Python: [Bug]: AF 1.1 call FoundryChatclient report Error.

[hylinux]

Description

• What Happened?
  I create a new Microsoft Foundry, and get it endpoint from Foundry Portal:
  https://hongweifoundry.services.ai.azure.com/api/projects/hongwei-test-project1

according the document: https://learn.microsoft.com/en-us/agent-framework/agents/providers/microsoft-foundry?pivots=programming-language-python

I setup two enviroments:
FOUNDRY_PROJECT_ENDPOINT="https://hongweifoundry.services.ai.azure.com/api/projects/hongwei-test-project1"
FOUNDRY_MODEL="gpt-5.4"

I am confirmed my model deployment name is "gpt-5.4".

and then I create a Agent like this:

Agent(
client=FoundryChatClient(
project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
model=os.environ["FOUNDRY_MODEL"],
credential=AzureCliCredential()),
instructions="You are an email assistant that helps users draft response to emails with professionalism.",
name="email_assistant_agent",
default_options={"response_format": EmailResponse}, #type: ignore
)

the code always reported:

File "C:\Users\honguo\source\repos\Python\agent-framework\control-flow\multi-selection-edge-group.venv\Lib\site-packages\agent_framework_openai_chat_client.py", line 499, in _handle_request_error
raise ChatClientException(
...<5 lines>...
) from ex
agent_framework.exceptions.ChatClientException: <class 'agent_framework_foundry._chat_client.FoundryChatClient'> service failed to complete the prompt: Error code: 404 - {'error': {'type': 'invalid_request_error', 'code': 'DeploymentNotFound', 'message': 'The API deployment for this resource does not exist. If you created the deployment within the last 5 minutes, please wait a moment and try again.'}}

• What did you expect to happen?
  hope it works

Code Sample

Error Messages / Stack Traces

 ~\source\repos\Python\agent-framework\control-flow\multi-selection-edge-group
❯ uv run .\main.py
{'api_key': None, 'base_url': None, 'org_id': None, 'model': 'my-gpt-54', 'embedding_model': None, 'chat_model': 'my-gpt-54', 'chat_completion_model': None}
<openai.AsyncOpenAI object at 0x0000027726C75F90>
False
{'api_key': None, 'base_url': None, 'org_id': None, 'model': 'my-gpt-54', 'embedding_model': None, 'chat_model': 'my-gpt-54', 'chat_completion_model': None}
<openai.AsyncOpenAI object at 0x0000027726CA68B0>
False
{'api_key': None, 'base_url': None, 'org_id': None, 'model': 'my-gpt-54', 'embedding_model': None, 'chat_model': 'my-gpt-54', 'chat_completion_model': None}
<openai.AsyncOpenAI object at 0x0000027726CABAD0>
False
Traceback (most recent call last):
  File "C:\Users\honguo\source\repos\Python\agent-framework\control-flow\multi-selection-edge-group\.venv\Lib\site-packages\agent_framework_openai\_chat_client.py", line 551, in _stream
    async with client.responses.stream(**run_options) as response:
               ~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^
  File "C:\Users\honguo\source\repos\Python\agent-framework\control-flow\multi-selection-edge-group\.venv\Lib\site-packages\openai\lib\streaming\responses\_responses.py", line 213, in __aenter__
    raw_stream = await self.__api_request
                 ^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\honguo\source\repos\Python\agent-framework\control-flow\multi-selection-edge-group\.venv\Lib\site-packages\openai\resources\responses\responses.py", line 2594, in create
    return await self._post(
           ^^^^^^^^^^^^^^^^^
    ...<43 lines>...
    )
    ^
  File "C:\Users\honguo\source\repos\Python\agent-framework\control-flow\multi-selection-edge-group\.venv\Lib\site-packages\openai\_base_client.py", line 1913, in post
    return await self.request(cast_to, opts, stream=stream, stream_cls=stream_cls)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\honguo\source\repos\Python\agent-framework\control-flow\multi-selection-edge-group\.venv\Lib\site-packages\openai\_base_client.py", line 1698, in request
    raise self._make_status_error_from_response(err.response) from None
openai.NotFoundError: Error code: 404 - {'error': {'type': 'invalid_request_error', 'code': 'DeploymentNotFound', 'message': 'The API deployment for this resource does not exist. If you created the deployment within the last 5 minutes, please wait a moment and try again.'}}

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "C:\Users\honguo\source\repos\Python\agent-framework\control-flow\multi-selection-edge-group\main.py", line 329, in <module>
    asyncio.run(main())
    ~~~~~~~~~~~^^^^^^^^
  File "C:\Program Files\Python314\Lib\asyncio\runners.py", line 204, in run
    return runner.run(main)
           ~~~~~~~~~~^^^^^^
  File "C:\Program Files\Python314\Lib\asyncio\runners.py", line 127, in run
    return self._loop.run_until_complete(task)
           ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^
  File "C:\Program Files\Python314\Lib\asyncio\base_events.py", line 719, in run_until_complete
    return future.result()
           ~~~~~~~~~~~~~^^
  File "C:\Users\honguo\source\repos\Python\agent-framework\control-flow\multi-selection-edge-group\main.py", line 319, in main
    async for event in workflow.run(email, stream=True):
    ...<6 lines>...
            print(f"Workflow output: {event.data}")
  File "C:\Users\honguo\source\repos\Python\agent-framework\control-flow\multi-selection-edge-group\.venv\Lib\site-packages\agent_framework\_types.py", line 3015, in __anext__
    update: UpdateT = await self._iterator.__anext__()
                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\honguo\source\repos\Python\agent-framework\control-flow\multi-selection-edge-group\.venv\Lib\site-packages\agent_framework\_workflows\_workflow.py", line 592, in _run_core
    async for event in self._run_workflow_with_tracing(
    ...<17 lines>...
        yield event
  File "C:\Users\honguo\source\repos\Python\agent-framework\control-flow\multi-selection-edge-group\.venv\Lib\site-packages\agent_framework\_workflows\_workflow.py", line 381, in _run_workflow_with_tracing
    async for event in self._runner.run_until_convergence():
    ...<9 lines>...
            yield pending_status
  File "C:\Users\honguo\source\repos\Python\agent-framework\control-flow\multi-selection-edge-group\.venv\Lib\site-packages\agent_framework\_workflows\_runner.py", line 124, in run_until_convergence
    await iteration_task
  File "C:\Users\honguo\source\repos\Python\agent-framework\control-flow\multi-selection-edge-group\.venv\Lib\site-packages\agent_framework\_workflows\_runner.py", line 210, in _run_iteration
    await asyncio.gather(*tasks)
  File "C:\Users\honguo\source\repos\Python\agent-framework\control-flow\multi-selection-edge-group\.venv\Lib\site-packages\agent_framework\_workflows\_runner.py", line 203, in _deliver_messages
    await asyncio.gather(*tasks)
  File "C:\Users\honguo\source\repos\Python\agent-framework\control-flow\multi-selection-edge-group\.venv\Lib\site-packages\agent_framework\_workflows\_runner.py", line 193, in _deliver_messages_for_edge_runner
    await _deliver_message_inner(edge_runner, message)
  File "C:\Users\honguo\source\repos\Python\agent-framework\control-flow\multi-selection-edge-group\.venv\Lib\site-packages\agent_framework\_workflows\_runner.py", line 187, in _deliver_message_inner
    return await edge_runner.send_message(message, self._state, self._ctx)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\honguo\source\repos\Python\agent-framework\control-flow\multi-selection-edge-group\.venv\Lib\site-packages\agent_framework\_workflows\_edge_runner.py", line 147, in send_message
    await self._execute_on_target(target_id, [source_id], message, state, ctx)
  File "C:\Users\honguo\source\repos\Python\agent-framework\control-flow\multi-selection-edge-group\.venv\Lib\site-packages\agent_framework\_workflows\_edge_runner.py", line 76, in _execute_on_target
    await target_executor.execute(
    ...<6 lines>...
    )
  File "C:\Users\honguo\source\repos\Python\agent-framework\control-flow\multi-selection-edge-group\.venv\Lib\site-packages\agent_framework\_workflows\_executor.py", line 279, in execute
    await handler(message, context)
  File "C:\Users\honguo\source\repos\Python\agent-framework\control-flow\multi-selection-edge-group\.venv\Lib\site-packages\agent_framework\_workflows\_executor.py", line 664, in wrapper
    return await func(self, message, ctx)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\honguo\source\repos\Python\agent-framework\control-flow\multi-selection-edge-group\.venv\Lib\site-packages\agent_framework\_workflows\_agent_executor.py", line 210, in run
    await self._run_agent_and_emit(ctx)
  File "C:\Users\honguo\source\repos\Python\agent-framework\control-flow\multi-selection-edge-group\.venv\Lib\site-packages\agent_framework\_workflows\_agent_executor.py", line 384, in _run_agent_and_emit
    response = await self._run_agent_streaming(cast(WorkflowContext[Never, AgentResponseUpdate], ctx))
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\honguo\source\repos\Python\agent-framework\control-flow\multi-selection-edge-group\.venv\Lib\site-packages\agent_framework\_workflows\_agent_executor.py", line 472, in _run_agent_streaming
    async for update in stream:
    ...<3 lines>...
            streamed_user_input_requests.extend(update.user_input_requests)
  File "C:\Users\honguo\source\repos\Python\agent-framework\control-flow\multi-selection-edge-group\.venv\Lib\site-packages\agent_framework\_types.py", line 3015, in __anext__
    update: UpdateT = await self._iterator.__anext__()
                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\honguo\source\repos\Python\agent-framework\control-flow\multi-selection-edge-group\.venv\Lib\site-packages\agent_framework\_types.py", line 3015, in __anext__
    update: UpdateT = await self._iterator.__anext__()
                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\honguo\source\repos\Python\agent-framework\control-flow\multi-selection-edge-group\.venv\Lib\site-packages\agent_framework\_types.py", line 3015, in __anext__
    update: UpdateT = await self._iterator.__anext__()
                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\honguo\source\repos\Python\agent-framework\control-flow\multi-selection-edge-group\.venv\Lib\site-packages\agent_framework\_tools.py", line 2410, in _stream
    async for update in inner_stream:
        yield update
  File "C:\Users\honguo\source\repos\Python\agent-framework\control-flow\multi-selection-edge-group\.venv\Lib\site-packages\agent_framework\_types.py", line 3015, in __anext__
    update: UpdateT = await self._iterator.__anext__()
                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\honguo\source\repos\Python\agent-framework\control-flow\multi-selection-edge-group\.venv\Lib\site-packages\agent_framework_openai\_chat_client.py", line 568, in _stream
    self._handle_request_error(ex)
    ~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^
  File "C:\Users\honguo\source\repos\Python\agent-framework\control-flow\multi-selection-edge-group\.venv\Lib\site-packages\agent_framework_openai\_chat_client.py", line 499, in _handle_request_error
    raise ChatClientException(
    ...<5 lines>...
    ) from ex
agent_framework.exceptions.ChatClientException: <class 'agent_framework_foundry._chat_client.FoundryChatClient'> service failed to complete the prompt: Error code: 404 - {'error': {'type': 'invalid_request_error', 'code': 'DeploymentNotFound', 'message': 'The API deployment for this resource does not exist. If you created the deployment within the last 5 minutes, please wait a moment and try again.'}}

