From a11ba9710ca0624b4bc1c51385d5131e96d3ccbd Mon Sep 17 00:00:00 2001
From: Kevin Lin <klin5061@gmail.com>
Date: Fri, 27 Feb 2026 11:15:37 -0800
Subject: [PATCH] feat(core): increase Gemini timeout to 10 minutes (#9714)

---
 conf.yaml                         | 1 +
 letta/llm_api/google_ai_client.py | 6 +++---
 letta/settings.py                 | 1 +
 3 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/conf.yaml b/conf.yaml
index b3b2eb82..cbb160c8 100644
--- a/conf.yaml
+++ b/conf.yaml
@@ -260,6 +260,7 @@ model:
     base_url: https://generativelanguage.googleapis.com/
     force_minimum_thinking_budget: false
     max_retries: 5
+    timeout_seconds: 600.0
 
   # Google Vertex (-> GOOGLE_CLOUD_*)
   # google_cloud:
diff --git a/letta/llm_api/google_ai_client.py b/letta/llm_api/google_ai_client.py
index f765a121..c41d9b94 100644
--- a/letta/llm_api/google_ai_client.py
+++ b/letta/llm_api/google_ai_client.py
@@ -9,7 +9,7 @@ from letta.llm_api.google_constants import GOOGLE_MODEL_FOR_API_KEY_CHECK
 from letta.llm_api.google_vertex_client import GoogleVertexClient
 from letta.log import get_logger
 from letta.schemas.llm_config import LLMConfig
-from letta.settings import model_settings, settings
+from letta.settings import model_settings
 
 logger = get_logger(__name__)
 
@@ -18,7 +18,7 @@ class GoogleAIClient(GoogleVertexClient):
     provider_label = "Google AI"
 
     def _get_client(self, llm_config: Optional[LLMConfig] = None):
-        timeout_ms = int(settings.llm_request_timeout_seconds * 1000)
+        timeout_ms = int(model_settings.gemini_timeout_seconds * 1000)
         api_key = None
         if llm_config:
             api_key, _, _ = self.get_byok_overrides(llm_config)
@@ -30,7 +30,7 @@ class GoogleAIClient(GoogleVertexClient):
         )
 
     async def _get_client_async(self, llm_config: Optional[LLMConfig] = None):
-        timeout_ms = int(settings.llm_request_timeout_seconds * 1000)
+        timeout_ms = int(model_settings.gemini_timeout_seconds * 1000)
         api_key = None
         if llm_config:
             api_key, _, _ = await self.get_byok_overrides_async(llm_config)
diff --git a/letta/settings.py b/letta/settings.py
index 3f236099..aa316385 100644
--- a/letta/settings.py
+++ b/letta/settings.py
@@ -204,6 +204,7 @@ class ModelSettings(BaseSettings):
     gemini_base_url: str = "https://generativelanguage.googleapis.com/"
     gemini_force_minimum_thinking_budget: bool = False
     gemini_max_retries: int = 5
+    gemini_timeout_seconds: float = 600.0
 
     # google vertex
     google_cloud_project: Optional[str] = None