chore: Upgrade openai-agents from 0.2.11 to 0.3.3

[aaronsteers]

chore: Upgrade openai-agents from 0.2.11 to 0.3.3

Summary

Upgrades the openai-agents library from version 0.2.11 to 0.3.3 to potentially address coordination issues identified in the agent system. This upgrade includes:

• openai-agents: 0.2.11 → 0.3.3
• openai: 1.106.1 → 1.109.1 (transitive dependency)
• emoji: Added v2.15.0 (new dependency)

Version 0.3.3 includes PR #1662 which adds AdvancedSQLiteSession with conversation branching & usage tracking capabilities that may help resolve the handoff tool failures and agent identity confusion issues identified in our investigation.

Review & Testing Checklist for Human

• End-to-end connector build test: Run a complete connector build using the manager-developer architecture to verify core functionality still works
• Handoff coordination verification: Check that developer → manager handoffs work properly (specifically that report_back_to_manager tool is available when needed)
• Agent identity consistency: Monitor logs for any agent identity confusion (e.g., developer trying to delegate tasks)

Test Plan Recommendation

Run the connector builder with a simple API (like JSONPlaceholder) and monitor the execution logs for:

1. Successful handoffs between manager and developer agents
2. Proper completion signaling (manager calling mark_job_success)
3. No tool availability errors during handbacks

Notes

This upgrade was requested as part of investigating coordination issues documented in this Devin session. The original investigation found specific problems with handoff tool availability and agent identity confusion that this library upgrade may help address.

Requested by: @aaronsteers

Summary by CodeRabbit

• Chores
  • Updated an underlying AI agent library to a newer version to improve compatibility and stability.
  • No user-facing behavior changes are expected in this release.
  • Enhances performance and reliability under the hood and aligns with the latest platform requirements.
  • Includes minor maintenance improvements and prepares the system for future feature work.
  • Addresses general upkeep to keep the application current without altering workflows.

[devin-ai-integration]

Original prompt from AJ Steers

@Devin - Review this execution log: <https://github.com/airbytehq/connector-builder-mcp/actions/runs/18415068059/job/52476733729?pr=122>

You'll note the "NOW:" "OBSERVED:", "NEXT:" pattern is not being practiced until the work is basically done. This tells me the prompt is not properly routing to the developer instructions in the first step. I also note from that log that the agent is already done but the agent is not aware so it tries to work again on the problem. See if you can find the problem with routing and/or prompting and/or coordination between manager and developer agents.
Thread URL: https://airbytehq-team.slack.com/archives/D089P0UPVT4/p1760121663439179?thread_ts=1760121663.439179

[devin-ai-integration]

🤖 Devin AI Engineer

I'll be helping with this pull request! Here's what you should know:

✅ I will automatically:

• Address comments on this PR. Add '(aside)' to your comment to have me ignore it.
• Look at CI failures and help fix them

Note: I can only respond to comments from users who have write access to this repository.

⚙️ Control Options:

• Disable automatic comment and CI monitoring

[github-actions]

👋 Greetings, Airbyte Team Member!

Here are some helpful tips and reminders for your convenience.

Testing This Branch via MCP

To test the changes in this specific branch with an MCP client like Claude Desktop, use the following configuration:

{
  "mcpServers": {
    "connector-builder-mcp-dev": {
      "command": "uvx",
      "args": ["--from", "git+https://github.com/airbytehq/connector-builder-mcp.git@devin/1760132669-upgrade-openai-agents", "connector-builder-mcp"]
    }
  }
}

Testing This Branch via CLI

You can test this version of the MCP Server using the following CLI snippet:

# Run the CLI from this branch:
uvx 'git+https://github.com/airbytehq/connector-builder-mcp.git@devin/1760132669-upgrade-openai-agents#egg=airbyte-connector-builder-mcp' --help

PR Slash Commands

Airbyte Maintainers can execute the following slash commands on your PR:

• /autofix - Fixes most formatting and linting issues
• /poe <command> - Runs any poe command in the uv virtual environment
• /poe build-connector prompt="Star Wars API" - Run the connector builder using the Star Wars API.

📝 Edit this welcome message.

[coderabbitai]

📝 Walkthrough

Walkthrough

Updated dependency constraint for openai-agents in connector_builder_agents/pyproject.toml from >=0.2.11 to >=0.3.3. No other files or public interfaces changed.

Changes

Cohort / File(s)	Summary
Dependency version bump connector_builder_agents/pyproject.toml	Bumped openai-agents requirement from >=0.2.11 to >=0.3.3; no other dependency or config changes.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~2 minutes

Suggested labels

enhancement

Pre-merge checks and finishing touches

✅ Passed checks (3 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title Check	✅ Passed	The title succinctly describes the primary change of upgrading the openai-agents dependency from version 0.2.11 to 0.3.3, matching the contents of the changeset without extraneous details.
Docstring Coverage	✅ Passed	No functions found in the changes. Docstring coverage check skipped.

✨ Finishing touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Post copyable unit tests in a comment
• Commit unit tests in branch devin/1760132669-upgrade-openai-agents

---

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

[github-actions]

PyTest Results (Fast)

0 tests  ±0   0 ✅ ±0   0s ⏱️ ±0s
0 suites ±0   0 💤 ±0 
0 files   ±0   0 ❌ ±0 

Results for commit 12aaaa0. ± Comparison against base commit 374cb49.

[coderabbitai]

Actionable comments posted: 0

🧹 Nitpick comments (1)

connector_builder_agents/pyproject.toml (1)

10-10: Tighten openai-agents version range
Add an upper bound to avoid pulling in 0.4.0 prereleases:

-    "openai-agents>=0.3.3",
+    "openai-agents>=0.3.3,<0.4.0",

All related packages (openai-agents-mcp, openinference-instrumentation-openai-agents, openai 1.109.1) are compatible with 0.3.3; regenerate the lockfile and rerun end-to-end tests.

📜 Review details

Configuration used: CodeRabbit UI

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 374cb49 and 12aaaa0.

⛔ Files ignored due to path filters (1)

• connector_builder_agents/uv.lock is excluded by !**/*.lock

📒 Files selected for processing (1)

• connector_builder_agents/pyproject.toml (1 hunks)

⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)

• GitHub Check: Run Evals (Single Connector)

[aaronsteers]

Best build time yet! Just around 3 minutes! https://github.com/airbytehq/connector-builder-mcp/actions/runs/18419163761/job/52489711554?pr=133

Points to us likely having been held back in efficiency due to library issues prior to now.

cc @pedroslopez

(Devin, no action needed.)