From 622a21bd9a47b08166d65a91c97c2dd942c86572 Mon Sep 17 00:00:00 2001
From: Waleed Latif <walif6@gmail.com>
Date: Thu, 20 Aug 2026 14:31:26 -0700
Subject: [PATCH] fix(connectors): only flag a Bitbucket listing capped when
 the cap withheld something

Review round 2.

takeIndexableWithinCap reports capReached as soon as the running total equals
maxItems, which is also true of a listing that ended at exactly that count.
Setting listingCapped there suppressed deletion reconciliation for a complete
listing, so upstream-deleted files and pull requests could stay in the knowledge
base indefinitely. applyMaxItemsCap now takes whether Bitbucket had more content
beyond the page -- a next link, or directories still queued on the frontier --
and flags the listing only when the cap actually withheld something, matching the
Databricks, Google Chat, and Workday connectors.
---
 .../connectors/bitbucket/bitbucket.test.ts    | 38 +++++++++++++++++++
 apps/sim/connectors/bitbucket/bitbucket.ts    | 20 ++++++++--
 2 files changed, 54 insertions(+), 4 deletions(-)

diff --git a/apps/sim/connectors/bitbucket/bitbucket.test.ts b/apps/sim/connectors/bitbucket/bitbucket.test.ts
index f6460e41c2..bab02ea9c7 100644
--- a/apps/sim/connectors/bitbucket/bitbucket.test.ts
+++ b/apps/sim/connectors/bitbucket/bitbucket.test.ts
@@ -357,6 +357,44 @@ describe('bitbucket maxItems cap', () => {
     expect(syncContext.listingCapped).toBe(true)
   })
 
+  it('leaves the listing reconcilable when a complete listing ends exactly on the cap', async () => {
+    mockApi([[/\/src\//, () => jsonResponse({ values: [fileEntry('a.md'), fileEntry('b.md')] })]])
+
+    const syncContext: Record<string, unknown> = {}
+    const result = await bitbucketConnector.listDocuments(
+      ACCESS_TOKEN,
+      { ...CONFIG, maxItems: '2' },
+      undefined,
+      syncContext
+    )
+
+    expect(result.documents).toHaveLength(2)
+    expect(syncContext.listingCapped).toBeUndefined()
+  })
+
+  it('flags the listing capped when the cap lands on a page boundary with more to come', async () => {
+    mockApi([
+      [
+        /\/src\//,
+        () =>
+          jsonResponse({
+            values: [fileEntry('a.md'), fileEntry('b.md')],
+            next: 'https://api.bitbucket.org/2.0/repositories/acme/widgets/src/abc/?page=2',
+          }),
+      ],
+    ])
+
+    const syncContext: Record<string, unknown> = {}
+    await bitbucketConnector.listDocuments(
+      ACCESS_TOKEN,
+      { ...CONFIG, maxItems: '2' },
+      undefined,
+      syncContext
+    )
+
+    expect(syncContext.listingCapped).toBe(true)
+  })
+
   it('leaves the listing reconcilable when no cap is configured', async () => {
     mockApi([[/\/src\//, () => jsonResponse({ values: [fileEntry('a.md'), fileEntry('b.md')] })]])
 
diff --git a/apps/sim/connectors/bitbucket/bitbucket.ts b/apps/sim/connectors/bitbucket/bitbucket.ts
index 1c02cf54eb..da47d45e8a 100644
--- a/apps/sim/connectors/bitbucket/bitbucket.ts
+++ b/apps/sim/connectors/bitbucket/bitbucket.ts
@@ -714,11 +714,20 @@ function pendingDirectories(syncContext: Record<string, unknown> | undefined): s
  * Applies the optional maxItems cap to a page, tracking the running total in
  * syncContext and flagging `listingCapped` when the cap truncates the listing.
  * Skipped (oversized) documents ride along without consuming the cap.
+ *
+ * `sourceHasMore` is whether Bitbucket still had content beyond this page — a
+ * `next` link, or directories still queued on the frontier. It is required because
+ * `takeIndexableWithinCap` reports `capReached` as soon as the running total
+ * *equals* maxItems, which is also true of a listing that ended at exactly that
+ * count. Setting `listingCapped` there would suppress deletion reconciliation for
+ * a listing that was in fact complete, leaving upstream-deleted files indexed
+ * indefinitely, so the flag is set only when the cap actually withheld something.
  */
 function applyMaxItemsCap(
   documents: ExternalDocument[],
   maxItems: number,
-  syncContext: Record<string, unknown> | undefined
+  syncContext: Record<string, unknown> | undefined,
+  sourceHasMore: boolean
 ): { documents: ExternalDocument[]; capped: boolean } {
   if (maxItems <= 0) return { documents, capped: false }
   const alreadyIndexed = (syncContext?.totalDocsFetched as number) ?? 0
@@ -734,7 +743,8 @@ function applyMaxItemsCap(
   )
   if (syncContext) {
     syncContext.totalDocsFetched = alreadyIndexed + indexableCount
-    if (capReached) syncContext.listingCapped = true
+    const withheld = taken.length < documents.length || sourceHasMore
+    if (capReached && withheld) syncContext.listingCapped = true
   }
   return { documents: taken, capped: capReached }
 }
@@ -922,7 +932,8 @@ export const bitbucketConnector: ConnectorConfig = {
       const { documents: capped, capped: hitLimit } = applyMaxItemsCap(
         documents,
         maxItems,
-        syncContext
+        syncContext,
+        Boolean(page.next) || frontier.length > 0
       )
       if (hitLimit) return { documents: capped, hasMore: false }
 
@@ -990,7 +1001,8 @@ export const bitbucketConnector: ConnectorConfig = {
     const { documents: capped, capped: hitLimit } = applyMaxItemsCap(
       documents,
       maxItems,
-      syncContext
+      syncContext,
+      Boolean(page.next)
     )
     if (hitLimit) return { documents: capped, hasMore: false }