Fix batch size (20→5) and script detection in monitor

- Reduce embed batch to 5 — AnythingLLM hangs on batches >10
- Fix check_script_running() to properly detect setup.py process
  (was returning false because pgrep matched monitor.py too)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

monitor.py

@@ -85,8 +85,15 @@ def check_api(config):
 def check_script_running():
     try:
         import subprocess
-        result = subprocess.run(["pgrep", "-f", "setup.py"], capture_output=True, text=True)
-        return result.returncode == 0
+        result = subprocess.run(
+            ["pgrep", "-af", "setup.py"],
+            capture_output=True, text=True
+        )
+        # Filter out monitor.py and grep itself
+        for line in result.stdout.strip().split("\n"):
+            if line and "monitor" not in line and "pgrep" not in line:
+                return True
+        return False
     except Exception:
         return None
 

setup.py

@@ -532,8 +532,8 @@ def assign_to_workspaces(config, persona_folders, progress, batch_size, delay):
 
         log.info(f"[{idx}/{total_personas}] → {codename} ({slug}): {len(new_docs)} docs to embed")
 
-        # Use smaller batches for embedding (10-20 is safer than 50)
-        embed_batch = min(batch_size, 20)
+        # Use small batches for embedding — AnythingLLM hangs on large batches
+        embed_batch = min(batch_size, 5)
         persona_ok = 0
         persona_fail = 0