mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-19 00:01:29 +00:00
An OpenAI batch where every request fails completes with status=completed but output_file_id=None. It matched neither the completed-with-output nor the failed/expired/cancelled branch, so batch_processed never flipped and the row was re-polled forever, saturating the oldest-N poll window and starving newer batches. Mark such batches complete + batch_processed=True (no cost to track). Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> |
||
|---|---|---|
| .. | ||
| cloudformation_stack | ||
| dist | ||
| enterprise_hooks | ||
| enterprise_ui | ||
| litellm_enterprise | ||
| __init__.py | ||
| LICENSE.md | ||
| pyproject.toml | ||
| README.md | ||
LiteLLM Enterprise
Code in this folder is licensed under a commercial license. Please review the LICENSE file within the /enterprise folder
These features are covered under the LiteLLM Enterprise contract
👉 Using in an Enterprise / Need specific features ? Meet with us here
See all Enterprise Features here 👉 Docs