Merge pull request #32 from openai/rm/sdk_bump

Bump open AI sdk version
pin to openai 1.66.2, update tests
make computer use example less verbose

Author: rm-openai

examples/tools/computer_use.py

@@ -1,6 +1,5 @@
 import asyncio
 import base64
-import logging
 from typing import Literal, Union
 
 from playwright.async_api import Browser, Page, Playwright, async_playwright
@@ -16,8 +15,10 @@
     trace,
 )
 
-logging.getLogger("openai.agents").setLevel(logging.DEBUG)
-logging.getLogger("openai.agents").addHandler(logging.StreamHandler())
+# Uncomment to see very verbose logs
+# import logging
+# logging.getLogger("openai.agents").setLevel(logging.DEBUG)
+# logging.getLogger("openai.agents").addHandler(logging.StreamHandler())
 
 
 async def main():

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "openai-agents"
-version = "0.0.2"
+version = "0.0.3"
 description = "OpenAI Agents SDK"
 readme = "README.md"
 requires-python = ">=3.9"
@@ -9,7 +9,7 @@ authors = [
     { name = "OpenAI", email = "support@openai.com" },
 ]
 dependencies = [
-    "openai>=1.66.0",
+    "openai>=1.66.2",
     "pydantic>=2.10, <3",
     "griffe>=1.5.6, <2",
     "typing-extensions>=4.12.2, <5",

src/agents/_run_impl.py

@@ -23,7 +23,7 @@
     ActionWait,
 )
 from openai.types.responses.response_input_param import ComputerCallOutput
-from openai.types.responses.response_output_item import Reasoning
+from openai.types.responses.response_reasoning_item import ResponseReasoningItem
 
 from . import _utils
 from .agent import Agent
@@ -288,7 +288,7 @@ def process_model_response(
                 items.append(ToolCallItem(raw_item=output, agent=agent))
             elif isinstance(output, ResponseFunctionWebSearch):
                 items.append(ToolCallItem(raw_item=output, agent=agent))
-            elif isinstance(output, Reasoning):
+            elif isinstance(output, ResponseReasoningItem):
                 items.append(ReasoningItem(raw_item=output, agent=agent))
             elif isinstance(output, ResponseComputerToolCall):
                 items.append(ToolCallItem(raw_item=output, agent=agent))

src/agents/items.py

@@ -19,7 +19,7 @@
     ResponseStreamEvent,
 )
 from openai.types.responses.response_input_item_param import ComputerCallOutput, FunctionCallOutput
-from openai.types.responses.response_output_item import Reasoning
+from openai.types.responses.response_reasoning_item import ResponseReasoningItem
 from pydantic import BaseModel
 from typing_extensions import TypeAlias
 
@@ -136,10 +136,10 @@ class ToolCallOutputItem(RunItemBase[Union[FunctionCallOutput, ComputerCallOutpu
 
 
 @dataclass
-class ReasoningItem(RunItemBase[Reasoning]):
+class ReasoningItem(RunItemBase[ResponseReasoningItem]):
     """Represents a reasoning item."""
 
-    raw_item: Reasoning
+    raw_item: ResponseReasoningItem
     """The raw reasoning item."""
 
     type: Literal["reasoning_item"] = "reasoning_item"

src/agents/models/openai_responses.py

@@ -361,7 +361,7 @@ def _convert_tool(cls, tool: Tool) -> tuple[ToolParam, IncludeLiteral | None]:
             includes = "file_search_call.results" if tool.include_search_results else None
         elif isinstance(tool, ComputerTool):
             converted_tool = {
-                "type": "computer-preview",
+                "type": "computer_use_preview",
                 "environment": tool.computer.environment,
                 "display_width": tool.computer.dimensions[0],
                 "display_height": tool.computer.dimensions[1],

src/agents/tool.py

@@ -284,3 +284,5 @@ def decorator(real_func: ToolFunction[...]) -> FunctionTool:
         return _create_function_tool(real_func)
 
     return decorator
+    return decorator
+    return decorator

tests/test_items_helpers.py

@@ -13,12 +13,12 @@
 from openai.types.responses.response_function_tool_call_param import ResponseFunctionToolCallParam
 from openai.types.responses.response_function_web_search import ResponseFunctionWebSearch
 from openai.types.responses.response_function_web_search_param import ResponseFunctionWebSearchParam
-from openai.types.responses.response_input_item_param import Reasoning as ReasoningInputParam
-from openai.types.responses.response_output_item import Reasoning, ReasoningContent
 from openai.types.responses.response_output_message import ResponseOutputMessage
 from openai.types.responses.response_output_message_param import ResponseOutputMessageParam
 from openai.types.responses.response_output_refusal import ResponseOutputRefusal
 from openai.types.responses.response_output_text import ResponseOutputText
+from openai.types.responses.response_reasoning_item import ResponseReasoningItem, Summary
+from openai.types.responses.response_reasoning_item_param import ResponseReasoningItemParam
 
 from agents import (
     Agent,
@@ -129,7 +129,7 @@ def test_text_message_outputs_across_list_of_runitems() -> None:
     item1: RunItem = MessageOutputItem(agent=Agent(name="test"), raw_item=message1)
     item2: RunItem = MessageOutputItem(agent=Agent(name="test"), raw_item=message2)
     # Create a non-message run item of a different type, e.g., a reasoning trace.
-    reasoning = Reasoning(id="rid", content=[], type="reasoning")
+    reasoning = ResponseReasoningItem(id="rid", summary=[], type="reasoning")
     non_message_item: RunItem = ReasoningItem(agent=Agent(name="test"), raw_item=reasoning)
     # Confirm only the message outputs are concatenated.
     assert ItemHelpers.text_message_outputs([item1, non_message_item, item2]) == "foobar"
@@ -266,16 +266,18 @@ def test_to_input_items_for_computer_call_click() -> None:
 
 def test_to_input_items_for_reasoning() -> None:
     """A reasoning output should produce the same dict as a reasoning input item."""
-    rc = ReasoningContent(text="why", type="reasoning_summary")
-    reasoning = Reasoning(id="rid1", content=[rc], type="reasoning")
+    rc = Summary(text="why", type="summary_text")
+    reasoning = ResponseReasoningItem(id="rid1", summary=[rc], type="reasoning")
     resp = ModelResponse(output=[reasoning], usage=Usage(), referenceable_id=None)
     input_items = resp.to_input_items()
     assert isinstance(input_items, list) and len(input_items) == 1
     converted_dict = input_items[0]
 
-    expected: ReasoningInputParam = {
+    expected: ResponseReasoningItemParam = {
         "id": "rid1",
-        "content": [{"text": "why", "type": "reasoning_summary"}],
+        "summary": [{"text": "why", "type": "summary_text"}],
         "type": "reasoning",
     }
+    print(converted_dict)
+    print(expected)
     assert converted_dict == expected

tests/test_openai_responses_converter.py

@@ -163,7 +163,7 @@ def drag(self, path: list[tuple[int, int]]) -> None:
     assert "function" in types
     assert "file_search" in types
     assert "web_search_preview" in types
-    assert "computer-preview" in types
+    assert "computer_use_preview" in types
     # Verify file search tool contains max_num_results and vector_store_ids
     file_params = next(ct for ct in converted.tools if ct["type"] == "file_search")
     assert file_params.get("max_num_results") == file_tool.max_num_results
@@ -173,7 +173,7 @@ def drag(self, path: list[tuple[int, int]]) -> None:
     assert web_params.get("user_location") == web_tool.user_location
     assert web_params.get("search_context_size") == web_tool.search_context_size
     # Verify computer tool contains environment and computed dimensions
-    comp_params = next(ct for ct in converted.tools if ct["type"] == "computer-preview")
+    comp_params = next(ct for ct in converted.tools if ct["type"] == "computer_use_preview")
     assert comp_params.get("environment") == "mac"
     assert comp_params.get("display_width") == 800
     assert comp_params.get("display_height") == 600

tests/test_run_step_processing.py

@@ -7,7 +7,7 @@
     ResponseFunctionWebSearch,
 )
 from openai.types.responses.response_computer_tool_call import ActionClick
-from openai.types.responses.response_output_item import Reasoning, ReasoningContent
+from openai.types.responses.response_reasoning_item import ResponseReasoningItem, Summary
 from pydantic import BaseModel
 
 from agents import (
@@ -287,8 +287,8 @@ def test_function_web_search_tool_call_parsed_correctly():
 def test_reasoning_item_parsed_correctly():
     # Verify that a Reasoning output item is converted into a ReasoningItem.
 
-    reasoning = Reasoning(
-        id="r1", type="reasoning", content=[ReasoningContent(text="why", type="reasoning_summary")]
+    reasoning = ResponseReasoningItem(
+        id="r1", type="reasoning", summary=[Summary(text="why", type="summary_text")]
     )
     response = ModelResponse(
         output=[reasoning],