litellm/litellm/router_utils
Sameer Kankute 7675488640
feat(router): add health-check-driven routing behind opt-in flag
Background health checks now feed deployment health state into the
router candidate-filtering pipeline. Unhealthy deployments are excluded
proactively instead of waiting for request failures to trigger cooldown.

Gated by `enable_health_check_routing: true` in general_settings.
Off by default — zero behavior change for existing users.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-27 20:57:08 +05:30
..
pre_call_checks Apply Black formatting to 11 files 2026-03-21 15:05:53 -07:00
router_callbacks
add_retry_fallback_headers.py
batch_utils.py style: run black formatter on entire codebase 2026-03-11 17:07:57 -03:00
client_initalization_utils.py
clientside_credential_handler.py
common_utils.py style: run black formatter on entire codebase 2026-03-11 17:07:57 -03:00
cooldown_cache.py style: run black formatter on entire codebase 2026-03-11 17:07:57 -03:00
cooldown_callbacks.py style: run black formatter on entire codebase 2026-03-11 17:07:57 -03:00
cooldown_handlers.py fix(router): add minimum request threshold for error rate cooldown (#17464) 2025-12-12 04:36:10 -08:00
fallback_event_handlers.py Revert "fix: prevent error when max_fallbacks exceeds available models (#20071)" 2026-02-03 15:15:30 +05:30
get_retry_from_policy.py inspect BadRequestError after all other policy types (#19878) 2026-01-27 18:15:04 -08:00
handle_error.py fix(handle_error.py): add unit tests 2025-08-11 18:25:30 -07:00
health_state_cache.py feat(router): add health-check-driven routing behind opt-in flag 2026-03-27 20:57:08 +05:30
pattern_match_deployments.py refactor: Add lazy loading for get_llm_provider (#18591) 2026-01-02 13:18:57 -08:00
prompt_caching_cache.py style: run black formatter on entire codebase 2026-03-11 17:07:57 -03:00
response_headers.py
search_api_router.py style: run black formatter on entire codebase 2026-03-11 17:07:57 -03:00