chore: migrate Python formatter from black to ruff format (BerriAI#31317)

Author: mateo-berri

.github/workflows/test-linting.yml

@@ -50,10 +50,10 @@ jobs:
         run: |
           uv sync --frozen
 
-      - name: Check Black formatting
+      - name: Check ruff format
         run: |
           cd litellm
-          uv run --no-sync black --check --exclude '/enterprise/' .
+          uv run --no-sync ruff format --check --line-length 88 --exclude '/enterprise/' .
           cd ..
 
       - name: Debug - Check file state

Makefile

@@ -20,13 +20,13 @@ help:
 	@echo "  make install-test-deps  - Install the full local test environment"
 	@echo "  make install-helm-unittest - Install helm unittest plugin"
 	@echo "  make install-hooks      - Install git hooks (Conventional Commits + Branches)"
-	@echo "  make format             - Apply Black code formatting"
-	@echo "  make format-check       - Check Black code formatting (matches CI)"
-	@echo "  make lint               - Run all linting (Ruff, basedpyright, Black check, circular imports, import safety)"
+	@echo "  make format             - Apply ruff format code formatting"
+	@echo "  make format-check       - Check ruff format code formatting (matches CI)"
+	@echo "  make lint               - Run all linting (Ruff, basedpyright, format check, circular imports, import safety)"
 	@echo "  make lint-ruff          - Run Ruff linting only"
 	@echo "  make lint-basedpyright  - Run basedpyright strict, gated by per-rule error counts"
 	@echo "  make lint-basedpyright-budget-update - Re-capture the basedpyright per-rule budget (ratchet)"
-	@echo "  make lint-black         - Check Black formatting (matches CI)"
+	@echo "  make lint-format        - Check ruff format formatting (matches CI)"
 	@echo "  make lint-ruff-budget - Gate the codebase total of each strict ruff rule against its ceiling"
 	@echo "  make lint-gate        - Strict ruff gate in CI-parity mode (fetches staging, simulates the merge)"
 	@echo "  make lint-ruff-budget-update - Re-capture per-rule baselines in ruff-strict-budget.json (ratchet)"
@@ -82,11 +82,13 @@ install-hooks:
 	./scripts/install_git_hooks.sh
 
 # Formatting
+# 88-column wrap matches the Black width the whole repo is formatted to; ruff.toml's
+# global line-length is 120 (for E501/isort), so 88 is forced here.
 format: install-dev
-	cd litellm && $(UV_RUN) black . && cd ..
+	cd litellm && $(UV_RUN) ruff format --line-length 88 --exclude '/enterprise/' . && cd ..
 
 format-check: install-dev
-	cd litellm && $(UV_RUN) black --check . && cd ..
+	cd litellm && $(UV_RUN) ruff format --check --line-length 88 --exclude '/enterprise/' . && cd ..
 
 # Linting targets
 lint-ruff: install-dev
@@ -131,7 +133,7 @@ lint-basedpyright: install-dev
 lint-basedpyright-budget-update: install-dev
 	($(UV_RUN) basedpyright --outputjson || true) | $(UV_RUN) python scripts/type_check_gate.py --update
 
-lint-black: format-check
+lint-format: format-check
 
 lint-ruff-budget: install-dev
 	$(UV_RUN) python scripts/ruff_strict_gate.py

litellm/__init__.py

@@ -390,12 +390,8 @@ def _dev_env_hot_reload_enabled() -> bool:
 enable_caching_on_provider_specific_optional_params: bool = (
     False  # feature-flag for caching on optional params - e.g. 'top_k'
 )
-caching: bool = (
-    False  # Not used anymore, will be removed in next MAJOR release - https://github.com/BerriAI/litellm/discussions/648
-)
-caching_with_models: bool = (
-    False  # # Not used anymore, will be removed in next MAJOR release - https://github.com/BerriAI/litellm/discussions/648
-)
+caching: bool = False  # Not used anymore, will be removed in next MAJOR release - https://github.com/BerriAI/litellm/discussions/648
+caching_with_models: bool = False  # # Not used anymore, will be removed in next MAJOR release - https://github.com/BerriAI/litellm/discussions/648
 cache: Optional["Cache"] = (
     None  # cache object <- use this - https://docs.litellm.ai/docs/caching
 )
@@ -416,9 +412,7 @@ def _dev_env_hot_reload_enabled() -> bool:
 
