1 Release published by 1 person

• v0.2.4

  published Jul 29, 2025

37 Pull requests merged by 15 people

• Add functionality to update agent during realtime session

  #1366 merged Aug 4, 2025

• Fix docstring formatting and add safe check for empty message content

  #1360 merged Aug 3, 2025

• Fix style and wording issues in handoffs.py

  #1356 merged Aug 3, 2025

• Fix type annotation and clarify tool behavior docs

  #1355 merged Aug 3, 2025

• Fix #980 Chat Completions: fails with function name for tool_choice parameter w/ streaming enabled

  #1206 merged Aug 1, 2025

• Fix #1277 missing StopAtTools and ToolsToFinalOutputFunction in agents module

  #1278 merged Aug 1, 2025

• Clarify shallow-copy behavior of tools and handoffs in Agent.clone()

  #1296 merged Aug 1, 2025

• Feat: separate tool_call_item and tool_call_output_item in stream events

  #974 merged Aug 1, 2025

• Fix(mcp): Unreachable structured content branch in invoke_mcp_tool

  #1250 merged Aug 1, 2025

• Handle processor exceptions and fix tracing log formatting

  #1292 merged Aug 1, 2025

• Update all translated document pages

  #1341 merged Aug 1, 2025

• Fix set_api_key breaking cached property mechanism

  #1339 merged Aug 1, 2025

• docs: Clarify and enhance run_demo_loop utility documentation for beginners

  #1330 merged Aug 1, 2025

• Update all translated document pages

  #1336 merged Aug 1, 2025

• Add tracing guide for non-OpenAI LLMs in docs/tracing.md

  #1329 merged Aug 1, 2025

• Export MultiProvider in public API (Fix #1325)

  #1326 merged Jul 31, 2025

• Realtime: make example customizable:

  #1332 merged Jul 31, 2025

• Update all translated document pages

  #1322 merged Jul 31, 2025

• Enhance exception guide in docs

  #1321 merged Jul 31, 2025

• Examples: use agent to interact with Remote PDF Documents

  #1319 merged Jul 31, 2025

• Update all translated document pages

  #1313 merged Jul 30, 2025

• Add support to realtime API for setting "speed" of the models responses

  #1309 merged Jul 30, 2025

• Fix #1238 by enhancing HandoffInputData and enable passing async functions

  #1302 merged Jul 30, 2025

• Add temporal demo to docs

  #1310 merged Jul 30, 2025

• Update all translated document pages

  #1308 merged Jul 30, 2025

• Fix tag errors in sessions document page

  #1307 merged Jul 30, 2025

• v0.2.4

  #1301 merged Jul 29, 2025

• Realtime: forward all raw model events

  #1252 merged Jul 29, 2025

• Realtime: Twilio example

  #1216 merged Jul 29, 2025

• Realtime: only cancel response if necessary

  #1243 merged Jul 29, 2025

• Realtime: enable a playback tracker

  #1242 merged Jul 29, 2025

• Update all translated document pages

  #1291 merged Jul 29, 2025

• Enhance Tool Behavior Documentation for Developer Clarity With Examples

  #1286 merged Jul 29, 2025

• examples: minor tweak on llm_as_a_judge example

  #1284 merged Jul 29, 2025

• Update all translated document pages

  #1289 merged Jul 29, 2025

• Fix _export_batches docstring to remove incorrect "threshold" reference

  #1287 merged Jul 28, 2025

• docs: fix UserContext example

  #1280 merged Jul 28, 2025

5 Pull requests opened by 4 people

• Allow to pass both session and input list

  #1298 opened Jul 29, 2025

• Fix: Emit tool_called events immediately in streaming runs

  #1300 opened Jul 29, 2025

• docs: Add a comprehensive example for handling function tool errors.

  #1354 opened Aug 2, 2025

• Add SQLAlchemy session backend for conversation history management

  #1357 opened Aug 3, 2025

• Mongodb memory session

  #1364 opened Aug 4, 2025

27 Issues closed by 10 people

• How can I connect an internally deployed custom model API to the OpenAI agents SDK?

  #1223 closed Aug 4, 2025

• RealtimeAgent: how to get the model to greet the caller to start the conversation?

  #1265 closed Aug 3, 2025

• as_tool Only Executes at Agent Level, Not During Runner Execution

  #1194 closed Aug 3, 2025

• Agent.name accepts non-str types despite docs specifying str

  #1351 closed Aug 2, 2025

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

  #1177 closed Aug 2, 2025

• Citations/Annotations Lost When Using LitellmModel with Perplexity Models

  #1345 closed Aug 1, 2025

• Chat Completions: fails with function name for tool_choice parameter w/ streaming enabled

  #980 closed Aug 1, 2025

• Improve tool_use_behavior documentation: Clarify import paths for StopAtTools and ToolsToFinalOutputFunction

  #1277 closed Aug 1, 2025

• Clarify Copy Type for tools and handoffs in Agent.clone() Documentation

  #1293 closed Aug 1, 2025

• invoke_mcp_tool behavior clarification for use_structured_content

  #1236 closed Aug 1, 2025

• Including Conversation History in a Gradio Chat Function

  #1338 closed Aug 1, 2025

• Run Notion MCP

  #1195 closed Aug 1, 2025

• MultiProvider not exported in public API but used as default in RunConfig

  #1325 closed Jul 31, 2025

• Bug: Unclear Docs for Tracing with Non-OpenAI LLMs

  #1327 closed Jul 31, 2025

• Bug: `Agent` `instructions` field is not required and accepts non-string types

  #1323 closed Jul 31, 2025

• Draft issue: Additional information needed

  #1187 closed Jul 31, 2025

• Items added to sessions during handoff do not show up

  #1238 closed Jul 30, 2025

• How can I access which tools were used and their outputs in an agent run (without external tracing)?

