fix(tests+docs): fix tuple unpacking and docs test failures

- Update test mocks that return (healthy, unhealthy) to return
  (healthy, unhealthy, {}) to match the new 3-value signature
- Update test unpackings of perform_shared_health_check to use
  healthy, unhealthy, _ = ...
- Add health_check_ignore_transient_errors to router_settings section
  in config_settings.md (it is a Router constructor param, so the doc
  test requires it there; it also lives in general_settings for proxy use)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

docs/my-website/docs/proxy/config_settings.md

@@ -397,6 +397,7 @@ router_settings:
 | guardrail_list | List[GuardrailTypedDict] | List of guardrail configurations for guardrail load balancing. Enables load balancing across multiple guardrail deployments with the same guardrail_name. [Further Docs](./guardrails/guardrail_load_balancing.md) |
 | enable_health_check_routing | boolean | If true, enables health check-driven deployment filtering to avoid routing requests to unhealthy deployments |
 | health_check_staleness_threshold | integer | Maximum age in seconds for cached health check results before marking deployments as stale |
+| health_check_ignore_transient_errors | boolean | If true, 429 (rate limit) and 408 (timeout) health check failures are ignored and do not affect routing or cooldown |
 
 
 ### environment variables - Reference

tests/proxy_unit_tests/test_proxy_server.py

@@ -2410,7 +2410,7 @@ async def test_run_background_health_check_reflects_llm_model_list(monkeypatch):
         model_list, details, max_concurrency=None
     ):
         called_model_lists.append(copy.deepcopy(model_list))
-        return (["healthy"], ["unhealthy"])
+        return (["healthy"], ["unhealthy"], {})
 
     monkeypatch.setattr(proxy_server, "health_check_interval", 1)
     monkeypatch.setattr(proxy_server, "health_check_details", None)
@@ -2460,7 +2460,7 @@ async def test_background_health_check_skip_disabled_models(monkeypatch):
         model_list, details, max_concurrency=None
     ):
         called_model_lists.append(copy.deepcopy(model_list))
-        return (["healthy"], [])
+        return (["healthy"], [], {})
 
     monkeypatch.setattr(proxy_server, "health_check_interval", 1)
     monkeypatch.setattr(proxy_server, "health_check_details", None)

tests/test_litellm/proxy/test_health_check_functions.py

@@ -481,7 +481,7 @@ async def test_perform_health_check_and_save_passes_model_id_to_perform_health_c
     unhealthy = []
 
     async def mock_perform_health_check(model_list, model=None, cli_model=None, details=True, model_id=None, max_concurrency=None):
-        return healthy, unhealthy
+        return healthy, unhealthy, {}
 
     with patch(
         "litellm.proxy.health_endpoints._health_endpoints.perform_health_check",

tests/test_litellm/proxy/test_shared_health_check.py

@@ -246,7 +246,7 @@ class TestSharedHealthCheckManager:
         model_list = [{"model_name": "test-model", "litellm_params": {"model": "test-model"}}]
         
         with patch("litellm.proxy.health_check_utils.shared_health_check_manager.perform_health_check") as mock_perform:
-            healthy, unhealthy = await shared_health_manager.perform_shared_health_check(
+            healthy, unhealthy, _ = await shared_health_manager.perform_shared_health_check(
                 model_list, details=True
             )
         
@@ -268,9 +268,9 @@ class TestSharedHealthCheckManager:
         expected_unhealthy = []
         
         with patch("litellm.proxy.health_check_utils.shared_health_check_manager.perform_health_check") as mock_perform:
-            mock_perform.return_value = (expected_healthy, expected_unhealthy)
+            mock_perform.return_value = (expected_healthy, expected_unhealthy, {})
             
-            healthy, unhealthy = await shared_health_manager.perform_shared_health_check(
+            healthy, unhealthy, _ = await shared_health_manager.perform_shared_health_check(
                 model_list, details=True
             )
         
@@ -302,7 +302,7 @@ class TestSharedHealthCheckManager:
         model_list = [{"model_name": "test-model", "litellm_params": {"model": "test-model"}}]
         
         with patch("asyncio.sleep") as mock_sleep:  # Mock sleep to avoid actual delay
-            healthy, unhealthy = await shared_health_manager.perform_shared_health_check(
+            healthy, unhealthy, _ = await shared_health_manager.perform_shared_health_check(
                 model_list, details=True
             )
         
@@ -324,9 +324,9 @@ class TestSharedHealthCheckManager:
         
         with patch("asyncio.sleep") as mock_sleep, \
              patch("litellm.proxy.health_check_utils.shared_health_check_manager.perform_health_check") as mock_perform:
-            mock_perform.return_value = (expected_healthy, expected_unhealthy)
+            mock_perform.return_value = (expected_healthy, expected_unhealthy, {})
             
-            healthy, unhealthy = await shared_health_manager.perform_shared_health_check(
+            healthy, unhealthy, _ = await shared_health_manager.perform_shared_health_check(
                 model_list, details=True
             )