diff --git a/vibn-frontend/app/api/chat/route.ts b/vibn-frontend/app/api/chat/route.ts
index 53fe661a..0b6d5666 100644
--- a/vibn-frontend/app/api/chat/route.ts
+++ b/vibn-frontend/app/api/chat/route.ts
@@ -397,9 +397,9 @@ export async function POST(request: Request) {
   const principal = await requireWorkspacePrincipal(request);
   if (principal instanceof NextResponse) return principal;
 
-  const userRow = await queryOne<{ data: any }>(
+  const userRow = await queryOne<{ data: { email?: string } }>(
     `SELECT data FROM fs_users WHERE id = $1 LIMIT 1`,
-    [principal.userId]
+    [principal.userId],
   );
   if (!userRow?.data?.email) {
     return NextResponse.json({ error: "Unauthorized user" }, { status: 401 });
@@ -1056,6 +1056,25 @@ export async function POST(request: Request) {
           }
         }
 
+        // Last-resort guard: the model produced NO user-facing text and NO
+        // tools (e.g. a "thinking" turn that returned only reasoning with an
+        // empty answer part). The tool-tray recovery above doesn't cover this
+        // case, so without this the user gets a silent blank bubble. Emit a
+        // short deterministic fallback so every turn says *something*.
+        if (
+          !aborted &&
+          assistantText.trim().length === 0 &&
+          !anyToolsExecuted
+        ) {
+          const fallback =
+            "I didn't produce a response for that — I may have spent the turn " +
+            "reasoning without writing an answer. Could you rephrase or add a " +
+            "bit more detail?";
+          assistantText = fallback;
+          assistantTextSegments.push(fallback);
+          emit({ type: "text", text: fallback });
+        }
+
         // Persist final assistant message. We include `textSegments`
         // alongside the legacy concatenated `content` so the client
         // can render reloaded threads with the same per-round bubble
diff --git a/vibn-frontend/app/api/chat/threads/[id]/route.ts b/vibn-frontend/app/api/chat/threads/[id]/route.ts
index 9a68db9a..3af1a36b 100644
--- a/vibn-frontend/app/api/chat/threads/[id]/route.ts
+++ b/vibn-frontend/app/api/chat/threads/[id]/route.ts
@@ -11,7 +11,7 @@ export async function GET(request: Request, { params }: { params: Promise<{ id:
   const principal = await requireWorkspacePrincipal(request);
   if (principal instanceof NextResponse) return principal;
 
-  const userRow = await queryOne<{ data: any }>(
+  const userRow = await queryOne<{ data: { email?: string } }>(
     `SELECT data FROM fs_users WHERE id = $1 LIMIT 1`,
     [principal.userId]
   );
@@ -42,7 +42,7 @@ export async function PATCH(request: Request, { params }: { params: Promise<{ id
   const principal = await requireWorkspacePrincipal(request);
   if (principal instanceof NextResponse) return principal;
 
-  const userRow = await queryOne<{ data: any }>(
+  const userRow = await queryOne<{ data: { email?: string } }>(
     `SELECT data FROM fs_users WHERE id = $1 LIMIT 1`,
     [principal.userId]
   );
@@ -64,7 +64,7 @@ export async function DELETE(request: Request, { params }: { params: Promise<{ i
   const principal = await requireWorkspacePrincipal(request);
   if (principal instanceof NextResponse) return principal;
 
-  const userRow = await queryOne<{ data: any }>(
+  const userRow = await queryOne<{ data: { email?: string } }>(
     `SELECT data FROM fs_users WHERE id = $1 LIMIT 1`,
     [principal.userId]
   );
diff --git a/vibn-frontend/app/api/chat/threads/route.ts b/vibn-frontend/app/api/chat/threads/route.ts
index c18ce52f..cffd62e2 100644
--- a/vibn-frontend/app/api/chat/threads/route.ts
+++ b/vibn-frontend/app/api/chat/threads/route.ts
@@ -57,7 +57,7 @@ export async function GET(request: Request) {
   const principal = await requireWorkspacePrincipal(request);
   if (principal instanceof NextResponse) return principal;
 
-  const userRow = await queryOne<{ data: any }>(
+  const userRow = await queryOne<{ data: { email?: string } }>(
     `SELECT data FROM fs_users WHERE id = $1 LIMIT 1`,
     [principal.userId]
   );
@@ -120,7 +120,7 @@ export async function POST(request: Request) {
   const principal = await requireWorkspacePrincipal(request);
   if (principal instanceof NextResponse) return principal;
 
-  const userRow = await queryOne<{ data: any }>(
+  const userRow = await queryOne<{ data: { email?: string } }>(
     `SELECT data FROM fs_users WHERE id = $1 LIMIT 1`,
     [principal.userId]
   );
diff --git a/vibn-frontend/lib/ai/gemini-chat.ts b/vibn-frontend/lib/ai/gemini-chat.ts
index d93513a9..c1ec1c75 100644
--- a/vibn-frontend/lib/ai/gemini-chat.ts
+++ b/vibn-frontend/lib/ai/gemini-chat.ts
@@ -155,6 +155,15 @@ export async function callGeminiChat(opts: {
       }
     }
 
+    // Empty-answer fallback: Gemini "thinking" responses can spend the whole
+    // turn emitting `thought` parts and return NO answer part — leaving `text`
+    // empty. Mirror the OpenAI-compatible adapter (which promotes
+    // reasoning_content when content is empty) so the user never gets a blank
+    // bubble. Only promote when there's also no tool call to render.
+    if (!text.trim() && thoughts.trim() && toolCalls.length === 0) {
+      text = thoughts.trim();
+    }
+
     return {
       text,
       thoughts,