fix(registry_gc): correct Gitea packages API + Cloudflare-friendly UA (#2)

scripts/registry_gc.py

@@ -1,42 +1,58 @@
 """Gitea container-registry garbage collection.
 
-Lists package versions for one container package and deletes versions
+Lists tagged versions of one container package and deletes old ones.
-older than --keep-days. Always preserves:
+Always preserves:
 
-  - the :latest tag
+  - the `latest` tag (Watchtower's auto-deploy target)
-  - the --keep-latest most-recent date-tagged versions
+  - the `--keep-latest` most-recent date-tagged versions (YYYY.MM.DD)
-  - anything pushed in the last --keep-days days
+  - the `--keep-latest` most-recent short-SHA tags (rollback pins)
+  - anything pushed within `--keep-days` days
 
-The actual disk reclaim happens on Gitea's next package GC cron (admin
+OCI blob-level versions (`sha256:...`) are never touched directly — those
-site settings). This script just marks the versions for deletion.
+are managed by Gitea's internal package GC cron when their last tag
+goes away.
 
 Usage:
 
-    python scripts/registry_gc.py \\
+    GITEA_TOKEN=... python scripts/registry_gc.py \\
-        --owner <user> \\
+        --owner justin \\
-        --package <product>-docs-mcp \\
+        --package hvm-docs \\
         --keep-days 90 \\
         --keep-latest 5
 
-Auth: reads GITEA_TOKEN from env (set in the workflow as a secret).
+The Gitea endpoint shape (confirmed 2026-05-22 against git.jpaul.io):
+
+    GET    /api/v1/packages/{owner}/container/{package}
+           -> [{id, version, created_at, ...}, ...]
+    DELETE /api/v1/packages/{owner}/container/{package}/{version}
 """
 from __future__ import annotations
 
 import argparse
+import json
 import os
+import re
 import sys
 from datetime import datetime, timedelta, timezone
-from urllib.request import Request, urlopen
 from urllib.error import HTTPError
-import json
+from urllib.parse import quote
-
+from urllib.request import Request, urlopen
 
 GITEA_HOST = os.environ.get("GITEA_HOST", "https://git.jpaul.io")
+DATE_TAG = re.compile(r"^\d{4}\.\d{2}\.\d{2}$")
+SHA_TAG = re.compile(r"^[0-9a-f]{7,40}$")  # short or full git SHA
+BLOB_VER = re.compile(r"^sha256:")          # OCI blob versions — skip
 
 
 def api(token: str, method: str, path: str) -> object:
+    # Explicit User-Agent: git.jpaul.io is behind Cloudflare, whose default
+    # Bot Fight Mode 403s `Python-urllib/X.Y` with error 1010. Any
+    # recognizable browser/curl-style UA passes.
     req = Request(f"{GITEA_HOST}{path}",
-                  headers={"Authorization": f"token {token}"},
+                  headers={
+                      "Authorization": f"token {token}",
+                      "User-Agent": "hvm-docs-registry-gc/1.0",
+                  },
                   method=method)
     try:
         with urlopen(req, timeout=30) as r:
@@ -63,44 +79,57 @@ def main() -> int:
         return 1
 
     versions = api(token, "GET",
-                   f"/api/v1/packages/{args.owner}/container/{args.package}/versions") or []
+                   f"/api/v1/packages/{args.owner}/container/{args.package}") or []
     if not versions:
-        print(f"no versions found for {args.owner}/{args.package}")
+        print(f"no versions found for {args.owner}/container/{args.package}")
         return 0
 
     cutoff = datetime.now(timezone.utc) - timedelta(days=args.keep_days)
+    print(f"  {len(versions)} version(s); cutoff={cutoff.isoformat()}  "
+          f"keep_days={args.keep_days}  keep_latest={args.keep_latest}")
 
-    # Date-tagged versions (YYYY.MM.DD), newest first
+    # Sort newest first by created_at.
-    date_tagged = []
+    def parsed_ts(v: dict) -> datetime:
-    for v in versions:
-        tags = v.get("tags") or []
-        for t in tags:
-            if len(t) == 10 and t[4] == "." and t[7] == ".":
-                date_tagged.append((t, v))
-                break
-    date_tagged.sort(key=lambda kv: kv[0], reverse=True)
-    keep_date_tags = {t for t, _ in date_tagged[:args.keep_latest]}
-
-    deleted = 0
-    for v in versions:
-        tags = v.get("tags") or []
-        if "latest" in tags:
-            continue
-        if any(t in keep_date_tags for t in tags):
-            continue
         try:
-            created = datetime.fromisoformat(v["created_at"].replace("Z", "+00:00"))
+            return datetime.fromisoformat(v["created_at"].replace("Z", "+00:00"))
         except (KeyError, ValueError):
+            return datetime.min.replace(tzinfo=timezone.utc)
+
+    versions.sort(key=parsed_ts, reverse=True)
+
+    # Compute the keep-set: top-N date tags + top-N sha tags + always latest.
+    keep_dates: list[str] = []
+    keep_shas: list[str] = []
+    for v in versions:
+        ver = v.get("version") or ""
+        if DATE_TAG.match(ver) and len(keep_dates) < args.keep_latest:
+            keep_dates.append(ver)
+        elif SHA_TAG.match(ver) and len(keep_shas) < args.keep_latest:
+            keep_shas.append(ver)
+    keep = {"latest", *keep_dates, *keep_shas}
+    print(f"  keep tags: {sorted(keep)}")
+
+    deleted = skipped_blob = skipped_age = skipped_keep = 0
+    for v in versions:
+        ver = v.get("version") or ""
+        ts = parsed_ts(v)
+        if BLOB_VER.match(ver):
+            skipped_blob += 1
             continue
-        if created >= cutoff:
+        if ver in keep:
+            skipped_keep += 1
             continue
-        version_id = v.get("id")
+        if ts >= cutoff:
-        print(f"  deleting v{version_id}  tags={tags}  created={v['created_at']}")
+            skipped_age += 1
+            continue
+        print(f"  deleting {ver!r}  id={v.get('id')}  created={v.get('created_at')}")
         if not args.dry_run:
             api(token, "DELETE",
-                f"/api/v1/packages/{args.owner}/container/{args.package}/versions/{version_id}")
+                f"/api/v1/packages/{args.owner}/container/{args.package}/{quote(ver, safe='')}")
             deleted += 1
-    print(f"done: {deleted} version(s) deleted")
+
+    print(f"done: deleted={deleted}  kept_named={skipped_keep}  "
+          f"kept_recent={skipped_age}  skipped_blobs={skipped_blob}")
     return 0