Skip to content

Conversation

@contextablemark
Copy link
Member

Summary

  • update ADKAgent.run to skip restarting executions when replayed prompts accompany tool results and mark those messages processed
  • add a regression test to ensure tool submissions with duplicated prompt IDs only continue the existing execution

Testing

  • uv run pytest tests/test_tool_result_flow.py::TestToolResultFlow::test_run_does_not_restart_execution_for_replayed_prompt_with_tool_results

Codex Task

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants