Add ruff.toml and fix lint errors (imports, type hints, formatting)

- Add ruff.toml to configure lint rules (ignore BLE001/S110/B017 which are
intentional in health checks and error handling)
- Fix import sorting (I001) across api.py, lm.py, sql.py, test_lm.py, test_search.py
- Modernize type hints: Generator[str] instead of Generator[str, None, None]
(UP043), X | None instead of Optional[X] (UP045), collections.abc.Gen
erator instead of typing.Generator (UP035)
- Use str.removeprefix() instead of startswith + slicing (FURB188)
- Use from-module import instead of aliased import (PLR0402)
- Reformat all source and test files with ruff format

ruff.toml

@@ -0,0 +1,7 @@
+target-version = "py313"
+
+[lint]
+# BLE001 – catching Exception is intentional in health checks and error-handling paths
+# S110 – try/except/pass is intentional for health probes that must not crash
+# B017 – pytest.raises(Exception) is acceptable for pydantic validation error checks
+ignore = ["BLE001", "S110", "B017"]

src/gazet/api.py

@@ -1,15 +1,14 @@
 import json
 import logging
 import uuid
+from collections.abc import AsyncIterator, Awaitable, Callable, Generator
 from contextlib import asynccontextmanager
-from collections.abc import AsyncIterator, Awaitable, Callable
-from typing import Any, Generator
-from fastapi.responses import Response
+from typing import Any
 
 import duckdb
 import pandas as pd
 from fastapi import FastAPI, HTTPException, Request
-from fastapi.responses import StreamingResponse
+from fastapi.responses import Response, StreamingResponse
 
 from .export import to_feature_collection
 from .geometry import normalize_geometry_to_geojson
@@ -83,7 +82,7 @@ def _df_to_records(df: pd.DataFrame) -> list[dict[str, Any]]:
 
 def _run_stream(
     base_con: duckdb.DuckDBPyConnection, query: str, backend: str = "gguf"
-) -> Generator[str, None, None]:
+) -> Generator[str]:
     """Yield NDJSON lines as each stage of the search completes.
 
     Event ``type`` values (in order of emission):

src/gazet/geometry.py

@@ -1,5 +1,5 @@
 import json
-from typing import Any, Optional
+from typing import Any
 
 import duckdb
 import pandas as pd
@@ -38,7 +38,7 @@ def normalize_geometry_to_geojson(
     if sample.empty:
         return result_df
 
-    def _simplify(val: Any) -> Optional[str]:
+    def _simplify(val: Any) -> str | None:
         if val is None:
             return None
         if isinstance(val, (bytes, bytearray, memoryview)):

src/gazet/lm.py

@@ -174,8 +174,7 @@ def _postprocess_sql(text: str) -> str:
     cleaned = text.strip()
     if "```sql" in cleaned:
         cleaned = cleaned.split("```sql", 1)[1]
-    if cleaned.startswith("```"):
-        cleaned = cleaned[3:]
+    cleaned = cleaned.removeprefix("```")
     if "```" in cleaned:
         cleaned = cleaned.split("```", 1)[0]
     return cleaned.strip()
@@ -302,8 +301,7 @@ def generate_places(user_query: str) -> PlacesResult:
     # Strip markdown fences if the model wrapped the JSON
     if raw_output.startswith("```"):
         raw_output = raw_output.split("```")[1]
-        if raw_output.startswith("json"):
-            raw_output = raw_output[4:]
+        raw_output = raw_output.removeprefix("json")
         raw_output = raw_output.strip()
 
     try:

src/gazet/sql.py

@@ -1,6 +1,7 @@
 import logging
 import re
-from typing import Any, Generator, Optional
+from collections.abc import Generator
+from typing import Any
 
 import duckdb
 import pandas as pd
@@ -91,7 +92,7 @@ def _normalize_ne_subtypes(sql: str) -> str:
     return sql
 
 
-def _strip_fences(sql: Optional[str]) -> str:
+def _strip_fences(sql: str | None) -> str:
     """Remove markdown code fences that the LM may wrap the SQL in."""
     if not sql:
         return ""
@@ -105,7 +106,7 @@ def _execute_sql(
     sql: str,
     label: str,
     iteration: int,
-) -> Generator[dict[str, Any], None, None]:
+) -> Generator[dict[str, Any]]:
     """Execute SQL and yield result/error events. Shared by both paths."""
     try:
         result_df = con.execute(sql).fetchdf()
@@ -135,7 +136,7 @@ def run_geo_sql_gguf(
     con: duckdb.DuckDBPyConnection,
     user_query: str,
     candidates_df: pd.DataFrame,
-) -> Generator[dict[str, Any], None, None]:
+) -> Generator[dict[str, Any]]:
     """Single-shot text-to-SQL via the finetuned GGUF model (llama-server).
 
     Event types:
@@ -178,7 +179,7 @@ def run_geo_sql_dspy(
     user_query: str,
     candidates_df: pd.DataFrame,
     max_iterations: int = MAX_SQL_ITERATIONS,
-) -> Generator[dict[str, Any], None, None]:
+) -> Generator[dict[str, Any]]:
     """Code-act retry loop using the DSPy SQL writer (Ollama / cloud LM).
 
     Same event types as ``run_geo_sql_gguf``.

tests/test_config.py

@@ -3,7 +3,7 @@
 import os
 from pathlib import Path
 
-import gazet.config as config
+from gazet import config
 
 
 class TestPreferNormalized:

tests/test_lm.py

@@ -1,10 +1,10 @@
 """Tests for gazet.lm — prompt templates, postprocessing, and GGUF helpers."""
 
 from gazet.lm import (
-    _postprocess_sql,
     _PLACES_SYSTEM_PROMPT,
     _SYSTEM_PROMPT_TEMPLATE,
     _USER_PROMPT_TEMPLATE,
+    _postprocess_sql,
 )
 from gazet.schemas import PlacesResult
 

tests/test_search.py

@@ -2,6 +2,7 @@
 
 import pandas as pd
 
+from gazet.schemas import Place
 from gazet.search import (
     get_by_id,
     get_division_by_id,
@@ -10,7 +11,6 @@ from gazet.search import (
     search_divisions_area,
     search_natural_earth,
 )
-from gazet.schemas import Place
 
 
 class TestSearchDivisionsArea: