ruff: add bugbear across packages (#31917)

mdrxy · web-flow · commit ae210c1590cf · 2025-07-08T12:22:55.000-04:00
WIP, other packages will get in next PRs
diff --git a/libs/cli/langchain_cli/namespaces/app.py b/libs/cli/langchain_cli/namespaces/app.py
@@ -134,19 +134,22 @@ def add(
         typer.Argument(help="The dependency to add"),
     ] = None,
     *,
-    api_path: Annotated[list[str], typer.Option(help="API paths to add")] = [],
+    api_path: Annotated[
+        Optional[list[str]],
+        typer.Option(help="API paths to add"),
+    ] = None,
     project_dir: Annotated[
         Optional[Path],
         typer.Option(help="The project directory"),
     ] = None,
     repo: Annotated[
-        list[str],
+        Optional[list[str]],
         typer.Option(help="Install templates from a specific github repo instead"),
-    ] = [],
+    ] = None,
     branch: Annotated[
-        list[str],
+        Optional[list[str]],
         typer.Option(help="Install templates from a specific branch"),
-    ] = [],
+    ] = None,
     pip: Annotated[
         bool,
         typer.Option(
@@ -163,6 +166,12 @@ def add(
     langchain app add extraction-openai-functions
     langchain app add git+ssh://git@github.com/efriis/simple-pirate.git
     """
+    if branch is None:
+        branch = []
+    if repo is None:
+        repo = []
+    if api_path is None:
+        api_path = []
     if not branch and not repo:
         warnings.warn(
             "Adding templates from the default branch and repo is deprecated."
diff --git a/libs/cli/langchain_cli/namespaces/integration.py b/libs/cli/langchain_cli/namespaces/integration.py
@@ -90,7 +90,7 @@ def new(
         replacements = _process_name(name)
     except ValueError as e:
         typer.echo(e)
-        raise typer.Exit(code=1)
+        raise typer.Exit(code=1) from None
 
     if name_class:
         if not re.match(r"^[A-Z][a-zA-Z0-9]*$", name_class):
diff --git a/libs/cli/langchain_cli/utils/git.py b/libs/cli/langchain_cli/utils/git.py
@@ -65,7 +65,7 @@ def parse_dependency_string(
         else:
             _, post_slash = find_slash.split("/", 1)
             if "@" in post_slash or "#" in post_slash:
-                _, ref = re.split(r"[@#]", post_slash, 1)
+                _, ref = re.split(r"[@#]", post_slash, maxsplit=1)
 
         # gitstring is everything before that
         gitstring = gitstring[: -len(ref) - 1] if ref is not None else gitstring
@@ -159,7 +159,7 @@ def _get_repo_path(gitstring: str, ref: Optional[str], repo_dir: Path) -> Path:
     hashed = hashlib.sha256((f"{gitstring}:{ref_str}").encode()).hexdigest()[:8]
 
     removed_protocol = gitstring.split("://")[-1]
-    removed_basename = re.split(r"[/:]", removed_protocol, 1)[-1]
+    removed_basename = re.split(r"[/:]", removed_protocol, maxsplit=1)[-1]
     removed_extras = removed_basename.split("#")[0]
     foldername = re.sub(r"\W", "_", removed_extras)
 
diff --git a/libs/cli/pyproject.toml b/libs/cli/pyproject.toml
@@ -50,6 +50,7 @@ exclude = [
 [tool.ruff.lint]
 select = [
     "A",      # flake8-builtins
+    "B",      # flake8-bugbear
     "ARG",    # flake8-unused-arguments
     "ASYNC",  # flake8-async
     "C4",     # flake8-comprehensions
@@ -96,6 +97,7 @@ ignore = [
     "D105",    # pydocstyle: Missing docstring in magic method
     "D107",    # pydocstyle: Missing docstring in __init__
     "D407",    # pydocstyle: Missing-dashed-underline-after-section
+    "COM812",  # Messes with the formatter
 ]
 pyupgrade.keep-runtime-typing = true
 
