feat(tooling): 5 retry attempts + refresh every 1000 requests (#833)

Bumped max_attempts from 3 to 5 — with per-system dedup and no stem
cap, the remaining dedup hits are mostly per-body collisions which
a couple extra attempts with rotated pools can escape.

Bumped --refresh default from 200 to 1000. Fewer subprocess restarts
= fewer model reloads via distrobox. KV-cache bleed risk is lower
now that the validation gauntlet is lighter.

Reverted the batch-prompt experiment — Gemma 2 2B drifts on
multi-line output; individual calls are more reliable.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

tooling/planet-gen/gemma_naming.py

@@ -1318,7 +1318,7 @@ def name_feature(
     hop: int,
     log: "Logger",
     verbose: bool,
-    max_attempts: int = 3,
+    max_attempts: int = 5,
 ) -> str:
     """Request a name from Gemma, enforce blocklist + per-system dedup +
     per-body cross-type dedup, skip on persistent failure.
@@ -1791,7 +1791,7 @@ def main():
     parser.add_argument(
         "--refresh",
         type=int,
-        default=200,
+        default=1000,
         help="Restart the voice subprocess every N requests (default: 200) "
              "to prevent KV-cache context bleed",
     )