fix: fail closed on incomplete weekly image and CVE surveys

cc-ci-plan/resolve-images.py

@@ -163,7 +163,8 @@ def parse_ref(ref: str) -> dict:
     return {"registry": host, "repo": repo, "tag": tag, "digest": digest}
 
 
-HUB_RECENT_PAGES = int(os.environ.get("RESOLVE_IMAGES_HUB_PAGES", "10"))
+HUB_RECENT_PAGES = int(os.environ.get("RESOLVE_IMAGES_HUB_PAGES", "40"))
+_HUB_TRUNCATED: set[str] = set()
 
 
 def _hub_tag_exists(repo: str, tag: str) -> bool:
@@ -177,10 +178,10 @@ def _hub_tag_exists(repo: str, tag: str) -> bool:
 def _hub_tags(repo: str) -> list[str]:
     """Recently-pushed tags, newest first.
 
-    Popular Docker Hub repos carry many thousands of tags, so a full enumeration is impractical —
-    but it is also unnecessary: a tag NEWER than the one we run must have been pushed AFTER it, so
-    ordering by last_updated and reading a bounded recent window is sufficient to find any upgrade.
-    (ghcr offers no ordering, which is why that path needs a different strategy.)
+    Popular Docker Hub repos carry many thousands of tags, so enumerate a bounded recent window.
+    A rebuilt old tag can displace a newer version from that window, so callers MUST treat a
+    truncated listing with no detected upgrade as unverified, not current. (ghcr offers no recency
+    ordering, which is why that path needs a different strategy.)
     """
     tags, url = [], (f"https://hub.docker.com/v2/repositories/{repo}/tags"
                      f"?page_size=100&ordering=last_updated")
@@ -191,6 +192,8 @@ def _hub_tags(repo: str) -> list[str]:
         url = d.get("next")
         if not url:
             break
+    if url:
+        _HUB_TRUNCATED.add(repo)
     return tags
 
 
@@ -236,15 +239,26 @@ def _oci_tags(host: str, repo: str) -> list[str]:
     hdrs = _oci_bearer(host, repo)
     tags, url = [], f"https://{host}/v2/{repo}/tags/list?n=1000"
     for _ in range(MAX_TAG_PAGES):
-        req = urllib.request.Request(url, headers={"User-Agent": UA, **hdrs})
-        with urllib.request.urlopen(req, timeout=TIMEOUT) as r:
-            tags += (json.load(r) or {}).get("tags") or []
-            link = r.headers.get("Link", "") or ""
+        for attempt in range(RETRIES):
+            req = urllib.request.Request(url, headers={"User-Agent": UA, **hdrs})
+            try:
+                with urllib.request.urlopen(req, timeout=TIMEOUT) as r:
+                    tags += (json.load(r) or {}).get("tags") or []
+                    link = r.headers.get("Link", "") or ""
+                break
+            except urllib.error.HTTPError as e:
+                if e.code not in (429, 503) or attempt == RETRIES - 1:
+                    raise
+                retry_after = e.headers.get("Retry-After") or ""
+                delay = min(int(retry_after) if retry_after.isdigit() else 2 ** (attempt + 1), 60)
+                time.sleep(delay)
         m = re.search(r'<([^>]+)>;\s*rel="next"', link)
         if not m:
             break
         nxt = m.group(1)
         url = f"https://{host}{nxt}" if nxt.startswith("/") else nxt
+    else:
+        raise RuntimeError(f"tag listing truncated after {MAX_TAG_PAGES} pages")
     return tags
 
 
@@ -367,8 +381,9 @@ def resolve(ref: str) -> dict:
     same = [t for t in set(tags) if shape(t) == want and vkey(t)]
     out["candidates"] = len(same)
     if not same:
-        # Not a failure: digest-only pins and `latest`/`stable` have no comparable siblings.
-        out["status"] = "no comparable tags (shape has no numeric siblings)"
+        # A floating or unusual tag cannot prove that an image is current. Keep it visible to
+        # callers rather than letting an empty candidate set become a false UPTODATE verdict.
+        out["status"] = "unverifiable: no comparable numeric tags"
         return out
     newest = max(same, key=vkey)
     out["newest_same_shape"] = newest
@@ -377,6 +392,10 @@ def resolve(ref: str) -> dict:
         if within:
             out["newest_within_major"] = max(within, key=vkey)
     out["upgrade_available"] = bool(cur and vkey(newest) > cur)
+    if (info["registry"] in ("docker.io", "registry-1.docker.io")
+            and info["repo"] in _HUB_TRUNCATED and not out["upgrade_available"]):
+        out["status"] = (f"unverifiable: Docker Hub listing truncated after "
+                         f"{HUB_RECENT_PAGES * 100} recent tags")
     return out
 
 
@@ -436,16 +455,16 @@ def main() -> int:
         "recipe": a.recipe,
         "images": results,
         "upgrades_available": [r["ref"] for r in results if r["upgrade_available"]],
-        "unresolved": [r["ref"] for r in results if r["status"].startswith("error")],
+        "unresolved": [r["ref"] for r in results if r["status"].startswith(("error", "skipped", "unverifiable"))],
         # The whole point: distinguish "checked, current" from "could not check".
-        "all_resolved": not any(r["status"].startswith("error") for r in results),
+        "all_resolved": bool(results) and all(r["status"] == "ok" for r in results),
     }
     if not a.table:
         print(json.dumps(report, indent=2))
         return 0
     print(f"{a.recipe} — {len(results)} images")
     for r in results:
-        flag = "UPGRADE" if r["upgrade_available"] else ("ERROR" if r["status"].startswith("error") else "current")
+        flag = "UPGRADE" if r["upgrade_available"] else ("UNKNOWN" if r["status"] != "ok" else "current")
         print(f"  [{flag:7}] {r['repo']}:{r['tag']}" + ("  (digest-pinned)" if r["digest"] else ""))
         print(f"            shape={r['shape']}  candidates={r['candidates']}"
               f"  newest_same_shape={r['newest_same_shape']}"