diff --git a/libs/langchain/langchain/__init__.py b/libs/langchain/langchain/__init__.py
@@ -29,12 +29,12 @@ def _warn_on_import(name: str, replacement: Optional[str] = None) -> None:
         warnings.warn(
             f"Importing {name} from langchain root module is no longer supported. "
             f"Please use {replacement} instead.",
-            stacklevel=3,
+            stacklevel=2,
         )
     else:
         warnings.warn(
             f"Importing {name} from langchain root module is no longer supported.",
-            stacklevel=3,
+            stacklevel=2,
         )
 
 
diff --git a/libs/langchain/langchain/chains/base.py b/libs/langchain/langchain/chains/base.py
@@ -255,7 +255,7 @@ def raise_callback_manager_deprecation(cls, values: dict) -> Any:
             warnings.warn(
                 "callback_manager is deprecated. Please use callbacks instead.",
                 DeprecationWarning,
-                stacklevel=4,
+                stacklevel=2,
             )
             values["callbacks"] = values.pop("callback_manager", None)
         return values
diff --git a/libs/langchain/langchain/chains/conversational_retrieval/base.py b/libs/langchain/langchain/chains/conversational_retrieval/base.py
@@ -504,7 +504,7 @@ def raise_deprecation(cls, values: dict) -> Any:
         warnings.warn(
             "`ChatVectorDBChain` is deprecated - "
             "please use `from langchain.chains import ConversationalRetrievalChain`",
-            stacklevel=4,
+            stacklevel=2,
         )
         return values
 
diff --git a/libs/langchain/langchain/chains/llm_checker/base.py b/libs/langchain/langchain/chains/llm_checker/base.py
@@ -112,7 +112,7 @@ def raise_deprecation(cls, values: dict) -> Any:
                 "Directly instantiating an LLMCheckerChain with an llm is deprecated. "
                 "Please instantiate with question_to_checked_assertions_chain "
                 "or using the from_llm class method.",
-                stacklevel=5,
+                stacklevel=2,
             )
             if (
                 "question_to_checked_assertions_chain" not in values
diff --git a/libs/langchain/langchain/chains/llm_math/base.py b/libs/langchain/langchain/chains/llm_math/base.py
@@ -177,7 +177,7 @@ def raise_deprecation(cls, values: dict) -> Any:
                 "Directly instantiating an LLMMathChain with an llm is deprecated. "
                 "Please instantiate with llm_chain argument or using the from_llm "
                 "class method.",
-                stacklevel=5,
+                stacklevel=2,
             )
             if "llm_chain" not in values and values["llm"] is not None:
                 prompt = values.get("prompt", PROMPT)
diff --git a/libs/langchain/langchain/chains/llm_summarization_checker/base.py b/libs/langchain/langchain/chains/llm_summarization_checker/base.py
@@ -118,7 +118,7 @@ def raise_deprecation(cls, values: dict) -> Any:
                 "Directly instantiating an LLMSummarizationCheckerChain with an llm is "
                 "deprecated. Please instantiate with"
                 " sequential_chain argument or using the from_llm class method.",
-                stacklevel=5,
+                stacklevel=2,
             )
             if "sequential_chain" not in values and values["llm"] is not None:
                 values["sequential_chain"] = _load_sequential_chain(
diff --git a/libs/langchain/langchain/chains/natbot/base.py b/libs/langchain/langchain/chains/natbot/base.py
@@ -74,7 +74,7 @@ def raise_deprecation(cls, values: dict) -> Any:
                 "Directly instantiating an NatBotChain with an llm is deprecated. "
                 "Please instantiate with llm_chain argument or using the from_llm "
                 "class method.",
-                stacklevel=5,
+                stacklevel=2,
             )
             if "llm_chain" not in values and values["llm"] is not None:
                 values["llm_chain"] = PROMPT | values["llm"] | StrOutputParser()
diff --git a/libs/langchain/langchain/chains/qa_with_sources/vector_db.py b/libs/langchain/langchain/chains/qa_with_sources/vector_db.py
@@ -77,7 +77,7 @@ def raise_deprecation(cls, values: dict) -> Any:
         warnings.warn(
             "`VectorDBQAWithSourcesChain` is deprecated - "
             "please use `from langchain.chains import RetrievalQAWithSourcesChain`",
-            stacklevel=5,
+            stacklevel=2,
         )
         return values
 
