mirror of
https://github.com/BerriAI/litellm.git
synced 2026-11-04 07:27:51 +00:00
ead221995e
Code outside the router now reaches it only through the entry points (registry, settings, health, select, apply, observe, register_plugin, retire) or the endpoint methods; the outside-member allowlist shrinks from 139 to 45. litellm/router.py no longer imports litellm.proxy: it asks the installed RouterHost (litellm/router_host.py) for vertex pass-through credentials, member auto-router authorization and auto-router prompt compression, and the proxy installs its host on import. Call sites where a model name can be missing keep the old answer instead of reaching an entry point with None. |
||
|---|---|---|
| .. | ||
| fixtures | ||
| __init__.py | ||
| test_adaptive_router.py | ||
| test_async_pre_routing.py | ||
| test_bandit.py | ||
| test_classifier.py | ||
| test_config.py | ||
| test_e2e_adaptive_router.py | ||
| test_hooks.py | ||
| test_router_dispatch.py | ||
| test_signals.py | ||
| test_state_endpoint.py | ||
| test_update_queue.py | ||