Lint print breakpoint (#1267)

Author: ahuang11

.pre-commit-config.yaml

@@ -23,6 +23,20 @@ repos:
     hooks:
       - id: isort
         name: isort (python)
+-   repo: https://github.com/pre-commit/pygrep-hooks
+    rev: v1.10.0
+    hooks:
+      - id: python-no-log-warn
+      - id: python-use-type-annotations
+    # Custom hook to catch breakpoint() calls
+-   repo: local
+    hooks:
+      - id: no-breakpoint
+        name: No breakpoint() calls
+        entry: breakpoint\(
+        language: pygrep
+        files: \.py$
+        types: [python]
 -   repo: https://github.com/shssoichiro/oxipng
     rev: v9.1.3
     hooks:

lumen/ai/llm.py

@@ -345,8 +345,8 @@ def warmup(cls, model_kwargs: dict | None):
             return
 
         from huggingface_hub import hf_hub_download
-        print(f"{cls.__name__} provider is downloading following models:\n\n{json.dumps(huggingface_models, indent=2)}")
-        for model, kwargs in model_kwargs.items():
+        print(f"{cls.__name__} provider is downloading following models:\n\n{json.dumps(huggingface_models, indent=2)}")  # noqa: T201
+        for kwargs in model_kwargs.values():
             repo = kwargs.get('repo', kwargs.get('repo_id'))
             model_file = kwargs.get('model_file')
             hf_hub_download(repo, model_file)
@@ -703,11 +703,11 @@ async def run_client(self, model_spec: str | dict, messages: list[Message], **kw
         """Override to handle Gemini-specific message format conversion."""
         try:
             from google.genai.types import GenerateContentConfig
-        except ImportError:
+        except ImportError as exc:
             raise ImportError(
                 "Please install the `google-generativeai` package to use Google AI models. "
                 "You can install it with `pip install -U google-genai`."
-            )
+            ) from exc
 
         client = await self.get_client(model_spec, **kwargs)
 

lumen/ai/schemas.py

@@ -81,7 +81,7 @@ def _generate_context(self, truncate: bool | None = None) -> str:
                 original_indices = list(range(len(cols_to_show)))
                 show_ellipsis = False
 
-            for i, (col, orig_idx) in enumerate(zip(cols_to_show, original_indices)):
+            for i, (col, orig_idx) in enumerate(zip(cols_to_show, original_indices, strict=False)):
                 if show_ellipsis and i == len(cols_to_show) // 2:
                     context += "...\n"
 
@@ -188,7 +188,7 @@ def _generate_context(self, truncate: bool | None = None) -> str:
                 original_indices = list(range(len(cols_to_show)))
                 show_ellipsis = False
 
-            for i, (col, orig_idx) in enumerate(zip(cols_to_show, original_indices)):
+            for i, (col, orig_idx) in enumerate(zip(cols_to_show, original_indices, strict=False)):
                 if show_ellipsis and i == len(cols_to_show) // 2:
                     context += "...\n"
 

lumen/ai/tools.py

@@ -529,7 +529,7 @@ def _format_results_for_refinement(self, results: list[dict[str, Any]]) -> str:
             Formatted description of document results
         """
         formatted_results = []
-        for i, result in enumerate(results):
+        for _i, result in enumerate(results):
             metadata = result.get('metadata', {})
             filename = metadata.get('filename', 'Unknown document')
             text_preview = truncate_string(result.get('text', ''), max_length=150)
@@ -670,7 +670,7 @@ def _format_results_for_refinement(self, results: list[dict[str, Any]]) -> str:
             Formatted description of table results
         """
         formatted_results = []
-        for i, result in enumerate(results):
+        for _i, result in enumerate(results):
             source_name = result['metadata'].get("source", "unknown")
             table_name = result['metadata'].get("table_name", "unknown")
             text = result["text"]

lumen/ai/translate.py

@@ -510,8 +510,8 @@ def pydantic_to_param_instance(model: BaseModel) -> param.Parameterized:
     try:
         parameterized_class = model._parameterized  # type: ignore
         valid_param_names = set(parameterized_class.param)
-    except AttributeError:
-        raise ValueError("The provided model does not have a _parameterized attribute, indicating it was not created from a param.Parameterized class.")
+    except AttributeError as exc:
+        raise ValueError("The provided model does not have a _parameterized attribute, indicating it was not created from a param.Parameterized class.") from exc
 
     kwargs = {}
     for key, value in model:
@@ -590,7 +590,7 @@ def function_to_model(function: FunctionType, skipped: list[str] | None = None)
     fields: dict[str, tuple[Any, FieldInfo]] = {}  # Changed core_schema.TypedDictField to tuple[Any, FieldInfo] for create_model
     description, field_descriptions = doc_descriptions(function, sig)
 
