8 Releases published by 1 person

• v0.2.1

  published Jul 16, 2025

• v0.2.2

  published Jul 17, 2025

• v0.2.3

  published Jul 21, 2025

• v0.2.4

  published Jul 29, 2025

• v0.2.5

  published Aug 7, 2025

• v0.2.6

  published Aug 11, 2025

• v0.2.7

  published Aug 14, 2025

• 0.2.8

  published Aug 15, 2025

135 Pull requests merged by 40 people

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

  #987 merged Aug 16, 2025

• Update all translated document pages

  #1503 merged Aug 15, 2025

• Add conditional tool enabling feature to agent as tool.

  #1193 merged Aug 15, 2025

• Fix #1494 by adding a link to Responses API documentation

  #1502 merged Aug 15, 2025

• 0.2.8

  #1501 merged Aug 15, 2025

• Realtime: allow arbitrarily sized messages

  #1500 merged Aug 15, 2025

• Realtime: fix history bug

  #1495 merged Aug 15, 2025

• Make shallow copies of lists instead of deep copies

  #1490 merged Aug 15, 2025

• Allow modifying the input sent to the model

  #1483 merged Aug 15, 2025

• Update all translated document pages

  #1484 merged Aug 14, 2025

• Docs: Add missing docstring to how_many_jokes tool

  #1479 merged Aug 14, 2025

• Docs: Clarify that guardrails apply to both user input and agent output

  #1482 merged Aug 14, 2025

• Docs: Add missing docstring to get_weather function

  #1478 merged Aug 14, 2025

• Add input validation and type conversion for user input

  #1476 merged Aug 14, 2025

• Fix: Clarify random_number function docstring for inclusive range

  #1475 merged Aug 14, 2025

• v0.2.7

  #1480 merged Aug 14, 2025

• Realtime: one guardrail trip event per response

  #1458 merged Aug 14, 2025

• Update all translated document pages

  #1473 merged Aug 14, 2025

• docs: Clarify the is_enabled parameter in handoff() documentation

  #1472 merged Aug 14, 2025

• Update all translated document pages

  #1471 merged Aug 14, 2025

• Migrate document translation script to gpt-5

  #1470 merged Aug 14, 2025

• Update all translated document pages

  #1469 merged Aug 14, 2025

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

  #1354 merged Aug 14, 2025

• Add input validation and type conversion for user input

  #1462 merged Aug 14, 2025

• Fix: Clarify random_number function docstring for inclusive range

  #1461 merged Aug 14, 2025

• Add a simple gpt-oss example

  #1440 merged Aug 14, 2025

• Fix #1407 Add reasoning.effort="minimal" and "verbosity" params to ModelSettings

  #1439 merged Aug 13, 2025

• Fix: enforce strict instructions function signature in get_system_prompt

  #1426 merged Aug 13, 2025

• feat(tests): add tests for unicode content, special characters, and concurrent access in SQLiteSession

  #1399 merged Aug 11, 2025

• Realtime: add handoff prompt prefix

  #1382 merged Aug 11, 2025

• Added runtime validation for Agent constructor arguments

  #998 merged Aug 11, 2025

• v0.2.6

  #1423 merged Aug 11, 2025

• chore(deps): Bump "openai>=1.99.6,<2"

  #1415 merged Aug 11, 2025

• Updated the default values for two parameters in the ModelSettings class to align with their documented behavior:

  #1392 merged Aug 11, 2025

• Add streaming function call arguments example

  #1052 merged Aug 11, 2025

• Add logprobs to ModelSettings

  #971 merged Aug 11, 2025

• Update all translated document pages

  #1413 merged Aug 11, 2025

• Improve accuracy of guardrails and lifecycle hook descriptions

  #1386 merged Aug 11, 2025

• Enhanced FAQ lookup tool in examples/customer_service app

  #1063 merged Aug 11, 2025

• feat: support agent output guardrails in realtime

  #1381 merged Aug 8, 2025

• v0.2.5

  #1398 merged Aug 7, 2025

• Realtime: send session update before tool response

  #1388 merged Aug 7, 2025

• Realtime: fix interrupt logic

  #1370 merged Aug 4, 2025

• Update all translated document pages

  #1369 merged Aug 4, 2025

• feat(viz): draw MCP servers

  #1368 merged Aug 4, 2025

• 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

• fix: convert litellm response with reasoning content to openai message

  #1098 merged Jul 28, 2025

• docs: remove non existent even_if_trace_running mention from trace docstring

  #1273 merged Jul 28, 2025

• Fix documentation typo and trailing comma in exporters

  #1272 merged Jul 28, 2025

• fix: enforce min trigger size=1 to prevent immediate exports

  #1270 merged Jul 28, 2025

• Fix etc. punctuation

  #1268 merged Jul 28, 2025

• refactor: remove inherited method from Agent class

  #1267 merged Jul 28, 2025

• gpt 4.5-preview is removed, use gpt-4.1

  #1266 merged Jul 28, 2025

• Consistently use "Python" in docstrings

  #1261 merged Jul 28, 2025

• Tweak on guardrail docstrings

  #1260 merged Jul 28, 2025

• Fix type placeholder convention

  #1259 merged Jul 26, 2025

• Update all translated document pages

  #1251 merged Jul 26, 2025

• docs: add LangDB AI Gateway as a tracing provider

  #1224 merged Jul 25, 2025

• Make Trace class inherit from abc.ABC for proper abstract base class behavior

  #1233 merged Jul 25, 2025

• Fix #1227 Chat Completions model fails to handle streaming with openai 1.97.1+

  #1246 merged Jul 25, 2025

• Realtime: send audio item/content index

  #1235 merged Jul 25, 2025

• [Bugfix] Fix wrong imports in examples

  #1241 merged Jul 25, 2025

• Add LiteLLM to acknowledgements section

  #1240 merged Jul 25, 2025

• Update all translated document pages

  #1232 merged Jul 24, 2025

• Adding docstring to get_weather tool

  #1231 merged Jul 24, 2025

• Fix RealtimeModel reference

  #1215 merged Jul 23, 2025

• Update all translated document pages

  #1221 merged Jul 23, 2025

• Fixes two issues in the tracing documentation

  #1212 merged Jul 23, 2025

• Update codex action to use repo syntax

  #1218 merged Jul 22, 2025

• Use real codex action

  #1217 merged Jul 22, 2025

• Set up codex for issues and PRs

  #1214 merged Jul 22, 2025

• Add prototype structure for banking demo

  #1205 merged Jul 22, 2025

• Add prototype structure for banking demo

  #1203 merged Jul 22, 2025

• Add automation script to generate mkdocstrings files

  #1048 merged Jul 21, 2025

• v0.2.3

  #1201 merged Jul 21, 2025

• Realtime: make sure we use the initial model settings

  #1198 merged Jul 21, 2025

• Realtime: add user agent header

  #1185 merged Jul 21, 2025

• 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

• Adjust #598 to only create a PR rather than pushing changes to main branch

  #1162 merged Jul 17, 2025

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

  #598 merged Jul 16, 2025

• v0.2.1

  #1151 merged Jul 16, 2025

• Realtime docs

  #1153 merged Jul 16, 2025

• Realtime: web demo

  #1149 merged Jul 16, 2025

• Unbreak tests

  #1157 merged Jul 16, 2025

• Empty mcp tool result error

  #1142 merged Jul 16, 2025

• Add Streaming of Function Call Arguments to Chat Completions

  #999 merged Jul 16, 2025

• Correct error message for invalid output types with strict JSON schema

  #1101 merged Jul 16, 2025

• MCP: add support for tool_result.structuredContent

  #1150 merged Jul 16, 2025

8 Pull requests opened by 5 people

• Initial pass at PostgreSQL session management

  #1163 opened Jul 17, 2025

• Feature: Make trace_include_sensitive_data configurable via environment variable

  #1192 opened Jul 19, 2025

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

  #1199 opened Jul 21, 2025

• 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

• Add SQLAlchemy session backend for conversation history management

  #1357 opened Aug 3, 2025

• Mongodb memory session

  #1364 opened Aug 4, 2025

• Feat: Add Optional Structured Session Storage

  #1474 opened Aug 14, 2025

147 Issues closed by 36 people

• Add is_enabled option to Agent as a tool pattern

  #1097 closed Aug 15, 2025

• Detailed guide on truncation option in ModelSettings

  #1494 closed Aug 15, 2025

• SQLiteSession: Consecutive same input should still trigger tool execution

  #1496 closed Aug 15, 2025

• File paths within Code Interpreter container instances

  #1489 closed Aug 15, 2025

• How to disable default OpenAI tracer and use only Datadog ddtrace for tracing

  #1477 closed Aug 15, 2025

• WebSearchTool never gets called in a multi agent setup but works with a single agent.

  #1488 closed Aug 15, 2025

• RunResult missing .usage property for token usage tracking

  #1487 closed Aug 15, 2025

• LiteLLM calls not working because of improper imports

  #1402 closed Aug 15, 2025

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

  #1196 closed Aug 15, 2025

• Add `timeout` feature for agent runs

  #1425 closed Aug 14, 2025

• Error code: 400 "No tool output found for function call"

  #673 closed Aug 14, 2025

• Very high response times at random during hand-offs

  #717 closed Aug 14, 2025

• Add reasoning.effort="minimal" and "verbosity" params to ModelSettings

  #1407 closed Aug 13, 2025

• Engineering review request — persistent emergent optimization layer ("NEO Core")

  #1441 closed Aug 13, 2025

• Gemini 2.5 does not work well with function call

  #1420 closed Aug 13, 2025

• Built-in Support for Sticky Session Routing / Direct Agent Handoff

  #1436 closed Aug 13, 2025

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

  #787 closed Aug 13, 2025

• Prompt the handed model to begin a structured conversation.

  #1428 closed Aug 13, 2025

• Agent keep retrying until hit max_retires on function calling

  #981 closed Aug 12, 2025

• Return

  #259 closed Aug 12, 2025

• Support for OpenAI Realtime Models in Agents SDK

  #239 closed Aug 12, 2025

• Agents SDK v0.0.4: Local Traces Missing Critical LLM Outputs and Tool Interaction Data

  #222 closed Aug 12, 2025

• Tracing for the realtime api

  #220 closed Aug 12, 2025

• Clarification on the need for RunContextWrapper[UserContext] and Agent[UserContext]

  #219 closed Aug 12, 2025

• Discrepancy in Documentation: strict_mode Parameter Mentioned but Not Implemented in function_tool Decorator

  #215 closed Aug 12, 2025

• 404 Error During Agent Handoff in Multi-Agent System

  #206 closed Aug 12, 2025

• Got this error with example file {'error': {'message': 'The model `computer-use-preview-2025-03-11` does not exist or you do not have access to it.', 'type': 'invalid_request_error', 'param': None, 'code': 'model_not_found'}}

  #183 closed Aug 12, 2025

• How to use the Custom Web Search tool

  #170 closed Aug 12, 2025

• collective Multi-agent reinforcement learning

  #160 closed Aug 12, 2025

• The output panel shows "Request failed" after the task is completed

  #157 closed Aug 12, 2025

• Are there some other way to set up the api token besides setting it as an environment variable?

  #154 closed Aug 12, 2025

• Is it possible to use a locally privatized model?

  #136 closed Aug 12, 2025

• Hosted tool 'computer_use_preview' is not supported

  #132 closed Aug 12, 2025

• from LangChain and Langgraph to openai-agents

  #128 closed Aug 12, 2025

• Changing the src/agents/models/openai_chatcompletions.py into smaller parts

  #119 closed Aug 12, 2025

• use localmodel with openai format does not work

  #118 closed Aug 12, 2025

• Proper way of managing large context window for ComputerTool

  #111 closed Aug 12, 2025

• Support for Gemini Flash

  #106 closed Aug 12, 2025

• Allow agent to return logprobs

  #715 closed Aug 12, 2025

• Agent session error in OpenAI Agents SDK when handling tool output

  #1429 closed Aug 12, 2025

• No validation on the Agent constructor arguments

  #996 closed Aug 11, 2025

• Latest `openai` release (`1.99.2`) breaks `LitellmModel`.

