"""host_deploy.sh 的仿真测试：假 systemctl / 假 curl，不碰真实主机。 每个用例都在临时目录里建一个假 APP_DIR，host_deploy.sh 的 CODEX_DEPLOY_* 环境变量把它指过去。生产默认值不受影响。 """ import hashlib import json import os import subprocess import tarfile import tempfile import unittest from pathlib import Path REPO_ROOT = os.path.dirname(os.path.dirname(os.path.dirname( os.path.abspath(__file__)))) HOST_SCRIPT = os.path.join(REPO_ROOT, "deploy", "host_deploy.sh") def make_tarball(source_dir, tarball): with tarfile.open(tarball, "w:gz", format=tarfile.PAX_FORMAT) as tf: for root, dirs, files in os.walk(source_dir): dirs.sort() for name in sorted(files): full = os.path.join(root, name) tf.add(full, arcname=os.path.relpath(full, source_dir)) with open(tarball, "rb") as f: return hashlib.sha256(f.read()).hexdigest() class HostDeploySim(unittest.TestCase): def setUp(self): self.tmp = tempfile.TemporaryDirectory() base = self.tmp.name self.app = os.path.join(base, "codex-app-server") os.makedirs(os.path.join(self.app, "work")) with open(os.path.join(self.app, "DEPLOYED_COMMIT"), "w") as f: f.write("oldcommit\n") with open(os.path.join(self.app, "work", "keep.txt"), "w") as f: f.write("keep\n") with open(os.path.join(self.app, "old.py"), "w") as f: f.write("x = 0\n") # 假 systemctl：is-active 一律失败（走 cloud-worker 分支），其余成功； # cat codex-cloud-server-2 按 FAKE_SERVER2_PRESENT 决定 unit 是否存在。 fake_bin = os.path.join(base, "fakebin") os.makedirs(fake_bin) with open(os.path.join(fake_bin, "systemctl"), "w") as f: f.write("#!/bin/sh\n" "echo \"$@\" >> \"$FAKE_SYSTEMCTL_LOG\"\n" "if [ \"$1\" = \"cat\" ] && [ \"$2\" = \"codex-cloud-server-2\" ]; then\n" " if [ \"$FAKE_SERVER2_PRESENT\" = \"0\" ]; then exit 1; fi\n" " exit 0\n" "fi\n" "if [ \"$1\" = \"is-active\" ]; then exit 1; fi\n" "exit 0\n") with open(os.path.join(fake_bin, "curl"), "w") as f: f.write("#!/bin/sh\ncat \"$FAKE_HEALTH_JSON\"\n") os.chmod(os.path.join(fake_bin, "systemctl"), 0o755) os.chmod(os.path.join(fake_bin, "curl"), 0o755) self.fake_bin = fake_bin self.health_path = os.path.join(base, "health.json") self.log_path = os.path.join(base, "systemctl.log") Path(self.log_path).write_text("", encoding="utf-8") self.env = dict(os.environ) self.env["PATH"] = fake_bin + os.pathsep + os.environ["PATH"] self.env["CODEX_DEPLOY_APP_DIR"] = self.app self.env["CODEX_DEPLOY_BACKUP_DIR"] = os.path.join(base, "backups") self.env["CODEX_DEPLOY_STAGING_DIR"] = os.path.join(base, "staging") self.env["CODEX_DEPLOY_OLD_DIR"] = os.path.join(base, "old") self.env["CODEX_DEPLOY_FAILED_DIR"] = os.path.join(base, "failed") self.env["CODEX_DEPLOY_PRESERVE_DIR"] = os.path.join(base, "preserve") self.env["CODEX_DEPLOY_HEALTH_INTERVAL"] = "0.1" self.env["CODEX_DEPLOY_HEALTH_ATTEMPTS"] = "3" self.env["FAKE_HEALTH_JSON"] = self.health_path self.env["FAKE_SYSTEMCTL_LOG"] = self.log_path self.env["FAKE_SERVER2_PRESENT"] = "1" def tearDown(self): self.tmp.cleanup() def set_health(self, payload): with open(self.health_path, "w") as f: json.dump(payload, f) def build_new_tarball(self, commit="newcommit"): src = os.path.join(self.tmp.name, "src") os.makedirs(src, exist_ok=True) with open(os.path.join(src, "DEPLOYED_COMMIT"), "w") as f: f.write(commit + "\n") with open(os.path.join(src, "new.py"), "w") as f: f.write("x = 1\n") tarball = os.path.join(self.tmp.name, "release.tar.gz") sha = make_tarball(src, tarball) return tarball, sha def run_host(self, tarball, sha, commit, extra_env=None): env = dict(self.env) if extra_env: env.update(extra_env) return