Non-technical end users
This test run didn't produce any results because no reports were collected from the scenarios. We can't tell if agents reliably share memories or not. It seems like there was a problem with the setup or data collection.
Campaign a2a-hermes-v3r15-mtls-develop FAIL
Infrastructure
Node roster
| # | Role | Agent ID | Public IP | Private IP |
|---|---|---|---|---|
| 1 | agent | ai:alice | 104.131.117.47 | 10.11.2.3 |
| 2 | agent | ai:bob | 104.236.18.121 | 10.11.2.2 |
| 3 | agent | ai:charlie | 45.55.240.219 | 10.11.2.4 |
| 4 | memory-only | — | 159.89.189.236 | 10.11.2.5 |
Baseline attestation BASELINE VIOLATION
Per the authoritative baseline spec, every agent node must emit a self-attestation before any scenario is permitted to run. This run's attestation:
Spec version: 1.0.0 — see authoritative baseline.
| Node | Agent | Framework | Authentic | MCP ai-memory | xAI cfg | xAI default | Agent ID | Federation | UFW off | iptables | dead-man | F1 xAI | F2a substrate | F2b agent (non-gating) | Config SHA | Pass |
|---|
a2a-baseline.json
{
"baseline_pass": false,
"per_node": [],
"failure_mode": "baseline-absent"
}
Run focus
Campaign failed: no scenario reports recovered.
What this campaign tested: No scenarios were exercised, despite requesting 35 scenarios across various transport, framework, and primitive axes, due to report recovery failure.
What it demonstrated: The run proved a critical failure in the testing infrastructure or harness, as no scenario results were generated or recovered.
AI NHI analysis · Claude Opus 4.7
Campaign failed: no scenario reports recovered.
FAIL — no scenario reports recovered
For three audiences
C-level decision makers
The campaign completely failed to yield results, elevating risk posture due to untested changes in the develop branch. Production readiness remains unassessed, and no customer-facing claims can be validated. No progress or changes detected versus prior runs since nothing was tested.
Engineers & architects
No scenario reports were recovered for any of the 35 requested scenarios (e.g., S1, S2, S4 through S42), indicating a harness failure at sha 006cdf4a787bfec7cfc5007fd40ae990e22e5860. All coverage axes (transport, framework, primitives) were untested, effectively skipping everything. Probable root cause: error in infrastructure provisioning, scenario execution, or report aggregation in the CI workflow.
What changes going into the next campaign
Debug and resolve report recovery issues in the CI harness to ensure scenario results are captured.