lanyuanxiaoyao/nex
1
0
Fork 0
Code Activity

feat: 补充 OpenAI 枚举参数和边界越界测试

Browse Source 
- service_tier: 补充 flex, priority 测试
- reasoning_effort: 补充 none, minimal 测试
- verbosity: 补充 medium, high 测试
- 边界越界测试: frequency_penalty, presence_penalty, top_p, n
- core.py: http_stream_request 支持 method 参数
- Anthropic: 补充 content_block_start 事件验证
This commit is contained in:
兰缘小妖
2026-04-21 14:15:27 +08:00
parent e1af978c56
commit da790db75b
3 changed files with 192 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
scripts/core.py
View File

@@ -140,7 +140,8 @@ def http_stream_request(
headers: Optional[Dict[str, str]] = None,
body: Optional[Any] = None,
ssl_ctx: Optional[ssl.SSLContext] = None,
retries: int = MAX_RETRIES
retries: int = MAX_RETRIES,
method: str = "POST"
) -> TestResult:
"""执行流式 HTTP 请求 (SSE，支持重试)
@@ -150,11 +151,12 @@ def http_stream_request(
body: 请求体 (dict)
ssl_ctx: SSL 上下文
retries: 重试次数
method: HTTP 方法 (默认 POST)
Returns:
TestResult 对象
"""
req = urllib.request.Request(url, method="POST")
req = urllib.request.Request(url, method=method)
if headers:
for k, v in headers.items():
req.add_header(k, v)

12
scripts/detect_anthropic.py
View File

@@ -262,6 +262,18 @@ def validate_anthropic_streaming_response(response_text: str) -> Tuple[bool, Lis
elif event_type == "message_stop":
has_message_stop = True
elif event_type == "content_block_start":
if "index" not in event:
errors.append(f"content_block_start 事件缺少 index 字段")
if "content_block" not in event:
errors.append(f"content_block_start 事件缺少 content_block 字段")
elif not isinstance(event["content_block"], dict):
errors.append(f"content_block_start 事件的 content_block 不是对象")
else:
cb = event["content_block"]
if "type" not in cb:
errors.append(f"content_block_start.content_block 缺少 type 字段")
elif event_type == "content_block_delta":
if "delta" not in event:
errors.append(f"content_block_delta 事件缺少 delta 字段")

178
scripts/detect_openai.py
View File

@@ -564,6 +564,102 @@ def main():
"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
}
))
# ---- --vision ----
if args.vision:
@@ -807,7 +903,7 @@ def main():
# reasoning_effort: 推理努力级别（需要模型支持）
cases.append(TestCase(
desc="reasoning_effort: medium",
desc="reasoning_effort: none",
method="POST",
url=chat_url,
headers=headers,
@@ -815,7 +911,20 @@ def main():
"model": model,
"messages": [{"role": "user", "content": "1+1=?"}],
"max_tokens": 10,
"reasoning_effort": "medium"
"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
))
@@ -832,6 +941,19 @@ def main():
},
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",
@@ -873,6 +995,32 @@ def main():
},
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(
@@ -888,6 +1036,32 @@ def main():
},
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 = []