Add realtime speech append control (#27917)

## Why

Realtime voice harness tuning needs app-side control over what backend
Codex text is spoken. Backend orchestrator text is written for a reading
UI, so automatically speaking every preamble, progress update, or final
assistant message can make the realtime voice model too chatty.

For experimentation, clients need two simple controls: keep app/client
text-item injection on the existing item-create path, and add an
explicit speakable path that app code can call only when it wants
realtime to speak. Automatic Codex output also needs an opt-in way to
switch from the protocol's default speakable path to regular realtime
items, with a caller-provided prefix so prompt wording can be tuned
outside core.

The default remains unchanged: if a client omits the new start fields
and never calls `appendSpeech`, automatic backend output continues down
the existing speakable path for the selected realtime protocol.

## What Changed

- Adds experimental `thread/realtime/appendSpeech` for app-provided
speakable text.
- Keeps existing `thread/realtime/appendText` as the item-create API for
app-provided realtime text items.
- Adds `codexResponsesAsItems` / `codex_responses_as_items` on
`thread/realtime/start` to send automatic Codex responses with
`conversation.item.create` instead of the protocol's default speakable
output path.
- Adds `codexResponseItemPrefix` / `codex_response_item_prefix` so
clients can prepend experiment instructions to those automatic Codex
response items.
- Keeps literal `conversation.handoff.append` routing scoped to the v1
speakable path; v2 default speech uses its item/function-output plus
`response.create` behavior.
- Removes the earlier public silent-context API and hardcoded
silent-context prefix.
- Updates realtime tests to cover default automatic speakable behavior,
opt-in automatic item-create behavior, and explicit `appendSpeech`
behavior.

## Validation

- `cargo check -p codex-core -p codex-app-server -p codex-api`
- `just test -p codex-app-server realtime_conversation`
- `just test -p codex-core realtime_conversation` (50/51 passed in the
filtered parallel run; the lone failure passed when rerun in isolation)
- `just test -p codex-core
conversation_mirrors_assistant_message_text_to_realtime_handoff`
- `just test -p codex-api
e2e_connect_and_exchange_events_against_mock_ws_server`
- `just fix -p codex-core`
- `just fix -p codex-app-server`
- `cargo build -p codex-cli`

codex-rs/protocol/src/protocol.rs

@@ -182,6 +182,10 @@ pub struct McpServerRefreshConfig {
 pub struct ConversationStartParams {
     /// Overrides the configured realtime architecture for this session only.
     pub architecture: Option<RealtimeConversationArchitecture>,
+    /// Sends automatic Codex responses as realtime conversation items instead of handoff appends.
+    pub codex_responses_as_items: bool,
+    /// Optional prefix added to automatic Codex response items when `codex_responses_as_items` is set.
+    pub codex_response_item_prefix: Option<String>,
     /// Overrides the configured realtime model for this session only.
     pub model: Option<String>,
     /// Selects whether the realtime session should produce text or audio output.
@@ -407,6 +411,11 @@ pub enum ConversationTextRole {
     Developer,
 }
 
+#[derive(Debug, Clone, PartialEq)]
+pub struct ConversationSpeechParams {
+    pub text: String,
+}
+
 /// Persistent thread-settings overrides that can be applied before user input or
 /// on their own.
 #[derive(Debug, Clone, Default, PartialEq)]
@@ -503,6 +512,9 @@ pub enum Op {
     /// Send text input to the running realtime conversation stream.
     RealtimeConversationText(ConversationTextParams),
 
+    /// Append speakable text to the running realtime conversation stream.
+    RealtimeConversationSpeech(ConversationSpeechParams),
+
     /// Close the running realtime conversation stream.
     RealtimeConversationClose,
 
@@ -762,6 +774,7 @@ impl Op {
             Self::RealtimeConversationStart(_) => "realtime_conversation_start",
             Self::RealtimeConversationAudio(_) => "realtime_conversation_audio",
             Self::RealtimeConversationText(_) => "realtime_conversation_text",
+            Self::RealtimeConversationSpeech(_) => "realtime_conversation_speech",
             Self::RealtimeConversationClose => "realtime_conversation_close",
             Self::RealtimeConversationListVoices => "realtime_conversation_list_voices",
             Self::UserInput { .. } => "user_input",