent.run(
+        "Now please send an email to colleague@company.com summarizing what you found.", session=session
+    )
     print(f"\n📋 Agent Response:\n{'-' * 40}")
     print(response.text)