From 2c88aa96ee3d3e536ce67bccd45d354e2ea6fe2d Mon Sep 17 00:00:00 2001
From: Alexander Whitestone <alexpaynex@gmail.com>
Date: Sun, 12 Apr 2026 22:29:54 -0400
Subject: [PATCH] fix(cron): Thread-safe save_jobs with file lock

Prevents race condition when parallel tick workers call mark_job_run()
concurrently. Uses fcntl.flock() to serialize jobs.json writes.

Without this fix, 6 parallel workers could read-modify-write jobs.json
simultaneously, causing lost status updates.
---
 cron/jobs.py | 32 ++++++++++++++++++--------------
 1 file changed, 18 insertions(+), 14 deletions(-)

diff --git a/cron/jobs.py b/cron/jobs.py
index 4d5d84ec9..3af8278b4 100644
--- a/cron/jobs.py
+++ b/cron/jobs.py
@@ -347,22 +347,26 @@ def load_jobs() -> List[Dict[str, Any]]:
 
 
 def save_jobs(jobs: List[Dict[str, Any]]):
-    """Save all jobs to storage."""
+    """Save all jobs to storage. Thread-safe via file lock."""
     ensure_dirs()
-    fd, tmp_path = tempfile.mkstemp(dir=str(JOBS_FILE.parent), suffix='.tmp', prefix='.jobs_')
-    try:
-        with os.fdopen(fd, 'w', encoding='utf-8') as f:
-            json.dump({"jobs": jobs, "updated_at": _hermes_now().isoformat()}, f, indent=2)
-            f.flush()
-            os.fsync(f.fileno())
-        os.replace(tmp_path, JOBS_FILE)
-        _secure_file(JOBS_FILE)
-    except BaseException:
+    import fcntl
+    lock_path = JOBS_FILE.parent / ".jobs.lock"
+    with open(lock_path, "w") as lock_fd:
+        fcntl.flock(lock_fd, fcntl.LOCK_EX)
+        fd, tmp_path = tempfile.mkstemp(dir=str(JOBS_FILE.parent), suffix='.tmp', prefix='.jobs_')
         try:
-            os.unlink(tmp_path)
-        except OSError:
-            pass
-        raise
+            with os.fdopen(fd, 'w', encoding='utf-8') as f:
+                json.dump({"jobs": jobs, "updated_at": _hermes_now().isoformat()}, f, indent=2)
+                f.flush()
+                os.fsync(f.fileno())
+            os.replace(tmp_path, JOBS_FILE)
+            _secure_file(JOBS_FILE)
+        except BaseException:
+            try:
+                os.unlink(tmp_path)
+            except OSError:
+                pass
+            raise
 
 
 def create_job(