| # | Role | Agent ID | Public IP | Private IP |
|---|---|---|---|---|
| 1 | agent | ai:alice | 104.236.87.150 | 10.11.0.3 |
| 2 | agent | ai:bob | 165.22.36.26 | 10.11.0.5 |
| 3 | agent | ai:charlie | 104.236.8.163 | 10.11.0.2 |
| 4 | memory-only | — | 167.172.233.211 | 10.11.0.4 |
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 due to failure in recovering any reports, providing zero coverage across transport, framework, and primitives axes.
What it demonstrated: The run demonstrated a complete failure in the testing process, proving nothing about agent memory sharing reliability.
AI NHI analysis · Claude Opus 4.7
FAIL — no scenario reports recovered
This test run didn't complete successfully, so we have no new information on how well AI agents share memories. Agents might still share memories reliably based on past tests, but this one gives us nothing. We should try running the tests again soon.
The entire campaign failed due to missing scenario reports, maintaining current risk posture with no advancement in production readiness. No new customer-facing claims on memory federation viability can be made. Results from prior runs remain the baseline; investigate CI harness for reliability.
Failure mode involved no scenario reports being recovered, impacting all requested scenarios (35 total) across federation mesh topology. Primitives like memory sharing were not tested; probable root cause is in the CI harness (sha: 2b40c827d10e058ebdba64981dc5801a322180ca) or infra setup on DigitalOcean nyc3. No specific testbook/probe identifiers available due to absent reports.
Debug and resolve the scenario report recovery issue in the CI workflow before retrying.