3 Commits

Author	SHA1	Message	Date
Aleix Conchillo Flaqué	373894fc65	Fold BaseTask.handoff_to into activate_task(deactivate_self=...) ... BaseTask.handoff_to was just deactivate_self + activate_task. Remove it and add a deactivate_self flag on activate_task instead, so there's one entry point for activating another task. LLMTask now overrides activate_task (mirroring its end() override) to keep the messages / result_callback hooks that finish an in-progress tool call before the target is activated. All multi-task examples and unit tests switch to the new call.	2026-05-21 10:13:21 -07:00
Aleix Conchillo Flaqué	8867426a97	Document sensor-controller example in the multi-task README ... Add a Local-section entry with the running instructions, example questions, and architecture diagram for the new sensor-controller example.	2026-05-21 10:13:21 -07:00
Aleix Conchillo Flaqué	a63abc41b6	Add README and env.example for multi-task examples ... Adapts the pipecat-subagents `examples/README.md` to the new layout (`multi-task/` umbrella, `local-handoff/`, `distributed-handoff/`, `remote-proxy-assistant/`, `parallel-debate/`, `code-assistant/`), updates the agent→task / job-RPC vocabulary, drops the single-agent and llm-and-flows examples (gone in the port), and adds a new section for the PGMQ handoff transport.	2026-05-21 10:13:21 -07:00