Files
serverAppConfigs/scripts/hf-manifest.py
T
Frank 5bd12d3193 hf-manifest.py: read X-Linked-* headers, never follow the resolve redirect
On Xet-backed repos (Qwen/Qwen3.8-Flash-Next-FP8), the resolve endpoint 302s
to a CDN bridge whose final ETag is the Xet CAS chunk-dag hash, NOT the
content sha256. urllib follows redirects, so the manifest recorded the Xet
hash and every downloaded shard failed sha256 verification against a hash no
download could ever match (8/8 shards FAIL, all sizes correct, on-disk bytes
matching the Tree API's lfs.oid). Classic LFS CDNs serve ETag=sha256, which
is why this was invisible on prior fetches.

Fix: HEAD via http.client, which does not follow redirects. 200 = direct
answer (Content-Length + ETag, non-LFS); 302 = LFS/Xet redirect
(X-Linked-Size + X-Linked-ETag = content sha256). Verified against the FP8
repo: shard model-00002-of-00131 now records 6841fe21..., the sha256 of the
bytes already on disk (cross-checked against the Tree API lfs.oid).
2026-09-26 22:46:24 -07:00

129 lines
4.9 KiB
Python
Executable File

#!/usr/bin/env python3
"""hf-manifest.py — generate an hf-fetch.sh manifest from a HuggingFace repo.
Usage: python3 scripts/hf-manifest.py <owner/repo> [outfile]
Lists the repo tree via the HF API and, for each file, records the size and
the content sha256. LFS and Xet-backed files redirect the resolve endpoint to
a CDN (302), whose own headers carry the truth: X-Linked-Size is the byte
count and X-Linked-ETag is the sha256 of the file's bytes. The redirect must
NOT be followed: on Xet-backed repos the bridge answers with ETag = the Xet
CAS chunk-dag hash, which is NOT the content sha256 (seen on
Qwen/Qwen3.8-Flash-Next-FP8, 2026-09-26: every shard "failed" verification
against a hash no download could ever match). Non-LFS files (config.json,
tokenizer, ...) are answered directly (200) and carry no 64-hex etag, so they
get a blank hash field — hf-fetch.sh then checks size only for them.
Output: one line per file, three space-separated fields:
<filename> <size_bytes> <sha256-or-blank>
Token: $HF_TOKEN, else ~/.cache/huggingface/token, else the llamaswap conf
(grep hf_...). Gated repos need a token that has been granted access.
"""
import http.client
import json
import os
import re
import sys
import urllib.request
from urllib.parse import urlsplit
def get_token():
t = os.environ.get("HF_TOKEN", "")
if not t:
p = os.path.expanduser("~/.cache/huggingface/token")
if os.path.exists(p):
with open(p) as f:
t = f.read().strip()
if not t:
p = os.path.expanduser("~/.config/llamaswap.conf.yaml")
if os.path.exists(p):
with open(p) as f:
m = re.search(r"hf_[a-zA-Z0-9]+", f.read())
if m:
t = m.group(0)
return t
def head(url, token):
"""HEAD via http.client, which does not follow redirects.
urllib's default opener follows the resolve endpoint's 302, and the Xet
bridge's ETag is the Xet CAS hash, not the content sha256 — so the 302's
own X-Linked-* headers must be read instead. Returns an http.client
response; the caller reads r.status and r.headers.
"""
parts = urlsplit(url)
conn = http.client.HTTPSConnection(parts.netloc, timeout=30)
path = parts.path + (f"?{parts.query}" if parts.query else "")
h = {"User-Agent": "hf-manifest/1.0"}
if token:
h["Authorization"] = f"Bearer {token}"
conn.request("HEAD", path, headers=h)
return conn.getresponse()
def main():
if len(sys.argv) < 2:
print(f"usage: {sys.argv[0]} <owner/repo> [outfile]", file=sys.stderr)
sys.exit(2)
repo = sys.argv[1]
outfile = sys.argv[2] if len(sys.argv) > 2 else None
token = get_token()
# 1. List the repo tree (siblings[].rfilename). Sizes and content sha256s
# come from the resolve endpoint's HEAD (not followed — see head());
# the API's siblings carry only rfilename.
api = f"https://huggingface.co/api/models/{repo}"
req = urllib.request.Request(
api, headers={"User-Agent": "hf-manifest/1.0",
**({"Authorization": f"Bearer {token}"} if token else {})})
with urllib.request.urlopen(req, timeout=30) as r:
meta = json.load(r)
siblings = meta.get("siblings", [])
print(f"# {repo}: {len(siblings)} entries", file=sys.stderr)
lines = []
for s in siblings:
name = s.get("rfilename", "")
if not name or name.endswith("/"):
continue
# 2. Size + content sha256 from the resolve endpoint's HEAD, not
# followed (see head()). 200 = direct answer (Content-Length +
# ETag); 302 = LFS/Xet redirect (X-Linked-Size + X-Linked-ETag =
# the sha256 of the file's bytes). Non-LFS files carry no 64-hex
# etag, so the hash field stays blank (hf-fetch.sh then checks
# size only for them).
size = 0
sha = ""
resolve = f"https://huggingface.co/{repo}/resolve/main/{name}"
try:
with head(resolve, token) as r:
if r.status == 404:
raise FileNotFoundError(name)
if r.status == 200:
size = int(r.headers.get("Content-Length") or 0)
etag = (r.headers.get("ETag") or "").strip('"')
else:
size = int(r.headers.get("X-Linked-Size")
or r.headers.get("Content-Length") or 0)
etag = (r.headers.get("X-Linked-ETag") or "").strip('"')
if re.fullmatch(r"[0-9a-f]{64}", etag):
sha = etag
except FileNotFoundError:
pass
lines.append(f"{name} {size} {sha}")
print(f" {name} {size:>12} {sha or '(size only)'}", file=sys.stderr)
out = "\n".join(lines) + "\n"
if outfile:
with open(outfile, "w") as f:
f.write(out)
print(f"wrote {outfile}", file=sys.stderr)
else:
sys.stdout.write(out)
if __name__ == "__main__":
main()