From 18e57c6e5facf0fee81c5d6d16451182df10a545 Mon Sep 17 00:00:00 2001
From: bonamin <just_big_v@yahoo.com>
Date: Wed, 30 Sep 2026 15:55:26 +0300
Subject: [PATCH] fix(mqtt): dedupe boot_report against the latest row, not any
 boot_count

98dd16b skipped a boot_report if ANY earlier row had the same boot_count.
That is wrong: the firmware's lifetime boot counter gets reset (reflash /
telemetry reset), and the data shows counts 1-4 recurring in July and again
in September. With that rule a real later boot reusing a number would be
dropped forever.

A retained redelivery is always a copy of the device's most recent boot, so
compare only against the latest row (boot_count + reset_reason). A genuine
new boot always differs from it - the counter moves forward or was reset.

Note: the one-off cleanup run on 2026-09-30 used the same wrong
(serial, boot_count) key and deleted some genuine boot rows along with the
redelivery duplicates; see the session notes / heartbeat-based reboot list.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---
 backend/database/pg_mqtt.py | 28 ++++++++++++++++++----------
 1 file changed, 18 insertions(+), 10 deletions(-)

diff --git a/backend/database/pg_mqtt.py b/backend/database/pg_mqtt.py
index 0a9a51e..d2caffc 100644
--- a/backend/database/pg_mqtt.py
+++ b/backend/database/pg_mqtt.py
@@ -445,22 +445,30 @@ async def insert_boot_event(device_serial: str, boot_count: int | None,
                             crash_pc: int | None = None,
                             crash_exc_cause: int | None = None,
                             crash_exc_vaddr: int | None = None) -> int | None:
-    """Insert a boot event, unless one with the same boot_count already exists
-    for this device (returns None then). boot_report is published retained on
-    system/info, so the broker redelivers the last one every time the backend
-    (re)subscribes — without this check each backend restart logged the
-    device's last boot (crash detail included) again as a brand-new event."""
+    """Insert a boot event, unless it is a repeat of the device's most recent
+    one (returns None then). boot_report is published retained on system/info,
+    so the broker redelivers the last one every time the backend (re)subscribes
+    — without this check each backend restart logged the device's last boot
+    (crash detail included) again as a brand-new event.
+
+    Only the LATEST row is compared, never "any row with this boot_count": the
+    firmware's lifetime counter gets reset (reflash / telemetry reset), so the
+    same boot_count legitimately appears again for a later, different boot. A
+    genuine new boot always differs from the latest row — the counter either
+    moved forward or was reset to a lower number."""
     async with AsyncSessionLocal() as session:
         if boot_count is not None:
-            dup = await session.execute(
+            latest = await session.execute(
                 text("""
-                    SELECT 1 FROM device_boot_events
-                    WHERE device_serial = :serial AND boot_count = :boot_count
+                    SELECT boot_count, reset_reason FROM device_boot_events
+                    WHERE device_serial = :serial
+                    ORDER BY occurred_at DESC
                     LIMIT 1
                 """),
-                {"serial": device_serial, "boot_count": boot_count},
+                {"serial": device_serial},
             )
-            if dup.first() is not None:
+            row = latest.first()
+            if row is not None and row.boot_count == boot_count and row.reset_reason == reset_reason:
                 return None
         result = await session.execute(
             text("""