jiayuhuang-openai b03545b5b8 Stream realtime V3 Codex handoff output (#33856) ...

## What changed

- Stream V3 agent message deltas to `delegation.context.append` at 200 ms intervals instead of waiting for each completed message.
- Send commentary without a prefix and label final or phase-less V1/V3 output with `"Agent Final Message":`.
- Bound streamed output while preserving both its beginning and final tail when truncation is required.
- Remove `codexResponseHandoffPrefix` from `thread/realtime/start`; unknown fields from older clients remain ignored.

## Testing

- Cover incremental V3 commentary and final output, Unicode-safe truncation, V1/V3 phase labeling, and legacy request compatibility.

GitOrigin-RevId: 633c18b5eb9a4f5756a264b63b7bfc185b073951

2026-07-17 15:54:33 +00:00

..

bin

app-server-protocol: export flat v2 schema bundle (#13324)

2026-03-03 10:25:51 -08:00

protocol

Stream realtime V3 Codex handoff output (#33856)

2026-07-17 15:54:33 +00:00

experimental_api.rs

Add turn-scoped environment selections (#18416)

2026-04-21 17:48:33 -07:00

export.rs

Expose exact per-response usage in raw app-server events (#32985)

2026-07-14 06:39:42 +00:00

lib.rs

Add ordinals to paginated rollout records (#32332)

2026-07-11 04:15:42 +00:00

rpc.rs

protocol: separate app and exec RPC ownership (#29714)

2026-06-23 22:37:31 +00:00

schema_fixtures.rs

Timestamp app-server notifications at emission (#32905)

2026-07-14 00:38:04 +00:00