  #1395 closed Aug 11, 2025

• ChatCompletionMessageToolCallParam can't not be converted with openai>=1.99.0

  #1401 closed Aug 11, 2025

• `TypeError: Cannot instantiate typing.Union` when running with latest `openai` Python package

  #1417 closed Aug 11, 2025

• TypeError: Cannot instantiate typing.Union when calling tools due to misuse of TypeAlias in chatcmpl_converter.py

  #1416 closed Aug 11, 2025

• Import error with openai package 1.99.0

  #1378 closed Aug 11, 2025

• Reasoning summary output items from Azure OpenAI models

  #1389 closed Aug 11, 2025

• How to use non-async agents when tools respond synchronously (no /responses endpoint)?

  #1391 closed Aug 11, 2025

• clear the memory of agents between handoffs

  #1244 closed Aug 11, 2025

• How do I obtain the assistant and input audio transcription events using RealtimeAgent?

  #1380 closed Aug 11, 2025

• LiteLLM: extra_body with guardrails is not taken into account

  #1324 closed Aug 11, 2025

• Discussion: Folder and files structure for context session management

  #1365 closed Aug 11, 2025

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

  #1004 closed Aug 11, 2025

• Will an agent call a tool multiple times?

  #1394 closed Aug 10, 2025

• TypeError: Cannot instantiate typing.Union

  #1411 closed Aug 10, 2025

• agent stop when no tool called

  #1279 closed Aug 10, 2025

• Best way to store structured conversation context

  #1299 closed Aug 10, 2025

• include_usage in ModelSettings class

  #1311 closed Aug 10, 2025

• How to show Metadata/Sessions/Tags when using Litellm version sdk

  #1210 closed Aug 9, 2025

• Agent-level MCP server tool filtering

  #1234 closed Aug 9, 2025

• How to Retrieve Tool Name from `tool_call_item` Event in Streaming?

  #1264 closed Aug 9, 2025

• How to handle files

  #1281 closed Aug 9, 2025

• Is it possible to silence `OPENAI_API_KEY is not set, skipping trace export`, without silencing third-party tracers?

  #1387 closed Aug 7, 2025

• tool_call_item event fires only after tool results instead of before

  #1037 closed Aug 7, 2025

• A2A - (Agent-to-Agent) Protocol Support

  #1374 closed Aug 6, 2025

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

  #1156 closed Aug 6, 2025

• docs: Propose adding examples for all `function_tool` parameters

  #1372 closed Aug 5, 2025

• Unhandled item type or structure with resoning item

  #1164 closed Aug 5, 2025

• Configure `failure_error_function` in FunctionTool class

  #1367 closed Aug 5, 2025

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

  #1239 closed Aug 5, 2025

• 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

• Support int and boolean types for Agent name parameter

  #1285 closed Jul 28, 2025

• Main(Triage) Agent does not generate final output as structured output when agent_as_tool is used.

  #1271 closed Jul 28, 2025

• ValidationError: logprobs Field required when using Runner.run_stream()

  #1269 closed Jul 28, 2025

• Validation Error for ResponseTextDeltaEvent – Missing logprobs Field

  #1276 closed Jul 28, 2025

• Validation Error for ResponseTextDeltaEvent – Missing logprobs Field

  #1275 closed Jul 28, 2025

• Agent output inaccurate when combining structured output and tool calls in OpenAI Agents SDK

  #1263 closed Jul 27, 2025

• Halt `Runner` on specific tool call

  #1126 closed Jul 27, 2025

• Inconsistent use of agent parameter vs guardrail_agent in quardrail function named homework_guardrail in Quickstart Tab of Documentation

  #1255 closed Jul 26, 2025

• Inconsistent use of agent parameter vs guardrail_agent in quardrail function named homework_guardrail in Quickstart Tab of Documentation.

  #1254 closed Jul 26, 2025

• Inconsistent use of agent parameter vs guardrail_agent in quardrail function named homework_guardrail in Quickstart Tab of Documentation.