Package Versions

agent-framework 1.1.0

Python Version

python 3.14

Additional Context

No response

[eavanvalkenburg]

This is the exact same setup I use every day, and also the paths to foundry look the same, so I don't know what else to do, could you confirm, that you can connect to the same model with other code (taking the snippet from the foundry portal for instance)?

[github-actions]

👋 Hi @hylinux — one thing worth checking before upgrading:

Your own debug output at the top of the stack trace shows:

{'api_key': None, 'base_url': None, 'org_id': None, 'model': 'my-gpt-54', 'embedding_model': None, 'chat_model': 'my-gpt-54', ...}

So the client is calling a deployment named my-gpt-54, not gpt-5.4. Since your code passes model=os.environ["FOUNDRY_MODEL"] explicitly, that means FOUNDRY_MODEL in your running process is actually set to my-gpt-54 — and a 404 DeploymentNotFound against my-gpt-54 is exactly what we'd expect if that deployment doesn't exist on your Foundry project.

Worth verifying:

• What your shell actually reports: echo $env:FOUNDRY_MODEL in PowerShell, or echo %FOUNDRY_MODEL% in cmd.
• Whether a .env file (or VS Code's Python env settings) is setting it to my-gpt-54 and overriding what you think you set.
• That the deployment name in your Foundry portal matches exactly — Azure deployment names are case-sensitive.

If FOUNDRY_MODEL really is gpt-5.4 after checking and you're still hitting the 404 after upgrading, please reopen with the output of echo $env:FOUNDRY_MODEL alongside a minimal snippet and we'll take another look. 🙏

[hylinux]

Hi, @eavanvalkenburg thanks for your help .

I re-produce this issue in my side once again:

1. my environment:

from the portal, I get the endpoint: https://hongweifoundry.services.ai.azure.com/api/projects/hongwei-test-project1

2. my model:

I got the model name: gpt-5.4

3. the sample code:

`
import asyncio

from agent_framework import Agent
from agent_framework.foundry import FoundryChatClient
from azure.identity import AzureCliCredential

async def main() -> None:
print("Hello from testcode1!")

chat_client = FoundryChatClient(
    project_endpoint="https://hongweifoundry.services.ai.azure.com/api/projects/hongwei-test-project1",
    model="gpt-5.4",
    credential=AzureCliCredential()
)

agent = Agent(
    client=chat_client,
    instructions="You are a help assisant",
    name="helpbot"
)

result = await agent.run("who are you?")
print("User: Who are you?")
print(f"Agent: {result}")

if name == "main":
asyncio.run(main())

`

4. the run result:
    ~\source\repos\Python\agent-framework\testcode1
   ❯ uv run .\main.py
   Hello from testcode1!
   Traceback (most recent call last):
   File "C:\Users\honguo\source\repos\Python\agent-framework\testcode1.venv\Lib\site-packages\agent_framework_openai_chat_client.py", line 584, in _get_response
   response = await client.responses.create(stream=False, **run_options)
   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
   File "C:\Users\honguo\source\repos\Python\agent-framework\testcode1.venv\Lib\site-packages\openai\resources\responses\responses.py", line 2594, in create
   return await self._post(
   ^^^^^^^^^^^^^^^^^
   ...<43 lines>...
   )
   ^
   File "C:\Users\honguo\source\repos\Python\agent-framework\testcode1.venv\Lib\site-packages\openai_base_client.py", line 1913, in post
   return await self.request(cast_to, opts, stream=stream, stream_cls=stream_cls)
   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
   File "C:\Users\honguo\source\repos\Python\agent-framework\testcode1.venv\Lib\site-packages\openai_base_client.py", line 1698, in request
   raise self._make_status_error_from_response(err.response) from None
   openai.NotFoundError: Error code: 404 - {'error': {'message': 'The API deployment for this resource does not exist. If you created the deployment within the last 5 minutes, please wait a moment and try again.', 'type': 'invalid_request_error', 'param': None, 'code': 'DeploymentNotFound'}}

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "C:\Users\honguo\source\repos\Python\agent-framework\testcode1\main.py", line 28, in
asyncio.run(main())
~~~~~~~~~~~^^^^^^^^
File "C:\Program Files\Python314\Lib\asyncio\runners.py", line 204, in run
return runner.run(main)
~~~~~~~~~~^^^^^^
File "C:\Program Files\Python314\Lib\asyncio\runners.py", line 127, in run
return self._loop.run_until_complete(task)
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^
File "C:\Program Files\Python314\Lib\asyncio\base_events.py", line 719, in run_until_complete
return future.result()
~~~~~~~~~~~~~^^
File "C:\Users\honguo\source\repos\Python\agent-framework\testcode1\main.py", line 23, in main
result = await agent.run("who are you?")
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\honguo\source\repos\Python\agent-framework\testcode1.venv\Lib\site-packages\agent_framework\observability.py", line 1641, in _run
response: AgentResponse[Any] = await execute()
^^^^^^^^^^^^^^^
File "C:\Users\honguo\source\repos\Python\agent-framework\testcode1.venv\Lib\site-packages\agent_framework_agents.py", line 954, in _run_non_streaming
response = await self._call_chat_client(ctx, stream=False)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\honguo\source\repos\Python\agent-framework\testcode1.venv\Lib\site-packages\agent_framework_tools.py", line 2335, in _get_response
await super_get_response(
^^^^^^^^^^^^^^^^^^^^^^^^^
...<6 lines>...
),
^
File "C:\Users\honguo\source\repos\Python\agent-framework\testcode1.venv\Lib\site-packages\agent_framework\observability.py", line 1381, in _get_response
await super_get_response(
^^^^^^^^^^^^^^^^^^^^^^^^^
...<7 lines>...
),
^
File "C:\Users\honguo\source\repos\Python\agent-framework\testcode1.venv\Lib\site-packages\agent_framework_openai_chat_client.py", line 586, in _get_response
self._handle_request_error(ex)
~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^
File "C:\Users\honguo\source\repos\Python\agent-framework\testcode1.venv\Lib\site-packages\agent_framework_openai_chat_client.py", line 494, in _handle_request_error
raise ChatClientException(
...<5 lines>...
) from ex
agent_framework.exceptions.ChatClientException: <class 'agent_framework_foundry._chat_client.FoundryChatClient'> service failed to complete the prompt: Error code: 404 - {'error': {'message': 'The API deployment for this resource does not exist. If you created the deployment within the last 5 minutes, please wait a moment and try again.', 'type': 'invalid_request_error', 'param': None, 'code': 'DeploymentNotFound'}}

I feel so confuse why this happen

my project file:

`
[project]
name = "testcode1"
version = "0.1.0"
description = "Add your description here"
readme = "README.md"
requires-python = ">=3.14"
dependencies = [
"agent-framework>=1.1.1",
]

[[tool.uv.index]]
url = "https://pypi.org/simple"
default = true

`

would you help me tale a look?

thanks

[moonbox3]

@hylinux you'll need to make sure your model is deployed to your project. Right now it's showing up as an Azure OpenAI deployment:

You'll know it's a project deployment when the target uri matches that of your project, not what you're currently seeing.