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

use anyhow::Result;
use app_test_support::McpProcess;
use app_test_support::create_mock_chat_completions_server;
use app_test_support::to_response;
use llmx_app_server_protocol::JSONRPCNotification;
use llmx_app_server_protocol::JSONRPCResponse;
use llmx_app_server_protocol::RequestId;
use llmx_app_server_protocol::ThreadStartParams;
use llmx_app_server_protocol::ThreadStartResponse;
use llmx_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 llmx_home = TempDir::new()?;
    create_config_toml(llmx_home.path(), &server.uri())?;

    // Start server and initialize.
    let mut mcp = McpProcess::new(llmx_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(llmx_home: &Path, server_uri: &str) -> std::io::Result<()> {
    let config_toml = llmx_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
"#
        ),
    )
}