grasp_agents 0.2.8__tar.gz → 0.2.10__tar.gz

{grasp_agents-0.2.8 → grasp_agents-0.2.10}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: grasp_agents
-Version: 0.2.8
+Version: 0.2.10
 Summary: Grasp Agents Library
 License-File: LICENSE.md
 Requires-Python: <4,>=3.11.4

{grasp_agents-0.2.8 → grasp_agents-0.2.10}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "grasp_agents"
-version = "0.2.8"
+version = "0.2.10"
 description = "Grasp Agents Library"
 readme = "README.md"
 requires-python = ">=3.11.4,<4"

{grasp_agents-0.2.8 → grasp_agents-0.2.10}/src/grasp_agents/cloud_llm.py

@@ -153,8 +153,7 @@ class CloudLLM(LLM[SettingsT, ConvertT], Generic[SettingsT, ConvertT]):
             and not self._struct_output_support
         ):
             raise ValueError(
-                f"Model {api_provider}:{self._model_name} does "
-                "not support structured outputs."
+                f"Model {self._model_name} does not support structured outputs."
             )
 
         self._rate_limiter: RateLimiterC[Conversation, AssistantMessage] | None = (

{grasp_agents-0.2.8 → grasp_agents-0.2.10}/src/grasp_agents/costs_dict.yaml

@@ -1,8 +1,32 @@
 costs:
-  google/gemini-2.5-flash-preview:
+  gemini-2.5-pro-preview-05-06:
+    input: 1.25
+    output: 10
+    cached_discount: 0.5
+  google/gemini-2.5-pro-preview:
+    input: 1.25
+    output: 10
+    cached_discount: 0.5
+  gemini-2.5-flash-preview-05-20:
     input: 0.15
     output: 0.60
     cached_discount: 0.5
+  google/gemini-2.5-flash-preview-05-20:
+    input: 0.15
+    output: 0.60
+    cached_discount: 0.5
+  gemini-1.5-pro:
+    input: 1.25
+    output: 5
+    cached_discount: 0.5
+  gemini-2.0-flash:
+    input: 0.1
+    output: 0.4
+    cached_discount: 0.5
+  google/gemini-2.0-flash-001:
+    input: 0.1
+    output: 0.4
+    cached_discount: 0.5
   gpt-4.1:
     input: 2.0
     output: 8.0
@@ -19,26 +43,10 @@ costs:
     input: 2.0
     output: 8.0
     cached_discount: 0.5
-  google/gemini-2.5-pro-preview-03-25:
-    input: 1.25
-    output: 10
-    cached_discount: 0.5
-  gemini-2.5-pro-preview-03-25:
-    input: 1.25
-    output: 10
-    cached_discount: 0.5
   llama-3.3-70b-versatile:
     input: 0.59
     output: 0.79
     cached_discount: 0.5
-  gemini-1.5-pro:
-    input: 1.25
-    output: 5
-    cached_discount: 0.5
-  gemini-2.0-flash:
-    input: 0.1
-    output: 0.4
-    cached_discount: 0.5
   anthropic/claude-3.5-sonnet:
     input: 3.0
     output: 15
@@ -47,9 +55,9 @@ costs:
     input: 3.0
     output: 15
     cached_discount: 0.5
-  google/gemini-2.0-flash-001:
-    input: 0.1
-    output: 0.4
+  anthropic/claude-sonnet-4:
+    input: 3.0
+    output: 15
     cached_discount: 0.5
   deepseek/deepseek-chat:
     input: 0.4

{grasp_agents-0.2.8 → grasp_agents-0.2.10}/src/grasp_agents/openai/openai_llm.py

@@ -1,5 +1,5 @@
 import logging
-from collections.abc import Iterable
+from collections.abc import Iterable, Mapping
 from copy import deepcopy
 from typing import Any, Literal
 
@@ -67,7 +67,7 @@ class OpenAILLM(CloudLLM[OpenAILLMSettings, OpenAIConverters]):
         model_id: str | None = None,
         llm_settings: OpenAILLMSettings | None = None,
         tools: list[BaseTool[BaseModel, Any, Any]] | None = None,
-        response_format: type | None = None,
+        response_format: type | Mapping[str, type] | None = None,
         # Connection settings
         async_http_client_params: (
             dict[str, Any] | AsyncHTTPClientParams | None