Files
ai-ticket-platform/backend/apps/modelhub/tests/test_structured_output.py
2026-09-18 15:26:19 +08:00

156 lines
4.9 KiB
Python

import pytest
from apps.modelhub.structured_output import (
StructuredOutputError,
build_structured_request,
ensure_compatible,
schema_hash,
)
OUTPUT_SCHEMA = {
"type": "object",
"properties": {"answer": {"type": "string"}},
"required": ["answer"],
"additionalProperties": False,
}
@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_modes_build_stable_requests(
mode,
expected_response_type,
schema_in_system_message,
):
messages = [{"role": "user", "content": "业务输入"}]
request_messages, response_format, metadata = build_structured_request(
messages,
mode=mode,
output_schema=OUTPUT_SCHEMA,
schema_name="draft.result/v1",
)
assert messages == [{"role": "user", "content": "业务输入"}]
assert metadata == {
"mode": mode,
"schema_name": "draft_result_v1",
"schema_hash": schema_hash(OUTPUT_SCHEMA),
"response_format_included": expected_response_type is not None,
"schema_in_system_message": schema_in_system_message,
}
if expected_response_type is None:
assert response_format is None
else:
assert response_format["type"] == expected_response_type
if mode == "native_json_schema":
assert response_format["json_schema"] == {
"name": "draft_result_v1",
"strict": True,
"schema": OUTPUT_SCHEMA,
}
assert request_messages == messages
else:
assert request_messages[0]["role"] == "system"
assert "<output_schema>" in request_messages[0]["content"]
assert '"additionalProperties":false' in request_messages[0]["content"]
assert request_messages[1:] == messages
@pytest.mark.parametrize(
("mode", "enforcement", "compatible"),
[
("native_json_schema", "native_json_schema", True),
("native_json_schema", "json_object", True),
("native_json_schema", "validated_json", True),
("json_object", "native_json_schema", False),
("json_object", "json_object", True),
("json_object", "validated_json", True),
("prompt_schema", "native_json_schema", False),
("prompt_schema", "json_object", False),
("prompt_schema", "validated_json", True),
],
)
def test_all_model_and_skill_compatibility_combinations(mode, enforcement, compatible):
if compatible:
ensure_compatible(mode=mode, test_status="passed", enforcement=enforcement)
return
with pytest.raises(StructuredOutputError) as caught:
ensure_compatible(mode=mode, test_status="passed", enforcement=enforcement)
assert caught.value.code == "structured_output_incompatible"
@pytest.mark.parametrize(
("mode", "status", "expected_code"),
[
("unconfigured", "untested", "structured_output_not_configured"),
("native_json_schema", "untested", "structured_output_not_verified"),
("native_json_schema", "failed", "structured_output_not_verified"),
],
)
def test_unconfigured_or_unverified_models_are_rejected(mode, status, expected_code):
with pytest.raises(StructuredOutputError) as caught:
ensure_compatible(
mode=mode,
test_status=status,
enforcement="validated_json",
)
assert caught.value.code == expected_code
def test_native_mode_rejects_unsupported_schema_keyword_before_provider_call():
schema = {
"type": "object",
"properties": {
"missing_fields": {
"type": "array",
"items": {"type": "string"},
"uniqueItems": True,
}
},
"required": ["missing_fields"],
"additionalProperties": False,
}
with pytest.raises(StructuredOutputError) as caught:
build_structured_request(
[{"role": "user", "content": "业务输入"}],
mode="native_json_schema",
output_schema=schema,
schema_name="facts",
)
assert caught.value.code == "structured_output_schema_unsupported"
assert "$.properties.missing_fields.uniqueItems" in str(caught.value)
def test_prompt_modes_keep_full_business_schema():
schema = {
"type": "object",
"properties": {
"values": {
"type": "array",
"items": {"type": "string"},
"uniqueItems": True,
}
},
"required": ["values"],
"additionalProperties": False,
}
messages, response_format, _ = build_structured_request(
[{"role": "user", "content": "业务输入"}],
mode="prompt_schema",
output_schema=schema,
schema_name="values",
)
assert response_format is None
assert '"uniqueItems":true' in messages[0]["content"]