Defer persistence of rollout file (#11028)

- Defer rollout persistence for fresh threads (`InitialHistory::New`):
keep rollout events in memory and only materialize rollout file + state
DB row on first `EventMsg::UserMessage`.
- Keep precomputed rollout path available before materialization.
- Change `thread/start` to build thread response from live config
snapshot and optional precomputed path.
- Improve pre-materialization behavior in app-server/TUI: clearer
invalid-request errors for file-backed ops and a friendlier `/fork` “not
ready yet” UX.
- Update tests to match deferred semantics across
start/read/archive/unarchive/fork/resume/review flows.
- Improved resilience of user_shell test, which should be unrelated to
this change but must be affected by timing changes

For Reviewers:
* The primary change is in recorder.rs
* Most of the other changes were to fix up broken assumptions in
existing tests

Testing:
* Manually tested CLI
* Exercised app server paths by manually running IDE Extension with
rebuilt CLI binary
* Only user-visible change is that `/fork` in TUI generates visible
error if used prior to first turn

codex-rs/app-server/tests/suite/archive_thread.rs

@@ -1,12 +1,19 @@
 use anyhow::Result;
 use app_test_support::McpProcess;
+use app_test_support::create_mock_responses_server_repeating_assistant;
 use app_test_support::to_response;
+use codex_app_server_protocol::AddConversationListenerParams;
+use codex_app_server_protocol::AddConversationSubscriptionResponse;
 use codex_app_server_protocol::ArchiveConversationParams;
 use codex_app_server_protocol::ArchiveConversationResponse;
+use codex_app_server_protocol::InputItem;
+use codex_app_server_protocol::JSONRPCNotification;
 use codex_app_server_protocol::JSONRPCResponse;
 use codex_app_server_protocol::NewConversationParams;
 use codex_app_server_protocol::NewConversationResponse;
 use codex_app_server_protocol::RequestId;
+use codex_app_server_protocol::SendUserMessageParams;
+use codex_app_server_protocol::SendUserMessageResponse;
 use codex_core::ARCHIVED_SESSIONS_SUBDIR;
 use std::path::Path;
 use tempfile::TempDir;
@@ -16,8 +23,9 @@ const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs
 
 #[tokio::test(flavor = "multi_thread", worker_threads = 2)]
 async fn archive_conversation_moves_rollout_into_archived_directory() -> Result<()> {
+    let server = create_mock_responses_server_repeating_assistant("Done").await;
     let codex_home = TempDir::new()?;
-    create_config_toml(codex_home.path())?;
+    create_config_toml(codex_home.path(), &server.uri())?;
 
     let mut mcp = McpProcess::new(codex_home.path()).await?;
     timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
@@ -40,9 +48,50 @@ async fn archive_conversation_moves_rollout_into_archived_directory() -> Result<
         ..
     } = to_response::<NewConversationResponse>(new_response)?;
 
+    assert!(
+        !rollout_path.exists(),
+        "expected rollout path {} to be deferred until first user message",
+        rollout_path.display()
+    );
+
+    let add_listener_request_id = mcp
+        .send_add_conversation_listener_request(AddConversationListenerParams {
+            conversation_id,
+            experimental_raw_events: false,
+        })
+        .await?;
+    let add_listener_response: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(add_listener_request_id)),
+    )
+    .await??;
+    let AddConversationSubscriptionResponse { subscription_id: _ } =
+        to_response::<AddConversationSubscriptionResponse>(add_listener_response)?;
+
+    let send_request_id = mcp
+        .send_send_user_message_request(SendUserMessageParams {
+            conversation_id,
+            items: vec![InputItem::Text {
+                text: "materialize".to_string(),
+                text_elements: Vec::new(),
+            }],
+        })
+        .await?;
+    let send_response: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(send_request_id)),
+    )
+    .await??;
+    let _: SendUserMessageResponse = to_response::<SendUserMessageResponse>(send_response)?;
+    let _: JSONRPCNotification = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("codex/event/task_complete"),
+    )
+    .await??;
+
     assert!(
         rollout_path.exists(),
-        "expected rollout path {} to exist",
+        "expected rollout path {} to exist after first user message",
         rollout_path.display()
     );
 
@@ -81,14 +130,25 @@ async fn archive_conversation_moves_rollout_into_archived_directory() -> Result<
     Ok(())
 }
 