diff --git a/libs/langchain/langchain/chains/query_constructor/parser.py b/libs/langchain/langchain/chains/query_constructor/parser.py
@@ -162,7 +162,7 @@ def date(self, item: Any) -> ISO8601Date:
             warnings.warn(
                 "Dates are expected to be provided in ISO 8601 date format "
                 "(YYYY-MM-DD).",
-                stacklevel=3,
+                stacklevel=2,
             )
         return {"date": item, "type": "date"}
 
diff --git a/libs/langchain/langchain/evaluation/schema.py b/libs/langchain/langchain/evaluation/schema.py
@@ -124,12 +124,12 @@ def _check_evaluation_args(
             msg = f"{self.__class__.__name__} requires an input string."
             raise ValueError(msg)
         if input_ is not None and not self.requires_input:
-            warn(self._skip_input_warning, stacklevel=3)
+            warn(self._skip_input_warning, stacklevel=2)
         if self.requires_reference and reference is None:
             msg = f"{self.__class__.__name__} requires a reference string."
             raise ValueError(msg)
         if reference is not None and not self.requires_reference:
-            warn(self._skip_reference_warning, stacklevel=3)
+            warn(self._skip_reference_warning, stacklevel=2)
 
 
 class StringEvaluator(_EvalArgsMixin, ABC):
diff --git a/libs/langchain/langchain/indexes/vectorstore.py b/libs/langchain/langchain/indexes/vectorstore.py
@@ -183,7 +183,7 @@ def _get_in_memory_vectorstore() -> type[VectorStore]:
         "Using InMemoryVectorStore as the default vectorstore."
         "This memory store won't persist data. You should explicitly"
         "specify a vectorstore when using VectorstoreIndexCreator",
-        stacklevel=3,
+        stacklevel=2,
     )
     return InMemoryVectorStore
 
diff --git a/libs/langchain/langchain/memory/chat_memory.py b/libs/langchain/langchain/memory/chat_memory.py
@@ -58,7 +58,7 @@ def _get_input_output(
                     f"'{self.__class__.__name__}' got multiple output keys:"
                     f" {outputs.keys()}. The default 'output' key is being used."
                     f" If this is not desired, please manually set 'output_key'.",
-                    stacklevel=3,
+                    stacklevel=2,
                 )
             else:
                 msg = (
diff --git a/libs/langchain/langchain/memory/combined.py b/libs/langchain/langchain/memory/combined.py
@@ -42,7 +42,7 @@ def check_input_key(cls, value: list[BaseMemory]) -> list[BaseMemory]:
                     "When using CombinedMemory, "
                     "input keys should be so the input is known. "
                     f" Was not set on {val}",
-                    stacklevel=5,
+                    stacklevel=2,
                 )
         return value
 
diff --git a/libs/langchain/langchain/retrievers/self_query/base.py b/libs/langchain/langchain/retrievers/self_query/base.py
@@ -27,12 +27,12 @@ def _get_builtin_translator(vectorstore: VectorStore) -> Visitor:
     """Get the translator class corresponding to the vector store class."""
     try:
         import langchain_community  # noqa: F401
-    except ImportError as e:
+    except ImportError as err:
         msg = (
             "The langchain-community package must be installed to use this feature."
             " Please install it using `pip install langchain-community`."
         )
-        raise ImportError(msg) from e
+        raise ImportError(msg) from err
 
     from langchain_community.query_constructors.astradb import AstraDBTranslator
     from langchain_community.query_constructors.chroma import ChromaTranslator
diff --git a/libs/langchain/langchain/smith/evaluation/runner_utils.py b/libs/langchain/langchain/smith/evaluation/runner_utils.py
@@ -350,7 +350,7 @@ def _validate_example_inputs_for_language_model(
         except InputFormatError:
             try:
                 _get_messages(first_example.inputs or {})
-            except InputFormatError as e:
+            except InputFormatError as err2:
                 msg = (
                     "Example inputs do not match language model input format. "
                     "Expected a dictionary with messages or a single prompt."
@@ -359,7 +359,7 @@ def _validate_example_inputs_for_language_model(
                     " to convert the example.inputs to a compatible format"
                     " for the llm or chat model you wish to evaluate."
                 )
-                raise InputFormatError(msg) from e
+                raise InputFormatError(msg) from err2
 
