Skip to content

Navigation Menu

Appearance settings

View all features
- BY COMPANY SIZE
  Enterprises
  Small and medium teams
  Startups
  Nonprofits
- BY USE CASE
  App Modernization
  DevSecOps
  DevOps
  CI/CD
  View all use cases
- BY INDUSTRY
  Healthcare
  Financial services
  Manufacturing
  Government
  View all industries
View all solutions
- EXPLORE BY TOPIC
  AI
  Software Development
  DevOps
  Security
  View all topics
- EXPLORE BY TYPE
  Customer stories
  Events & webinars
  Ebooks & reports
  Business insights
  GitHub Skills
- SUPPORT & SERVICES
  Documentation
  Customer support
  Community forum
  Trust center
  Partners
- COMMUNITY
  GitHub SponsorsFund open source developers
- PROGRAMS
  Security Lab
  Maintainer Community
  Accelerator
  Archive Program
- REPOSITORIES
  Topics
  Trending
  Collections
- ENTERPRISE SOLUTIONS
  Enterprise platformAI-powered developer platform
- AVAILABLE ADD-ONS
  GitHub Advanced SecurityEnterprise-grade security features
  Copilot for BusinessEnterprise-grade AI features
  Premium SupportEnterprise-grade 24/7 support
Pricing

Search code, repositories, users, issues, pull requests...

Search

Clear

Search syntax tips

Provide feedback

We read every piece of feedback, and take your input very seriously.

Include my email address so I can be contacted

Saved searches

Use saved searches to filter your results more quickly

Name

Query

To see all available qualifiers, see our documentation.

Appearance settings

You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session.

Dismiss alert

openai / openai-agents-python Public

Notifications You must be signed in to change notification settings
Fork 3k
Star 18.2k

Code
Issues 150
Pull requests 16
Actions
Security
Insights

Additional navigation options

Code
Issues
Pull requests
Actions
Security
Insights

Human-in-the-Loop Implementation#2021

Closed

mjschock wants to merge 65 commits intoopenai:mainopenai/openai-agents-python:mainfrom

mjschock:mainmjschock/openai-agents-python:mainCopy head branch name to clipboard

Conversation Commits65 (65)Checks Files changed

Closed

Human-in-the-Loop Implementation#2021
mjschock wants to merge 65 commits intoopenai:mainfrom
mjschock:main

Commits

Commits on Dec 22, 2025

feat: implement human-in-the-loop (HITL) approval infrastructure

mjschock
and
claude
committed
feat: integrate HITL approval checking into run execution loop

mjschock
and
claude
committed
feat: add RunState parameter support to Runner.run() methods

mjschock
and
claude
committed
feat: add to_state() method to RunResult for resuming runs

mjschock
and
claude
committed
feat: add streaming HITL support and complete human-in-the-loop implementation

mjschock
and
claude
committed
fix: prime server conversation tracker in streaming path to prevent message duplication

mjschock
and
claude
committed
ci: fix issues that surfaced in CI
mjschock
committed
fix: Bring up coverage to minimum and add session hitl examples
mjschock
committed
fix: ensure RunState serialization compatibility with openai-agents-js
mjschock
committed
fix: standardize call_id extraction in ServerConversationTracker
mjschock
committed
test: add tests for RunState resumption and serialization to bring up coverage
mjschock
committed
fix: Updates following rebase, include test coverage
mjschock
committed
fix: address issues around resuming run state with conversation history
mjschock
committed
fix: address duplicating session history issue mentioned by @chatgpt-codex-connector
mjschock
committed
fix: update RunState with current turn persisted item tracking
mjschock
committed
fix: addressing edge cases when resuming
mjschock
committed
fix: addressing edge cases when resuming (continued)
mjschock
committed
fix: addressing rebase issues
mjschock
committed
fix: improving parity with openai-agent-js hitl functionality
mjschock
committed
fix: bring coverage back up, addressing edge cases
mjschock
committed
fix: cleanup
mjschock
committed
fix: rename summary_message back to assistant_message
mjschock
committed
fix: enhance agent state management during resume, ensuring correct agent usage and saving tool outputs to session
mjschock
committed
fix: finish up human-in-the-loop port
mjschock
committed
fix: add auto_previous_response_id parameter to test_start_streaming_fresh_run_exercises_persistence
mjschock
committed
fix: typing updates to pass `make old_version_tests`
mjschock
committed
fix: remove dead code and add failing hitl error scenarios
mjschock
committed
fix: address failing hitl error scenarios
mjschock
committed
fix: change logging level for _ServerConversationTracker creation to debug
mjschock
committed
fix: pass context_wrapper to _coerce_apply_patch_operation in ApplyPatchAction
mjschock
committed
fix: add test to ensure current turn is preserved when converting RunResult to RunState
mjschock
committed
fix: update RunResult to track current turn number and ensure it is preserved during state conversion
mjschock
committed
fix: add tests to ensure ToolApprovalItem hashability and preserve persisted item count during streamed run resumption
mjschock
committed
refactor: simplify condition for current turn persisted item count in AgentRunner
mjschock
committed
test: add tests to preserve tool output types during run state serialization
mjschock
committed
fix: enhance output item conversion logic to preserve non-function call types in RunState
mjschock
committed
fix: update test to use ResponseCustomToolCall for apply_patch call in HITL coverage
mjschock
committed
fix: remove unused import of RunImpl in AgentRunner
mjschock
committed
test: add test to ensure prepare_input converts Pydantic models to JSON-serializable dicts
mjschock
committed
fix: improve input item conversion logic to handle both dicts and RunItem instances
mjschock
committed
test: add test to verify prepare_input tracks sent items to prevent duplicates
mjschock
committed
fix: track sent items in _ServerConversationTracker to prevent duplicates
mjschock
committed
test: add test to verify normalization of tool outputs by stripping protocol-only fields
mjschock
committed
fix: ensure consistent normalization of input items by always calling to_input_item() for RunItem instances
mjschock
committed
test: add test to verify filtering of items by fingerprint in prepare_input after resume
mjschock
committed
feat: add original_input_fingerprints to _ServerConversationTracker for improved filtering of rehydrated items
mjschock
committed
test: add test for interrupted run state to ensure model response preservation during resumption
mjschock
committed
fix: add processed_response to RunImpl and AgentRunner for improved state management
mjschock
committed
test: add test to verify no duplicates are saved when resuming with all items already persisted
mjschock
committed
fix: refine turn management and input saving logic to prevent duplicates during resume scenarios
mjschock
committed
test: add approval check test to ensure function tools requiring approval are executed before shell tools
mjschock
committed
fix: reorganize tool execution order to prioritize approval checks for function and shell tools
mjschock
committed
test: add test to verify interruption is raised when resuming with unapproved tool
mjschock
committed
fix: implement tool approval checks to handle interruptions before proceeding with new items
mjschock
committed
test: add test to verify that resuming after approval only executes unapproved tools once
mjschock
committed
fix: enhance tool execution logic to prevent re-execution of already processed tools by filtering based on call_ids
mjschock
committed
test: add test to ensure providerData is preserved during MCP approval deserialization
mjschock
committed
fix: preserve and restore providerData during normalization for MCP approval requests
mjschock
committed
Revert "fix: refine turn management and input saving logic to prevent duplicates during resume scenarios"
mjschock
committed
Revert "test: add test to verify no duplicates are saved when resuming with all items already persisted"
mjschock
committed
fix: address lint issues after rebase
mjschock
committed
test: add test to verify no duplicates are created when resuming with all items already persisted
mjschock
committed
fix: refine logic to prevent duplicate item persistence during resumption scenarios
mjschock
committed
test: add test to ensure structured tool outputs are preserved during run state serialization
mjschock
committed
fix: enhance output handling in run state serialization to preserve structured types and ensure compatibility
mjschock
committed

Footer

© 2026 GitHub, Inc.

Footer navigation

Terms
Privacy
Security
Status
Community
Docs
Contact

You can’t perform that action at this time.