test(azure_ai): cover Foundry agents on the project Responses API

tests/unit/llms/azure_ai/responses/test_azure_ai_responses_transformation.py

@@ -1,5 +1,6 @@
 import json
 from typing import Final
+from unittest.mock import patch
 
 import httpx
 import pytest
@@ -7,6 +8,7 @@ import respx
 
 import litellm
 from litellm.llms.azure.responses.transformation import AzureOpenAIResponsesAPIConfig
+from litellm.llms.azure_ai.common_utils import AZURE_AI_AGENTS_SCOPE
 from litellm.llms.azure_ai.responses.transformation import AzureAIResponsesAPIConfig
 from litellm.responses.main import _will_bridge_to_chat_completions
 from litellm.types.llms.openai import ResponsesAPIOptionalRequestParams
@@ -103,7 +105,7 @@ def test_other_hosts_keep_chat_bridge(model, api_base):
     assert config is None
 
 
-@pytest.mark.parametrize("model", ["claude-3-5-sonnet", "model_router/gpt-5", "agents/my-agent"])
+@pytest.mark.parametrize("model", ["claude-3-5-sonnet", "model_router/gpt-5", "agents/asst_abc123"])
 def test_non_openai_surfaces_keep_chat_bridge(model):
     config = ProviderConfigManager.get_provider_responses_api_config(
         provider="azure_ai", model=model, api_base=FOUNDRY_PROJECT_BASE
@@ -383,3 +385,227 @@ def test_foundry_responses_none_unlocks_temperature_off_the_azure_ai_row(
 
     assert params["temperature"] == 0.2
     assert params["reasoning"] == {"effort": "none"}
+
+
+@pytest.mark.asyncio
+@respx.mock
+@pytest.mark.parametrize(
+    "model,expected_reference",
+    [
+        ("azure_ai/agents/support-agent", {"type": "agent_reference", "name": "support-agent"}),
+        ("azure_ai/agents/support-agent:3", {"type": "agent_reference", "name": "support-agent", "version": "3"}),
+    ],
+)
+async def test_aresponses_sends_agent_reference_instead_of_model(model, expected_reference):
+    route = respx.post(url__regex=r".*/openai/v1/responses(\?.*)?$").mock(
+        return_value=httpx.Response(200, json=_responses_payload("gpt-4.1"))
+    )
+
+    await litellm.aresponses(
+        model=model, input="What is 2+2?", max_output_tokens=50, api_base=FOUNDRY_PROJECT_BASE, api_key="fake-key"
+    )
+
+    request = route.calls.last.request
+    body = json.loads(request.content)
+    assert f"{request.url.scheme}://{request.url.host}{request.url.path}" == FOUNDRY_RESPONSES_URL
+    assert body["agent_reference"] == expected_reference
+    assert "model" not in body
+    assert body["input"] == "What is 2+2?"
+    assert body["max_output_tokens"] == 50
+
+
+@pytest.mark.asyncio
+@respx.mock
+async def test_router_aresponses_keeps_the_deployment_agent_over_extra_body():
+    route = respx.post(url__regex=r".*/openai/v1/responses(\?.*)?$").mock(
+        return_value=httpx.Response(200, json=_responses_payload("gpt-4.1"))
+    )
+    router = litellm.Router(
+        model_list=[
+            {
+                "model_name": "support-agent",
+                "litellm_params": {
+                    "model": "azure_ai/agents/support-agent",
+                    "api_base": FOUNDRY_PROJECT_BASE,
+                    "api_key": "fake-key",
+                },
+            }
+        ],
+        num_retries=0,
+    )
+
+    await router.aresponses(
+        model="support-agent",
+        input="What is 2+2?",
+        extra_body={"agent_reference": {"type": "agent_reference", "name": "billing-agent"}, "store": False},
+    )
+
+    body = json.loads(route.calls.last.request.content)
+    assert body["agent_reference"] == {"type": "agent_reference", "name": "support-agent"}
+    assert body["store"] is False
+    assert "model" not in body
+
+
+AGENT_OWNED_PARAMS = {
+    "instructions": "Answer in French",
+    "temperature": 0.2,
+    "top_p": 0.5,
+    "tools": [WEATHER_TOOL],
+    "text": {"format": {"type": "text"}},
+    "reasoning": {"effort": "high"},
+}
+
+
+@pytest.mark.asyncio
+@respx.mock
+async def test_aresponses_drops_agent_owned_params_under_drop_params():
+    route = respx.post(url__regex=r".*/openai/v1/responses(\?.*)?$").mock(
+        return_value=httpx.Response(200, json=_responses_payload("gpt-4.1"))
+    )
+
+    await litellm.aresponses(
+        model="azure_ai/agents/support-agent",
+        input="What is 2+2?",
+        tool_choice="auto",
+        drop_params=True,
+        api_base=FOUNDRY_PROJECT_BASE,
+        api_key="fake-key",
+        **AGENT_OWNED_PARAMS,
+    )
+
+    body = json.loads(route.calls.last.request.content)
+    assert body.keys().isdisjoint(AGENT_OWNED_PARAMS)
+    assert body["tool_choice"] == "auto"
+
+
+@pytest.mark.asyncio
+@respx.mock
+async def test_aresponses_reaches_the_agent_when_the_deployment_declares_reasoning_efforts():
+    route = respx.post(url__regex=r".*/openai/v1/responses(\?.*)?$").mock(
+        return_value=httpx.Response(200, json=_responses_payload("gpt-4.1"))
+    )
+
+    await litellm.aresponses(
+        model="azure_ai/agents/support-agent",
+        input="What is 2+2?",
+        max_output_tokens=50,
+        api_base=FOUNDRY_PROJECT_BASE,
+        api_key="fake-key",
+        model_info={"reasoning_effort_levels": ["low", "medium", "high"]},
+    )
+
+    body = json.loads(route.calls.last.request.content)
+    assert body["agent_reference"] == {"type": "agent_reference", "name": "support-agent"}
+    assert body["max_output_tokens"] == 50
+
+
+@pytest.mark.asyncio
+@respx.mock
+@pytest.mark.parametrize("param", sorted(AGENT_OWNED_PARAMS))
+async def test_aresponses_rejects_agent_owned_params_without_drop_params(param):
+    route = respx.post(url__regex=r".*/openai/v1/responses(\?.*)?$")
+
+    with pytest.raises(litellm.UnsupportedParamsError, match=param):
+        await litellm.aresponses(
+            model="azure_ai/agents/support-agent",
+            input="What is 2+2?",
+            api_base=FOUNDRY_PROJECT_BASE,
+            api_key="fake-key",
+            **{param: AGENT_OWNED_PARAMS[param]},
+        )
+
+    assert not route.called
+
+
+@pytest.mark.asyncio
+@respx.mock
+async def test_aresponses_streams_agent_answers_from_foundry():
+    completed = _responses_payload("gpt-4.1")
+    stream_body = "".join(
+        f"event: {event['type']}\ndata: {json.dumps(event)}\n\n"
+        for event in (
+            {"type": "response.created", "response": {**completed, "status": "in_progress"}},
+            {"type": "response.output_text.delta", "item_id": "msg_1", "output_index": 0, "content_index": 0, "delta": "4"},
+            {"type": "response.completed", "response": completed},
+        )
+    )
+    route = respx.post(url__regex=r".*/openai/v1/responses(\?.*)?$").mock(
+        return_value=httpx.Response(200, text=stream_body, headers={"content-type": "text/event-stream"})
+    )
+
+    stream = await litellm.aresponses(
+        model="azure_ai/agents/support-agent",
+        input="What is 2+2?",
+        stream=True,
+        api_base=FOUNDRY_PROJECT_BASE,
+        api_key="fake-key",
+    )
+    events = [event async for event in stream]
+
+    assert json.loads(route.calls.last.request.content)["stream"] is True
+    assert [event.type for event in events] == ["response.created", "response.output_text.delta", "response.completed"]
+    assert events[1].delta == "4"
+
+
+@pytest.mark.asyncio
+@respx.mock
+@pytest.mark.parametrize(
+    "configured_scope,expected_scope",
+    [(None, AZURE_AI_AGENTS_SCOPE), ("api://custom-app/.default", "api://custom-app/.default")],
+)
+async def test_aresponses_mints_the_service_principal_token_for_the_agents_scope(configured_scope, expected_scope):
+    route = respx.post(url__regex=r".*/openai/v1/responses(\?.*)?$").mock(
+        return_value=httpx.Response(200, json=_responses_payload("gpt-4.1"))
+    )
+
+    with patch("litellm.llms.azure.common_utils.get_azure_ad_token_from_entra_id") as mock_entra_id:  # test-quality-ok: stubs the Entra token fetch to assert the scope an agent entry requests and the bearer it sends; live service principal path proven by the PR's Foundry e2e QA
+        mock_entra_id.return_value = lambda: "agent-sp-token"
+        await litellm.aresponses(
+            model="azure_ai/agents/support-agent",
+            input="What is 2+2?",
+            api_base=FOUNDRY_PROJECT_BASE,
+            tenant_id="tenant",
+            client_id="client",
+            client_secret="secret",
+            azure_scope=configured_scope,
+        )
+
+    mock_entra_id.assert_called_once_with(
+        tenant_id="tenant", client_id="client", client_secret="secret", scope=expected_scope
+    )
+    assert route.calls.last.request.headers["Authorization"] == "Bearer agent-sp-token"
+
+
+def _agent_answer_payload(text: str) -> dict:
+    return {
+        **_responses_payload("gpt-4.1"),
+        "output": [
+            {
+                "type": "message",
+                "id": "msg_1",
+                "status": "completed",
+                "role": "assistant",
+                "content": [{"type": "output_text", "text": text, "annotations": []}],
+            }
+        ],
+    }
+
+
+@pytest.mark.asyncio
+@respx.mock
+async def test_acompletion_reaches_the_agent_through_the_project_responses_api():
+    route = respx.post(url__regex=r".*/openai/v1/responses(\?.*)?$").mock(
+        return_value=httpx.Response(200, json=_agent_answer_payload("4"))
+    )
+
+    response = await litellm.acompletion(
+        model="azure_ai/agents/support-agent",
+        messages=[{"role": "user", "content": "What is 2+2?"}],
+        api_base=FOUNDRY_PROJECT_BASE,
+        api_key="fake-key",
+    )
+
+    body = json.loads(route.calls.last.request.content)
+    assert body["agent_reference"] == {"type": "agent_reference", "name": "support-agent"}
+    assert "model" not in body
+    assert response.choices[0].message.content == "4"