Phase 1: Repository & Infrastructure Setup

- Renamed directories: codex-rs -> llmx-rs, codex-cli -> llmx-cli
- Updated package.json files:
  - Root: llmx-monorepo
  - CLI: @llmx/llmx
  - SDK: @llmx/llmx-sdk
- Updated pnpm workspace configuration
- Renamed binary: codex.js -> llmx.js
- Updated environment variables: CODEX_* -> LLMX_*
- Changed repository URLs to valknar/llmx

🤖 Generated with Claude Code

llmx-rs/app-server/tests/all.rs

@@ -0,0 +1,3 @@
+// Single integration test binary that aggregates all test modules.
+// The submodules live in `tests/suite/`.
+mod suite;

llmx-rs/app-server/tests/common/Cargo.toml

@@ -0,0 +1,26 @@
+[package]
+edition = "2024"
+name = "app_test_support"
+version = { workspace = true }
+
+[lib]
+path = "lib.rs"
+
+[dependencies]
+anyhow = { workspace = true }
+assert_cmd = { workspace = true }
+base64 = { workspace = true }
+chrono = { workspace = true }
+codex-app-server-protocol = { workspace = true }
+codex-core = { workspace = true }
+codex-protocol = { workspace = true }
+serde = { workspace = true }
+serde_json = { workspace = true }
+tokio = { workspace = true, features = [
+    "io-std",
+    "macros",
+    "process",
+    "rt-multi-thread",
+] }
+uuid = { workspace = true }
+wiremock = { workspace = true }

llmx-rs/app-server/tests/common/auth_fixtures.rs

@@ -0,0 +1,135 @@
+use std::path::Path;
+
+use anyhow::Context;
+use anyhow::Result;
+use base64::Engine;
+use base64::engine::general_purpose::URL_SAFE_NO_PAD;
+use chrono::DateTime;
+use chrono::Utc;
+use codex_core::auth::AuthCredentialsStoreMode;
+use codex_core::auth::AuthDotJson;
+use codex_core::auth::save_auth;
+use codex_core::token_data::TokenData;
+use codex_core::token_data::parse_id_token;
+use serde_json::json;
+
+/// Builder for writing a fake ChatGPT auth.json in tests.
+#[derive(Debug, Clone)]
+pub struct ChatGptAuthFixture {
+    access_token: String,
+    refresh_token: String,
+    account_id: Option<String>,
+    claims: ChatGptIdTokenClaims,
+    last_refresh: Option<Option<DateTime<Utc>>>,
+}
+
+impl ChatGptAuthFixture {
+    pub fn new(access_token: impl Into<String>) -> Self {
+        Self {
+            access_token: access_token.into(),
+            refresh_token: "refresh-token".to_string(),
+            account_id: None,
+            claims: ChatGptIdTokenClaims::default(),
+            last_refresh: None,
+        }
+    }
+
+    pub fn refresh_token(mut self, refresh_token: impl Into<String>) -> Self {
+        self.refresh_token = refresh_token.into();
+        self
+    }
+
+    pub fn account_id(mut self, account_id: impl Into<String>) -> Self {
+        self.account_id = Some(account_id.into());
+        self
+    }
+
+    pub fn plan_type(mut self, plan_type: impl Into<String>) -> Self {
+        self.claims.plan_type = Some(plan_type.into());
+        self
+    }
+
+    pub fn email(mut self, email: impl Into<String>) -> Self {
+        self.claims.email = Some(email.into());
+        self
+    }
+
+    pub fn last_refresh(mut self, last_refresh: Option<DateTime<Utc>>) -> Self {
+        self.last_refresh = Some(last_refresh);
+        self
+    }
+
+    pub fn claims(mut self, claims: ChatGptIdTokenClaims) -> Self {
+        self.claims = claims;
+        self
+    }
+}
+
+#[derive(Debug, Clone, Default)]
+pub struct ChatGptIdTokenClaims {
+    pub email: Option<String>,
+    pub plan_type: Option<String>,
+}
+
+impl ChatGptIdTokenClaims {
+    pub fn new() -> Self {
+        Self::default()
+    }
+
+    pub fn email(mut self, email: impl Into<String>) -> Self {
+        self.email = Some(email.into());
+        self
+    }
+
+    pub fn plan_type(mut self, plan_type: impl Into<String>) -> Self {
+        self.plan_type = Some(plan_type.into());
+        self
+    }
+}
+
+pub fn encode_id_token(claims: &ChatGptIdTokenClaims) -> Result<String> {
+    let header = json!({ "alg": "none", "typ": "JWT" });
+    let mut payload = serde_json::Map::new();
+    if let Some(email) = &claims.email {
+        payload.insert("email".to_string(), json!(email));
+    }
+    if let Some(plan_type) = &claims.plan_type {
+        payload.insert(
+            "https://api.openai.com/auth".to_string(),
+            json!({ "chatgpt_plan_type": plan_type }),
+        );
+    }
+    let payload = serde_json::Value::Object(payload);
+
+    let header_b64 =
+        URL_SAFE_NO_PAD.encode(serde_json::to_vec(&header).context("serialize jwt header")?);
+    let payload_b64 =
+        URL_SAFE_NO_PAD.encode(serde_json::to_vec(&payload).context("serialize jwt payload")?);
+    let signature_b64 = URL_SAFE_NO_PAD.encode(b"signature");
+    Ok(format!("{header_b64}.{payload_b64}.{signature_b64}"))
+}
+
+pub fn write_chatgpt_auth(
+    codex_home: &Path,
+    fixture: ChatGptAuthFixture,
+    cli_auth_credentials_store_mode: AuthCredentialsStoreMode,
+) -> Result<()> {
+    let id_token_raw = encode_id_token(&fixture.claims)?;
+    let id_token = parse_id_token(&id_token_raw).context("parse id token")?;
+    let tokens = TokenData {
+        id_token,
+        access_token: fixture.access_token,
+        refresh_token: fixture.refresh_token,
+        account_id: fixture.account_id,
+    };
+
+    let last_refresh = fixture.last_refresh.unwrap_or_else(|| Some(Utc::now()));
+
+    let auth = AuthDotJson {
+        openai_api_key: None,
+        tokens: Some(tokens),
+        last_refresh,
+    };
+
+    save_auth(codex_home, &auth, cli_auth_credentials_store_mode).context("write auth.json")
+}

llmx-rs/app-server/tests/common/lib.rs

@@ -0,0 +1,25 @@
+mod auth_fixtures;
+mod mcp_process;
+mod mock_model_server;
+mod responses;
+mod rollout;
+
+pub use auth_fixtures::ChatGptAuthFixture;
+pub use auth_fixtures::ChatGptIdTokenClaims;
+pub use auth_fixtures::encode_id_token;
+pub use auth_fixtures::write_chatgpt_auth;
+use codex_app_server_protocol::JSONRPCResponse;
+pub use mcp_process::McpProcess;
+pub use mock_model_server::create_mock_chat_completions_server;
+pub use mock_model_server::create_mock_chat_completions_server_unchecked;
+pub use responses::create_apply_patch_sse_response;
+pub use responses::create_final_assistant_message_sse_response;
+pub use responses::create_shell_sse_response;
+pub use rollout::create_fake_rollout;
+use serde::de::DeserializeOwned;
+
+pub fn to_response<T: DeserializeOwned>(response: JSONRPCResponse) -> anyhow::Result<T> {
+    let value = serde_json::to_value(response.result)?;
+    let codex_response = serde_json::from_value(value)?;
+    Ok(codex_response)
+}

llmx-rs/app-server/tests/common/mcp_process.rs

@@ -0,0 +1,631 @@
+use std::collections::VecDeque;
+use std::path::Path;
+use std::process::Stdio;
+use std::sync::atomic::AtomicI64;
+use std::sync::atomic::Ordering;
+use tokio::io::AsyncBufReadExt;
+use tokio::io::AsyncWriteExt;
+use tokio::io::BufReader;
+use tokio::process::Child;
+use tokio::process::ChildStdin;
+use tokio::process::ChildStdout;
+
+use anyhow::Context;
+use assert_cmd::prelude::*;
+use codex_app_server_protocol::AddConversationListenerParams;
+use codex_app_server_protocol::ArchiveConversationParams;
+use codex_app_server_protocol::CancelLoginAccountParams;
+use codex_app_server_protocol::CancelLoginChatGptParams;
+use codex_app_server_protocol::ClientInfo;
+use codex_app_server_protocol::ClientNotification;
+use codex_app_server_protocol::FeedbackUploadParams;
+use codex_app_server_protocol::GetAccountParams;
+use codex_app_server_protocol::GetAuthStatusParams;
+use codex_app_server_protocol::InitializeParams;
+use codex_app_server_protocol::InterruptConversationParams;
+use codex_app_server_protocol::JSONRPCError;
+use codex_app_server_protocol::JSONRPCMessage;
+use codex_app_server_protocol::JSONRPCNotification;
+use codex_app_server_protocol::JSONRPCRequest;
+use codex_app_server_protocol::JSONRPCResponse;
+use codex_app_server_protocol::ListConversationsParams;
+use codex_app_server_protocol::LoginApiKeyParams;
+use codex_app_server_protocol::ModelListParams;
+use codex_app_server_protocol::NewConversationParams;
+use codex_app_server_protocol::RemoveConversationListenerParams;
+use codex_app_server_protocol::RequestId;
+use codex_app_server_protocol::ResumeConversationParams;
+use codex_app_server_protocol::SendUserMessageParams;
+use codex_app_server_protocol::SendUserTurnParams;
+use codex_app_server_protocol::ServerRequest;
+use codex_app_server_protocol::SetDefaultModelParams;
+use codex_app_server_protocol::ThreadArchiveParams;
+use codex_app_server_protocol::ThreadListParams;
+use codex_app_server_protocol::ThreadResumeParams;
+use codex_app_server_protocol::ThreadStartParams;
+use codex_app_server_protocol::TurnInterruptParams;
+use codex_app_server_protocol::TurnStartParams;
+use std::process::Command as StdCommand;
+use tokio::process::Command;
+
+pub struct McpProcess {
+    next_request_id: AtomicI64,
+    /// Retain this child process until the client is dropped. The Tokio runtime
+    /// will make a "best effort" to reap the process after it exits, but it is
+    /// not a guarantee. See the `kill_on_drop` documentation for details.
+    #[allow(dead_code)]
+    process: Child,
+    stdin: ChildStdin,
+    stdout: BufReader<ChildStdout>,
+    pending_user_messages: VecDeque<JSONRPCNotification>,
+}
+
+impl McpProcess {
+    pub async fn new(codex_home: &Path) -> anyhow::Result<Self> {
+        Self::new_with_env(codex_home, &[]).await
+    }
+
+    /// Creates a new MCP process, allowing tests to override or remove
+    /// specific environment variables for the child process only.
+    ///
+    /// Pass a tuple of (key, Some(value)) to set/override, or (key, None) to
+    /// remove a variable from the child's environment.
+    pub async fn new_with_env(
+        codex_home: &Path,
+        env_overrides: &[(&str, Option<&str>)],
+    ) -> anyhow::Result<Self> {
+        // Use assert_cmd to locate the binary path and then switch to tokio::process::Command
+        let std_cmd = StdCommand::cargo_bin("codex-app-server")
+            .context("should find binary for codex-mcp-server")?;
+
+        let program = std_cmd.get_program().to_owned();
+
+        let mut cmd = Command::new(program);
+
+        cmd.stdin(Stdio::piped());
+        cmd.stdout(Stdio::piped());
+        cmd.stderr(Stdio::piped());
+        cmd.env("CODEX_HOME", codex_home);
+        cmd.env("RUST_LOG", "debug");
+
+        for (k, v) in env_overrides {
+            match v {
+                Some(val) => {
+                    cmd.env(k, val);
+                }
+                None => {
+                    cmd.env_remove(k);
+                }
+            }
+        }
+
+        let mut process = cmd
+            .kill_on_drop(true)
+            .spawn()
+            .context("codex-mcp-server proc should start")?;
+        let stdin = process
+            .stdin
+            .take()
+            .ok_or_else(|| anyhow::format_err!("mcp should have stdin fd"))?;
+        let stdout = process
+            .stdout
+            .take()
+            .ok_or_else(|| anyhow::format_err!("mcp should have stdout fd"))?;
+        let stdout = BufReader::new(stdout);
+
+        // Forward child's stderr to our stderr so failures are visible even
+        // when stdout/stderr are captured by the test harness.
+        if let Some(stderr) = process.stderr.take() {
+            let mut stderr_reader = BufReader::new(stderr).lines();
+            tokio::spawn(async move {
+                while let Ok(Some(line)) = stderr_reader.next_line().await {
+                    eprintln!("[mcp stderr] {line}");
+                }
+            });
+        }
+        Ok(Self {
+            next_request_id: AtomicI64::new(0),
+            process,
+            stdin,
+            stdout,
+            pending_user_messages: VecDeque::new(),
+        })
+    }
+
+    /// Performs the initialization handshake with the MCP server.
+    pub async fn initialize(&mut self) -> anyhow::Result<()> {
+        let params = Some(serde_json::to_value(InitializeParams {
+            client_info: ClientInfo {
+                name: "codex-app-server-tests".to_string(),
+                title: None,
+                version: "0.1.0".to_string(),
+            },
+        })?);
+        let req_id = self.send_request("initialize", params).await?;
+        let initialized = self.read_jsonrpc_message().await?;
+        let JSONRPCMessage::Response(response) = initialized else {
+            unreachable!("expected JSONRPCMessage::Response for initialize, got {initialized:?}");
+        };
+        if response.id != RequestId::Integer(req_id) {
+            anyhow::bail!(
+                "initialize response id mismatch: expected {}, got {:?}",
+                req_id,
+                response.id
+            );
+        }
+
+        // Send notifications/initialized to ack the response.
+        self.send_notification(ClientNotification::Initialized)
+            .await?;
+
+        Ok(())
+    }
+
+    /// Send a `newConversation` JSON-RPC request.
+    pub async fn send_new_conversation_request(
+        &mut self,
+        params: NewConversationParams,
+    ) -> anyhow::Result<i64> {
+        let params = Some(serde_json::to_value(params)?);
+        self.send_request("newConversation", params).await
+    }
+
+    /// Send an `archiveConversation` JSON-RPC request.
+    pub async fn send_archive_conversation_request(
+        &mut self,
+        params: ArchiveConversationParams,
+    ) -> anyhow::Result<i64> {
+        let params = Some(serde_json::to_value(params)?);
+        self.send_request("archiveConversation", params).await
+    }
+
+    /// Send an `addConversationListener` JSON-RPC request.
+    pub async fn send_add_conversation_listener_request(
+        &mut self,
+        params: AddConversationListenerParams,
+    ) -> anyhow::Result<i64> {
+        let params = Some(serde_json::to_value(params)?);
+        self.send_request("addConversationListener", params).await
+    }
+
+    /// Send a `sendUserMessage` JSON-RPC request with a single text item.
+    pub async fn send_send_user_message_request(
+        &mut self,
+        params: SendUserMessageParams,
+    ) -> anyhow::Result<i64> {
+        // Wire format expects variants in camelCase; text item uses external tagging.
+        let params = Some(serde_json::to_value(params)?);
+        self.send_request("sendUserMessage", params).await
+    }
+
+    /// Send a `removeConversationListener` JSON-RPC request.
+    pub async fn send_remove_conversation_listener_request(
+        &mut self,
+        params: RemoveConversationListenerParams,
+    ) -> anyhow::Result<i64> {
+        let params = Some(serde_json::to_value(params)?);
+        self.send_request("removeConversationListener", params)
+            .await
+    }
+
+    /// Send a `sendUserTurn` JSON-RPC request.
+    pub async fn send_send_user_turn_request(
+        &mut self,
+        params: SendUserTurnParams,
+    ) -> anyhow::Result<i64> {
+        let params = Some(serde_json::to_value(params)?);
+        self.send_request("sendUserTurn", params).await
+    }
+
+    /// Send a `interruptConversation` JSON-RPC request.
+    pub async fn send_interrupt_conversation_request(
+        &mut self,
+        params: InterruptConversationParams,
+    ) -> anyhow::Result<i64> {
+        let params = Some(serde_json::to_value(params)?);
+        self.send_request("interruptConversation", params).await
+    }
+
+    /// Send a `getAuthStatus` JSON-RPC request.
+    pub async fn send_get_auth_status_request(
+        &mut self,
+        params: GetAuthStatusParams,
+    ) -> anyhow::Result<i64> {
+        let params = Some(serde_json::to_value(params)?);
+        self.send_request("getAuthStatus", params).await
+    }
+
+    /// Send a `getUserSavedConfig` JSON-RPC request.
+    pub async fn send_get_user_saved_config_request(&mut self) -> anyhow::Result<i64> {
+        self.send_request("getUserSavedConfig", None).await
+    }
+
+    /// Send a `getUserAgent` JSON-RPC request.
+    pub async fn send_get_user_agent_request(&mut self) -> anyhow::Result<i64> {
+        self.send_request("getUserAgent", None).await
+    }
+
+    /// Send an `account/rateLimits/read` JSON-RPC request.
+    pub async fn send_get_account_rate_limits_request(&mut self) -> anyhow::Result<i64> {
+        self.send_request("account/rateLimits/read", None).await
+    }
+
+    /// Send an `account/read` JSON-RPC request.
+    pub async fn send_get_account_request(
+        &mut self,
+        params: GetAccountParams,
+    ) -> anyhow::Result<i64> {
+        let params = Some(serde_json::to_value(params)?);
+        self.send_request("account/read", params).await
+    }
+
+    /// Send a `feedback/upload` JSON-RPC request.
+    pub async fn send_feedback_upload_request(
+        &mut self,
+        params: FeedbackUploadParams,
+    ) -> anyhow::Result<i64> {
+        let params = Some(serde_json::to_value(params)?);
+        self.send_request("feedback/upload", params).await
+    }
+
+    /// Send a `userInfo` JSON-RPC request.
+    pub async fn send_user_info_request(&mut self) -> anyhow::Result<i64> {
+        self.send_request("userInfo", None).await
+    }
+
+    /// Send a `setDefaultModel` JSON-RPC request.
+    pub async fn send_set_default_model_request(
+        &mut self,
+        params: SetDefaultModelParams,
+    ) -> anyhow::Result<i64> {
+        let params = Some(serde_json::to_value(params)?);
+        self.send_request("setDefaultModel", params).await
+    }
+
+    /// Send a `listConversations` JSON-RPC request.
+    pub async fn send_list_conversations_request(
+        &mut self,
+        params: ListConversationsParams,
+    ) -> anyhow::Result<i64> {
+        let params = Some(serde_json::to_value(params)?);
+        self.send_request("listConversations", params).await
+    }
+
+    /// Send a `thread/start` JSON-RPC request.
+    pub async fn send_thread_start_request(
+        &mut self,
+        params: ThreadStartParams,
+    ) -> anyhow::Result<i64> {
+        let params = Some(serde_json::to_value(params)?);
+        self.send_request("thread/start", params).await
+    }
+
+    /// Send a `thread/resume` JSON-RPC request.
+    pub async fn send_thread_resume_request(
+        &mut self,
+        params: ThreadResumeParams,
+    ) -> anyhow::Result<i64> {
+        let params = Some(serde_json::to_value(params)?);
+        self.send_request("thread/resume", params).await
+    }
+
+    /// Send a `thread/archive` JSON-RPC request.
+    pub async fn send_thread_archive_request(
+        &mut self,
+        params: ThreadArchiveParams,
+    ) -> anyhow::Result<i64> {
+        let params = Some(serde_json::to_value(params)?);
+        self.send_request("thread/archive", params).await
+    }
+
+    /// Send a `thread/list` JSON-RPC request.
+    pub async fn send_thread_list_request(
+        &mut self,
+        params: ThreadListParams,
+    ) -> anyhow::Result<i64> {
+        let params = Some(serde_json::to_value(params)?);
+        self.send_request("thread/list", params).await
+    }
+
+    /// Send a `model/list` JSON-RPC request.
+    pub async fn send_list_models_request(
+        &mut self,
+        params: ModelListParams,
+    ) -> anyhow::Result<i64> {
+        let params = Some(serde_json::to_value(params)?);
+        self.send_request("model/list", params).await
+    }
+
+    /// Send a `resumeConversation` JSON-RPC request.
+    pub async fn send_resume_conversation_request(
+        &mut self,
+        params: ResumeConversationParams,
+    ) -> anyhow::Result<i64> {
+        let params = Some(serde_json::to_value(params)?);
+        self.send_request("resumeConversation", params).await
+    }
+
+    /// Send a `loginApiKey` JSON-RPC request.
+    pub async fn send_login_api_key_request(
+        &mut self,
+        params: LoginApiKeyParams,
+    ) -> anyhow::Result<i64> {
+        let params = Some(serde_json::to_value(params)?);
+        self.send_request("loginApiKey", params).await
+    }
+
+    /// Send a `loginChatGpt` JSON-RPC request.
+    pub async fn send_login_chat_gpt_request(&mut self) -> anyhow::Result<i64> {
+        self.send_request("loginChatGpt", None).await
+    }
+
+    /// Send a `turn/start` JSON-RPC request (v2).
+    pub async fn send_turn_start_request(
+        &mut self,
+        params: TurnStartParams,
+    ) -> anyhow::Result<i64> {
+        let params = Some(serde_json::to_value(params)?);
+        self.send_request("turn/start", params).await
+    }
+
+    /// Send a `turn/interrupt` JSON-RPC request (v2).
+    pub async fn send_turn_interrupt_request(
+        &mut self,
+        params: TurnInterruptParams,
+    ) -> anyhow::Result<i64> {
+        let params = Some(serde_json::to_value(params)?);
+        self.send_request("turn/interrupt", params).await
+    }
+
+    /// Send a `cancelLoginChatGpt` JSON-RPC request.
+    pub async fn send_cancel_login_chat_gpt_request(
+        &mut self,
+        params: CancelLoginChatGptParams,
+    ) -> anyhow::Result<i64> {
+        let params = Some(serde_json::to_value(params)?);
+        self.send_request("cancelLoginChatGpt", params).await
+    }
+
+    /// Send a `logoutChatGpt` JSON-RPC request.
+    pub async fn send_logout_chat_gpt_request(&mut self) -> anyhow::Result<i64> {
+        self.send_request("logoutChatGpt", None).await
+    }
+
+    /// Send an `account/logout` JSON-RPC request.
+    pub async fn send_logout_account_request(&mut self) -> anyhow::Result<i64> {
+        self.send_request("account/logout", None).await
+    }
+
+    /// Send an `account/login/start` JSON-RPC request for API key login.
+    pub async fn send_login_account_api_key_request(
+        &mut self,
+        api_key: &str,
+    ) -> anyhow::Result<i64> {
+        let params = serde_json::json!({
+            "type": "apiKey",
+            "apiKey": api_key,
+        });
+        self.send_request("account/login/start", Some(params)).await
+    }
+
+    /// Send an `account/login/start` JSON-RPC request for ChatGPT login.
+    pub async fn send_login_account_chatgpt_request(&mut self) -> anyhow::Result<i64> {
+        let params = serde_json::json!({
+            "type": "chatgpt"
+        });
+        self.send_request("account/login/start", Some(params)).await
+    }
+
+    /// Send an `account/login/cancel` JSON-RPC request.
+    pub async fn send_cancel_login_account_request(
+        &mut self,
+        params: CancelLoginAccountParams,
+    ) -> anyhow::Result<i64> {
+        let params = Some(serde_json::to_value(params)?);
+        self.send_request("account/login/cancel", params).await
+    }
+
+    /// Send a `fuzzyFileSearch` JSON-RPC request.
+    pub async fn send_fuzzy_file_search_request(
+        &mut self,
+        query: &str,
+        roots: Vec<String>,
+        cancellation_token: Option<String>,
+    ) -> anyhow::Result<i64> {
+        let mut params = serde_json::json!({
+            "query": query,
+            "roots": roots,
+        });
+        if let Some(token) = cancellation_token {
+            params["cancellationToken"] = serde_json::json!(token);
+        }
+        self.send_request("fuzzyFileSearch", Some(params)).await
+    }
+
+    async fn send_request(
+        &mut self,
+        method: &str,
+        params: Option<serde_json::Value>,
+    ) -> anyhow::Result<i64> {
+        let request_id = self.next_request_id.fetch_add(1, Ordering::Relaxed);
+
+        let message = JSONRPCMessage::Request(JSONRPCRequest {
+            id: RequestId::Integer(request_id),
+            method: method.to_string(),
+            params,
+        });
+        self.send_jsonrpc_message(message).await?;
+        Ok(request_id)
+    }
+
+    pub async fn send_response(
+        &mut self,
+        id: RequestId,
+        result: serde_json::Value,
+    ) -> anyhow::Result<()> {
+        self.send_jsonrpc_message(JSONRPCMessage::Response(JSONRPCResponse { id, result }))
+            .await
+    }
+
+    pub async fn send_notification(
+        &mut self,
+        notification: ClientNotification,
+    ) -> anyhow::Result<()> {
+        let value = serde_json::to_value(notification)?;
+        self.send_jsonrpc_message(JSONRPCMessage::Notification(JSONRPCNotification {
+            method: value
+                .get("method")
+                .and_then(|m| m.as_str())
+                .ok_or_else(|| anyhow::format_err!("notification missing method field"))?
+                .to_string(),
+            params: value.get("params").cloned(),
+        }))
+        .await
+    }
+
+    async fn send_jsonrpc_message(&mut self, message: JSONRPCMessage) -> anyhow::Result<()> {
+        eprintln!("writing message to stdin: {message:?}");
+        let payload = serde_json::to_string(&message)?;
+        self.stdin.write_all(payload.as_bytes()).await?;
+        self.stdin.write_all(b"\n").await?;
+        self.stdin.flush().await?;
+        Ok(())
+    }
+
+    async fn read_jsonrpc_message(&mut self) -> anyhow::Result<JSONRPCMessage> {
+        let mut line = String::new();
+        self.stdout.read_line(&mut line).await?;
+        let message = serde_json::from_str::<JSONRPCMessage>(&line)?;
+        eprintln!("read message from stdout: {message:?}");
+        Ok(message)
+    }
+
+    pub async fn read_stream_until_request_message(&mut self) -> anyhow::Result<ServerRequest> {
+        eprintln!("in read_stream_until_request_message()");
+
+        loop {
+            let message = self.read_jsonrpc_message().await?;
+
+            match message {
+                JSONRPCMessage::Notification(notification) => {
+                    eprintln!("notification: {notification:?}");
+                    self.enqueue_user_message(notification);
+                }
+                JSONRPCMessage::Request(jsonrpc_request) => {
+                    return jsonrpc_request.try_into().with_context(
+                        || "failed to deserialize ServerRequest from JSONRPCRequest",
+                    );
+                }
+                JSONRPCMessage::Error(_) => {
+                    anyhow::bail!("unexpected JSONRPCMessage::Error: {message:?}");
+                }
+                JSONRPCMessage::Response(_) => {
+                    anyhow::bail!("unexpected JSONRPCMessage::Response: {message:?}");
+                }
+            }
+        }
+    }
+
+    pub async fn read_stream_until_response_message(
+        &mut self,
+        request_id: RequestId,
+    ) -> anyhow::Result<JSONRPCResponse> {
+        eprintln!("in read_stream_until_response_message({request_id:?})");
+
+        loop {
+            let message = self.read_jsonrpc_message().await?;
+            match message {
+                JSONRPCMessage::Notification(notification) => {
+                    eprintln!("notification: {notification:?}");
+                    self.enqueue_user_message(notification);
+                }
+                JSONRPCMessage::Request(_) => {
+                    anyhow::bail!("unexpected JSONRPCMessage::Request: {message:?}");
+                }
+                JSONRPCMessage::Error(_) => {
+                    anyhow::bail!("unexpected JSONRPCMessage::Error: {message:?}");
+                }
+                JSONRPCMessage::Response(jsonrpc_response) => {
+                    if jsonrpc_response.id == request_id {
+                        return Ok(jsonrpc_response);
+                    }
+                }
+            }
+        }
+    }
+
+    pub async fn read_stream_until_error_message(
+        &mut self,
+        request_id: RequestId,
+    ) -> anyhow::Result<JSONRPCError> {
+        loop {
+            let message = self.read_jsonrpc_message().await?;
+            match message {
+                JSONRPCMessage::Notification(notification) => {
+                    eprintln!("notification: {notification:?}");
+                    self.enqueue_user_message(notification);
+                }
+                JSONRPCMessage::Request(_) => {
+                    anyhow::bail!("unexpected JSONRPCMessage::Request: {message:?}");
+                }
+                JSONRPCMessage::Response(_) => {
+                    // Keep scanning; we're waiting for an error with matching id.
+                }
+                JSONRPCMessage::Error(err) => {
+                    if err.id == request_id {
+                        return Ok(err);
+                    }
+                }
+            }
+        }
+    }
+
+    pub async fn read_stream_until_notification_message(
+        &mut self,
+        method: &str,
+    ) -> anyhow::Result<JSONRPCNotification> {
+        eprintln!("in read_stream_until_notification_message({method})");
+
+        if let Some(notification) = self.take_pending_notification_by_method(method) {
+            return Ok(notification);
+        }
+
+        loop {
+            let message = self.read_jsonrpc_message().await?;
+            match message {
+                JSONRPCMessage::Notification(notification) => {
+                    if notification.method == method {
+                        return Ok(notification);
+                    }
+                    self.enqueue_user_message(notification);
+                }
+                JSONRPCMessage::Request(_) => {
+                    anyhow::bail!("unexpected JSONRPCMessage::Request: {message:?}");
+                }
+                JSONRPCMessage::Error(_) => {
+                    anyhow::bail!("unexpected JSONRPCMessage::Error: {message:?}");
+                }
+                JSONRPCMessage::Response(_) => {
+                    anyhow::bail!("unexpected JSONRPCMessage::Response: {message:?}");
+                }
+            }
+        }
+    }
+
+    fn take_pending_notification_by_method(&mut self, method: &str) -> Option<JSONRPCNotification> {
+        if let Some(pos) = self
+            .pending_user_messages
+            .iter()
+            .position(|notification| notification.method == method)
+        {
+            return self.pending_user_messages.remove(pos);
+        }
+        None
+    }
+
+    fn enqueue_user_message(&mut self, notification: JSONRPCNotification) {
+        if notification.method == "codex/event/user_message" {
+            self.pending_user_messages.push_back(notification);
+        }
+    }
+}

llmx-rs/app-server/tests/common/mock_model_server.rs

@@ -0,0 +1,66 @@
+use std::sync::atomic::AtomicUsize;
+use std::sync::atomic::Ordering;
+
+use wiremock::Mock;
+use wiremock::MockServer;
+use wiremock::Respond;
+use wiremock::ResponseTemplate;
+use wiremock::matchers::method;
+use wiremock::matchers::path;
+
+/// Create a mock server that will provide the responses, in order, for
+/// requests to the `/v1/chat/completions` endpoint.
+pub async fn create_mock_chat_completions_server(responses: Vec<String>) -> MockServer {
+    let server = MockServer::start().await;
+
+    let num_calls = responses.len();
+    let seq_responder = SeqResponder {
+        num_calls: AtomicUsize::new(0),
+        responses,
+    };
+
+    Mock::given(method("POST"))
+        .and(path("/v1/chat/completions"))
+        .respond_with(seq_responder)
+        .expect(num_calls as u64)
+        .mount(&server)
+        .await;
+
+    server
+}
+
+/// Same as `create_mock_chat_completions_server` but does not enforce an
+/// expectation on the number of calls.
+pub async fn create_mock_chat_completions_server_unchecked(responses: Vec<String>) -> MockServer {
+    let server = MockServer::start().await;
+
+    let seq_responder = SeqResponder {
+        num_calls: AtomicUsize::new(0),
+        responses,
+    };
+
+    Mock::given(method("POST"))
+        .and(path("/v1/chat/completions"))
+        .respond_with(seq_responder)
+        .mount(&server)
+        .await;
+
+    server
+}
+
+struct SeqResponder {
+    num_calls: AtomicUsize,
+    responses: Vec<String>,
+}
+
+impl Respond for SeqResponder {
+    fn respond(&self, _: &wiremock::Request) -> ResponseTemplate {
+        let call_num = self.num_calls.fetch_add(1, Ordering::SeqCst);
+        match self.responses.get(call_num) {
+            Some(response) => ResponseTemplate::new(200)
+                .insert_header("content-type", "text/event-stream")
+                .set_body_raw(response.clone(), "text/event-stream"),
+            None => panic!("no response for {call_num}"),
+        }
+    }
+}

llmx-rs/app-server/tests/common/responses.rs

@@ -0,0 +1,95 @@
+use serde_json::json;
+use std::path::Path;
+
+pub fn create_shell_sse_response(
+    command: Vec<String>,
+    workdir: Option<&Path>,
+    timeout_ms: Option<u64>,
+    call_id: &str,
+) -> anyhow::Result<String> {
+    // The `arguments`` for the `shell` tool is a serialized JSON object.
+    let tool_call_arguments = serde_json::to_string(&json!({
+        "command": command,
+        "workdir": workdir.map(|w| w.to_string_lossy()),
+        "timeout": timeout_ms
+    }))?;
+    let tool_call = json!({
+        "choices": [
+            {
+                "delta": {
+                    "tool_calls": [
+                        {
+                            "id": call_id,
+                            "function": {
+                                "name": "shell",
+                                "arguments": tool_call_arguments
+                            }
+                        }
+                    ]
+                },
+                "finish_reason": "tool_calls"
+            }
+        ]
+    });
+
+    let sse = format!(
+        "data: {}\n\ndata: DONE\n\n",
+        serde_json::to_string(&tool_call)?
+    );
+    Ok(sse)
+}
+
+pub fn create_final_assistant_message_sse_response(message: &str) -> anyhow::Result<String> {
+    let assistant_message = json!({
+        "choices": [
+            {
+                "delta": {
+                    "content": message
+                },
+                "finish_reason": "stop"
+            }
+        ]
+    });
+
+    let sse = format!(
+        "data: {}\n\ndata: DONE\n\n",
+        serde_json::to_string(&assistant_message)?
+    );
+    Ok(sse)
+}
+
+pub fn create_apply_patch_sse_response(
+    patch_content: &str,
+    call_id: &str,
+) -> anyhow::Result<String> {
+    // Use shell command to call apply_patch with heredoc format
+    let shell_command = format!("apply_patch <<'EOF'\n{patch_content}\nEOF");
+    let tool_call_arguments = serde_json::to_string(&json!({
+        "command": ["bash", "-lc", shell_command]
+    }))?;
+
+    let tool_call = json!({
+        "choices": [
+            {
+                "delta": {
+                    "tool_calls": [
+                        {
+                            "id": call_id,
+                            "function": {
+                                "name": "shell",
+                                "arguments": tool_call_arguments
+                            }
+                        }
+                    ]
+                },
+                "finish_reason": "tool_calls"
+            }
+        ]
+    });
+
+    let sse = format!(
+        "data: {}\n\ndata: DONE\n\n",
+        serde_json::to_string(&tool_call)?
+    );
+    Ok(sse)
+}

llmx-rs/app-server/tests/common/rollout.rs

@@ -0,0 +1,82 @@
+use anyhow::Result;
+use codex_protocol::ConversationId;
+use codex_protocol::protocol::SessionMeta;
+use codex_protocol::protocol::SessionSource;
+use serde_json::json;
+use std::fs;
+use std::path::Path;
+use std::path::PathBuf;
+use uuid::Uuid;
+
+/// Create a minimal rollout file under `CODEX_HOME/sessions/YYYY/MM/DD/`.
+///
+/// - `filename_ts` is the filename timestamp component in `YYYY-MM-DDThh-mm-ss` format.
+/// - `meta_rfc3339` is the envelope timestamp used in JSON lines.
+/// - `preview` is the user message preview text.
+/// - `model_provider` optionally sets the provider in the session meta payload.
+///
+/// Returns the generated conversation/session UUID as a string.
+pub fn create_fake_rollout(
+    codex_home: &Path,
+    filename_ts: &str,
+    meta_rfc3339: &str,
+    preview: &str,
+    model_provider: Option<&str>,
+) -> Result<String> {
+    let uuid = Uuid::new_v4();
+    let uuid_str = uuid.to_string();
+    let conversation_id = ConversationId::from_string(&uuid_str)?;
+
+    // sessions/YYYY/MM/DD derived from filename_ts (YYYY-MM-DDThh-mm-ss)
+    let year = &filename_ts[0..4];
+    let month = &filename_ts[5..7];
+    let day = &filename_ts[8..10];
+    let dir = codex_home.join("sessions").join(year).join(month).join(day);
+    fs::create_dir_all(&dir)?;
+
+    let file_path = dir.join(format!("rollout-{filename_ts}-{uuid}.jsonl"));
+
+    // Build JSONL lines
+    let payload = serde_json::to_value(SessionMeta {
+        id: conversation_id,
+        timestamp: meta_rfc3339.to_string(),
+        cwd: PathBuf::from("/"),
+        originator: "codex".to_string(),
+        cli_version: "0.0.0".to_string(),
+        instructions: None,
+        source: SessionSource::Cli,
+        model_provider: model_provider.map(str::to_string),
+    })?;
+
+    let lines = [
+        json!({
+            "timestamp": meta_rfc3339,
+            "type": "session_meta",
+            "payload": payload
+        })
+        .to_string(),
+        json!({
+            "timestamp": meta_rfc3339,
+            "type":"response_item",
+            "payload": {
+                "type":"message",
+                "role":"user",
+                "content":[{"type":"input_text","text": preview}]
+            }
+        })
+        .to_string(),
+        json!({
+            "timestamp": meta_rfc3339,
+            "type":"event_msg",
+            "payload": {
+                "type":"user_message",
+                "message": preview,
+                "kind": "plain"
+            }
+        })
+        .to_string(),
+    ];
+
+    fs::write(file_path, lines.join("\n") + "\n")?;
+    Ok(uuid_str)
+}

llmx-rs/app-server/tests/suite/archive_conversation.rs

@@ -0,0 +1,94 @@
+use anyhow::Result;
+use app_test_support::McpProcess;
+use app_test_support::to_response;
+use codex_app_server_protocol::ArchiveConversationParams;
+use codex_app_server_protocol::ArchiveConversationResponse;
+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_core::ARCHIVED_SESSIONS_SUBDIR;
+use std::path::Path;
+use tempfile::TempDir;
+use tokio::time::timeout;
+
+const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(20);
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn archive_conversation_moves_rollout_into_archived_directory() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path())?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let new_request_id = mcp
+        .send_new_conversation_request(NewConversationParams {
+            model: Some("mock-model".to_string()),
+            ..Default::default()
+        })
+        .await?;
+    let new_response: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(new_request_id)),
+    )
+    .await??;
+
+    let NewConversationResponse {
+        conversation_id,
+        rollout_path,
+        ..
+    } = to_response::<NewConversationResponse>(new_response)?;
+
+    assert!(
+        rollout_path.exists(),
+        "expected rollout path {} to exist",
+        rollout_path.display()
+    );
+
+    let archive_request_id = mcp
+        .send_archive_conversation_request(ArchiveConversationParams {
+            conversation_id,
+            rollout_path: rollout_path.clone(),
+        })
+        .await?;
+    let archive_response: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(archive_request_id)),
+    )
+    .await??;
+
+    let _: ArchiveConversationResponse =
+        to_response::<ArchiveConversationResponse>(archive_response)?;
+
+    let archived_directory = codex_home.path().join(ARCHIVED_SESSIONS_SUBDIR);
+    let archived_rollout_path =
+        archived_directory.join(rollout_path.file_name().unwrap_or_else(|| {
+            panic!("rollout path {} missing file name", rollout_path.display())
+        }));
+
+    assert!(
+        !rollout_path.exists(),
+        "expected rollout path {} to be moved",
+        rollout_path.display()
+    );
+    assert!(
+        archived_rollout_path.exists(),
+        "expected archived rollout path {} to exist",
+        archived_rollout_path.display()
+    );
+
+    Ok(())
+}
+
+fn create_config_toml(codex_home: &Path) -> std::io::Result<()> {
+    let config_toml = codex_home.join("config.toml");
+    std::fs::write(config_toml, config_contents())
+}
+
+fn config_contents() -> &'static str {
+    r#"model = "mock-model"
+approval_policy = "never"
+sandbox_mode = "read-only"
+"#
+}

