mirror of
https://github.com/openai/codex.git
synced 2026-10-19 17:28:46 +00:00
## What Built on the realtime speech-control plumbing merged in #27917. - Add optional `codexResponseHandoffPrefix` to `thread/realtime/start`. - Apply that prefix only to automatic V1 commentary sent through `conversation.handoff.append`; final answers remain unprefixed. - Add opt-in `clientManagedHandoffs`. When true, core suppresses automatic response handoffs and completion output so delivery is controlled by explicit client append APIs. - Preserve existing automatic behavior by default. `codexResponsesAsItems: true` continues to select item routing when client-managed mode is disabled. ## Why Voice clients need two delivery policies: automatic background context with silent commentary instructions and fully client-owned handoffs. Phase-aware prefixing keeps routine commentary silent without suppressing the final answer, while client-managed mode lets an app decide exactly which updates to append. ## Validation - `just fmt` - `cargo test -p codex-app-server-protocol serialize_thread_realtime_start` - `RUST_MIN_STACK=16777216 cargo test -p codex-core --test all conversation_handoff_persists_across_item_done_until_turn_complete` - `RUST_MIN_STACK=16777216 cargo test -p codex-app-server --test all webrtc_v1_client_managed_handoffs_disable_automatic_output` - `RUST_MIN_STACK=16777216 cargo test -p codex-app-server --test all webrtc_v1_final_automatic_handoff_omits_silent_prefix` - `cargo build -p codex-cli --bin codex` - Local Codex Apps compatibility check: 43 focused webview tests passed, and a live voice session routed through the source-built app-server. The explicit `RUST_MIN_STACK` avoids a macOS Tokio test-worker stack overflow seen with the default test environment.
174 lines
5.4 KiB
Rust
174 lines
5.4 KiB
Rust
use super::RealtimeHandoffState;
|
|
use super::RealtimeSessionKind;
|
|
use super::realtime_delegation_from_handoff;
|
|
use super::realtime_request_headers;
|
|
use super::realtime_text_from_handoff_request;
|
|
use super::wrap_realtime_delegation_input;
|
|
use async_channel::bounded;
|
|
use codex_config::config_toml::RealtimeWsVersion;
|
|
use codex_protocol::protocol::RealtimeHandoffRequested;
|
|
use codex_protocol::protocol::RealtimeTranscriptEntry;
|
|
use pretty_assertions::assert_eq;
|
|
|
|
#[test]
|
|
fn prefers_handoff_input_transcript_over_active_transcript() {
|
|
let handoff = RealtimeHandoffRequested {
|
|
handoff_id: "handoff_1".to_string(),
|
|
item_id: "item_1".to_string(),
|
|
input_transcript: "ignored".to_string(),
|
|
active_transcript: vec![
|
|
RealtimeTranscriptEntry {
|
|
role: "user".to_string(),
|
|
text: "hello".to_string(),
|
|
},
|
|
RealtimeTranscriptEntry {
|
|
role: "assistant".to_string(),
|
|
text: "hi there".to_string(),
|
|
},
|
|
],
|
|
};
|
|
assert_eq!(
|
|
realtime_text_from_handoff_request(&handoff),
|
|
Some("ignored".to_string())
|
|
);
|
|
}
|
|
|
|
#[test]
|
|
fn extracts_text_from_handoff_request_active_transcript_if_input_missing() {
|
|
let handoff = RealtimeHandoffRequested {
|
|
handoff_id: "handoff_1".to_string(),
|
|
item_id: "item_1".to_string(),
|
|
input_transcript: String::new(),
|
|
active_transcript: vec![RealtimeTranscriptEntry {
|
|
role: "user".to_string(),
|
|
text: "hello".to_string(),
|
|
}],
|
|
};
|
|
assert_eq!(
|
|
realtime_text_from_handoff_request(&handoff),
|
|
Some("user: hello".to_string())
|
|
);
|
|
}
|
|
|
|
#[test]
|
|
fn wraps_handoff_with_transcript_delta() {
|
|
let handoff = RealtimeHandoffRequested {
|
|
