feat: add generation metrics to logs (think, rounds, tokens)

Log think flag, round count, prompt/output token counts per generation.
Change log category from 'usage' to 'generation' for clean MCP filtering.

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

src/fabledassistant/services/logging.py

@@ -68,12 +68,12 @@ async def log_generation(
     """Persist per-generation timing breakdown to app_logs for benchmarking."""
     async with async_session() as session:
         log = AppLog(
-            category="usage",
+            category="generation",
             user_id=user_id,
             action="generation",
             endpoint=f"/chat/conversations/{conv_id}",
             duration_ms=timing.get("total_ms"),
-            details=json.dumps({"model": model, **timing}),
+            details=json.dumps({"model": model, "conv_id": conv_id, **timing}),
         )
         session.add(log)
         await session.commit()