chore(langchain): cleanup ruff config

Author: cbornet

libs/langchain_v1/langchain/__init__.py

@@ -5,7 +5,7 @@
 __version__ = "1.0.0a3"
 
 
-def __getattr__(name: str) -> Any:  # noqa: ANN401
+def __getattr__(name: str) -> Any:
     """Get an attribute from the package.
 
     TODO: will be removed in a future alpha version.

libs/langchain_v1/langchain/agents/react_agent.py

@@ -221,7 +221,7 @@ def __init__(
                 "Expected `model` to be a BaseChatModel or a string, got {type(model)}."
                 "The `model` parameter should not have pre-bound tools, simply pass the model and tools separately."
             )
-            raise ValueError(msg)
+            raise TypeError(msg)
 
         self._setup_tools()
         self._setup_state_schema()
@@ -397,13 +397,13 @@ def _handle_single_structured_output(
                     "structured_response": structured_response,
                 }
             )
-        except Exception as exc:  # noqa: BLE001
+        except Exception as exc:
             exception = StructuredOutputValidationError(tool_call["name"], exc)
 
             should_retry, error_message = self._handle_structured_output_error(exception)
 
             if not should_retry:
-                raise exception
+                raise exception from exc
 
             return Command(
                 update={

libs/langchain_v1/langchain/agents/tool_node.py

@@ -119,7 +119,7 @@ def msg_content_output(output: Any) -> Union[str, list[dict]]:
     # any existing ToolNode usage.
     try:
         return json.dumps(output, ensure_ascii=False)
-    except Exception:  # noqa: BLE001
+    except Exception:
         return str(output)
 
 
@@ -202,7 +202,7 @@ def _handle_tool_error(
             f"Got unexpected type of `handle_tool_error`. Expected bool, str "
             f"or callable. Received: {flag}"
         )
-        raise ValueError(msg)
+        raise TypeError(msg)
     return content
 
 
@@ -417,7 +417,7 @@ def tools_by_name(self) -> dict[str, BaseTool]:
 
     def _func(
         self,
-        input: Union[
+        input_: Union[
             list[AnyMessage],
             dict[str, Any],
             BaseModel,
@@ -426,7 +426,7 @@ def _func(
         *,
         store: Optional[BaseStore],  # noqa: UP045
     ) -> Any:
-        tool_calls, input_type = self._parse_input(input, store)
+        tool_calls, input_type = self._parse_input(input_, store)
         config_list = get_config_list(config, len(tool_calls))
         input_types = [input_type] * len(tool_calls)
         with get_executor_for_config(config) as executor:
@@ -436,7 +436,7 @@ def _func(
 
     async def _afunc(
         self,
-        input: Union[
+        input_: Union[
             list[AnyMessage],
             dict[str, Any],
             BaseModel,
@@ -445,7 +445,7 @@ async def _afunc(
         *,
         store: Optional[BaseStore],  # noqa: UP045
     ) -> Any:
-        tool_calls, input_type = self._parse_input(input, store)
+        tool_calls, input_type = self._parse_input(input_, store)
         outputs = await asyncio.gather(
             *(self._arun_one(call, input_type, config) for call in tool_calls)
         )
@@ -625,24 +625,24 @@ async def _arun_one(
 
     def _parse_input(
         self,
-        input: Union[
+        input_: Union[
             list[AnyMessage],
             dict[str, Any],
             BaseModel,
         ],
         store: BaseStore | None,
     ) -> tuple[list[ToolCall], Literal["list", "dict", "tool_calls"]]:
         input_type: Literal["list", "dict", "tool_calls"]
-        if isinstance(input, list):
-            if isinstance(input[-1], dict) and input[-1].get("type") == "tool_call":
+        if isinstance(input_, list):
+            if isinstance(input_[-1], dict) and input_[-1].get("type") == "tool_call":
                 input_type = "tool_calls"
-                tool_calls = cast("list[ToolCall]", input)
+                tool_calls = cast("list[ToolCall]", input_)
                 return tool_calls, input_type
             input_type = "list"
-            messages = input
-        elif isinstance(input, dict) and (messages := input.get(self._messages_key, [])):
+            messages = input_
+        elif isinstance(input_, dict) and (messages := input_.get(self._messages_key, [])):
             input_type = "dict"
-        elif messages := getattr(input, self._messages_key, []):
+        elif messages := getattr(input_, self._messages_key, []):
             # Assume dataclass-like state that can coerce from dict
             input_type = "dict"
         else:
@@ -651,12 +651,12 @@ def _parse_input(
 
         try:
             latest_ai_message = next(m for m in reversed(messages) if isinstance(m, AIMessage))
-        except StopIteration:
+        except StopIteration as e:
             msg = "No AIMessage found in input"
-            raise ValueError(msg)
+            raise ValueError(msg) from e
 
         tool_calls = [
-            self.inject_tool_args(call, input, store) for call in latest_ai_message.tool_calls
+            self.inject_tool_args(call, input_, store) for call in latest_ai_message.tool_calls
         ]
         return tool_calls, input_type
 
