mirror of
https://github.com/wiltodelta/remove-ai-watermarks.git
synced 2026-10-14 13:30:55 +02:00
Authenticate C2PA registry-sync GitHub API calls to fix CI rate-limiting
scripts/sync_c2pa_soft_bindings.py --check hits api.github.com to resolve the latest upstream commit SHA, unauthenticated. That endpoint's 60/hour rate limit is per source IP, which GitHub Actions runners exhaust fast since many workflows share the runner IP pool -- this was failing the lint job with "403: rate limit exceeded" on every push regardless of whether the change touched anything related. Send an Authorization: Bearer header built from GITHUB_TOKEN/GH_TOKEN when set, scoped to api.github.com only (raw.githubusercontent.com is a separate, much higher-limit CDN and doesn't need it). Wire the workflow's own GITHUB_TOKEN secret into that step's env so CI actually has one to send, raising the limit to 5000/hour. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
This commit is contained in:
1 parent
be8f24c7cb
commit
e3bbe88155
3 files changed
+49
-1
No files matched your search
@@ -7,6 +7,7 @@ import argparse
|
||||
import hashlib
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
import re
|
||||
import sys
|
||||
from dataclasses import dataclass
|
||||
@@ -54,7 +55,18 @@ class RegistryRow:
|
||||
def _read_bytes(source: str) -> bytes:
|
||||
parsed = urlparse(source)
|
||||
if parsed.scheme in {"http", "https"}:
|
||||
request = Request(source, headers={"User-Agent": "remove-ai-watermarks-c2pa-registry-sync"})
|
||||
headers = {"User-Agent": "remove-ai-watermarks-c2pa-registry-sync"}
|
||||
# api.github.com rate-limits unauthenticated requests to 60/hour PER SOURCE IP,
|
||||
# which CI runners exhaust fast since many workflows across many repos share
|
||||
# GitHub's runner IP pool -- a 403 "rate limit exceeded" here is that, not an
|
||||
# outage. A GITHUB_TOKEN (Actions injects one into every run; export it as an
|
||||
# env var to reach this process) raises the same endpoint to 5000/hour.
|
||||
# raw.githubusercontent.com is a separate, much higher-limit CDN and does not
|
||||
# need this.
|
||||
token = os.environ.get("GITHUB_TOKEN") or os.environ.get("GH_TOKEN")
|
||||
if token and parsed.hostname == "api.github.com":
|
||||
headers["Authorization"] = f"Bearer {token}"
|
||||
request = Request(source, headers=headers)
|
||||
with urlopen(request, timeout=30) as response:
|
||||
return response.read()
|
||||
return Path(source).read_bytes()
|
||||
|
||||
Reference in new issue
Block a user