chore: fix pre commit and run it

.pre-commit-config.yaml

@@ -1,4 +1,3 @@
-
 # See https://pre-commit.com for more information
 # See https://pre-commit.com/hooks.html for more hooks
 repos:
@@ -12,7 +11,7 @@ repos:
       - id: end-of-file-fixer
         description: Makes sure files end in a newline and only a newline.
       - id: check-added-large-files
-        args: ['--maxkb=5000']
+        args: ["--maxkb=5000"]
         description: Prevent giant files from being committed.
       - id: check-case-conflict
         description: Check for files with names that would conflict on case-insensitive filesystems like MacOS/Windows.
@@ -21,10 +20,10 @@ repos:
     hooks:
       - id: pydoclint
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.9.0
+    rev: v0.15.12
     hooks:
-      - id: ruff
-        args: [ --fix ]
+      - id: ruff-check
+        args: [--fix]
       - id: ruff-format
   - repo: local
     hooks:

benchmarks/baselines/ablations.py

@@ -71,7 +71,7 @@ def _evaluate(
 
     for task in tasks:
         query_latencies: list[float] = []
-        results: list[SearchResult]
+        results: list[SearchResult] = []
         for _ in range(_LATENCY_RUNS):
             started = time.perf_counter()
             results = index.search(task.query, top_k=_TOP_K, mode=mode, alpha=alpha)

benchmarks/baselines/coderankembed.py

@@ -3,6 +3,7 @@
 import sys
 import time
 from collections import defaultdict
+from collections.abc import Sequence
 from dataclasses import asdict, dataclass, field
 from pathlib import Path
 
@@ -39,7 +40,7 @@ def __init__(self, model: SentenceTransformer, max_seq_length: int = 512) -> Non
         self._model = model
         self._model.max_seq_length = max_seq_length
 
-    def encode(self, texts: list[str]) -> np.ndarray:
+    def encode(self, texts: Sequence[str]) -> np.ndarray:
         """Encode texts with query or document prompt based on batch size."""
         if len(texts) == 1:
             return self._model.encode(texts, prompt_name="query", batch_size=1)  # type: ignore[return-value]
@@ -77,7 +78,7 @@ def _evaluate(
 
     for task in tasks:
         query_latencies: list[float] = []
-        results: list[SearchResult]
+        results: list[SearchResult] = []
         for _ in range(_LATENCY_RUNS):
             started = time.perf_counter()
             results = index.search(task.query, top_k=_TOP_K, mode=mode)

benchmarks/plot.py

@@ -110,8 +110,7 @@ def _format_ms(v: float, _: object) -> str:
 
 
 def _make_plot(out_path: Path, *, warm: bool = False) -> None:
-    """
-    Generate a speed-vs-quality scatter plot.
+    """Generate a speed-vs-quality scatter plot.
 
     :param out_path: Destination PNG path.
     :param warm: If True, use per-query latency (index pre-built). If False, use index + query latency.

benchmarks/run_benchmark.py

@@ -1,5 +1,4 @@
 import argparse
-import json
 import sys
 import time
 from collections import defaultdict
@@ -54,7 +53,7 @@ def _evaluate(
 
     for task in tasks:
         query_latencies: list[float] = []
-        results: list[SearchResult]
+        results: list[SearchResult] = []
         for _ in range(_LATENCY_RUNS):
             started = time.perf_counter()
             results = index.search(task.query, top_k=_DIRECT_TOP_K)

benchmarks/speed_benchmark.py

@@ -194,7 +194,7 @@ def _bench_colgrep(spec: RepoSpec, tasks: list[Task]) -> tuple[float, tuple[floa
     if proc.returncode != 0:
         print(f"  WARNING: colgrep init failed: {proc.stderr.strip()}", file=sys.stderr)
     if "(0 files)" in proc.stdout or "(0 files)" in proc.stderr:
-        print(f"  SKIP: colgrep indexed 0 files (unsupported language?)", file=sys.stderr)
+        print("  SKIP: colgrep indexed 0 files (unsupported language?)", file=sys.stderr)
         return None
     latencies: list[float] = []
     code_only = spec.language != "bash"

pyproject.toml

@@ -110,7 +110,7 @@ ignore = [
     # Allow Any type
     "ANN401",
     # Pydocstyle ignores
-    "D100", "D101", "D104", "D203", "D212", "D401",
+    "D100", "D101", "D104", "D203", "D213", "D401",
 ]
 
 [tool.pydoclint]

src/semble/index/dense.py

@@ -2,7 +2,6 @@
 import numpy.typing as npt
 from huggingface_hub.utils.tqdm import disable_progress_bars
 from model2vec import StaticModel
-from numpy import typing as npt
 from vicinity.backends.basic import CosineBasicBackend
 from vicinity.datatypes import QueryResult
 from vicinity.utils import normalize