../ runs index

Campaign a2a-hermes-v3r16-mtls-release-v0.6.2 FAIL

Agent group
hermes (homogeneous)
ai-memory ref
release/v0.6.2
Completed at
2026-04-22T21:24:31Z
Overall pass
false
Skipped reports
0

Infrastructure

Provider
digitalocean
Region
nyc3
Droplet size
s-2vcpu-4gb
Topology
4-node federation mesh (W=2/N=4)
Scenarios started
Scenarios ended
Dispatched by
alphaonedev
Harness SHA
4bf59f540624
Workflow run
https://github.com/alphaonedev/ai-memory-ai2ai-gate/actions/runs/24802396324

Node roster

#RoleAgent IDPublic IPPrivate IP
1agentai:alice45.55.70.18110.11.2.3
2agentai:bob209.97.146.20010.11.2.5
3agentai:charlie138.197.39.4810.11.2.2
4memory-only45.55.36.21410.11.2.4

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.

NodeAgentFrameworkAuthenticMCP ai-memoryxAI cfgxAI defaultAgent IDFederationUFW offiptablesdead-manF1 xAIF2a substrateF2b agent (non-gating)Config SHAPass
a2a-baseline.json
{
	"baseline_pass": false,
	"per_node": [],
	"failure_mode": "baseline-absent"
}

raw file

Run focus

Campaign failed: no scenario reports recovered.

What this campaign tested: No scenarios were exercised; 35 were requested but none reported due to recovery failure.

What it demonstrated: The run proved nothing about agent memory sharing as no test results were generated.

AI NHI analysis · Claude Opus 4.7

Campaign failed: no scenario reports recovered.

FAIL — no scenario reports recovered

For three audiences

Non-technical end users

This test run didn't work at all because no results came back from any of the planned checks. That means we have no information on whether agents can reliably share memories with each other. It's like the test never happened.

C-level decision makers

High risk to production readiness as the entire campaign failed without producing any results, blocking validation of v0.6.2 release. No customer-facing claims can be made about reliability improvements versus prior runs. This indicates a harness or infra issue that needs immediate triage before re-run.

Engineers & architects

The campaign harness failed to recover any scenario reports, impacting all requested scenarios (1 through 42, excluding some gaps) across transport, framework, and primitives axes. Probable root cause is a CI workflow or infra provisioning error, as evidenced by empty timing and scenarios arrays; no specific S# or F# identifiers available due to total failure. Investigate harness_sha 4bf59f5406248cf8fd87fbccf96f0f537d850a7c and workflow_url for defects.

What changes going into the next campaign

Debug and fix report recovery in the CI harness before re-running the campaign.

All artifacts