fix: verify raw source bytes and bound reads after file changes

src/micro_scout/index.py

@@ -12,7 +12,7 @@ from typing import TYPE_CHECKING
 
 import numpy as np
 
-from micro_scout.symbols import Symbol, build_edges, parse_source, source_paths
+from micro_scout.symbols import Symbol, build_edges, parse_source, read_source, source_paths
 from micro_scout.text import digest
 
 if TYPE_CHECKING:
@@ -68,8 +68,8 @@ def build_index(
     for path in source_paths(root):
         relative = path.relative_to(root).as_posix()
         try:
-            text = path.read_text(encoding="utf-8")
-        except (UnicodeError, OSError) as exc:
+            text = read_source(path)
+        except (ValueError, OSError) as exc:
             warnings.append({"path": relative, "reason": type(exc).__name__})
             continue
         files[relative] = digest(text)

src/micro_scout/scout.py

@@ -13,7 +13,7 @@ import numpy as np
 
 from micro_scout.index import Index
 from micro_scout.lexical import BM25, reciprocal_rank_fusion, top_indices
-from micro_scout.symbols import EXTENSIONS, Symbol
+from micro_scout.symbols import EXTENSIONS, Symbol, read_source
 from micro_scout.text import digest
 
 if TYPE_CHECKING:
@@ -55,7 +55,7 @@ class Scout:
                     )
                 ):
                     raise ValueError("Source path escapes repository or uses a symlink")
-                text = path.read_text(encoding="utf-8")
+                text = read_source(path)
             except (OSError, UnicodeError) as exc:
                 raise StaleReferenceError(
                     f"Source unavailable: {symbol.path}; rebuild index"

src/micro_scout/symbols.py

@@ -44,6 +44,16 @@ EXCLUDED = {
     ".mypy_cache",
     ".pytest_cache",
 }
+MAX_FILE_BYTES = 1_000_000
+
+
+def read_source(path: Path, max_bytes: int = MAX_FILE_BYTES) -> str:
+    """Read bounded UTF-8 without newline translation, so SHA-256 matches file bytes."""
+    with path.open("rb") as stream:
+        raw = stream.read(max_bytes + 1)
+    if len(raw) > max_bytes:
+        raise ValueError("Source exceeds the file-size limit")
+    return raw.decode("utf-8")
 
 
 @dataclass(frozen=True)
@@ -71,7 +81,7 @@ class Symbol:
         return asdict(self)
 
 
-def source_paths(root: Path, max_file_bytes: int = 1_000_000) -> list[Path]:
+def source_paths(root: Path, max_file_bytes: int = MAX_FILE_BYTES) -> list[Path]:
     """Honor gitignore when available; never traverse symlinks or hidden trees."""
     root = root.resolve(strict=True)
     if not root.is_dir():