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

codex-rs/app-server-protocol/src/protocol/common.rs

@@ -3390,7 +3390,6 @@ mod tests {
                 flush_transcript_tail_on_session_end: Some(true),
                 codex_responses_as_items: None,
                 codex_response_item_prefix: None,
-                codex_response_handoff_prefix: Some("silent context".to_string()),
                 thread_id: "thr_123".to_string(),
                 model: Some("realtime-treatment-model".to_string()),
                 output_modality: RealtimeOutputModality::Audio,
@@ -3412,7 +3411,6 @@ mod tests {
                     "flushTranscriptTailOnSessionEnd": true,
                     "codexResponsesAsItems": null,
                     "codexResponseItemPrefix": null,
-                    "codexResponseHandoffPrefix": "silent context",
                     "model": "realtime-treatment-model",
                     "outputModality": "audio",
                     "includeStartupContext": false,
@@ -3437,7 +3435,6 @@ mod tests {
                 flush_transcript_tail_on_session_end: None,
                 codex_responses_as_items: None,
                 codex_response_item_prefix: None,
-                codex_response_handoff_prefix: None,
                 thread_id: "thr_123".to_string(),
                 model: None,
                 output_modality: RealtimeOutputModality::Audio,
@@ -3459,7 +3456,6 @@ mod tests {
                     "flushTranscriptTailOnSessionEnd": null,
                     "codexResponsesAsItems": null,
                     "codexResponseItemPrefix": null,
-                    "codexResponseHandoffPrefix": null,
                     "model": null,
                     "outputModality": "audio",
                     "includeStartupContext": null,
@@ -3479,7 +3475,6 @@ mod tests {
                 flush_transcript_tail_on_session_end: None,
                 codex_responses_as_items: None,
                 codex_response_item_prefix: None,
-                codex_response_handoff_prefix: None,
                 thread_id: "thr_123".to_string(),
                 model: None,
                 output_modality: RealtimeOutputModality::Audio,
@@ -3501,7 +3496,6 @@ mod tests {
                     "flushTranscriptTailOnSessionEnd": null,
                     "codexResponsesAsItems": null,
                     "codexResponseItemPrefix": null,
-                    "codexResponseHandoffPrefix": null,
                     "model": null,
                     "outputModality": "audio",
                     "includeStartupContext": null,
@@ -3520,6 +3514,8 @@ mod tests {
             "id": 9,
             "params": {
                 "threadId": "thr_123",
+                // Retain runtime compatibility with clients that have not yet removed this field.
+                "codexResponseHandoffPrefix": "",
                 "outputModality": "audio",
                 "realtimeSessionId": null,
                 "transport": null,
@@ -3719,7 +3715,6 @@ mod tests {
                 flush_transcript_tail_on_session_end: None,
                 codex_responses_as_items: None,
                 codex_response_item_prefix: None,
-                codex_response_handoff_prefix: None,
                 thread_id: "thr_123".to_string(),
                 model: None,
                 output_modality: RealtimeOutputModality::Audio,