fix: address CodeRabbit review feedback (round 4)

- Warn when cluster_tips hits the entity fetch limit
- Skip deletion when LLM returns no consolidated tips for a cluster
- Guard against None .message.content in combine_cluster

Author: JAYARAM RADHAKRISHNAN

kaizen/frontend/client/kaizen_client.py

@@ -94,6 +94,13 @@ def cluster_tips(
             threshold = self.config.clustering_threshold
 
         entities = self.get_all_entities(namespace_id, filters={"type": "guideline"}, limit=limit)
+        if len(entities) >= limit:
+            logger.warning(
+                "Fetched %d entities (hit limit=%d); clustering results may be incomplete. "
+                "Consider increasing the limit.",
+                len(entities),
+                limit,
+            )
         return cluster_entities(entities, threshold=threshold)
 
     def consolidate_tips(
@@ -134,8 +141,13 @@ def consolidate_tips(
                     )
                     for tip in consolidated_tips
                 ]
-                if new_entities:
-                    self.update_entities(namespace_id, new_entities, enable_conflict_resolution=False)
+                if not new_entities:
+                    logger.warning(
+                        "LLM returned no consolidated tips for cluster (IDs: %s); skipping deletion.",
+                        [e.id for e in cluster],
+                    )
+                    continue
+                self.update_entities(namespace_id, new_entities, enable_conflict_resolution=False)
             except Exception:
                 logger.warning(
                     "Failed to consolidate cluster of %d entities (IDs: %s); skipping.",

kaizen/llm/tips/clustering.py

@@ -183,7 +183,7 @@ def combine_cluster(entities: list[RecordedEntity]) -> list[Tip]:
     for attempt in range(3):
         try:
             if constrained_decoding_supported:
-                clean_response = (
+                content = (
                     completion(
                         model=llm_settings.tips_model,
                         messages=[{"role": "user", "content": prompt}],
@@ -193,8 +193,11 @@ def combine_cluster(entities: list[RecordedEntity]) -> list[Tip]:
                     .choices[0]
                     .message.content
                 )
+                if content is None:
+                    raise KaizenException("LLM returned None content for combine_cluster")
+                clean_response = content
             else:
-                response = (
+                content = (
                     completion(
                         model=llm_settings.tips_model,
                         messages=[{"role": "user", "content": prompt}],
@@ -203,7 +206,9 @@ def combine_cluster(entities: list[RecordedEntity]) -> list[Tip]:
                     .choices[0]
                     .message.content
                 )
-                clean_response = clean_llm_response(response)
+                if content is None:
+                    raise KaizenException("LLM returned None content for combine_cluster")
+                clean_response = clean_llm_response(content)
 
             return TipGenerationResponse.model_validate(json.loads(clean_response)).tips
         except Exception as e: