Add notifier tests (#4064)

Proposal:
1. Use anyhow for tests and avoid unwrap
2. Extract a helper for starting a test instance of codex

codex-rs/core/tests/common/Cargo.toml

@@ -1,12 +1,13 @@
 [package]
+edition = "2024"
 name = "core_test_support"
 version = { workspace = true }
-edition = "2024"
 
 [lib]
 path = "lib.rs"
 
 [dependencies]
+anyhow = { workspace = true }
 codex-core = { workspace = true }
 serde_json = { workspace = true }
 tempfile = { workspace = true }

codex-rs/core/tests/common/lib.rs

@@ -8,6 +8,7 @@ use codex_core::config::ConfigOverrides;
 use codex_core::config::ConfigToml;
 
 pub mod responses;
+pub mod test_codex;
 
 /// Returns a default `Config` whose on-disk state is confined to the provided
 /// temporary directory. Using a per-test directory keeps tests hermetic and

codex-rs/core/tests/common/test_codex.rs

@@ -0,0 +1,75 @@
+use std::mem::swap;
+use std::sync::Arc;
+
+use codex_core::CodexAuth;
+use codex_core::CodexConversation;
+use codex_core::ConversationManager;
+use codex_core::ModelProviderInfo;
+use codex_core::NewConversation;
+use codex_core::built_in_model_providers;
+use codex_core::config::Config;
+use codex_core::protocol::SessionConfiguredEvent;
+use tempfile::TempDir;
+
+use crate::load_default_config_for_test;
+
+type ConfigMutator = dyn FnOnce(&mut Config);
+
+pub struct TestCodexBuilder {
+    config_mutators: Vec<Box<ConfigMutator>>,
+}
+
+impl TestCodexBuilder {
+    pub fn with_config<T>(mut self, mutator: T) -> Self
+    where
+        T: FnOnce(&mut Config) + 'static,
+    {
+        self.config_mutators.push(Box::new(mutator));
+        self
+    }
+
+    pub async fn build(&mut self, server: &wiremock::MockServer) -> anyhow::Result<TestCodex> {
+        // Build config pointing to the mock server and spawn Codex.
+        let model_provider = ModelProviderInfo {
+            base_url: Some(format!("{}/v1", server.uri())),
+            ..built_in_model_providers()["openai"].clone()
+        };
+        let home = TempDir::new()?;
+        let cwd = TempDir::new()?;
+        let mut config = load_default_config_for_test(&home);
+        config.cwd = cwd.path().to_path_buf();
+        config.model_provider = model_provider;
+        let mut mutators = vec![];
+        swap(&mut self.config_mutators, &mut mutators);
+
+        for mutator in mutators {
+            mutator(&mut config)
+        }
+        let conversation_manager = ConversationManager::with_auth(CodexAuth::from_api_key("dummy"));
+        let NewConversation {
+            conversation,
+            session_configured,
+            ..
+        } = conversation_manager.new_conversation(config).await?;
+
+        Ok(TestCodex {
+            home,
+            cwd,
+            codex: conversation,
+            session_configured,
+        })
+    }
+}
+
+pub struct TestCodex {
+    pub home: TempDir,
+    pub cwd: TempDir,
+    pub codex: Arc<CodexConversation>,
+    pub session_configured: SessionConfiguredEvent,
+}
+
+pub fn test_codex() -> TestCodexBuilder {
+    TestCodexBuilder {
+        config_mutators: vec![],
+    }
+}

codex-rs/core/tests/suite/mod.rs

@@ -15,3 +15,4 @@ mod rollout_list_find;
 mod seatbelt;
 mod stream_error_allows_next_turn;
 mod stream_no_completed;
+mod user_notification;

codex-rs/core/tests/suite/user_notification.rs

@@ -0,0 +1,73 @@
+#![cfg(not(target_os = "windows"))]
+
+use std::os::unix::fs::PermissionsExt;
+
+use codex_core::protocol::EventMsg;
+use codex_core::protocol::InputItem;
+use codex_core::protocol::Op;
+use core_test_support::non_sandbox_test;
+use core_test_support::responses;
+use core_test_support::test_codex::TestCodex;
+use core_test_support::test_codex::test_codex;
+use core_test_support::wait_for_event;
+use tempfile::TempDir;
+use wiremock::matchers::any;
+
+use responses::ev_assistant_message;
+use responses::ev_completed;
+use responses::sse;
+use responses::start_mock_server;
+use tokio::time::Duration;
+use tokio::time::sleep;
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn summarize_context_three_requests_and_instructions() -> anyhow::Result<()> {
+    non_sandbox_test!(result);
+
+    let server = start_mock_server().await;
+
+    let sse1 = sse(vec![ev_assistant_message("m1", "Done"), ev_completed("r1")]);
+
+    responses::mount_sse_once(&server, any(), sse1).await;
+
+    let notify_dir = TempDir::new()?;
+    // write a script to the notify that touches a file next to it
+    let notify_script = notify_dir.path().join("notify.sh");
+    std::fs::write(
+        &notify_script,
+        r#"#!/bin/bash
+set -e
+echo -n "${@: -1}" > $(dirname "${0}")/notify.txt"#,
+    )?;
+    std::fs::set_permissions(&notify_script, std::fs::Permissions::from_mode(0o755))?;
+
+    let notify_file = notify_dir.path().join("notify.txt");
+    let notify_script_str = notify_script.to_str().unwrap().to_string();
+
+    let TestCodex { codex, .. } = test_codex()
+        .with_config(move |cfg| cfg.notify = Some(vec![notify_script_str]))
+        .build(&server)
+        .await?;
+
+    // 1) Normal user input – should hit server once.
+    codex
+        .submit(Op::UserInput {
+            items: vec![InputItem::Text {
+                text: "hello world".into(),
+            }],
+        })
+        .await?;
+    wait_for_event(&codex, |ev| matches!(ev, EventMsg::TaskComplete(_))).await;
+
+    // We fork the notify script, so we need to wait for it to write to the file.
+    for _ in 0..100u32 {
+        if notify_file.exists() {
+            break;
+        }
+        sleep(Duration::from_millis(100)).await;
+    }
+
+    assert!(notify_file.exists());
+
+    Ok(())
+}