feat: split memories part 2 (#19860)

Keep extracting memories out of core and moving the write trigger in the
app-server
This is temporary and it should move at the client level as a follow-up
This makes core fully independant from `codex-memories-write`

---------

Co-authored-by: Codex <noreply@openai.com>

codex-rs/core/src/tools/handlers/request_user_input.rs

@@ -5,7 +5,6 @@ use crate::tools::context::ToolPayload;
 use crate::tools::handlers::parse_arguments;
 use crate::tools::registry::ToolHandler;
 use crate::tools::registry::ToolKind;
-use codex_protocol::protocol::SessionSource;
 use codex_protocol::request_user_input::RequestUserInputArgs;
 use codex_tools::REQUEST_USER_INPUT_TOOL_NAME;
 use codex_tools::normalize_request_user_input_args;
@@ -40,7 +39,7 @@ impl ToolHandler for RequestUserInputHandler {
             }
         };
 
-        if matches!(turn.session_source, SessionSource::SubAgent(_)) {
+        if turn.session_source.is_non_root_agent() {
             return Err(FunctionCallError::RespondToModel(
                 "request_user_input can only be used by the root thread".to_string(),
             ));

codex-rs/core/src/tools/handlers/request_user_input_tests.rs

@@ -4,6 +4,7 @@ use crate::tools::context::ToolInvocation;
 use crate::tools::context::ToolPayload;
 use crate::turn_diff_tracker::TurnDiffTracker;
 use codex_protocol::ThreadId;
+use codex_protocol::protocol::SessionSource;
 use codex_protocol::protocol::SubAgentSource;
 use pretty_assertions::assert_eq;
 use serde_json::json;