Drop the systemd units; the script now locks itself and finds claude

resume-stalled-sessions.py

@@ -8,15 +8,20 @@ cause has cleared.
 """
 
 import argparse
+import fcntl
 import json
 import os
 import re
+import shutil
 import subprocess
 import sys
 from datetime import datetime, timedelta
 from pathlib import Path
 from zoneinfo import ZoneInfo
 
+# Where `claude` installs itself, and what a scheduler's minimal PATH omits.
+CLAUDE_FALLBACK_DIRS = ("~/.local/bin", "/usr/local/bin", "/opt/homebrew/bin")
+
 DEFAULT_PROMPT = (
     "Continue where you left off. Your previous run was interrupted by a "
     "transient failure (usage limit, API outage, or network), which has cleared."
@@ -64,8 +69,36 @@ def log(message):
     print(f"{datetime.now().astimezone().isoformat(timespec='seconds')} {message}", flush=True)
 
 
+def resolve_claude(name):
+    """Absolute path to the Claude Code binary, or None if it cannot be found."""
+    found = shutil.which(name)
+    if found:
+        return found
+    for directory in CLAUDE_FALLBACK_DIRS:
+        candidate = Path(directory).expanduser() / name
+        if candidate.is_file() and os.access(candidate, os.X_OK):
+            return str(candidate)
+    return None
+
+
+def single_instance(path):
+    """Exclusive lock for this run, or None when another run already holds it.
+
+    Overlapping runs both read the ledger before either writes it, so both
+    resume the same session — two agents racing on one git worktree.
+    """
+    path.parent.mkdir(parents=True, exist_ok=True)
+    handle = path.open("w")
+    try:
+        fcntl.flock(handle, fcntl.LOCK_EX | fcntl.LOCK_NB)
+    except OSError:
+        handle.close()
+        return None
+    return handle
+
+
 def active_sessions(claude_bin):
-    """Sessions Claude Code still considers active (completed ones are excluded)."""
+    """Sessions Claude Code still considers active, or None if they cannot be read."""
     try:
         done = subprocess.run(
             [claude_bin, "agents", "--json"],
@@ -73,12 +106,12 @@ def active_sessions(claude_bin):
         )
     except (OSError, subprocess.SubprocessError) as err:
         log(f"error: could not list sessions: {err}")
-        return []
+        return None
     try:
         return json.loads(done.stdout)
     except json.JSONDecodeError as err:
         log(f"error: unparseable session list: {err}")
-        return []
+        return None
 
 
 def pid_alive(pid):
@@ -259,8 +292,22 @@ def main():
     parser.add_argument("--prompt", default=os.environ.get("WATCHDOG_PROMPT", DEFAULT_PROMPT))
     args = parser.parse_args()
 
+    claude_bin = resolve_claude(args.claude_bin)
+    if not claude_bin:
+        log(f"error: '{args.claude_bin}' is not in PATH or "
+            f"{', '.join(CLAUDE_FALLBACK_DIRS)} — resuming nothing")
+        return 1
+
+    state_dir = args.claude_home / "session-watchdog"
+    lock = None
+    if not args.dry_run:
+        lock = single_instance(state_dir / ".lock")  # released when main returns
+        if lock is None:
+            log("another run is still going, skipping")
+            return 0
+
     now = datetime.now().astimezone()
-    ledger_path = args.claude_home / "session-watchdog" / "ledger.json"
+    ledger_path = state_dir / "ledger.json"
     ledger = load_ledger(ledger_path)
 
     recent = [at for at in ledger["resumes"] if now.timestamp() - at < 86400]
@@ -271,7 +318,10 @@ def main():
         log(f"circuit breaker: {len(recent)} resumes in the last 24h (max {args.max_per_day})")
         return 0
 
-    sessions = active_sessions(args.claude_bin)
+    sessions = active_sessions(claude_bin)
+    if sessions is None:
+        return 1
+
     resumed = 0
     for job in candidates(sessions, args.claude_home / "jobs", now):
         if resumed >= budget:
@@ -279,7 +329,7 @@ def main():
         tried = ledger["attempts"].get(job["session_id"], 0)
         if tried >= args.max_attempts:
             continue
-        if not resume(job, args.claude_bin, args.prompt, args.dry_run):
+        if not resume(job, claude_bin, args.prompt, args.dry_run):
             continue
         ledger["attempts"][job["session_id"]] = tried + 1
         ledger["resumes"] = recent + [now.timestamp()]