The first external RESONANCE benchmark run produced a strong result — and an equally important limit. OpenAI Agents SDK passed every executable framework probe we mapped to State, Causality, Phase, Transition, Time, Recovery, Verification and Evidence. The score stops at 95 because this run did not exercise a real sandbox or network containment boundary.

pinned SHAinstall597 testsscoreevidence artifact

95 is not “95% safe.”

The benchmark is a framework capability baseline. It asks whether the tested revision exposes and executes mechanisms that matter for trustworthy action trajectories. It does not certify a particular model, application, tool policy, business invariant, credential boundary or production deployment.

That distinction is the point. A verification system becomes less useful the moment a score outruns the evidence behind it.

S

State · 10/10348 upstream tests passed · run state, serialization and resume coverage.

C

Causality · 10/1053 upstream tests passed · run-item and tool/action correlation structures.

P

Phase · 10/102 HITL scenarios passed · approval interruption, persistence and resume.

T

Transition · 10/10108 run-step tests passed · execution, interruptions and step outcomes.

τ

Time · 10/1025 soft-cancel tests passed · immediate vs after-turn timing semantics.

R

Recovery · 10/105 run-error-handler tests passed.

V

Verification · 10/10Guardrail and execution-result paths exercised in the run-step suite.

E

Evidence · 10/1056 trace-processor tests passed.

B

Containment · 5/10Partial by design: no live sandbox, OS privilege or network boundary in this baseline.

X

Reproducibility · 10/10Exact target SHA + offline/deterministic framework tests + durable artifact digest.

What actually ran

The canonical GitHub Actions workflow cloned openai/openai-agents-python at commit 2231eb5d40cd4a9d6b86f79492e984eeb3301263, installed that revision, and executed seven unique upstream suites. The framework's own deterministic test machinery means the baseline did not need a production API key or live model call.

348State

test_run_state.py

53Causality

test_run_internal_items.py

2Phase

test_hitl_session_scenario.py

108Transition + Verification

test_run_step_execution.py

25Time

test_soft_cancel.py

5Recovery

test_run_internal_error_handlers.py

56Evidence

test_trace_processor.py

597Total unique tests

All passed in the canonical run.

The strongest result is not the number 95. It is that the score has a reproducible path back to executable evidence.

The missing five points matter most.

A framework can manage state, approvals, traces and error paths correctly while an application still exposes too much filesystem, shell, credential, network or production access. That is why RESONANCE deliberately withheld half of the containment points.

The next run should introduce a real declared sandbox boundary and attempt safe, synthetic overreach: filesystem escape, unauthorized network access and privilege expansion. The desired result is not merely a blocked request; it is a preserved evidence chain explaining what was attempted, which boundary stopped it and what state survived.

Interpretation boundary

This report verifies framework capability coverage at one pinned revision. It does not verify prompt-injection resistance of arbitrary applications, correctness of user-defined tools, financial authorization, domain invariants, production credential isolation, network containment or the safety of every agent built with the SDK.

  1. Pinned upstream commit
  2. Canonical GitHub Actions run
  3. Benchmark runner
  4. Durable result JSON

Artifact digest: sha256:d0759dc612a299abc976bc45fe4a45aec8da6bfbcbd50c7194a95c464e39c3bb. Score scope: structural framework baseline, not external safety certification.

Verdict: OpenAI Agents SDK v0.19.4 at the tested revision demonstrates a strong structural baseline for building verifiable agent workflows. The next verification frontier is containment plus application-specific invariants under injected faults.

RESONANCE Verified Report #001

Target → pinned revision → executable probes → evidence artifact → bounded claim.

Back to Issue 001