refactor: consolidate symlink-safe atomic replace into shared helper

Extract the islink/realpath guard from the 16743 fix into a single
atomic_replace() helper in utils.py, then migrate every os.replace()
call site in the codebase to use it.

The original PR #16777 correctly identified and fixed the bug, but
only patched 9 of ~24 call sites. The same bug class (managed
deployments that symlink state files silently losing the link on
every write) still existed at auth.json, sessions file, gateway
config, env_loader, webhook subscriptions, debug store, model
catalog, pairing, google OAuth, nous rate guard, and more.

Rather than add another 10+ copies of the same three-line guard,
consolidate into atomic_replace(tmp, target) which:
- resolves symlinks via os.path.realpath before os.replace
- returns the resolved real path so callers can re-apply permissions
- is a drop-in replacement for os.replace at the use sites

Changes:
- utils.py: new atomic_replace() helper + atomic_json_write /
  atomic_yaml_write now call it instead of inlining the guard
- 16 files: all os.replace() call sites migrated to atomic_replace()
  - agent/{google_oauth, nous_rate_guard, shell_hooks}.py
  - cron/jobs.py
  - gateway/{pairing, session, platforms/telegram}.py
  - hermes_cli/{auth, config, debug, env_loader, model_catalog, webhook}.py
  - tools/{memory_tool, skill_manager_tool, skills_sync}.py

Tests: tests/test_atomic_replace_symlinks.py pins the invariant for
atomic_replace + atomic_json_write + atomic_yaml_write, covers plain
files, first-time creates, broken symlinks, and permission preservation.

Refs #16743
Builds on #16777 by @vominh1919.

hermes_cli/auth.py

@@ -43,6 +43,7 @@ import yaml
 
 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."""
@@ -3666,9 +3667,7 @@ def sanitize_env_file() -> int:
             f.writelines(sanitized)
             f.flush()
             os.fsync(f.fileno())
-        # Resolve symlinks so os.replace writes to the real file (GitHub #16743).
-        real_path = os.path.realpath(env_path) if os.path.islink(env_path) else env_path
-        os.replace(tmp_path, real_path)
+        atomic_replace(tmp_path, env_path)
     except BaseException:
         try:
             os.unlink(tmp_path)
@@ -3771,9 +3770,7 @@ def save_env_value(key: str, value: str):
             f.writelines(lines)
             f.flush()
             os.fsync(f.fileno())
-        # Resolve symlinks so os.replace writes to the real file (GitHub #16743).
-        real_path = os.path.realpath(env_path) if os.path.islink(env_path) else env_path
-        os.replace(tmp_path, real_path)
+        atomic_replace(tmp_path, env_path)
         # Restore original permissions before _secure_file may tighten them.
         if original_mode is not None:
             try:
@@ -3829,9 +3826,7 @@ def remove_env_value(key: str) -> bool:
                 f.writelines(new_lines)
                 f.flush()
                 os.fsync(f.fileno())
-            # Resolve symlinks so os.replace writes to the real file (GitHub #16743).
-            real_path = os.path.realpath(env_path) if os.path.islink(env_path) else env_path
-            os.replace(tmp_path, real_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 pathlib import Path
 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 @@ import sys
 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 pathlib import Path
 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 pathlib import Path
 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: