fix(chat): audit fixes — retention, rag_project_id, cleanup scheduler, tool rounds

- cleanup_old_conversations now excludes briefing conversations (was
  silently deleting briefing history after the retention window)
- list_conversations response now includes rag_project_id, matching the
  shape returned by the single-conversation GET endpoint
- create_conversation_from_article: removed duplicate async_session import
  (_session2 was a copy of the same import); consolidated into one
- MAX_TOOL_ROUNDS fixed from 5→6 to match the actual range(6) loop;
  loop updated to range(MAX_TOOL_ROUNDS) so the constant is accurate
- Chat retention cleanup moved from per-request (every GET /conversations)
  to a daily scheduled job in event_scheduler.py; route no longer runs
  a DB write on every read

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

src/fabledassistant/routes/chat.py

@@ -11,7 +11,6 @@ from fabledassistant.config import Config
 from fabledassistant.services.chat import (
     add_message,
     bulk_delete_conversations,
-    cleanup_old_conversations,
     create_conversation,
     delete_conversation,
     get_conversation,
@@ -40,14 +39,6 @@ async def list_conversations_route():
     uid = get_current_user_id()
     limit, offset = parse_pagination()
     conv_type = request.args.get("type", "chat")
-    # Apply retention policy before returning list
-    retention_str = await get_setting(uid, "chat_retention_days", "90")
-    try:
-        retention_days = int(retention_str)
-    except (ValueError, TypeError):
-        retention_days = 90
-    if retention_days > 0:
-        await cleanup_old_conversations(uid, retention_days)
     conversations, total = await list_conversations(uid, limit=limit, offset=offset, conv_type=conv_type)
     return jsonify({
         "conversations": conversations,
@@ -510,6 +501,7 @@ async def create_conversation_from_article(item_id: int):
     """Create a chat conversation seeded with an RSS article's content."""
     from sqlalchemy import select as _select
     from fabledassistant.models import async_session as _async_session
+    from fabledassistant.models.conversation import Message
     from fabledassistant.models.rss_feed import RssItem, RssFeed
 
     uid = get_current_user_id()
@@ -538,9 +530,7 @@ async def create_conversation_from_article(item_id: int):
     if item.url:
         seeded_text += f"\n\nSource: {item.url}"
 
-    from fabledassistant.models.conversation import Message
-    from fabledassistant.models import async_session as _session2
-    async with _session2() as session:
+    async with _async_session() as session:
         msg = Message(
             conversation_id=conv.id,
             role="assistant",

src/fabledassistant/services/chat.py

@@ -81,6 +81,7 @@ async def list_conversations(
                 "model": conv.model,
                 "conversation_type": conv.conversation_type,
                 "briefing_date": conv.briefing_date.isoformat() if conv.briefing_date else None,
+                "rag_project_id": conv.rag_project_id,
                 "message_count": row[1],
                 "created_at": conv.created_at.isoformat(),
                 "updated_at": conv.updated_at.isoformat(),
@@ -131,8 +132,9 @@ async def cleanup_old_conversations(user_id: int, days: int) -> int:
             .where(
                 Conversation.user_id == user_id,
                 Conversation.updated_at < cutoff,
-                Conversation.conversation_type != "mcp",   # preserve MCP audit trail
-                Conversation.conversation_type != "voice",  # voice convs managed separately
+                Conversation.conversation_type != "mcp",      # preserve MCP audit trail
+                Conversation.conversation_type != "voice",    # voice convs managed separately
+                Conversation.conversation_type != "briefing", # briefing history managed by briefing system
             )
             .returning(Conversation.id)
         )

src/fabledassistant/services/event_scheduler.py

@@ -1,7 +1,8 @@
-"""Scheduler jobs for calendar events.
+"""Scheduler jobs for background maintenance tasks.
 
-- Reminder notifications: checks every 5 minutes for due reminders.
+- Reminder notifications: checks every 5 minutes for due event reminders.
 - CalDAV pull sync: runs every hour for all users with CalDAV configured.
+- Chat retention cleanup: runs daily, deleting old conversations per user setting.
 
 Uses the same BackgroundScheduler pattern as briefing_scheduler.py.
 """
@@ -97,6 +98,44 @@ def _run_caldav_sync_threadsafe(loop: asyncio.AbstractEventLoop) -> None:
     asyncio.run_coroutine_threadsafe(_run_caldav_sync(), loop)
 
 
+# ---------------------------------------------------------------------------
+# Chat retention cleanup job
+# ---------------------------------------------------------------------------
+
+async def _run_chat_retention_cleanup() -> None:
+    """Delete old conversations for all users according to their retention setting."""
+    from sqlalchemy import select as sa_select  # noqa: PLC0415
+
+    from fabledassistant.models.user import User  # noqa: PLC0415
+    from fabledassistant.services.chat import cleanup_old_conversations  # noqa: PLC0415
+    from fabledassistant.services.settings import get_setting  # noqa: PLC0415
+
+    async with async_session() as session:
+        result = await session.execute(sa_select(User.id))
+        user_ids = [row[0] for row in result.all()]
+
+    total_deleted = 0
+    for user_id in user_ids:
+        try:
+            retention_str = await get_setting(user_id, "chat_retention_days", "90")
+            try:
+                retention_days = int(retention_str)
+            except (ValueError, TypeError):
+                retention_days = 90
+            if retention_days > 0:
+                deleted = await cleanup_old_conversations(user_id, retention_days)
+                total_deleted += deleted
+        except Exception:
+            logger.warning("Chat retention cleanup failed for user %d", user_id, exc_info=True)
+
+    if total_deleted:
+        logger.info("Chat retention cleanup: deleted %d conversation(s)", total_deleted)
+
+
+def _run_chat_retention_threadsafe(loop: asyncio.AbstractEventLoop) -> None:
+    asyncio.run_coroutine_threadsafe(_run_chat_retention_cleanup(), loop)
+
+
 # ---------------------------------------------------------------------------
 # Lifecycle
 # ---------------------------------------------------------------------------
@@ -126,8 +165,17 @@ def start_event_scheduler(loop: asyncio.AbstractEventLoop) -> None:
         replace_existing=True,
     )
 
+    # Chat retention cleanup once per day
+    _scheduler.add_job(
+        _run_chat_retention_threadsafe,
+        trigger=IntervalTrigger(hours=24),
+        args=[loop],
+        id="chat_retention_cleanup",
+        replace_existing=True,
+    )
+
     _scheduler.start()
-    logger.info("Event scheduler started (reminders every 5m, CalDAV sync every 1h)")
+    logger.info("Event scheduler started (reminders every 5m, CalDAV sync every 1h, chat cleanup every 24h)")
 
 
 def stop_event_scheduler() -> None:

src/fabledassistant/services/generation_task.py

@@ -217,7 +217,7 @@ async def run_generation(
     voice_mode: bool = False,
 ) -> None:
     """Stream LLM response into buffer with periodic DB flushes."""
-    MAX_TOOL_ROUNDS = 5
+    MAX_TOOL_ROUNDS = 6
     msg_id = buf.assistant_message_id
 
     buf.append_event("status", {"status": "Building context..."})
@@ -294,7 +294,7 @@ async def run_generation(
         cancelled = False
         research_completed = False
 
-        for _round in range(MAX_TOOL_ROUNDS + 1):
+        for _round in range(MAX_TOOL_ROUNDS):
             timing["rounds"] = _round + 1
             round_tool_calls: list[dict] = []
             logger.info("Generation round %d started for conv %d (model=%s)", _round, conv_id, model)