1 Release published by 1 person

• v0.2.2

  published Jul 17, 2025

12 Pull requests merged by 9 people

• Update all translated document pages

  #1184 merged Jul 18, 2025

• Fix image_generator example error on Windows OS

  #1180 merged Jul 18, 2025

• fix: Apply strict JSON schema validation in FunctionTool constructor

  #1041 merged Jul 18, 2025

• Mark some dataclasses as pydantic dataclasses

  #1131 merged Jul 18, 2025

• fix: fallback to function name for unnamed output_guardrail decorators

  #1133 merged Jul 18, 2025

• Add missing guardrail exception import to quickstart

  #1161 merged Jul 18, 2025

• fix: ensure ResponseUsage token fields are int, not None (fixes #1179)

  #1181 merged Jul 18, 2025

• Fix spelling, grammar, and minor formatting issues in running agents documentation

  #1128 merged Jul 18, 2025

• Update all translated document pages

  #1173 merged Jul 17, 2025

• [realtime] Add direct access to model layer from session

  #1172 merged Jul 17, 2025

• v0.2.2

  #1170 merged Jul 17, 2025

• Realtime: only update model settings from session

  #1169 merged Jul 17, 2025

8 Pull requests opened by 7 people

• feat: Add reasoning item handling to skip non-message content

  #1166 opened Jul 17, 2025

• Fix MCP tool name conflicts by adding server name prefixes

  #1178 opened Jul 18, 2025

• Realtime: add user agent header

  #1185 opened Jul 18, 2025

• docs(examples): use UserLocation dataclass in WebSearchTool example

  #1188 opened Jul 19, 2025

• Create pylint.yml

  #1189 opened Jul 19, 2025

• fix(mcp-server): assign original_name with type ignore and wrap long docstring

  #1190 opened Jul 19, 2025

• Feature: Make trace_include_sensitive_data configurable via environment variable

  #1192 opened Jul 19, 2025

• Add conditional tool enabling feature to agent as tool.

  #1193 opened Jul 20, 2025

14 Issues closed by 5 people

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

  #986 closed Jul 20, 2025

• Agent unable to perform multiple Web Searches by using WebSearchTool

  #993 closed Jul 20, 2025

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

  #995 closed Jul 20, 2025

• How should I handle when the response from MCP or some tool is JSON, which contains the base64 encoding of the file.

  #1001 closed Jul 20, 2025

• Tool Call Execution Problem with Structured Output

  #1012 closed Jul 20, 2025

• Passing Local Context to MCP Server Tools

  #1021 closed Jul 20, 2025

• Reasoning only coming before final output

  #1036 closed Jul 20, 2025

• Import error - MCPServer

  #1059 closed Jul 19, 2025

• Specifying `model_provider` for each `Agent`

  #1137 closed Jul 18, 2025

• xAI Grok 4 Usage

  #1056 closed Jul 18, 2025

• Anthropic Tool calls failing with litellm after update to 0.2.0

  #1147 closed Jul 18, 2025

• FunctionTool ignores strict_json_schema parameter

  #992 closed Jul 18, 2025

• Streaming: ResponseUsage validation error when token fields are None

  #1179 closed Jul 18, 2025

• Retreive context variables on MCP server

  #1175 closed Jul 18, 2025

8 Issues opened by 8 people

• Draft issue: Additional information needed

  #1187 opened Jul 19, 2025

• Suggestions for using user feedback as tools?

  #1186 opened Jul 18, 2025

• Add support for global or environment-based default for `trace_include_sensitive_data` in `RunConfig`

  #1183 opened Jul 18, 2025

• cannot use custom cert when connecting to server with MCPServerSse

  #1182 opened Jul 18, 2025

• [Question] Relationships between instructions, prompt, handoff, and input_type/output_type in openai-agent-sdk

  #1177 opened Jul 18, 2025

• tool_name and tool_description for Agent#as_tool() method

  #1174 opened Jul 17, 2025

• Realtime API with Multiple Tool Calls Results in No Voice Output

  #1168 opened Jul 17, 2025

• Please fix the issue where duplicate tool names in multiple MCP tools cause the agent list to hang

  #1167 opened Jul 17, 2025

16 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.

• from LangChain and Langgraph to openai-agents

  #128 commented on Jul 17, 2025 • 0 new comments

• Prevent Token Wastage When Input Guardrails Delay Error Generation

  #867 commented on Jul 17, 2025 • 0 new comments

• items_to_messages method not handle "ResponseReasoningItemParam"

  #1165 commented on Jul 17, 2025 • 0 new comments

• Unhandled item type or structure with resoning item

  #1164 commented on Jul 17, 2025 • 0 new comments

• No OpenAI tracing with Azure Foundry models

  #1051 commented on Jul 18, 2025 • 0 new comments

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

  #972 commented on Jul 18, 2025 • 0 new comments

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

  #787 commented on Jul 18, 2025 • 0 new comments

• Tool Call Results are not Appearing in Realtime API and Tool Calls are Not Showing Up in Tracing

  #1156 commented on Jul 18, 2025 • 0 new comments

• Function tool choice causing pydantic validation error

  #980 commented on Jul 19, 2025 • 0 new comments

• agents.exceptions.UserError: Unhandled item type or structure when use reasoning model with tool call.

  #1004 commented on Jul 19, 2025 • 0 new comments

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

  #839 commented on Jul 17, 2025 • 0 new comments

• Feat: separate tool_call_item and tool_call_output_item in stream events

  #974 commented on Jul 18, 2025 • 0 new comments

• Add MCP Tools to visualization.

  #979 commented on Jul 19, 2025 • 0 new comments

• Added runtime validation for Agent name field

  #998 commented on Jul 18, 2025 • 0 new comments

• Add automation script to generate mkdocstrings files

  #1048 commented on Jul 19, 2025 • 0 new comments

• Initial pass at PostgreSQL session management

  #1163 commented on Jul 18, 2025 • 0 new comments