 
 def _validate_example_inputs_for_chain(
diff --git a/libs/langchain/langchain/tools/__init__.py b/libs/langchain/langchain/tools/__init__.py
@@ -78,8 +78,8 @@ def __getattr__(name: str) -> Any:
             f"`from langchain_community.tools import {name}`.\n\n"
             "To install langchain-community run "
             "`pip install -U langchain-community`.",
-            category=LangChainDeprecationWarning,
             stacklevel=2,
+            category=LangChainDeprecationWarning,
         )
 
     return getattr(tools, name)
diff --git a/libs/langchain/pyproject.toml b/libs/langchain/pyproject.toml
@@ -145,6 +145,7 @@ ignore-words-list = "momento,collison,ned,foor,reworkd,parth,whats,aapply,mysogy
 [tool.ruff.lint]
 select = [
     "A",      # flake8-builtins
+    "B",      # flake8-bugbear
     "ASYNC",  # flake8-async
     "B",      # flake8-bugbear
     "C4",     # flake8-comprehensions
@@ -195,6 +196,7 @@ ignore = [
     "S112",    # Rarely useful
     "RUF012",  # Doesn't play well with Pydantic
     "SLF001",  # Private member access
+    "UP007",   # pyupgrade: non-pep604-annotation-union
 ]
 
 pydocstyle.convention = "google"
diff --git a/libs/partners/anthropic/langchain_anthropic/chat_models.py b/libs/partners/anthropic/langchain_anthropic/chat_models.py
@@ -314,7 +314,7 @@ def _format_messages(
     system: Union[str, list[dict], None] = None
     formatted_messages: list[dict] = []
     merged_messages = _merge_messages(messages)
-    for i, message in enumerate(merged_messages):
+    for _i, message in enumerate(merged_messages):
         if message.type == "system":
             if system is not None:
                 msg = "Received multiple non-consecutive system messages."
@@ -496,7 +496,7 @@ def _handle_anthropic_bad_request(e: anthropic.BadRequestError) -> None:
     """Handle Anthropic BadRequestError."""
     if ("messages: at least one message is required") in e.message:
         message = "Received only system message(s). "
-        warnings.warn(message)
+        warnings.warn(message, stacklevel=2)
         raise e
     raise
 
@@ -1558,7 +1558,7 @@ def _get_llm_for_structured_output_when_thinking_is_enabled(
             "generated. Consider disabling `thinking` or adjust your prompt to ensure "
             "the tool is called."
         )
-        warnings.warn(thinking_admonition)
+        warnings.warn(thinking_admonition, stacklevel=2)
         llm = self.bind_tools(
             [schema],
             ls_structured_output_format={
@@ -2120,7 +2120,7 @@ def _make_message_chunk_from_anthropic_event(
         )
     ):
         if coerce_content_to_string:
-            warnings.warn("Received unexpected tool content block.")
+            warnings.warn("Received unexpected tool content block.", stacklevel=2)
         content_block = event.content_block.model_dump()
         content_block["index"] = event.index
         if event.content_block.type == "tool_use":
diff --git a/libs/partners/anthropic/langchain_anthropic/llms.py b/libs/partners/anthropic/langchain_anthropic/llms.py
@@ -170,6 +170,7 @@ def raise_warning(cls, values: dict) -> Any:
             "This Anthropic LLM is deprecated. "
             "Please use `from langchain_anthropic import ChatAnthropic` "
             "instead",
+            stacklevel=2,
         )
         return values
 
diff --git a/libs/partners/anthropic/pyproject.toml b/libs/partners/anthropic/pyproject.toml
@@ -62,6 +62,7 @@ target-version = "py39"
 [tool.ruff.lint]
 select = [
     "A",      # flake8-builtins
+    "B",      # flake8-bugbear
     "ASYNC",  # flake8-async
     "C4",     # flake8-comprehensions
     "COM",    # flake8-commas
diff --git a/libs/partners/anthropic/tests/integration_tests/test_chat_models.py b/libs/partners/anthropic/tests/integration_tests/test_chat_models.py
@@ -1210,6 +1210,5 @@ def test_search_result_top_level() -> None:
 
 def test_async_shared_client() -> None:
     llm = ChatAnthropic(model="claude-3-5-haiku-latest")
-    llm._async_client  # Instantiates lazily
     _ = asyncio.run(llm.ainvoke("Hello"))
     _ = asyncio.run(llm.ainvoke("Hello"))
diff --git a/libs/partners/chroma/langchain_chroma/vectorstores.py b/libs/partners/chroma/langchain_chroma/vectorstores.py
@@ -479,7 +479,7 @@ def add_images(
                             "Try filtering complex metadata using "
                             "langchain_community.vectorstores.utils.filter_complex_metadata."
                         )
-                        raise ValueError(e.args[0] + "\n\n" + msg)
+                        raise ValueError(e.args[0] + "\n\n" + msg) from e
                     raise e
             if empty_ids:
                 images_without_metadatas = [b64_texts[j] for j in empty_ids]
@@ -566,7 +566,7 @@ def add_texts(
                             "Try filtering complex metadata from the document using "
                             "langchain_community.vectorstores.utils.filter_complex_metadata."
                         )
-                        raise ValueError(e.args[0] + "\n\n" + msg)
+                        raise ValueError(e.args[0] + "\n\n" + msg) from e
                     raise e
             if empty_ids:
                 texts_without_metadatas = [texts[j] for j in empty_ids]
diff --git a/libs/partners/chroma/pyproject.toml b/libs/partners/chroma/pyproject.toml
@@ -64,6 +64,7 @@ target-version = "py39"
 [tool.ruff.lint]
 select = [
     "A",      # flake8-builtins
+    "B",      # flake8-bugbear
     "ASYNC",  # flake8-async
     "C4",     # flake8-comprehensions
     "COM",    # flake8-commas
diff --git a/libs/partners/chroma/tests/integration_tests/test_vectorstores.py b/libs/partners/chroma/tests/integration_tests/test_vectorstores.py
@@ -787,7 +787,7 @@ def test_collection_none_after_delete(
         _ = vectorstore._collection
     with pytest.raises(Exception, match="does not exist"):
         vectorstore._client.get_collection("test_collection")
-    with pytest.raises(Exception):
+    with pytest.raises(Exception):  # noqa: B017
         vectorstore.similarity_search("foo")
 
 
diff --git a/libs/partners/groq/langchain_groq/chat_models.py b/libs/partners/groq/langchain_groq/chat_models.py
@@ -418,7 +418,8 @@ def build_extra(cls, values: dict[str, Any]) -> Any:
                 warnings.warn(
                     f"""WARNING! {field_name} is not default parameter.
                     {field_name} was transferred to model_kwargs.
-                    Please confirm that {field_name} is what you intended."""
+                    Please confirm that {field_name} is what you intended.""",
+                    stacklevel=2,
                 )
                 extra[field_name] = values.pop(field_name)
 
diff --git a/libs/partners/groq/pyproject.toml b/libs/partners/groq/pyproject.toml
@@ -46,6 +46,7 @@ target-version = "py39"
 [tool.ruff.lint]
 select = [
     "A",      # flake8-builtins
+    "B",      # flake8-bugbear
     "ASYNC",  # flake8-async
     "C4",     # flake8-comprehensions
     "COM",    # flake8-commas
diff --git a/libs/partners/huggingface/langchain_huggingface/embeddings/huggingface_endpoint.py b/libs/partners/huggingface/langchain_huggingface/embeddings/huggingface_endpoint.py
@@ -98,12 +98,12 @@ def validate_environment(self) -> Self:
             self.client = client
             self.async_client = async_client
 
-        except ImportError:
+        except ImportError as e:
             msg = (
                 "Could not import huggingface_hub python package. "
                 "Please install it with `pip install huggingface_hub`."
             )
-            raise ImportError(msg)
+            raise ImportError(msg) from e
         return self
 
     def embed_documents(self, texts: list[str]) -> list[list[float]]:
diff --git a/libs/partners/huggingface/langchain_huggingface/llms/huggingface_pipeline.py b/libs/partners/huggingface/langchain_huggingface/llms/huggingface_pipeline.py
diff --git a/libs/partners/huggingface/pyproject.toml b/libs/partners/huggingface/pyproject.toml

Original file line number	Diff line number	Diff line change
`@@ -29,12 +29,12 @@ def _warn_on_import(name: str, replacement: Optional[str] = None) -> None:`
`29`	`29`	`warnings.warn(`
`30`	`30`	`f"Importing {name} from langchain root module is no longer supported. "`
`31`	`31`	`f"Please use {replacement} instead.",`
`32`		`- stacklevel=3,`
	`32`	`+ stacklevel=2,`
`33`	`33`	`)`
`34`	`34`	`else:`
`35`	`35`	`warnings.warn(`
`36`	`36`	`f"Importing {name} from langchain root module is no longer supported.",`
`37`		`- stacklevel=3,`
	`37`	`+ stacklevel=2,`
`38`	`38`	`)`
`39`	`39`
`40`	`40`
Original file line number	Diff line number	Diff line change
`@@ -255,7 +255,7 @@ def raise_callback_manager_deprecation(cls, values: dict) -> Any:`
`255`	`255`	`warnings.warn(`
`256`	`256`	`"callback_manager is deprecated. Please use callbacks instead.",`
`257`	`257`	`DeprecationWarning,`
`258`		`- stacklevel=4,`
	`258`	`+ stacklevel=2,`
`259`	`259`	`)`
`260`	`260`	`values["callbacks"] = values.pop("callback_manager", None)`
`261`	`261`	`return values`
Original file line number	Diff line number	Diff line change
`@@ -504,7 +504,7 @@ def raise_deprecation(cls, values: dict) -> Any:`
`504`	`504`	`warnings.warn(`
`505`	`505`	"`ChatVectorDBChain` is deprecated - "
`506`	`506`	"please use `from langchain.chains import ConversationalRetrievalChain`",
`507`		`- stacklevel=4,`
	`507`	`+ stacklevel=2,`
`508`	`508`	`)`
`509`	`509`	`return values`
`510`	`510`
Original file line number	Diff line number	Diff line change
`@@ -112,7 +112,7 @@ def raise_deprecation(cls, values: dict) -> Any:`
`112`	`112`	`"Directly instantiating an LLMCheckerChain with an llm is deprecated. "`
`113`	`113`	`"Please instantiate with question_to_checked_assertions_chain "`
`114`	`114`	`"or using the from_llm class method.",`
`115`		`- stacklevel=5,`
	`115`	`+ stacklevel=2,`
`116`	`116`	`)`
`117`	`117`	`if (`
`118`	`118`	`"question_to_checked_assertions_chain" not in values`
Original file line number	Diff line number	Diff line change
`@@ -177,7 +177,7 @@ def raise_deprecation(cls, values: dict) -> Any:`
`177`	`177`	`"Directly instantiating an LLMMathChain with an llm is deprecated. "`
`178`	`178`	`"Please instantiate with llm_chain argument or using the from_llm "`
`179`	`179`	`"class method.",`
`180`		`- stacklevel=5,`
	`180`	`+ stacklevel=2,`
`181`	`181`	`)`
`182`	`182`	`if "llm_chain" not in values and values["llm"] is not None:`
`183`	`183`	`prompt = values.get("prompt", PROMPT)`
Original file line number	Diff line number	Diff line change
`@@ -118,7 +118,7 @@ def raise_deprecation(cls, values: dict) -> Any:`
`118`	`118`	`"Directly instantiating an LLMSummarizationCheckerChain with an llm is "`
`119`	`119`	`"deprecated. Please instantiate with"`
`120`	`120`	`" sequential_chain argument or using the from_llm class method.",`
`121`		`- stacklevel=5,`
	`121`	`+ stacklevel=2,`
`122`	`122`	`)`
`123`	`123`	`if "sequential_chain" not in values and values["llm"] is not None:`
`124`	`124`	`values["sequential_chain"] = _load_sequential_chain(`