Non-technical end users
This test run completely failed to produce any results. We have no information on whether agents can reliably share memories with each other. The problem seems to be that the system couldn't collect any data from the tests.
Campaign a2a-ironclaw-v3r19-mtls-release-v0.6.2 FAIL
Infrastructure
Node roster
| # | Role | Agent ID | Public IP | Private IP |
|---|---|---|---|---|
| 1 | agent | ai:alice | 138.197.11.207 | 10.10.2.4 |
| 2 | agent | ai:bob | 104.131.90.230 | 10.10.2.5 |
| 3 | agent | ai:charlie | 164.90.135.59 | 10.10.2.3 |
| 4 | memory-only | — | 167.71.182.60 | 10.10.2.2 |
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 due to a failure in recovering any reports, despite requesting 35 scenarios covering various transport, framework, and primitive axes.
What it demonstrated: The run proved nothing about agent memory sharing as no results were collected or demonstrated.
AI NHI analysis · Claude Opus 4.7
Campaign failed: no scenario reports recovered.
FAIL — zero scenarios executed or reported.
For three audiences
C-level decision makers
This run indicates high risk with zero test coverage, rendering the system not ready for production deployment. No customer-facing claims about reliability can be supported. Compared to prior runs, this represents a regression in test harness stability.
Engineers & architects
All 35 requested scenarios (S1, S1b, S2, S4-S6, S9-S18, S22-S25, S28-S42) failed to produce reports, likely due to a harness issue in report recovery post-execution. No primitives or failure modes were tested; probable root cause is in the CI workflow at harness_sha 28875c272ce86d10b81466cec10ac4da7bf57b74. No specific F# probes triggered as execution didn't proceed to reporting.
What changes going into the next campaign
Debug and resolve the report recovery failure in the test harness before the next campaign.