llmx-rs/app-server/tests/suite/auth.rs

@@ -0,0 +1,230 @@
+use anyhow::Result;
+use app_test_support::McpProcess;
+use app_test_support::to_response;
+use codex_app_server_protocol::AuthMode;
+use codex_app_server_protocol::GetAuthStatusParams;
+use codex_app_server_protocol::GetAuthStatusResponse;
+use codex_app_server_protocol::JSONRPCError;
+use codex_app_server_protocol::JSONRPCResponse;
+use codex_app_server_protocol::LoginApiKeyParams;
+use codex_app_server_protocol::LoginApiKeyResponse;
+use codex_app_server_protocol::RequestId;
+use pretty_assertions::assert_eq;
+use std::path::Path;
+use tempfile::TempDir;
+use tokio::time::timeout;
+
+const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
+
+fn create_config_toml_custom_provider(
+    codex_home: &Path,
+    requires_openai_auth: bool,
+) -> std::io::Result<()> {
+    let config_toml = codex_home.join("config.toml");
+    let requires_line = if requires_openai_auth {
+        "requires_openai_auth = true\n"
+    } else {
+        ""
+    };
+    let contents = format!(
+        r#"
+model = "mock-model"
+approval_policy = "never"
+sandbox_mode = "danger-full-access"
+
+model_provider = "mock_provider"
+
+[model_providers.mock_provider]
+name = "Mock provider for test"
+base_url = "http://127.0.0.1:0/v1"
+wire_api = "chat"
+request_max_retries = 0
+stream_max_retries = 0
+{requires_line}
+"#
+    );
+    std::fs::write(config_toml, contents)
+}
+
+fn create_config_toml(codex_home: &Path) -> std::io::Result<()> {
+    let config_toml = codex_home.join("config.toml");
+    std::fs::write(
+        config_toml,
+        r#"
+model = "mock-model"
+approval_policy = "never"
+sandbox_mode = "danger-full-access"
+"#,
+    )
+}
+
+fn create_config_toml_forced_login(codex_home: &Path, forced_method: &str) -> std::io::Result<()> {
+    let config_toml = codex_home.join("config.toml");
+    let contents = format!(
+        r#"
+model = "mock-model"
+approval_policy = "never"
+sandbox_mode = "danger-full-access"
+forced_login_method = "{forced_method}"
+"#
+    );
+    std::fs::write(config_toml, contents)
+}
+
+async fn login_with_api_key_via_request(mcp: &mut McpProcess, api_key: &str) -> Result<()> {
+    let request_id = mcp
+        .send_login_api_key_request(LoginApiKeyParams {
+            api_key: api_key.to_string(),
+        })
+        .await?;
+
+    let resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+    let _: LoginApiKeyResponse = to_response(resp)?;
+    Ok(())
+}
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn get_auth_status_no_auth() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path())?;
+
+    let mut mcp = McpProcess::new_with_env(codex_home.path(), &[("OPENAI_API_KEY", None)]).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let request_id = mcp
+        .send_get_auth_status_request(GetAuthStatusParams {
+            include_token: Some(true),
+            refresh_token: Some(false),
+        })
+        .await?;
+
+    let resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+    let status: GetAuthStatusResponse = to_response(resp)?;
+    assert_eq!(status.auth_method, None, "expected no auth method");
+    assert_eq!(status.auth_token, None, "expected no token");
+    Ok(())
+}
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn get_auth_status_with_api_key() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path())?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    login_with_api_key_via_request(&mut mcp, "sk-test-key").await?;
+
+    let request_id = mcp
+        .send_get_auth_status_request(GetAuthStatusParams {
+            include_token: Some(true),
+            refresh_token: Some(false),
+        })
+        .await?;
+
+    let resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+    let status: GetAuthStatusResponse = to_response(resp)?;
+    assert_eq!(status.auth_method, Some(AuthMode::ApiKey));
+    assert_eq!(status.auth_token, Some("sk-test-key".to_string()));
+    Ok(())
+}
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn get_auth_status_with_api_key_when_auth_not_required() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_config_toml_custom_provider(codex_home.path(), false)?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    login_with_api_key_via_request(&mut mcp, "sk-test-key").await?;
+
+    let request_id = mcp
+        .send_get_auth_status_request(GetAuthStatusParams {
+            include_token: Some(true),
+            refresh_token: Some(false),
+        })
+        .await?;
+
+    let resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+    let status: GetAuthStatusResponse = to_response(resp)?;
+    assert_eq!(status.auth_method, None, "expected no auth method");
+    assert_eq!(status.auth_token, None, "expected no token");
+    assert_eq!(
+        status.requires_openai_auth,
+        Some(false),
+        "requires_openai_auth should be false",
+    );
+    Ok(())
+}
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn get_auth_status_with_api_key_no_include_token() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path())?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    login_with_api_key_via_request(&mut mcp, "sk-test-key").await?;
+
+    // Build params via struct so None field is omitted in wire JSON.
+    let params = GetAuthStatusParams {
+        include_token: None,
+        refresh_token: Some(false),
+    };
+    let request_id = mcp.send_get_auth_status_request(params).await?;
+
+    let resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+    let status: GetAuthStatusResponse = to_response(resp)?;
+    assert_eq!(status.auth_method, Some(AuthMode::ApiKey));
+    assert!(status.auth_token.is_none(), "token must be omitted");
+    Ok(())
+}
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn login_api_key_rejected_when_forced_chatgpt() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_config_toml_forced_login(codex_home.path(), "chatgpt")?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let request_id = mcp
+        .send_login_api_key_request(LoginApiKeyParams {
+            api_key: "sk-test-key".to_string(),
+        })
+        .await?;
+
+    let err: JSONRPCError = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_error_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+
+    assert_eq!(
+        err.error.message,
+        "API key login is disabled. Use ChatGPT login instead."
+    );
+    Ok(())
+}

llmx-rs/app-server/tests/suite/codex_message_processor_flow.rs

@@ -0,0 +1,523 @@
+use anyhow::Result;
+use app_test_support::McpProcess;
+use app_test_support::create_final_assistant_message_sse_response;
+use app_test_support::create_mock_chat_completions_server;
+use app_test_support::create_shell_sse_response;
+use app_test_support::to_response;
+use codex_app_server_protocol::AddConversationListenerParams;
+use codex_app_server_protocol::AddConversationSubscriptionResponse;
+use codex_app_server_protocol::ExecCommandApprovalParams;
+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::RemoveConversationListenerParams;
+use codex_app_server_protocol::RemoveConversationSubscriptionResponse;
+use codex_app_server_protocol::RequestId;
+use codex_app_server_protocol::SendUserMessageParams;
+use codex_app_server_protocol::SendUserMessageResponse;
+use codex_app_server_protocol::SendUserTurnParams;
+use codex_app_server_protocol::SendUserTurnResponse;
+use codex_app_server_protocol::ServerRequest;
+use codex_core::protocol::AskForApproval;
+use codex_core::protocol::SandboxPolicy;
+use codex_core::protocol_config_types::ReasoningEffort;
+use codex_core::protocol_config_types::ReasoningSummary;
+use codex_core::spawn::CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR;
+use codex_protocol::config_types::SandboxMode;
+use codex_protocol::parse_command::ParsedCommand;
+use codex_protocol::protocol::Event;
+use codex_protocol::protocol::EventMsg;
+use pretty_assertions::assert_eq;
+use std::env;
+use std::path::Path;
+use tempfile::TempDir;
+use tokio::time::timeout;
+
+const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 4)]
+async fn test_codex_jsonrpc_conversation_flow() -> Result<()> {
+    if env::var(CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR).is_ok() {
+        println!(
+            "Skipping test because it cannot execute when network is disabled in a Codex sandbox."
+        );
+        return Ok(());
+    }
+
+    let tmp = TempDir::new()?;
+    // Temporary Codex home with config pointing at the mock server.
+    let codex_home = tmp.path().join("codex_home");
+    std::fs::create_dir(&codex_home)?;
+    let working_directory = tmp.path().join("workdir");
+    std::fs::create_dir(&working_directory)?;
+
+    // Create a mock model server that immediately ends each turn.
+    // Two turns are expected: initial session configure + one user message.
+    let responses = vec![
+        create_shell_sse_response(
+            vec!["ls".to_string()],
+            Some(&working_directory),
+            Some(5000),
+            "call1234",
+        )?,
+        create_final_assistant_message_sse_response("Enjoy your new git repo!")?,
+    ];
+    let server = create_mock_chat_completions_server(responses).await;
+    create_config_toml(&codex_home, &server.uri())?;
+
+    // Start MCP server and initialize.
+    let mut mcp = McpProcess::new(&codex_home).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    // 1) newConversation
+    let new_conv_id = mcp
+        .send_new_conversation_request(NewConversationParams {
+            cwd: Some(working_directory.to_string_lossy().into_owned()),
+            ..Default::default()
+        })
+        .await?;
+    let new_conv_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(new_conv_id)),
+    )
+    .await??;
+    let new_conv_resp = to_response::<NewConversationResponse>(new_conv_resp)?;
+    let NewConversationResponse {
+        conversation_id,
+        model,
+        reasoning_effort: _,
+        rollout_path: _,
+    } = new_conv_resp;
+    assert_eq!(model, "mock-model");
+
+    // 2) addConversationListener
+    let add_listener_id = mcp
+        .send_add_conversation_listener_request(AddConversationListenerParams {
+            conversation_id,
+            experimental_raw_events: false,
+        })
+        .await?;
+    let add_listener_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(add_listener_id)),
+    )
+    .await??;
+    let AddConversationSubscriptionResponse { subscription_id } =
+        to_response::<AddConversationSubscriptionResponse>(add_listener_resp)?;
+
+    // 3) sendUserMessage (should trigger notifications; we only validate an OK response)
+    let send_user_id = mcp
+        .send_send_user_message_request(SendUserMessageParams {
+            conversation_id,
+            items: vec![codex_app_server_protocol::InputItem::Text {
+                text: "text".to_string(),
+            }],
+        })
+        .await?;
+    let send_user_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(send_user_id)),
+    )
+    .await??;
+    let SendUserMessageResponse {} = to_response::<SendUserMessageResponse>(send_user_resp)?;
+
+    // Verify the task_finished notification is received.
+    // Note this also ensures that the final request to the server was made.
+    let task_finished_notification: JSONRPCNotification = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("codex/event/task_complete"),
+    )
+    .await??;
+    let serde_json::Value::Object(map) = task_finished_notification
+        .params
+        .expect("notification should have params")
+    else {
+        panic!("task_finished_notification should have params");
+    };
+    assert_eq!(
+        map.get("conversationId")
+            .expect("should have conversationId"),
+        &serde_json::Value::String(conversation_id.to_string())
+    );
+
+    // 4) removeConversationListener
+    let remove_listener_id = mcp
+        .send_remove_conversation_listener_request(RemoveConversationListenerParams {
+            subscription_id,
+        })
+        .await?;
+    let remove_listener_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(remove_listener_id)),
+    )
+    .await??;
+    let RemoveConversationSubscriptionResponse {} = to_response(remove_listener_resp)?;
+
+    Ok(())
+}
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 4)]
+async fn test_send_user_turn_changes_approval_policy_behavior() -> Result<()> {
+    if env::var(CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR).is_ok() {
+        println!(
+            "Skipping test because it cannot execute when network is disabled in a Codex sandbox."
+        );
+        return Ok(());
+    }
+
+    let tmp = TempDir::new()?;
+    let codex_home = tmp.path().join("codex_home");
+    std::fs::create_dir(&codex_home)?;
+    let working_directory = tmp.path().join("workdir");
+    std::fs::create_dir(&working_directory)?;
+
+    // Mock server will request a python shell call for the first and second turn, then finish.
+    let responses = vec![
+        create_shell_sse_response(
+            vec![
+                "python3".to_string(),
+                "-c".to_string(),
+                "print(42)".to_string(),
+            ],
+            Some(&working_directory),
+            Some(5000),
+            "call1",
+        )?,
+        create_final_assistant_message_sse_response("done 1")?,
+        create_shell_sse_response(
+            vec![
+                "python3".to_string(),
+                "-c".to_string(),
+                "print(42)".to_string(),
+            ],
+            Some(&working_directory),
+            Some(5000),
+            "call2",
+        )?,
+        create_final_assistant_message_sse_response("done 2")?,
+    ];
+    let server = create_mock_chat_completions_server(responses).await;
+    create_config_toml(&codex_home, &server.uri())?;
+
+    // Start MCP server and initialize.
+    let mut mcp = McpProcess::new(&codex_home).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    // 1) Start conversation with approval_policy=untrusted
+    let new_conv_id = mcp
+        .send_new_conversation_request(NewConversationParams {
+            cwd: Some(working_directory.to_string_lossy().into_owned()),
+            ..Default::default()
+        })
+        .await?;
+    let new_conv_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(new_conv_id)),
+    )
+    .await??;
+    let NewConversationResponse {
+        conversation_id, ..
+    } = to_response::<NewConversationResponse>(new_conv_resp)?;
+
+    // 2) addConversationListener
+    let add_listener_id = mcp
+        .send_add_conversation_listener_request(AddConversationListenerParams {
+            conversation_id,
+            experimental_raw_events: false,
+        })
+        .await?;
+    let _: AddConversationSubscriptionResponse = to_response::<AddConversationSubscriptionResponse>(
+        timeout(
+            DEFAULT_READ_TIMEOUT,
+            mcp.read_stream_until_response_message(RequestId::Integer(add_listener_id)),
+        )
+        .await??,
+    )?;
+
+    // 3) sendUserMessage triggers a shell call; approval policy is Untrusted so we should get an elicitation
+    let send_user_id = mcp
+        .send_send_user_message_request(SendUserMessageParams {
+            conversation_id,
+            items: vec![codex_app_server_protocol::InputItem::Text {
+                text: "run python".to_string(),
+            }],
+        })
+        .await?;
+    let _send_user_resp: SendUserMessageResponse = to_response::<SendUserMessageResponse>(
+        timeout(
+            DEFAULT_READ_TIMEOUT,
+            mcp.read_stream_until_response_message(RequestId::Integer(send_user_id)),
+        )
+        .await??,
+    )?;
+
+    // Expect an ExecCommandApproval request (elicitation)
+    let request = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_request_message(),
+    )
+    .await??;
+    let ServerRequest::ExecCommandApproval { request_id, params } = request else {
+        panic!("expected ExecCommandApproval request, got: {request:?}");
+    };
+
+    assert_eq!(
+        ExecCommandApprovalParams {
+            conversation_id,
+            call_id: "call1".to_string(),
+            command: vec![
+                "python3".to_string(),
+                "-c".to_string(),
+                "print(42)".to_string(),
+            ],
+            cwd: working_directory.clone(),
+            reason: None,
+            risk: None,
+            parsed_cmd: vec![ParsedCommand::Unknown {
+                cmd: "python3 -c 'print(42)'".to_string()
+            }],
+        },
+        params
+    );
+
+    // Approve so the first turn can complete
+    mcp.send_response(
+        request_id,
+        serde_json::json!({ "decision": codex_core::protocol::ReviewDecision::Approved }),
+    )
+    .await?;
+
+    // Wait for first TaskComplete
+    let _ = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("codex/event/task_complete"),
+    )
+    .await??;
+
+    // 4) sendUserTurn with approval_policy=never should run without elicitation
+    let send_turn_id = mcp
+        .send_send_user_turn_request(SendUserTurnParams {
+            conversation_id,
+            items: vec![codex_app_server_protocol::InputItem::Text {
+                text: "run python again".to_string(),
+            }],
+            cwd: working_directory.clone(),
+            approval_policy: AskForApproval::Never,
+            sandbox_policy: SandboxPolicy::new_read_only_policy(),
+            model: "mock-model".to_string(),
+            effort: Some(ReasoningEffort::Medium),
+            summary: ReasoningSummary::Auto,
+        })
+        .await?;
+    // Acknowledge sendUserTurn
+    let _send_turn_resp: SendUserTurnResponse = to_response::<SendUserTurnResponse>(
+        timeout(
+            DEFAULT_READ_TIMEOUT,
+            mcp.read_stream_until_response_message(RequestId::Integer(send_turn_id)),
+        )
+        .await??,
+    )?;
+
+    // Ensure we do NOT receive an ExecCommandApproval request before the task completes.
+    // If any Request is seen while waiting for task_complete, the helper will error and the test fails.
+    let _ = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("codex/event/task_complete"),
+    )
+    .await??;
+
+    Ok(())
+}
+
+// Helper: minimal config.toml pointing at mock provider.
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 4)]
+async fn test_send_user_turn_updates_sandbox_and_cwd_between_turns() -> Result<()> {
+    if env::var(CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR).is_ok() {
+        println!(
+            "Skipping test because it cannot execute when network is disabled in a Codex sandbox."
+        );
+        return Ok(());
+    }
+
+    let tmp = TempDir::new()?;
+    let codex_home = tmp.path().join("codex_home");
+    std::fs::create_dir(&codex_home)?;
+    let workspace_root = tmp.path().join("workspace");
+    std::fs::create_dir(&workspace_root)?;
+    let first_cwd = workspace_root.join("turn1");
+    let second_cwd = workspace_root.join("turn2");
+    std::fs::create_dir(&first_cwd)?;
+    std::fs::create_dir(&second_cwd)?;
+
+    let responses = vec![
+        create_shell_sse_response(
+            vec![
+                "bash".to_string(),
+                "-lc".to_string(),
+                "echo first turn".to_string(),
+            ],
+            None,
+            Some(5000),
+            "call-first",
+        )?,
+        create_final_assistant_message_sse_response("done first")?,
+        create_shell_sse_response(
+            vec![
+                "bash".to_string(),
+                "-lc".to_string(),
+                "echo second turn".to_string(),
+            ],
+            None,
+            Some(5000),
+            "call-second",
+        )?,
+        create_final_assistant_message_sse_response("done second")?,
+    ];
+    let server = create_mock_chat_completions_server(responses).await;
+    create_config_toml(&codex_home, &server.uri())?;
+
+    let mut mcp = McpProcess::new(&codex_home).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let new_conv_id = mcp
+        .send_new_conversation_request(NewConversationParams {
+            cwd: Some(first_cwd.to_string_lossy().into_owned()),
+            approval_policy: Some(AskForApproval::Never),
+            sandbox: Some(SandboxMode::WorkspaceWrite),
+            ..Default::default()
+        })
+        .await?;
+    let new_conv_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(new_conv_id)),
+    )
+    .await??;
+    let NewConversationResponse {
+        conversation_id,
+        model,
+        ..
+    } = to_response::<NewConversationResponse>(new_conv_resp)?;
+
+    let add_listener_id = mcp
+        .send_add_conversation_listener_request(AddConversationListenerParams {
+            conversation_id,
+            experimental_raw_events: false,
+        })
+        .await?;
+    timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(add_listener_id)),
+    )
+    .await??;
+
+    let first_turn_id = mcp
+        .send_send_user_turn_request(SendUserTurnParams {
+            conversation_id,
+            items: vec![InputItem::Text {
+                text: "first turn".to_string(),
+            }],
+            cwd: first_cwd.clone(),
+            approval_policy: AskForApproval::Never,
+            sandbox_policy: SandboxPolicy::WorkspaceWrite {
+                writable_roots: vec![first_cwd.clone()],
+                network_access: false,
+                exclude_tmpdir_env_var: false,
+                exclude_slash_tmp: false,
+            },
+            model: model.clone(),
+            effort: Some(ReasoningEffort::Medium),
+            summary: ReasoningSummary::Auto,
+        })
+        .await?;
+    timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(first_turn_id)),
+    )
+    .await??;
+    timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("codex/event/task_complete"),
+    )
+    .await??;
+
+    let second_turn_id = mcp
+        .send_send_user_turn_request(SendUserTurnParams {
+            conversation_id,
+            items: vec![InputItem::Text {
+                text: "second turn".to_string(),
+            }],
+            cwd: second_cwd.clone(),
+            approval_policy: AskForApproval::Never,
+            sandbox_policy: SandboxPolicy::DangerFullAccess,
+            model: model.clone(),
+            effort: Some(ReasoningEffort::Medium),
+            summary: ReasoningSummary::Auto,
+        })
+        .await?;
+    timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(second_turn_id)),
+    )
+    .await??;
+
+    let exec_begin_notification = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("codex/event/exec_command_begin"),
+    )
+    .await??;
+    let params = exec_begin_notification
+        .params
+        .clone()
+        .expect("exec_command_begin params");
+    let event: Event = serde_json::from_value(params).expect("deserialize exec begin event");
+    let exec_begin = match event.msg {
+        EventMsg::ExecCommandBegin(exec_begin) => exec_begin,
+        other => panic!("expected ExecCommandBegin event, got {other:?}"),
+    };
+    assert_eq!(
+        exec_begin.cwd, second_cwd,
+        "exec turn should run from updated cwd"
+    );
+    assert_eq!(
+        exec_begin.command,
+        vec![
+            "bash".to_string(),
+            "-lc".to_string(),
+            "echo second turn".to_string()
+        ],
+        "exec turn should run expected command"
+    );
+
+    timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("codex/event/task_complete"),
+    )
+    .await??;
+
+    Ok(())
+}
+
+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,
+        format!(
+            r#"
+model = "mock-model"
+approval_policy = "untrusted"
+
+model_provider = "mock_provider"
+
+[model_providers.mock_provider]
+name = "Mock provider for test"
+base_url = "{server_uri}/v1"
+wire_api = "chat"
+request_max_retries = 0
+stream_max_retries = 0
+"#
+        ),
+    )
+}

llmx-rs/app-server/tests/suite/config.rs

@@ -0,0 +1,152 @@
+use anyhow::Result;
+use app_test_support::McpProcess;
+use app_test_support::to_response;
+use codex_app_server_protocol::GetUserSavedConfigResponse;
+use codex_app_server_protocol::JSONRPCResponse;
+use codex_app_server_protocol::Profile;
+use codex_app_server_protocol::RequestId;
+use codex_app_server_protocol::SandboxSettings;
+use codex_app_server_protocol::Tools;
+use codex_app_server_protocol::UserSavedConfig;
+use codex_core::protocol::AskForApproval;
+use codex_protocol::config_types::ForcedLoginMethod;
+use codex_protocol::config_types::ReasoningEffort;
+use codex_protocol::config_types::ReasoningSummary;
+use codex_protocol::config_types::SandboxMode;
+use codex_protocol::config_types::Verbosity;
+use pretty_assertions::assert_eq;
+use std::collections::HashMap;
+use std::path::Path;
+use tempfile::TempDir;
+use tokio::time::timeout;
+
+const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
+
+fn create_config_toml(codex_home: &Path) -> std::io::Result<()> {
+    let config_toml = codex_home.join("config.toml");
+    std::fs::write(
+        config_toml,
+        r#"
+model = "gpt-5-codex"
+approval_policy = "on-request"
+sandbox_mode = "workspace-write"
+model_reasoning_summary = "detailed"
+model_reasoning_effort = "high"
+model_verbosity = "medium"
+profile = "test"
+forced_chatgpt_workspace_id = "12345678-0000-0000-0000-000000000000"
+forced_login_method = "chatgpt"
+
+[sandbox_workspace_write]
+writable_roots = ["/tmp"]
+network_access = true
+exclude_tmpdir_env_var = true
+exclude_slash_tmp = true
+
+[tools]
+web_search = false
+view_image = true
+
+[profiles.test]
+model = "gpt-4o"
+approval_policy = "on-request"
+model_reasoning_effort = "high"
+model_reasoning_summary = "detailed"
+model_verbosity = "medium"
+model_provider = "openai"
+chatgpt_base_url = "https://api.chatgpt.com"
+"#,
+    )
+}
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 4)]
+async fn get_config_toml_parses_all_fields() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path())?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let request_id = mcp.send_get_user_saved_config_request().await?;
+    let resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+
+    let config: GetUserSavedConfigResponse = to_response(resp)?;
+    let expected = GetUserSavedConfigResponse {
+        config: UserSavedConfig {
+            approval_policy: Some(AskForApproval::OnRequest),
+            sandbox_mode: Some(SandboxMode::WorkspaceWrite),
+            sandbox_settings: Some(SandboxSettings {
+                writable_roots: vec!["/tmp".into()],
+                network_access: Some(true),
+                exclude_tmpdir_env_var: Some(true),
+                exclude_slash_tmp: Some(true),
+            }),
+            forced_chatgpt_workspace_id: Some("12345678-0000-0000-0000-000000000000".into()),
+            forced_login_method: Some(ForcedLoginMethod::Chatgpt),
+            model: Some("gpt-5-codex".into()),
+            model_reasoning_effort: Some(ReasoningEffort::High),
+            model_reasoning_summary: Some(ReasoningSummary::Detailed),
+            model_verbosity: Some(Verbosity::Medium),
+            tools: Some(Tools {
+                web_search: Some(false),
+                view_image: Some(true),
+            }),
+            profile: Some("test".to_string()),
+            profiles: HashMap::from([(
+                "test".into(),
+                Profile {
+                    model: Some("gpt-4o".into()),
+                    approval_policy: Some(AskForApproval::OnRequest),
+                    model_reasoning_effort: Some(ReasoningEffort::High),
+                    model_reasoning_summary: Some(ReasoningSummary::Detailed),
+                    model_verbosity: Some(Verbosity::Medium),
+                    model_provider: Some("openai".into()),
+                    chatgpt_base_url: Some("https://api.chatgpt.com".into()),
+                },
+            )]),
+        },
+    };
+
+    assert_eq!(config, expected);
+    Ok(())
+}
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn get_config_toml_empty() -> Result<()> {
+    let codex_home = TempDir::new()?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let request_id = mcp.send_get_user_saved_config_request().await?;
+    let resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+
+    let config: GetUserSavedConfigResponse = to_response(resp)?;
+    let expected = GetUserSavedConfigResponse {
+        config: UserSavedConfig {
+            approval_policy: None,
+            sandbox_mode: None,
+            sandbox_settings: None,
+            forced_chatgpt_workspace_id: None,
+            forced_login_method: None,
+            model: None,
+            model_reasoning_effort: None,
+            model_reasoning_summary: None,
+            model_verbosity: None,
+            tools: None,
+            profile: None,
+            profiles: HashMap::new(),
+        },
+    };
+
+    assert_eq!(config, expected);
+    Ok(())
+}

llmx-rs/app-server/tests/suite/create_conversation.rs

@@ -0,0 +1,142 @@
+use anyhow::Result;
+use app_test_support::McpProcess;
+use app_test_support::create_final_assistant_message_sse_response;
+use app_test_support::create_mock_chat_completions_server;
+use app_test_support::to_response;
+use codex_app_server_protocol::AddConversationListenerParams;
+use codex_app_server_protocol::AddConversationSubscriptionResponse;
+use codex_app_server_protocol::InputItem;
+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 pretty_assertions::assert_eq;
+use serde_json::json;
+use std::path::Path;
+use tempfile::TempDir;
+use tokio::time::timeout;
+
+const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn test_conversation_create_and_send_message_ok() -> Result<()> {
+    // Mock server – we won't strictly rely on it, but provide one to satisfy any model wiring.
+    let responses = vec![create_final_assistant_message_sse_response("Done")?];
+    let server = create_mock_chat_completions_server(responses).await;
+
+    // Temporary Codex home with config pointing at the mock server.
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path(), &server.uri())?;
+
+    // Start MCP server process and initialize.
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    // Create a conversation via the new JSON-RPC API.
+    let new_conv_id = mcp
+        .send_new_conversation_request(NewConversationParams {
+            model: Some("o3".to_string()),
+            ..Default::default()
+        })
+        .await?;
+    let new_conv_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(new_conv_id)),
+    )
+    .await??;
+    let NewConversationResponse {
+        conversation_id,
+        model,
+        reasoning_effort: _,
+        rollout_path: _,
+    } = to_response::<NewConversationResponse>(new_conv_resp)?;
+    assert_eq!(model, "o3");
+
+    // Add a listener so we receive notifications for this conversation (not strictly required for this test).
+    let add_listener_id = mcp
+        .send_add_conversation_listener_request(AddConversationListenerParams {
+            conversation_id,
+            experimental_raw_events: false,
+        })
+        .await?;
+    let _sub: AddConversationSubscriptionResponse =
+        to_response::<AddConversationSubscriptionResponse>(
+            timeout(
+                DEFAULT_READ_TIMEOUT,
+                mcp.read_stream_until_response_message(RequestId::Integer(add_listener_id)),
+            )
+            .await??,
+        )?;
+
+    // Now send a user message via the wire API and expect an OK (empty object) result.
+    let send_id = mcp
+        .send_send_user_message_request(SendUserMessageParams {
+            conversation_id,
+            items: vec![InputItem::Text {
+                text: "Hello".to_string(),
+            }],
+        })
+        .await?;
+    let send_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(send_id)),
+    )
+    .await??;
+    let _ok: SendUserMessageResponse = to_response::<SendUserMessageResponse>(send_resp)?;
+
+    // avoid race condition by waiting for the mock server to receive the chat.completions request
+    let deadline = std::time::Instant::now() + DEFAULT_READ_TIMEOUT;
+    let requests = loop {
+        let requests = server.received_requests().await.unwrap_or_default();
+        if !requests.is_empty() {
+            break requests;
+        }
+        if std::time::Instant::now() >= deadline {
+            panic!("mock server did not receive the chat.completions request in time");
+        }
+        tokio::time::sleep(std::time::Duration::from_millis(10)).await;
+    };
+
+    // Verify the outbound request body matches expectations for Chat Completions.
+    let request = requests
+        .first()
+        .expect("mock server should have received at least one request");
+    let body = request.body_json::<serde_json::Value>()?;
+    assert_eq!(body["model"], json!("o3"));
+    assert!(body["stream"].as_bool().unwrap_or(false));
+    let messages = body["messages"]
+        .as_array()
+        .expect("messages should be array");
+    let last = messages.last().expect("at least one message");
+    assert_eq!(last["role"], json!("user"));
+    assert_eq!(last["content"], json!("Hello"));
+
+    drop(server);
+    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");
+    std::fs::write(
+        config_toml,
+        format!(
+            r#"
+model = "mock-model"
+approval_policy = "never"
+sandbox_mode = "danger-full-access"
+
+model_provider = "mock_provider"
+
+[model_providers.mock_provider]
+name = "Mock provider for test"
+base_url = "{server_uri}/v1"
+wire_api = "chat"
+request_max_retries = 0
+stream_max_retries = 0
+"#
+        ),
+    )
+}

llmx-rs/app-server/tests/suite/fuzzy_file_search.rs

@@ -0,0 +1,128 @@
+use anyhow::Result;
+use anyhow::anyhow;
+use app_test_support::McpProcess;
+use codex_app_server_protocol::JSONRPCResponse;
+use codex_app_server_protocol::RequestId;
+use pretty_assertions::assert_eq;
+use serde_json::json;
+use tempfile::TempDir;
+use tokio::time::timeout;
+
+const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn test_fuzzy_file_search_sorts_and_includes_indices() -> Result<()> {
+    // Prepare a temporary Codex home and a separate root with test files.
+    let codex_home = TempDir::new()?;
+    let root = TempDir::new()?;
+
+    // Create files designed to have deterministic ordering for query "abe".
+    std::fs::write(root.path().join("abc"), "x")?;
+    std::fs::write(root.path().join("abcde"), "x")?;
+    std::fs::write(root.path().join("abexy"), "x")?;
+    std::fs::write(root.path().join("zzz.txt"), "x")?;
+    let sub_dir = root.path().join("sub");
+    std::fs::create_dir_all(&sub_dir)?;
+    let sub_abce_path = sub_dir.join("abce");
+    std::fs::write(&sub_abce_path, "x")?;
+    let sub_abce_rel = sub_abce_path
+        .strip_prefix(root.path())?
+        .to_string_lossy()
+        .to_string();
+
+    // Start MCP server and initialize.
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let root_path = root.path().to_string_lossy().to_string();
+    // Send fuzzyFileSearch request.
+    let request_id = mcp
+        .send_fuzzy_file_search_request("abe", vec![root_path.clone()], None)
+        .await?;
+
+    // Read response and verify shape and ordering.
+    let resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+
+    let value = resp.result;
+    // The path separator on Windows affects the score.
+    let expected_score = if cfg!(windows) { 69 } else { 72 };
+
+    assert_eq!(
+        value,
+        json!({
+            "files": [
+                {
+                    "root": root_path.clone(),
+                    "path": "abexy",
+                    "file_name": "abexy",
+                    "score": 88,
+                    "indices": [0, 1, 2],
+                },
+                {
+                    "root": root_path.clone(),
+                    "path": "abcde",
+                    "file_name": "abcde",
+                    "score": 74,
+                    "indices": [0, 1, 4],
+                },
+                {
+                    "root": root_path.clone(),
+                    "path": sub_abce_rel,
+                    "file_name": "abce",
+                    "score": expected_score,
+                    "indices": [4, 5, 7],
+                },
+            ]
+        })
+    );
+
+    Ok(())
+}
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn test_fuzzy_file_search_accepts_cancellation_token() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    let root = TempDir::new()?;
+
+    std::fs::write(root.path().join("alpha.txt"), "contents")?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let root_path = root.path().to_string_lossy().to_string();
+    let request_id = mcp
+        .send_fuzzy_file_search_request("alp", vec![root_path.clone()], None)
+        .await?;
+
+    let request_id_2 = mcp
+        .send_fuzzy_file_search_request(
+            "alp",
+            vec![root_path.clone()],
+            Some(request_id.to_string()),
+        )
+        .await?;
+
+    let resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(request_id_2)),
+    )
+    .await??;
+
+    let files = resp
+        .result
+        .get("files")
+        .ok_or_else(|| anyhow!("files key missing"))?
+        .as_array()
+        .ok_or_else(|| anyhow!("files not array"))?
+        .clone();
+
+    assert_eq!(files.len(), 1);
+    assert_eq!(files[0]["root"], root_path);
+    assert_eq!(files[0]["path"], "alpha.txt");
+
+    Ok(())
+}

llmx-rs/app-server/tests/suite/interrupt.rs

@@ -0,0 +1,162 @@
+#![cfg(unix)]
+// Support code lives in the `app_test_support` crate under tests/common.
+
+use std::path::Path;
+
+use codex_app_server_protocol::AddConversationListenerParams;
+use codex_app_server_protocol::InterruptConversationParams;
+use codex_app_server_protocol::InterruptConversationResponse;
+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::protocol::TurnAbortReason;
+use core_test_support::skip_if_no_network;
+use tempfile::TempDir;
+use tokio::time::timeout;
+
+use app_test_support::McpProcess;
+use app_test_support::create_mock_chat_completions_server;
+use app_test_support::create_shell_sse_response;
+use app_test_support::to_response;
+
+const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn test_shell_command_interruption() {
+    skip_if_no_network!();
+
+    if let Err(err) = shell_command_interruption().await {
+        panic!("failure: {err}");
+    }
+}
+
+async fn shell_command_interruption() -> anyhow::Result<()> {
+    // Use a cross-platform blocking command. On Windows plain `sleep` is not guaranteed to exist
+    // (MSYS/GNU coreutils may be absent) and the failure causes the tool call to finish immediately,
+    // which triggers a second model request before the test sends the explicit follow-up. That
+    // prematurely consumes the second mocked SSE response and leads to a third POST (panic: no response for 2).
+    // Powershell Start-Sleep is always available on Windows runners. On Unix we keep using `sleep`.
+    #[cfg(target_os = "windows")]
+    let shell_command = vec![
+        "powershell".to_string(),
+        "-Command".to_string(),
+        "Start-Sleep -Seconds 10".to_string(),
+    ];
+    #[cfg(not(target_os = "windows"))]
+    let shell_command = vec!["sleep".to_string(), "10".to_string()];
+
+    let tmp = TempDir::new()?;
+    // Temporary Codex home with config pointing at the mock server.
+    let codex_home = tmp.path().join("codex_home");
+    std::fs::create_dir(&codex_home)?;
+    let working_directory = tmp.path().join("workdir");
+    std::fs::create_dir(&working_directory)?;
+
+    // Create mock server with a single SSE response: the long sleep command
+    let server = create_mock_chat_completions_server(vec![create_shell_sse_response(
+        shell_command.clone(),
+        Some(&working_directory),
+        Some(10_000), // 10 seconds timeout in ms
+        "call_sleep",
+    )?])
+    .await;
+    create_config_toml(&codex_home, server.uri())?;
+
+    // Start MCP server and initialize.
+    let mut mcp = McpProcess::new(&codex_home).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    // 1) newConversation
+    let new_conv_id = mcp
+        .send_new_conversation_request(NewConversationParams {
+            cwd: Some(working_directory.to_string_lossy().into_owned()),
+            ..Default::default()
+        })
+        .await?;
+    let new_conv_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(new_conv_id)),
+    )
+    .await??;
+    let new_conv_resp = to_response::<NewConversationResponse>(new_conv_resp)?;
+    let NewConversationResponse {
+        conversation_id, ..
+    } = new_conv_resp;
+
+    // 2) addConversationListener
+    let add_listener_id = mcp
+        .send_add_conversation_listener_request(AddConversationListenerParams {
+            conversation_id,
+            experimental_raw_events: false,
+        })
+        .await?;
+    let _add_listener_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(add_listener_id)),
+    )
+    .await??;
+
+    // 3) sendUserMessage (should trigger notifications; we only validate an OK response)
+    let send_user_id = mcp
+        .send_send_user_message_request(SendUserMessageParams {
+            conversation_id,
+            items: vec![codex_app_server_protocol::InputItem::Text {
+                text: "run first sleep command".to_string(),
+            }],
+        })
+        .await?;
+    let send_user_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(send_user_id)),
+    )
+    .await??;
+    let SendUserMessageResponse {} = to_response::<SendUserMessageResponse>(send_user_resp)?;
+
+    // Give the command a moment to start
+    tokio::time::sleep(std::time::Duration::from_secs(1)).await;
+
+    // 4) send interrupt request
+    let interrupt_id = mcp
+        .send_interrupt_conversation_request(InterruptConversationParams { conversation_id })
+        .await?;
+    let interrupt_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(interrupt_id)),
+    )
+    .await??;
+    let InterruptConversationResponse { abort_reason } =
+        to_response::<InterruptConversationResponse>(interrupt_resp)?;
+    assert_eq!(TurnAbortReason::Interrupted, abort_reason);
+
+    Ok(())
+}
+
+// ---------------------------------------------------------------------------
+// Helpers
+// ---------------------------------------------------------------------------
+
+fn create_config_toml(codex_home: &Path, server_uri: String) -> std::io::Result<()> {
+    let config_toml = codex_home.join("config.toml");
+    std::fs::write(
+        config_toml,
+        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 = "chat"
+request_max_retries = 0
+stream_max_retries = 0
+"#
+        ),
+    )
+}

llmx-rs/app-server/tests/suite/list_resume.rs

@@ -0,0 +1,356 @@
+use anyhow::Result;
+use app_test_support::McpProcess;
+use app_test_support::create_fake_rollout;
+use app_test_support::to_response;
+use codex_app_server_protocol::JSONRPCNotification;
+use codex_app_server_protocol::JSONRPCResponse;
+use codex_app_server_protocol::ListConversationsParams;
+use codex_app_server_protocol::ListConversationsResponse;
+use codex_app_server_protocol::NewConversationParams; // reused for overrides shape
+use codex_app_server_protocol::RequestId;
+use codex_app_server_protocol::ResumeConversationParams;
+use codex_app_server_protocol::ResumeConversationResponse;
+use codex_app_server_protocol::ServerNotification;
+use codex_app_server_protocol::SessionConfiguredNotification;
+use codex_core::protocol::EventMsg;
+use codex_protocol::models::ContentItem;
+use codex_protocol::models::ResponseItem;
+use pretty_assertions::assert_eq;
+use tempfile::TempDir;
+use tokio::time::timeout;
+
+const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn test_list_and_resume_conversations() -> Result<()> {
+    // Prepare a temporary CODEX_HOME with a few fake rollout files.
+    let codex_home = TempDir::new()?;
+    create_fake_rollout(
+        codex_home.path(),
+        "2025-01-02T12-00-00",
+        "2025-01-02T12:00:00Z",
+        "Hello A",
+        Some("openai"),
+    )?;
+    create_fake_rollout(
+        codex_home.path(),
+        "2025-01-01T13-00-00",
+        "2025-01-01T13:00:00Z",
+        "Hello B",
+        Some("openai"),
+    )?;
+    create_fake_rollout(
+        codex_home.path(),
+        "2025-01-01T12-00-00",
+        "2025-01-01T12:00:00Z",
+        "Hello C",
+        None,
+    )?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    // Request first page with size 2
+    let req_id = mcp
+        .send_list_conversations_request(ListConversationsParams {
+            page_size: Some(2),
+            cursor: None,
+            model_providers: None,
+        })
+        .await?;
+    let resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(req_id)),
+    )
+    .await??;
+    let ListConversationsResponse { items, next_cursor } =
+        to_response::<ListConversationsResponse>(resp)?;
+
+    assert_eq!(items.len(), 2);
+    // Newest first; preview text should match
+    assert_eq!(items[0].preview, "Hello A");
+    assert_eq!(items[1].preview, "Hello B");
+    assert_eq!(items[0].model_provider, "openai");
+    assert_eq!(items[1].model_provider, "openai");
+    assert!(items[0].path.is_absolute());
+    assert!(next_cursor.is_some());
+
+    // Request the next page using the cursor
+    let req_id2 = mcp
+        .send_list_conversations_request(ListConversationsParams {
+            page_size: Some(2),
+            cursor: next_cursor,
+            model_providers: None,
+        })
+        .await?;
+    let resp2: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(req_id2)),
+    )
+    .await??;
+    let ListConversationsResponse {
+        items: items2,
+        next_cursor: next2,
+        ..
+    } = to_response::<ListConversationsResponse>(resp2)?;
+    assert_eq!(items2.len(), 1);
+    assert_eq!(items2[0].preview, "Hello C");
+    assert_eq!(items2[0].model_provider, "openai");
+    assert_eq!(next2, None);
+
+    // Add a conversation with an explicit non-OpenAI provider for filter tests.
+    create_fake_rollout(
+        codex_home.path(),
+        "2025-01-01T11-30-00",
+        "2025-01-01T11:30:00Z",
+        "Hello TP",
+        Some("test-provider"),
+    )?;
+
+    // Filtering by model provider should return only matching sessions.
+    let filter_req_id = mcp
+        .send_list_conversations_request(ListConversationsParams {
+            page_size: Some(10),
+            cursor: None,
+            model_providers: Some(vec!["test-provider".to_string()]),
+        })
+        .await?;
+    let filter_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(filter_req_id)),
+    )
+    .await??;
+    let ListConversationsResponse {
+        items: filtered_items,
+        next_cursor: filtered_next,
+    } = to_response::<ListConversationsResponse>(filter_resp)?;
+    assert_eq!(filtered_items.len(), 1);
+    assert_eq!(filtered_next, None);
+    assert_eq!(filtered_items[0].preview, "Hello TP");
+    assert_eq!(filtered_items[0].model_provider, "test-provider");
+
+    // Empty filter should include every session regardless of provider metadata.
+    let unfiltered_req_id = mcp
+        .send_list_conversations_request(ListConversationsParams {
+            page_size: Some(10),
+            cursor: None,
+            model_providers: Some(Vec::new()),
+        })
+        .await?;
+    let unfiltered_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(unfiltered_req_id)),
+    )
+    .await??;
+    let ListConversationsResponse {
+        items: unfiltered_items,
+        next_cursor: unfiltered_next,
+    } = to_response::<ListConversationsResponse>(unfiltered_resp)?;
+    assert_eq!(unfiltered_items.len(), 4);
+    assert!(unfiltered_next.is_none());
+
+    let empty_req_id = mcp
+        .send_list_conversations_request(ListConversationsParams {
+            page_size: Some(10),
+            cursor: None,
+            model_providers: Some(vec!["other".to_string()]),
+        })
+        .await?;
+    let empty_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(empty_req_id)),
+    )
+    .await??;
+    let ListConversationsResponse {
+        items: empty_items,
+        next_cursor: empty_next,
+    } = to_response::<ListConversationsResponse>(empty_resp)?;
+    assert!(empty_items.is_empty());
+    assert!(empty_next.is_none());
+
+    let first_item = &items[0];
+
+    // Now resume one of the sessions from an explicit rollout path.
+    let resume_req_id = mcp
+        .send_resume_conversation_request(ResumeConversationParams {
+            path: Some(first_item.path.clone()),
+            conversation_id: None,
+            history: None,
+            overrides: Some(NewConversationParams {
+                model: Some("o3".to_string()),
+                ..Default::default()
+            }),
+        })
+        .await?;
+
+    // Expect a codex/event notification with msg.type == sessionConfigured
+    let notification: JSONRPCNotification = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("sessionConfigured"),
+    )
+    .await??;
+    let session_configured: ServerNotification = notification.try_into()?;
+    let ServerNotification::SessionConfigured(SessionConfiguredNotification {
+        model,
+        rollout_path,
+        initial_messages: session_initial_messages,
+        ..
+    }) = session_configured
+    else {
+        unreachable!("expected sessionConfigured notification");
+    };
+    assert_eq!(model, "o3");
+    assert_eq!(rollout_path, first_item.path.clone());
+    let session_initial_messages = session_initial_messages
+        .expect("expected initial messages when resuming from rollout path");
+    match session_initial_messages.as_slice() {
+        [EventMsg::UserMessage(message)] => {
+            assert_eq!(message.message, first_item.preview.clone());
+        }
+        other => panic!("unexpected initial messages from rollout resume: {other:#?}"),
+    }
+
+    // Then the response for resumeConversation
+    let resume_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(resume_req_id)),
+    )
+    .await??;
+    let ResumeConversationResponse {
+        conversation_id,
+        model: resume_model,
+        initial_messages: response_initial_messages,
+        ..
+    } = to_response::<ResumeConversationResponse>(resume_resp)?;
+    // conversation id should be a valid UUID
+    assert!(!conversation_id.to_string().is_empty());
+    assert_eq!(resume_model, "o3");
+    let response_initial_messages =
+        response_initial_messages.expect("expected initial messages in resume response");
+    match response_initial_messages.as_slice() {
+        [EventMsg::UserMessage(message)] => {
+            assert_eq!(message.message, first_item.preview.clone());
+        }
+        other => panic!("unexpected initial messages in resume response: {other:#?}"),
+    }
+
+    // Resuming with only a conversation id should locate the rollout automatically.
+    let resume_by_id_req_id = mcp
+        .send_resume_conversation_request(ResumeConversationParams {
+            path: None,
+            conversation_id: Some(first_item.conversation_id),
+            history: None,
+            overrides: Some(NewConversationParams {
+                model: Some("o3".to_string()),
+                ..Default::default()
+            }),
+        })
+        .await?;
+    let notification: JSONRPCNotification = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("sessionConfigured"),
+    )
+    .await??;
+    let session_configured: ServerNotification = notification.try_into()?;
+    let ServerNotification::SessionConfigured(SessionConfiguredNotification {
+        model,
+        rollout_path,
+        initial_messages: session_initial_messages,
+        ..
+    }) = session_configured
+    else {
+        unreachable!("expected sessionConfigured notification");
+    };
+    assert_eq!(model, "o3");
+    assert_eq!(rollout_path, first_item.path.clone());
+    let session_initial_messages = session_initial_messages
+        .expect("expected initial messages when resuming from conversation id");
+    match session_initial_messages.as_slice() {
+        [EventMsg::UserMessage(message)] => {
+            assert_eq!(message.message, first_item.preview.clone());
+        }
+        other => panic!("unexpected initial messages from conversation id resume: {other:#?}"),
+    }
+    let resume_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(resume_by_id_req_id)),
+    )
+    .await??;
+    let ResumeConversationResponse {
+        conversation_id: by_id_conversation_id,
+        model: by_id_model,
+        initial_messages: by_id_initial_messages,
+        ..
+    } = to_response::<ResumeConversationResponse>(resume_resp)?;
+    assert!(!by_id_conversation_id.to_string().is_empty());
+    assert_eq!(by_id_model, "o3");
+    let by_id_initial_messages = by_id_initial_messages
+        .expect("expected initial messages when resuming from conversation id response");
+    match by_id_initial_messages.as_slice() {
+        [EventMsg::UserMessage(message)] => {
+            assert_eq!(message.message, first_item.preview.clone());
+        }
+        other => {
+            panic!("unexpected initial messages in conversation id resume response: {other:#?}")
+        }
+    }
+
+    // Resuming with explicit history should succeed even without a stored rollout.
+    let fork_history_text = "Hello from history";
+    let history = vec![ResponseItem::Message {
+        id: None,
+        role: "user".to_string(),
+        content: vec![ContentItem::InputText {
+            text: fork_history_text.to_string(),
+        }],
+    }];
+    let resume_with_history_req_id = mcp
+        .send_resume_conversation_request(ResumeConversationParams {
+            path: None,
+            conversation_id: None,
+            history: Some(history),
+            overrides: Some(NewConversationParams {
+                model: Some("o3".to_string()),
+                ..Default::default()
+            }),
+        })
+        .await?;
+    let notification: JSONRPCNotification = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("sessionConfigured"),
+    )
+    .await??;
+    let session_configured: ServerNotification = notification.try_into()?;
+    let ServerNotification::SessionConfigured(SessionConfiguredNotification {
+        model,
+        initial_messages: session_initial_messages,
+        ..
+    }) = session_configured
+    else {
+        unreachable!("expected sessionConfigured notification");
+    };
+    assert_eq!(model, "o3");
+    assert!(
+        session_initial_messages.as_ref().is_none_or(Vec::is_empty),
+        "expected no initial messages when resuming from explicit history but got {session_initial_messages:#?}"
+    );
+    let resume_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(resume_with_history_req_id)),
+    )
+    .await??;
+    let ResumeConversationResponse {
+        conversation_id: history_conversation_id,
+        model: history_model,
+        initial_messages: history_initial_messages,
+        ..
+    } = to_response::<ResumeConversationResponse>(resume_resp)?;
+    assert!(!history_conversation_id.to_string().is_empty());
+    assert_eq!(history_model, "o3");
+    assert!(
+        history_initial_messages.as_ref().is_none_or(Vec::is_empty),
+        "expected no initial messages in resume response when history is provided but got {history_initial_messages:#?}"
+    );
+
+    Ok(())
+}

llmx-rs/app-server/tests/suite/login.rs

@@ -0,0 +1,206 @@
+use anyhow::Result;
+use app_test_support::McpProcess;
+use app_test_support::to_response;
+use codex_app_server_protocol::CancelLoginChatGptParams;
+use codex_app_server_protocol::CancelLoginChatGptResponse;
+use codex_app_server_protocol::GetAuthStatusParams;
+use codex_app_server_protocol::GetAuthStatusResponse;
+use codex_app_server_protocol::JSONRPCError;
+use codex_app_server_protocol::JSONRPCResponse;
+use codex_app_server_protocol::LoginChatGptResponse;
+use codex_app_server_protocol::LogoutChatGptResponse;
+use codex_app_server_protocol::RequestId;
+use codex_core::auth::AuthCredentialsStoreMode;
+use codex_login::login_with_api_key;
+use serial_test::serial;
+use std::path::Path;
+use std::time::Duration;
+use tempfile::TempDir;
+use tokio::time::timeout;
+
+const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
+
+// Helper to create a config.toml; mirrors create_conversation.rs
+fn create_config_toml(codex_home: &Path) -> std::io::Result<()> {
+    let config_toml = codex_home.join("config.toml");
+    std::fs::write(
+        config_toml,
+        r#"
+model = "mock-model"
+approval_policy = "never"
+sandbox_mode = "danger-full-access"
+
+model_provider = "mock_provider"
+
+[model_providers.mock_provider]
+name = "Mock provider for test"
+base_url = "http://127.0.0.1:0/v1"
+wire_api = "chat"
+request_max_retries = 0
+stream_max_retries = 0
+"#,
+    )
+}
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn logout_chatgpt_removes_auth() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path())?;
+    login_with_api_key(
+        codex_home.path(),
+        "sk-test-key",
+        AuthCredentialsStoreMode::File,
+    )?;
+    assert!(codex_home.path().join("auth.json").exists());
+
+    let mut mcp = McpProcess::new_with_env(codex_home.path(), &[("OPENAI_API_KEY", None)]).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let id = mcp.send_logout_chat_gpt_request().await?;
+    let resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(id)),
+    )
+    .await??;
+    let _ok: LogoutChatGptResponse = to_response(resp)?;
+
+    assert!(
+        !codex_home.path().join("auth.json").exists(),
+        "auth.json should be deleted"
+    );
+
+    // Verify status reflects signed-out state.
+    let status_id = mcp
+        .send_get_auth_status_request(GetAuthStatusParams {
+            include_token: Some(true),
+            refresh_token: Some(false),
+        })
+        .await?;
+    let status_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(status_id)),
+    )
+    .await??;
+    let status: GetAuthStatusResponse = to_response(status_resp)?;
+    assert_eq!(status.auth_method, None);
+    assert_eq!(status.auth_token, None);
+    Ok(())
+}
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+// Serialize tests that launch the login server since it binds to a fixed port.
+#[serial(login_port)]
+async fn login_and_cancel_chatgpt() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path())?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let login_id = mcp.send_login_chat_gpt_request().await?;
+    let login_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(login_id)),
+    )
+    .await??;
+    let login: LoginChatGptResponse = to_response(login_resp)?;
+
+    let cancel_id = mcp
+        .send_cancel_login_chat_gpt_request(CancelLoginChatGptParams {
+            login_id: login.login_id,
+        })
+        .await?;
+    let cancel_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(cancel_id)),
+    )
+    .await??;
+    let _ok: CancelLoginChatGptResponse = to_response(cancel_resp)?;
+
+    // Optionally observe the completion notification; do not fail if it races.
+    let maybe_note = timeout(
+        Duration::from_secs(2),
+        mcp.read_stream_until_notification_message("codex/event/login_chat_gpt_complete"),
+    )
+    .await;
+    if maybe_note.is_err() {
+        eprintln!("warning: did not observe login_chat_gpt_complete notification after cancel");
+    }
+    Ok(())
+}
+
+fn create_config_toml_forced_login(codex_home: &Path, forced_method: &str) -> std::io::Result<()> {
+    let config_toml = codex_home.join("config.toml");
+    let contents = format!(
+        r#"
+model = "mock-model"
+approval_policy = "never"
+sandbox_mode = "danger-full-access"
+forced_login_method = "{forced_method}"
+"#
+    );
+    std::fs::write(config_toml, contents)
+}
+
+fn create_config_toml_forced_workspace(
+    codex_home: &Path,
+    workspace_id: &str,
+) -> std::io::Result<()> {
+    let config_toml = codex_home.join("config.toml");
+    let contents = format!(
+        r#"
+model = "mock-model"
+approval_policy = "never"
+sandbox_mode = "danger-full-access"
+forced_chatgpt_workspace_id = "{workspace_id}"
+"#
+    );
+    std::fs::write(config_toml, contents)
+}
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn login_chatgpt_rejected_when_forced_api() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_config_toml_forced_login(codex_home.path(), "api")?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let request_id = mcp.send_login_chat_gpt_request().await?;
+    let err: JSONRPCError = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_error_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+
+    assert_eq!(
+        err.error.message,
+        "ChatGPT login is disabled. Use API key login instead."
+    );
+    Ok(())
+}
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+// Serialize tests that launch the login server since it binds to a fixed port.
+#[serial(login_port)]
+async fn login_chatgpt_includes_forced_workspace_query_param() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_config_toml_forced_workspace(codex_home.path(), "ws-forced")?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let request_id = mcp.send_login_chat_gpt_request().await?;
+    let resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+
+    let login: LoginChatGptResponse = to_response(resp)?;
+    assert!(
+        login.auth_url.contains("allowed_workspace_id=ws-forced"),
+        "auth URL should include forced workspace"
+    );
+    Ok(())
+}

llmx-rs/app-server/tests/suite/mod.rs

@@ -0,0 +1,14 @@
+mod archive_conversation;
+mod auth;
+mod codex_message_processor_flow;
+mod config;
+mod create_conversation;
+mod fuzzy_file_search;
+mod interrupt;
+mod list_resume;
+mod login;
+mod send_message;
+mod set_default_model;
+mod user_agent;
+mod user_info;
+mod v2;

llmx-rs/app-server/tests/suite/send_message.rs

@@ -0,0 +1,391 @@
+use anyhow::Result;
+use app_test_support::McpProcess;
+use app_test_support::create_final_assistant_message_sse_response;
+use app_test_support::create_mock_chat_completions_server;
+use app_test_support::to_response;
+use codex_app_server_protocol::AddConversationListenerParams;
+use codex_app_server_protocol::AddConversationSubscriptionResponse;
+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_protocol::ConversationId;
+use codex_protocol::models::ContentItem;
+use codex_protocol::models::ResponseItem;
+use codex_protocol::protocol::RawResponseItemEvent;
+use pretty_assertions::assert_eq;
+use std::path::Path;
+use tempfile::TempDir;
+use tokio::time::timeout;
+
+const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
+
+#[tokio::test]
+async fn test_send_message_success() -> Result<()> {
+    // Spin up a mock completions server that immediately ends the Codex turn.
+    // Two Codex turns hit the mock model (session start + send-user-message). Provide two SSE responses.
+    let responses = vec![
+        create_final_assistant_message_sse_response("Done")?,
+        create_final_assistant_message_sse_response("Done")?,
+    ];
+    let server = create_mock_chat_completions_server(responses).await;
+
+    // Create a temporary Codex home with config pointing at the mock server.
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path(), &server.uri())?;
+
+    // Start MCP server process and initialize.
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    // Start a conversation using the new wire API.
+    let new_conv_id = mcp
+        .send_new_conversation_request(NewConversationParams {
+            ..Default::default()
+        })
+        .await?;
+    let new_conv_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(new_conv_id)),
+    )
+    .await??;
+    let NewConversationResponse {
+        conversation_id, ..
+    } = to_response::<_>(new_conv_resp)?;
+
+    // 2) addConversationListener
+    let add_listener_id = mcp
+        .send_add_conversation_listener_request(AddConversationListenerParams {
+            conversation_id,
+            experimental_raw_events: false,
+        })
+        .await?;
+    let add_listener_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(add_listener_id)),
+    )
+    .await??;
+    let AddConversationSubscriptionResponse { subscription_id: _ } =
+        to_response::<_>(add_listener_resp)?;
+
+    // Now exercise sendUserMessage twice.
+    send_message("Hello", conversation_id, &mut mcp).await?;
+    send_message("Hello again", conversation_id, &mut mcp).await?;
+    Ok(())
+}
+
+#[expect(clippy::expect_used)]
+async fn send_message(
+    message: &str,
+    conversation_id: ConversationId,
+    mcp: &mut McpProcess,
+) -> Result<()> {
+    // Now exercise sendUserMessage.
+    let send_id = mcp
+        .send_send_user_message_request(SendUserMessageParams {
+            conversation_id,
+            items: vec![InputItem::Text {
+                text: message.to_string(),
+            }],
+        })
+        .await?;
+
+    let response: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(send_id)),
+    )
+    .await??;
+
+    let _ok: SendUserMessageResponse = to_response::<SendUserMessageResponse>(response)?;
+
+    // Verify the task_finished notification is received.
+    // Note this also ensures that the final request to the server was made.
+    let task_finished_notification: JSONRPCNotification = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("codex/event/task_complete"),
+    )
+    .await??;
+    let serde_json::Value::Object(map) = task_finished_notification
+        .params
+        .expect("notification should have params")
+    else {
+        panic!("task_finished_notification should have params");
+    };
+    assert_eq!(
+        map.get("conversationId")
+            .expect("should have conversationId"),
+        &serde_json::Value::String(conversation_id.to_string())
+    );
+
+    let raw_attempt = tokio::time::timeout(
+        std::time::Duration::from_millis(200),
+        mcp.read_stream_until_notification_message("codex/event/raw_response_item"),
+    )
+    .await;
+    assert!(
+        raw_attempt.is_err(),
+        "unexpected raw item notification when not opted in"
+    );
+    Ok(())
+}
+
+#[tokio::test]
+async fn test_send_message_raw_notifications_opt_in() -> Result<()> {
+    let responses = vec![create_final_assistant_message_sse_response("Done")?];
+    let server = create_mock_chat_completions_server(responses).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 new_conv_id = mcp
+        .send_new_conversation_request(NewConversationParams {
+            developer_instructions: Some("Use the test harness tools.".to_string()),
+            ..Default::default()
+        })
+        .await?;
+    let new_conv_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(new_conv_id)),
+    )
+    .await??;
+    let NewConversationResponse {
+        conversation_id, ..
+    } = to_response::<_>(new_conv_resp)?;
+
+    let add_listener_id = mcp
+        .send_add_conversation_listener_request(AddConversationListenerParams {
+            conversation_id,
+            experimental_raw_events: true,
+        })
+        .await?;
+    let add_listener_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(add_listener_id)),
+    )
+    .await??;
+    let AddConversationSubscriptionResponse { subscription_id: _ } =
+        to_response::<_>(add_listener_resp)?;
+
+    let send_id = mcp
+        .send_send_user_message_request(SendUserMessageParams {
+            conversation_id,
+            items: vec![InputItem::Text {
+                text: "Hello".to_string(),
+            }],
+        })
+        .await?;
+
+    let developer = read_raw_response_item(&mut mcp, conversation_id).await;
+    assert_developer_message(&developer, "Use the test harness tools.");
+
+    let instructions = read_raw_response_item(&mut mcp, conversation_id).await;
+    assert_instructions_message(&instructions);
+
+    let environment = read_raw_response_item(&mut mcp, conversation_id).await;
+    assert_environment_message(&environment);
+
+    let response: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(send_id)),
+    )
+    .await??;
+    let _ok: SendUserMessageResponse = to_response::<SendUserMessageResponse>(response)?;
+
+    let user_message = read_raw_response_item(&mut mcp, conversation_id).await;
+    assert_user_message(&user_message, "Hello");
+
+    let assistant_message = read_raw_response_item(&mut mcp, conversation_id).await;
+    assert_assistant_message(&assistant_message, "Done");
+
+    let _ = tokio::time::timeout(
+        std::time::Duration::from_millis(250),
+        mcp.read_stream_until_notification_message("codex/event/task_complete"),
+    )
+    .await;
+
+    Ok(())
+}
+
+#[tokio::test]
+async fn test_send_message_session_not_found() -> Result<()> {
+    // Start MCP without creating a Codex session
+    let codex_home = TempDir::new()?;
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let unknown = ConversationId::new();
+    let req_id = mcp
+        .send_send_user_message_request(SendUserMessageParams {
+            conversation_id: unknown,
+            items: vec![InputItem::Text {
+                text: "ping".to_string(),
+            }],
+        })
+        .await?;
+
+    // Expect an error response for unknown conversation.
+    let err = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_error_message(RequestId::Integer(req_id)),
+    )
+    .await??;
+    assert_eq!(err.id, RequestId::Integer(req_id));
+    Ok(())
+}
+
+// ---------------------------------------------------------------------------
+// Helpers
+// ---------------------------------------------------------------------------
+
+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,
+        format!(
+            r#"
+model = "mock-model"
+approval_policy = "never"
+sandbox_mode = "danger-full-access"
+
+model_provider = "mock_provider"
+
+[model_providers.mock_provider]
+name = "Mock provider for test"
+base_url = "{server_uri}/v1"
+wire_api = "chat"
+request_max_retries = 0
+stream_max_retries = 0
+"#
+        ),
+    )
+}
+
+#[expect(clippy::expect_used)]
+async fn read_raw_response_item(
+    mcp: &mut McpProcess,
+    conversation_id: ConversationId,
+) -> ResponseItem {
+    let raw_notification: JSONRPCNotification = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("codex/event/raw_response_item"),
+    )
+    .await
+    .expect("codex/event/raw_response_item notification timeout")
+    .expect("codex/event/raw_response_item notification resp");
+
+    let serde_json::Value::Object(params) = raw_notification
+        .params
+        .expect("codex/event/raw_response_item should have params")
+    else {
+        panic!("codex/event/raw_response_item should have params");
+    };
+
+    let conversation_id_value = params
+        .get("conversationId")
+        .and_then(|value| value.as_str())
+        .expect("raw response item should include conversationId");
+
+    assert_eq!(
+        conversation_id_value,
+        conversation_id.to_string(),
+        "raw response item conversation mismatch"
+    );
+
+    let msg_value = params
+        .get("msg")
+        .cloned()
+        .expect("raw response item should include msg payload");
+
+    let event: RawResponseItemEvent =
+        serde_json::from_value(msg_value).expect("deserialize raw response item");
+    event.item
+}
+
+fn assert_instructions_message(item: &ResponseItem) {
+    match item {
+        ResponseItem::Message { role, content, .. } => {
+            assert_eq!(role, "user");
+            let texts = content_texts(content);
+            let is_instructions = texts
+                .iter()
+                .any(|text| text.starts_with("# AGENTS.md instructions for "));
+            assert!(
+                is_instructions,
+                "expected instructions message, got {texts:?}"
+            );
+        }
+        other => panic!("expected instructions message, got {other:?}"),
+    }
+}
+
+fn assert_developer_message(item: &ResponseItem, expected_text: &str) {
+    match item {
+        ResponseItem::Message { role, content, .. } => {
+            assert_eq!(role, "developer");
+            let texts = content_texts(content);
+            assert_eq!(
+                texts,
+                vec![expected_text],
+                "expected developer instructions message, got {texts:?}"
+            );
+        }
+        other => panic!("expected developer instructions message, got {other:?}"),
+    }
+}
+
+fn assert_environment_message(item: &ResponseItem) {
+    match item {
+        ResponseItem::Message { role, content, .. } => {
+            assert_eq!(role, "user");
+            let texts = content_texts(content);
+            assert!(
+                texts
+                    .iter()
+                    .any(|text| text.contains("<environment_context>")),
+                "expected environment context message, got {texts:?}"
+            );
+        }
+        other => panic!("expected environment message, got {other:?}"),
+    }
+}
+
+fn assert_user_message(item: &ResponseItem, expected_text: &str) {
+    match item {
+        ResponseItem::Message { role, content, .. } => {
+            assert_eq!(role, "user");
+            let texts = content_texts(content);
+            assert_eq!(texts, vec![expected_text]);
+        }
+        other => panic!("expected user message, got {other:?}"),
+    }
+}
+
+fn assert_assistant_message(item: &ResponseItem, expected_text: &str) {
+    match item {
+        ResponseItem::Message { role, content, .. } => {
+            assert_eq!(role, "assistant");
+            let texts = content_texts(content);
+            assert_eq!(texts, vec![expected_text]);
+        }
+        other => panic!("expected assistant message, got {other:?}"),
+    }
+}
+
+fn content_texts(content: &[ContentItem]) -> Vec<&str> {
+    content
+        .iter()
+        .filter_map(|item| match item {
+            ContentItem::InputText { text } | ContentItem::OutputText { text } => {
+                Some(text.as_str())
+            }
+            _ => None,
+        })
+        .collect()
+}

llmx-rs/app-server/tests/suite/set_default_model.rs

@@ -0,0 +1,64 @@
+use anyhow::Result;
+use app_test_support::McpProcess;
+use app_test_support::to_response;
+use codex_app_server_protocol::JSONRPCResponse;
+use codex_app_server_protocol::RequestId;
+use codex_app_server_protocol::SetDefaultModelParams;
+use codex_app_server_protocol::SetDefaultModelResponse;
+use codex_core::config::ConfigToml;
+use pretty_assertions::assert_eq;
+use std::path::Path;
+use tempfile::TempDir;
+use tokio::time::timeout;
+
+const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn set_default_model_persists_overrides() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path())?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let params = SetDefaultModelParams {
+        model: Some("gpt-4.1".to_string()),
+        reasoning_effort: None,
+    };
+
+    let request_id = mcp.send_set_default_model_request(params).await?;
+
+    let resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+
+    let _: SetDefaultModelResponse = to_response(resp)?;
+
+    let config_path = codex_home.path().join("config.toml");
+    let config_contents = tokio::fs::read_to_string(&config_path).await?;
+    let config_toml: ConfigToml = toml::from_str(&config_contents)?;
+
+    assert_eq!(
+        ConfigToml {
+            model: Some("gpt-4.1".to_string()),
+            model_reasoning_effort: None,
+            ..Default::default()
+        },
+        config_toml,
+    );
+    Ok(())
+}
+
+// Helper to create a config.toml; mirrors create_conversation.rs
+fn create_config_toml(codex_home: &Path) -> std::io::Result<()> {
+    let config_toml = codex_home.join("config.toml");
+    std::fs::write(
+        config_toml,
+        r#"
+model = "gpt-5-codex"
+model_reasoning_effort = "medium"
+"#,
+    )
+}

llmx-rs/app-server/tests/suite/user_agent.rs

@@ -0,0 +1,41 @@
+use anyhow::Result;
+use app_test_support::McpProcess;
+use app_test_support::to_response;
+use codex_app_server_protocol::GetUserAgentResponse;
+use codex_app_server_protocol::JSONRPCResponse;
+use codex_app_server_protocol::RequestId;
+use pretty_assertions::assert_eq;
+use tempfile::TempDir;
+use tokio::time::timeout;
+
+const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn get_user_agent_returns_current_codex_user_agent() -> Result<()> {
+    let codex_home = TempDir::new()?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let request_id = mcp.send_get_user_agent_request().await?;
+    let response: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+
+    let os_info = os_info::get();
+    let user_agent = format!(
+        "codex_cli_rs/0.0.0 ({} {}; {}) {} (codex-app-server-tests; 0.1.0)",
+        os_info.os_type(),
+        os_info.version(),
+        os_info.architecture().unwrap_or("unknown"),
+        codex_core::terminal::user_agent()
+    );
+
+    let received: GetUserAgentResponse = to_response(response)?;
+    let expected = GetUserAgentResponse { user_agent };
+
+    assert_eq!(received, expected);
+    Ok(())
+}

llmx-rs/app-server/tests/suite/user_info.rs

@@ -0,0 +1,46 @@
+use anyhow::Result;
+use app_test_support::ChatGptAuthFixture;
+use app_test_support::McpProcess;
+use app_test_support::to_response;
+use app_test_support::write_chatgpt_auth;
+use codex_app_server_protocol::JSONRPCResponse;
+use codex_app_server_protocol::RequestId;
+use codex_app_server_protocol::UserInfoResponse;
+use codex_core::auth::AuthCredentialsStoreMode;
+use pretty_assertions::assert_eq;
+use std::time::Duration;
+use tempfile::TempDir;
+use tokio::time::timeout;
+
+const DEFAULT_READ_TIMEOUT: Duration = Duration::from_secs(10);
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn user_info_returns_email_from_auth_json() -> Result<()> {
+    let codex_home = TempDir::new()?;
+
+    write_chatgpt_auth(
+        codex_home.path(),
+        ChatGptAuthFixture::new("access")
+            .refresh_token("refresh")
+            .email("user@example.com"),
+        AuthCredentialsStoreMode::File,
+    )?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let request_id = mcp.send_user_info_request().await?;
+    let response: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+
+    let received: UserInfoResponse = to_response(response)?;
+    let expected = UserInfoResponse {
+        alleged_user_email: Some("user@example.com".to_string()),
+    };
+
+    assert_eq!(received, expected);
+    Ok(())
+}

llmx-rs/app-server/tests/suite/v2/account.rs

@@ -0,0 +1,492 @@
+use anyhow::Result;
+use anyhow::bail;
+use app_test_support::McpProcess;
+use app_test_support::to_response;
+
+use app_test_support::ChatGptAuthFixture;
+use app_test_support::write_chatgpt_auth;
+use codex_app_server_protocol::Account;
+use codex_app_server_protocol::AuthMode;
+use codex_app_server_protocol::CancelLoginAccountParams;
+use codex_app_server_protocol::CancelLoginAccountResponse;
+use codex_app_server_protocol::GetAccountParams;
+use codex_app_server_protocol::GetAccountResponse;
+use codex_app_server_protocol::JSONRPCError;
+use codex_app_server_protocol::JSONRPCResponse;
+use codex_app_server_protocol::LoginAccountResponse;
+use codex_app_server_protocol::LogoutAccountResponse;
+use codex_app_server_protocol::RequestId;
+use codex_app_server_protocol::ServerNotification;
+use codex_core::auth::AuthCredentialsStoreMode;
+use codex_login::login_with_api_key;
+use codex_protocol::account::PlanType as AccountPlanType;
+use pretty_assertions::assert_eq;
+use serial_test::serial;
+use std::path::Path;
+use std::time::Duration;
+use tempfile::TempDir;
+use tokio::time::timeout;
+
+const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
+
+// Helper to create a minimal config.toml for the app server
+#[derive(Default)]
+struct CreateConfigTomlParams {
+    forced_method: Option<String>,
+    forced_workspace_id: Option<String>,
+    requires_openai_auth: Option<bool>,
+}
+
+fn create_config_toml(codex_home: &Path, params: CreateConfigTomlParams) -> std::io::Result<()> {
+    let config_toml = codex_home.join("config.toml");
+    let forced_line = if let Some(method) = params.forced_method {
+        format!("forced_login_method = \"{method}\"\n")
+    } else {
+        String::new()
+    };
+    let forced_workspace_line = if let Some(ws) = params.forced_workspace_id {
+        format!("forced_chatgpt_workspace_id = \"{ws}\"\n")
+    } else {
+        String::new()
+    };
+    let requires_line = match params.requires_openai_auth {
+        Some(true) => "requires_openai_auth = true\n".to_string(),
+        Some(false) => String::new(),
+        None => String::new(),
+    };
+    let contents = format!(
+        r#"
+model = "mock-model"
+approval_policy = "never"
+sandbox_mode = "danger-full-access"
+{forced_line}
+{forced_workspace_line}
+
+model_provider = "mock_provider"
+
+[model_providers.mock_provider]
+name = "Mock provider for test"
+base_url = "http://127.0.0.1:0/v1"
+wire_api = "chat"
+request_max_retries = 0
+stream_max_retries = 0
+{requires_line}
+"#
+    );
+    std::fs::write(config_toml, contents)
+}
+
+#[tokio::test]
+async fn logout_account_removes_auth_and_notifies() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path(), CreateConfigTomlParams::default())?;
+
+    login_with_api_key(
+        codex_home.path(),
+        "sk-test-key",
+        AuthCredentialsStoreMode::File,
+    )?;
+    assert!(codex_home.path().join("auth.json").exists());
+
+    let mut mcp = McpProcess::new_with_env(codex_home.path(), &[("OPENAI_API_KEY", None)]).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let id = mcp.send_logout_account_request().await?;
+    let resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(id)),
+    )
+    .await??;
+    let _ok: LogoutAccountResponse = to_response(resp)?;
+
+    let note = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("account/updated"),
+    )
+    .await??;
+    let parsed: ServerNotification = note.try_into()?;
+    let ServerNotification::AccountUpdated(payload) = parsed else {
+        bail!("unexpected notification: {parsed:?}");
+    };
+    assert!(
+        payload.auth_mode.is_none(),
+        "auth_method should be None after logout"
+    );
+
+    assert!(
+        !codex_home.path().join("auth.json").exists(),
+        "auth.json should be deleted"
+    );
+
+    let get_id = mcp
+        .send_get_account_request(GetAccountParams {
+            refresh_token: false,
+        })
+        .await?;
+    let get_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(get_id)),
+    )
+    .await??;
+    let account: GetAccountResponse = to_response(get_resp)?;
+    assert_eq!(account.account, None);
+    Ok(())
+}
+
+#[tokio::test]
+async fn login_account_api_key_succeeds_and_notifies() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path(), CreateConfigTomlParams::default())?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let req_id = mcp
+        .send_login_account_api_key_request("sk-test-key")
+        .await?;
+    let resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(req_id)),
+    )
+    .await??;
+    let login: LoginAccountResponse = to_response(resp)?;
+    assert_eq!(login, LoginAccountResponse::ApiKey {});
+
+    let note = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("account/login/completed"),
+    )
+    .await??;
+    let parsed: ServerNotification = note.try_into()?;
+    let ServerNotification::AccountLoginCompleted(payload) = parsed else {
+        bail!("unexpected notification: {parsed:?}");
+    };
+    pretty_assertions::assert_eq!(payload.login_id, None);
+    pretty_assertions::assert_eq!(payload.success, true);
+    pretty_assertions::assert_eq!(payload.error, None);
+
+    let note = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("account/updated"),
+    )
+    .await??;
+    let parsed: ServerNotification = note.try_into()?;
+    let ServerNotification::AccountUpdated(payload) = parsed else {
+        bail!("unexpected notification: {parsed:?}");
+    };
+    pretty_assertions::assert_eq!(payload.auth_mode, Some(AuthMode::ApiKey));
+
+    assert!(codex_home.path().join("auth.json").exists());
+    Ok(())
+}
+
+#[tokio::test]
+async fn login_account_api_key_rejected_when_forced_chatgpt() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_config_toml(
+        codex_home.path(),
+        CreateConfigTomlParams {
+            forced_method: Some("chatgpt".to_string()),
+            ..Default::default()
+        },
+    )?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let request_id = mcp
+        .send_login_account_api_key_request("sk-test-key")
+        .await?;
+    let err: JSONRPCError = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_error_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+
+    assert_eq!(
+        err.error.message,
+        "API key login is disabled. Use ChatGPT login instead."
+    );
+    Ok(())
+}
+
+#[tokio::test]
+async fn login_account_chatgpt_rejected_when_forced_api() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_config_toml(
+        codex_home.path(),
+        CreateConfigTomlParams {
+            forced_method: Some("api".to_string()),
+            ..Default::default()
+        },
+    )?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let request_id = mcp.send_login_account_chatgpt_request().await?;
+    let err: JSONRPCError = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_error_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+
+    assert_eq!(
+        err.error.message,
+        "ChatGPT login is disabled. Use API key login instead."
+    );
+    Ok(())
+}
+
+#[tokio::test]
+// Serialize tests that launch the login server since it binds to a fixed port.
+#[serial(login_port)]
+async fn login_account_chatgpt_start() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path(), CreateConfigTomlParams::default())?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let request_id = mcp.send_login_account_chatgpt_request().await?;
+    let resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+
+    let login: LoginAccountResponse = to_response(resp)?;
+    let LoginAccountResponse::Chatgpt { login_id, auth_url } = login else {
+        bail!("unexpected login response: {login:?}");
+    };
+    assert!(
+        auth_url.contains("redirect_uri=http%3A%2F%2Flocalhost"),
+        "auth_url should contain a redirect_uri to localhost"
+    );
+
+    let cancel_id = mcp
+        .send_cancel_login_account_request(CancelLoginAccountParams {
+            login_id: login_id.clone(),
+        })
+        .await?;
+    let cancel_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(cancel_id)),
+    )
+    .await??;
+    let _ok: CancelLoginAccountResponse = to_response(cancel_resp)?;
+
+    let note = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("account/login/completed"),
+    )
+    .await??;
+    let parsed: ServerNotification = note.try_into()?;
+    let ServerNotification::AccountLoginCompleted(payload) = parsed else {
+        bail!("unexpected notification: {parsed:?}");
+    };
+    pretty_assertions::assert_eq!(payload.login_id, Some(login_id));
+    pretty_assertions::assert_eq!(payload.success, false);
+    assert!(
+        payload.error.is_some(),
+        "expected a non-empty error on cancel"
+    );
+
+    let maybe_updated = timeout(
+        Duration::from_millis(500),
+        mcp.read_stream_until_notification_message("account/updated"),
+    )
+    .await;
+    assert!(
+        maybe_updated.is_err(),
+        "account/updated should not be emitted when login is cancelled"
+    );
+    Ok(())
+}
+
+#[tokio::test]
+// Serialize tests that launch the login server since it binds to a fixed port.
+#[serial(login_port)]
+async fn login_account_chatgpt_includes_forced_workspace_query_param() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_config_toml(
+        codex_home.path(),
+        CreateConfigTomlParams {
+            forced_workspace_id: Some("ws-forced".to_string()),
+            ..Default::default()
+        },
+    )?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let request_id = mcp.send_login_account_chatgpt_request().await?;
+    let resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+
+    let login: LoginAccountResponse = to_response(resp)?;
+    let LoginAccountResponse::Chatgpt { auth_url, .. } = login else {
+        bail!("unexpected login response: {login:?}");
+    };
+    assert!(
+        auth_url.contains("allowed_workspace_id=ws-forced"),
+        "auth URL should include forced workspace"
+    );
+    Ok(())
+}
+
+#[tokio::test]
+async fn get_account_no_auth() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_config_toml(
+        codex_home.path(),
+        CreateConfigTomlParams {
+            requires_openai_auth: Some(true),
+            ..Default::default()
+        },
+    )?;
+
+    let mut mcp = McpProcess::new_with_env(codex_home.path(), &[("OPENAI_API_KEY", None)]).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let params = GetAccountParams {
+        refresh_token: false,
+    };
+    let request_id = mcp.send_get_account_request(params).await?;
+
+    let resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+    let account: GetAccountResponse = to_response(resp)?;
+
+    assert_eq!(account.account, None, "expected no account");
+    assert_eq!(account.requires_openai_auth, true);
+    Ok(())
+}
+
+#[tokio::test]
+async fn get_account_with_api_key() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_config_toml(
+        codex_home.path(),
+        CreateConfigTomlParams {
+            requires_openai_auth: Some(true),
+            ..Default::default()
+        },
+    )?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let req_id = mcp
+        .send_login_account_api_key_request("sk-test-key")
+        .await?;
+    let resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(req_id)),
+    )
+    .await??;
+    let _login_ok = to_response::<LoginAccountResponse>(resp)?;
+
+    let params = GetAccountParams {
+        refresh_token: false,
+    };
+    let request_id = mcp.send_get_account_request(params).await?;
+
+    let resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+    let received: GetAccountResponse = to_response(resp)?;
+
+    let expected = GetAccountResponse {
+        account: Some(Account::ApiKey {}),
+        requires_openai_auth: true,
+    };
+    assert_eq!(received, expected);
+    Ok(())
+}
+
+#[tokio::test]
+async fn get_account_when_auth_not_required() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_config_toml(
+        codex_home.path(),
+        CreateConfigTomlParams {
+            requires_openai_auth: Some(false),
+            ..Default::default()
+        },
+    )?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let params = GetAccountParams {
+        refresh_token: false,
+    };
+    let request_id = mcp.send_get_account_request(params).await?;
+
+    let resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+    let received: GetAccountResponse = to_response(resp)?;
+
+    let expected = GetAccountResponse {
+        account: None,
+        requires_openai_auth: false,
+    };
+    assert_eq!(received, expected);
+    Ok(())
+}
+
+#[tokio::test]
+async fn get_account_with_chatgpt() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_config_toml(
+        codex_home.path(),
+        CreateConfigTomlParams {
+            requires_openai_auth: Some(true),
+            ..Default::default()
+        },
+    )?;
+    write_chatgpt_auth(
+        codex_home.path(),
+        ChatGptAuthFixture::new("access-chatgpt")
+            .email("user@example.com")
+            .plan_type("pro"),
+        AuthCredentialsStoreMode::File,
+    )?;
+
+    let mut mcp = McpProcess::new_with_env(codex_home.path(), &[("OPENAI_API_KEY", None)]).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let params = GetAccountParams {
+        refresh_token: false,
+    };
+    let request_id = mcp.send_get_account_request(params).await?;
+
+    let resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+    let received: GetAccountResponse = to_response(resp)?;
+
+    let expected = GetAccountResponse {
+        account: Some(Account::Chatgpt {
+            email: "user@example.com".to_string(),
+            plan_type: AccountPlanType::Pro,
+        }),
+        requires_openai_auth: true,
+    };
+    assert_eq!(received, expected);
+    Ok(())
+}

llmx-rs/app-server/tests/suite/v2/mod.rs

@@ -0,0 +1,9 @@
+mod account;
+mod model_list;
+mod rate_limits;
+mod thread_archive;
+mod thread_list;
+mod thread_resume;
+mod thread_start;
+mod turn_interrupt;
+mod turn_start;

