From e8c0257ea656c3b3fdb2d846261429ab92c9e54b Mon Sep 17 00:00:00 2001
From: Vadym Samoilenko <vadymsamoilenko@oliver.agency>
Date: Mon, 2 Mar 2026 12:42:04 +0000
Subject: [PATCH] Add timeouts to Gemini API calls to prevent 10+ minute hangs

Primary model (gemini-3.1-pro-preview): 45s timeout
Fallback model (gemini-3-flash-preview): 60s timeout

Without timeouts, the fallback model under high load would wait
indefinitely, causing analysis to hang for 10+ minutes per file.
asyncio.TimeoutError from the primary model is now handled the same
as other exceptions (falls through to fallback).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---
 backend/app/services/gemini_service.py | 30 ++++++++++++++++++++------
 1 file changed, 23 insertions(+), 7 deletions(-)

diff --git a/backend/app/services/gemini_service.py b/backend/app/services/gemini_service.py
index 14b7752..7d80e2d 100755
--- a/backend/app/services/gemini_service.py
+++ b/backend/app/services/gemini_service.py
@@ -1,3 +1,4 @@
+import asyncio
 import json
 import logging
 from typing import List, Tuple
@@ -10,6 +11,10 @@ from app.models.schemas import SubReview, RagStatus
 # Configure logging
 logger = logging.getLogger(__name__)
 
+# Timeout (seconds) for each Gemini API call
+_PRIMARY_TIMEOUT = 45
+_FALLBACK_TIMEOUT = 60
+
 
 class GeminiService:
     """Service wrapper for Google Gemini API calls."""
@@ -26,23 +31,34 @@ class GeminiService:
         self.fallback_model = "gemini-3-flash-preview"
 
     async def _generate_content(self, contents, config) -> any:
-        """Call generate_content, falling back to fallback_model if the primary fails."""
+        """Call generate_content, falling back to fallback_model if the primary fails or times out."""
         try:
-            return await self.client.aio.models.generate_content(
-                model=self.model,
-                contents=contents,
-                config=config,
+            return await asyncio.wait_for(
+                self.client.aio.models.generate_content(
+                    model=self.model,
+                    contents=contents,
+                    config=config,
+                ),
+                timeout=_PRIMARY_TIMEOUT,
+            )
+        except asyncio.TimeoutError:
+            logger.warning(
+                f"[GEMINI API] Primary model {self.model} timed out after {_PRIMARY_TIMEOUT}s. "
+                f"Retrying with fallback {self.fallback_model}"
             )
         except Exception as e:
             logger.warning(
                 f"[GEMINI API] Primary model {self.model} failed: {e}. "
                 f"Retrying with fallback {self.fallback_model}"
             )
-            return await self.client.aio.models.generate_content(
+        return await asyncio.wait_for(
+            self.client.aio.models.generate_content(
                 model=self.fallback_model,
                 contents=contents,
                 config=config,
-            )
+            ),
+            timeout=_FALLBACK_TIMEOUT,
+        )
 
     async def analyze_with_image(
         self,