Skip to content

bump default request timeout 30s -> 60s #9

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
goharanwar wants to merge 1 commit into from
Closed

bump default request timeout 30s -> 60s #9

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -102,7 +102,7 @@ python run_tests.py --profile core -p 4
|----------|-------------|----------|
| `VECTARA_API_KEY` | Personal API key | Yes |
| `VECTARA_BASE_URL` | API URL (default: `https://api.vectara.io`) | No |
| `VECTARA_TIMEOUT` | Request timeout in seconds (default: 30) | No |
| `VECTARA_TIMEOUT` | Request timeout in seconds (default: 60) | No |
| `VECTARA_LLM_NAME` | LLM model name for generation | No |
| `VECTARA_GENERATION_PRESET` | Generation preset name | No |
| `OPENAI_API_KEY` | OpenAI key for BYOL LLM tests (regression only) | No |
Expand Down
9 changes: 7 additions & 2 deletions utils/config.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,8 +27,13 @@ def base_url(self) -> str:

@property
def request_timeout(self) -> int:
"""Get request timeout in seconds."""
return int(os.environ.get("VECTARA_TIMEOUT", "30"))
"""Get request timeout in seconds.

Default 60s — agent execution involves LLM generation which routinely
runs > 30s in staging; matches the explicit budget asserted by
test_execute_agent_response_time.
"""
return int(os.environ.get("VECTARA_TIMEOUT", "60"))

@property
def max_retries(self) -> int:
Expand Down
Loading