📄 api/core/workflow/graph_engine/graph_traversal/skip_propagator.py:83-86

The reordering of mark_edge_skipped() to occur AFTER propagate_skip_from_edge() breaks the recursive skip propagation entirely.

How it fails:

1. _propagate_skip_to_node("A") is called for a skipped node A
2. For each outgoing edge from A, propagate_skip_from_edge(edge.id) is called BEFORE mark_edge_skipped(edge.id)
3. Inside propagate_skip_from_edge, it calls analyze_edge_states(incoming_edges) on the downstream node
4. Since the edge has NOT been marked as skipped yet (still UNKNOWN), analyze_edge_states returns has_unknown=True
5. The method returns immediately without propagating — the skip chain is broken

Evidence from the same file: The skip_branch_paths() method (line 95-97) correctly marks the edge as skipped BEFORE calling propagate_skip_from_edge(). The original order in _propagate_skip_to_node was also correct (mark first, then propagate).

Impact: Skip states will not propagate beyond the first level of outgoing edges. Downstream nodes that should be skipped will remain in UNKNOWN state, potentially causing the workflow to hang waiting for nodes that will never execute.

        for edge in outgoing_edges:
            self._state_manager.mark_edge_skipped(edge.id)
            # Recursively propagate skip
            self.propagate_skip_from_edge(edge.id)

📄 api/core/workflow/graph_engine/graph_traversal/skip_propagator.py:62

A print(f"Starting execution for node: {downstream_node_id}") statement is left in production workflow execution code. This will write to stdout on every workflow node execution where skip propagation triggers the "has_taken" path.

Impact:

• Pollutes application logs/stdout in production
• In containerized/serverless environments, this adds noise to structured logging
• Performance overhead from string formatting on every invocation (minor but unnecessary)

This should either be removed or replaced with proper logging using the logging module at DEBUG level.

            # Start execution and enqueue node
            self._state_manager.start_execution(downstream_node_id)

📄 api/tests/unit_tests/core/workflow/graph_engine/graph_traversal/test_skip_propagator.py:78-80

The test test_propagate_skip_from_edge_with_taken_edge_enqueues_node verifies that both start_execution and enqueue_node are called, but doesn't verify the ordering. Since the whole point of this PR is to ensure start_execution() happens before enqueue_node() (to prevent premature workflow completion), the test should assert the call order.

You can use mock.assert_has_calls([call.start_execution("node_2"), call.enqueue_node("node_2")]) or check mock_state_manager.mock_calls to verify ordering.