mirror of
https://github.com/openai/codex.git
synced 2026-04-30 11:21:34 +03:00
Add realtime audio device config (#12849)
## Summary - add top-level realtime audio config for microphone and speaker selection - apply configured devices when starting realtime capture and playback - keep missing-device behavior on the system default fallback path ## Validation - just write-config-schema - cargo test -p codex-core realtime_audio - cargo test -p codex-tui - just fix -p codex-core - just fix -p codex-tui - just fmt --------- Co-authored-by: Codex <noreply@openai.com>
This commit is contained in:
@@ -426,6 +426,9 @@ pub struct Config {
|
||||
/// Base URL for requests to ChatGPT (as opposed to the OpenAI API).
|
||||
pub chatgpt_base_url: String,
|
||||
|
||||
/// Machine-local realtime audio device preferences used by realtime voice.
|
||||
pub realtime_audio: RealtimeAudioConfig,
|
||||
|
||||
/// Experimental / do not use. Overrides only the realtime conversation
|
||||
/// websocket transport base URL (the `Op::RealtimeConversation` `/ws`
|
||||
/// connection) without changing normal provider HTTP requests.
|
||||
@@ -1175,6 +1178,10 @@ pub struct ConfigToml {
|
||||
/// Base URL for requests to ChatGPT (as opposed to the OpenAI API).
|
||||
pub chatgpt_base_url: Option<String>,
|
||||
|
||||
/// Machine-local realtime audio device preferences used by realtime voice.
|
||||
#[serde(default)]
|
||||
pub audio: Option<RealtimeAudioToml>,
|
||||
|
||||
/// Experimental / do not use. Overrides only the realtime conversation
|
||||
/// websocket transport base URL (the `Op::RealtimeConversation` `/ws`
|
||||
/// connection) without changing normal provider HTTP requests.
|
||||
@@ -1306,6 +1313,19 @@ impl ProjectConfig {
|
||||
}
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, Default, PartialEq, Eq)]
|
||||
pub struct RealtimeAudioConfig {
|
||||
pub microphone: Option<String>,
|
||||
pub speaker: Option<String>,
|
||||
}
|
||||
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, Default, PartialEq, Eq, JsonSchema)]
|
||||
#[schemars(deny_unknown_fields)]
|
||||
pub struct RealtimeAudioToml {
|
||||
pub microphone: Option<String>,
|
||||
pub speaker: Option<String>,
|
||||
}
|
||||
|
||||
#[derive(Serialize, Deserialize, Debug, Clone, Default, PartialEq, JsonSchema)]
|
||||
#[schemars(deny_unknown_fields)]
|
||||
pub struct ToolsToml {
|
||||
@@ -2146,6 +2166,12 @@ impl Config {
|
||||
.chatgpt_base_url
|
||||
.or(cfg.chatgpt_base_url)
|
||||
.unwrap_or("https://chatgpt.com/backend-api/".to_string()),
|
||||
realtime_audio: cfg
|
||||
.audio
|
||||
.map_or_else(RealtimeAudioConfig::default, |audio| RealtimeAudioConfig {
|
||||
microphone: audio.microphone,
|
||||
speaker: audio.speaker,
|
||||
}),
|
||||
experimental_realtime_ws_base_url: cfg.experimental_realtime_ws_base_url,
|
||||
experimental_realtime_ws_backend_prompt: cfg.experimental_realtime_ws_backend_prompt,
|
||||
forced_chatgpt_workspace_id,
|
||||
@@ -4766,6 +4792,7 @@ model_verbosity = "high"
|
||||
model_verbosity: None,
|
||||
personality: Some(Personality::Pragmatic),
|
||||
chatgpt_base_url: "https://chatgpt.com/backend-api/".to_string(),
|
||||
realtime_audio: RealtimeAudioConfig::default(),
|
||||
experimental_realtime_ws_base_url: None,
|
||||
experimental_realtime_ws_backend_prompt: None,
|
||||
base_instructions: None,
|
||||
@@ -4892,6 +4919,7 @@ model_verbosity = "high"
|
||||
model_verbosity: None,
|
||||
personality: Some(Personality::Pragmatic),
|
||||
chatgpt_base_url: "https://chatgpt.com/backend-api/".to_string(),
|
||||
realtime_audio: RealtimeAudioConfig::default(),
|
||||
experimental_realtime_ws_base_url: None,
|
||||
experimental_realtime_ws_backend_prompt: None,
|
||||
base_instructions: None,
|
||||
@@ -5016,6 +5044,7 @@ model_verbosity = "high"
|
||||
model_verbosity: None,
|
||||
personality: Some(Personality::Pragmatic),
|
||||
chatgpt_base_url: "https://chatgpt.com/backend-api/".to_string(),
|
||||
realtime_audio: RealtimeAudioConfig::default(),
|
||||
experimental_realtime_ws_base_url: None,
|
||||
experimental_realtime_ws_backend_prompt: None,
|
||||
base_instructions: None,
|
||||
@@ -5126,6 +5155,7 @@ model_verbosity = "high"
|
||||
model_verbosity: Some(Verbosity::High),
|
||||
personality: Some(Personality::Pragmatic),
|
||||
chatgpt_base_url: "https://chatgpt.com/backend-api/".to_string(),
|
||||
realtime_audio: RealtimeAudioConfig::default(),
|
||||
experimental_realtime_ws_base_url: None,
|
||||
experimental_realtime_ws_backend_prompt: None,
|
||||
base_instructions: None,
|
||||
@@ -5970,6 +6000,39 @@ experimental_realtime_ws_backend_prompt = "prompt from config"
|
||||
);
|
||||
Ok(())
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn realtime_audio_loads_from_config_toml() -> std::io::Result<()> {
|
||||
let cfg: ConfigToml = toml::from_str(
|
||||
r#"
|
||||
[audio]
|
||||
microphone = "USB Mic"
|
||||
speaker = "Desk Speakers"
|
||||
"#,
|
||||
)
|
||||
.expect("TOML deserialization should succeed");
|
||||
|
||||
let realtime_audio = cfg
|
||||
.audio
|
||||
.as_ref()
|
||||
.expect("realtime audio config should be present");
|
||||
assert_eq!(realtime_audio.microphone.as_deref(), Some("USB Mic"));
|
||||
assert_eq!(realtime_audio.speaker.as_deref(), Some("Desk Speakers"));
|
||||
|
||||
let codex_home = TempDir::new()?;
|
||||
let config = Config::load_from_base_config_with_overrides(
|
||||
cfg,
|
||||
ConfigOverrides::default(),
|
||||
codex_home.path().to_path_buf(),
|
||||
)?;
|
||||
|
||||
assert_eq!(config.realtime_audio.microphone.as_deref(), Some("USB Mic"));
|
||||
assert_eq!(
|
||||
config.realtime_audio.speaker.as_deref(),
|
||||
Some("Desk Speakers")
|
||||
);
|
||||
Ok(())
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
|
||||
Reference in New Issue
Block a user