fix: preserve symlinks during atomic file writes (#16743)

agent/google_oauth.py

@@ -98,6 +98,7 @@
 
 # Regex patterns for fallback scraping from an installed gemini-cli.
 import re as _re
+from utils import atomic_replace
 _CLIENT_ID_PATTERN = _re.compile(
     r"OAUTH_CLIENT_ID\s*=\s*['\"]([0-9]+-[a-z0-9]+\.apps\.googleusercontent\.com)['\"]"
 )
@@ -499,7 +500,7 @@ def save_credentials(creds: GoogleCredentials) -> Path:
                 fh.flush()
                 os.fsync(fh.fileno())
             os.chmod(tmp_path, stat.S_IRUSR | stat.S_IWUSR)
-            os.replace(tmp_path, path)
+            atomic_replace(tmp_path, path)
         finally:
             try:
                 if tmp_path.exists():

agent/nous_rate_guard.py

@@ -18,6 +18,7 @@
 import tempfile
 import time
 from typing import Any, Mapping, Optional
+from utils import atomic_replace
 
 logger = logging.getLogger(__name__)
 
@@ -118,7 +119,7 @@ def record_nous_rate_limit(
         try:
             with os.fdopen(fd, "w") as f:
                 json.dump(state, f)
-            os.replace(tmp_path, path)
+            atomic_replace(tmp_path, path)
         except Exception:
             # Clean up temp file on failure
             try:

agent/shell_hooks.py

@@ -76,6 +76,7 @@
     fcntl = None  # type: ignore[assignment]
 
 from hermes_constants import get_hermes_home
+from utils import atomic_replace
 
 logger = logging.getLogger(__name__)
 
@@ -568,7 +569,7 @@ def save_allowlist(data: Dict[str, Any]) -> None:
         try:
             with os.fdopen(fd, "w") as fh:
                 fh.write(json.dumps(data, indent=2, sort_keys=True))
-            os.replace(tmp_path, p)
+            atomic_replace(tmp_path, p)
         except Exception:
             try:
                 os.unlink(tmp_path)

cron/jobs.py

@@ -21,6 +21,7 @@
 logger = logging.getLogger(__name__)
 
 from hermes_time import now as _hermes_now
+from utils import atomic_replace
 
 try:
     from croniter import croniter
@@ -367,7 +368,7 @@ def save_jobs(jobs: List[Dict[str, Any]]):
             json.dump({"jobs": jobs, "updated_at": _hermes_now().isoformat()}, f, indent=2)
             f.flush()
             os.fsync(f.fileno())
-        os.replace(tmp_path, JOBS_FILE)
+        atomic_replace(tmp_path, JOBS_FILE)
         _secure_file(JOBS_FILE)
     except BaseException:
         try:
@@ -863,7 +864,7 @@ def save_job_output(job_id: str, output: str):
             f.write(output)
             f.flush()
             os.fsync(f.fileno())
-        os.replace(tmp_path, output_file)
+        atomic_replace(tmp_path, output_file)
         _secure_file(output_file)
     except BaseException:
         try:

gateway/pairing.py

@@ -28,6 +28,7 @@
 from typing import Optional
 
 from hermes_constants import get_hermes_dir
+from utils import atomic_replace
 
 
 # Unambiguous alphabet -- excludes 0/O, 1/I to prevent confusion
@@ -59,7 +60,7 @@ def _secure_write(path: Path, data: str) -> None:
             f.write(data)
             f.flush()
             os.fsync(f.fileno())
-        os.replace(tmp_path, str(path))
+        atomic_replace(tmp_path, path)
         try:
             os.chmod(path, 0o600)
         except OSError:

gateway/platforms/telegram.py

@@ -84,6 +84,7 @@ class _MockContextTypes:
     discover_fallback_ips,
     parse_fallback_ip_env,
 )
+from utils import atomic_replace
 
 
 def check_telegram_requirements() -> bool:
@@ -554,7 +555,7 @@ def _persist_dm_topic_thread_id(self, chat_id: int, topic_name: str, thread_id:
                         _yaml.dump(config, f, default_flow_style=False, sort_keys=False)
                         f.flush()
                         os.fsync(f.fileno())
-                    os.replace(tmp_path, config_path)
+                    atomic_replace(tmp_path, config_path)
                 except BaseException:
                     try:
                         os.unlink(tmp_path)

gateway/session.py

@@ -64,6 +64,7 @@ def _hash_chat_id(value: str) -> str:
     canonical_whatsapp_identifier,
     normalize_whatsapp_identifier,
 )
+from utils import atomic_replace
 
 
 @dataclass
@@ -705,7 +706,7 @@ def _save(self) -> None:
                 json.dump(data, f, indent=2)
                 f.flush()
                 os.fsync(f.fileno())
-            os.replace(tmp_path, sessions_file)
+            atomic_replace(tmp_path, sessions_file)
         except BaseException:
             try:
                 os.unlink(tmp_path)

hermes_cli/auth.py

@@ -43,6 +43,7 @@
 
 from hermes_cli.config import get_hermes_home, get_config_path, read_raw_config
 from hermes_constants import OPENROUTER_BASE_URL
+from utils import atomic_replace
 
 logger = logging.getLogger(__name__)
 
@@ -828,7 +829,7 @@ def _save_auth_store(auth_store: Dict[str, Any]) -> Path:
             handle.write(payload)
             handle.flush()
             os.fsync(handle.fileno())
-        os.replace(tmp_path, auth_file)
+        atomic_replace(tmp_path, auth_file)
         try:
             dir_fd = os.open(str(auth_file.parent), os.O_RDONLY)
         except OSError:

hermes_cli/config.py

@@ -227,6 +227,7 @@ def get_container_exec_info() -> Optional[dict]:
 
 # Re-export from hermes_constants — canonical definition lives there.
 from hermes_constants import get_hermes_home  # noqa: F811,E402
+from utils import atomic_replace
 
 def get_config_path() -> Path:
     """Get the main config file path."""
@@ -3666,7 +3667,7 @@ def sanitize_env_file() -> int:
             f.writelines(sanitized)
             f.flush()
             os.fsync(f.fileno())
-        os.replace(tmp_path, env_path)
+        atomic_replace(tmp_path, env_path)
     except BaseException:
         try:
             os.unlink(tmp_path)
@@ -3769,7 +3770,7 @@ def save_env_value(key: str, value: str):
             f.writelines(lines)
             f.flush()
             os.fsync(f.fileno())
-        os.replace(tmp_path, env_path)
+        atomic_replace(tmp_path, env_path)
         # Restore original permissions before _secure_file may tighten them.
         if original_mode is not None:
             try:
@@ -3825,7 +3826,7 @@ def remove_env_value(key: str) -> bool:
                 f.writelines(new_lines)
                 f.flush()
                 os.fsync(f.fileno())
-            os.replace(tmp_path, env_path)
+            atomic_replace(tmp_path, env_path)
             if original_mode is not None:
                 try:
                     os.chmod(env_path, original_mode)

hermes_cli/debug.py

@@ -18,6 +18,7 @@
 from typing import Optional
 
 from hermes_constants import get_hermes_home
+from utils import atomic_replace
 
 
 # ---------------------------------------------------------------------------
@@ -79,7 +80,7 @@ def _save_pending(entries: list[dict]) -> None:
         path.parent.mkdir(parents=True, exist_ok=True)
         tmp = path.with_suffix(".json.tmp")
         tmp.write_text(json.dumps(entries, indent=2), encoding="utf-8")
-        os.replace(tmp, path)
+        atomic_replace(tmp, path)
     except OSError:
         # Non-fatal — worst case the user has to run ``hermes debug delete``
         # manually.

hermes_cli/env_loader.py

@@ -7,6 +7,7 @@
 from pathlib import Path
 
 from dotenv import load_dotenv
+from utils import atomic_replace
 
 
 # Env var name suffixes that indicate credential values.  These are the
@@ -127,7 +128,7 @@ def _sanitize_env_file_if_needed(path: Path) -> None:
                     f.writelines(sanitized)
                     f.flush()
                     os.fsync(f.fileno())
-                os.replace(tmp, path)
+                atomic_replace(tmp, path)
             except BaseException:
                 try:
                     os.unlink(tmp)

hermes_cli/model_catalog.py

@@ -54,6 +54,7 @@
 from typing import Any
 
 from hermes_cli import __version__ as _HERMES_VERSION
+from utils import atomic_replace
 
 logger = logging.getLogger(__name__)
 
@@ -190,7 +191,7 @@ def _write_disk_cache(data: dict[str, Any]) -> None:
         with open(tmp, "w") as fh:
             json.dump(data, fh, indent=2)
             fh.write("\n")
-        os.replace(tmp, path)
+        atomic_replace(tmp, path)
     except OSError as exc:
         logger.info("model catalog cache write failed: %s", exc)
 

hermes_cli/webhook.py

@@ -19,6 +19,7 @@
 from typing import Dict
 
 from hermes_constants import display_hermes_home
+from utils import atomic_replace
 
 
 _SUBSCRIPTIONS_FILENAME = "webhook_subscriptions.json"
@@ -52,7 +53,7 @@ def _save_subscriptions(subs: Dict[str, dict]) -> None:
         json.dumps(subs, indent=2, ensure_ascii=False),
         encoding="utf-8",
     )
-    os.replace(str(tmp_path), str(path))
+    atomic_replace(tmp_path, path)
 
 
 def _get_webhook_config() -> dict: