mirror of
https://github.com/BerriAI/litellm.git
synced 2026-11-05 07:37:50 +00:00
The tag writer read the in-memory auth object, which the spend collector, batch and background cost polling, and the failure hook all drop, so their tag rows never got a team. The proxy now stamps user_api_key_is_virtual_key in request metadata from the unforgeable via_virtual_key marker (client-sent user_api_key_* fields are already stripped), the failure hook and batch attribution set it too, and the writer reads it with user_api_key_team_id The schema compatibility check flags a removed or changed @@unique again, since an older proxy's ON CONFLICT names it, and ignores trailing // comments on field lines |
||
|---|---|---|
| .. | ||
| 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