Fix claim_timeout default from 300 to 600 in orchestrator

The DistributionManager, config builder, and UI all already used 600 as
the default, but the orchestrator's fallback was still 300. This caused
premature job reclaim when workers loaded models for the first time.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

generation_orchestrator.py

@@ -1501,7 +1501,7 @@ def _run_distributed_generation(
     )
 
     worker_urls = distribution_config.get("worker_urls", [])
-    claim_timeout = distribution_config.get("claim_timeout", 300)
+    claim_timeout = distribution_config.get("claim_timeout", 600)
 
     # Inject trigger word mode into configs so workers can use it
     for conf in expanded: