fix(logs): a line with no RouterOS id had no protection against re-insertion (v0.24.4-beta)

Follows #137. The v0.24.1 fix made the count honest and stopped a thousand
round trips per poll, but it assumed the unique index on (device_id, log_id)
would reject lines already stored. For most devices it does. For a device
whose log entries carry no `.id` it never could: the column was set to NULL,
and PostgreSQL treats NULLs as *distinct* in a unique index, so every NULL
conflicts with nothing. Those devices re-inserted their entire buffer on
every poll, for ever, and the constraint that was supposed to stop it was
structurally incapable of firing.

A line with no id now gets a key derived from its own content -- timestamp,
topics and message -- so the existing index does the work. The `#` prefix
keeps it out of the space of real RouterOS ids (`*` plus hex), so the two
cannot collide, and parseRosId already rejects it, which matters because the
watermark is a max over real ids and must not be poisoned by a synthetic one.

The trade, stated rather than buried: two genuinely separate lines sharing a
timestamp, topic and message collapse into one. RouterOS timestamps are
second-resolution, so that can happen. Losing a repeat of an identical
message is a much smaller loss than growing the table by the whole buffer
every minute without bound.

This was found by reading a comment on #137 I had not read before closing it
-- log output from a device with eleven lines total, reporting eleven new
entries every minute for forty-five minutes. My own fleet cannot reproduce
it: every event here carries a real `.id`, with no nulls and no duplicates,
which is exactly why the hole was invisible from here. So this closes a
defect demonstrable from the schema; whether it is the whole of that
reporter's problem is still an open question and the issue is reopened to ask.

Verified no regression where ids are healthy: no surrogate keys generated, no
nulls, no duplicates, and counts that vary with real activity.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

README.md

@@ -6,7 +6,7 @@
 </p>
 
 <p align="center">
-  <img src="https://img.shields.io/badge/version-0.24.3_Beta-blue" alt="Version" />
+  <img src="https://img.shields.io/badge/version-0.24.4_Beta-blue" alt="Version" />
   <img src="https://img.shields.io/badge/license-AGPLv3-blue" alt="License" />
   <img src="https://img.shields.io/badge/docker-compose-2496ED?logo=docker&logoColor=white" alt="Docker" />
   <img src="https://img.shields.io/badge/TypeScript-5.3-3178C6?logo=typescript&logoColor=white" alt="TypeScript" />

backend/package.json

@@ -1,6 +1,6 @@
 {
   "name": "mikrotik-manager-backend",
-  "version": "0.24.3-beta",
+  "version": "0.24.4-beta",
   "description": "Mikrotik Network Management Platform - Backend API",
   "main": "dist/index.js",
   "scripts": {

backend/src/services/mikrotik/DeviceCollector.ts

@@ -30,7 +30,7 @@ const UPDATE_DOWNLOAD_TIMEOUT_MS = 10 * 60_000;
  * learned to abandon a timed-out connection, desynchronised the session (#137).
  */
 const LOG_READ_TIMEOUT_MS = 120_000;
-import { selectNewLogLines, highestStoredId, type RawLogLine } from '../../utils/logDedup';
+import { selectNewLogLines, highestStoredId, surrogateLogId, type RawLogLine } from '../../utils/logDedup';
 import { alertService } from '../AlertService';
 
 /** DB column limits for topology_links (see migrate.ts); reject oversize rows instead of silent truncation. */
@@ -852,17 +852,23 @@ export class DeviceCollector {
 
       const pending: unknown[][] = [];
       for (const log of fresh) {
-        const logId = (log['.id'] || '') as string;
+        const rawId = (log['.id'] || '') as string;
+        const topics = (log['topics'] as string) || '';
+        const message = (log['message'] as string) || '';
         const time = this.parseLogTime(log['time'] || '');
-        const severity = this.mapLogSeverity((log['topics'] as string) || '');
+        const severity = this.mapLogSeverity(topics);
+        // Never store a null log_id: the unique index that stops re-insertion
+        // does not constrain nulls, so a device whose lines carry no `.id`
+        // would accumulate the same entries for ever (#137).
+        const logId = rawId || surrogateLogId(log['time'] || '', topics, message);
         pending.push([
           this.device.id,
           time.toISOString(),
           severity,
-          (log['topics'] as string) || null,
-          (log['message'] as string) || '',
+          topics || null,
+          message,
           JSON.stringify(log),
-          logId || null,
+          logId,
         ]);
       }
 

backend/src/utils/__tests__/logDedup.test.ts

@@ -1,5 +1,6 @@
 import {
-  parseRosId, highestStoredId, isLogReset, selectNewLogLines, type RawLogLine,
+  parseRosId, highestStoredId, isLogReset, selectNewLogLines,
+  surrogateLogId, isSurrogateLogId, type RawLogLine,
 } from '../logDedup';
 
 // Fixed clock so timestamp comparisons are deterministic.
@@ -91,3 +92,49 @@ describe('selectNewLogLines', () => {
     expect(selectNewLogLines(logs, { lastStoredId: 0, latestStoredTime, parseTime })).toHaveLength(0);
   });
 });
+
+describe('surrogateLogId', () => {
+  const line = ['sep/08 02:38:10', 'system,info', 'router rebooted'] as const;
+
+  it('is stable for the same line', () => {
+    expect(surrogateLogId(...line)).toBe(surrogateLogId(...line));
+  });
+
+  it('differs when any field differs', () => {
+    const base = surrogateLogId(...line);
+    expect(surrogateLogId('sep/08 02:38:11', line[1], line[2])).not.toBe(base);
+    expect(surrogateLogId(line[0], 'system,error', line[2])).not.toBe(base);
+    expect(surrogateLogId(line[0], line[1], 'something else')).not.toBe(base);
+  });
+
+  // Field boundaries are separated, so shifting text between fields cannot
+  // produce the same key.
+  it('does not confuse field boundaries', () => {
+    expect(surrogateLogId('a', 'b', 'c')).not.toBe(surrogateLogId('ab', '', 'c'));
+  });
+
+  // The column is VARCHAR(20); an over-long key would throw on insert.
+  it('fits the log_id column', () => {
+    const id = surrogateLogId('x'.repeat(500), 'y'.repeat(500), 'z'.repeat(5000));
+    expect(id.length).toBeLessThanOrEqual(20);
+  });
+
+  it('cannot be mistaken for a RouterOS id', () => {
+    const id = surrogateLogId(...line);
+    expect(id.startsWith('#')).toBe(true);
+    expect(isSurrogateLogId(id)).toBe(true);
+    expect(isSurrogateLogId('*CC75')).toBe(false);
+    expect(isSurrogateLogId(null)).toBe(false);
+  });
+
+  /**
+   * The watermark is a max over RouterOS's own hex ids. A synthesised id must
+   * not be parsed as one, or it would poison the high-water mark and make every
+   * real line look already-seen.
+   */
+  it('is ignored by the id watermark', () => {
+    const id = surrogateLogId(...line);
+    expect(parseRosId(id)).toBe(0);
+    expect(highestStoredId([id, '*10'])).toBe(0x10);
+  });
+});

backend/src/utils/logDedup.ts

@@ -7,6 +7,8 @@
  * the entire buffer once a minute.
  */
 
+import { createHash } from 'crypto';
+
 export interface RawLogLine {
   '.id'?: string;
   time?: string;
@@ -81,3 +83,35 @@ export function selectNewLogLines(
   }
   return out;
 }
+
+/**
+ * A stable identifier for a log line that RouterOS gave no `.id`.
+ *
+ * The events table has a unique index on (device_id, log_id) and relies on it
+ * to reject lines already stored. PostgreSQL treats NULLs as *distinct* in a
+ * unique index, so a NULL log_id conflicts with nothing: a device whose log
+ * entries carry no `.id` had no protection at all and re-inserted the same
+ * lines on every poll, without bound.
+ *
+ * Deriving the key from the line's own content restores that protection. The
+ * `#` prefix keeps it out of the space of real RouterOS ids, which are `*`
+ * followed by hex, so the two can never collide or be mistaken for each other.
+ *
+ * The trade, stated plainly: two genuinely separate lines with the same
+ * timestamp, topic and text collapse into one. RouterOS timestamps are
+ * second-resolution, so that is possible. Losing a repeat of an identical
+ * message is a far smaller loss than growing the table by the whole buffer
+ * every minute for ever.
+ */
+export function surrogateLogId(time: string, topics: string, message: string): string {
+  const hash = createHash('sha256')
+    .update(`${time}\u0000${topics}\u0000${message}`)
+    .digest('hex')
+    .slice(0, 16);
+  return `#${hash}`;           // 17 chars, inside the column's VARCHAR(20)
+}
+
+/** True for the ids this module synthesised, as opposed to RouterOS's own. */
+export function isSurrogateLogId(id: string | null | undefined): boolean {
+  return typeof id === 'string' && id.startsWith('#');
+}

frontend/package.json

@@ -1,6 +1,6 @@
 {
   "name": "mikrotik-manager-frontend",
-  "version": "0.24.3-beta",
+  "version": "0.24.4-beta",
   "private": true,
   "type": "module",
   "scripts": {

frontend/src/version.ts

@@ -1 +1 @@
-export const APP_VERSION = 'v0.24.3 Beta';
+export const APP_VERSION = 'v0.24.4 Beta';