Python: [BREAKING] Standardize model selection on model (#4999)

* Refactor Anthropic model option and provider clients

Rename the Anthropic client model option from model_id to model, add provider-specific Anthropic wrappers for Foundry, Bedrock, and Vertex, and expose them through the Anthropic, Foundry, Amazon, and Google namespaces. Update core option handling, docs, samples, and tests accordingly.

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

* Fix Anthropic skills sample typing

Cast the Anthropic beta client to Any in the skills sample so the pre-commit sample pyright check no longer fails on beta skills and files endpoints that are not exposed by the current SDK stubs.

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

* undo sample mypy

* Retry CI after transient external failures

Retrigger PR validation after an unrelated Copilot review workflow SAML failure and a transient external tau2 git fetch failure in the Windows Python test setup.

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

* Address review feedback on model option merging

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

* Address Anthropic compatibility review feedback

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

* moved all to `model`

* fixes for azure ai search

* Python: standardize remaining sample env var names

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

* Python: fix foundry-local pyright compatibility

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

* updated env vars in cicd

---------

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

python/packages/devui/agent_framework_devui/_discovery.py

@@ -391,7 +391,7 @@ class EntityDiscovery:
             source=source,  # IMPORTANT: Pass the source parameter
             tools=[str(tool) for tool in (tools_list or [])],
             instructions=instructions,
-            model_id=model,
+            model=model,
             chat_client_type=chat_client_type,
             context_provider=context_provider_list,
             middleware=middlewares_list,
@@ -846,7 +846,7 @@ class EntityDiscovery:
                 description=description,
                 tools=tools_union,
                 instructions=instructions,
-                model_id=model,
+                model=model,
                 chat_client_type=chat_client_type,
                 context_provider=context_provider_list,
                 middleware=middlewares_list,

python/packages/devui/agent_framework_devui/_mapper.py

@@ -770,9 +770,9 @@ class MessageMapper:
         from .models._openai_custom import AgentCompletedEvent, AgentFailedEvent, AgentStartedEvent
 
         try:
-            # Get model name from request or use 'devui' as default
+            # Get model from request or use 'devui' as default
             request_obj = context.get("request")
-            model_name = request_obj.model if request_obj and request_obj.model else "devui"
+            model = request_obj.model if request_obj and request_obj.model else "devui"
 
             if isinstance(event, AgentStartedEvent):
                 execution_id = f"agent_{uuid4().hex[:12]}"
@@ -783,7 +783,7 @@ class MessageMapper:
                     id=f"resp_{execution_id}",
                     object="response",
                     created_at=float(time.time()),
-                    model=model_name,
+                    model=model,
                     output=[],
                     status="in_progress",
                     parallel_tool_calls=False,
@@ -818,7 +818,7 @@ class MessageMapper:
                     id=f"resp_{execution_id}",
                     object="response",
                     created_at=float(time.time()),
-                    model=model_name,
+                    model=model,
                     output=[],
                     status="failed",
                     error=response_error,
@@ -865,16 +865,16 @@ class MessageMapper:
                 # Return proper OpenAI event objects
                 events: list[Any] = []
 
-                # Get model name from request or use 'devui' as default
+                # Get model from request or use 'devui' as default
                 request_obj = context.get("request")
-                model_name = request_obj.model if request_obj and request_obj.model else "devui"
+                model = request_obj.model if request_obj and request_obj.model else "devui"
 
                 # Create a full Response object with all required fields
                 response_obj = Response(
                     id=f"resp_{workflow_id}",
                     object="response",
                     created_at=float(time.time()),
-                    model=model_name,
+                    model=model,
                     output=[],  # Empty output list initially
                     status="in_progress",
                     # Required fields with safe defaults
@@ -989,9 +989,9 @@ class MessageMapper:
                 # Import Response and ResponseError types
                 from openai.types.responses import Response, ResponseError
 
-                # Get model name from request or use 'devui' as default
+                # Get model from request or use 'devui' as default
                 request_obj = context.get("request")
-                model_name = request_obj.model if request_obj and request_obj.model else "devui"
+                model = request_obj.model if request_obj and request_obj.model else "devui"
 
                 # Extract error message from WorkflowErrorDetails
                 if details:
@@ -1013,7 +1013,7 @@ class MessageMapper:
                     id=f"resp_{workflow_id}",
                     object="response",
                     created_at=float(time.time()),
-                    model=model_name,
+                    model=model,
                     output=[],
                     status="failed",
                     error=response_error,

python/packages/devui/agent_framework_devui/_session.py

@@ -20,7 +20,7 @@ class RequestRecord(TypedDict):
     entity_id: str
     executor: str
     input: Any
-    model_id: str
+    model: str
     stream: bool
     execution_time: NotRequired[float]
     status: NotRequired[str]
@@ -91,7 +91,7 @@ class SessionManager:
             logger.debug(f"Closed session: {session_id}")
 
     def add_request_record(
-        self, session_id: str, entity_id: str, executor_name: str, request_input: Any, model_id: str
+        self, session_id: str, entity_id: str, executor_name: str, request_input: Any, model: str
     ) -> str:
         """Add a request record to a session.
 