  #1253 closed Jul 25, 2025

• Add LangDB AI as tracing Provider in docs

  #1222 closed Jul 25, 2025

• Chat Completions model fails to handle streaming with openai 1.97.1+

  #1227 closed Jul 25, 2025

• reasoning_item_created never called on stream

  #1025 closed Jul 25, 2025

• Question about session memory

  #1229 closed Jul 24, 2025

• Agent attempts to use non-existing tool

  #686 closed Jul 24, 2025

• function_tool calling - agents orchertratins

  #769 closed Jul 24, 2025

• Only 1 handoff getting called no matter what

  #771 closed Jul 23, 2025

• SDK support for retrieving historical traces

  #793 closed Jul 23, 2025

• Intermittent 60+ sec delays during agent hand-offs in multi-agent flows

  #1219 closed Jul 22, 2025

• Support multimodal input for Sessions

  #1211 closed Jul 22, 2025

• Azure OpenAI rejects system prompt from prompt_with_handoff_instructions

  #806 closed Jul 22, 2025

• separate stream items for "tool_call_item" and "tool_call_output_item"

  #831 closed Jul 22, 2025

• Realtime: Handoffs don't hand back up to original agent

  #1197 closed Jul 21, 2025

• Suggestions for using user feedback as tools?

  #1186 closed Jul 21, 2025

• Pydantic requirements mismatch

  #967 closed Jul 21, 2025

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

  #972 closed Jul 21, 2025

• Cannot run visualization

  #978 closed Jul 21, 2025

• Agent as a tool input_type

  #984 closed Jul 21, 2025

• 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

• Realtime Voice Not Quite Working

  #1136 closed Jul 16, 2025

• tool_name parameter on as_tool() does not default to agent name as expected

  #1159 closed Jul 16, 2025

• Agent(name=…) accepts non-string types due to Pydantic coercion

  #1148 closed Jul 16, 2025

• Dependencies for v0.2 Realtime Not Up to Date

  #1158 closed Jul 16, 2025

• Empty tool output incorrectly triggers “Errored MCP tool result”

  #1035 closed Jul 16, 2025

• Support Streaming of Function Call Arguments

  #834 closed Jul 16, 2025

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

  #894 closed Jul 16, 2025

• Intent Classifier Support

  #628 closed Jul 16, 2025

51 Issues opened by 36 people

• Why does Agent.name accept non-string values at runtime?

  #1504 opened Aug 16, 2025

• trace_include_sensitive_data=False does not apply to agents as tools

  #1492 opened Aug 15, 2025

• Title: Handoff fails with Invalid 'input[1].id': '__fake_id__' when using non-OpenAI models and OpenAI tracing

  #1485 opened Aug 15, 2025

• Tools not getting called w/ gpt-4.1

  #1481 opened Aug 14, 2025

• openai.BadRequestError with gpt-oss-120b - Expected 2 output messages (reasoning and final), but got 3.

  #1468 opened Aug 14, 2025

• RealtimeAgent Error(message='Conversation already has an active response in progress: Wait until the response is finished')

  #1466 opened Aug 14, 2025

• Tool not invoked on consecutive calls when using SQLiteSession in OpenAI Agent SDK

  #1465 opened Aug 14, 2025

• How can you add session (memory) to realtime agents

  #1464 opened Aug 14, 2025

• Add Flag for Priority Processing Tier (or Tier in general)

  #1459 opened Aug 13, 2025

• `RunResult` missing `.usage` attribute in latest OpenAI Agents SDK

  #1457 opened Aug 13, 2025

• `UserError` not raised when invalid tool type is passed to `tools` parameter

  #1443 opened Aug 13, 2025

• agents.exceptions.MaxTurnsExceeded with Llama 3.3

  #1442 opened Aug 13, 2025

• Fail to load traces when using a different API key for tracing

  #1437 opened Aug 13, 2025

• Model parameter compatibility documentation

  #1435 opened Aug 13, 2025

• in history_updated events, the status of 'assistant' is always 'in_progress'. After the assistant has spoken or generated audio, it must say 'Completed'

  #1434 opened Aug 13, 2025

• Unexpected behavior with MCP server tools

  #1430 opened Aug 12, 2025

• RuntimeError: aclose(): asynchronous generator is already running w/ realtime/app example

  #1427 opened Aug 12, 2025

• Eval integration

  #1418 opened Aug 11, 2025

• Cannot use outputType with gpt-oss:20b

  #1414 opened Aug 11, 2025

• LLM-friendly Documentation

  #1412 opened Aug 11, 2025

• gpt-5 model fails to complete my tasks while gpt-4.1 completes

  #1409 opened Aug 8, 2025

• How to track finish_reason when using the Runner class

  #1406 opened Aug 8, 2025

• if mcp initialize fails, the streaming hangs

  #1404 opened Aug 8, 2025

• GPT-5 does not work well compared to 4.1

  #1397 opened Aug 7, 2025

• how to cleanup mcp servers correctly?

  #1393 opened Aug 7, 2025

• Issue with output_type and Custom LLM Providers in openai-agents-python

  #1390 opened Aug 7, 2025

• Suggestion: Database schema for conversations could be better

  #1385 opened Aug 6, 2025

• RunContextWrapper in MCP server tools

  #1383 opened Aug 6, 2025

• Does gpt-oss support Agents SDK tools?

  #1379 opened Aug 5, 2025

• Proposal: Return results to the parent Agent

  #1376 opened Aug 5, 2025

• Run `custom_output_extractor` AFTER `RunHooks.on_tool_end`

  #1375 opened Aug 5, 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

• Figuring out how to use streamable http mcp server

  #1316 opened Jul 30, 2025

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

  #1304 opened Jul 30, 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

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

  #1282 opened Jul 28, 2025

• Handoffs to deterministic workflows

  #1274 opened Jul 28, 2025

• Anthropic caching not supported on LiteLLM

  #1257 opened Jul 25, 2025

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

  #1249 opened Jul 25, 2025

• Request to Graduate LiteLLM Integration Out of Beta

  #1237 opened Jul 24, 2025

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

  #1183 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

• items_to_messages method not handle "ResponseReasoningItemParam"

  #1165 opened Jul 17, 2025

56 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 run configuration inheritance for agent-as-tool workflows

  #1006 commented on Aug 15, 2025 • 1 new comment

• Truncate span input when input is too large

  #260 commented on Jul 26, 2025 • 0 new comments

• invalid_request_error when using "chat_completions" with triage agent (gemini -> any other model)

  #237 commented on Jul 26, 2025 • 0 new comments

• Best practices for long running tools?

  #295 commented on Jul 27, 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

• A2A (Agent2Agent) support

  #472 commented on Aug 1, 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

• Agent run with previous_response_id fails - No tool output found for function call call_WdnUUKXKvwy3jk....

  #1061 commented on Aug 5, 2025 • 0 new comments

• will there be a Java version of openai-agents-java in the future?

  #115 commented on Aug 11, 2025 • 0 new comments

• BadRequestError while trying out input guardrails w/ Groq

  #129 commented on Aug 12, 2025 • 0 new comments

• Tool calling with LiteLLM and thinking models fail

  #765 commented on Aug 13, 2025 • 0 new comments

• from agents.extensions.models.litellm_model import LitellmModel

  #666 commented on Aug 14, 2025 • 0 new comments

• FileSearchTool runs despite InputGuardrailTripwireTriggered

  #889 commented on Aug 14, 2025 • 0 new comments

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

  #636 commented on Aug 14, 2025 • 0 new comments

• Local memory and context window length

  #177 commented on Aug 14, 2025 • 0 new comments

• Add Support for Image Return in Agent Tools

  #341 commented on Aug 15, 2025 • 0 new comments

• OAuth support for MCPServerSse

  #657 commented on Aug 15, 2025 • 0 new comments

• Function calling fails on “application/json” MIME type with the latest Gemini models

  #656 commented on Aug 15, 2025 • 0 new comments

• Add `method_tool` Functionality

  #94 commented on Aug 15, 2025 • 0 new comments

• No OpenAI tracing with Azure Foundry models

  #1051 commented on Aug 15, 2025 • 0 new comments

• bugs in run.py

  #570 commented on Aug 16, 2025 • 0 new comments

• History Cleaning

  #545 commented on Aug 16, 2025 • 0 new comments

• Websocket streaming audio in realtime from client

  #536 commented on Aug 16, 2025 • 0 new comments

• Timeout after 300 seconds with any error message. Could it be rate limiting?

  #511 commented on Aug 16, 2025 • 0 new comments

• Add reasoning support for custom models.

  #492 commented on Aug 16, 2025 • 0 new comments

• fix(#94): handle special parameters (self/cls) correctly with context parameter

  #137 commented on Aug 15, 2025 • 0 new comments

• Ensure that input_guardrails can block tools from running

  #931 commented on Aug 11, 2025 • 0 new comments

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

  #1057 commented on Aug 15, 2025 • 0 new comments

• Add support for reference images in Agents SDK for image generation

  #1017 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

• Feature Request: Support streaming tool call outputs

  #692 commented on Jul 24, 2025 • 0 new comments

• multiple inputs with session support

  #1140 commented on Jul 25, 2025 • 0 new comments

• 2 Messages after a successful tool call

  #1129 commented on Jul 25, 2025 • 0 new comments

• Union type not permitted in AaaT

  #1091 commented on Jul 25, 2025 • 0 new comments

• Incomplete RunItemStreamEvent names list

  #1020 commented on Jul 25, 2025 • 0 new comments

• Unclosed client session when using some litellm models

  #1016 commented on Jul 25, 2025 • 0 new comments

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

  #991 commented on Jul 25, 2025 • 0 new comments

• Get exception raised in tool invocation

  #945 commented on Jul 25, 2025 • 0 new comments

• CodeInterpreter tool is appending data to the end of the filename in containers

  #911 commented on Jul 25, 2025 • 0 new comments

• Get pydantic serializer warnings in calling Runner.run

  #880 commented on Jul 25, 2025 • 0 new comments

• MCP tools turn upstream HTTP errors into AgentsException, crashing the run

  #879 commented on Jul 25, 2025 • 0 new comments

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

  #772 commented on Jul 25, 2025 • 0 new comments

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

  #758 commented on Jul 26, 2025 • 0 new comments

• MCP server restart cause Agent to fail

  #693 commented on Jul 26, 2025 • 0 new comments

• Unable to use reasoning models with tool calls using LitellmModel

  #678 commented on Jul 26, 2025 • 0 new comments

• Custom model provider ignored when using agents as tools

  #663 commented on Jul 26, 2025 • 0 new comments

• Resource tracker warning (leaked semaphores) with MCPServerStdio

  #618 commented on Jul 26, 2025 • 0 new comments

• [Bug]: UnicodeDecodeError when importing litellm_model on Windows

  #610 commented on Jul 26, 2025 • 0 new comments

• Ordering of events in Runner.run_streamed is incorrect

  #583 commented on Jul 26, 2025 • 0 new comments

• Reasoning model items provide to General model

  #569 commented on Jul 26, 2025 • 0 new comments

• Usage tokens no longer automatically show

  #548 commented on Jul 26, 2025 • 0 new comments

• Cannot get the last tool_call_output event in stream_events when MaxTurnsExceeded

  #526 commented on Jul 26, 2025 • 0 new comments

• Duplicate tool names across MCP servers cause errors

  #464 commented on Jul 26, 2025 • 0 new comments

• The voice models aren't waiting for a pause(a very natural phenomenon when using a voice agent) and generating an output mid sentence when talking to the voice agent implemented using "VoicePipline" .

  #369 commented on Jul 26, 2025 • 0 new comments

• Random transcript gets printed/generated when talking to the voice agent implemented using "VoicePipline" . Eg - "Transcription: Kurs." Mind you there is no background noise.

  #368 commented on Jul 26, 2025 • 0 new comments

• Streamed Voice Agent Demo - Multiple Performance Issues

  #301 commented on Jul 26, 2025 • 0 new comments