perf: set watermarks even when no archives found to prevent re-scanning

Previously, channels/topics with no new archives never had their
watermark updated. This meant every cycle re-scanned all messages from
scratch just to discover nothing new — especially costly for the 1079-
topic Model Printing Emporium forum.

- Add maxScannedMessageId to ChannelScanResult (highest msg ID seen)
- Set channel watermark to scan boundary when no archives are found
- Set topic watermark to scan boundary when no archives are found
- Fall back to scan watermark when archive processing doesn't advance it

After one full cycle, subsequent cycles will skip already-scanned
messages via the early-exit boundary check, dramatically reducing
TDLib API calls on channels with mostly non-archive content.

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

worker/src/tdlib/download.ts

@@ -79,6 +79,8 @@ export interface ChannelScanResult {
   archives: TelegramMessage[];
   photos: TelegramPhoto[];
   totalScanned: number;
+  /** Highest message ID seen during scan (for watermark, even when no archives found). */
+  maxScannedMessageId: bigint | null;
 }
 
 export type ScanProgressCallback = (messagesScanned: number) => void;
@@ -158,6 +160,7 @@ export async function getChannelMessages(
   const archives: TelegramMessage[] = [];
   const photos: TelegramPhoto[] = [];
   const boundary = lastProcessedMessageId ? Number(lastProcessedMessageId) : null;
+  let maxScannedMessageId: bigint | null = null;
 
   // Open the chat so TDLib can access it
   try {
@@ -204,6 +207,12 @@ export async function getChannelMessages(
 
       totalScanned += result.messages.length;
 
+      // Track highest message ID (first message in batch = newest, since results are newest-first)
+      const batchMaxId = BigInt(result.messages[0].id);
+      if (maxScannedMessageId === null || batchMaxId > maxScannedMessageId) {
+        maxScannedMessageId = batchMaxId;
+      }
+
       for (const msg of result.messages) {
         // Check for archive documents
         const doc = msg.content?.document;
@@ -271,6 +280,7 @@ export async function getChannelMessages(
     archives: archives.reverse(),
     photos: photos.reverse(),
     totalScanned,
+    maxScannedMessageId,
   };
 }
 

worker/src/tdlib/topics.ts

@@ -178,6 +178,7 @@ export async function getTopicMessages(
   const archives: TelegramMessage[] = [];
   const photos: TelegramPhoto[] = [];
   const boundary = lastProcessedMessageId ? Number(lastProcessedMessageId) : null;
+  let maxScannedMessageId: bigint | null = null;
 
   let currentFromId = 0;
   let totalScanned = 0;
@@ -239,6 +240,12 @@ export async function getTopicMessages(
 
     totalScanned += result.messages.length;
 
+    // Track highest message ID (first message = newest, since results are newest-first)
+    const batchMaxId = BigInt(result.messages[0].id);
+    if (maxScannedMessageId === null || batchMaxId > maxScannedMessageId) {
+      maxScannedMessageId = batchMaxId;
+    }
+
     for (const msg of result.messages) {
       // Check for archive documents
       const doc = msg.content?.document;
@@ -302,6 +309,7 @@ export async function getTopicMessages(
     archives: archives.reverse(),
     photos: photos.reverse(),
     totalScanned,
+    maxScannedMessageId,
   };
 }