 _current_cost = 0.0  # private variable, used if max budget is set
 error_logs: Dict = {}
-add_function_to_prompt: bool = (
-    False  # if function calling not supported by api, append function call details to system prompt
-)
+add_function_to_prompt: bool = False  # if function calling not supported by api, append function call details to system prompt
 client_session: Optional[httpx.Client] = None
 aclient_session: Optional[httpx.AsyncClient] = None
 model_fallbacks: Optional[List] = None  # Deprecated for 'litellm.fallbacks'
@@ -485,9 +479,7 @@ def _dev_env_hot_reload_enabled() -> bool:
 disable_add_prefix_to_prompt: bool = (
     False  # used by anthropic, to disable adding prefix to prompt
 )
-disable_copilot_system_to_assistant: bool = (
-    False  # If false (default), converts all 'system' role messages to 'assistant' for GitHub Copilot compatibility. Set to true to disable this behavior.
-)
+disable_copilot_system_to_assistant: bool = False  # If false (default), converts all 'system' role messages to 'assistant' for GitHub Copilot compatibility. Set to true to disable this behavior.
 public_mcp_servers: Optional[List[str]] = None
 public_mcp_hub_strict_whitelist: bool = True
 public_model_groups: Optional[List[str]] = None
@@ -507,17 +499,13 @@ def _dev_env_hot_reload_enabled() -> bool:
 
 
 ######## Networking Settings ########
-use_aiohttp_transport: bool = (
-    True  # Older variable, aiohttp is now the default. use disable_aiohttp_transport instead.
-)
+use_aiohttp_transport: bool = True  # Older variable, aiohttp is now the default. use disable_aiohttp_transport instead.
 aiohttp_trust_env: bool = False  # set to true to use HTTP_ Proxy settings
 disable_aiohttp_transport: bool = False  # Set this to true to use httpx instead
 disable_aiohttp_trust_env: bool = (
     False  # When False, aiohttp will respect HTTP(S)_PROXY env vars
 )
-force_ipv4: bool = (
-    False  # when True, litellm will force ipv4 for all LLM requests. Some users have seen httpx ConnectionError when using ipv6.
-)
+force_ipv4: bool = False  # when True, litellm will force ipv4 for all LLM requests. Some users have seen httpx ConnectionError when using ipv6.
 network_mock: bool = False  # When True, use mock transport — no real network calls
 
 ####### STOP SEQUENCE LIMIT #######
@@ -551,12 +539,12 @@ def _dev_env_hot_reload_enabled() -> bool:
 from litellm.litellm_core_utils.get_model_cost_map import get_model_cost_map
 
 model_cost = get_model_cost_map(url=model_cost_map_url)
-cost_discount_config: Dict[str, float] = (
-    {}
-)  # Provider-specific cost discounts {"vertex_ai": 0.05} = 5% discount
-cost_margin_config: Dict[str, Union[float, Dict[str, float]]] = (
-    {}
-)  # Provider-specific or global cost margins. Examples:
+cost_discount_config: Dict[
+    str, float
+] = {}  # Provider-specific cost discounts {"vertex_ai": 0.05} = 5% discount
+cost_margin_config: Dict[
+    str, Union[float, Dict[str, float]]
+] = {}  # Provider-specific or global cost margins. Examples:
 # Percentage: {"openai": 0.10} = 10% margin
 # Fixed: {"openai": {"fixed_amount": 0.001}} = $0.001 per request
 # Global: {"global": 0.05} = 5% global margin on all providers
@@ -1457,9 +1445,9 @@ def add_known_models(model_cost_map: Optional[Dict] = None):
 from .types.llms.custom_llm import CustomLLMItem
 
 custom_provider_map: List[CustomLLMItem] = []
-_custom_providers: List[str] = (
-    []
-)  # internal helper util, used to track names of custom providers
+_custom_providers: List[
+    str
+] = []  # internal helper util, used to track names of custom providers
 disable_hf_tokenizer_download: Optional[bool] = (
     None  # disable huggingface tokenizer download. Defaults to openai clk100
 )

litellm/_redis.py

@@ -327,7 +327,9 @@ def _get_redis_client_logic(**env_overrides):
         **env_overrides,
     }
 
-    _startup_nodes: Optional[Union[str, list]] = redis_kwargs.get("startup_nodes", None) or get_secret(  # type: ignore
+    _startup_nodes: Optional[Union[str, list]] = redis_kwargs.get(
+        "startup_nodes", None
+    ) or get_secret(  # type: ignore
         "REDIS_CLUSTER_NODES"
     )
 
@@ -338,7 +340,9 @@ def _get_redis_client_logic(**env_overrides):
     elif _startup_nodes is None:
         redis_kwargs.pop("startup_nodes", None)
 
-    _sentinel_nodes: Optional[Union[str, list]] = redis_kwargs.get("sentinel_nodes", None) or get_secret(  # type: ignore
+    _sentinel_nodes: Optional[Union[str, list]] = redis_kwargs.get(
+        "sentinel_nodes", None
+    ) or get_secret(  # type: ignore
         "REDIS_SENTINEL_NODES"
     )
 
@@ -609,7 +613,8 @@ def get_redis_async_client(
 
         # Create async RedisCluster with IAM token as password if available
         cluster_client = async_redis.RedisCluster(
-            startup_nodes=new_startup_nodes, **cluster_kwargs  # type: ignore
+            startup_nodes=new_startup_nodes,
+            **cluster_kwargs,  # type: ignore
         )
 
         return cluster_client

litellm/assistants/main.py

@@ -184,7 +184,9 @@ def get_assistants(
             response=httpx.Response(
                 status_code=400,
                 content="Unsupported provider",
-                request=httpx.Request(method="create_thread", url="https://github.com/BerriAI/litellm"),  # type: ignore
+                request=httpx.Request(
+                    method="create_thread", url="https://github.com/BerriAI/litellm"
+                ),  # type: ignore
             ),
         )
 
@@ -198,7 +200,9 @@ def get_assistants(
             response=httpx.Response(
                 status_code=400,
                 content="Unsupported provider",
-                request=httpx.Request(method="create_thread", url="https://github.com/BerriAI/litellm"),  # type: ignore
+                request=httpx.Request(
+                    method="create_thread", url="https://github.com/BerriAI/litellm"
+                ),  # type: ignore
             ),
         )
 
@@ -394,7 +398,9 @@ def create_assistants(
             response=httpx.Response(
                 status_code=400,
                 content="Unsupported provider",
-                request=httpx.Request(method="create_thread", url="https://github.com/BerriAI/litellm"),  # type: ignore
+                request=httpx.Request(
+                    method="create_thread", url="https://github.com/BerriAI/litellm"
+                ),  # type: ignore
             ),
         )
     if response is None:
@@ -761,7 +767,9 @@ def create_thread(
             response=httpx.Response(
                 status_code=400,
                 content="Unsupported provider",
-                request=httpx.Request(method="create_thread", url="https://github.com/BerriAI/litellm"),  # type: ignore
+                request=httpx.Request(
+                    method="create_thread", url="https://github.com/BerriAI/litellm"
+                ),  # type: ignore
             ),
         )
     return response  # type: ignore
@@ -916,7 +924,9 @@ def get_thread(
             response=httpx.Response(
                 status_code=400,
                 content="Unsupported provider",
-                request=httpx.Request(method="create_thread", url="https://github.com/BerriAI/litellm"),  # type: ignore
+                request=httpx.Request(
+                    method="create_thread", url="https://github.com/BerriAI/litellm"
+                ),  # type: ignore
             ),
         )
     return response  # type: ignore
@@ -1103,7 +1113,9 @@ def add_message(
             response=httpx.Response(
                 status_code=400,
                 content="Unsupported provider",
-                request=httpx.Request(method="create_thread", url="https://github.com/BerriAI/litellm"),  # type: ignore
+                request=httpx.Request(
+                    method="create_thread", url="https://github.com/BerriAI/litellm"
+                ),  # type: ignore
             ),
         )
 
@@ -1263,7 +1275,9 @@ def get_messages(
             response=httpx.Response(
                 status_code=400,
                 content="Unsupported provider",
-                request=httpx.Request(method="create_thread", url="https://github.com/BerriAI/litellm"),  # type: ignore
+                request=httpx.Request(
+                    method="create_thread", url="https://github.com/BerriAI/litellm"
+                ),  # type: ignore
             ),
         )
 
@@ -1478,7 +1492,9 @@ def run_thread(
             response=httpx.Response(
                 status_code=400,
                 content="Unsupported provider",
-                request=httpx.Request(method="create_thread", url="https://github.com/BerriAI/litellm"),  # type: ignore
+                request=httpx.Request(
+                    method="create_thread", url="https://github.com/BerriAI/litellm"
+                ),  # type: ignore
             ),
         )
     return response  # type: ignore

litellm/assistants/utils.py

@@ -71,9 +71,7 @@ def _check_valid_arg(supported_params):
     if custom_llm_provider == "openai":
         optional_params = non_default_params
     elif custom_llm_provider == "azure":
-        supported_params = (
-            litellm.AzureOpenAIAssistantsAPIConfig().get_supported_openai_create_message_params()
-        )
+        supported_params = litellm.AzureOpenAIAssistantsAPIConfig().get_supported_openai_create_message_params()
         _check_valid_arg(supported_params=supported_params)
         optional_params = litellm.AzureOpenAIAssistantsAPIConfig().map_openai_params_create_message_params(
             non_default_params=non_default_params, optional_params=optional_params

