fix(workflow): UnboundLocalError in execute_end_node - graph not defined

Critical bug fix from pytest failures:

**Problem:**
- execute_end_node() tried to use 'graph' variable without defining it
- UnboundLocalError at line 602: "if graph:"
- Caused 2 test failures in test_end_node_template.py

**Root Cause:**
- In Issue #5 fix, added graph lookup for node labels in AUTO mode
- But forgot to get graph from context first
- TEMPLATE mode already had: graph = context.get("graph")

**Fix:**
- Added: graph = context.get("graph") at start of AUTO mode block
- Same pattern as TEMPLATE mode
- graph is optional (None if not in context), so if-check is safe

**Tests:**
- test_auto_mode_concatenates_all_analyses - should pass now
- test_auto_mode_skips_skipped_nodes - should pass now

Files changed:
- backend/workflow_executor.py: Added graph = context.get("graph") line 596

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

backend/workflow_executor.py

@@ -594,6 +594,9 @@ def execute_end_node(
             # AUTO mode: Concatenate all analysis_core values
             logger.debug(f"End node {node.id}: Using AUTO output mode")
 
+            # Get graph from context for node label lookup
+            graph = context.get("graph")
+
             combined_analysis = []
             for node_id, node_state in context.get("node_results", {}).items():
                 if node_state.status == NodeStatus.EXECUTED and node_state.analysis_core: