lanyuanxiaoyao
44d6af026a
- 提取共享定义（tool_weather, image_url, json_schema_math）到功能块前 - 流式用例精简为代表子集：核心 6-8 个 + 扩展各 1-2 个 + 高级参数代表 - OpenAI: 15 个流式用例（核心 8 + vision/tools/logprobs/json_schema + 高级参数） - Anthropic: 11 个流式用例（核心 6 + vision/tools/thinking + 高级参数） - 更新 README：新增流式测试覆盖原则、parse_sse_events 函数说明
1200 lines
39 KiB
Python
Executable File
1200 lines
39 KiB
Python
Executable File
#!/usr/bin/env python3
|
||
"""OpenAI 兼容性接口测试脚本
|
||
|
||
用法:
|
||
python3 scripts/openai_compat_test.py --base_url <url> [options]
|
||
|
||
示例:
|
||
python3 scripts/openai_compat_test.py --base_url https://api.example.com/v1
|
||
python3 scripts/openai_compat_test.py --base_url https://api.example.com/v1 --api_key sk-xxx --model gpt-4o
|
||
python3 scripts/openai_compat_test.py --base_url https://api.example.com/v1 --stream --tools
|
||
"""
|
||
|
||
import json
|
||
import argparse
|
||
from typing import Dict, List, Tuple, Any, Optional
|
||
from core import (
|
||
create_ssl_context,
|
||
TestCase,
|
||
run_test_suite,
|
||
validate_response_structure,
|
||
)
|
||
|
||
|
||
def build_headers(api_key: str) -> Dict[str, str]:
|
||
"""构建 OpenAI API 请求头"""
|
||
h = {"Content-Type": "application/json"}
|
||
if api_key:
|
||
h["Authorization"] = f"Bearer {api_key}"
|
||
return h
|
||
|
||
|
||
# ==================== OpenAI 响应验证函数 ====================
|
||
|
||
def validate_openai_models_list_response(response_text: str) -> Tuple[bool, List[str]]:
|
||
"""验证 OpenAI Models List 响应
|
||
|
||
根据API文档，响应应包含：
|
||
- object: "list"
|
||
- data: array of Model objects
|
||
"""
|
||
errors = []
|
||
|
||
try:
|
||
data = json.loads(response_text)
|
||
except json.JSONDecodeError as e:
|
||
return False, [f"响应不是有效的JSON: {e}"]
|
||
|
||
# 检查必需字段
|
||
if "object" not in data:
|
||
errors.append("缺少必需字段: object")
|
||
elif data["object"] != "list":
|
||
errors.append(f"字段 'object' 值错误: 期望 'list', 实际 '{data['object']}'")
|
||
|
||
if "data" not in data:
|
||
errors.append("缺少必需字段: data")
|
||
elif not isinstance(data["data"], list):
|
||
errors.append(f"字段 'data' 类型错误: 期望 list, 实际 {type(data['data']).__name__}")
|
||
else:
|
||
# 验证每个 model 对象
|
||
for i, model in enumerate(data["data"]):
|
||
if not isinstance(model, dict):
|
||
errors.append(f"data[{i}] 不是对象")
|
||
continue
|
||
|
||
# 检查 model 对象的必需字段
|
||
model_required = ["id", "object", "created", "owned_by"]
|
||
for field in model_required:
|
||
if field not in model:
|
||
errors.append(f"data[{i}] 缺少必需字段: {field}")
|
||
|
||
# 检查 object 字段值
|
||
if "object" in model and model["object"] != "model":
|
||
errors.append(f"data[{i}].object 值错误: 期望 'model', 实际 '{model['object']}'")
|
||
|
||
return len(errors) == 0, errors
|
||
|
||
|
||
def validate_openai_model_retrieve_response(response_text: str) -> Tuple[bool, List[str]]:
|
||
"""验证 OpenAI Model Retrieve 响应
|
||
|
||
根据API文档，响应应包含：
|
||
- id: string
|
||
- object: "model"
|
||
- created: number
|
||
- owned_by: string
|
||
"""
|
||
required_fields = ["id", "object", "created", "owned_by"]
|
||
field_types = {
|
||
"id": str,
|
||
"object": str,
|
||
"created": (int, float),
|
||
"owned_by": str
|
||
}
|
||
enum_values = {
|
||
"object": ["model"]
|
||
}
|
||
|
||
return validate_response_structure(response_text, required_fields, field_types, enum_values)
|
||
|
||
|
||
def validate_openai_chat_completion_response(response_text: str, expected_n: Optional[int] = None) -> Tuple[bool, List[str]]:
|
||
"""验证 OpenAI Chat Completion 响应
|
||
|
||
根据API文档，响应应包含：
|
||
- id: string
|
||
- object: "chat.completion"
|
||
- created: number
|
||
- model: string
|
||
- choices: array
|
||
- usage: object (可选)
|
||
|
||
Args:
|
||
response_text: 响应文本
|
||
expected_n: 期望的 choices 数量（对应请求中的 n 参数）
|
||
"""
|
||
errors = []
|
||
|
||
try:
|
||
data = json.loads(response_text)
|
||
except json.JSONDecodeError as e:
|
||
return False, [f"响应不是有效的JSON: {e}"]
|
||
|
||
# 检查必需字段
|
||
required_fields = ["id", "object", "created", "model", "choices"]
|
||
for field in required_fields:
|
||
if field not in data:
|
||
errors.append(f"缺少必需字段: {field}")
|
||
|
||
