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, 3 insertions, 1 deletions

diff --git a/src/personalization/config/settings.py b/src/personalization/config/settings.py
index 1bb1bbe..8f0cc8a 100644
--- a/src/personalization/config/settings.py
+++ b/src/personalization/config/settings.py
@@ -37,7 +37,9 @@ def _resolve_config_path(env_key: str, default_rel: str) -> Path:
     value = os.getenv(env_key)
     if value:
         return Path(value).expanduser().resolve()
-    return (Path.cwd() / default_rel).resolve()
+    # Use project root (parent of src/personalization/config) instead of cwd
+    project_root = Path(__file__).parent.parent.parent.parent
+    return (project_root / default_rel).resolve()
 
 
 def load_local_models_config(path: Optional[str] = None) -> LocalModelsConfig: