Foundry Evals integration for Python

Add evaluation framework with local and Foundry-hosted evaluator support:

- EvalItem/EvalResult core types with conversation splitting strategies
- @evaluator decorator for defining custom evaluation functions
- LocalEvaluator for running evaluations locally
- FoundryEvals provider for Azure AI Foundry hosted evaluations
- evaluate_agent() orchestration with expected values support
- evaluate_workflow() for multi-agent workflow evaluation
- Comprehensive test suite and evaluation samples

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Author: alliscode

python/packages/azure-ai/agent_framework_azure_ai/__init__.py

@@ -2,6 +2,17 @@
 
 import importlib.metadata
 
+# Re-export core eval types for convenience
+from agent_framework._eval import (
+    EvalItem,
+    EvalItemResult,
+    EvalResults,
+    EvalScoreResult,
+    Evaluator,
+    evaluate_agent,
+    evaluate_workflow,
+)
+
 from ._agent_provider import AzureAIAgentsProvider
 from ._chat_client import AzureAIAgentClient, AzureAIAgentOptions
 from ._client import AzureAIClient, AzureAIProjectAgentOptions, RawAzureAIClient
@@ -11,6 +22,12 @@
     AzureAIInferenceEmbeddingSettings,
     RawAzureAIInferenceEmbeddingClient,
 )
+from ._foundry_evals import (
+    FoundryEvals,
+    evaluate_foundry_target,
+    evaluate_traces,
+    setup_continuous_eval,
+)
 from ._foundry_memory_provider import FoundryMemoryProvider
 from ._project_provider import AzureAIProjectAgentProvider
 from ._shared import AzureAISettings
@@ -31,8 +48,19 @@
     "AzureAIProjectAgentOptions",
     "AzureAIProjectAgentProvider",
     "AzureAISettings",
+    "EvalItem",
+    "EvalItemResult",
+    "EvalResults",
+    "EvalScoreResult",
+    "Evaluator",
+    "FoundryEvals",
     "FoundryMemoryProvider",
     "RawAzureAIClient",
     "RawAzureAIInferenceEmbeddingClient",
     "__version__",
+    "evaluate_agent",
+    "evaluate_foundry_target",
+    "evaluate_traces",
+    "evaluate_workflow",
+    "setup_continuous_eval",
 ]