# 检查 object 字段值
|
||
if "object" in data and data["object"] != "chat.completion":
|
||
errors.append(f"字段 'object' 值错误: 期望 'chat.completion', 实际 '{data['object']}'")
|
||
|
||
# 检查 choices 数组
|
||
if "choices" in data:
|
||
if not isinstance(data["choices"], list):
|
||
errors.append(f"字段 'choices' 类型错误: 期望 list, 实际 {type(data['choices']).__name__}")
|
||
else:
|
||
# 校验 choices 数量与 n 参数匹配
|
||
if expected_n is not None and len(data["choices"]) != expected_n:
|
||
errors.append(f"choices 数量不匹配: 期望 {expected_n}, 实际 {len(data['choices'])}")
|
||
|
||
for i, choice in enumerate(data["choices"]):
|
||
if not isinstance(choice, dict):
|
||
errors.append(f"choices[{i}] 不是对象")
|
||
continue
|
||
|
||
# 检查 choice 对象的必需字段
|
||
choice_required = ["index", "message", "finish_reason"]
|
||
for field in choice_required:
|
||
if field not in choice:
|
||
errors.append(f"choices[{i}] 缺少必需字段: {field}")
|
||
|
||
# 检查 message 对象
|
||
if "message" in choice and isinstance(choice["message"], dict):
|
||
msg = choice["message"]
|
||
if "role" not in msg:
|
||
errors.append(f"choices[{i}].message 缺少必需字段: role")
|
||
elif msg["role"] != "assistant":
|
||
errors.append(f"choices[{i}].message.role 值错误: 期望 'assistant', 实际 '{msg['role']}'")
|
||
|
||
# 检查 usage 对象（可选）
|
||
if "usage" in data and data["usage"] is not None:
|
||
if not isinstance(data["usage"], dict):
|
||
errors.append(f"字段 'usage' 类型错误: 期望 object, 实际 {type(data['usage']).__name__}")
|
||
else:
|
||
usage_required = ["prompt_tokens", "completion_tokens", "total_tokens"]
|
||
for field in usage_required:
|
||
if field not in data["usage"]:
|
||
errors.append(f"usage 缺少必需字段: {field}")
|
||
|
||
return len(errors) == 0, errors
|
||
|
||
|
||
def validate_openai_streaming_response(response_text: str, expected_n: Optional[int] = None) -> Tuple[bool, List[str]]:
|
||
"""验证 OpenAI 流式响应
|
||
|
||
流式响应使用 SSE 格式，每行以 "data: " 开头，包含 chat.completion.chunk 对象。
|
||
最后一个事件是 "data: [DONE]"。
|
||
|
||
验证要点：
|
||
- 每个事件是有效的 JSON
|
||
- object 字段为 "chat.completion.chunk"
|
||
- choices 数组存在
|
||
- 如果指定了 expected_n，校验 choices 数量匹配
|
||
- 最后一个非[DONE]事件的 finish_reason 不为 null
|
||
|
||
Args:
|
||
response_text: SSE 格式的响应文本
|
||
expected_n: 期望的 choices 数量
|
||
|
||
Returns:
|
||
(是否验证通过, 错误信息列表)
|
||
"""
|
||
from core import parse_sse_events
|
||
|
||
errors = []
|
||
events = parse_sse_events(response_text)
|
||
|
||
if not events:
|
||
errors.append("未收到任何 SSE 事件")
|
||
return False, errors
|
||
|
||
chunk_count = 0
|
||
choice_counts = set()
|
||
|
||
for i, event_data in enumerate(events):
|
||
try:
|
||
event = json.loads(event_data)
|
||
except json.JSONDecodeError as e:
|
||
errors.append(f"事件[{i}] 不是有效的JSON: {e}")
|
||
continue
|
||
|
||
chunk_count += 1
|
||
|
||
# 检查 object 字段
|
||
if "object" not in event:
|
||
errors.append(f"事件[{i}] 缺少必需字段: object")
|
||
elif event["object"] != "chat.completion.chunk":
|
||
errors.append(f"事件[{i}].object 值错误: 期望 'chat.completion.chunk', 实际 '{event['object']}'")
|
||
|
||
# 检查 choices 数组
|
||
if "choices" not in event:
|
||
errors.append(f"事件[{i}] 缺少必需字段: choices")
|
||
elif not isinstance(event["choices"], list):
|
||
errors.append(f"事件[{i}].choices 类型错误: 期望 list")
|
||
else:
|
||
choice_counts.add(len(event["choices"]))
|
||
if expected_n is not None and len(event["choices"]) != expected_n:
|
||
errors.append(f"事件[{i}].choices 数量不匹配: 期望 {expected_n}, 实际 {len(event['choices'])}")
|
||
|
||
for j, choice in enumerate(event["choices"]):
|
||
if not isinstance(choice, dict):
|
||
errors.append(f"事件[{i}].choices[{j}] 不是对象")
|
||
continue
|
||
|
||
if "index" not in choice:
|
||
errors.append(f"事件[{i}].choices[{j}] 缺少必需字段: index")
|
||
|
||
# 过滤掉空 choices 的情况（如最后一个 usage chunk）
|
||
non_empty_choice_counts = {c for c in choice_counts if c > 0}
|
||
if expected_n is not None and expected_n not in non_empty_choice_counts:
|
||
errors.append(f"流式响应中 choices 数量不一致: 期望 {expected_n}, 实际出现 {non_empty_choice_counts}")
|
||
|
||
return len(errors) == 0, errors
|
||
|
||
|
||
def main():
|
||
parser = argparse.ArgumentParser(
|
||
description="OpenAI 兼容性接口测试",
|
||
formatter_class=argparse.RawDescriptionHelpFormatter,
|
||
)
|
||
parser.add_argument("--base_url", required=True, help="API 基础地址 (如 https://api.example.com/v1)")
|
||
parser.add_argument("--api_key", default="", help="API 密钥 (默认空)")
|
||
parser.add_argument("--model", default="gpt-4o", help="模型名称 (默认 gpt-4o)")
|
||
parser.add_argument("--vision", action="store_true", help="执行视觉相关测试")
|
||
parser.add_argument("--stream", action="store_true", help="执行流式响应测试")
|
||
parser.add_argument("--tools", action="store_true", help="执行工具调用测试")
|
||
parser.add_argument("--logprobs", action="store_true", help="执行 logprobs 测试")
|
||
parser.add_argument("--json_schema", action="store_true", help="执行 Structured Output 测试")
|
||
parser.add_argument("--all", action="store_true", help="开启所有扩展测试")
|
||
args = parser.parse_args()
|
||
|
||
if args.all:
|
||
args.vision = True
|
||
args.stream = True
|
||
args.tools = True
|
||
args.logprobs = True
|
||
args.json_schema = True
|
||
|
||
base_url = args.base_url.rstrip("/")
|
||
api_key = args.api_key
|
||
model = args.model
|
||
ssl_ctx = create_ssl_context()
|
||
headers = build_headers(api_key)
|
||
headers_bad_auth = build_headers("invalid-key-xxx")
|
||
|
||
chat_url = f"{base_url}/chat/completions"
|
||
|
||
# --- 收集测试用例 ---
|
||
cases: List[TestCase] = []
|
||
|
||
# ---- Models API ----
|
||
cases.append(TestCase(
|
||
desc="获取模型列表 (GET /models)",
|
||
method="GET",
|
||
url=f"{base_url}/models",
|
||
headers=headers,
|
||
validator=validate_openai_models_list_response
|
||
))
|
||
cases.append(TestCase(
|
||
desc="获取指定模型详情 (GET /models/{model})",
|
||
method="GET",
|
||
url=f"{base_url}/models/{model}",
|
||
headers=headers,
|
||
validator=validate_openai_model_retrieve_response
|
||
))
|
||
cases.append(TestCase(
|
||
desc="获取不存在的模型 (GET /models/nonexistent-model-xxx)",
|
||
method="GET",
|
||
url=f"{base_url}/models/nonexistent-model-xxx",
|
||
headers=headers
|
||
))
|
||
|
||
# ---- Chat Completions: 正面用例 ----
|
||
cases.append(TestCase(
|
||
desc="基本对话（仅 user）",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"model": model,
|
||
"messages": [{"role": "user", "content": "Hi"}],
|
||
"max_tokens": 5
|
||
},
|
||
validator=validate_openai_chat_completion_response
|
||
))
|
||
cases.append(TestCase(
|
||
desc="system + user 对话",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"model": model,
|
||
"messages": [
|
||
{"role": "system", "content": "You are a helpful assistant."},
|
||
{"role": "user", "content": "1+1="}
|
||
],
|
||
"max_tokens": 5
|
||
},
|
||
validator=validate_openai_chat_completion_response
|
||
))
|
||
cases.append(TestCase(
|
||
desc="developer + user 对话",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"model": model,
|
||
"messages": [
|
||
{"role": "developer", "content": "You are a helpful assistant."},
|
||
{"role": "user", "content": "1+1="}
|
||
],
|
||
"max_tokens": 5
|
||
},
|
||
validator=validate_openai_chat_completion_response
|
||
))
|
||
cases.append(TestCase(
|
||
desc="多轮对话（含 assistant 历史）",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"model": model,
|
||
"messages": [
|
||
{"role": "user", "content": "Hi"},
|
||
{"role": "assistant", "content": "Hello!"},
|
||
{"role": "user", "content": "1+1="}
|
||
],
|
||
"max_tokens": 5
|
||
},
|
||
validator=validate_openai_chat_completion_response
|
||
))
|
||
cases.append(TestCase(
|
||
desc="temperature + top_p",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"model": model,
|
||
"messages": [{"role": "user", "content": "Hi"}],
|
||
"max_tokens": 5,
|
||
"temperature": 0.5,
|
||
"top_p": 0.9
|
||
},
|
||
validator=validate_openai_chat_completion_response
|
||
))
|
||
cases.append(TestCase(
|
||
desc="max_tokens 限制",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"model": model,
|
||
"messages": [{"role": "user", "content": "讲一个故事"}],
|
||
"max_tokens": 10
|
||
},
|
||
validator=validate_openai_chat_completion_response
|
||
))
|
||
cases.append(TestCase(
|
||
desc="stop sequences",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"model": model,
|
||
