Fimeg/letta-server
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

feat(core): increase Gemini timeout to 10 minutes (#9714)

Browse Source
This commit is contained in:
Kevin Lin
2026-02-27 11:15:37 -08:00
committed by Caren Thomas
parent ab784e702d
commit a11ba9710c
3 changed files with 5 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
conf.yaml
View File

@@ -260,6 +260,7 @@ model:
base_url: https://generativelanguage.googleapis.com/ base_url: https://generativelanguage.googleapis.com/
force_minimum_thinking_budget: false force_minimum_thinking_budget: false
max_retries: 5 max_retries: 5
timeout_seconds: 600.0
# Google Vertex (-> GOOGLE_CLOUD_*) # Google Vertex (-> GOOGLE_CLOUD_*)
# google_cloud: # google_cloud:

6
letta/llm_api/google_ai_client.py
View File

@@ -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.llm_api.google_vertex_client import GoogleVertexClient
from letta.log import get_logger from letta.log import get_logger
from letta.schemas.llm_config import LLMConfig from letta.schemas.llm_config import LLMConfig
from letta.settings import model_settings, settings from letta.settings import model_settings
logger = get_logger(__name__) logger = get_logger(__name__)
@@ -18,7 +18,7 @@ class GoogleAIClient(GoogleVertexClient):
provider_label = "Google AI" provider_label = "Google AI"
def _get_client(self, llm_config: Optional[LLMConfig] = None): 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 api_key = None
if llm_config: if llm_config:
api_key, _, _ = self.get_byok_overrides(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): 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 api_key = None
if llm_config: if llm_config:
api_key, _, _ = await self.get_byok_overrides_async(llm_config) api_key, _, _ = await self.get_byok_overrides_async(llm_config)

1
letta/settings.py
View File

@@ -204,6 +204,7 @@ class ModelSettings(BaseSettings):
gemini_base_url: str = "https://generativelanguage.googleapis.com/" gemini_base_url: str = "https://generativelanguage.googleapis.com/"
gemini_force_minimum_thinking_budget: bool = False gemini_force_minimum_thinking_budget: bool = False
gemini_max_retries: int = 5 gemini_max_retries: int = 5
gemini_timeout_seconds: float = 600.0
# google vertex # google vertex
google_cloud_project: Optional[str] = None google_cloud_project: Optional[str] = None