@@ -676,19 +676,19 @@ def _validate_tool_call(self, call: ToolCall) -> ToolMessage | None:
     def _inject_state(
         self,
         tool_call: ToolCall,
-        input: Union[
+        input_: Union[
             list[AnyMessage],
             dict[str, Any],
             BaseModel,
         ],
     ) -> ToolCall:
         state_args = self._tool_to_state_args[tool_call["name"]]
-        if state_args and isinstance(input, list):
+        if state_args and isinstance(input_, list):
             required_fields = list(state_args.values())
             if (
                 len(required_fields) == 1 and required_fields[0] == self._messages_key
             ) or required_fields[0] is None:
-                input = {self._messages_key: input}
+                input_ = {self._messages_key: input_}
             else:
                 err_msg = (
                     f"Invalid input to ToolNode. Tool {tool_call['name']} requires "
@@ -699,14 +699,14 @@ def _inject_state(
                     err_msg += f" State should contain fields {required_fields_str}."
                 raise ValueError(err_msg)
 
-        if isinstance(input, dict):
+        if isinstance(input_, dict):
             tool_state_args = {
-                tool_arg: input[state_field] if state_field else input
+                tool_arg: input_[state_field] if state_field else input_
                 for tool_arg, state_field in state_args.items()
             }
         else:
             tool_state_args = {
-                tool_arg: getattr(input, state_field) if state_field else input
+                tool_arg: getattr(input_, state_field) if state_field else input_
                 for tool_arg, state_field in state_args.items()
             }
 
@@ -737,7 +737,7 @@ def _inject_store(self, tool_call: ToolCall, store: BaseStore | None) -> ToolCal
     def inject_tool_args(
         self,
         tool_call: ToolCall,
-        input: Union[
+        input_: Union[
             list[AnyMessage],
             dict[str, Any],
             BaseModel,
@@ -758,7 +758,7 @@ def inject_tool_args(
         Args:
             tool_call: The tool call dictionary to augment with injected arguments.
                 Must contain 'name', 'args', 'id', and 'type' fields.
-            input: The current graph state to inject into tools requiring state access.
+            input_: The current graph state to inject into tools requiring state access.
                 Can be a message list, state dictionary, or BaseModel instance.
             store: The persistent store instance to inject into tools requiring storage.
                 Will be None if no store is configured for the graph.
@@ -781,7 +781,7 @@ def inject_tool_args(
             return tool_call
 
         tool_call_copy: ToolCall = copy(tool_call)
-        tool_call_with_state = self._inject_state(tool_call_copy, input)
+        tool_call_with_state = self._inject_state(tool_call_copy, input_)
         return self._inject_store(tool_call_with_state, store)
 
     def _validate_tool_command(

libs/langchain_v1/langchain/chat_models/base.py

@@ -628,6 +628,7 @@ def with_config(
         )
 
     @property
+    @override
     def InputType(self) -> TypeAlias:
         """Get the input type for this runnable."""
         from langchain_core.prompt_values import (
@@ -819,6 +820,7 @@ async def atransform(
             yield x
 
     @overload
+    @override
     def astream_log(
         self,
         input: Any,
@@ -836,6 +838,7 @@ def astream_log(
     ) -> AsyncIterator[RunLogPatch]: ...
 
     @overload
+    @override
     def astream_log(
         self,
         input: Any,

libs/langchain_v1/pyproject.toml

@@ -59,7 +59,7 @@ test = [
 ]
 codespell = ["codespell<3.0.0,>=2.2.0"]
 lint = [
-    "ruff>=0.12.2",
+    "ruff<0.13,>=0.12.11",
 ]
 typing = [
     "mypy<0.18,>=1.17.1",
@@ -70,7 +70,6 @@ test_integration = [
     "vcrpy>=7.0",
     "wrapt>=1.15.0",
     "python-dotenv>=1.0.0",
-    "cassio>=0.1.0",
     "langchainhub>=0.1.16",
     "langchain-core",
     "langchain-text-splitters",
@@ -107,71 +106,43 @@ select = [
   "ALL"
 ]
 ignore = [
-  "COM812",  # Messes with the formatter
-  "ISC001",  # Messes with the formatter
-  "PERF203", # Rarely useful
-  "SLF001",  # Private member access
-  "UP007",   # pyupgrade: non-pep604-annotation-union
-  "PLC0415", # Imports should be at the top. Not always desirable
-  "PLR0913", # Too many arguments in function definition
-  "PLC0414", # Inconsistent with how type checkers expect to be notified of intentional re-exports
+    "C90",     # McCabe complexity
+    "COM812",  # Messes with the formatter
+    "ISC001",  # Messes with the formatter
+    "PERF203", # Rarely useful
+    "PLR09",   # Too many something (arg, statements, etc)
+    "UP007",   # pyupgrade: non-pep604-annotation-union
+    "PLC0415", # Imports should be at the top. Not always desirable
+
+    # TODO rules
+    "ANN401",
+    "BLE",
+]
+unfixable = [
+    "B028",    # People should intentionally tune the stacklevel
+    "PLW1510", # People should intentionally set the check argument
 ]
-unfixable = ["B028"] # People should intentionally tune the stacklevel
 
 pydocstyle.convention = "google"
 pyupgrade.keep-runtime-typing = true
 flake8-annotations.allow-star-arg-any = true
 
