Files
pipecat/tests
Mark Backman 1c94feaaff Inject <ui_state> via the LLM's on_before_process_frame hook
Move <ui_state> snapshot injection out of respond_with_llm into a
cross-cutting on_before_process_frame handler on the UIWorker's LLM, so it
appends the current snapshot to the context the request is built from, just
before each inference. Injection is gated to the user-turn-initiating
inference so a tool-calling turn never stacks duplicate <ui_state> blocks;
respond_with_llm no longer injects manually.

Also drop the bridged parameter from UIWorker: there is no viable way to
bridge a UIWorker between workers — a shared, teed context would be polluted
by the injection, and per-worker turn detection off teed frames isn't
supported. Other workers keep their PipelineWorker bridging.
2026-05-21 23:20:40 -04:00
..
2026-03-10 14:54:49 +01:00
2026-03-09 12:07:45 -03:00
2026-05-21 23:20:40 -04:00
2026-05-21 23:20:40 -04:00
2026-05-21 23:20:40 -04:00