test(router_code_coverage.py): check if all router functions are dire… (#6186)

* test(router_code_coverage.py): check if all router functions are directly tested

prevent regressions

* docs(configs.md): document all environment variables (#6185)

* docs: make it easier to find anthropic/openai prompt caching doc

* aded codecov yml (#6207)

* fix codecov.yaml

* run ci/cd again

* (refactor) caching use LLMCachingHandler for async_get_cache and set_cache  (#6208)

* use folder for caching

* fix importing caching

* fix clickhouse pyright

* fix linting

* fix correctly pass kwargs and args

* fix test case for embedding

* fix linting

* fix embedding caching logic

* fix refactor handle utils.py

* fix test_embedding_caching_azure_individual_items_reordered

* (feat) prometheus have well defined latency buckets (#6211)

* fix prometheus have well defined latency buckets

* use a well define latency bucket

* use types file for prometheus logging

* add test for LATENCY_BUCKETS

* fix prom testing

* fix config.yml

* (refactor caching) use LLMCachingHandler for caching streaming responses  (#6210)

* use folder for caching

* fix importing caching

* fix clickhouse pyright

* fix linting

* fix correctly pass kwargs and args

* fix test case for embedding

* fix linting

* fix embedding caching logic

* fix refactor handle utils.py

* refactor async set stream cache

* fix linting

* bump (#6187)

* update code cov yaml

* fix config.yml

* add caching component to code cov

* fix config.yml ci/cd

* add coverage for proxy auth

* (refactor caching) use common `_retrieve_from_cache` helper  (#6212)

* use folder for caching

* fix importing caching

* fix clickhouse pyright

* fix linting

* fix correctly pass kwargs and args

* fix test case for embedding

* fix linting

* fix embedding caching logic

* fix refactor handle utils.py

* refactor async set stream cache

* fix linting

* refactor - use _retrieve_from_cache

* refactor use _convert_cached_result_to_model_response

* fix linting errors

* bump: version 1.49.2 → 1.49.3

* fix code cov components

* test(test_router_helpers.py): add router component unit tests

* test: add additional router tests

* test: add more router testing

* test: add more router testing + more mock functions

* ci(router_code_coverage.py): fix check

---------

Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>
Co-authored-by: yujonglee <yujonglee.dev@gmail.com>

litellm/router.py

@@ -111,6 +111,7 @@ from litellm.types.router import (
     RouterModelGroupAliasItem,
     RouterRateLimitError,
     RouterRateLimitErrorBasic,
+    RoutingStrategy,
     updateDeployment,
     updateLiteLLMParams,
 )
@@ -519,6 +520,9 @@ class Router:
             self._initialize_alerting()
 
     def validate_fallbacks(self, fallback_param: Optional[List]):
+        """
+        Validate the fallbacks parameter.
+        """
         if fallback_param is None:
             return
 
@@ -530,8 +534,13 @@ class Router:
                     f"Dictionary '{fallback_dict}' must have exactly one key, but has {len(fallback_dict)} keys."
                 )
 
-    def routing_strategy_init(self, routing_strategy: str, routing_strategy_args: dict):
-        if routing_strategy == "least-busy":
+    def routing_strategy_init(
+        self, routing_strategy: Union[RoutingStrategy, str], routing_strategy_args: dict
+    ):
+        if (
+            routing_strategy == RoutingStrategy.LEAST_BUSY.value
+            or routing_strategy == RoutingStrategy.LEAST_BUSY
+        ):
             self.leastbusy_logger = LeastBusyLoggingHandler(
                 router_cache=self.cache, model_list=self.model_list
             )
@@ -542,7 +551,10 @@ class Router:
                 litellm.input_callback = [self.leastbusy_logger]  # type: ignore
             if isinstance(litellm.callbacks, list):
                 litellm.callbacks.append(self.leastbusy_logger)  # type: ignore
-        elif routing_strategy == "usage-based-routing":
+        elif (
+            routing_strategy == RoutingStrategy.USAGE_BASED_ROUTING.value
+            or routing_strategy == RoutingStrategy.USAGE_BASED_ROUTING
+        ):
             self.lowesttpm_logger = LowestTPMLoggingHandler(
                 router_cache=self.cache,
                 model_list=self.model_list,
@@ -550,7 +562,10 @@ class Router:
             )
             if isinstance(litellm.callbacks, list):
                 litellm.callbacks.append(self.lowesttpm_logger)  # type: ignore
-        elif routing_strategy == "usage-based-routing-v2":
+        elif (
+            routing_strategy == RoutingStrategy.USAGE_BASED_ROUTING_V2.value
+            or routing_strategy == RoutingStrategy.USAGE_BASED_ROUTING_V2
+        ):
             self.lowesttpm_logger_v2 = LowestTPMLoggingHandler_v2(
                 router_cache=self.cache,
                 model_list=self.model_list,
@@ -558,7 +573,10 @@ class Router:
             )
             if isinstance(litellm.callbacks, list):
                 litellm.callbacks.append(self.lowesttpm_logger_v2)  # type: ignore
-        elif routing_strategy == "latency-based-routing":
+        elif (
+            routing_strategy == RoutingStrategy.LATENCY_BASED.value
+            or routing_strategy == RoutingStrategy.LATENCY_BASED
+        ):
             self.lowestlatency_logger = LowestLatencyLoggingHandler(
                 router_cache=self.cache,
                 model_list=self.model_list,
@@ -566,7 +584,10 @@ class Router:
             )
             if isinstance(litellm.callbacks, list):
                 litellm.callbacks.append(self.lowestlatency_logger)  # type: ignore
-        elif routing_strategy == "cost-based-routing":
+        elif (
+            routing_strategy == RoutingStrategy.COST_BASED.value
+            or routing_strategy == RoutingStrategy.COST_BASED
+        ):
             self.lowestcost_logger = LowestCostLoggingHandler(
                 router_cache=self.cache,
                 model_list=self.model_list,
@@ -574,10 +595,14 @@ class Router:
             )
             if isinstance(litellm.callbacks, list):
                 litellm.callbacks.append(self.lowestcost_logger)  # type: ignore
+        else:
+            pass
 
     def print_deployment(self, deployment: dict):
         """
         returns a copy of the deployment with the api key masked
+
+        Only returns 2 characters of the api key and masks the rest with * (10 *).
         """
         try:
             _deployment_copy = copy.deepcopy(deployment)
@@ -1746,7 +1771,6 @@ class Router:
         try:
             kwargs["model"] = model
             kwargs["prompt"] = prompt
-            kwargs["original_function"] = self.text_completion
             kwargs["num_retries"] = kwargs.get("num_retries", self.num_retries)
             kwargs.get("request_timeout", self.timeout)
             kwargs.setdefault("metadata", {}).update({"model_group": model})
@@ -1770,13 +1794,7 @@ class Router:
             # call via litellm.completion()
             return litellm.text_completion(**{**data, "prompt": prompt, "caching": self.cache_responses, **kwargs})  # type: ignore
         except Exception as e:
-            if self.num_retries > 0:
-                kwargs["model"] = model
-                kwargs["messages"] = messages
-                kwargs["original_function"] = self.text_completion
-                return self.function_with_retries(**kwargs)
-            else:
-                raise e
+            raise e
 
     async def atext_completion(
         self,
@@ -3005,7 +3023,7 @@ class Router:
 
     async def make_call(self, original_function: Any, *args, **kwargs):
         """
-        Handler for making a call to the .completion()/.embeddings() functions.
+        Handler for making a call to the .completion()/.embeddings()/etc. functions.
         """
         model_group = kwargs.get("model")
         response = await original_function(*args, **kwargs)