@@ -100,7 +100,7 @@ class SessionManager:
             entity_id: ID of the entity being executed
             executor_name: Name of the executor
             request_input: Input for the request
-            model_id: Model name
+            model: Model name
 
         Returns:
             Request ID
@@ -115,7 +115,7 @@ class SessionManager:
             "entity_id": entity_id,
             "executor": executor_name,
             "input": request_input,
-            "model_id": model_id,
+            "model": model,
             "stream": True,
         }
         session["requests"].append(request_record)
@@ -163,7 +163,7 @@ class SessionManager:
                     "timestamp": req["timestamp"].isoformat(),
                     "entity_id": req["entity_id"],
                     "executor": req["executor"],
-                    "model": req["model_id"],
+                    "model": req["model"],
                     "input_length": len(str(req["input"])) if req["input"] else 0,
                     "execution_time": req.get("execution_time"),
                     "status": req.get("status", "unknown"),

python/packages/devui/agent_framework_devui/_utils.py

@@ -59,13 +59,13 @@ def extract_agent_metadata(entity_object: Any) -> dict[str, Any]:
         chat_opts = entity_object.default_options
         chat_opts_dict = _string_key_dict(chat_opts)
         if chat_opts_dict is not None:
-            model_id = chat_opts_dict.get("model_id")
-            if model_id:
-                metadata["model"] = model_id
-        elif hasattr(chat_opts, "model_id") and chat_opts.model_id:
-            metadata["model"] = chat_opts.model_id
-    if metadata["model"] is None and hasattr(entity_object, "client") and hasattr(entity_object.client, "model_id"):
-        metadata["model"] = entity_object.client.model_id
+            model = chat_opts_dict.get("model")
+            if model:
+                metadata["model"] = model
+        elif hasattr(chat_opts, "model") and chat_opts.model:
+            metadata["model"] = chat_opts.model
+    if metadata["model"] is None and hasattr(entity_object, "client") and hasattr(entity_object.client, "model"):
+        metadata["model"] = entity_object.client.model
 
     # Try to get chat client type
     if hasattr(entity_object, "client"):

python/packages/devui/agent_framework_devui/models/_discovery_models.py

@@ -44,7 +44,7 @@ class EntityInfo(BaseModel):
 
     # Agent-specific fields (optional, populated when available)
     instructions: str | None = None
-    model_id: str | None = None
+    model: str | None = None
     chat_client_type: str | None = None
     context_provider: list[str] | None = None
     middleware: list[str] | None = None

python/packages/devui/dev.md

@@ -37,7 +37,7 @@ OPENAI_CHAT_MODEL="gpt-4o-mini"
 
 # Or for Azure OpenAI
 AZURE_OPENAI_ENDPOINT="your-endpoint"
-AZURE_OPENAI_DEPLOYMENT_NAME="your-deployment-name"
+AZURE_OPENAI_MODEL="your-deployment-name"
 ```
 
 ## 4. Test DevUI

python/packages/devui/frontend/src/components/layout/deployment-modal.tsx

@@ -247,7 +247,7 @@ services:
       # Or Azure OpenAI
       - AZURE_OPENAI_API_KEY=\${AZURE_OPENAI_API_KEY}
       - AZURE_OPENAI_ENDPOINT=\${AZURE_OPENAI_ENDPOINT}
-      - AZURE_OPENAI_DEPLOYMENT_NAME=\${AZURE_OPENAI_DEPLOYMENT_NAME}
+      - AZURE_OPENAI_MODEL=\${AZURE_OPENAI_MODEL}
       # Optional: Enable instrumentation
       - ENABLE_INSTRUMENTATION=\${ENABLE_INSTRUMENTATION:-false}
     ports:

python/packages/devui/frontend/src/data/gallery/sample-entities.ts

@@ -78,7 +78,7 @@ export const SAMPLE_ENTITIES: SampleEntity[] = [
         required: true,
       },
       {
-        name: "AZURE_OPENAI_DEPLOYMENT_NAME",
+        name: "AZURE_OPENAI_MODEL",
         description: "Name of the deployed model in Azure OpenAI",
         required: true,
         example: "gpt-4o",

python/packages/devui/tests/devui/test_server.py

@@ -151,7 +151,7 @@ async def test_credential_cleanup() -> None:
     # Create mock chat client with credential
     mock_client = Mock()
     mock_client.async_credential = mock_credential
-    mock_client.model_id = "test-model"
+    mock_client.model = "test-model"
     mock_client.function_invocation_configuration = None
 
     # Create agent with mock client
@@ -184,7 +184,7 @@ async def test_credential_cleanup_error_handling() -> None:
     # Create mock chat client with credential
     mock_client = Mock()
     mock_client.async_credential = mock_credential
-    mock_client.model_id = "test-model"
+    mock_client.model = "test-model"
     mock_client.function_invocation_configuration = None
 
     # Create agent with mock client
@@ -219,7 +219,7 @@ async def test_multiple_credential_attributes() -> None:
     mock_client = Mock()
     mock_client.credential = mock_cred1
     mock_client.async_credential = mock_cred2
-    mock_client.model_id = "test-model"
+    mock_client.model = "test-model"
     mock_client.function_invocation_configuration = None
 
     # Create agent with mock client