microsoft/autogen · error · ValueError

Node '{node.name}' has a mix of conditional and unconditiona

Error message

Node '{node.name}' has a mix of conditional and unconditional edges.

What it means

Raised by DiGraph.graph_validate per node when a single node has both conditional edges (with condition= or condition_function=) and unconditional edges. Mixing the two on one node makes branching ambiguous (the unconditional edge always fires, so the conditions can never steer), so validation requires a node's outgoing edges to be either all conditional or all unconditional.

Source

Thrown at python/packages/autogen-agentchat/src/autogen_agentchat/teams/_group_chat/_graph/_digraph_group_chat.py:226

        """Validate graph structure and execution rules."""
        if not self.nodes:
            raise ValueError("Graph has no nodes.")

        if not self.get_start_nodes():
            raise ValueError("Graph must have at least one start node")

        if not self.get_leaf_nodes():
            raise ValueError("Graph must have at least one leaf node")

        # Outgoing edge condition validation (per node)
        for node in self.nodes.values():
            # Check that if a node has an outgoing conditional edge, then all outgoing edges are conditional
            has_condition = any(
                edge.condition is not None or edge.condition_function is not None for edge in node.edges
            )
            has_unconditioned = any(edge.condition is None and edge.condition_function is None for edge in node.edges)
            if has_condition and has_unconditioned:
                raise ValueError(f"Node '{node.name}' has a mix of conditional and unconditional edges.")

        # Validate activation conditions across all edges in the graph
        self._validate_activation_conditions()

        self._has_cycles = self.has_cycles_with_exit()

    def _validate_activation_conditions(self) -> None:
        """Validate that all edges pointing to the same target node have consistent activation_condition values.

        Raises:
            ValueError: If edges pointing to the same target have different activation_condition values
        """
        target_activation_conditions: Dict[str, Dict[str, str]] = {}  # target_node -> {activation_group -> condition}

        for node in self.nodes.values():
            for edge in node.edges:
                target = edge.target  # The target node this edge points to
                activation_group = edge.activation_group

View on GitHub (pinned to 027ecf0a37)

Solutions

Make every outgoing edge of that node conditional, encoding the default branch as condition="..." / condition_function=... returning True when no other branch matches.
Or keep all edges of the node unconditional (single-path) and move the branching to a downstream node.
Name the node from the error message to locate the offending edges quickly.

Example fix

// before
builder.add_edge(router, fast_path)
builder.add_edge(router, slow_path, condition="complex task")  # mixed

// after
builder.add_edge(router, fast_path, condition="simple task")
builder.add_edge(router, slow_path, condition="complex task")

Defensive patterns

Strategy: validation

Validate before calling

for name, node in builder.nodes.items():
    conditional = [e for e in node.edges if e.condition is not None or e.condition_function is not None]
    unconditional = [e for e in node.edges if e.condition is None and e.condition_function is None]
    if conditional and unconditional:
        raise ValueError(f"Node '{name}' mixes conditional and unconditional outgoing edges")

Type guard

def node_edges_are_uniform(node) -> bool:
    flags = [(e.condition is not None or e.condition_function is not None) for e in node.edges]
    return all(flags) or not any(flags)

Try / catch

try:
    flow = GraphFlow(participants, graph_builder=builder)
except ValueError as e:
    if "mix of conditional and unconditional edges" in str(e):
        # make all outgoing edges of the named node conditional (encode default as a condition)
        ...

Prevention

Treat every router node as fully conditional; encode the default branch as an explicit condition.
Review a node's outgoing edges as a group when editing a graph.
Add a structural lint pass over builder.nodes in tests.

When it happens

Trigger: builder.add_edge(a, b) followed by builder.add_edge(a, c, condition="x") — node a mixes both kinds; adding a 'default' fallback edge next to conditional edges; incremental edits that add one conditional edge to a previously unconditional fan-out.

Common situations: Trying to express 'if X go to c, otherwise always go to b' — which this API does not support directly; refactoring a router node; copying edge definitions from different examples into one node.

Related errors

AI-assisted analysis of microsoft/autogen@027ecf0a37 (2026-08-15). Data as JSON: /api/errors/92f889c241a0cb94. Report an issue: GitHub.