classifier: Point at gemma4:26b and retry transient fetches

Every classification returned "HTTP Error 404" because the configured
model gemma4:26b-64k no longer exists on the Ollama host: the tag was
retired upstream and the local weights were deleted, so all pending
updates fell back to manual review. Switch to the current gemma4:26b
tag (25.2B, 262k context) and make it explicit in .env so the
classifier no longer depends on the code default matching reality.

PieFed intermittently returned an empty body, which surfaced as a
current version error in the digest. Retry version fetches with a
short backoff so one bad response no longer triggers an alert.

Leave-one-out validation for the new model: immich 6/7 (the miss is
the conditional-breaking example where the model follows the written
rule that thresholds below the running version do not apply),
freshrss 6/6, uptime-kuma 4/4.

update_monitor/classifier.py

@@ -31,7 +31,7 @@ class Classifier:
         model: str = "",
     ) -> None:
         self.base_url = base_url or os.getenv("OLLAMA_BASE_URL", "http://192.168.1.20:11434")
-        self.model = model or os.getenv("OLLAMA_MODEL", "gemma4:26b-64k")
+        self.model = model or os.getenv("OLLAMA_MODEL", "gemma4:26b")
 
     def classify(
         self,