Problem

When using GraphFlow with a termination condition, the second task execution would immediately terminate without running any agents. The first task would run successfully, but subsequent tasks would skip all agents and go directly to the stop agent.

This was demonstrated by the following issue:

# First task runs correctly
result1 = await team.run(task="First task")  # ✅ Works fine

# Second task fails immediately  
result2 = await team.run(task="Second task")  # ❌ Only user + stop messages

Root Cause

The GraphFlowManager was not resetting its execution state when termination occurred. After the first task completed:

1. The _ready queue was empty (all nodes had been processed)
2. The _remaining and _enqueued_any tracking structures remained in "completed" state
3. The _message_thread retained history from the previous task

This left the graph in a "completed" state, causing subsequent tasks to immediately trigger the stop agent instead of executing the workflow.

Solution

Added an override of the _apply_termination_condition method in GraphFlowManager to automatically reset the graph execution state when termination occurs:

async def _apply_termination_condition(
    self, delta: Sequence[BaseAgentEvent | BaseChatMessage], increment_turn_count: bool = False
) -> bool:
    # Call the base implementation first
    terminated = await super()._apply_termination_condition(delta, increment_turn_count)
    
    # If terminated, reset the graph execution state and message thread for the next task
    if terminated:
        self._remaining = {target: Counter(groups) for target, groups in self._graph.get_remaining_map().items()}
        self._enqueued_any = {n: {g: False for g in self._enqueued_any[n]} for n in self._enqueued_any}
        self._ready = deque([n for n in self._graph.get_start_nodes()])
        # Clear the message thread to start fresh for the next task
        self._message_thread.clear()
    
    return terminated

This ensures that when a task completes (termination condition is met), the graph is automatically reset to its initial state ready for the next task.

Testing

Added a comprehensive test case test_digraph_group_chat_multiple_task_execution that validates:

• Multiple tasks can be run sequentially without explicit reset calls
• All agents are executed the expected number of times
• Both tasks produce the correct number of messages
• The fix works with various termination conditions (MaxMessageTermination, TextMentionTermination)

Result

GraphFlow now works like SelectorGroupChat where multiple tasks can be run sequentially without explicit resets between them:

# Both tasks now work correctly
result1 = await team.run(task="First task")   # ✅ 5 messages, all agents called
result2 = await team.run(task="Second task")  # ✅ 5 messages, all agents called again

Fixes #6746.

💬 Share your feedback on Copilot coding agent for the chance to win a $200 gift card! Click here to start the survey.