feat: init commint

backend/apps/modelhub/tests/test_services.py

@@ -1,6 +1,12 @@
 import httpx
 import pytest
-from openai import APITimeoutError, AuthenticationError, InternalServerError, RateLimitError
+from openai import (
+    APITimeoutError,
+    AuthenticationError,
+    BadRequestError,
+    InternalServerError,
+    RateLimitError,
+)
 
 from apps.modelhub.crypto import encrypt_secret
 from apps.modelhub.models import ModelDeployment, ModelInvocation, ModelProvider
@@ -67,6 +73,60 @@ def test_non_transient_error_fails_without_exposing_raw_error(db, monkeypatch):
     assert "secret provider detail" not in invocation.error_message
 
 
+@pytest.mark.parametrize(
+    ("mode", "expected_response_type", "schema_in_system_message"),
+    [
+        ("native_json_schema", "json_schema", False),
+        ("json_object", "json_object", True),
+        ("prompt_schema", None, True),
+    ],
+)
+def test_structured_invocation_records_request_and_audit_snapshot(
+    db,
+    monkeypatch,
+    mode,
+    expected_response_type,
+    schema_in_system_message,
+):
+    invocation = create_invocation()
+    invocation.deployment.structured_output_mode = mode
+    invocation.deployment.save(update_fields=["structured_output_mode"])
+    captured = {}
+    output_schema = {
+        "type": "object",
+        "properties": {"answer": {"type": "string"}},
+        "required": ["answer"],
+        "additionalProperties": False,
+    }
+
+    def request(*args, **kwargs):
+        captured.update(kwargs)
+        captured["messages"] = args[1]
+        return CompletionResult('{"answer":"ok"}', 10, 4)
+
+    monkeypatch.setattr("apps.modelhub.services._request_completion", request)
+
+    execute_invocation(
+        invocation,
+        invocation.input_snapshot["messages"],
+        output_schema=output_schema,
+        schema_name="answer-result",
+    )
+
+    invocation.refresh_from_db()
+    structured = invocation.model_snapshot["structured_output"]
+    assert structured["mode"] == mode
+    assert structured["schema_hash"]
+    assert structured["schema_name"] == "answer-result"
+    assert structured["schema_in_system_message"] is schema_in_system_message
+    assert invocation.input_snapshot["output_schema"] == output_schema
+    assert invocation.input_snapshot["structured_output"] == structured
+    if expected_response_type is None:
+        assert "response_format" not in captured or captured["response_format"] is None
+    else:
+        assert captured["response_format"]["type"] == expected_response_type
+
+
 def test_agent_time_budget_does_not_repeat_a_full_timeout(db, monkeypatch):
     invocation = create_invocation()
     calls = []
@@ -98,6 +158,47 @@ def provider_error(error_type, status_code):
     return error_type("provider raw error", response=response, body={})
 
 
+@pytest.mark.parametrize(
+    ("mode", "expected_code"),
+    [
+        ("native_json_schema", "structured_output_unsupported"),
+        ("json_object", "structured_output_unsupported"),
+        ("prompt_schema", "bad_request"),
+    ],
+)
+def test_response_format_rejection_does_not_downgrade_mode(
+    db,
+    monkeypatch,
+    mode,
+    expected_code,
+):
+    invocation = create_invocation()
+    invocation.deployment.structured_output_mode = mode
+    invocation.deployment.save(update_fields=["structured_output_mode"])
+    monkeypatch.setattr(
+        "apps.modelhub.services._request_completion",
+        lambda *args, **kwargs: (_ for _ in ()).throw(
+            provider_error(BadRequestError, 400)
+        ),
+    )
+
+    execute_invocation(
+        invocation,
+        invocation.input_snapshot["messages"],
+        output_schema={
+            "type": "object",
+            "properties": {"answer": {"type": "string"}},
+            "required": ["answer"],
+            "additionalProperties": False,
+        },
+    )
+
+    invocation.refresh_from_db()
+    assert invocation.status == "failed"
+    assert invocation.error_code == expected_code
+    assert invocation.retry_count == 0
+
+
 @pytest.mark.parametrize(
     ("error", "expected_code", "expected_calls"),
     [