"messages": [{"role": "user", "content": "数数: 1,2,3,"}],
|
||
"max_tokens": 20,
|
||
"stop": ["5"]
|
||
},
|
||
validator=validate_openai_chat_completion_response
|
||
))
|
||
cases.append(TestCase(
|
||
desc="n=2 多候选",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"model": model,
|
||
"messages": [{"role": "user", "content": "Hi"}],
|
||
"max_tokens": 5,
|
||
"n": 2
|
||
},
|
||
validator=lambda r: validate_openai_chat_completion_response(r, expected_n=2)
|
||
))
|
||
cases.append(TestCase(
|
||
desc="seed 参数",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"model": model,
|
||
"messages": [{"role": "user", "content": "Hi"}],
|
||
"max_tokens": 5,
|
||
"seed": 42
|
||
},
|
||
validator=validate_openai_chat_completion_response
|
||
))
|
||
cases.append(TestCase(
|
||
desc="frequency_penalty + presence_penalty",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"model": model,
|
||
"messages": [{"role": "user", "content": "Hi"}],
|
||
"max_tokens": 5,
|
||
"frequency_penalty": 0.5,
|
||
"presence_penalty": 0.5
|
||
},
|
||
validator=validate_openai_chat_completion_response
|
||
))
|
||
cases.append(TestCase(
|
||
desc="max_completion_tokens 参数",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"model": model,
|
||
"messages": [{"role": "user", "content": "讲一个故事"}],
|
||
"max_completion_tokens": 10
|
||
},
|
||
validator=validate_openai_chat_completion_response
|
||
))
|
||
cases.append(TestCase(
|
||
desc="JSON mode (response_format: json_object)",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"model": model,
|
||
"messages": [
|
||
{"role": "system", "content": "以 JSON 格式回复: {\"answer\": \"ok\"}"},
|
||
{"role": "user", "content": "test"}
|
||
],
|
||
"max_tokens": 10,
|
||
"response_format": {"type": "json_object"}
|
||
},
|
||
validator=validate_openai_chat_completion_response
|
||
))
|
||
|
||
# ---- Chat Completions: 负面用例 ----
|
||
cases.append(TestCase(
|
||
desc="缺少 model 参数",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"messages": [{"role": "user", "content": "Hi"}],
|
||
"max_tokens": 5
|
||
}
|
||
))
|
||
cases.append(TestCase(
|
||
desc="缺少 messages 参数",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"model": model,
|
||
"max_tokens": 5
|
||
}
|
||
))
|
||
cases.append(TestCase(
|
||
desc="messages 为空数组",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"model": model,
|
||
"messages": [],
|
||
"max_tokens": 5
|
||
}
|
||
))
|
||
cases.append(TestCase(
|
||
desc="无效 API key",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers_bad_auth,
|
||
body={
|
||
"model": model,
|
||
"messages": [{"role": "user", "content": "Hi"}],
|
||
"max_tokens": 5
|
||
}
|
||
))
|
||
cases.append(TestCase(
|
||
desc="不存在的模型 (chat)",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"model": "nonexistent-model-xxx",
|
||
"messages": [{"role": "user", "content": "Hi"}],
|
||
"max_tokens": 5
|
||
}
|
||
))
|
||
cases.append(TestCase(
|
||
desc="畸形 JSON body",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body="invalid json{"
|
||
))
|
||
|
||
cases.append(TestCase(
|
||
desc="max_tokens 为负数",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"model": model,
|
||
"messages": [{"role": "user", "content": "Hi"}],
|
||
"max_tokens": -1
|
||
}
|
||
))
|
||
cases.append(TestCase(
|
||
desc="max_tokens = 0",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"model": model,
|
||
"messages": [{"role": "user", "content": "Hi"}],
|
||
"max_tokens": 0
|
||
}
|
||
))
|
||
cases.append(TestCase(
|
||
desc="temperature 超出范围 (2.5)",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"model": model,
|
||
"messages": [{"role": "user", "content": "Hi"}],
|
||
"max_tokens": 5,
|
||
"temperature": 2.5
|
||
}
|
||
))
|
||
cases.append(TestCase(
|
||
desc="frequency_penalty 超出范围 (3.0)",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"model": model,
|
||
"messages": [{"role": "user", "content": "Hi"}],
|
||
"max_tokens": 5,
|
||
"frequency_penalty": 3.0
|
||
}
|
||
))
|
||
cases.append(TestCase(
|
||
desc="frequency_penalty 超出范围 (-3.0)",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"model": model,
