| # | Role | Agent ID | Public IP | Private IP |
|---|---|---|---|---|
| 1 | agent | ai:alice | 45.55.44.9 | 10.11.2.4 |
| 2 | agent | ai:bob | 167.71.168.132 | 10.11.2.5 |
| 3 | agent | ai:charlie | 167.71.242.41 | 10.11.2.2 |
| 4 | memory-only | — | 167.172.236.26 | 10.11.2.3 |
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 |
|---|
{
"baseline_pass": false,
"per_node": [],
"failure_mode": "baseline-absent"
}
Run focus
What this campaign tested: No scenarios were exercised, providing zero coverage across transport, framework, or primitives axes due to report recovery failure.
What it demonstrated: The results demonstrated a complete failure in the testing harness, preventing any assessment of AI memory federation functionality.
AI NHI analysis · Claude Opus 4.7
FAIL — no scenarios executed or reported.
This test run didn't produce any results because no scenario reports were collected. As a result, we couldn't determine if the AI agents can reliably share memories with each other. The setup needs fixing to run proper tests in the future.
The campaign failed entirely without results, highlighting significant risks in CI pipeline reliability and blocking production readiness evaluation. Customer-facing claims about agent memory sharing remain unvalidated due to this harness issue. This represents a full regression, as no prior partial successes were built upon.
The run aborted with 'no scenario reports recovered' despite 35 scenarios requested, resulting in an empty scenarios array and overall_pass false. This impacts all primitives, with probable root cause in the harness collection/upload process (harness_sha: 28875c272ce86d10b81466cec10ac4da7bf57b74); no specific S# or F# executed. Infrastructure provisioned successfully (4-node mesh), but post-execution reporting failed entirely.
Implement logging and error handling in the harness to diagnose and prevent report recovery failures.