diff --git a/codex-rs/core/tests/all.rs b/codex-rs/core/tests/all.rs
new file mode 100644
index 0000000000..a77ad987ec
--- /dev/null
+++ b/codex-rs/core/tests/all.rs
@@ -0,0 +1,3 @@
+// Single integration test binary that aggregates all test modules.
+// The submodules live in `tests/all/`.
+mod suite;
diff --git a/codex-rs/core/tests/cli_stream.rs b/codex-rs/core/tests/suite/cli_stream.rs
similarity index 100%
rename from codex-rs/core/tests/cli_stream.rs
rename to codex-rs/core/tests/suite/cli_stream.rs
diff --git a/codex-rs/core/tests/client.rs b/codex-rs/core/tests/suite/client.rs
similarity index 100%
rename from codex-rs/core/tests/client.rs
rename to codex-rs/core/tests/suite/client.rs
diff --git a/codex-rs/core/tests/compact.rs b/codex-rs/core/tests/suite/compact.rs
similarity index 100%
rename from codex-rs/core/tests/compact.rs
rename to codex-rs/core/tests/suite/compact.rs
diff --git a/codex-rs/core/tests/exec.rs b/codex-rs/core/tests/suite/exec.rs
similarity index 100%
rename from codex-rs/core/tests/exec.rs
rename to codex-rs/core/tests/suite/exec.rs
diff --git a/codex-rs/core/tests/exec_stream_events.rs b/codex-rs/core/tests/suite/exec_stream_events.rs
similarity index 100%
rename from codex-rs/core/tests/exec_stream_events.rs
rename to codex-rs/core/tests/suite/exec_stream_events.rs
diff --git a/codex-rs/core/tests/live_cli.rs b/codex-rs/core/tests/suite/live_cli.rs
similarity index 100%
rename from codex-rs/core/tests/live_cli.rs
rename to codex-rs/core/tests/suite/live_cli.rs
diff --git a/codex-rs/core/tests/suite/mod.rs b/codex-rs/core/tests/suite/mod.rs
new file mode 100644
index 0000000000..22aa826699
--- /dev/null
+++ b/codex-rs/core/tests/suite/mod.rs
@@ -0,0 +1,12 @@
+// Aggregates all former standalone integration tests as modules.
+
+mod cli_stream;
+mod client;
+mod compact;
+mod exec;
+mod exec_stream_events;
+mod live_cli;
+mod prompt_caching;
+mod seatbelt;
+mod stream_error_allows_next_turn;
+mod stream_no_completed;
diff --git a/codex-rs/core/tests/prompt_caching.rs b/codex-rs/core/tests/suite/prompt_caching.rs
similarity index 98%
rename from codex-rs/core/tests/prompt_caching.rs
rename to codex-rs/core/tests/suite/prompt_caching.rs
index 17965e4915..68605ab44f 100644
--- a/codex-rs/core/tests/prompt_caching.rs
+++ b/codex-rs/core/tests/suite/prompt_caching.rs
@@ -107,8 +107,8 @@ async fn codex_mini_latest_tools() {
     assert_eq!(requests.len(), 2, "expected two POST requests");
 
     let expected_instructions = [
-        include_str!("../prompt.md"),
-        include_str!("../../apply-patch/apply_patch_tool_instructions.md"),
+        include_str!("../../prompt.md"),
+        include_str!("../../../apply-patch/apply_patch_tool_instructions.md"),
     ]
     .join("\n");
 
@@ -188,7 +188,7 @@ async fn prompt_tools_are_consistent_across_requests() {
     let requests = server.received_requests().await.unwrap();
     assert_eq!(requests.len(), 2, "expected two POST requests");
 
-    let expected_instructions: &str = include_str!("../prompt.md");
+    let expected_instructions: &str = include_str!("../../prompt.md");
     // our internal implementation is responsible for keeping tools in sync
     // with the OpenAI schema, so we just verify the tool presence here
     let expected_tools_names: &[&str] = &["shell", "update_plan", "apply_patch"];
diff --git a/codex-rs/core/tests/seatbelt.rs b/codex-rs/core/tests/suite/seatbelt.rs
similarity index 100%
rename from codex-rs/core/tests/seatbelt.rs
rename to codex-rs/core/tests/suite/seatbelt.rs
diff --git a/codex-rs/core/tests/stream_error_allows_next_turn.rs b/codex-rs/core/tests/suite/stream_error_allows_next_turn.rs
similarity index 100%
rename from codex-rs/core/tests/stream_error_allows_next_turn.rs
rename to codex-rs/core/tests/suite/stream_error_allows_next_turn.rs
diff --git a/codex-rs/core/tests/stream_no_completed.rs b/codex-rs/core/tests/suite/stream_no_completed.rs
similarity index 100%
rename from codex-rs/core/tests/stream_no_completed.rs
rename to codex-rs/core/tests/suite/stream_no_completed.rs