Support plaintext agent messages (#27830)

## Why

Multi-agent v2 `send_message` deliveries already reach the receiving
model as typed `agent_message` items with encrypted content.
Child-completion notifications are generated by Codex itself, so their
content is plaintext and previously fell back to a serialized JSON
envelope inside an assistant message.

With plaintext `input_text` supported for `agent_message`, both delivery
paths can use the same model-visible type while preserving explicit
author and recipient metadata.

## What changed

- add plaintext `input_text` support to `AgentMessageInputContent` and
regenerate the affected app-server schemas
- preserve `InterAgentCommunication` as structured mailbox input instead
of converting it to assistant text
- record delivered communications as typed `agent_message` history items
- persist a dedicated rollout item so local delivery metadata such as
`trigger_turn` remains available without leaking into the Responses
request
- reconstruct typed agent messages on resume and preserve fork-turn
truncation behavior
- remove request-time assistant-content parsing
- preserve plaintext and encrypted inter-agent deliveries in stage-one
memory inputs
- normalize and link plaintext and encrypted agent messages in rollout
traces without treating inbound messages as child results
- cover the real MultiAgent V2 child-completion path end to end with
deterministic mailbox synchronization

## Verification

- `just test -p codex-core
plaintext_multi_agent_v2_completion_sends_agent_message`
- `just test -p codex-core input_queue_drains_mailbox_in_delivery_order
record_initial_history_reconstructs_typed_inter_agent_message
fork_turn_positions_use_inter_agent_delivery_metadata`
- `just test -p codex-memories-write
serializes_inter_agent_communications_for_memory`
- `just test -p codex-rollout-trace
agent_messages_preserve_routing_and_content
sub_agent_started_activity_creates_spawn_edge`
- `just test -p codex-rollout-trace
agent_result_edge_falls_back_to_child_thread_without_result_message`
- `just test -p codex-protocol -p codex-rollout -p
codex-app-server-protocol`

codex-rs/rollout-trace/src/model/conversation.rs

@@ -3,6 +3,7 @@ use serde::Serialize;
 
 use crate::payload::RawPayloadId;
 
+use super::AgentPath;
 use super::AgentThreadId;
 use super::CodeCellId;
 use super::CodexTurnId;
@@ -32,6 +33,9 @@ pub struct ConversationItem {
     /// Codex channel for assistant/tool content, when the item is channel-specific.
     pub channel: Option<ConversationChannel>,
     pub kind: ConversationItemKind,
+    /// Routing metadata carried by a Responses `agent_message` item.
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub agent_message: Option<AgentMessageMetadata>,
     pub body: ConversationBody,
     /// Protocol/model `call_id` for function/custom tool call and output items.
     pub call_id: Option<ModelVisibleCallId>,
@@ -39,6 +43,15 @@ pub struct ConversationItem {
     pub produced_by: Vec<ProducerRef>,
 }
 
+/// Sender and destination identities attached to a model-visible agent message.
+#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
+pub struct AgentMessageMetadata {
+    /// Agent path that authored the message.
+    pub author: AgentPath,
+    /// Agent path that received the message.
+    pub recipient: AgentPath,
+}
+
 /// Model-visible role assigned to a conversation item.
 #[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
 #[serde(rename_all = "snake_case")]