mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-13 23:11:40 +00:00
CheckBatchCost put only user_api_key_user_id=job.created_by on the synthetic logging object it builds for a completed batch. Batches created by a virtual key without a user_id land in LiteLLM_ManagedObjectTable with created_by=NULL, so _should_track_cost_callback saw no key, user, team or end user and _PROXY_track_cost_callback dropped the row without logging anything, while the poller still flipped batch_processed to true; the batch was billed nowhere and never retried. Fall back to LITELLM_PROXY_ADMIN_NAME the same way the aretrieve_batch call already does, and forward the job's team_id so team budgets see batch spend. 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