perf: reduce memory usage by ~200MB+ at startup (#2013)

* perf: reduce memory usage by ~200MB+ at startup

Two key optimizations:

1. Use importlib.util.find_spec() instead of __import__() in dependency
   checking. find_spec() only locates modules without executing them,
   avoiding loading all 36 dependencies (~222MB) into memory at startup.

2. Introduce shared aiohttp.ClientSession via httpclient module.
   Previously, every HTTP request created a new ClientSession, which
   creates a new TCPConnector and SSL context, loading system root
   certificates each time (~270MB total allocations observed via memray).
   Now all HTTP client code reuses shared sessions.

   - satori.py and coze_server_api/client.py are left unchanged as they
     create one session per adapter lifecycle (not per-request).

Profiling data (memray):
- Peak memory: 403MB
- SSL context creation: 270MB / 6.7M allocations (67% of total)
- Dependency import: 222MB (55% of peak)
- Expected reduction: 150-350MB at startup

* fix: remove unused aiohttp imports (ruff F401)

* style: ruff format
This commit is contained in:
Junyan Chin
2026-02-27 20:09:03 +08:00
committed by GitHub
parent 2dc5999583
commit 88132dff8a
13 changed files with 370 additions and 321 deletions
@@ -1,5 +1,5 @@
import requests
import aiohttp
from langbot.pkg.utils import httpclient
def post_json(base_url, token, data=None):
@@ -63,16 +63,16 @@ async def async_request(
"""
headers = {'Content-Type': 'application/json'}
url = f'{base_url}?key={token_key}'
async with aiohttp.ClientSession() as session:
async with session.request(
method=method, url=url, params=params, headers=headers, data=data, json=json
) as response:
response.raise_for_status() # 如果状态码不是200,抛出异常
result = await response.json()
# print(result)
return result
# if result.get('Code') == 200:
#
# return await result
# else:
# raise RuntimeError("请求失败",response.text)
session = httpclient.get_session()
async with session.request(
method=method, url=url, params=params, headers=headers, data=data, json=json
) as response:
response.raise_for_status() # 如果状态码不是200,抛出异常
result = await response.json()
# print(result)
return result
# if result.get('Code') == 200:
#
# return await result
# else:
# raise RuntimeError("请求失败",response.text)