mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-26 03:04:13 +00:00
* refactor(router.py): move assistants api endpoints to using 1 pass-through factory function Reduces code, increases testing coverage * refactor(router.py): reduce _common_check_available_deployment function size make code more maintainable - reduce possible errors * test(router_code_coverage.py): include batch_utils + pattern matching in enforced 100% code coverage Improves reliability * fix(router.py): fix model id match model dump |
||
---|---|---|
.. | ||
router_callbacks | ||
batch_utils.py | ||
client_initalization_utils.py | ||
cooldown_cache.py | ||
cooldown_callbacks.py | ||
cooldown_handlers.py | ||
fallback_event_handlers.py | ||
handle_error.py | ||
pattern_match_deployments.py |