-fn create_config_toml(codex_home: &Path) -> std::io::Result<()> {
+fn create_config_toml(codex_home: &Path, server_uri: &str) -> std::io::Result<()> {
     let config_toml = codex_home.join("config.toml");
-    std::fs::write(config_toml, config_contents())
+    std::fs::write(config_toml, config_contents(server_uri))
 }
 
-fn config_contents() -> &'static str {
-    r#"model = "mock-model"
+fn config_contents(server_uri: &str) -> String {
+    format!(
+        r#"model = "mock-model"
 approval_policy = "never"
 sandbox_mode = "read-only"
+
+model_provider = "mock_provider"
+
+[model_providers.mock_provider]
+name = "Mock provider for test"
+base_url = "{server_uri}/v1"
+wire_api = "responses"
+request_max_retries = 0
+stream_max_retries = 0
 "#
+    )
 }

codex-rs/app-server/tests/suite/v2/review.rs

@@ -19,7 +19,9 @@ use codex_app_server_protocol::ServerRequest;
 use codex_app_server_protocol::ThreadItem;
 use codex_app_server_protocol::ThreadStartParams;
 use codex_app_server_protocol::ThreadStartResponse;
+use codex_app_server_protocol::TurnStartParams;
 use codex_app_server_protocol::TurnStatus;
+use codex_app_server_protocol::UserInput as V2UserInput;
 use serde_json::json;
 use tempfile::TempDir;
 use tokio::time::timeout;
@@ -270,6 +272,7 @@ async fn review_start_with_detached_delivery_returns_new_thread_id() -> Result<(
     timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
 
     let thread_id = start_default_thread(&mut mcp).await?;
+    materialize_thread_rollout(&mut mcp, &thread_id).await?;
 
     let review_req = mcp
         .send_review_start_request(ReviewStartParams {
@@ -387,6 +390,30 @@ async fn start_default_thread(mcp: &mut McpProcess) -> Result<String> {
     Ok(thread.id)
 }
 
+async fn materialize_thread_rollout(mcp: &mut McpProcess, thread_id: &str) -> Result<()> {
+    let turn_req = mcp
+        .send_turn_start_request(TurnStartParams {
+            thread_id: thread_id.to_string(),
+            input: vec![V2UserInput::Text {
+                text: "materialize rollout".to_string(),
+                text_elements: Vec::new(),
+            }],
+            ..Default::default()
+        })
+        .await?;
+    timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(turn_req)),
+    )
+    .await??;
+    timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("turn/completed"),
+    )
+    .await??;
+    Ok(())
+}
+
 fn create_config_toml(codex_home: &std::path::Path, server_uri: &str) -> std::io::Result<()> {
     create_config_toml_with_approval_policy(codex_home, server_uri, "never")
 }

codex-rs/app-server/tests/suite/v2/thread_archive.rs

@@ -1,12 +1,17 @@
 use anyhow::Result;
 use app_test_support::McpProcess;
+use app_test_support::create_mock_responses_server_repeating_assistant;
 use app_test_support::to_response;
+use codex_app_server_protocol::JSONRPCError;
 use codex_app_server_protocol::JSONRPCResponse;
 use codex_app_server_protocol::RequestId;
 use codex_app_server_protocol::ThreadArchiveParams;
 use codex_app_server_protocol::ThreadArchiveResponse;
 use codex_app_server_protocol::ThreadStartParams;
 use codex_app_server_protocol::ThreadStartResponse;
+use codex_app_server_protocol::TurnStartParams;
+use codex_app_server_protocol::TurnStartResponse;
+use codex_app_server_protocol::UserInput;
 use codex_core::ARCHIVED_SESSIONS_SUBDIR;
 use codex_core::find_thread_path_by_id_str;
 use std::path::Path;
@@ -16,9 +21,10 @@ use tokio::time::timeout;
 const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
 
 #[tokio::test]
-async fn thread_archive_moves_rollout_into_archived_directory() -> Result<()> {
+async fn thread_archive_requires_materialized_rollout() -> Result<()> {
+    let server = create_mock_responses_server_repeating_assistant("Done").await;
     let codex_home = TempDir::new()?;
-    create_config_toml(codex_home.path())?;
+    create_config_toml(codex_home.path(), &server.uri())?;
 
     let mut mcp = McpProcess::new(codex_home.path()).await?;
     timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
@@ -38,17 +44,73 @@ async fn thread_archive_moves_rollout_into_archived_directory() -> Result<()> {
     let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(start_resp)?;
     assert!(!thread.id.is_empty());
 
-    // Locate the rollout path recorded for this thread id.
-    let rollout_path = find_thread_path_by_id_str(codex_home.path(), &thread.id)
-        .await?
-        .expect("expected rollout path for thread id to exist");
+    let rollout_path = thread.path.clone().expect("thread path");
+    assert!(
+        !rollout_path.exists(),
+        "fresh thread rollout should not exist yet at {}",
+        rollout_path.display()
+    );
+    assert!(
+        find_thread_path_by_id_str(codex_home.path(), &thread.id)
+            .await?
+            .is_none(),
+        "thread id should not be discoverable before rollout materialization"
+    );
+
+    // Archive should fail before the rollout is materialized.
+    let archive_id = mcp
+        .send_thread_archive_request(ThreadArchiveParams {
+            thread_id: thread.id.clone(),
+        })
+        .await?;
+    let archive_err: JSONRPCError = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_error_message(RequestId::Integer(archive_id)),
+    )
+    .await??;
+    assert!(
+        archive_err
+            .error
+            .message
+            .contains("no rollout found for thread id"),
+        "unexpected archive error: {}",
+        archive_err.error.message
+    );
+
+    // Materialize rollout via a real user turn and confirm archive succeeds.
+    let turn_start_id = mcp
+        .send_turn_start_request(TurnStartParams {
+            thread_id: thread.id.clone(),
+            input: vec![UserInput::Text {
+                text: "materialize".to_string(),
+                text_elements: Vec::new(),
+            }],
+            ..Default::default()
+        })
+        .await?;
+    let turn_start_response: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(turn_start_id)),
+    )
+    .await??;
+    let _: TurnStartResponse = to_response::<TurnStartResponse>(turn_start_response)?;
+    timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("turn/completed"),
+    )
+    .await??;
+
     assert!(
         rollout_path.exists(),
-        "expected {} to exist",
+        "expected rollout path {} to exist after first user message",
         rollout_path.display()
     );
 
-    // Archive the thread.
+    let discovered_path = find_thread_path_by_id_str(codex_home.path(), &thread.id)
+        .await?
+        .expect("expected rollout path for thread id to exist after materialization");
+    assert_paths_match_on_disk(&discovered_path, &rollout_path)?;
+
     let archive_id = mcp
         .send_thread_archive_request(ThreadArchiveParams {
             thread_id: thread.id.clone(),
@@ -80,14 +142,32 @@ async fn thread_archive_moves_rollout_into_archived_directory() -> Result<()> {
     Ok(())
 }
 
-fn create_config_toml(codex_home: &Path) -> std::io::Result<()> {
+fn create_config_toml(codex_home: &Path, server_uri: &str) -> std::io::Result<()> {
     let config_toml = codex_home.join("config.toml");
-    std::fs::write(config_toml, config_contents())
+    std::fs::write(config_toml, config_contents(server_uri))
 }
 
-fn config_contents() -> &'static str {
-    r#"model = "mock-model"
+fn config_contents(server_uri: &str) -> String {
+    format!(
+        r#"model = "mock-model"
 approval_policy = "never"
 sandbox_mode = "read-only"
+
+model_provider = "mock_provider"
+
+[model_providers.mock_provider]
+name = "Mock provider for test"
+base_url = "{server_uri}/v1"
+wire_api = "responses"
+request_max_retries = 0
+stream_max_retries = 0
 "#
+    )
+}
+
+fn assert_paths_match_on_disk(actual: &Path, expected: &Path) -> std::io::Result<()> {
+    let actual = actual.canonicalize()?;
+    let expected = expected.canonicalize()?;
+    assert_eq!(actual, expected);
+    Ok(())
 }

codex-rs/app-server/tests/suite/v2/thread_fork.rs

@@ -3,6 +3,7 @@ use app_test_support::McpProcess;
 use app_test_support::create_fake_rollout;
 use app_test_support::create_mock_responses_server_repeating_assistant;
 use app_test_support::to_response;
+use codex_app_server_protocol::JSONRPCError;
 use codex_app_server_protocol::JSONRPCNotification;
 use codex_app_server_protocol::JSONRPCResponse;
 use codex_app_server_protocol::RequestId;
@@ -10,6 +11,8 @@ use codex_app_server_protocol::SessionSource;
 use codex_app_server_protocol::ThreadForkParams;
 use codex_app_server_protocol::ThreadForkResponse;
 use codex_app_server_protocol::ThreadItem;
+use codex_app_server_protocol::ThreadStartParams;
+use codex_app_server_protocol::ThreadStartResponse;
 use codex_app_server_protocol::ThreadStartedNotification;
 use codex_app_server_protocol::TurnStatus;
 use codex_app_server_protocol::UserInput;
@@ -117,6 +120,51 @@ async fn thread_fork_creates_new_thread_and_emits_started() -> Result<()> {
     Ok(())
 }
 
+#[tokio::test]
+async fn thread_fork_rejects_unmaterialized_thread() -> Result<()> {
+    let server = create_mock_responses_server_repeating_assistant("Done").await;
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path(), &server.uri())?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let start_id = mcp
+        .send_thread_start_request(ThreadStartParams {
+            model: Some("mock-model".to_string()),
+            ..Default::default()
+        })
+        .await?;
+    let start_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(start_id)),
+    )
+    .await??;
+    let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(start_resp)?;
+
+    let fork_id = mcp
+        .send_thread_fork_request(ThreadForkParams {
+            thread_id: thread.id,
+            ..Default::default()
+        })
+        .await?;
+    let fork_err: JSONRPCError = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_error_message(RequestId::Integer(fork_id)),
+    )
+    .await??;
+    assert!(
+        fork_err
+            .error
+            .message
+            .contains("no rollout found for thread id"),
+        "unexpected fork error: {}",
+        fork_err.error.message
+    );
+
+    Ok(())
+}
+
 // Helper to create a config.toml pointing at the mock model server.
 fn create_config_toml(codex_home: &Path, server_uri: &str) -> std::io::Result<()> {
     let config_toml = codex_home.join("config.toml");

codex-rs/app-server/tests/suite/v2/thread_read.rs

@@ -3,12 +3,15 @@ use app_test_support::McpProcess;
 use app_test_support::create_fake_rollout_with_text_elements;
 use app_test_support::create_mock_responses_server_repeating_assistant;
 use app_test_support::to_response;
+use codex_app_server_protocol::JSONRPCError;
 use codex_app_server_protocol::JSONRPCResponse;
 use codex_app_server_protocol::RequestId;
 use codex_app_server_protocol::SessionSource;
 use codex_app_server_protocol::ThreadItem;
 use codex_app_server_protocol::ThreadReadParams;
 use codex_app_server_protocol::ThreadReadResponse;
+use codex_app_server_protocol::ThreadStartParams;
+use codex_app_server_protocol::ThreadStartResponse;
 use codex_app_server_protocol::TurnStatus;
 use codex_app_server_protocol::UserInput;
 use codex_protocol::user_input::ByteRange;
@@ -134,6 +137,105 @@ async fn thread_read_can_include_turns() -> Result<()> {
     Ok(())
 }
 
+#[tokio::test]
+async fn thread_read_loaded_thread_returns_precomputed_path_before_materialization() -> Result<()> {
+    let server = create_mock_responses_server_repeating_assistant("Done").await;
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path(), &server.uri())?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let start_id = mcp
+        .send_thread_start_request(ThreadStartParams {
+            model: Some("mock-model".to_string()),
+            ..Default::default()
+        })
+        .await?;
+    let start_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(start_id)),
+    )
+    .await??;
+    let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(start_resp)?;
+    let thread_path = thread.path.clone().expect("thread path");
+    assert!(
+        !thread_path.exists(),
+        "fresh thread rollout should not be materialized yet"
+    );
+
+    let read_id = mcp
+        .send_thread_read_request(ThreadReadParams {
+            thread_id: thread.id.clone(),
+            include_turns: false,
+        })
+        .await?;
+    let read_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(read_id)),
+    )
+    .await??;
+    let ThreadReadResponse { thread: read } = to_response::<ThreadReadResponse>(read_resp)?;
+
+    assert_eq!(read.id, thread.id);
+    assert_eq!(read.path, Some(thread_path));
+    assert!(read.preview.is_empty());
+    assert_eq!(read.turns.len(), 0);
+
+    Ok(())
+}
+
+#[tokio::test]
+async fn thread_read_include_turns_rejects_unmaterialized_loaded_thread() -> Result<()> {
+    let server = create_mock_responses_server_repeating_assistant("Done").await;
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path(), &server.uri())?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let start_id = mcp
+        .send_thread_start_request(ThreadStartParams {
+            model: Some("mock-model".to_string()),
+            ..Default::default()
+        })
+        .await?;
+    let start_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(start_id)),
+    )
+    .await??;
+    let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(start_resp)?;
+    let thread_path = thread.path.clone().expect("thread path");
+    assert!(
+        !thread_path.exists(),
+        "fresh thread rollout should not be materialized yet"
+    );
+
+    let read_id = mcp
+        .send_thread_read_request(ThreadReadParams {
+            thread_id: thread.id.clone(),
+            include_turns: true,
+        })
+        .await?;
+    let read_err: JSONRPCError = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_error_message(RequestId::Integer(read_id)),
+    )
+    .await??;
+
+    assert!(
+        read_err
+            .error
+            .message
+            .contains("includeTurns is unavailable before first user message"),
+        "unexpected error: {}",
+        read_err.error.message
+    );
+
+    Ok(())
+}
+
 // Helper to create a config.toml pointing at the mock model server.
 fn create_config_toml(codex_home: &Path, server_uri: &str) -> std::io::Result<()> {
     let config_toml = codex_home.join("config.toml");

