From 2483200963e43e7335e02f3f51440db089bcc1a3 Mon Sep 17 00:00:00 2001
From: Teknium <127238744+teknium1@users.noreply.github.com>
Date: Tue, 16 Jun 2026 05:56:50 -0700
Subject: [PATCH] test(tui): isolate session-create no-race test from
 shard-sibling leakage (#47230)

test_session_create_no_race_keeps_worker_alive flaked on CI shard 3 with
'build thread unregistered its own notify despite no race' while passing
20/20 in isolation locally. Root cause: daemon build threads from sibling
session.create tests in the same shard process mutate the shared
server._sessions dict under _sessions_lock and can replace/pop entries
mid-run, flipping this build thread's 'replaced' check (server.py:1011) to
True and triggering a spurious unregister_gateway_notify.

Fix is test-only: snapshot + clear server._sessions before the request so
the test sees only its own session, restore siblings in finally. Also assert
agent_ready.wait() actually returned True (was silently ignoring timeout) and
bump the timeout 2s -> 10s for loaded CI runners.
---
 tests/test_tui_gateway_server.py | 58 +++++++++++++++++++-------------
 1 file changed, 35 insertions(+), 23 deletions(-)

diff --git a/tests/test_tui_gateway_server.py b/tests/test_tui_gateway_server.py
index 2b37b5788bb..956385dc51e 100644
--- a/tests/test_tui_gateway_server.py
+++ b/tests/test_tui_gateway_server.py
@@ -4901,33 +4901,45 @@ def test_session_create_no_race_keeps_worker_alive(monkeypatch):
     )
     monkeypatch.setattr(_approval, "load_permanent_allowlist", lambda: None)
 
-    resp = server.handle_request(
-        {
-            "id": "1",
-            "method": "session.create",
-            "params": {"cols": 80},
-        }
-    )
-    sid = resp["result"]["session_id"]
+    # Isolate from sibling-test leakage: daemon build threads from prior
+    # session.create tests in the same shard process mutate the shared
+    # ``server._sessions`` dict under ``_sessions_lock`` and can replace/pop
+    # entries mid-run, which would flip this build thread's ``replaced`` check
+    # to True and trigger a spurious unregister. Snapshot, clear, and restore
+    # so this test sees only its own session regardless of shard composition.
+    _saved_sessions = dict(server._sessions)
+    server._sessions.clear()
 
-    # Wait for the build to finish (ready event inside session dict).
-    session = server._sessions[sid]
-    session["agent_ready"].wait(timeout=2.0)
+    try:
+        resp = server.handle_request(
+            {
+                "id": "1",
+                "method": "session.create",
+                "params": {"cols": 80},
+            }
+        )
+        sid = resp["result"]["session_id"]
 
-    # Build finished without a close race — nothing should have been
-    # cleaned up by the orphan check.
-    assert (
-        closed_workers == []
-    ), f"build thread closed its own worker despite no race: {closed_workers}"
-    assert (
-        unregistered_keys == []
-    ), f"build thread unregistered its own notify despite no race: {unregistered_keys}"
+        # Wait for the build to finish (ready event inside session dict).
+        session = server._sessions[sid]
+        built = session["agent_ready"].wait(timeout=10.0)
+        assert built, "agent build did not complete within timeout"
 
-    # Session should have the live worker installed.
-    assert session.get("slash_worker") is not None
+        # Build finished without a close race — nothing should have been
+        # cleaned up by the orphan check.
+        assert (
+            closed_workers == []
+        ), f"build thread closed its own worker despite no race: {closed_workers}"
+        assert (
+            unregistered_keys == []
+        ), f"build thread unregistered its own notify despite no race: {unregistered_keys}"
 
-    # Cleanup
-    server._sessions.pop(sid, None)
+        # Session should have the live worker installed.
+        assert session.get("slash_worker") is not None
+    finally:
+        # Cleanup + restore sibling sessions we snapshotted.
+        server._sessions.clear()
+        server._sessions.update(_saved_sessions)
 
 
 def test_get_db_degrades_cleanly_when_sessiondb_init_fails(monkeypatch):