bito-code-review[bot] commented on code in PR #40299: URL: https://github.com/apache/superset/pull/40299#discussion_r3287228259
########## superset/mcp_service/report/schemas.py: ########## @@ -0,0 +1,290 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor license agreements. See the NOTICE file +# distributed with this work for additional information +# regarding copyright ownership. The ASF licenses this file +# to you under the Apache License, Version 2.0 (the +# "License"); you may not use this file except in compliance +# with the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, +# software distributed under the License is distributed on an +# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY +# KIND, either express or implied. See the License for the +# specific language governing permissions and limitations +# under the License. + +""" +Pydantic schemas for report (alerts & reports) related responses. +""" + +from __future__ import annotations + +from datetime import datetime +from typing import Annotated, Any, Dict, List, Literal + +import humanize +from pydantic import ( + BaseModel, + ConfigDict, + Field, + field_validator, + model_serializer, + model_validator, + PositiveInt, +) + +from superset.daos.base import ColumnOperator, ColumnOperatorEnum +from superset.mcp_service.common.cache_schemas import ( + CreatedByMeMixin, + MetadataCacheControl, + OwnedByMeMixin, +) +from superset.mcp_service.constants import DEFAULT_PAGE_SIZE, MAX_PAGE_SIZE +from superset.mcp_service.privacy import filter_user_directory_fields +from superset.mcp_service.system.schemas import PaginationInfo +from superset.mcp_service.utils.schema_utils import ( + parse_json_or_list, + parse_json_or_model_list, +) + + +class ReportFilter(ColumnOperator): + """ + Filter object for report listing. + col: The column to filter on. Must be one of the allowed filter fields. + opr: The operator to use. Must be one of the supported operators. + value: The value to filter by (type depends on col and opr). + """ + + col: Literal[ + "name", + "type", + "active", + "dashboard_id", + "chart_id", + ] = Field( + ..., + description="Column to filter on. Use get_schema(model_type='report') for " + "available filter columns.", + ) + opr: ColumnOperatorEnum = Field( + ..., + description="Operator to use. Use get_schema(model_type='report') for " + "available operators.", + ) + value: str | int | float | bool | List[str | int | float | bool] = Field( + ..., description="Value to filter by (type depends on col and opr)" + ) + + +class ReportInfo(BaseModel): + id: int | None = Field(None, description="Report/Alert ID") + name: str | None = Field(None, description="Report/Alert name") + description: str | None = Field(None, description="Report/Alert description") + type: str | None = Field(None, description="Schedule type: 'Alert' or 'Report'") + active: bool | None = Field(None, description="Whether the schedule is active") + crontab: str | None = Field(None, description="Cron expression for scheduling") + dashboard_id: int | None = Field( + None, description="Associated dashboard ID, if any" + ) + chart_id: int | None = Field(None, description="Associated chart ID, if any") + owners: List[Any] | None = Field( + None, description="List of owners (filtered by privacy controls)" + ) + changed_on: str | datetime | None = Field( + None, description="Last modification timestamp" + ) + changed_on_humanized: str | None = Field( + None, description="Humanized modification time" + ) + created_on: str | datetime | None = Field(None, description="Creation timestamp") + created_on_humanized: str | None = Field( + None, description="Humanized creation time" + ) + model_config = ConfigDict( + from_attributes=True, + ser_json_timedelta="iso8601", + populate_by_name=True, + ) + + @model_serializer(mode="wrap") + def _filter_fields_by_context(self, serializer: Any, info: Any) -> Dict[str, Any]: + """Filter fields based on serialization context. + + If context contains 'select_columns', only include those fields. + Otherwise, include all fields (default behavior). + """ + data = filter_user_directory_fields(serializer(self)) + + if info.context and isinstance(info.context, dict): + select_columns = info.context.get("select_columns") + if select_columns: + requested_fields = set(select_columns) + return {k: v for k, v in data.items() if k in requested_fields} + + return data + + +class ReportList(BaseModel): + reports: List[ReportInfo] + count: int + total_count: int + page: int + page_size: int + total_pages: int + has_previous: bool + has_next: bool + columns_requested: List[str] = Field( + default_factory=list, + description="Requested columns for the response", + ) + columns_loaded: List[str] = Field( + default_factory=list, + description="Columns that were actually loaded for each report", + ) + columns_available: List[str] = Field( + default_factory=list, + description="All columns available for selection via select_columns parameter", + ) + sortable_columns: List[str] = Field( + default_factory=list, + description="Columns that can be used with order_column parameter", + ) + filters_applied: List[ColumnOperator] = Field( + default_factory=list, + description="List of advanced filter dicts applied to the query.", + ) + pagination: PaginationInfo | None = None + timestamp: datetime | None = None + model_config = ConfigDict(ser_json_timedelta="iso8601") + + +class ListReportsRequest(OwnedByMeMixin, CreatedByMeMixin, MetadataCacheControl): + """Request schema for list_reports.""" + + filters: Annotated[ + List[ReportFilter], + Field( + default_factory=list, + description="List of filter objects (column, operator, value). Each " + "filter is an object with 'col', 'opr', and 'value' " + "properties. Cannot be used together with 'search'.", + ), + ] + select_columns: Annotated[ + List[str], + Field( + default_factory=list, + description="List of columns to select. Defaults to common columns if not " + "specified.", + ), + ] + search: Annotated[ + str | None, + Field( + default=None, + description="Text search string to match against report fields. Cannot " + "be used together with 'filters'.", + ), + ] + order_column: Annotated[ + str | None, Field(default=None, description="Column to order results by") + ] + order_direction: Annotated[ + Literal["asc", "desc"], + Field( + default="desc", description="Direction to order results ('asc' or 'desc')" + ), + ] + page: Annotated[ + PositiveInt, + Field(default=1, description="Page number for pagination (1-based)"), + ] + page_size: Annotated[ + int, + Field( + default=DEFAULT_PAGE_SIZE, + gt=0, + le=MAX_PAGE_SIZE, + description=f"Number of items per page (max {MAX_PAGE_SIZE})", + ), + ] + + @field_validator("filters", mode="before") + @classmethod + def parse_filters(cls, v: Any) -> List[ReportFilter]: + """Accept both JSON string and list of objects.""" + return parse_json_or_model_list(v, ReportFilter, "filters") + + @field_validator("select_columns", mode="before") + @classmethod + def parse_columns(cls, v: Any) -> List[str]: + """Accept JSON array, list, or comma-separated string.""" + return parse_json_or_list(v, "select_columns") + + @model_validator(mode="after") + def validate_search_and_filters(self) -> "ListReportsRequest": + """Prevent using both search and filters simultaneously.""" + if self.search and self.filters: + raise ValueError( + "Cannot use both 'search' and 'filters' parameters simultaneously. " + "Use either 'search' for text-based searching across multiple fields, " + "or 'filters' for precise column-based filtering, but not both." + ) + return self + + +class ReportError(BaseModel): + error: str = Field(..., description="Error message") + error_type: str = Field(..., description="Type of error") + timestamp: str | datetime | None = Field(None, description="Error timestamp") + model_config = ConfigDict(ser_json_timedelta="iso8601") + + @classmethod + def create(cls, error: str, error_type: str) -> "ReportError": + """Create a standardized ReportError with timestamp.""" + from datetime import datetime, timezone + + return cls( + error=error, error_type=error_type, timestamp=datetime.now(timezone.utc) + ) + + +class GetReportInfoRequest(MetadataCacheControl): + """Request schema for get_report_info — identifier is a numeric ID only.""" + + identifier: Annotated[ + int, + Field(description="Report/Alert numeric ID"), + ] + + +def _humanize_timestamp(dt: datetime | None) -> str | None: + """Convert a datetime to a humanized string like '2 hours ago'.""" + if dt is None: + return None + now = datetime.now(dt.tzinfo) if dt.tzinfo else datetime.now() Review Comment: <div> <div id="suggestion"> <div id="issue"><b>datetime.now() called without timezone</b></div> <div id="fix"> Add timezone argument to `datetime.now()` call on line 268. Use `datetime.now(dt.tzinfo)` or `datetime.now(timezone.utc)` for consistency. </div> <details> <summary> <b>Code suggestion</b> </summary> <blockquote>Check the AI-generated fix before applying</blockquote> <div id="code"> ````suggestion now = datetime.now(dt.tzinfo) if dt.tzinfo else datetime.now(timezone.utc) ```` </div> </details> </div> <small><i>Code Review Run #840a5b</i></small> </div> --- Should Bito avoid suggestions like this for future reviews? (<a href=https://alpha.bito.ai/home/ai-agents/review-rules>Manage Rules</a>) - [ ] Yes, avoid them -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
