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/main.py

@@ -42,6 +42,10 @@ from litellm import (  # type: ignore
 )
 from litellm.integrations.custom_logger import CustomLogger
 from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj
+from litellm.litellm_core_utils.mock_functions import (
+    mock_embedding,
+    mock_image_generation,
+)
 from litellm.llms.custom_httpx.http_handler import AsyncHTTPHandler, HTTPHandler
 from litellm.secret_managers.main import get_secret_str
 from litellm.utils import (
@@ -3163,6 +3167,7 @@ def embedding(
     tpm = kwargs.pop("tpm", None)
     litellm_logging_obj: LiteLLMLoggingObj = kwargs.get("litellm_logging_obj")  # type: ignore
     cooldown_time = kwargs.get("cooldown_time", None)
+    mock_response: Optional[List[float]] = kwargs.get("mock_response", None)  # type: ignore
     max_parallel_requests = kwargs.pop("max_parallel_requests", None)
     model_info = kwargs.get("model_info", None)
     metadata = kwargs.get("metadata", None)
@@ -3268,6 +3273,9 @@ def embedding(
         custom_llm_provider=custom_llm_provider,
         **non_default_params,
     )
+
+    if mock_response is not None:
+        return mock_embedding(model=model, mock_response=mock_response)
     ### REGISTER CUSTOM MODEL PRICING -- IF GIVEN ###
     if input_cost_per_token is not None and output_cost_per_token is not None:
         litellm.register_model(
@@ -4377,6 +4385,7 @@ def image_generation(
         aimg_generation = kwargs.get("aimg_generation", False)
         litellm_call_id = kwargs.get("litellm_call_id", None)
         logger_fn = kwargs.get("logger_fn", None)
+        mock_response: Optional[str] = kwargs.get("mock_response", None)  # type: ignore
         proxy_server_request = kwargs.get("proxy_server_request", None)
         model_info = kwargs.get("model_info", None)
         metadata = kwargs.get("metadata", {})
@@ -4486,6 +4495,8 @@ def image_generation(
             },
             custom_llm_provider=custom_llm_provider,
         )
+        if mock_response is not None:
+            return mock_image_generation(model=model, mock_response=mock_response)
 
         if custom_llm_provider == "azure":
             # azure configs