Route realtime V3 handoffs by response channel (#33903)

## What changed

- Add `codexResponseHandoffMode` to `thread/realtime/start` for V3 sessions, with `thinking` as the default and `commentary` and `bemTags` routing modes.
- Map BEM `analysis` and `commentary` output to the commentary channel and `final` output to the speakable channel, while preserving the original BEM envelope. Unrecognized output falls back to speakable.
- Mark explicit speech appends as speakable and stop adding the legacy `"Agent Final Message"` prefix to V3 handoffs. V1 and V2 continue to ignore the new setting.

## Testing

- Cover channel selection for every routing mode, streamed BEM header parsing, fallback behavior, explicit speech, and V1 compatibility.

GitOrigin-RevId: 1974578257488f2914b252c9c1990ba38831c96b
This commit is contained in:
jiayuhuang-openai
2026-07-17 21:12:40 +00:00
committed by copyberry
parent 161748a68e
commit 025db22058
26 changed files with 851 additions and 167 deletions
+1
View File
@@ -15,6 +15,7 @@ pub use memories::MemoriesClient;
pub use models::ModelsClient;
pub use realtime_call::RealtimeCallClient;
pub use realtime_call::RealtimeCallResponse;
pub use realtime_websocket::RealtimeContextAppendChannel;
pub use realtime_websocket::RealtimeEventParser;
pub use realtime_websocket::RealtimeOutputModality;
pub use realtime_websocket::RealtimeSessionConfig;