From 7f52e0e8918539b787df37c3f2df86db06ba450c Mon Sep 17 00:00:00 2001
From: Logan Cusano <logan@simplestepsolutions.com>
Date: Mon, 26 Oct 2026 02:24:07 -0400
Subject: [PATCH] checkin: report host disk free/total bytes (#41)

/recordings is a bind mount of the host checkout, so shutil.disk_usage on it
is the disk the recorder writes to and Docker fills. Explicit nulls on error
so C2 never keeps a stale reading. Server half: server-26 feat/41-node-disk.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---
 drb-edge-node/app/internal/mqtt_manager.py | 18 ++++++++++++++++++
 drb-edge-node/tests/test_mqtt_manager.py   | 13 +++++++++++++
 2 files changed, 31 insertions(+)

diff --git a/drb-edge-node/app/internal/mqtt_manager.py b/drb-edge-node/app/internal/mqtt_manager.py
index 834c059..09eb12a 100644
--- a/drb-edge-node/app/internal/mqtt_manager.py
+++ b/drb-edge-node/app/internal/mqtt_manager.py
@@ -1,5 +1,6 @@
 import asyncio
 import json
+import shutil
 from datetime import datetime, timezone
 from collections import deque
 from typing import Optional, Callable, Awaitable, Dict, Any
@@ -8,6 +9,22 @@ from app.config import settings
 from app.internal.logger import logger
 from app.internal import credentials, key_pickup
 
+
+def disk_report(path: str) -> Dict[str, Optional[int]]:
+    """Free/total bytes of the filesystem holding `path` (node-26#41).
+
+    /recordings is a bind mount of the host checkout, so this is the host disk
+    the recorder writes to and Docker's images/build cache live on. A full disk
+    stopped node-002 recording for 17 days while it still showed Online. Nulls
+    on error, so C2 overwrites a stale reading instead of keeping it.
+    """
+    try:
+        usage = shutil.disk_usage(path)
+    except OSError:
+        return {"disk_free_bytes": None, "disk_total_bytes": None}
+    return {"disk_free_bytes": usage.free, "disk_total_bytes": usage.total}
+
+
 CommandCallback = Callable[[Dict[str, Any]], Awaitable[None]]
 ConfigCallback = Callable[[Dict[str, Any]], Awaitable[None]]
 ApiKeyCallback = Callable[[Dict[str, Any]], Awaitable[None]]
@@ -372,6 +389,7 @@ class MQTTManager:
             count = devices.get("count") or None
         if count is not None:
             payload["sdr_count"] = count
+        payload.update(disk_report(settings.recordings_path))
         self._publish(self._t_checkin, payload, qos=1)
 
     def _publish(self, topic: str, payload: dict, qos: int = 0, retain: bool = False):
diff --git a/drb-edge-node/tests/test_mqtt_manager.py b/drb-edge-node/tests/test_mqtt_manager.py
index cfcb60f..96686d6 100644
--- a/drb-edge-node/tests/test_mqtt_manager.py
+++ b/drb-edge-node/tests/test_mqtt_manager.py
@@ -140,3 +140,16 @@ def test_build_client_does_not_touch_offline_buffer(monkeypatch):
 
     assert list(mqtt_manager._offline_buffer) == [("nodes/test/metadata", {"call_id": "sentinel"})]
     mqtt_manager._offline_buffer.clear()
+
+
+def test_disk_report_reads_free_and_total(tmp_path):
+    from app.internal.mqtt_manager import disk_report
+    rep = disk_report(str(tmp_path))
+    assert rep["disk_total_bytes"] > 0
+    assert 0 <= rep["disk_free_bytes"] <= rep["disk_total_bytes"]
+
+
+def test_disk_report_nulls_when_path_unreadable(tmp_path):
+    # node-26#41: nulls (not omitted keys) so C2 never keeps a stale reading.
+    from app.internal.mqtt_manager import disk_report
+    assert disk_report(str(tmp_path / "missing")) == {"disk_free_bytes": None, "disk_total_bytes": None}