|
||
"messages": [{"role": "user", "content": "Hi"}],
|
||
"max_tokens": 5,
|
||
"frequency_penalty": -3.0
|
||
}
|
||
))
|
||
cases.append(TestCase(
|
||
desc="presence_penalty 超出范围 (3.0)",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"model": model,
|
||
"messages": [{"role": "user", "content": "Hi"}],
|
||
"max_tokens": 5,
|
||
"presence_penalty": 3.0
|
||
}
|
||
))
|
||
cases.append(TestCase(
|
||
desc="presence_penalty 超出范围 (-3.0)",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"model": model,
|
||
"messages": [{"role": "user", "content": "Hi"}],
|
||
"max_tokens": 5,
|
||
"presence_penalty": -3.0
|
||
}
|
||
))
|
||
cases.append(TestCase(
|
||
desc="top_p 超出范围 (1.5)",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"model": model,
|
||
"messages": [{"role": "user", "content": "Hi"}],
|
||
"max_tokens": 5,
|
||
"top_p": 1.5
|
||
}
|
||
))
|
||
cases.append(TestCase(
|
||
desc="top_p 超出范围 (-0.1)",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"model": model,
|
||
"messages": [{"role": "user", "content": "Hi"}],
|
||
"max_tokens": 5,
|
||
"top_p": -0.1
|
||
}
|
||
))
|
||
cases.append(TestCase(
|
||
desc="n 为负数",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"model": model,
|
||
"messages": [{"role": "user", "content": "Hi"}],
|
||
"max_tokens": 5,
|
||
"n": -1
|
||
}
|
||
))
|
||
cases.append(TestCase(
|
||
desc="n 为 0",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"model": model,
|
||
"messages": [{"role": "user", "content": "Hi"}],
|
||
"max_tokens": 5,
|
||
"n": 0
|
||
}
|
||
))
|
||
|
||
# ---- 共享定义（供流式和非流式用例共同使用）----
|
||
image_url = (
|
||
"https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/"
|
||
"Gfp-wisconsin-madison-the-nature-boardwalk.jpg/"
|
||
"2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg"
|
||
)
|
||
tool_weather = {
|
||
"type": "function",
|
||
"function": {
|
||
"name": "get_weather",
|
||
"description": "获取指定城市的天气",
|
||
"parameters": {
|
||
"type": "object",
|
||
"properties": {
|
||
"location": {"type": "string", "description": "城市名称"}
|
||
},
|
||
"required": ["location"]
|
||
}
|
||
}
|
||
}
|
||
json_schema_math = {
|
||
"name": "math_answer",
|
||
"strict": True,
|
||
"schema": {
|
||
"type": "object",
|
||
"properties": {
|
||
"answer": {"type": "number"},
|
||
"explanation": {"type": "string"}
|
||
},
|
||
"required": ["answer", "explanation"],
|
||
"additionalProperties": False
|
||
}
|
||
}
|
||
|
||
# ---- --vision ----
|
||
if args.vision:
|
||
cases.append(TestCase(
|
||
desc="图片 URL 输入 + detail 参数 (--vision)",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"model": model,
|
||
"messages": [
|
||
{"role": "system", "content": "简短描述图片"},
|
||
{"role": "user", "content": [
|
||
{"type": "text", "text": "用一个词描述这张图"},
|
||
{"type": "image_url", "image_url": {
|
||
"url": image_url, "detail": "low"
|
||
}}
|
||
]}
|
||
],
|
||
"max_tokens": 10
|
||
},
|
||
validator=validate_openai_chat_completion_response
|
||
))
|
||
|
||
# ---- --stream ----
|
||
if args.stream:
|
||
# 核心用例
|
||
cases.append(TestCase(
|
||
desc="流式基本对话",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={"model": model, "messages": [{"role": "user", "content": "Hi"}], "max_tokens": 5, "stream": True},
|
||
stream=True,
|
||
validator=validate_openai_streaming_response
|
||
))
|
||
cases.append(TestCase(
|
||
desc="流式 + include_usage",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={"model": model, "messages": [{"role": "user", "content": "Hi"}], "max_tokens": 5, "stream": True, "stream_options": {"include_usage": True}},
|
||
stream=True,
|
||
validator=validate_openai_streaming_response
|
||
))
|
||
cases.append(TestCase(
|
||
desc="流式 + system prompt",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={"model": model, "messages": [{"role": "system", "content": "有帮助的助手"}, {"role": "user", "content": "Hi"}], "max_tokens": 5, "stream": True},
|
||
stream=True,
|
||
validator=validate_openai_streaming_response
|
||
))
|
||
cases.append(TestCase(
|
||
desc="流式多轮对话",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={"model": model, "messages": [{"role": "user", "content": "1+1?"}, {"role": "assistant", "content": "2"}, {"role": "user", "content": "2+2?"}], "max_tokens": 5, "stream": True},
|
||
stream=True,
|
||
validator=validate_openai_streaming_response
|
||
))
|
||
cases.append(TestCase(
|
||
desc="流式 temperature + top_p",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={"model": model, "messages": [{"role": "user", "content": "Hi"}], "temperature": 0.5, "top_p": 0.9, "max_tokens": 5, "stream": True},
|
||
stream=True,
|
||
validator=validate_openai_streaming_response
|
||
))
|
||
cases.append(TestCase(
|
||
desc="流式 max_tokens",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={"model": model, "messages": [{"role": "user", "content": "Hi"}], "max_tokens": 3, "stream": True},
|
||
stream=True,
|
||
validator=validate_openai_streaming_response
|
||
))
|
||
cases.append(TestCase(
|
||
desc="流式 stop_sequences",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={"model": model, "messages": [{"role": "user", "content": "数数: 1,2,3,"}], "max_tokens": 10, "stop": ["5"], "stream": True},
|
||
stream=True,
|
||
validator=validate_openai_streaming_response
|
||
))
|
||
cases.append(TestCase(
|
||
desc="流式 JSON mode",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={"model": model, "messages": [{"role": "system", "content": "以JSON回复"}, {"role": "user", "content": "颜色"}], "max_tokens": 20, "response_format": {"type": "json_object"}, "stream": True},
|
||
stream=True,
|
||
validator=validate_openai_streaming_response
|
||
))
|
||
|
||
# 流式 + vision
|
||
if args.vision:
|
||
cases.append(TestCase(
|
||
desc="流式图片输入",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={"model": model, "messages": [{"role": "user", "content": [{"type": "text", "text": "描述图"}, {"type": "image_url", "image_url": {"url": image_url}}]}], "max_tokens": 10, "stream": True},
|
||
stream=True,
|
||
validator=validate_openai_streaming_response
|
||
))
|
||
|
||
# 流式 + tools
|
||
if args.tools:
|
||
cases.append(TestCase(
|
||
desc="流式工具调用 auto",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={"model": model, "messages": [{"role": "user", "content": "北京天气？"}], "max_tokens": 50, "stream": True, "tools": [tool_weather], "tool_choice": "auto"},
|
||
stream=True,
|
||
validator=validate_openai_streaming_response
|
||
))
|
||
cases.append(TestCase(
|
||
desc="流式多轮工具调用",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={"model": model, "messages": [{"role": "user", "content": "北京天气？"}, {"role": "assistant", "content": None, "tool_calls": [{"id": "call_001", "type": "function", "function": {"name": "get_weather", "arguments": '{"location": "Beijing"}'}}]}, {"role": "tool", "tool_call_id": "call_001", "content": '{"temp": 22}'}], "max_tokens": 10, "stream": True, "tools": [tool_weather]},
|
||
stream=True,
|
||
validator=validate_openai_streaming_response
|
||
))
|
||
|
||
# 流式 + logprobs
|
||
if args.logprobs:
|
||
cases.append(TestCase(
|
||
desc="流式 logprobs",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={"model": model, "messages": [{"role": "user", "content": "Hi"}], "max_tokens": 5, "logprobs": True, "top_logprobs": 2, "stream": True},
|
||
stream=True,
|
||
validator=validate_openai_streaming_response
|
||
))
|
||
|
||
# 流式 + json_schema
|
||
if args.json_schema:
|
||
cases.append(TestCase(
|
||
desc="流式 json_schema",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={"model": model, "messages": [{"role": "user", "content": "1+1=?"}], "max_tokens": 20, "response_format": {"type": "json_schema", "json_schema": json_schema_math}, "stream": True},
|
||
stream=True,
|
||
validator=validate_openai_streaming_response
|
||
))
|
||
|
||
# 流式高级参数（选代表）
|
||
cases.append(TestCase(
|
||
desc="流式 reasoning_effort: medium",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={"model": model, "messages": [{"role": "user", "content": "Hi"}], "max_tokens": 5, "reasoning_effort": "medium", "stream": True},
|
||
stream=True,
|
||
validator=validate_openai_streaming_response
|
||
))
|
||
cases.append(TestCase(
|
||
