feat: Complete pipeline runner integration for API-based task launch

- Add backend/core/pipeline_runner.py with full pipeline execution logic
- Integrate main.py pipeline startup into REST API
- Add comprehensive logging and error handling
- Support mock/live/backtest modes via API

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

backend/api/runtime.py

@@ -375,21 +375,25 @@ async def _run_pipeline(
     bootstrap: Dict[str, Any],
     stop_event: asyncio.Event
 ) -> None:
-    """Background task to run the trading pipeline.
+    """Background task to run the trading pipeline."""
+    import logging
+    logger = logging.getLogger(__name__)
+
+    from backend.core.pipeline_runner import run_pipeline
 
-    This is a placeholder - actual implementation will integrate with main.py
-    """
     try:
-        # TODO: Integrate with main.py pipeline execution
-        # This should call the actual pipeline startup logic from main.py
-
-        # For now, just wait until stop event is set
-        while not stop_event.is_set():
-            await asyncio.sleep(1)
-
+        logger.info(f"Starting pipeline for run_id: {run_id}")
+        await run_pipeline(
+            run_id=run_id,
+            run_dir=run_dir,
+            bootstrap=bootstrap,
+            stop_event=stop_event,
+        )
+        logger.info(f"Pipeline completed for run_id: {run_id}")
     except asyncio.CancelledError:
-        # Handle cancellation gracefully
+        logger.info(f"Pipeline cancelled for run_id: {run_id}")
+        raise
+    except Exception as e:
+        logger.exception(f"Pipeline failed for run_id: {run_id}: {e}")
+        # Re-raise to allow proper cleanup
         raise
-    finally:
-        # Cleanup
-        pass