subprocess.run( ["sh", HOST_SCRIPT, tarball, sha, commit], capture_output=True, text=True, env=env) def systemctl_log(self): with open(self.log_path) as f: return f.read() def live_commit(self): with open(os.path.join(self.app, "DEPLOYED_COMMIT")) as f: return f.read().strip() def test_success_swaps_and_preserves_work(self): self.set_health({"ok": True, "backend": "postgres", "db_ok": True, "commit": "newcommit"}) tarball, sha = self.build_new_tarball() r = self.run_host(tarball, sha, "newcommit") self.assertEqual(r.returncode, 0, r.stdout + r.stderr) self.assertIn("RELEASE_OK", r.stdout) self.assertIn("commit=newcommit", r.stdout) self.assertEqual(self.live_commit(), "newcommit") with open(os.path.join(self.app, "work", "keep.txt")) as f: self.assertEqual(f.read().strip(), "keep") self.assertTrue(os.path.exists(os.path.join(self.app, "new.py"))) self.assertFalse(os.path.exists(os.path.join(self.app, "old.py"))) backups = os.listdir(self.env["CODEX_DEPLOY_BACKUP_DIR"]) self.assertEqual(len(backups), 1) self.assertIn("oldcommit", backups[0]) def test_bad_sha_never_touches_live(self): self.set_health({"ok": True, "backend": "postgres", "db_ok": True, "commit": "newcommit"}) tarball, _sha = self.build_new_tarball() r = self.run_host(tarball, "0" * 64, "newcommit") self.assertNotEqual(r.returncode, 0) self.assertEqual(self.live_commit(), "oldcommit") self.assertFalse(os.path.exists(self.env["CODEX_DEPLOY_BACKUP_DIR"]) and os.listdir(self.env["CODEX_DEPLOY_BACKUP_DIR"])) def test_manifest_mismatch_never_touches_live(self): self.set_health({"ok": True, "backend": "postgres", "db_ok": True, "commit": "newcommit"}) tarball, sha = self.build_new_tarball(commit="othercommit") r = self.run_host(tarball, sha, "newcommit") self.assertNotEqual(r.returncode, 0) self.assertEqual(self.live_commit(), "oldcommit") def test_health_failure_rolls_back(self): # health 通过但 commit 是旧的：这是旧链路会误报成功的情况， # 新链路必须回滚，live 回到 oldcommit。 self.set_health({"ok": True, "backend": "postgres", "db_ok": True, "commit": "oldcommit"}) tarball, sha = self.build_new_tarball() r = self.run_host(tarball, sha, "newcommit") self.assertNotEqual(r.returncode, 0) self.assertEqual(self.live_commit(), "oldcommit") with open(os.path.join(self.app, "work", "keep.txt")) as f: self.assertEqual(f.read().strip(), "keep") def test_server2_stopped_started_when_present(self): # 2026-10-27 首推教训：server-2 存在时必须同批停/起， # 否则 LB 混跑新旧内存代码。 self.set_health({"ok": True, "backend": "postgres", "db_ok": True, "commit": "newcommit"}) tarball, sha = self.build_new_tarball() r = self.run_host(tarball, sha, "newcommit") self.assertEqual(r.returncode, 0, r.stdout + r.stderr) log = self.systemctl_log() self.assertIn( "stop codex-cloud-worker codex-cloud-server codex-cloud-server-2", log) self.assertIn( "start codex-cloud-server codex-cloud-server-2 codex-cloud-worker", log) def test_server2_skipped_when_unit_absent(self): # 老主机没有 server-2 unit 时退回单机行为，不报错、不提它。 self.set_health({"ok": True, "backend": "postgres", "db_ok": True, "commit": "newcommit"}) tarball, sha = self.build_new_tarball() r = self.run_host(tarball, sha, "newcommit", extra_env={"FAKE_SERVER2_PRESENT": "0"}) self.assertEqual(r.returncode, 0, r.stdout + r.stderr) # 探测行 cat 本身会提到 server-2（探测失败才判定不存在）， # 所以断言停/起行里没有它，而不是全日志没有这个词。 log = self.systemctl_log() self.assertIn("stop codex-cloud-worker codex-cloud-server\n", log) self.assertIn("start codex-cloud-server codex-cloud-worker\n", log) if __name__ == "__main__": unittest.main()