desc="流式 service_tier: auto",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={"model": model, "messages": [{"role": "user", "content": "Hi"}], "max_tokens": 5, "service_tier": "auto", "stream": True},
|
||
stream=True,
|
||
validator=validate_openai_streaming_response
|
||
))
|
||
|
||
# ---- --tools ----
|
||
if args.tools:
|
||
cases.append(TestCase(
|
||
desc="工具调用 tool_choice: auto (--tools)",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"model": model,
|
||
"messages": [{"role": "user", "content": "北京天气怎么样？"}],
|
||
"max_tokens": 50,
|
||
"tools": [tool_weather],
|
||
"tool_choice": "auto"
|
||
},
|
||
validator=validate_openai_chat_completion_response
|
||
))
|
||
cases.append(TestCase(
|
||
desc="工具调用 tool_choice: required (--tools)",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"model": model,
|
||
"messages": [{"role": "user", "content": "北京天气怎么样？"}],
|
||
"max_tokens": 50,
|
||
"tools": [tool_weather],
|
||
"tool_choice": "required"
|
||
},
|
||
validator=validate_openai_chat_completion_response
|
||
))
|
||
cases.append(TestCase(
|
||
desc="指定函数调用 tool_choice: {name} (--tools)",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"model": model,
|
||
"messages": [{"role": "user", "content": "北京天气怎么样？"}],
|
||
"max_tokens": 50,
|
||
"tools": [tool_weather],
|
||
"tool_choice": {
|
||
"type": "function",
|
||
"function": {"name": "get_weather"}
|
||
}
|
||
},
|
||
validator=validate_openai_chat_completion_response
|
||
))
|
||
cases.append(TestCase(
|
||
desc="多轮工具调用（构造 tool 结果）(--tools)",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"model": model,
|
||
"messages": [
|
||
{"role": "user", "content": "北京天气怎么样？"},
|
||
{"role": "assistant", "content": None, "tool_calls": [{
|
||
"id": "call_001", "type": "function",
|
||
"function": {
|
||
"name": "get_weather",
|
||
"arguments": "{\"location\": \"Beijing\"}"
|
||
}
|
||
}]},
|
||
{"role": "tool", "tool_call_id": "call_001",
|
||
"content": "{\"temperature\": 22, \"condition\": \"晴\"}"}
|
||
],
|
||
"max_tokens": 20,
|
||
"tools": [tool_weather]
|
||
},
|
||
validator=validate_openai_chat_completion_response
|
||
))
|
||
cases.append(TestCase(
|
||
desc="parallel_tool_calls: false (--tools)",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"model": model,
|
||
"messages": [{"role": "user", "content": "北京和上海的天气怎么样？"}],
|
||
"max_tokens": 50,
|
||
"tools": [tool_weather],
|
||
"tool_choice": "auto",
|
||
"parallel_tool_calls": False
|
||
},
|
||
validator=validate_openai_chat_completion_response
|
||
))
|
||
|
||
# ---- --logprobs ----
|
||
if args.logprobs:
|
||
cases.append(TestCase(
|
||
desc="logprobs + top_logprobs (--logprobs)",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"model": model,
|
||
"messages": [{"role": "user", "content": "Hi"}],
|
||
"max_tokens": 5,
|
||
"logprobs": True,
|
||
"top_logprobs": 2
|
||
},
|
||
validator=validate_openai_chat_completion_response
|
||
))
|
||
|
||
# ---- --json-schema ----
|
||
if args.json_schema:
|
||
cases.append(TestCase(
|
||
desc="Structured Output json_schema (--json_schema)",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"model": model,
|
||
"messages": [{"role": "user", "content": "1+1等于几？"}],
|
||
"max_tokens": 20,
|
||
"response_format": {
|
||
"type": "json_schema",
|
||
"json_schema": json_schema_math
|
||
}
|
||
},
|
||
validator=validate_openai_chat_completion_response
|
||
))
|
||
|
||
# ---- 高级参数测试 ----
|
||
# logit_bias: 修改特定token的似然
|
||
cases.append(TestCase(
|
||
desc="logit_bias 参数测试",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"model": model,
|
||
"messages": [{"role": "user", "content": "Hello"}],
|
||
"max_tokens": 5,
|
||
"logit_bias": {"1234": -100, "5678": 50}
|
||
},
|
||
validator=validate_openai_chat_completion_response
|
||
))
|
||
|
||
# reasoning_effort: 推理努力级别（需要模型支持）
|
||
cases.append(TestCase(
|
||
desc="reasoning_effort: none",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"model": model,
|
||
"messages": [{"role": "user", "content": "1+1=?"}],
|
||
"max_tokens": 10,
|
||
"reasoning_effort": "none"
|
||
},
|
||
validator=validate_openai_chat_completion_response
|
||
))
|
||
cases.append(TestCase(
|
||
desc="reasoning_effort: minimal",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"model": model,
|
||
"messages": [{"role": "user", "content": "1+1=?"}],
|
||
"max_tokens": 10,
|
||
"reasoning_effort": "minimal"
|
||
},
|
||
validator=validate_openai_chat_completion_response
|
||
))
|
||
cases.append(TestCase(
|
||
desc="reasoning_effort: low",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"model": model,
|
||
"messages": [{"role": "user", "content": "1+1=?"}],
|
||
"max_tokens": 10,
|
||
"reasoning_effort": "low"
|
||
},
|
||
validator=validate_openai_chat_completion_response
|
||
))
|
||
cases.append(TestCase(
|
||
desc="reasoning_effort: medium",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"model": model,
|
||
"messages": [{"role": "user", "content": "1+1=?"}],
|
||
"max_tokens": 10,
|
||
"reasoning_effort": "medium"
|
||
},
|
||
validator=validate_openai_chat_completion_response
|
||
))
|
||
cases.append(TestCase(
|
||
desc="reasoning_effort: high",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"model": model,
|
||
"messages": [{"role": "user", "content": "1+1=?"}],
|
||
"max_tokens": 10,
|
||
"reasoning_effort": "high"
|
||
},
|
||
validator=validate_openai_chat_completion_response
|
||
))
|
||
|
||
# service_tier: 服务层级
|
||
cases.append(TestCase(
|
||
desc="service_tier: auto",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"model": model,
|
||
"messages": [{"role": "user", "content": "Hi"}],
|
||
"max_tokens": 5,
|
||
"service_tier": "auto"
|
||
},
|
||
validator=validate_openai_chat_completion_response
|
||
))
|
||
cases.append(TestCase(
|
||
desc="service_tier: default",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"model": model,
|
||
"messages": [{"role": "user", "content": "Hi"}],
|
||
"max_tokens": 5,
|
||
"service_tier": "default"
|
||
},
|
||
validator=validate_openai_chat_completion_response
|
||
))
|
||
cases.append(TestCase(
|
||
desc="service_tier: flex",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"model": model,
|
||
"messages": [{"role": "user", "content": "Hi"}],
|
||
"max_tokens": 5,
|
||
"service_tier": "flex"
|
||
},
|
||
validator=validate_openai_chat_completion_response
|
||
))
|
||
cases.append(TestCase(
|
||
desc="service_tier: priority",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"model": model,
|
||
"messages": [{"role": "user", "content": "Hi"}],
|
||
"max_tokens": 5,
|
||
"service_tier": "priority"
|
||
},
|
||
validator=validate_openai_chat_completion_response
|
||
))
|
||
|
||
# verbosity: 冗长程度
|
||
cases.append(TestCase(
|
||
desc="verbosity: low",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"model": model,
|
||
"messages": [{"role": "user", "content": "介绍一下Python"}],
|
||
"max_tokens": 50,
|
||
"verbosity": "low"
|
||
},
|
||
validator=validate_openai_chat_completion_response
|
||
))
|
||
cases.append(TestCase(
|
||
desc="verbosity: medium",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"model": model,
|
||
"messages": [{"role": "user", "content": "介绍一下Python"}],
|
||
"max_tokens": 50,
|
||
"verbosity": "medium"
|
||
},
|
||
validator=validate_openai_chat_completion_response
|
||
))
|
||
cases.append(TestCase(
|
||
desc="verbosity: high",
|
||
method="POST",
|
||
url=chat_url,
|
||
headers=headers,
|
||
body={
|
||
"model": model,
|
||
"messages": [{"role": "user", "content": "介绍一下Python"}],
|
||
"max_tokens": 50,
|
||
"verbosity": "high"
|
||
},
|
||
validator=validate_openai_chat_completion_response
|
||
))
|
||
|
||
# ---- 执行测试 ----
|
||
flags = []
|
||
if args.vision:
|
||
flags.append("vision")
|
||
if args.stream:
|
||
flags.append("stream")
|
||
if args.tools:
|
||
flags.append("tools")
|
||
if args.logprobs:
|
||
flags.append("logprobs")
|
||
if args.json_schema:
|
||
flags.append("json-schema")
|
||
|
||
run_test_suite(
|
||
cases=cases,
|
||
ssl_ctx=ssl_ctx,
|
||
title="OpenAI 兼容性测试",
|
||
base_url=base_url,
|
||
model=model,
|
||
flags=flags
|
||
)
|
||
|
||
|
||
if __name__ == "__main__":
|
||
main()
|