handoff_id: "handoff_1".to_string(),
|
|
item_id: "item_1".to_string(),
|
|
input_transcript: "delegate this".to_string(),
|
|
active_transcript: vec![
|
|
RealtimeTranscriptEntry {
|
|
role: "user".to_string(),
|
|
text: "hello".to_string(),
|
|
},
|
|
RealtimeTranscriptEntry {
|
|
role: "assistant".to_string(),
|
|
text: "hi there".to_string(),
|
|
},
|
|
],
|
|
};
|
|
assert_eq!(
|
|
realtime_delegation_from_handoff(&handoff),
|
|
Some(
|
|
"<realtime_delegation>\n <input>delegate this</input>\n <transcript_delta>user: hello\nassistant: hi there</transcript_delta>\n</realtime_delegation>"
|
|
.to_string()
|
|
)
|
|
);
|
|
}
|
|
|
|
#[test]
|
|
fn extracts_text_from_handoff_request_input_transcript_if_messages_missing() {
|
|
let handoff = RealtimeHandoffRequested {
|
|
handoff_id: "handoff_1".to_string(),
|
|
item_id: "item_1".to_string(),
|
|
input_transcript: "ignored".to_string(),
|
|
active_transcript: vec![],
|
|
};
|
|
assert_eq!(
|
|
realtime_text_from_handoff_request(&handoff),
|
|
Some("ignored".to_string())
|
|
);
|
|
}
|
|
|
|
#[test]
|
|
fn ignores_empty_handoff_request_input_transcript() {
|
|
let handoff = RealtimeHandoffRequested {
|
|
handoff_id: "handoff_1".to_string(),
|
|
item_id: "item_1".to_string(),
|
|
input_transcript: String::new(),
|
|
active_transcript: vec![],
|
|
};
|
|
assert_eq!(realtime_text_from_handoff_request(&handoff), None);
|
|
}
|
|
|
|
#[test]
|
|
fn wraps_realtime_delegation_input() {
|
|
assert_eq!(
|
|
wrap_realtime_delegation_input("hello", /*transcript_delta*/ None),
|
|
"<realtime_delegation>\n <input>hello</input>\n</realtime_delegation>"
|
|
);
|
|
}
|
|
|
|
#[test]
|
|
fn wraps_realtime_delegation_input_with_xml_escaping() {
|
|
assert_eq!(
|
|
wrap_realtime_delegation_input("use a < b && c > d", Some("saw <that>")),
|
|
"<realtime_delegation>\n <input>use a < b && c > d</input>\n <transcript_delta>saw <that></transcript_delta>\n</realtime_delegation>"
|
|
);
|
|
}
|
|
|
|
#[test]
|
|
fn wraps_realtime_delegation_input_with_xml_escaping_without_transcript() {
|
|
assert_eq!(
|
|
wrap_realtime_delegation_input("use a < b && c > d", /*transcript_delta*/ None),
|
|
"<realtime_delegation>\n <input>use a < b && c > d</input>\n</realtime_delegation>"
|
|
);
|
|
}
|
|
|
|
#[tokio::test]
|
|
async fn clears_active_handoff_explicitly() {
|
|
let (tx, _rx) = bounded(1);
|
|
let state = RealtimeHandoffState::new(
|
|
tx,
|
|
/*client_managed_handoffs*/ false,
|
|
/*codex_responses_as_items*/ false,
|
|
/*codex_response_item_prefix*/ None,
|
|
/*codex_response_handoff_prefix*/ None,
|
|
RealtimeSessionKind::V1,
|
|
);
|
|
|
|
*state.active_handoff.lock().await = Some("handoff_1".to_string());
|
|
assert_eq!(
|
|
state.active_handoff.lock().await.clone(),
|
|
Some("handoff_1".to_string())
|
|
);
|
|
|
|
*state.active_handoff.lock().await = None;
|
|
assert_eq!(state.active_handoff.lock().await.clone(), None);
|
|
}
|
|
|
|
#[test]
|
|
fn uses_quicksilver_alpha_header_for_realtime_v1() {
|
|
let headers =
|
|
realtime_request_headers(Some("session_1"), Some("sk-test"), RealtimeWsVersion::V1)
|
|
.expect("headers")
|
|
.expect("headers");
|
|
|
|
assert_eq!(
|
|
headers
|
|
.get("openai-alpha")
|
|
.and_then(|value| value.to_str().ok()),
|
|
Some("quicksilver=v1")
|
|
);
|
|
}
|
|
|
|
#[test]
|
|
fn omits_quicksilver_alpha_header_for_realtime_v2() {
|
|
let headers =
|
|
realtime_request_headers(Some("session_1"), Some("sk-test"), RealtimeWsVersion::V2)
|
|
.expect("headers")
|
|
.expect("headers");
|
|
|
|
assert!(headers.get("openai-alpha").is_none());
|
|
}
|