llmx-rs/app-server/tests/suite/v2/model_list.rs

@@ -0,0 +1,186 @@
+use std::time::Duration;
+
+use anyhow::Result;
+use anyhow::anyhow;
+use app_test_support::McpProcess;
+use app_test_support::to_response;
+use codex_app_server_protocol::JSONRPCError;
+use codex_app_server_protocol::JSONRPCResponse;
+use codex_app_server_protocol::Model;
+use codex_app_server_protocol::ModelListParams;
+use codex_app_server_protocol::ModelListResponse;
+use codex_app_server_protocol::ReasoningEffortOption;
+use codex_app_server_protocol::RequestId;
+use codex_protocol::config_types::ReasoningEffort;
+use pretty_assertions::assert_eq;
+use tempfile::TempDir;
+use tokio::time::timeout;
+
+const DEFAULT_TIMEOUT: Duration = Duration::from_secs(10);
+const INVALID_REQUEST_ERROR_CODE: i64 = -32600;
+
+#[tokio::test]
+async fn list_models_returns_all_models_with_large_limit() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+
+    timeout(DEFAULT_TIMEOUT, mcp.initialize()).await??;
+
+    let request_id = mcp
+        .send_list_models_request(ModelListParams {
+            limit: Some(100),
+            cursor: None,
+        })
+        .await?;
+
+    let response: JSONRPCResponse = timeout(
+        DEFAULT_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+
+    let ModelListResponse {
+        data: items,
+        next_cursor,
+    } = to_response::<ModelListResponse>(response)?;
+
+    let expected_models = vec![
+        Model {
+            id: "gpt-5-codex".to_string(),
+            model: "gpt-5-codex".to_string(),
+            display_name: "gpt-5-codex".to_string(),
+            description: "Optimized for codex.".to_string(),
+            supported_reasoning_efforts: vec![
+                ReasoningEffortOption {
+                    reasoning_effort: ReasoningEffort::Low,
+                    description: "Fastest responses with limited reasoning".to_string(),
+                },
+                ReasoningEffortOption {
+                    reasoning_effort: ReasoningEffort::Medium,
+                    description: "Dynamically adjusts reasoning based on the task".to_string(),
+                },
+                ReasoningEffortOption {
+                    reasoning_effort: ReasoningEffort::High,
+                    description: "Maximizes reasoning depth for complex or ambiguous problems"
+                        .to_string(),
+                },
+            ],
+            default_reasoning_effort: ReasoningEffort::Medium,
+            is_default: true,
+        },
+        Model {
+            id: "gpt-5".to_string(),
+            model: "gpt-5".to_string(),
+            display_name: "gpt-5".to_string(),
+            description: "Broad world knowledge with strong general reasoning.".to_string(),
+            supported_reasoning_efforts: vec![
+                ReasoningEffortOption {
+                    reasoning_effort: ReasoningEffort::Minimal,
+                    description: "Fastest responses with little reasoning".to_string(),
+                },
+                ReasoningEffortOption {
+                    reasoning_effort: ReasoningEffort::Low,
+                    description: "Balances speed with some reasoning; useful for straightforward \
+                                   queries and short explanations"
+                        .to_string(),
+                },
+                ReasoningEffortOption {
+                    reasoning_effort: ReasoningEffort::Medium,
+                    description: "Provides a solid balance of reasoning depth and latency for \
+                         general-purpose tasks"
+                        .to_string(),
+                },
+                ReasoningEffortOption {
+                    reasoning_effort: ReasoningEffort::High,
+                    description: "Maximizes reasoning depth for complex or ambiguous problems"
+                        .to_string(),
+                },
+            ],
+            default_reasoning_effort: ReasoningEffort::Medium,
+            is_default: false,
+        },
+    ];
+
+    assert_eq!(items, expected_models);
+    assert!(next_cursor.is_none());
+    Ok(())
+}
+
+#[tokio::test]
+async fn list_models_pagination_works() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+
+    timeout(DEFAULT_TIMEOUT, mcp.initialize()).await??;
+
+    let first_request = mcp
+        .send_list_models_request(ModelListParams {
+            limit: Some(1),
+            cursor: None,
+        })
+        .await?;
+
+    let first_response: JSONRPCResponse = timeout(
+        DEFAULT_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(first_request)),
+    )
+    .await??;
+
+    let ModelListResponse {
+        data: first_items,
+        next_cursor: first_cursor,
+    } = to_response::<ModelListResponse>(first_response)?;
+
+    assert_eq!(first_items.len(), 1);
+    assert_eq!(first_items[0].id, "gpt-5-codex");
+    let next_cursor = first_cursor.ok_or_else(|| anyhow!("cursor for second page"))?;
+
+    let second_request = mcp
+        .send_list_models_request(ModelListParams {
+            limit: Some(1),
+            cursor: Some(next_cursor.clone()),
+        })
+        .await?;
+
+    let second_response: JSONRPCResponse = timeout(
+        DEFAULT_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(second_request)),
+    )
+    .await??;
+
+    let ModelListResponse {
+        data: second_items,
+        next_cursor: second_cursor,
+    } = to_response::<ModelListResponse>(second_response)?;
+
+    assert_eq!(second_items.len(), 1);
+    assert_eq!(second_items[0].id, "gpt-5");
+    assert!(second_cursor.is_none());
+    Ok(())
+}
+
+#[tokio::test]
+async fn list_models_rejects_invalid_cursor() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+
+    timeout(DEFAULT_TIMEOUT, mcp.initialize()).await??;
+
+    let request_id = mcp
+        .send_list_models_request(ModelListParams {
+            limit: None,
+            cursor: Some("invalid".to_string()),
+        })
+        .await?;
+
+    let error: JSONRPCError = timeout(
+        DEFAULT_TIMEOUT,
+        mcp.read_stream_until_error_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+
+    assert_eq!(error.id, RequestId::Integer(request_id));
+    assert_eq!(error.error.code, INVALID_REQUEST_ERROR_CODE);
+    assert_eq!(error.error.message, "invalid cursor: invalid");
+    Ok(())
+}

llmx-rs/app-server/tests/suite/v2/rate_limits.rs

@@ -0,0 +1,181 @@
+use anyhow::Result;
+use app_test_support::ChatGptAuthFixture;
+use app_test_support::McpProcess;
+use app_test_support::to_response;
+use app_test_support::write_chatgpt_auth;
+use codex_app_server_protocol::GetAccountRateLimitsResponse;
+use codex_app_server_protocol::JSONRPCError;
+use codex_app_server_protocol::JSONRPCResponse;
+use codex_app_server_protocol::LoginApiKeyParams;
+use codex_app_server_protocol::RateLimitSnapshot;
+use codex_app_server_protocol::RateLimitWindow;
+use codex_app_server_protocol::RequestId;
+use codex_core::auth::AuthCredentialsStoreMode;
+use pretty_assertions::assert_eq;
+use serde_json::json;
+use std::path::Path;
+use tempfile::TempDir;
+use tokio::time::timeout;
+use wiremock::Mock;
+use wiremock::MockServer;
+use wiremock::ResponseTemplate;
+use wiremock::matchers::header;
+use wiremock::matchers::method;
+use wiremock::matchers::path;
+
+const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
+const INVALID_REQUEST_ERROR_CODE: i64 = -32600;
+
+#[tokio::test]
+async fn get_account_rate_limits_requires_auth() -> Result<()> {
+    let codex_home = TempDir::new()?;
+
+    let mut mcp = McpProcess::new_with_env(codex_home.path(), &[("OPENAI_API_KEY", None)]).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let request_id = mcp.send_get_account_rate_limits_request().await?;
+
+    let error: JSONRPCError = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_error_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+
+    assert_eq!(error.id, RequestId::Integer(request_id));
+    assert_eq!(error.error.code, INVALID_REQUEST_ERROR_CODE);
+    assert_eq!(
+        error.error.message,
+        "codex account authentication required to read rate limits"
+    );
+
+    Ok(())
+}
+
+#[tokio::test]
+async fn get_account_rate_limits_requires_chatgpt_auth() -> Result<()> {
+    let codex_home = TempDir::new()?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    login_with_api_key(&mut mcp, "sk-test-key").await?;
+
+    let request_id = mcp.send_get_account_rate_limits_request().await?;
+
+    let error: JSONRPCError = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_error_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+
+    assert_eq!(error.id, RequestId::Integer(request_id));
+    assert_eq!(error.error.code, INVALID_REQUEST_ERROR_CODE);
+    assert_eq!(
+        error.error.message,
+        "chatgpt authentication required to read rate limits"
+    );
+
+    Ok(())
+}
+
+#[tokio::test]
+async fn get_account_rate_limits_returns_snapshot() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    write_chatgpt_auth(
+        codex_home.path(),
+        ChatGptAuthFixture::new("chatgpt-token")
+            .account_id("account-123")
+            .plan_type("pro"),
+        AuthCredentialsStoreMode::File,
+    )?;
+
+    let server = MockServer::start().await;
+    let server_url = server.uri();
+    write_chatgpt_base_url(codex_home.path(), &server_url)?;
+
+    let primary_reset_timestamp = chrono::DateTime::parse_from_rfc3339("2025-01-01T00:02:00Z")
+        .expect("parse primary reset timestamp")
+        .timestamp();
+    let secondary_reset_timestamp = chrono::DateTime::parse_from_rfc3339("2025-01-01T01:00:00Z")
+        .expect("parse secondary reset timestamp")
+        .timestamp();
+    let response_body = json!({
+        "plan_type": "pro",
+        "rate_limit": {
+            "allowed": true,
+            "limit_reached": false,
+            "primary_window": {
+                "used_percent": 42,
+                "limit_window_seconds": 3600,
+                "reset_after_seconds": 120,
+                "reset_at": primary_reset_timestamp,
+            },
+            "secondary_window": {
+                "used_percent": 5,
+                "limit_window_seconds": 86400,
+                "reset_after_seconds": 43200,
+                "reset_at": secondary_reset_timestamp,
+            }
+        }
+    });
+
+    Mock::given(method("GET"))
+        .and(path("/api/codex/usage"))
+        .and(header("authorization", "Bearer chatgpt-token"))
+        .and(header("chatgpt-account-id", "account-123"))
+        .respond_with(ResponseTemplate::new(200).set_body_json(response_body))
+        .mount(&server)
+        .await;
+
+    let mut mcp = McpProcess::new_with_env(codex_home.path(), &[("OPENAI_API_KEY", None)]).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let request_id = mcp.send_get_account_rate_limits_request().await?;
+
+    let response: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+
+    let received: GetAccountRateLimitsResponse = to_response(response)?;
+
+    let expected = GetAccountRateLimitsResponse {
+        rate_limits: RateLimitSnapshot {
+            primary: Some(RateLimitWindow {
+                used_percent: 42,
+                window_duration_mins: Some(60),
+                resets_at: Some(primary_reset_timestamp),
+            }),
+            secondary: Some(RateLimitWindow {
+                used_percent: 5,
+                window_duration_mins: Some(1440),
+                resets_at: Some(secondary_reset_timestamp),
+            }),
+        },
+    };
+    assert_eq!(received, expected);
+
+    Ok(())
+}
+
+async fn login_with_api_key(mcp: &mut McpProcess, api_key: &str) -> Result<()> {
+    let request_id = mcp
+        .send_login_api_key_request(LoginApiKeyParams {
+            api_key: api_key.to_string(),
+        })
+        .await?;
+
+    timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(request_id)),
+    )
+    .await??;
+
+    Ok(())
+}
+
+fn write_chatgpt_base_url(codex_home: &Path, base_url: &str) -> std::io::Result<()> {
+    let config_toml = codex_home.join("config.toml");
+    std::fs::write(config_toml, format!("chatgpt_base_url = \"{base_url}\"\n"))
+}

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

@@ -0,0 +1,93 @@
+use anyhow::Result;
+use app_test_support::McpProcess;
+use app_test_support::to_response;
+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_core::ARCHIVED_SESSIONS_SUBDIR;
+use codex_core::find_conversation_path_by_id_str;
+use std::path::Path;
+use tempfile::TempDir;
+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<()> {
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path())?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    // Start a thread.
+    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)?;
+    assert!(!thread.id.is_empty());
+
+    // Locate the rollout path recorded for this thread id.
+    let rollout_path = find_conversation_path_by_id_str(codex_home.path(), &thread.id)
+        .await?
+        .expect("expected rollout path for thread id to exist");
+    assert!(
+        rollout_path.exists(),
+        "expected {} to exist",
+        rollout_path.display()
+    );
+
+    // Archive the thread.
+    let archive_id = mcp
+        .send_thread_archive_request(ThreadArchiveParams {
+            thread_id: thread.id.clone(),
+        })
+        .await?;
+    let archive_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(archive_id)),
+    )
+    .await??;
+    let _: ThreadArchiveResponse = to_response::<ThreadArchiveResponse>(archive_resp)?;
+
+    // Verify file moved.
+    let archived_directory = codex_home.path().join(ARCHIVED_SESSIONS_SUBDIR);
+    // The archived file keeps the original filename (rollout-...-<id>.jsonl).
+    let archived_rollout_path =
+        archived_directory.join(rollout_path.file_name().expect("rollout file name"));
+    assert!(
+        !rollout_path.exists(),
+        "expected rollout path {} to be moved",
+        rollout_path.display()
+    );
+    assert!(
+        archived_rollout_path.exists(),
+        "expected archived rollout path {} to exist",
+        archived_rollout_path.display()
+    );
+
+    Ok(())
+}
+
+fn create_config_toml(codex_home: &Path) -> std::io::Result<()> {
+    let config_toml = codex_home.join("config.toml");
+    std::fs::write(config_toml, config_contents())
+}
+
+fn config_contents() -> &'static str {
+    r#"model = "mock-model"
+approval_policy = "never"
+sandbox_mode = "read-only"
+"#
+}

llmx-rs/app-server/tests/suite/v2/thread_list.rs

@@ -0,0 +1,220 @@
+use anyhow::Result;
+use app_test_support::McpProcess;
+use app_test_support::create_fake_rollout;
+use app_test_support::to_response;
+use codex_app_server_protocol::JSONRPCResponse;
+use codex_app_server_protocol::RequestId;
+use codex_app_server_protocol::ThreadListParams;
+use codex_app_server_protocol::ThreadListResponse;
+use serde_json::json;
+use tempfile::TempDir;
+use tokio::time::timeout;
+use uuid::Uuid;
+
+const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
+
+#[tokio::test]
+async fn thread_list_basic_empty() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_minimal_config(codex_home.path())?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    // List threads in an empty CODEX_HOME; should return an empty page with nextCursor: null.
+    let list_id = mcp
+        .send_thread_list_request(ThreadListParams {
+            cursor: None,
+            limit: Some(10),
+            model_providers: None,
+        })
+        .await?;
+    let list_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(list_id)),
+    )
+    .await??;
+    let ThreadListResponse { data, next_cursor } = to_response::<ThreadListResponse>(list_resp)?;
+    assert!(data.is_empty());
+    assert_eq!(next_cursor, None);
+
+    Ok(())
+}
+
+// Minimal config.toml for listing.
+fn create_minimal_config(codex_home: &std::path::Path) -> std::io::Result<()> {
+    let config_toml = codex_home.join("config.toml");
+    std::fs::write(
+        config_toml,
+        r#"
+model = "mock-model"
+approval_policy = "never"
+"#,
+    )
+}
+
+#[tokio::test]
+async fn thread_list_pagination_next_cursor_none_on_last_page() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_minimal_config(codex_home.path())?;
+
+    // Create three rollouts so we can paginate with limit=2.
+    let _a = create_fake_rollout(
+        codex_home.path(),
+        "2025-01-02T12-00-00",
+        "2025-01-02T12:00:00Z",
+        "Hello",
+        Some("mock_provider"),
+    )?;
+    let _b = create_fake_rollout(
+        codex_home.path(),
+        "2025-01-01T13-00-00",
+        "2025-01-01T13:00:00Z",
+        "Hello",
+        Some("mock_provider"),
+    )?;
+    let _c = create_fake_rollout(
+        codex_home.path(),
+        "2025-01-01T12-00-00",
+        "2025-01-01T12:00:00Z",
+        "Hello",
+        Some("mock_provider"),
+    )?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    // Page 1: limit 2 → expect next_cursor Some.
+    let page1_id = mcp
+        .send_thread_list_request(ThreadListParams {
+            cursor: None,
+            limit: Some(2),
+            model_providers: Some(vec!["mock_provider".to_string()]),
+        })
+        .await?;
+    let page1_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(page1_id)),
+    )
+    .await??;
+    let ThreadListResponse {
+        data: data1,
+        next_cursor: cursor1,
+    } = to_response::<ThreadListResponse>(page1_resp)?;
+    assert_eq!(data1.len(), 2);
+    for thread in &data1 {
+        assert_eq!(thread.preview, "Hello");
+        assert_eq!(thread.model_provider, "mock_provider");
+        assert!(thread.created_at > 0);
+    }
+    let cursor1 = cursor1.expect("expected nextCursor on first page");
+
+    // Page 2: with cursor → expect next_cursor None when no more results.
+    let page2_id = mcp
+        .send_thread_list_request(ThreadListParams {
+            cursor: Some(cursor1),
+            limit: Some(2),
+            model_providers: Some(vec!["mock_provider".to_string()]),
+        })
+        .await?;
+    let page2_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(page2_id)),
+    )
+    .await??;
+    let ThreadListResponse {
+        data: data2,
+        next_cursor: cursor2,
+    } = to_response::<ThreadListResponse>(page2_resp)?;
+    assert!(data2.len() <= 2);
+    for thread in &data2 {
+        assert_eq!(thread.preview, "Hello");
+        assert_eq!(thread.model_provider, "mock_provider");
+        assert!(thread.created_at > 0);
+    }
+    assert_eq!(cursor2, None, "expected nextCursor to be null on last page");
+
+    Ok(())
+}
+
+#[tokio::test]
+async fn thread_list_respects_provider_filter() -> Result<()> {
+    let codex_home = TempDir::new()?;
+    create_minimal_config(codex_home.path())?;
+
+    // Create rollouts under two providers.
+    let _a = create_fake_rollout(
+        codex_home.path(),
+        "2025-01-02T10-00-00",
+        "2025-01-02T10:00:00Z",
+        "X",
+        Some("mock_provider"),
+    )?; // mock_provider
+    // one with a different provider
+    let uuid = Uuid::new_v4();
+    let dir = codex_home
+        .path()
+        .join("sessions")
+        .join("2025")
+        .join("01")
+        .join("02");
+    std::fs::create_dir_all(&dir)?;
+    let file_path = dir.join(format!("rollout-2025-01-02T11-00-00-{uuid}.jsonl"));
+    let lines = [
+        json!({
+            "timestamp": "2025-01-02T11:00:00Z",
+            "type": "session_meta",
+            "payload": {
+                "id": uuid,
+                "timestamp": "2025-01-02T11:00:00Z",
+                "cwd": "/",
+                "originator": "codex",
+                "cli_version": "0.0.0",
+                "instructions": null,
+                "source": "vscode",
+                "model_provider": "other_provider"
+            }
+        })
+        .to_string(),
+        json!({
+            "timestamp": "2025-01-02T11:00:00Z",
+            "type":"response_item",
+            "payload": {"type":"message","role":"user","content":[{"type":"input_text","text":"X"}]}
+        })
+        .to_string(),
+        json!({
+            "timestamp": "2025-01-02T11:00:00Z",
+            "type":"event_msg",
+            "payload": {"type":"user_message","message":"X","kind":"plain"}
+        })
+        .to_string(),
+    ];
+    std::fs::write(file_path, lines.join("\n") + "\n")?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    // Filter to only other_provider; expect 1 item, nextCursor None.
+    let list_id = mcp
+        .send_thread_list_request(ThreadListParams {
+            cursor: None,
+            limit: Some(10),
+            model_providers: Some(vec!["other_provider".to_string()]),
+        })
+        .await?;
+    let resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(list_id)),
+    )
+    .await??;
+    let ThreadListResponse { data, next_cursor } = to_response::<ThreadListResponse>(resp)?;
+    assert_eq!(data.len(), 1);
+    assert_eq!(next_cursor, None);
+    let thread = &data[0];
+    assert_eq!(thread.preview, "X");
+    assert_eq!(thread.model_provider, "other_provider");
+    let expected_ts = chrono::DateTime::parse_from_rfc3339("2025-01-02T11:00:00Z")?.timestamp();
+    assert_eq!(thread.created_at, expected_ts);
+
+    Ok(())
+}

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

@@ -0,0 +1,79 @@
+use anyhow::Result;
+use app_test_support::McpProcess;
+use app_test_support::create_mock_chat_completions_server;
+use app_test_support::to_response;
+use codex_app_server_protocol::JSONRPCResponse;
+use codex_app_server_protocol::RequestId;
+use codex_app_server_protocol::ThreadResumeParams;
+use codex_app_server_protocol::ThreadResumeResponse;
+use codex_app_server_protocol::ThreadStartParams;
+use codex_app_server_protocol::ThreadStartResponse;
+use tempfile::TempDir;
+use tokio::time::timeout;
+
+const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
+
+#[tokio::test]
+async fn thread_resume_returns_existing_thread() -> Result<()> {
+    let server = create_mock_chat_completions_server(vec![]).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??;
+
+    // Start a thread.
+    let start_id = mcp
+        .send_thread_start_request(ThreadStartParams {
+            model: Some("gpt-5-codex".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)?;
+
+    // Resume it via v2 API.
+    let resume_id = mcp
+        .send_thread_resume_request(ThreadResumeParams {
+            thread_id: thread.id.clone(),
+        })
+        .await?;
+    let resume_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(resume_id)),
+    )
+    .await??;
+    let ThreadResumeResponse { thread: resumed } =
+        to_response::<ThreadResumeResponse>(resume_resp)?;
+    assert_eq!(resumed, thread);
+
+    Ok(())
+}
+
+// Helper to create a config.toml pointing at the mock model server.
+fn create_config_toml(codex_home: &std::path::Path, server_uri: &str) -> std::io::Result<()> {
+    let config_toml = codex_home.join("config.toml");
+    std::fs::write(
+        config_toml,
+        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 = "chat"
+request_max_retries = 0
+stream_max_retries = 0
+"#
+        ),
+    )
+}

