From 7ca369b6418596d691b2edc5910904af4f0f5a0e Mon Sep 17 00:00:00 2001
From: AJ Isaacs <ajisaacs27@gmail.com>
Date: Thu, 26 Feb 2026 12:59:03 -0500
Subject: [PATCH] feat: add one-time migration script for user notes to
 profiles

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---
 scripts/migrate_notes_to_profiles.py | 78 ++++++++++++++++++++++++++++
 1 file changed, 78 insertions(+)
 create mode 100644 scripts/migrate_notes_to_profiles.py

diff --git a/scripts/migrate_notes_to_profiles.py b/scripts/migrate_notes_to_profiles.py
new file mode 100644
index 0000000..3e940f0
--- /dev/null
+++ b/scripts/migrate_notes_to_profiles.py
@@ -0,0 +1,78 @@
+"""One-time migration: convert existing timestamped UserNotes into profile summaries.
+
+Run with: python scripts/migrate_notes_to_profiles.py
+
+Requires .env with DB_CONNECTION_STRING and LLM env vars.
+"""
+import asyncio
+import os
+import sys
+
+sys.path.insert(0, os.path.dirname(os.path.dirname(__file__)))
+
+from dotenv import load_dotenv
+load_dotenv()
+
+from utils.database import Database
+from utils.llm_client import LLMClient
+
+
+async def main():
+    db = Database()
+    if not await db.init():
+        print("Database not available.")
+        return
+
+    llm = LLMClient(
+        base_url=os.getenv("LLM_BASE_URL", ""),
+        model=os.getenv("LLM_MODEL", "gpt-4o-mini"),
+        api_key=os.getenv("LLM_API_KEY", "not-needed"),
+    )
+
+    states = await db.load_all_user_states()
+    migrated = 0
+
+    for state in states:
+        notes = state.get("user_notes", "")
+        if not notes or not notes.strip():
+            continue
+
+        # Check if already looks like a profile (no timestamps)
+        if not any(line.strip().startswith("[") for line in notes.split("\n")):
+            print(f"  User {state['user_id']}: already looks like a profile, skipping.")
+            continue
+
+        print(f"  User {state['user_id']}: migrating notes...")
+        print(f"    Old: {notes[:200]}")
+
+        # Ask LLM to summarize notes into a profile
+        result = await llm.extract_memories(
+            conversation=[{"role": "user", "content": f"Here are observation notes about a user:\n{notes}"}],
+            username="unknown",
+            current_profile="",
+        )
+
+        if result and result.get("profile_update"):
+            profile = result["profile_update"]
+            print(f"    New: {profile[:200]}")
+            await db.save_user_state(
+                user_id=state["user_id"],
+                offense_count=state["offense_count"],
+                immune=state["immune"],
+                off_topic_count=state["off_topic_count"],
+                baseline_coherence=state.get("baseline_coherence", 0.85),
+                user_notes=profile,
+                warned=state.get("warned", False),
+                last_offense_at=state.get("last_offense_at"),
+            )
+            migrated += 1
+        else:
+            print(f"    No profile generated, keeping existing notes.")
+
+    await llm.close()
+    await db.close()
+    print(f"\nMigrated {migrated}/{len(states)} user profiles.")
+
+
+if __name__ == "__main__":
+    asyncio.run(main())