CREDO23 acbeb60a43 test(automations/actions): lock agent_task helpers (auto_decide + finalize) ... auto_decide.build_auto_decisions (3): produces one decision per action_request entry, defaults to one decision for legacy scalar interrupts, and skips malformed interrupts silently so a misbehaving tool can't take down the whole agent_task step. finalize.extract_final_assistant_message (4): string-content AIMessage returned verbatim, list-of-parts content concatenated (skipping non-text parts like tool_use), walks back past trailing ToolMessages to find the last AIMessage, and returns None when no extractable text is present (so callers can branch on silence vs. empty). 7 tests, pure unit.		2026-05-28 19:03:29 +02:00
..
actions	test(automations/actions): lock agent_task helpers (auto_decide + finalize)	2026-05-28 19:03:29 +02:00
dispatch	test(automations/dispatch): lock _validate_inputs + DispatchError	2026-05-28 19:03:00 +02:00
runtime	test(automations/runtime): lock execute_step + with_retries	2026-05-28 19:03:08 +02:00
templating	test(automations/templating): lock render, filters, environment, context	2026-05-28 19:03:22 +02:00
triggers	test(automations/triggers): lock schedule cron + params	2026-05-28 19:02:52 +02:00