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

@@ -0,0 +1,90 @@
+use anyhow::Result;
+use app_test_support::McpProcess;
+use app_test_support::create_mock_chat_completions_server;
+use app_test_support::to_response;
+use codex_app_server_protocol::JSONRPCNotification;
+use codex_app_server_protocol::JSONRPCResponse;
+use codex_app_server_protocol::RequestId;
+use codex_app_server_protocol::ThreadStartParams;
+use codex_app_server_protocol::ThreadStartResponse;
+use codex_app_server_protocol::ThreadStartedNotification;
+use std::path::Path;
+use tempfile::TempDir;
+use tokio::time::timeout;
+
+const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
+
+#[tokio::test]
+async fn thread_start_creates_thread_and_emits_started() -> Result<()> {
+    // Provide a mock server and config so model wiring is valid.
+    let server = create_mock_chat_completions_server(vec![]).await;
+
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path(), &server.uri())?;
+
+    // Start server and initialize.
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    // Start a v2 thread with an explicit model override.
+    let req_id = mcp
+        .send_thread_start_request(ThreadStartParams {
+            model: Some("gpt-5".to_string()),
+            ..Default::default()
+        })
+        .await?;
+
+    // Expect a proper JSON-RPC response with a thread id.
+    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!(!thread.id.is_empty(), "thread id should not be empty");
+    assert!(
+        thread.preview.is_empty(),
+        "new threads should start with an empty preview"
+    );
+    assert_eq!(thread.model_provider, "mock_provider");
+    assert!(
+        thread.created_at > 0,
+        "created_at should be a positive UNIX timestamp"
+    );
+
+    // A corresponding thread/started notification should arrive.
+    let notif: JSONRPCNotification = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("thread/started"),
+    )
+    .await??;
+    let started: ThreadStartedNotification =
+        serde_json::from_value(notif.params.expect("params must be present"))?;
+    assert_eq!(started.thread, thread);
+
+    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");
+    std::fs::write(
+        config_toml,
+        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 = "chat"
+request_max_retries = 0
+stream_max_retries = 0
+"#
+        ),
+    )
+}

llmx-rs/app-server/tests/suite/v2/turn_interrupt.rs

@@ -0,0 +1,128 @@
+#![cfg(unix)]
+
+use anyhow::Result;
+use app_test_support::McpProcess;
+use app_test_support::create_mock_chat_completions_server;
+use app_test_support::create_shell_sse_response;
+use app_test_support::to_response;
+use codex_app_server_protocol::JSONRPCResponse;
+use codex_app_server_protocol::RequestId;
+use codex_app_server_protocol::ThreadStartParams;
+use codex_app_server_protocol::ThreadStartResponse;
+use codex_app_server_protocol::TurnInterruptParams;
+use codex_app_server_protocol::TurnInterruptResponse;
+use codex_app_server_protocol::TurnStartParams;
+use codex_app_server_protocol::TurnStartResponse;
+use codex_app_server_protocol::UserInput as V2UserInput;
+use tempfile::TempDir;
+use tokio::time::timeout;
+
+const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
+
+#[tokio::test]
+async fn turn_interrupt_aborts_running_turn() -> Result<()> {
+    // Use a portable sleep command to keep the turn running.
+    #[cfg(target_os = "windows")]
+    let shell_command = vec![
+        "powershell".to_string(),
+        "-Command".to_string(),
+        "Start-Sleep -Seconds 10".to_string(),
+    ];
+    #[cfg(not(target_os = "windows"))]
+    let shell_command = vec!["sleep".to_string(), "10".to_string()];
+
+    let tmp = TempDir::new()?;
+    let codex_home = tmp.path().join("codex_home");
+    std::fs::create_dir(&codex_home)?;
+    let working_directory = tmp.path().join("workdir");
+    std::fs::create_dir(&working_directory)?;
+
+    // Mock server: long-running shell command then (after abort) nothing else needed.
+    let server = create_mock_chat_completions_server(vec![create_shell_sse_response(
+        shell_command.clone(),
+        Some(&working_directory),
+        Some(10_000),
+        "call_sleep",
+    )?])
+    .await;
+    create_config_toml(&codex_home, &server.uri())?;
+
+    let mut mcp = McpProcess::new(&codex_home).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    // Start a v2 thread and capture its id.
+    let thread_req = mcp
+        .send_thread_start_request(ThreadStartParams {
+            model: Some("mock-model".to_string()),
+            ..Default::default()
+        })
+        .await?;
+    let thread_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(thread_req)),
+    )
+    .await??;
+    let ThreadStartResponse { thread } = to_response::<ThreadStartResponse>(thread_resp)?;
+
+    // Start a turn that triggers a long-running command.
+    let turn_req = mcp
+        .send_turn_start_request(TurnStartParams {
+            thread_id: thread.id.clone(),
+            input: vec![V2UserInput::Text {
+                text: "run sleep".to_string(),
+            }],
+            cwd: Some(working_directory.clone()),
+            ..Default::default()
+        })
+        .await?;
+    let turn_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(turn_req)),
+    )
+    .await??;
+    let TurnStartResponse { turn } = to_response::<TurnStartResponse>(turn_resp)?;
+
+    // Give the command a brief moment to start.
+    tokio::time::sleep(std::time::Duration::from_secs(1)).await;
+
+    // Interrupt the in-progress turn by id (v2 API).
+    let interrupt_id = mcp
+        .send_turn_interrupt_request(TurnInterruptParams {
+            thread_id: thread.id,
+            turn_id: turn.id,
+        })
+        .await?;
+    let interrupt_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(interrupt_id)),
+    )
+    .await??;
+    let _resp: TurnInterruptResponse = to_response::<TurnInterruptResponse>(interrupt_resp)?;
+
+    // No fields to assert on; successful deserialization confirms proper response shape.
+    Ok(())
+}
+
+// Helper to create a config.toml pointing at the mock model server.
+fn create_config_toml(codex_home: &std::path::Path, server_uri: &str) -> std::io::Result<()> {
+    let config_toml = codex_home.join("config.toml");
+    std::fs::write(
+        config_toml,
+        format!(
+            r#"
+model = "mock-model"
+approval_policy = "never"
+sandbox_mode = "workspace-write"
+
+model_provider = "mock_provider"
+
+[model_providers.mock_provider]
+name = "Mock provider for test"
+base_url = "{server_uri}/v1"
+wire_api = "chat"
+request_max_retries = 0
+stream_max_retries = 0
+"#
+        ),
+    )
+}

llmx-rs/app-server/tests/suite/v2/turn_start.rs

@@ -0,0 +1,486 @@
+use anyhow::Result;
+use app_test_support::McpProcess;
+use app_test_support::create_final_assistant_message_sse_response;
+use app_test_support::create_mock_chat_completions_server;
+use app_test_support::create_mock_chat_completions_server_unchecked;
+use app_test_support::create_shell_sse_response;
+use app_test_support::to_response;
+use codex_app_server_protocol::JSONRPCNotification;
+use codex_app_server_protocol::JSONRPCResponse;
+use codex_app_server_protocol::RequestId;
+use codex_app_server_protocol::ServerRequest;
+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::TurnStartedNotification;
+use codex_app_server_protocol::UserInput as V2UserInput;
+use codex_core::protocol_config_types::ReasoningEffort;
+use codex_core::protocol_config_types::ReasoningSummary;
+use codex_protocol::parse_command::ParsedCommand;
+use codex_protocol::protocol::Event;
+use codex_protocol::protocol::EventMsg;
+use core_test_support::skip_if_no_network;
+use pretty_assertions::assert_eq;
+use std::path::Path;
+use tempfile::TempDir;
+use tokio::time::timeout;
+
+const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
+
+#[tokio::test]
+async fn turn_start_emits_notifications_and_accepts_model_override() -> Result<()> {
+    // Provide a mock server and config so model wiring is valid.
+    // Three Codex turns hit the mock model (session start + two turn/start calls).
+    let responses = vec![
+        create_final_assistant_message_sse_response("Done")?,
+        create_final_assistant_message_sse_response("Done")?,
+        create_final_assistant_message_sse_response("Done")?,
+    ];
+    let server = create_mock_chat_completions_server_unchecked(responses).await;
+
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path(), &server.uri(), "never")?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    // Start a thread (v2) and capture its id.
+    let thread_req = mcp
+        .send_thread_start_request(ThreadStartParams {
+            model: Some("mock-model".to_string()),
+            ..Default::default()
+        })
+        .await?;
+    let thread_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(thread_req)),
+    )
+    .await??;
+    let ThreadStartResponse { thread } = to_response::<ThreadStartResponse>(thread_resp)?;
+
+    // Start a turn with only input and thread_id set (no overrides).
+    let turn_req = mcp
+        .send_turn_start_request(TurnStartParams {
+            thread_id: thread.id.clone(),
+            input: vec![V2UserInput::Text {
+                text: "Hello".to_string(),
+            }],
+            ..Default::default()
+        })
+        .await?;
+    let turn_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(turn_req)),
+    )
+    .await??;
+    let TurnStartResponse { turn } = to_response::<TurnStartResponse>(turn_resp)?;
+    assert!(!turn.id.is_empty());
+
+    // Expect a turn/started notification.
+    let notif: JSONRPCNotification = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("turn/started"),
+    )
+    .await??;
+    let started: TurnStartedNotification =
+        serde_json::from_value(notif.params.expect("params must be present"))?;
+    assert_eq!(
+        started.turn.status,
+        codex_app_server_protocol::TurnStatus::InProgress
+    );
+
+    // Send a second turn that exercises the overrides path: change the model.
+    let turn_req2 = mcp
+        .send_turn_start_request(TurnStartParams {
+            thread_id: thread.id.clone(),
+            input: vec![V2UserInput::Text {
+                text: "Second".to_string(),
+            }],
+            model: Some("mock-model-override".to_string()),
+            ..Default::default()
+        })
+        .await?;
+    let turn_resp2: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(turn_req2)),
+    )
+    .await??;
+    let TurnStartResponse { turn: turn2 } = to_response::<TurnStartResponse>(turn_resp2)?;
+    assert!(!turn2.id.is_empty());
+    // Ensure the second turn has a different id than the first.
+    assert_ne!(turn.id, turn2.id);
+
+    // Expect a second turn/started notification as well.
+    let _notif2: JSONRPCNotification = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("turn/started"),
+    )
+    .await??;
+
+    // And we should ultimately get a task_complete without having to add a
+    // legacy conversation listener explicitly (auto-attached by thread/start).
+    let _task_complete: JSONRPCNotification = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("codex/event/task_complete"),
+    )
+    .await??;
+
+    Ok(())
+}
+
+#[tokio::test]
+async fn turn_start_accepts_local_image_input() -> Result<()> {
+    // Two Codex turns hit the mock model (session start + turn/start).
+    let responses = vec![
+        create_final_assistant_message_sse_response("Done")?,
+        create_final_assistant_message_sse_response("Done")?,
+    ];
+    // Use the unchecked variant because the request payload includes a LocalImage
+    // which the strict matcher does not currently cover.
+    let server = create_mock_chat_completions_server_unchecked(responses).await;
+
+    let codex_home = TempDir::new()?;
+    create_config_toml(codex_home.path(), &server.uri(), "never")?;
+
+    let mut mcp = McpProcess::new(codex_home.path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    let thread_req = mcp
+        .send_thread_start_request(ThreadStartParams {
+            model: Some("mock-model".to_string()),
+            ..Default::default()
+        })
+        .await?;
+    let thread_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(thread_req)),
+    )
+    .await??;
+    let ThreadStartResponse { thread } = to_response::<ThreadStartResponse>(thread_resp)?;
+
+    let image_path = codex_home.path().join("image.png");
+    // No need to actually write the file; we just exercise the input path.
+
+    let turn_req = mcp
+        .send_turn_start_request(TurnStartParams {
+            thread_id: thread.id.clone(),
+            input: vec![V2UserInput::LocalImage { path: image_path }],
+            ..Default::default()
+        })
+        .await?;
+    let turn_resp: JSONRPCResponse = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(turn_req)),
+    )
+    .await??;
+    let TurnStartResponse { turn } = to_response::<TurnStartResponse>(turn_resp)?;
+    assert!(!turn.id.is_empty());
+
+    // This test only validates that turn/start responds and returns a turn.
+    Ok(())
+}
+
+#[tokio::test]
+async fn turn_start_exec_approval_toggle_v2() -> Result<()> {
+    skip_if_no_network!(Ok(()));
+
+    let tmp = TempDir::new()?;
+    let codex_home = tmp.path().to_path_buf();
+
+    // Mock server: first turn requests a shell call (elicitation), then completes.
+    // Second turn same, but we'll set approval_policy=never to avoid elicitation.
+    let responses = vec![
+        create_shell_sse_response(
+            vec![
+                "python3".to_string(),
+                "-c".to_string(),
+                "print(42)".to_string(),
+            ],
+            None,
+            Some(5000),
+            "call1",
+        )?,
+        create_final_assistant_message_sse_response("done 1")?,
+        create_shell_sse_response(
+            vec![
+                "python3".to_string(),
+                "-c".to_string(),
+                "print(42)".to_string(),
+            ],
+            None,
+            Some(5000),
+            "call2",
+        )?,
+        create_final_assistant_message_sse_response("done 2")?,
+    ];
+    let server = create_mock_chat_completions_server(responses).await;
+    // Default approval is untrusted to force elicitation on first turn.
+    create_config_toml(codex_home.as_path(), &server.uri(), "untrusted")?;
+
+    let mut mcp = McpProcess::new(codex_home.as_path()).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    // thread/start
+    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)?;
+
+    // turn/start — expect ExecCommandApproval request from server
+    let first_turn_id = mcp
+        .send_turn_start_request(TurnStartParams {
+            thread_id: thread.id.clone(),
+            input: vec![V2UserInput::Text {
+                text: "run python".to_string(),
+            }],
+            ..Default::default()
+        })
+        .await?;
+    // Acknowledge RPC
+    timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(first_turn_id)),
+    )
+    .await??;
+
+    // Receive elicitation
+    let server_req = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_request_message(),
+    )
+    .await??;
+    let ServerRequest::ExecCommandApproval { request_id, params } = server_req else {
+        panic!("expected ExecCommandApproval request");
+    };
+    assert_eq!(params.call_id, "call1");
+    assert_eq!(
+        params.parsed_cmd,
+        vec![ParsedCommand::Unknown {
+            cmd: "python3 -c 'print(42)'".to_string()
+        }]
+    );
+
+    // Approve and wait for task completion
+    mcp.send_response(
+        request_id,
+        serde_json::json!({ "decision": codex_core::protocol::ReviewDecision::Approved }),
+    )
+    .await?;
+    timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("codex/event/task_complete"),
+    )
+    .await??;
+
+    // Second turn with approval_policy=never should not elicit approval
+    let second_turn_id = mcp
+        .send_turn_start_request(TurnStartParams {
+            thread_id: thread.id.clone(),
+            input: vec![V2UserInput::Text {
+                text: "run python again".to_string(),
+            }],
+            approval_policy: Some(codex_app_server_protocol::AskForApproval::Never),
+            sandbox_policy: Some(codex_app_server_protocol::SandboxPolicy::DangerFullAccess),
+            model: Some("mock-model".to_string()),
+            effort: Some(ReasoningEffort::Medium),
+            summary: Some(ReasoningSummary::Auto),
+            ..Default::default()
+        })
+        .await?;
+    timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(second_turn_id)),
+    )
+    .await??;
+
+    // Ensure we do NOT receive an ExecCommandApproval request before task completes
+    timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("codex/event/task_complete"),
+    )
+    .await??;
+
+    Ok(())
+}
+
+#[tokio::test]
+async fn turn_start_updates_sandbox_and_cwd_between_turns_v2() -> Result<()> {
+    // When returning Result from a test, pass an Ok(()) to the skip macro
+    // so the early return type matches. The no-arg form returns unit.
+    skip_if_no_network!(Ok(()));
+
+    let tmp = TempDir::new()?;
+    let codex_home = tmp.path().join("codex_home");
+    std::fs::create_dir(&codex_home)?;
+    let workspace_root = tmp.path().join("workspace");
+    std::fs::create_dir(&workspace_root)?;
+    let first_cwd = workspace_root.join("turn1");
+    let second_cwd = workspace_root.join("turn2");
+    std::fs::create_dir(&first_cwd)?;
+    std::fs::create_dir(&second_cwd)?;
+
+    let responses = vec![
+        create_shell_sse_response(
+            vec![
+                "bash".to_string(),
+                "-lc".to_string(),
+                "echo first turn".to_string(),
+            ],
+            None,
+            Some(5000),
+            "call-first",
+        )?,
+        create_final_assistant_message_sse_response("done first")?,
+        create_shell_sse_response(
+            vec![
+                "bash".to_string(),
+                "-lc".to_string(),
+                "echo second turn".to_string(),
+            ],
+            None,
+            Some(5000),
+            "call-second",
+        )?,
+        create_final_assistant_message_sse_response("done second")?,
+    ];
+    let server = create_mock_chat_completions_server(responses).await;
+    create_config_toml(&codex_home, &server.uri(), "untrusted")?;
+
+    let mut mcp = McpProcess::new(&codex_home).await?;
+    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
+
+    // thread/start
+    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)?;
+
+    // first turn with workspace-write sandbox and first_cwd
+    let first_turn = mcp
+        .send_turn_start_request(TurnStartParams {
+            thread_id: thread.id.clone(),
+            input: vec![V2UserInput::Text {
+                text: "first turn".to_string(),
+            }],
+            cwd: Some(first_cwd.clone()),
+            approval_policy: Some(codex_app_server_protocol::AskForApproval::Never),
+            sandbox_policy: Some(codex_app_server_protocol::SandboxPolicy::WorkspaceWrite {
+                writable_roots: vec![first_cwd.clone()],
+                network_access: false,
+                exclude_tmpdir_env_var: false,
+                exclude_slash_tmp: false,
+            }),
+            model: Some("mock-model".to_string()),
+            effort: Some(ReasoningEffort::Medium),
+            summary: Some(ReasoningSummary::Auto),
+        })
+        .await?;
+    timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(first_turn)),
+    )
+    .await??;
+    timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("codex/event/task_complete"),
+    )
+    .await??;
+
+    // second turn with workspace-write and second_cwd, ensure exec begins in second_cwd
+    let second_turn = mcp
+        .send_turn_start_request(TurnStartParams {
+            thread_id: thread.id.clone(),
+            input: vec![V2UserInput::Text {
+                text: "second turn".to_string(),
+            }],
+            cwd: Some(second_cwd.clone()),
+            approval_policy: Some(codex_app_server_protocol::AskForApproval::Never),
+            sandbox_policy: Some(codex_app_server_protocol::SandboxPolicy::DangerFullAccess),
+            model: Some("mock-model".to_string()),
+            effort: Some(ReasoningEffort::Medium),
+            summary: Some(ReasoningSummary::Auto),
+        })
+        .await?;
+    timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_response_message(RequestId::Integer(second_turn)),
+    )
+    .await??;
+
+    let exec_begin_notification = timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("codex/event/exec_command_begin"),
+    )
+    .await??;
+    let params = exec_begin_notification
+        .params
+        .clone()
+        .expect("exec_command_begin params");
+    let event: Event = serde_json::from_value(params).expect("deserialize exec begin event");
+    let exec_begin = match event.msg {
+        EventMsg::ExecCommandBegin(exec_begin) => exec_begin,
+        other => panic!("expected ExecCommandBegin event, got {other:?}"),
+    };
+    assert_eq!(exec_begin.cwd, second_cwd);
+    assert_eq!(
+        exec_begin.command,
+        vec![
+            "bash".to_string(),
+            "-lc".to_string(),
+            "echo second turn".to_string()
+        ]
+    );
+
+    timeout(
+        DEFAULT_READ_TIMEOUT,
+        mcp.read_stream_until_notification_message("codex/event/task_complete"),
+    )
+    .await??;
+
+    Ok(())
+}
+
+// Helper to create a config.toml pointing at the mock model server.
+fn create_config_toml(
+    codex_home: &Path,
+    server_uri: &str,
+    approval_policy: &str,
+) -> std::io::Result<()> {
+    let config_toml = codex_home.join("config.toml");
+    std::fs::write(
+        config_toml,
+        format!(
+            r#"
+model = "mock-model"
+approval_policy = "{approval_policy}"
+sandbox_mode = "read-only"
+
+model_provider = "mock_provider"
+
+[model_providers.mock_provider]
+name = "Mock provider for test"
+base_url = "{server_uri}/v1"
+wire_api = "chat"
+request_max_retries = 0
+stream_max_retries = 0
+"#
+        ),
+    )
+}