-    for index, (name, p) in enumerate(sig.parameters.items()):
+    for _index, (name, p) in enumerate(sig.parameters.items()):
         if p.annotation is sig.empty:
             annotation = Any
         else:

lumen/ai/ui.py

@@ -192,7 +192,7 @@ def __init__(
             self._notebook_export, *(
                 Button(
                     name=label, button_type='primary',
-                    on_click=lambda _: e(self.interface),
+                    on_click=lambda _, e=e: e(self.interface),
                     stylesheets=['.bk-btn { padding: 4.5px 6px;']
                 )
                 for label, e in self.export_functions.items()
@@ -591,7 +591,7 @@ def _set_conversation(self, conversation: list[Any]):
     async def _cleanup_explorations(self, event):
         if len(event.new) <= len(event.old):
             return
-        for i, (old, new) in enumerate(zip(event.old, event.new)):
+        for i, (old, new) in enumerate(zip(event.old, event.new, strict=False)):
             if old is new:
                 continue
             self._contexts.pop(i)

lumen/ai/utils.py

@@ -318,7 +318,7 @@ async def get_schema(
     count = schema.pop("__len__", None)
 
     if not include_type:
-        for field, spec in schema.items():
+        for spec in schema.values():
             if "type" in spec:
                 spec.pop("type")
 
@@ -387,7 +387,7 @@ async def get_schema(
                 continue
 
     # Format any other numeric values in the schema
-    for field, spec in schema.items():
+    for spec in schema.values():
         for key, value in spec.items():
             if isinstance(value, (int, float)) and key not in ['type']:
                 spec[key] = format_float(value)

lumen/ai/vector_store.py

@@ -167,10 +167,6 @@ async def _generate_context(self, document: str, chunk: str, previous_context: s
         if isinstance(response, str):
             return response
         else:
-            print(
-                f"Used: {response.usage.prompt_tokens} total tokens ({response.usage.prompt_tokens_details.cached_tokens} cached) and output {response.usage.completion_tokens}"
-            )
-            print("\n\n")
             return response.choices[0].message.content
 
     @pn_cache
@@ -1059,7 +1055,7 @@ def _setup_database(self, embedding_dim: int) -> None:
             "class": self.embeddings.__class__.__module__ + "." + self.embeddings.__class__.__name__,
             "params": {}
         }
-        for param_name, param_obj in self.embeddings.param.objects().items():
+        for param_name, _param_obj in self.embeddings.param.objects().items():
             if param_name not in ['name']:
                 value = getattr(self.embeddings, param_name)
                 if isinstance(value, (str, int, float, bool, list, dict)) or value is None:

lumen/ai/views.py

@@ -164,7 +164,7 @@ async def render(self):
             value=True, name="Rendering component...", height=50, width=50
         )
 
-        if self.render_output and (self.active != (len(self._main)-1)) or self.spec is None:
+        if (self.render_output and (self.active != (len(self._main)-1))) or self.spec is None:
             return
 
         if self.spec in self._last_output:
@@ -235,8 +235,8 @@ def process_error(err):
                 # $.encoding.x.sort: '-host_count' is not one of ..
                 #$.encoding.x: 'value' is a required property
                 if (
-                    last_path != path
-                    and last_path.split(path)[-1].count(".") <= 1
+                    (last_path != path
+                    and last_path.split(path)[-1].count(".") <= 1)
                     or path in rejected_paths
                 ):
                     rejected_paths.add(path)
@@ -271,7 +271,7 @@ def _validate_spec(cls, spec):
             spec_copy.pop("params", None)
             vega_lite_validator.validate(spec_copy)
         except ValidationError as e:
-            raise ValidationError(cls._format_validation_error(e))
+            raise ValidationError(cls._format_validation_error(e)) from e
         return super()._validate_spec(spec)
 
     def __str__(self):

lumen/base.py

@@ -331,7 +331,7 @@ def _validate_dict_or_list_subtypes(
     def _deprecation(
         cls, msg: str, key: str, spec: dict[str, Any], update: dict[str, Any]
     ):
-        warnings.warn(msg, DeprecationWarning)
+        warnings.warn(msg, DeprecationWarning, stacklevel=2)
         if key not in spec:
             spec[key] = {}
         spec[key].update(update)
@@ -360,7 +360,7 @@ def _validate_param(cls, key: str, value: Any, spec: dict[str, Any]):
             pobj._validate(value)
         except Exception as e:
             msg = f"{cls.__name__} component {key!r} value failed validation: {e!s}"
-            raise ValidationError(msg, spec, key)
+            raise ValidationError(msg, spec, key) from e
 
     @classmethod
     def _is_component_key(cls, key: str) -> bool:
@@ -615,7 +615,7 @@ def _import_module(cls, component_type: str):
                     f"component '{component_type}', the '{e.name}' package "
                     "must be installed."
                 )
-                raise ImportError(msg)
+                raise ImportError(msg) from e
 
     @classmethod
     def _get_type(