codeflash-admin/codeflash
1
0
Fork 0
mirror of https://github.com/codeflash-ai/codeflash.git synced 2026-05-04 18:25:17 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix: increase API read timeout from 90s to 300s to prevent flaky E2E failures

Browse source 
The flat 90s timeout was too aggressive for LLM-powered endpoints
(/testgen, /optimize, /refinement) under load, causing ReadTimeoutError
and failing the async-optimization E2E test. Split into (10s connect,
300s read) tuple so connections fail fast but LLM inference gets adequate time.
This commit is contained in:
Kevin Turcios 2026-04-10 02:33:16 -05:00
parent 72a41a5665
commit 4ac573f10f
1 changed files with 4 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
codeflash/api/aiservice.py
View file

@ -47,7 +47,9 @@ class AiServiceClient:
self.headers = {"Authorization": f"Bearer {get_codeflash_api_key()}", "Connection": "close"}
self.llm_call_counter = count(1)
self.is_local = self.base_url == "http://localhost:8000"
self.timeout: float | None = 300 if self.is_local else 90
# (connect_timeout, read_timeout) — connect should be fast; read
# can be slow because the server runs LLM inference.
self.timeout: float | tuple[float, float] | None = (10, 300)
def get_next_sequence(self) -> int:
"""Get the next LLM call sequence number."""
@ -88,7 +90,7 @@ class AiServiceClient:
endpoint: str,
method: str = "POST",
payload: dict[str, Any] | list[dict[str, Any]] | None = None,
timeout: float | None = None,
timeout: float | tuple[float, float] | None = None,
) -> requests.Response:
"""Make an API request to the given endpoint on the AI service.