aer1-openai-agents

AER-1 verifiable workflow receipts for the OpenAI Agents SDK. One line of integration turns any traced agent run into an offline-verifiable receipt (draft-zambo-aer1, Section 8) covering every model call, tool call, and agent step.

The AER-1 framework collector family

The OpenAI Agents SDK collector in the AER-1 framework collector family. Any agent running on these frameworks can emit verifiable AER-1 execution receipts: every step recorded, hash-chained, one Merkle root over the whole run.

• aer1-smolagents ��� SmolAgents agents via step callbacks
• aer1-openai-agents ��� the OpenAI Agents SDK via its TracingProcessor
• aer1-crewai ��� CrewAI crews via the event bus
• aer1-langgraph ��� LangGraph swarms via callback handler
• aer1-autogen ��� AutoGen multi-agent chats

Plus the aer1 metapackage: pip install aer1, then import aer1; aer1.instrument(). One line, zero config, auto-detects your framework.

Install

pip install aer1-openai-agents

Use (copy, paste, run ��� no API keys needed)

# pip install aer1-openai-agents
import asyncio
from agents import Agent, Runner, function_tool
from agents.testing.model import ScriptedModel, assistant_message, function_call
from aer1_openai_agents import install

@function_tool
def get_weather(city: str) -> str:
    """Get the weather for a city."""
    return f"Sunny in {city}"

async def main():
    processor = install(goal="Check the weather")
    scripted = ScriptedModel(steps=[
        [function_call("get_weather", {"city": "Austin"}, call_id="call_1")],
        [assistant_message("It is sunny in Austin.")],
    ])
    agent = Agent(name="weather", instructions="Answer briefly.",
                  tools=[get_weather])
    agent.model = scripted  # swap for your real model in production

    result = await Runner.run(agent, "What is the weather in Austin?")
    receipt = processor.finalize(final_answer=result.final_output)
    assert processor.verify(receipt) == []  # VALID
    processor.save("receipt.json", receipt)

asyncio.run(main())

install() registers the receipt processor directly. Prefer the standard path in production if you also want the SDK's own tracing dashboard:

from agents.tracing import add_trace_processor
from aer1_openai_agents import AER1TracingProcessor

processor = AER1TracingProcessor(goal="Summarize the quarterly report")
add_trace_processor(processor)

install() additionally skips the SDK's backend trace exporter, so no trace data leaves your machine and proxy-heavy environments cannot fail at registration time. Either way the integration is: register the processor, run the agent, finalize. The processor implements the SDK's TracingProcessor interface, the same pattern other observability integrations use.

What you get

A JSON receipt with the AER-1 Section 8 workflow members:

• type, version, workflow_id, receipt_id, session_id
• goal, status, output_hash, verify_url
• steps: one per ended SDK span (model calls, tool calls, agent boundaries, handoffs), each with seq, receipt_id, tool, receipt_hash, started_at, ended_at, status
• merkle_root: the Section 8.1 root over the ordered step receipt ids

Each step's receipt_hash is SHA-256 over the canonical JSON of the span's observed content, so the hash commits to what the agent actually did. verify() re-checks everything offline: all 14 Table 2/3 member requirements, seq ordering 1..n, no duplicate step receipt ids, and the Merkle root recomputed.

Verify

from aer1_openai_agents import verify_workflow_receipt

failures = verify_workflow_receipt(receipt)
assert failures == []  # empty means valid

The processor never touches the network and never changes agent behavior. It only observes.

Spec

Based on draft-zambo-aer1, Section 8 (verifiable workflow receipts). Verification procedure documented at https://datatracker.ietf.org/doc/draft-zambo-aer1/