1 Release published by 1 person

• v0.1.0

  published Jun 27, 2025

16 Pull requests merged by 12 people

• v0.1.0

  #963 merged Jun 27, 2025

• Add safety check handling for ComputerTool

  #923 merged Jun 27, 2025

• Add reasoning content - fix on #494

  #871 merged Jun 27, 2025

• Import Path Inconsistency

  #960 merged Jun 27, 2025

• Annotating the openai.Omit type so that ModelSettings can be serialized by pydantic

  #938 merged Jun 27, 2025

• Fix #944 by updating the models document page to cover extra_args

  #950 merged Jun 27, 2025

• Fix incorrect argument description in on_trace_end docstring

  #958 merged Jun 27, 2025

• Tweak in pyproject.toml

  #952 merged Jun 27, 2025

• feat: add MCP tool filtering support

  #861 merged Jun 27, 2025

• replace .py file with .ipynb for Jupyter example

  #262 merged Jun 27, 2025

• Fix and Document parallel_tool_calls Attribute in ModelSettings

  #763 merged Jun 27, 2025

• Add uv as an alternative Python environment setup option for issue #884

  #909 merged Jun 27, 2025

• fix: add ensure_ascii=False to json.dumps for correct Unicode output

  #639 merged Jun 27, 2025

• Duplicate Classifier in pyproject.toml

  #951 merged Jun 27, 2025

• Fix #892 by adding proper tool description in context.md

  #937 merged Jun 25, 2025

• Fix #604 Chat Completion model raises runtime error when response.choices is empty

  #935 merged Jun 25, 2025

14 Pull requests opened by 12 people

• Support Claude extended thinking

  #941 opened Jun 25, 2025

• Fix critical tracing module issues and improve reliability

  #962 opened Jun 27, 2025

• chore(vscode): upgrade .vscode/settings.json to full‑stack DX config

  #964 opened Jun 27, 2025

• symlink CLAUDE.md to AGENTS.md

  #965 opened Jun 27, 2025

• Fix CI workflow Create main.yml

  #969 opened Jun 29, 2025

• Create Readme.md

  #970 opened Jun 29, 2025

• Add logprobs

  #971 opened Jun 30, 2025

• Feat: separate tool_call_item and tool_call_output_item in stream events

  #974 opened Jun 30, 2025

• fix: MCP filtering, make agent and run ctx optional

  #977 opened Jun 30, 2025

• Add MCP Tools to visualization.

  #979 opened Jun 30, 2025

• Revert "Add is_enabled to handoffs (#925)"

  #982 opened Jul 1, 2025

• feat(agents): Add on_llm_start and on_llm_end Lifecycle Hooks

  #987 opened Jul 1, 2025

• avoid concat tool call delta id

  #990 opened Jul 2, 2025

• Create Security

  #994 opened Jul 2, 2025

17 Issues closed by 8 people

• chat completion model failed to produce multiple tool call items

  #989 closed Jul 2, 2025

• Open ai agent python

  #983 closed Jul 2, 2025

• docs/mcp.md

  #988 closed Jul 1, 2025

• Agent taking too long to return answers

  #961 closed Jun 30, 2025

• metadata retrieval not available by design?

  #852 closed Jun 30, 2025

• acknowledged_safety_checks during response

  #843 closed Jun 27, 2025

• How do I find token usage after running an Agent?

  #948 closed Jun 27, 2025

• Add "user" property from Reponses API for caching/tracking and abuse issues

  #944 closed Jun 27, 2025

• Guardrailing Tool calls

  #956 closed Jun 27, 2025

• parallel_tool_calls default is True in the client, despite docs saying False

  #762 closed Jun 27, 2025

• Add uv as well

  #884 closed Jun 27, 2025

• Unable to use tool calling when using Llama 4 scout via LiteLLM Proxy

  #723 closed Jun 27, 2025

• Max turns exceeded

  #844 closed Jun 27, 2025

• Best setup for tracing with Azure

  #846 closed Jun 27, 2025

• Empty assistant message after a hand-off

  #856 closed Jun 27, 2025

• Best practices for integrating Gradio's Agent and Tool

  #862 closed Jun 27, 2025

• [Bug]: SDK crashes when `choices` is `None` (provider-error payload)

  #604 closed Jun 25, 2025

25 Issues opened by 25 people

• Agent(name=…)

  #996 opened Jul 2, 2025

• Converter.items_to_messages cannot handle assistant message with both content and tool_calls

  #995 opened Jul 2, 2025

• Agent unable to perform multiple Web Searches by using WebSearchTool

  #993 opened Jul 2, 2025

• FunctionTool ignores strict_json_schema parameter

  #992 opened Jul 2, 2025

• Input guardrail tripwire allows tool execution to continue after exception is raised

  #991 opened Jul 2, 2025

• Error Using Gemini API Key with Agent-as-Tool Pattern in openai-agent-sdk

  #986 opened Jul 1, 2025

• Error "Item ‘rs_ABCD’ of type ‘reasoning’ was provided without its required..." when using CodeInterpreter

