wip: tool result fixes -- persistence

tools/binary_extensions.py

@@ -0,0 +1,42 @@
+"""Binary file extensions to skip for text-based operations.
+
+These files can't be meaningfully compared as text and are often large.
+Ported from free-code src/constants/files.ts.
+"""
+
+BINARY_EXTENSIONS = frozenset({
+    # Images
+    ".png", ".jpg", ".jpeg", ".gif", ".bmp", ".ico", ".webp", ".tiff", ".tif",
+    # Videos
+    ".mp4", ".mov", ".avi", ".mkv", ".webm", ".wmv", ".flv", ".m4v", ".mpeg", ".mpg",
+    # Audio
+    ".mp3", ".wav", ".ogg", ".flac", ".aac", ".m4a", ".wma", ".aiff", ".opus",
+    # Archives
+    ".zip", ".tar", ".gz", ".bz2", ".7z", ".rar", ".xz", ".z", ".tgz", ".iso",
+    # Executables/binaries
+    ".exe", ".dll", ".so", ".dylib", ".bin", ".o", ".a", ".obj", ".lib",
+    ".app", ".msi", ".deb", ".rpm",
+    # Documents (PDF is here; read_file excludes it at the call site)
+    ".pdf", ".doc", ".docx", ".xls", ".xlsx", ".ppt", ".pptx",
+    ".odt", ".ods", ".odp",
+    # Fonts
+    ".ttf", ".otf", ".woff", ".woff2", ".eot",
+    # Bytecode / VM artifacts
+    ".pyc", ".pyo", ".class", ".jar", ".war", ".ear", ".node", ".wasm", ".rlib",
+    # Database files
+    ".sqlite", ".sqlite3", ".db", ".mdb", ".idx",
+    # Design / 3D
+    ".psd", ".ai", ".eps", ".sketch", ".fig", ".xd", ".blend", ".3ds", ".max",
+    # Flash
+    ".swf", ".fla",
+    # Lock/profiling data
+    ".lockb", ".dat", ".data",
+})
+
+
+def has_binary_extension(path: str) -> bool:
+    """Check if a file path has a binary extension. Pure string check, no I/O."""
+    dot = path.rfind(".")
+    if dot == -1:
+        return False
+    return path[dot:].lower() in BINARY_EXTENSIONS