Add RAG rewrite, 60-session experiment scripts, and analysis tools

- RAG rewrite adapter and vector preference pipeline in personalized_llm
- 60-session experiment queue scripts (reflection, rag, rag_vector, rag_rewrite)
- Vector-preference correlation analysis and visualization scripts
- Local reward model batch processing improvements
- Updated CLAUDE.md with full experiment documentation and notes

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

1 files changed, 8 insertions, 5 deletions

diff --git a/collaborativeagents/scripts/conflict_scenario_generator.py b/collaborativeagents/scripts/conflict_scenario_generator.py
index 9d00de8..eaf8ef2 100644
--- a/collaborativeagents/scripts/conflict_scenario_generator.py
+++ b/collaborativeagents/scripts/conflict_scenario_generator.py
@@ -367,11 +367,14 @@ class ConflictScenarioGenerator:
         # Find conflict groups in these preferences
         conflict_groups = {}
         for pref in preferences:
-            cg = pref.get('conflict_group')
-            if cg:
-                if cg not in conflict_groups:
-                    conflict_groups[cg] = []
-                conflict_groups[cg].append(pref)
+            # Handle both dict preferences (with conflict_group) and string preferences
+            if isinstance(pref, dict):
+                cg = pref.get('conflict_group')
+                if cg:
+                    if cg not in conflict_groups:
+                        conflict_groups[cg] = []
+                    conflict_groups[cg].append(pref)
+            # String preferences don't have conflict groups - skip them
 
         # Find a conflict group with at least 2 preferences
         for cg, prefs in conflict_groups.items():