  #985 opened Jul 1, 2025

• Agent as a tool input_type

  #984 opened Jul 1, 2025

• Agent keep retrying until hit max_retires on function calling

  #981 opened Jul 1, 2025

• Function tool choice causing pydantic validation error

  #980 opened Jun 30, 2025

• Cannot run visualization

  #978 opened Jun 30, 2025

• [BUG]: MCP Server unecessarily requires use of Agent and RunContext

  #976 opened Jun 30, 2025

• Failed to run when trying the example financial_research_agent with qwen3

  #975 opened Jun 30, 2025

• Handoff to agent that uses websearch tool call fails. But works fine if agent is called as a tool

  #972 opened Jun 30, 2025

• pydantic_core._pydantic_core.ValidationError: 1 validation error for ResponseFunctionWebSearch action

  #968 opened Jun 29, 2025

• Pydantic requirements mismatch

  #967 opened Jun 28, 2025

• Agent streaming with guardrails issue

  #959 opened Jun 27, 2025

• Typed handoffs

  #955 opened Jun 27, 2025

• How to add multiple MCP servers in an Agent?

  #954 opened Jun 27, 2025

• Potentially Adding Citation feature button for Researchers

  #949 opened Jun 26, 2025

• Clarify how to filter final vs. intermediate generation events in streaming API

  #947 opened Jun 26, 2025

• MCPServerSse not able to connect to mcp server running within docker container

  #946 opened Jun 26, 2025

• Get exception raised in tool invocation

  #945 opened Jun 26, 2025

• Go version of the Agents SDK?

  #942 opened Jun 26, 2025

• Expose tool call arguments in RunHooks on_tool_start and on_tool_end

  #939 opened Jun 25, 2025

26 Unresolved conversations

Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.

• Add Sessions for Automatic Conversation History Management

  #752 commented on Jul 1, 2025 • 16 new comments

• Add on_start support to VoiceWorkflowBase and VoicePipeline

  #922 commented on Jun 27, 2025 • 2 new comments

• Added support for "return" handoffs (#1)

  #869 commented on Jun 30, 2025 • 0 new comments

• [Fix]: Get logger from tracing folder instead of agents folder

  #839 commented on Jun 28, 2025 • 0 new comments

• feat(tools): run sync tools in a thread to avoid event loop blocking

  #820 commented on Jul 1, 2025 • 0 new comments

• Add a new GH Actions job to automatically update translated document pagse

  #598 commented on Jul 1, 2025 • 0 new comments

• Support a callable model

  #312 commented on Jun 27, 2025 • 0 new comments

• Custom model provider ignored when using agents as tools

  #663 commented on Jul 2, 2025 • 0 new comments

• OpenAI SDK does not expose MCP session ID, making stateful streamable HTTP sessions impossible

  #924 commented on Jul 2, 2025 • 0 new comments

• Add reasoning support for custom models.

  #492 commented on Jul 1, 2025 • 0 new comments

• Missing Handling for `delta.reasoning_content` in `agents.models.chatcmpl_stream_handler.ChatCmplStreamHandler.handle_stream`

  #578 commented on Jul 1, 2025 • 0 new comments

• Yield reasoning delta in the response or add hooks to handle

  #825 commented on Jul 1, 2025 • 0 new comments

• Support Streaming of Function Call Arguments

  #834 commented on Jul 1, 2025 • 0 new comments

• When using the Azure LLM key and employing "Runner.run_streamed", the token usage returned is 0.

  #838 commented on Jul 1, 2025 • 0 new comments

• Error initializing MCP server: Connection closed

  #822 commented on Jul 1, 2025 • 0 new comments

• `output_type=List[str]` silently disables “thinking” in Qwen-3 (and similar models), cutting run-time by ~50 % compared with `output_type=str`

  #902 commented on Jun 30, 2025 • 0 new comments

• Human-In-The-Loop Architecture should be implemented on top priority!

  #636 commented on Jun 30, 2025 • 0 new comments

• How to service agents over HTTP

  #126 commented on Jun 30, 2025 • 0 new comments

• When will realtime capabilities be added like they are in the Typescript SDK?

  #894 commented on Jun 30, 2025 • 0 new comments

• SSL error for streaming voice terminal app

  #423 commented on Jun 29, 2025 • 0 new comments

• Tool calling with LiteLLM and thinking models fail

  #765 commented on Jun 29, 2025 • 0 new comments

• Add Session Memory

  #745 commented on Jun 27, 2025 • 0 new comments

• results field in Code Interpreter always returns None

  #917 commented on Jun 27, 2025 • 0 new comments

• Passing the Encoded image to @tool

  #883 commented on Jun 27, 2025 • 0 new comments

• Support for short‑term and long‑term memory in Agents SDK

  #887 commented on Jun 26, 2025 • 0 new comments

• Mem0ai integration as example for create memory agents

  #832 commented on Jun 26, 2025 • 0 new comments