Added more advanced ruff config

.github/workflows/ci.yml

@@ -27,7 +27,7 @@ jobs:
       - name: Install uv
         run: curl -LsSf https://astral.sh/uv/install.sh | sh
       - name: Install dependencies
-        run: uv sync --group lint
+        run: uv sync --group code-quality
       - name: Run linter
         run: uv run ruff check
       - name: Run formatter

.pre-commit-config.yaml

@@ -1,6 +1,6 @@
 repos:
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.12.1
+    rev: v0.12.12
     hooks:
       # Run the linter
       - id: ruff
@@ -16,7 +16,7 @@ repos:
         language: system
 
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.6.0
+    rev: v6.0.0
     hooks:
       - id: trailing-whitespace
       - id: end-of-file-fixer

app/config.py

@@ -1,15 +1,13 @@
-from pathlib import Path
 from functools import lru_cache
+from pathlib import Path
 
-from pydantic import AnyHttpUrl, ValidationInfo, field_validator, SecretStr
+from pydantic import AnyHttpUrl, SecretStr, field_validator
 from pydantic_settings import BaseSettings, SettingsConfigDict
 
-from app.utils.config_utils import EncryptedField, EnvironmentType
+from app.utils.config_utils import EnvironmentType
 
 
 class Settings(BaseSettings):
-    # FERNET_DECRYPTOR: FernetDecryptorField = Field("MASTER_KEY")
-
     PROJECT_NAME: str = "MCP Server"
     API_V1_STR: str = "/api/v1"
     VERSION: str = "0.0.1"
@@ -39,17 +37,12 @@ class Settings(BaseSettings):
     RAW_XML_PATH: str = "raw.xml"
     XML_SAMPLE_SIZE: int = 1000
 
-    @field_validator("*", mode="after")
-    def _decryptor(cls, v, validation_info: ValidationInfo, *args, **kwargs):
-        if isinstance(v, EncryptedField):
-            return v.get_decrypted_value(validation_info.data["FERNET_DECRYPTOR"])
-        return v
-
     @field_validator("BACKEND_CORS_ORIGINS", mode="after")
+    @classmethod
     def assemble_cors_origins(cls, v: str | list[str]) -> list[str] | str:
         if isinstance(v, str) and not v.startswith("["):
             return [i.strip() for i in v.split(",")]
-        elif isinstance(v, (list, str)):
+        if isinstance(v, (list, str)):
             return v
         raise ValueError(v)
 
@@ -61,7 +54,7 @@ def assemble_cors_origins(cls, v: str | list[str]) -> list[str] | str:
 
 @lru_cache
 def get_settings() -> Settings:
-    return Settings()
+    return Settings()  # type: ignore[call-arg
 
 
 settings = get_settings()

app/main.py

@@ -2,9 +2,8 @@
 
 from fastmcp import FastMCP
 
-from app.mcp.v1.mcp import mcp_router
 from app.config import settings
-
+from app.mcp.v1.mcp import mcp_router
 
 print("SETUP -> Setting up the app", file=sys.stderr)
 mcp = FastMCP(settings.PROJECT_NAME)

app/mcp/v1/mcp.py

@@ -1,6 +1,6 @@
 from fastmcp import FastMCP
 
-from app.mcp.v1.tools import xml_reader, es_reader, ch_reader, duckdb_reader
+from app.mcp.v1.tools import ch_reader, duckdb_reader, es_reader, xml_reader
 
 mcp_router = FastMCP(name="Main MCP")
 

app/mcp/v1/tools/ch_reader.py

@@ -1,12 +1,13 @@
 from typing import Any
+
 from fastmcp import FastMCP
 
-from app.schemas.record import RecordType, IntervalType, HealthRecordSearchParams
+from app.schemas.record import HealthRecordSearchParams, IntervalType, RecordType
 from app.services.health.clickhouse import (
     get_health_summary_from_ch,
-    search_health_records_from_ch,
     get_statistics_by_type_from_ch,
     get_trend_data_from_ch,
+    search_health_records_from_ch,
 )
 
 ch_reader_router = FastMCP(name="CH Reader MCP")
@@ -16,7 +17,8 @@
 def get_health_summary_ch() -> dict[str, Any]:
     """
     Get a summary of Apple Health data from ClickHouse.
-    The function returns total record count, record type breakdown, and (optionally) a date range aggregation.
+    The function returns total record count, record type breakdown, and
+    (optionally) a date range aggregation.
 
     Notes for LLM:
     - IMPORTANT - Do not guess, autofill, or assume any missing data.
@@ -38,9 +40,11 @@ def search_health_records_ch(params: HealthRecordSearchParams) -> dict[str, Any]
     - params: HealthRecordSearchParams object containing all search/filter parameters.
 
     Notes for LLMs:
-    - This function should return a list of health record documents (dicts) matching the search criteria.
+    - This function should return a list of health record documents (dicts)
+      matching the search criteria.
     - Each document in the list should represent a single health record as stored in ClickHouse.
-    - If an error occurs, the function should return a list with a single dict containing an 'error' key and the error message.
+    - If an error occurs, the function should return a list with a single dict
+      containing an 'error' key and the error message.
     - Use this to retrieve structured health data for further analysis, filtering, or display.
     - Example source_name: "Rob’s iPhone", "Polar Flow", "Sync Solver".
     - Example date_from/date_to: "2020-01-01T00:00:00+00:00"
@@ -61,7 +65,8 @@ def get_statistics_by_type_ch(record_type: RecordType | str) -> dict[str, Any]:
     Get comprehensive statistics for a specific health record type from ClickHouse.
 
     Parameters:
-    - record_type: The type of health record to analyze. Use RecordType for most frequent types. Use str if that type is beyond RecordType scope.
+    - record_type: The type of health record to analyze. Use RecordType for
+      most frequent types. Use str if that type is beyond RecordType scope.
 
     Returns:
     - record_type: The analyzed record type
@@ -76,12 +81,17 @@ def get_statistics_by_type_ch(record_type: RecordType | str) -> dict[str, Any]:
 
     Notes for LLMs:
     - This function provides comprehensive statistical analysis for any health record type.
-    - The value_statistics object contains all basic statistics (count, min, max, avg, sum) for the 'value' field.
+    - The value_statistics object contains all basic statistics (count, min,
+      max, avg, sum) for the 'value' field.
     - The sources breakdown shows which devices/apps contributed data for this record type.
-    - Example types: "HKQuantityTypeIdentifierStepCount", "HKQuantityTypeIdentifierBodyMassIndex", "HKQuantityTypeIdentifierHeartRate", etc.
-    - Use this function to understand the distribution, range, and trends of specific health metrics.
-    - The function is useful for health analysis, identifying outliers, and understanding data quality.
-    - date_range key for query is commented, since it contained hardcoded from date, but you can use it anyway if you replace startDate with your data.
+    - Example types: "HKQuantityTypeIdentifierStepCount",
+      "HKQuantityTypeIdentifierBodyMassIndex", "HKQuantityTypeIdentifierHeartRate", etc.
+    - Use this function to understand the distribution, range, and trends of
+      specific health metrics.
+    - The function is useful for health analysis, identifying outliers, and
+      understanding data quality.
+    - date_range key for query is commented, since it contained hardcoded from
+      date, but you can use it anyway if you replace startDate with your data.
     - IMPORTANT - Do not guess, autofill, or assume any missing data.
     - When asked for medical advice, ask the user whether he wants to use DuckDB, ClickHouse or
     Elasticsearch.
@@ -100,7 +110,8 @@ def get_trend_data_ch(
     date_to: str | None = None,
 ) -> dict[str, Any]:
     """
-    Get trend data for a specific health record type over time using ClickHouse date histogram aggregation.
+    Get trend data for a specific health record type over time using ClickHouse
+    date histogram aggregation.
 
     Parameters:
     - record_type: The type of health record to analyze (e.g., "HKQuantityTypeIdentifierStepCount")
@@ -120,7 +131,8 @@ def get_trend_data_ch(
     Notes for LLMs:
     - Use this to analyze trends, patterns, and seasonal variations in health data
     - The function automatically handles date filtering if date_from/date_to are provided
-    - IMPORTANT - interval must be one of: "day", "week", "month", or "year". Do not use other values.
+    - IMPORTANT - interval must be one of: "day", "week", "month", or "year".
+      Do not use other values.
     - Do not guess, autofill, or assume any missing data.
     - When asked for medical advice, ask the user whether he wants to use DuckDB, ClickHouse or
     Elasticsearch.

app/mcp/v1/tools/duckdb_reader.py

@@ -1,12 +1,13 @@
 from typing import Any
+
 from fastmcp import FastMCP
 
-from app.schemas.record import RecordType, IntervalType, HealthRecordSearchParams
+from app.schemas.record import HealthRecordSearchParams, IntervalType, RecordType
 from app.services.health.duckdb_queries import (
     get_health_summary_from_duckdb,
-    search_health_records_from_duckdb,
     get_statistics_by_type_from_duckdb,
     get_trend_data_from_duckdb,
+    search_health_records_from_duckdb,
 )
 
 duckdb_reader_router = FastMCP(name="CH Reader MCP")
@@ -16,7 +17,8 @@
 def get_health_summary_duckdb() -> list[dict[str, Any]]:
     """
     Get a summary of Apple Health data from DuckDB.
-    The function returns total record count, record type breakdown, and (optionally) a date range aggregation.
+    The function returns total record count, record type breakdown, and
+    (optionally) a date range aggregation.
 
     Notes for LLM:
     - IMPORTANT - Do not guess, autofill, or assume any missing data.
@@ -38,9 +40,11 @@ def search_health_records_duckdb(params: HealthRecordSearchParams) -> list[dict[
     - params: HealthRecordSearchParams object containing all search/filter parameters.
 
     Notes for LLMs:
-    - This function should return a list of health record documents (dicts) matching the search criteria.
+    - This function should return a list of health record documents (dicts)
+      matching the search criteria.
     - Each document in the list should represent a single health record as stored in ClickHouse.
-    - If an error occurs, the function should return a list with a single dict containing an 'error' key and the error message.
+    - If an error occurs, the function should return a list with a single dict
+      containing an 'error' key and the error message.
     - Use this to retrieve structured health data for further analysis, filtering, or display.
     - Example source_name: "Rob’s iPhone", "Polar Flow", "Sync Solver".
     - Example date_from/date_to: "2020-01-01T00:00:00+00:00"
@@ -61,7 +65,8 @@ def get_statistics_by_type_duckdb(record_type: RecordType | str) -> list[dict[st
     Get comprehensive statistics for a specific health record type from DuckDB.
 
     Parameters:
-    - record_type: The type of health record to analyze. Use RecordType for most frequent types. Use str if that type is beyond RecordType scope.
+    - record_type: The type of health record to analyze. Use RecordType for
+      most frequent types. Use str if that type is beyond RecordType scope.
 
     Returns:
     - record_type: The analyzed record type
@@ -76,12 +81,17 @@ def get_statistics_by_type_duckdb(record_type: RecordType | str) -> list[dict[st
 
     Notes for LLMs:
     - This function provides comprehensive statistical analysis for any health record type.
-    - The value_statistics object contains all basic statistics (count, min, max, avg, sum) for the 'value' field.
+    - The value_statistics object contains all basic statistics (count, min,
+      max, avg, sum) for the 'value' field.
     - The sources breakdown shows which devices/apps contributed data for this record type.
-    - Example types: "HKQuantityTypeIdentifierStepCount", "HKQuantityTypeIdentifierBodyMassIndex", "HKQuantityTypeIdentifierHeartRate", etc.
-    - Use this function to understand the distribution, range, and trends of specific health metrics.
-    - The function is useful for health analysis, identifying outliers, and understanding data quality.
-    - date_range key for query is commented, since it contained hardcoded from date, but you can use it anyway if you replace startDate with your data.
+    - Example types: "HKQuantityTypeIdentifierStepCount",
+      "HKQuantityTypeIdentifierBodyMassIndex", "HKQuantityTypeIdentifierHeartRate", etc.
+    - Use this function to understand the distribution, range, and trends of
+      specific health metrics.
+    - The function is useful for health analysis, identifying outliers, and
+      understanding data quality.
+    - date_range key for query is commented, since it contained hardcoded from
+      date, but you can use it anyway if you replace startDate with your data.
     - IMPORTANT - Do not guess, autofill, or assume any missing data.
     - When asked for medical advice, ask the user whether he wants to use DuckDB, ClickHouse or
     Elasticsearch.
@@ -100,7 +110,8 @@ def get_trend_data_duckdb(
     date_to: str | None = None,
 ) -> list[dict[str, Any]]:
     """
-    Get trend data for a specific health record type over time using DuckDB date histogram aggregation.
+    Get trend data for a specific health record type over time using DuckDB
+    date histogram aggregation.
 
     Parameters:
     - record_type: The type of health record to analyze (e.g., "HKQuantityTypeIdentifierStepCount")
@@ -120,7 +131,8 @@ def get_trend_data_duckdb(
     Notes for LLMs:
     - Use this to analyze trends, patterns, and seasonal variations in health data
     - The function automatically handles date filtering if date_from/date_to are provided
-    - IMPORTANT - interval must be one of: "day", "week", "month", or "year". Do not use other values.
+    - IMPORTANT - interval must be one of: "day", "week", "month", or "year".
+      Do not use other values.
     - Do not guess, autofill, or assume any missing data.
     - When asked for medical advice, ask the user whether he wants to use DuckDB, ClickHouse or
     Elasticsearch.

app/mcp/v1/tools/es_reader.py

@@ -1,12 +1,13 @@
 from typing import Any
+
 from fastmcp import FastMCP
 
-from app.schemas.record import RecordType, IntervalType, HealthRecordSearchParams
+from app.schemas.record import HealthRecordSearchParams, IntervalType, RecordType
 from app.services.health.elasticsearch import (
     get_health_summary_from_es,
-    search_health_records_logic,
     get_statistics_by_type_logic,
     get_trend_data_logic,
+    search_health_records_logic,
 )
 
 es_reader_router = FastMCP(name="ES Reader MCP")
@@ -16,7 +17,8 @@
 def get_health_summary_es() -> dict[str, Any]:
     """
     Get a summary of Apple Health data from Elasticsearch.
-    The function returns total record count, record type breakdown, and (optionally) a date range aggregation.
+    The function returns total record count, record type breakdown, and
+    (optionally) a date range aggregation.
 
     Notes for LLM:
     - IMPORTANT - Do not guess, auto-fill, or assume any missing data.
@@ -38,9 +40,11 @@ def search_health_records_es(params: HealthRecordSearchParams) -> list[dict[str,
     - params: HealthRecordSearchParams object containing all search/filter parameters.
 
     Notes for LLMs:
-    - This function should return a list of health record documents (dicts) matching the search criteria.
+    - This function should return a list of health record documents (dicts)
+      matching the search criteria.
     - Each document in the list should represent a single health record as stored in Elasticsearch.
-    - If an error occurs, the function should return a list with a single dict containing an 'error' key and the error message.
+    - If an error occurs, the function should return a list with a single dict
+      containing an 'error' key and the error message.
     - Use this to retrieve structured health data for further analysis, filtering, or display.
     - Example source_name: "Rob’s iPhone", "Polar Flow", "Sync Solver".
     - Example date_from/date_to: "2020-01-01T00:00:00+00:00"
@@ -61,7 +65,8 @@ def get_statistics_by_type_es(record_type: RecordType | str) -> dict[str, Any]:
     Get comprehensive statistics for a specific health record type from Elasticsearch.
 
     Parameters:
-    - record_type: The type of health record to analyze. Use RecordType for most frequent types. Use str if that type is beyond RecordType scope.
+    - record_type: The type of health record to analyze. Use RecordType for
+      most frequent types. Use str if that type is beyond RecordType scope.
 
     Returns:
     - record_type: The analyzed record type
@@ -76,12 +81,17 @@ def get_statistics_by_type_es(record_type: RecordType | str) -> dict[str, Any]:
 
     Notes for LLMs:
     - This function provides comprehensive statistical analysis for any health record type.
-    - The value_statistics object contains all basic statistics (count, min, max, avg, sum) for the 'value' field.
+    - The value_statistics object contains all basic statistics (count, min,
+      max, avg, sum) for the 'value' field.
     - The sources breakdown shows which devices/apps contributed data for this record type.
-    - Example types: "HKQuantityTypeIdentifierStepCount", "HKQuantityTypeIdentifierBodyMassIndex", "HKQuantityTypeIdentifierHeartRate", etc.
-    - Use this function to understand the distribution, range, and trends of specific health metrics.
-    - The function is useful for health analysis, identifying outliers, and understanding data quality.
-    - date_range key for query is commented, since it contained hardcoded from date, but you can use it anyway if you replace startDate with your data.
+    - Example types: "HKQuantityTypeIdentifierStepCount",
+      "HKQuantityTypeIdentifierBodyMassIndex", "HKQuantityTypeIdentifierHeartRate", etc.
+    - Use this function to understand the distribution, range, and trends of
+      specific health metrics.
+    - The function is useful for health analysis, identifying outliers, and
+      understanding data quality.
+    - date_range key for query is commented, since it contained hardcoded from
+      date, but you can use it anyway if you replace startDate with your data.
     - IMPORTANT - Do not guess, auto-fill, or assume any missing data.
     - When asked for medical advice, ask the user whether he wants to use DuckDB, ClickHouse or
     Elasticsearch.
@@ -100,7 +110,8 @@ def get_trend_data_es(
     date_to: str | None = None,
 ) -> dict[str, Any]:
     """
-    Get trend data for a specific health record type over time using Elasticsearch date histogram aggregation.
+    Get trend data for a specific health record type over time using
+    Elasticsearch date histogram aggregation.
 
     Parameters:
     - record_type: The type of health record to analyze (e.g., "HKQuantityTypeIdentifierStepCount")
@@ -120,7 +131,8 @@ def get_trend_data_es(
     Notes for LLMs:
     - Use this to analyze trends, patterns, and seasonal variations in health data
     - The function automatically handles date filtering if date_from/date_to are provided
-    - IMPORTANT - interval must be one of: "day", "week", "month", or "year". Do not use other values.
+    - IMPORTANT - interval must be one of: "day", "week", "month", or "year".
+      Do not use other values.
     - Do not guess, auto-fill, or assume any missing data.
     - When asked for medical advice, ask the user whether he wants to use DuckDB, ClickHouse or
     Elasticsearch.