Add optional blake3 hashing during asset scanning

- Make blake3 import lazy in hashing.py (only imported when needed)
- Add compute_hashes parameter to AssetSeeder.start(), build_asset_specs(), and seed_assets()
- Fix missing tag clearing: include is_missing states in sync when update_missing_tags=True
- Clear is_missing flag on cache states when files are restored with matching mtime/size
- Fix validation error serialization in routes.py (use json.loads(ve.json()))

Amp-Thread-ID: https://ampcode.com/threads/T-019c3614-56d4-74a8-a717-19922d6dbbee
Co-authored-by: Amp <amp@ampcode.com>
This commit is contained in:
Luke Mino-Altherr
2026-02-06 19:22:56 -08:00
parent 7a75af59ab
commit a2d26dece5
11 changed files with 119 additions and 52 deletions

View File

@@ -2,10 +2,23 @@ import asyncio
import os
from typing import IO
from blake3 import blake3
DEFAULT_CHUNK = 8 * 1024 * 1024
_blake3 = None
def _get_blake3():
global _blake3
if _blake3 is None:
try:
from blake3 import blake3 as _b3
_blake3 = _b3
except ImportError:
raise ImportError(
"blake3 is required for asset hashing. Install with: pip install blake3"
)
return _blake3
def compute_blake3_hash(
fp: str | IO[bytes],
@@ -42,7 +55,7 @@ def _hash_file_obj(file_obj: IO, chunk_size: int = DEFAULT_CHUNK) -> str:
if orig_pos != 0:
file_obj.seek(0)
h = blake3()
h = _get_blake3()()
while True:
chunk = file_obj.read(chunk_size)
if not chunk: