fix(knowledge): let sourceConfirmedEmpty also bypass the mass-deletion safety threshold

The zero-document guard bypass alone wasn't enough: for a trashed
spreadsheet with more than 5 tabs, reconciliation would proceed but
the separate mass-deletion ratio guard (>50% deleted, >5 docs) still
blocked the actual delete on a normal sync, requiring a forced full
resync anyway. Extracted the ratio guard into
exceedsDeletionSafetyThreshold, mirroring shouldSkipEmptyListing, so
a connector's positive source confirmation bypasses both guards
consistently.

Author: waleedlatif1

apps/sim/lib/knowledge/connectors/sync-engine.test.ts

@@ -116,6 +116,61 @@ describe('shouldSkipEmptyListing', () => {
   })
 })
 
+describe('exceedsDeletionSafetyThreshold', () => {
+  it('does not block a small deletion, even above 50%', async () => {
+    const { exceedsDeletionSafetyThreshold } = await import(
+      '@/lib/knowledge/connectors/sync-engine'
+    )
+
+    expect(exceedsDeletionSafetyThreshold(4, 5, undefined, {})).toBe(false)
+  })
+
+  it('does not block a large deletion below 50%', async () => {
+    const { exceedsDeletionSafetyThreshold } = await import(
+      '@/lib/knowledge/connectors/sync-engine'
+    )
+
+    expect(exceedsDeletionSafetyThreshold(6, 20, undefined, {})).toBe(false)
+  })
+
+  it('blocks a deletion above both the ratio and count thresholds by default', async () => {
+    const { exceedsDeletionSafetyThreshold } = await import(
+      '@/lib/knowledge/connectors/sync-engine'
+    )
+
+    expect(exceedsDeletionSafetyThreshold(10, 10, undefined, {})).toBe(true)
+    expect(exceedsDeletionSafetyThreshold(10, 10, undefined, undefined)).toBe(true)
+  })
+
+  it('does not block on a forced fullSync', async () => {
+    const { exceedsDeletionSafetyThreshold } = await import(
+      '@/lib/knowledge/connectors/sync-engine'
+    )
+
+    expect(exceedsDeletionSafetyThreshold(10, 10, true, {})).toBe(false)
+  })
+
+  it('does not block when the connector confirms the deletion against the source', async () => {
+    const { exceedsDeletionSafetyThreshold } = await import(
+      '@/lib/knowledge/connectors/sync-engine'
+    )
+
+    expect(exceedsDeletionSafetyThreshold(10, 10, undefined, { sourceConfirmedEmpty: true })).toBe(
+      false
+    )
+  })
+
+  it('still blocks when sourceConfirmedEmpty is falsy', async () => {
+    const { exceedsDeletionSafetyThreshold } = await import(
+      '@/lib/knowledge/connectors/sync-engine'
+    )
+
+    expect(exceedsDeletionSafetyThreshold(10, 10, undefined, { sourceConfirmedEmpty: false })).toBe(
+      true
+    )
+  })
+})
+
 describe('resolveTagMapping', () => {
   beforeEach(() => {
     vi.clearAllMocks()

apps/sim/lib/knowledge/connectors/sync-engine.ts

@@ -264,6 +264,27 @@ export function shouldSkipEmptyListing(
   return !syncContext?.sourceConfirmedEmpty
 }
 
+/**
+ * Decides whether a deletion should be blocked by the mass-deletion safety
+ * threshold (more than half of existing documents, over 5) instead of proceeding.
+ *
+ * This guards against a connector-side bug or transient glitch producing a
+ * listing that looks mostly empty. `sourceConfirmedEmpty` bypasses it the same
+ * way it bypasses `shouldSkipEmptyListing` — the connector positively verified
+ * the deletion against the source rather than merely inferring it from a
+ * listing, so the extra caution this threshold provides doesn't apply.
+ */
+export function exceedsDeletionSafetyThreshold(
+  removedCount: number,
+  existingCount: number,
+  fullSync: boolean | undefined,
+  syncContext: Record<string, unknown> | undefined
+): boolean {
+  if (fullSync || syncContext?.sourceConfirmedEmpty) return false
+  const deletionRatio = existingCount > 0 ? removedCount / existingCount : 0
+  return deletionRatio > 0.5 && removedCount > 5
+}
+
 /**
  * Resolves tag values from connector metadata using the connector's mapTags function.
  * Translates semantic keys returned by mapTags to actual DB slots using the
@@ -826,12 +847,20 @@ export async function executeSync(
         .map((d) => d.id)
 
       if (removedIds.length > 0) {
-        const deletionRatio = existingDocs.length > 0 ? removedIds.length / existingDocs.length : 0
-
-        if (deletionRatio > 0.5 && removedIds.length > 5 && !options?.fullSync) {
+        if (
+          exceedsDeletionSafetyThreshold(
+            removedIds.length,
+            existingDocs.length,
+            options?.fullSync,
+            syncContext
+          )
+        ) {
           logger.warn(
             `Skipping deletion of ${removedIds.length}/${existingDocs.length} docs — exceeds safety threshold. Trigger a full sync to force cleanup.`,
-            { connectorId, deletionRatio: Math.round(deletionRatio * 100) }
+            {
+              connectorId,
+              deletionRatio: Math.round((removedIds.length / existingDocs.length) * 100),
+            }
           )
         } else {
           await hardDeleteDocuments(removedIds, syncLogId)