litellm/batches/main.py

@@ -359,7 +359,9 @@ def create_batch(
                 response=httpx.Response(
                     status_code=400,
                     content="Unsupported provider",
-                    request=httpx.Request(method="create_batch", url="https://github.com/BerriAI/litellm"),  # type: ignore
+                    request=httpx.Request(
+                        method="create_batch", url="https://github.com/BerriAI/litellm"
+                    ),  # type: ignore
                 ),
             )
         return response
@@ -553,7 +555,9 @@ def _handle_retrieve_batch_providers_without_provider_config(
             response=httpx.Response(
                 status_code=400,
                 content="Unsupported provider",
-                request=httpx.Request(method="retrieve_batch", url="https://github.com/BerriAI/litellm"),  # type: ignore
+                request=httpx.Request(
+                    method="retrieve_batch", url="https://github.com/BerriAI/litellm"
+                ),  # type: ignore
             ),
         )
     return response
@@ -819,7 +823,11 @@ def list_batches(
                 max_retries=optional_params.max_retries,
             )
         elif custom_llm_provider == "azure":
-            api_base = optional_params.api_base or litellm.api_base or get_secret_str("AZURE_API_BASE")  # type: ignore
+            api_base = (
+                optional_params.api_base
+                or litellm.api_base
+                or get_secret_str("AZURE_API_BASE")
+            )  # type: ignore
             api_version = (
                 optional_params.api_version
                 or litellm.api_version
@@ -887,7 +895,9 @@ def list_batches(
                 response=httpx.Response(
                     status_code=400,
                     content="Unsupported provider",
-                    request=httpx.Request(method="create_thread", url="https://github.com/BerriAI/litellm"),  # type: ignore
+                    request=httpx.Request(
+                        method="create_thread", url="https://github.com/BerriAI/litellm"
+                    ),  # type: ignore
                 ),
             )
         return response
@@ -1097,7 +1107,9 @@ def cancel_batch(
                 response=httpx.Response(
                     status_code=400,
                     content="Unsupported provider",
-                    request=httpx.Request(method="cancel_batch", url="https://github.com/BerriAI/litellm"),  # type: ignore
+                    request=httpx.Request(
+                        method="cancel_batch", url="https://github.com/BerriAI/litellm"
+                    ),  # type: ignore
                 ),
             )
         return response

litellm/budget_manager.py

@@ -67,9 +67,7 @@ def load_data(self):
             )
             response = response.json()
             if response["status"] == "error":
-                self.user_dict = (
-                    {}
-                )  # assume this means the user dict hasn't been stored yet
+                self.user_dict = {}  # assume this means the user dict hasn't been stored yet
             else:
                 self.user_dict = response["data"]
 

litellm/caching/caching_handler.py

@@ -79,9 +79,7 @@ class CachingHandlerResponse(BaseModel):
 
     cached_result: Optional[Any] = None
     final_embedding_cached_response: Optional[EmbeddingResponse] = None
-    embedding_all_elements_cache_hit: bool = (
-        False  # this is set to True when all elements in the list have a cache hit in the embedding cache, if true return the final_embedding_cached_response no need to make an API call
-    )
+    embedding_all_elements_cache_hit: bool = False  # this is set to True when all elements in the list have a cache hit in the embedding cache, if true return the final_embedding_cached_response no need to make an API call
 
 
 in_memory_cache_obj = InMemoryCache()
@@ -165,10 +163,11 @@ async def _async_get_cache(
         """
         # Check if caching should be performed BEFORE doing expensive operations
         if (
-            (kwargs.get("caching", None) is None and litellm.cache is not None)
-            or kwargs.get("caching", False) is True
-        ) and (
-            kwargs.get("cache", {}).get("no-cache", False) is not True
+            (
+                (kwargs.get("caching", None) is None and litellm.cache is not None)
+                or kwargs.get("caching", False) is True
+            )
+            and (kwargs.get("cache", {}).get("no-cache", False) is not True)
         ):  # allow users to control returning cached responses from the completion function
             args = args or ()
             final_embedding_cached_response: Optional[EmbeddingResponse] = None

litellm/caching/redis_cluster_cache.py

@@ -79,7 +79,8 @@ async def test_connection(self) -> dict:
 
             # Create a fresh Redis Cluster client with current settings
             redis_client = redis_async.RedisCluster(
-                startup_nodes=new_startup_nodes, **cluster_kwargs  # type: ignore
+                startup_nodes=new_startup_nodes,
+                **cluster_kwargs,  # type: ignore
             )
 
             # Test the connection