  #1306 closed Jul 30, 2025

• MCPServerSse connection status

  #1297 closed Jul 30, 2025

• How can I access which tools were used and their outputs in an agent run (without external tracing)?

  #1305 closed Jul 30, 2025

• Random Invalid URL completion error on agents SDK

  #816 closed Jul 30, 2025

• Enhance Documentation for HandoffInputData Structure and Usage

  #1294 closed Jul 29, 2025

• One problem regarding RunItem

  #1283 closed Jul 29, 2025

• Is the same agent instance needed

  #1290 closed Jul 29, 2025

• Couldn't find agents.memory when importing modules

  #1225 closed Jul 29, 2025

• cannot use custom cert when connecting to server with MCPServerSse

  #1182 closed Jul 29, 2025

• Bug: `context.context.name` used in dynamic instruction in Agent documentation, but `name` not in UserContext

  #1262 closed Jul 28, 2025

15 Issues opened by 13 people

• Configure `failure_error_function` in FunctionTool class

  #1367 opened Aug 4, 2025

• Discussion: Folder and files structure for context session management

  #1365 opened Aug 4, 2025

• Distributed tracing

  #1363 opened Aug 4, 2025

• MongoDB Session Store

  #1362 opened Aug 4, 2025

• Discrepancy Between `make check` and CI

  #1350 opened Aug 2, 2025

• Citations/Annotations Lost When Using LitellmModel with Perplexity Models

  #1346 opened Aug 1, 2025

• Support for Streaming Events from Long-Running Tools

  #1333 opened Aug 1, 2025

• SQLAlchemy Session Store for Production Databases

  #1328 opened Jul 31, 2025

• LiteLLM: extra_body with guardrails is not taken into account

  #1324 opened Jul 31, 2025

• Figuring out how to use streamable http mcp server

  #1316 opened Jul 30, 2025

• include_usage in ModelSettings class

  #1311 opened Jul 30, 2025

• 400 error when using saved prompt with built-in tool names in tool_choice

  #1304 opened Jul 30, 2025

• Best way to store structured conversation context

  #1299 opened Jul 29, 2025

• Docs: Enhance all documentation pages with runnable code examples for clarity

  #1295 opened Jul 29, 2025

• MCPServerStreamableHttp connection error corrupt next async calls

  #1288 opened Jul 28, 2025

31 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.

• Feature: Redis Session Management

  #1247 commented on Aug 4, 2025 • 6 new comments

• Initial pass at PostgreSQL session management

  #1163 commented on Aug 1, 2025 • 4 new comments

• Enh - Use handoff_description as Default Fallback for Tool Description in as_tool() of agents

  #1199 commented on Jul 29, 2025 • 0 new comments

• Add conditional tool enabling feature to agent as tool.

  #1193 commented on Aug 1, 2025 • 0 new comments

• Feature: Make trace_include_sensitive_data configurable via environment variable

  #1192 commented on Aug 1, 2025 • 0 new comments

• Fix MCP tool name conflicts by adding server name prefixes

  #1178 commented on Aug 4, 2025 • 0 new comments

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

  #1166 commented on Aug 1, 2025 • 0 new comments

• Enhanced FAQ lookup tool in examples/customer_service app

  #1063 commented on Jul 30, 2025 • 0 new comments

• feat: #864 support streaming nested tool events in Agent.as_tool

  #1057 commented on Aug 2, 2025 • 0 new comments

• Added runtime validation for Agent constructor arguments

  #998 commented on Aug 3, 2025 • 0 new comments

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

  #987 commented on Aug 3, 2025 • 0 new comments

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

  #985 commented on Aug 4, 2025 • 0 new comments

• items_to_messages method not handle "ResponseReasoningItemParam"

  #1165 commented on Aug 4, 2025 • 0 new comments

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

  #1004 commented on Aug 4, 2025 • 0 new comments

• Unhandled item type or structure with resoning item

  #1164 commented on Aug 4, 2025 • 0 new comments

• Tool call parsed as regular message or raises errors (litellm+Mistral)

  #1196 commented on Aug 4, 2025 • 0 new comments

• clear the memory of agents between handoffs

  #1244 commented on Aug 4, 2025 • 0 new comments

• FileSearchTool runs despite InputGuardrailTripwireTriggered

  #889 commented on Aug 3, 2025 • 0 new comments

• Bug: `run_streamed` Buffers `tool_call_item` Events, Delaying Real-Time Feedback

  #1282 commented on Aug 3, 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 Aug 2, 2025 • 0 new comments

• Agent calls a tool: transfer_to_<some_functionality> instead of just carrying out a conversation to capture data.

  #1239 commented on Aug 2, 2025 • 0 new comments

• Why have agents (or GPT 4.1) slowed down so much?

  #1249 commented on Aug 1, 2025 • 0 new comments

• Local memory and context window length

  #177 commented on Aug 1, 2025 • 0 new comments

• A2A (Agent2Agent) support

  #472 commented on Aug 1, 2025 • 0 new comments

• Request to Graduate LiteLLM Integration Out of Beta

  #1237 commented on Aug 1, 2025 • 0 new comments

• tool_call_item event fires only after tool results instead of before

  #1037 commented on Jul 31, 2025 • 0 new comments

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

  #924 commented on Jul 31, 2025 • 0 new comments

• Add Support for Image Return in Agent Tools

  #341 commented on Jul 30, 2025 • 0 new comments

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

  #787 commented on Jul 30, 2025 • 0 new comments

• agent stop when no tool called

  #1279 commented on Jul 29, 2025 • 0 new comments

• How to handle files

  #1281 commented on Jul 29, 2025 • 0 new comments