New standalone page covering the full health check routing feature:
allowed_fails_policy integration, health_check_ignore_transient_errors,
architecture SVG, step-by-step setup, and gotchas (TTL, AllowedFails semantics).
Replaces the inline section in health.md with a link to the new page.
Added to the Routing & Load Balancing sidebar.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The previous fix only skipped cooldown counter increments. The health state
cache was still marking 429/408 endpoints as is_healthy=False, causing the
binary health check filter to exclude them from routing.
Now, when health_check_ignore_transient_errors=True, 429/408 endpoints are
also excluded from the unhealthy list passed to build_deployment_health_states(),
so the binary filter treats them as unaffected (not unhealthy).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
When enabled, health check failures with 429 (rate limit) or 408 (timeout)
status codes are skipped from the cooldown pipeline. These are transient
load issues, not broken deployments. Auth errors (401), 404, and 5xx errors
still increment counters and trigger cooldown as before.
Config (general_settings):
health_check_ignore_transient_errors: true
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Health check failures now increment the same per-deployment failure
counters used by allowed_fails_policy, so users can control how many
health check failures of each error type are required before a
deployment enters cooldown.
- ahealth_check() preserves the original exception in its return dict
- run_with_timeout() returns a litellm.Timeout on health check timeout
- _perform_health_check() propagates exceptions to unhealthy endpoints
- _write_health_state_to_router_cache() calls _set_cooldown_deployments
for each unhealthy endpoint that has an exception
- When allowed_fails_policy is set, the binary health check filter is
bypassed so cooldown is the sole routing exclusion mechanism
- Safety net: if all deployments are in cooldown with
enable_health_check_routing=True, the cooldown filter is bypassed
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The isort hook picked up a stale rename from the working directory.
Both router.py and proxy_server.py need litellm._uuid, not _litellm_uuid.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- model_id is now added after _clean_endpoint_data() so it survives
health_check_details: False (MINIMAL_DISPLAY_PARAMS filtering)
- Health state write failures logged at warning instead of debug
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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>
The isort hook picked up a stale rename from the working directory.
Both router.py and proxy_server.py need litellm._uuid, not _litellm_uuid.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- model_id is now added after _clean_endpoint_data() so it survives
health_check_details: False (MINIMAL_DISPLAY_PARAMS filtering)
- Health state write failures logged at warning instead of debug
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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>
Reset _ENABLE_TEAM_STALE_ALIAS_BYPASS to None in both test functions
to ensure test isolation and prevent ordering-dependent failures
Made-with: Cursor
- Reorder team_public_model_name assignment to happen before model_name mutation for clarity
- Add comment explaining no-rename fast-exit case in _update_existing_team_model_assignment
- Add comment explaining final patch_data.model_name = None applies to all code paths
Made-with: Cursor
- Cache LITELLM_ENABLE_TEAM_STALE_ALIAS_BYPASS at module level to avoid hot-path secret lookups
- Add clarifying comments for should_include_deployment team isolation logic
- Add negative assertion for update_team.assert_not_called() in test
- Add docstring clarification for _get_team_deployments helper pattern
- Add explicit assertion message in test_get_model_list_alias_optimization
Made-with: Cursor
- Add deduplication guard in _update_team_model_index to prevent duplicate indices
- Add wildcard comment in map_team_model for clarity
- Add monkeypatch to test_team_alias_stale_bypass_disabled_by_default for determinism
- Extract _get_team_deployments helper to centralize DB access pattern
- Add clarifying comments for team_public_model_name assignment ordering
Made-with: Cursor
- Check alias target pattern to detect stale team aliases
- Fix PrismaClient type annotation to Optional
- Eliminate in-place mutation in index update logic
Made-with: Cursor
- Use O(1) team index lookup instead of map_team_model in alias guard
- Fix MockPrismaClient to validate where clause filters
- Add comment explaining DB query trade-off for team deployments
Made-with: Cursor
- Skip model_aliases rewrite if model resolves to team deployments
- Add test coverage for sibling-preservation branch
- Update MockPrismaClient to support sibling deployment scenarios
Made-with: Cursor
- Add clarifying comments to test assertions
- Query prisma DB instead of in-memory router to avoid stale state
- Prevents incorrect deletion of old public name when siblings exist
Made-with: Cursor
Guard should_include_deployment fallback to only return deployments
matching the requested team_id, preventing public-name collisions
from leaking deployments across teams
Made-with: Cursor
- Add None guard for original_model_name in _add_team_model_to_db
- Remove stale old public name when renaming team model
- Add comment clarifying team deployment early-return priority
Made-with: Cursor
Remove temporary fire-emoji router logs used for local verification while keeping team sibling deployment routing behavior unchanged.
Made-with: Cursor
Remove team model_alias rewrites and resolve team deployments by team_public_model_name with team_id so sibling deployments stay in the routing candidate pool, with explicit logs showing candidate selection before load balancing.
Made-with: Cursor
Order-based routing and fallback work without enable_pre_call_checks
in the current code. Remove the stale requirement from both doc files.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
When fallbacks use non-standard formats (e.g. ["claude-3-haiku"] or
[{"model": "...", "messages": [...]}]), detect them with
_check_non_standard_fallback_format and pass them through directly
instead of trying to parse with get_fallback_model_group which only
handles the standard dict-keyed format.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
When a request to an order=1 deployment fails, the router now
automatically tries order=2, order=3, etc. before falling through to
external fallbacks. Works for all error types (429, 404, connection
errors). Requires enable_pre_call_checks=True.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
When order=1 deployments fail, the router now automatically tries order=2,
then order=3, etc. before falling through to external fallbacks. This removes
the need for enable_pre_call_checks and makes order work as a true priority-based
fallback chain within a model group.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- GCPIAMCredentialProvider now inherits from redis.credentials.CredentialProvider
so redis-py's async path calls get_credentials_async() properly
- move _redis_credential_provider import to top of _redis.py (PEP 8)
- remove dead else-branch that silently no-oped (gcp_service_account from
redis_kwargs.get() was always None since it's popped by _get_redis_client_logic)
- remove mid-function 'from litellm import get_secret_str' inline import
- remove unused 'call' import from test_redis.py
Extract GCPIAMCredentialProvider and _generate_gcp_iam_access_token
into litellm/_redis_credential_provider.py. _redis.py imports them
from there, keeping the public API unchanged.
Async RedisCluster was generating the IAM token once at startup and
storing it as a static password. After the 1-hour GCP token TTL, any
new connection (including to newly-discovered cluster nodes) would fail
to authenticate.
Fix: introduce GCPIAMCredentialProvider that implements redis-py's
CredentialProvider protocol. It calls _generate_gcp_iam_access_token()
on every new connection, matching what the sync redis_connect_func
already does. async_redis.RedisCluster accepts a credential_provider
kwarg which is invoked per-connection.
