letta-nightly 0.7.0.dev20250422104203__tar.gz → 0.7.0.dev20250423003112__tar.gz

{letta_nightly-0.7.0.dev20250422104203 → letta_nightly-0.7.0.dev20250423003112}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: letta-nightly
-Version: 0.7.0.dev20250422104203
+Version: 0.7.0.dev20250423003112
 Summary: Create LLM agents with long-term memory and custom tools
 License: Apache License
 Author: Letta Team

{letta_nightly-0.7.0.dev20250422104203 → letta_nightly-0.7.0.dev20250423003112}/letta/llm_api/google_vertex_client.py

@@ -2,7 +2,7 @@ import uuid
 from typing import List, Optional
 
 from google import genai
-from google.genai.types import FunctionCallingConfig, FunctionCallingConfigMode, GenerateContentResponse, ToolConfig
+from google.genai.types import FunctionCallingConfig, FunctionCallingConfigMode, GenerateContentResponse, ThinkingConfig, ToolConfig
 
 from letta.helpers.datetime_helpers import get_utc_time
 from letta.helpers.json_helpers import json_dumps
@@ -60,6 +60,15 @@ class GoogleVertexClient(GoogleAIClient):
         )
         request_data["config"]["tool_config"] = tool_config.model_dump()
 
+        # Add thinking_config
+        # If enable_reasoner is False, set thinking_budget to 0
+        # Otherwise, use the value from max_reasoning_tokens
+        thinking_budget = 0 if not self.llm_config.enable_reasoner else self.llm_config.max_reasoning_tokens
+        thinking_config = ThinkingConfig(
+            thinking_budget=thinking_budget,
+        )
+        request_data["config"]["thinking_config"] = thinking_config.model_dump()
+
         return request_data
 
     def convert_response_to_chat_completion(

{letta_nightly-0.7.0.dev20250422104203 → letta_nightly-0.7.0.dev20250423003112}/letta/schemas/llm_config.py

@@ -72,7 +72,7 @@ class LLMConfig(BaseModel):
         description="The reasoning effort to use when generating text reasoning models",
     )
     max_reasoning_tokens: int = Field(
-        0, description="Configurable thinking budget for extended thinking, only used if enable_reasoner is True. Minimum value is 1024."
+        0, description="Configurable thinking budget for extended thinking. Used for enable_reasoner and also for Google Vertex models like Gemini 2.5 Flash. Minimum value is 1024 when used with enable_reasoner."
     )
 
     # FIXME hack to silence pydantic protected namespace warning

{letta_nightly-0.7.0.dev20250422104203 → letta_nightly-0.7.0.dev20250423003112}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "letta-nightly"
-version = "0.7.0.dev20250422104203"
+version = "0.7.0.dev20250423003112"
 packages = [
     {include = "letta"},
 ]