codex-rs/app-server/tests/suite/v2/thread_resume.rs

@@ -35,7 +35,7 @@ const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs
 const CODEX_5_2_INSTRUCTIONS_TEMPLATE_DEFAULT: &str = "You are Codex, a coding agent based on GPT-5. You and the user share the same workspace and collaborate to achieve the user's goals.";
 
 #[tokio::test]
-async fn thread_resume_returns_original_thread() -> Result<()> {
+async fn thread_resume_rejects_unmaterialized_thread() -> Result<()> {
     let server = create_mock_responses_server_repeating_assistant("Done").await;
     let codex_home = TempDir::new()?;
     create_config_toml(codex_home.path(), &server.uri())?;
@@ -57,24 +57,26 @@ async fn thread_resume_returns_original_thread() -> Result<()> {
     .await??;
     let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(start_resp)?;
 
-    // Resume it via v2 API.
+    // Resume should fail before the first user message materializes rollout storage.
     let resume_id = mcp
         .send_thread_resume_request(ThreadResumeParams {
             thread_id: thread.id.clone(),
             ..Default::default()
         })
         .await?;
-    let resume_resp: JSONRPCResponse = timeout(
+    let resume_err: JSONRPCError = timeout(
         DEFAULT_READ_TIMEOUT,
-        mcp.read_stream_until_response_message(RequestId::Integer(resume_id)),
+        mcp.read_stream_until_error_message(RequestId::Integer(resume_id)),
     )
     .await??;
-    let ThreadResumeResponse {
-        thread: resumed, ..
-    } = to_response::<ThreadResumeResponse>(resume_resp)?;
-    let mut expected = thread;
-    expected.updated_at = resumed.updated_at;
-    assert_eq!(resumed, expected);
+    assert!(
+        resume_err
+            .error
+            .message
+            .contains("no rollout found for thread id"),
+        "unexpected resume error: {}",
+        resume_err.error.message
+    );
 
     Ok(())
 }
@@ -322,6 +324,27 @@ async fn thread_resume_prefers_path_over_thread_id() -> Result<()> {
     .await??;
     let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(start_resp)?;
 
+    let turn_id = mcp
+        .send_turn_start_request(TurnStartParams {
+            thread_id: thread.id.clone(),
+            input: vec![UserInput::Text {
+                text: "materialize".to_string(),
+                text_elements: Vec::new(),
+            }],
+            ..Default::default()
+        })
+        .await?;
+    timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(turn_id)),
+    )
+    .await??;
+    timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("turn/completed"),
+    )
+    .await??;
+
     let thread_path = thread.path.clone().expect("thread path");
     let resume_id = mcp
         .send_thread_resume_request(ThreadResumeParams {
@@ -339,9 +362,8 @@ async fn thread_resume_prefers_path_over_thread_id() -> Result<()> {
     let ThreadResumeResponse {
         thread: resumed, ..
     } = to_response::<ThreadResumeResponse>(resume_resp)?;
-    let mut expected = thread;
-    expected.updated_at = resumed.updated_at;
-    assert_eq!(resumed, expected);
+    assert_eq!(resumed.id, thread.id);
+    assert_eq!(resumed.path, thread.path);
 
