pickle -> sqlite store: D6 async writes, D9 reload race, one-shot pickle migration

fjerkroa_bot/persistence.py

@@ -0,0 +1,87 @@
+"""SQLite persistence for history + memory (SPEC-009).
+
+One database per deployment, stdlib sqlite3 only (D-010). Callers run
+the sync methods in a worker thread (`asyncio.to_thread`) so the
+event loop never blocks on disk (PER-05 / D6).
+"""
+
+import logging
+import os
+import pickle
+import sqlite3
+from contextlib import closing
+from pathlib import Path
+from typing import Any, Dict, List, Optional
+
+SCHEMA_VERSION = 1
+
+
+class PersistentStore:
+    def __init__(self, db_path: Path) -> None:
+        self.db_path = Path(db_path)
+        self._init_db()
+
+    def _connect(self) -> sqlite3.Connection:
+        conn = sqlite3.connect(self.db_path)
+        conn.execute("PRAGMA journal_mode=WAL")
+        return conn
+
+    def _init_db(self) -> None:
+        self.db_path.parent.mkdir(parents=True, exist_ok=True)
+        with closing(self._connect()) as conn, conn:
+            if conn.execute("PRAGMA user_version").fetchone()[0] < SCHEMA_VERSION:
+                conn.execute(
+                    "CREATE TABLE IF NOT EXISTS history (id INTEGER PRIMARY KEY, channel TEXT NOT NULL, role TEXT NOT NULL, content TEXT NOT NULL)"
+                )
+                conn.execute("CREATE INDEX IF NOT EXISTS history_channel ON history (channel)")
+                conn.execute("CREATE TABLE IF NOT EXISTS memory (channel TEXT PRIMARY KEY, content TEXT NOT NULL)")
+                conn.execute(f"PRAGMA user_version = {SCHEMA_VERSION}")
+        os.chmod(self.db_path, 0o600)  # conversation data (PER-04)
+
+    def load_history(self, channel: str) -> List[Dict[str, Any]]:
+        with closing(self._connect()) as conn:
+            rows = conn.execute("SELECT role, content FROM history WHERE channel = ? ORDER BY id", (channel,)).fetchall()
+        return [{"role": role, "content": content} for role, content in rows]
+
+    def save_history(self, channel: str, history: List[Dict[str, Any]]) -> None:
+        # Full replace per save: histories are small (<= history-limit)
+        # and trims must be reflected (D-011)
+        with closing(self._connect()) as conn, conn:
+            conn.execute("DELETE FROM history WHERE channel = ?", (channel,))
+            conn.executemany(
+                "INSERT INTO history (channel, role, content) VALUES (?, ?, ?)",
+                [(channel, str(entry.get("role", "user")), str(entry.get("content", ""))) for entry in history],
+            )
+
+    def load_memory(self, channel: str) -> Optional[str]:
+        with closing(self._connect()) as conn:
+            row = conn.execute("SELECT content FROM memory WHERE channel = ?", (channel,)).fetchone()
+        return row[0] if row else None
+
+    def save_memory(self, channel: str, content: str) -> None:
+        with closing(self._connect()) as conn, conn:
+            conn.execute(
+                "INSERT INTO memory (channel, content) VALUES (?, ?) ON CONFLICT(channel) DO UPDATE SET content = excluded.content",
+                (channel, content),
+            )
+
+    def migrate_pickles(self, channel: str, history_file: Path, memory_file: Path) -> None:
+        """Import legacy pickles once; rename them *.migrated (PER-03)."""
+        if self.load_history(channel) or self.load_memory(channel) is not None:
+            return
+        if history_file.exists():
+            try:
+                with open(history_file, "rb") as fd:
+                    self.save_history(channel, pickle.load(fd))
+                history_file.rename(history_file.with_name(history_file.name + ".migrated"))
+                logging.info(f"migrated legacy history pickle for {channel}")
+            except Exception as err:
+                logging.error(f"failed to migrate history pickle {history_file}: {err!r}")
+        if memory_file.exists():
+            try:
+                with open(memory_file, "rb") as fd:
+                    self.save_memory(channel, str(pickle.load(fd)))
+                memory_file.rename(memory_file.with_name(memory_file.name + ".migrated"))
+                logging.info(f"migrated legacy memory pickle for {channel}")
+            except Exception as err:
+                logging.error(f"failed to migrate memory pickle {memory_file}: {err!r}")