Overview

9 Pull requests merged by8 people

• Add comment to handoff_occured misspelling

  #792 mergedMay 30, 2025

• docs: fix typo in docstring for is_strict_json_schema method

  #775 mergedMay 30, 2025

• Update input_guardrails.py

  #774 mergedMay 30, 2025

• Fix typo: Replace 'two' with 'three' in /docs/mcp.md

  #757 mergedMay 30, 2025

• Fix typo in assertion message for handoff function

  #780 mergedMay 30, 2025

• Small fix for litellm model

  #789 mergedMay 30, 2025

• Fixed Python syntax

  #665 mergedMay 29, 2025

• Added RunErrorDetails object for MaxTurnsExceeded exception

  #743 mergedMay 29, 2025

• Add Portkey AI as a tracing provider

  #785 mergedMay 29, 2025

4 Pull requests opened by4 people

• Fix and Document `parallel_tool_calls` Attribute in ModelSettings

  #763 openedMay 26, 2025

• Added support for passing tool_call_id via the RunContextWrapper

  #766 openedMay 27, 2025

• grammar fix

  #790 openedMay 30, 2025

• Add `exclude_params` feature to `function_tool` for hidden parameter injection

  #795 openedMay 30, 2025

11 Issues closed by5 people

• How to use openai-agents to call text2image API?

  #725 closedJun 1, 2025

• How to integrate audio input in agent sdk? (not realtime or voice pipeline, e.g., gpt-4o audio)

  #738 closedJun 1, 2025

• @function_tool bug?

  #794 closedMay 30, 2025

• agents.WebSearchTool bug

  #788 closedMay 30, 2025

• Add Portkey AI as tracing Provider in docs

  #786 closedMay 29, 2025

• Tracing client error 400 (MCP)

  #710 closedMay 29, 2025

• Ba

  #755 closedMay 27, 2025

• MCP Stdio- Hosted tools are not supported with the ChatCompletions API

  #761 closedMay 26, 2025

• How to pass hardcoded dynamic messages as agent's responses in the chat history ?

  #695 closedMay 26, 2025

• litellm proxy with openai-agents

  #696 closedMay 26, 2025

• How to pass reasoning=generate_summary for ComputerTool Agent?

  #698 closedMay 26, 2025

23 Issues opened by22 people

• Is it possible to use both local tools and mcp server tools?

  #797 openedMay 31, 2025

• Background thread is created on library import

  #796 openedMay 31, 2025

• SDK support for retrieving historical traces

  #793 openedMay 30, 2025

• Parallel Tool Calling: Q/Bug?

  #791 openedMay 30, 2025

• Processing image/ multi modal responses in function tool results?

  #787 openedMay 29, 2025

• [Feature Request] Add REPL-style `run_demo_loop` utility for rapid agent testing and debugging

  #784 openedMay 29, 2025

• web_search_preview tool call is not limited by max_turns option

  #783 openedMay 29, 2025

• Rate Limit Support

  #782 openedMay 28, 2025

• Misleading Assertion Logic and Message for on_handoff/input_type in `handoff()` function at `agents/handoffs.py`

  #781 openedMay 28, 2025

• Return an image from an MCP tool call and pass it to LLM

  #779 openedMay 28, 2025

• web_search_preview never triggers agents.lifecycle.AgentHooks.on_tool_start

  #778 openedMay 28, 2025

• Unexpected output type, ignoring: <class 'openai.types.responses.response_output_item.McpCall'>

  #777 openedMay 28, 2025

• Always access the OpenAI platform when using the DeepSeek model with LitellmModel

  #773 openedMay 28, 2025

• Bug: Pydantic Warnings and `.final_output` Serialization Issue with Code Interpreter File Citations

  #772 openedMay 28, 2025

• Only 1 handoff getting called no matter what

  #771 openedMay 28, 2025

• function_tool calling - agents orchertratins

  #769 openedMay 27, 2025

• Agents Reproducibility - seed ? top_p=0?

  #768 openedMay 27, 2025

• How to dynamically add/remove tools in a `tool_use_behavior="run_llm_again"`-loop

  #767 openedMay 27, 2025

• Tool calling with LiteLLM and thinking models fail

  #765 openedMay 27, 2025

• How to implement handoff between parents and children agents in different paths

  #764 openedMay 27, 2025

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

  #762 openedMay 26, 2025

• ValidationError` from `InputTokensDetails` when using `LitellmModel` with `None` cached\_tokens

  #760 openedMay 26, 2025

• LiteLLM + Gemini 2.5 Pro: cached_tokens=None crashes Agents SDK with Pydantic int-validation error

  #758 openedMay 26, 2025

27 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 onMay 31, 2025 • 7 new comments

• docs: fix output guardrail step description

  #724 commented onMay 30, 2025 • 0 new comments

• Make Runner an abstract base class

  #720 commented onJun 1, 2025 • 0 new comments

• visualize the complete Agent Loop with an interactive UML

  #713 commented onMay 29, 2025 • 0 new comments

• Create The moon dev

  #709 commented onMay 28, 2025 • 0 new comments

• docs: Enhance fetch_user_age tool: include UID and correct output format

  #702 commented onMay 26, 2025 • 0 new comments

• docs: Fix context example syntax and improve clarity

  #700 commented onMay 26, 2025 • 0 new comments

• Fix incorrect and ambiguous guardrail documentation: Input/Output Guardrails and agent sequencing

  #699 commented onMay 26, 2025 • 0 new comments

• docs: Fix Guardrail intro to include output validation

  #697 commented onMay 26, 2025 • 0 new comments

• Added support for gpt4o-realtime models for Speect to Speech interactions

  #659 commented onMay 29, 2025 • 0 new comments

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

  #636 commented onJun 1, 2025 • 0 new comments

• Input format in agent as tool

  #655 commented onJun 1, 2025 • 0 new comments

• PyCharm Fails to Recognize Agent Constructor Arguments (v0.0.15)

  #712 commented onJun 1, 2025 • 0 new comments

• Can't implement guardrails with litellm

  #740 commented onJun 1, 2025 • 0 new comments

• Add Session Memory

  #745 commented onMay 31, 2025 • 0 new comments

• Will session memory be implemented in the future?

  #748 commented onMay 31, 2025 • 0 new comments

• How would I handoff a non-reasoning model with tool calls to a reasoning model?

  #722 commented onMay 30, 2025 • 0 new comments

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

  #604 commented onMay 30, 2025 • 0 new comments

• Streaming Output issue got unnecesory text in output

  #753 commented onMay 30, 2025 • 0 new comments

• Unable to use reasoning models with tool calls using LitellmModel

  #678 commented onMay 30, 2025 • 0 new comments

• Why does the Computer protocol not have the goto method?

  #547 commented onMay 29, 2025 • 0 new comments

• Best practices for long running tools?

  #295 commented onMay 29, 2025 • 0 new comments

• How to provide resources with a MCP server?

  #676 commented onMay 27, 2025 • 0 new comments

• Issue with Multi-turn Handoff and Slot Filling

  #741 commented onMay 27, 2025 • 0 new comments

• Enhance `on_tool_start` Hook to Include Tool Call Arguments

  #252 commented onMay 26, 2025 • 0 new comments

• Cannot get the last tool_call_output event in stream_events when MaxTurnsExceeded

  #526 commented onMay 26, 2025 • 0 new comments

• How to pass the control back to triage agent

  #714 commented onMay 26, 2025 • 0 new comments