     Ok(())
 }
@@ -412,12 +434,17 @@ async fn thread_resume_accepts_personality_override() -> Result<()> {
     skip_if_no_network!(Ok(()));
 
     let server = responses::start_mock_server().await;
-    let body = responses::sse(vec![
+    let first_body = responses::sse(vec![
         responses::ev_response_created("resp-1"),
         responses::ev_assistant_message("msg-1", "Done"),
         responses::ev_completed("resp-1"),
     ]);
-    let response_mock = responses::mount_sse_once(&server, body).await;
+    let second_body = responses::sse(vec![
+        responses::ev_response_created("resp-2"),
+        responses::ev_assistant_message("msg-2", "Done"),
+        responses::ev_completed("resp-2"),
+    ]);
+    let response_mock = responses::mount_sse_sequence(&server, vec![first_body, second_body]).await;
 
     let codex_home = TempDir::new()?;
     create_config_toml(codex_home.path(), &server.uri())?;
@@ -438,9 +465,30 @@ async fn thread_resume_accepts_personality_override() -> Result<()> {
     .await??;
     let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(start_resp)?;
 
+    let materialize_id = mcp
+        .send_turn_start_request(TurnStartParams {
+            thread_id: thread.id.clone(),
+            input: vec![UserInput::Text {
+                text: "seed history".to_string(),
+                text_elements: Vec::new(),
+            }],
+            ..Default::default()
+        })
+        .await?;
+    timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(materialize_id)),
+    )
+    .await??;
+    timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("turn/completed"),
+    )
+    .await??;
+
     let resume_id = mcp
         .send_thread_resume_request(ThreadResumeParams {
-            thread_id: thread.id.clone(),
+            thread_id: thread.id,
             model: Some("gpt-5.2-codex".to_string()),
             personality: Some(Personality::Friendly),
             ..Default::default()
@@ -451,11 +499,11 @@ async fn thread_resume_accepts_personality_override() -> Result<()> {
         mcp.read_stream_until_response_message(RequestId::Integer(resume_id)),
     )
     .await??;
-    let _resume: ThreadResumeResponse = to_response::<ThreadResumeResponse>(resume_resp)?;
+    let resume: ThreadResumeResponse = to_response::<ThreadResumeResponse>(resume_resp)?;
 
     let turn_id = mcp
         .send_turn_start_request(TurnStartParams {
-            thread_id: thread.id,
+            thread_id: resume.thread.id,
             input: vec![UserInput::Text {
                 text: "Hello".to_string(),
                 text_elements: Vec::new(),
@@ -475,7 +523,10 @@ async fn thread_resume_accepts_personality_override() -> Result<()> {
     )
     .await??;
 
-    let request = response_mock.single_request();
+    let requests = response_mock.requests();
+    let request = requests
+        .last()
+        .expect("expected request for resumed thread turn");
     let developer_texts = request.message_input_texts("developer");
     assert!(
         developer_texts

codex-rs/app-server/tests/suite/v2/thread_start.rs

@@ -59,6 +59,12 @@ async fn thread_start_creates_thread_and_emits_started() -> Result<()> {
         thread.created_at > 0,
         "created_at should be a positive UNIX timestamp"
     );
+    let thread_path = thread.path.clone().expect("thread path should be present");
+    assert!(thread_path.is_absolute(), "thread path should be absolute");
+    assert!(
+        !thread_path.exists(),
+        "fresh thread rollout should not be materialized until first user message"
+    );
 
     // A corresponding thread/started notification should arrive.
     let notif: JSONRPCNotification = timeout(
@@ -114,6 +120,37 @@ model_reasoning_effort = "high"
     Ok(())
 }
 
+#[tokio::test]
+async fn thread_start_ephemeral_remains_pathless() -> Result<()> {
+    let server = create_mock_responses_server_repeating_assistant("Done").await;
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path(), &server.uri())?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let req_id = mcp
+        .send_thread_start_request(ThreadStartParams {
+            model: Some("gpt-5.1".to_string()),
+            ephemeral: Some(true),
+            ..Default::default()
+        })
+        .await?;
+
+    let resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(req_id)),
+    )
+    .await??;
+    let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(resp)?;
+    assert_eq!(
+        thread.path, None,
+        "ephemeral threads should not expose a path"
+    );
+
+    Ok(())
+}
+
 #[tokio::test]
 async fn thread_start_fails_when_required_mcp_server_fails_to_initialize() -> Result<()> {
     let server = create_mock_responses_server_repeating_assistant("Done").await;

codex-rs/app-server/tests/suite/v2/thread_unarchive.rs

@@ -1,5 +1,6 @@
 use anyhow::Result;
 use app_test_support::McpProcess;
+use app_test_support::create_mock_responses_server_repeating_assistant;
 use app_test_support::to_response;
 use codex_app_server_protocol::JSONRPCResponse;
 use codex_app_server_protocol::RequestId;
@@ -9,6 +10,9 @@ use codex_app_server_protocol::ThreadStartParams;
 use codex_app_server_protocol::ThreadStartResponse;
 use codex_app_server_protocol::ThreadUnarchiveParams;
 use codex_app_server_protocol::ThreadUnarchiveResponse;
+use codex_app_server_protocol::TurnStartParams;
+use codex_app_server_protocol::TurnStartResponse;
+use codex_app_server_protocol::UserInput;
 use codex_core::find_archived_thread_path_by_id_str;
 use codex_core::find_thread_path_by_id_str;
 use std::fs::FileTimes;
@@ -23,8 +27,9 @@ const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs
 
 #[tokio::test]
 async fn thread_unarchive_moves_rollout_back_into_sessions_directory() -> Result<()> {
+    let server = create_mock_responses_server_repeating_assistant("Done").await;
     let codex_home = TempDir::new()?;
-    create_config_toml(codex_home.path())?;
+    create_config_toml(codex_home.path(), &server.uri())?;
 
     let mut mcp = McpProcess::new(codex_home.path()).await?;
     timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
@@ -42,9 +47,34 @@ async fn thread_unarchive_moves_rollout_back_into_sessions_directory() -> Result
     .await??;
     let ThreadStartResponse { thread, .. } = to_response::<ThreadStartResponse>(start_resp)?;
 
-    let rollout_path = find_thread_path_by_id_str(codex_home.path(), &thread.id)
+    let rollout_path = thread.path.clone().expect("thread path");
+
+    let turn_start_id = mcp
+        .send_turn_start_request(TurnStartParams {
+            thread_id: thread.id.clone(),
+            input: vec![UserInput::Text {
+                text: "materialize".to_string(),
+                text_elements: Vec::new(),
+            }],
+            ..Default::default()
+        })
+        .await?;
+    let turn_start_response: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(turn_start_id)),
+    )
+    .await??;
+    let _: TurnStartResponse = to_response::<TurnStartResponse>(turn_start_response)?;
+    timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("turn/completed"),
+    )
+    .await??;
+
+    let found_rollout_path = find_thread_path_by_id_str(codex_home.path(), &thread.id)
         .await?
         .expect("expected rollout path for thread id to exist");
+    assert_paths_match_on_disk(&found_rollout_path, &rollout_path)?;
 
     let archive_id = mcp
         .send_thread_archive_request(ThreadArchiveParams {
@@ -108,14 +138,32 @@ async fn thread_unarchive_moves_rollout_back_into_sessions_directory() -> Result
     Ok(())
 }
 
-fn create_config_toml(codex_home: &Path) -> std::io::Result<()> {
+fn create_config_toml(codex_home: &Path, server_uri: &str) -> std::io::Result<()> {
     let config_toml = codex_home.join("config.toml");
-    std::fs::write(config_toml, config_contents())
+    std::fs::write(config_toml, config_contents(server_uri))
 }
 
-fn config_contents() -> &'static str {
-    r#"model = "mock-model"
+fn config_contents(server_uri: &str) -> String {
+    format!(
+        r#"model = "mock-model"
 approval_policy = "never"
 sandbox_mode = "read-only"
+
+model_provider = "mock_provider"
+
+[model_providers.mock_provider]
+name = "Mock provider for test"
+base_url = "{server_uri}/v1"
+wire_api = "responses"
+request_max_retries = 0
+stream_max_retries = 0
 "#
+    )
+}
+
+fn assert_paths_match_on_disk(actual: &Path, expected: &Path) -> std::io::Result<()> {
+    let actual = actual.canonicalize()?;
+    let expected = expected.canonicalize()?;
+    assert_eq!(actual, expected);
+    Ok(())
 }