-[tool.ruff.lint.per-file-ignores]
-"tests/*" = [
-  "D1", # Documentation rules
-  "PLC0415", # Imports should be at the top. Not always desirable for tests
-]
-"langchain/agents/*" = [
-    "ANN401", # we use Any right now, need to narrow
-    "E501", # line too long, needs to fix
-    "A002", # input is shadowing builtin
-    "A001", # input is shadowing builtin
-    "B904", # use from for exceptions
-    "PLR2004", # magic values are fine for this case
-    "C901", # too complex
-    "TRY004", # type error exception
-    "PLR0912", # too many branches
-    "PLR0911", # too many return statements
-]
+[tool.ruff.lint.extend-per-file-ignores]
 "tests/unit_tests/agents/*" = ["ALL"]
 "tests/integration_tests/agents/*" = ["ALL"]
-
-[tool.ruff.lint.extend-per-file-ignores]
 "scripts/check_imports.py" = ["ALL"]
 
-"langchain/chat_models/base.py" = [
-    "ANN",
-    "C901",
-    "FIX002",
-    "N802",
-    "PLR0911",
-    "PLR0912",
-    "PLR0915",
-]
-
-"langchain/embeddings/base.py" = [
-    "PLR0911",
-    "PLR0913",
+"langchain/agents/*" = [
+    "E501",    # line too long, needs to fix
+    "PLR2004", # magic values are fine for this case
 ]
 
-"tests/**/*.py" = [
-    "S101",   # Tests need assertions
-    "S311",   # Standard pseudo-random generators are not suitable for cryptographic purposes
-    "SLF001", # Private member access in tests
+"tests/*" = [
+    "D1",       # Documentation rules
+    "S101",    # Tests need assertions
+    "S311",    # Standard pseudo-random generators are not suitable for cryptographic purposes
+    "SLF001",  # Private member access in tests
     "PLR2004", # Magic values are perfectly fine in unit tests (e.g. 0, 1, 2, etc.)
-    "C901", # Too complex
-    "ANN401", # Annotated type is not necessary
-    "N802", # Function name should be lowercase
-    "PLW1641", # Object does not implement __hash__ method
-    "ARG002", # Unused argument
-    "BLE001", # Do not catch blind exception
-    "N801", # class name should use CapWords convention
 ]
 
 [tool.coverage.run]

libs/langchain_v1/tests/integration_tests/cache/fake_embeddings.py

@@ -3,6 +3,7 @@
 import math
 
 from langchain_core.embeddings import Embeddings
+from typing_extensions import override
 
 fake_texts = ["foo", "bar", "baz"]
 
@@ -20,6 +21,7 @@ def embed_documents(self, texts: list[str]) -> list[list[float]]:
     async def aembed_documents(self, texts: list[str]) -> list[list[float]]:
         return self.embed_documents(texts)
 
+    @override
     def embed_query(self, text: str) -> list[float]:
         """Return constant query embeddings.
 

libs/langchain_v1/tests/integration_tests/chat_models/test_base.py

@@ -11,7 +11,7 @@
 from langchain.chat_models import init_chat_model
 
 
-class multiply(BaseModel):
+class Multiply(BaseModel):
     """Product of two ints."""
 
     x: int
@@ -21,7 +21,7 @@ class multiply(BaseModel):
 @pytest.mark.requires("langchain_openai", "langchain_anthropic")
 async def test_init_chat_model_chain() -> None:
     model = init_chat_model("gpt-4o", configurable_fields="any", config_prefix="bar")
-    model_with_tools = model.bind_tools([multiply])
+    model_with_tools = model.bind_tools([Multiply])
 
     model_with_config = model_with_tools.with_config(
         RunnableConfig(tags=["foo"]),

libs/langchain_v1/tests/unit_tests/agents/test_react_agent.py

@@ -266,7 +266,7 @@ def tool2(some_val: int) -> str:
             }
         )
     # check valid agent constructor
-    with pytest.raises(ValueError):
+    with pytest.raises(TypeError):
         create_agent(
             model.bind_tools(tools),
             tools,

libs/langchain_v1/tests/unit_tests/embeddings/test_caching.py

@@ -7,6 +7,7 @@
 
 import pytest
 from langchain_core.embeddings import Embeddings
+from typing_extensions import override
 
 from langchain.embeddings import CacheBackedEmbeddings
 from langchain.storage.in_memory import InMemoryStore
@@ -23,6 +24,7 @@ def embed_documents(self, texts: list[str]) -> list[list[float]]:
             embeddings.append([len(text), len(text) + 1])
         return embeddings
 
+    @override
     def embed_query(self, text: str) -> list[float]:
         # Simulate embedding a query
         return [5.0, 6.0]