fix: Remove max_tokens parameter that triggered Gemini safety filters

Testing revealed that max_tokens=2000 parameter causes Gemini to block
requests with safety filters, even for safe content.

Removed max_tokens from generate_text() call - Gemini will use default.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

zopk_knowledge_service.py

@@ -344,10 +344,10 @@ class ZOPKKnowledgeService:
                 published_date=published_date
             )
 
+            # NOTE: max_tokens removed - testing showed it triggers safety filters!
             response = self.gemini.generate_text(
                 prompt=prompt,
                 temperature=0.1,  # Low temperature for consistency
-                max_tokens=2000,
                 user_id=self.user_id,
                 feature='zopk_knowledge_extraction'
             )