| # | Role | Agent ID | Public IP | Private IP |
|---|---|---|---|---|
| 1 | agent | ai:alice | 138.197.21.12 | 10.11.2.4 |
| 2 | agent | ai:bob | 138.197.126.11 | 10.11.2.3 |
| 3 | agent | ai:charlie | 104.131.95.255 | 10.11.2.5 |
| 4 | memory-only | — | 174.138.64.27 | 10.11.2.2 |
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: 1.4.0 — 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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| node-2 | ai:bob | hermes Hermes Agent v0.10.0 (2026.4.16) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | — | 21635cf63640 | FAIL |
{
"baseline_pass": false,
"per_node": [
{
"spec_version": "1.4.0",
"agent_type": "hermes",
"agent_id": "ai:bob",
"node_index": "2",
"framework_version": "Hermes Agent v0.10.0 (2026.4.16)",
"ai_memory_version": "v0.6.2",
"peer_urls": "https://10.11.2.4:9077,https://10.11.2.5:9077,https://10.11.2.2:9077",
"config_file_sha256": "21635cf6364057fd2a004d28aac89abf8438671d85f9fd2ed1e654d812d23ff1",
"config_attestation": {
"framework_is_authentic": true,
"mcp_server_ai_memory_registered": true,
"llm_backend_is_xai_grok": true,
"llm_is_default_provider": true,
"mcp_command_is_ai_memory": true,
"agent_id_stamped": true,
"federation_live": true,
"ufw_disabled": true,
"iptables_flushed": true,
"dead_man_switch_scheduled": true
},
"negative_invariants": {
"_description": "Alternative A2A channels must be OFF so a passing scenario is only passing via ai-memory shared memory. Any true here = thesis-preserving.",
"a2a_protocol_off": true,
"sub_agent_or_sessions_spawn_off": true,
"alternative_channels_off": true,
"tool_allowlist_is_memory_only": true,
"a2a_gate_profile_locked": true
},
"functional_probes": {
"xai_grok_chat_reachable": true,
"xai_grok_sample_reply": "READY",
"substrate_http_canary_f2a": true,
"substrate_http_canary_uuid": "13ab798a-1777-4e7a-8a85-343d22e22c66",
"agent_mcp_canary_f2b": false,
"agent_mcp_canary_uuid": "3d744d16-1c2c-48e9-a50e-35d7853cacfc",
"agent_canary_response_head": "Traceback (most recent call last): File \"/usr/local/bin/hermes\", line 11, in <module> main() File \"/root/.hermes/hermes-agent/hermes_cli/main.py\", line 8859, in main args.func(args) File \"/root/.hermes/hermes-agent/hermes_cli/main.py\", line 1159, in cmd_chat from cli import main as cli_main File \"/root/.hermes/hermes-agent/cli.py\", line 43, in <module> from prompt_toolkit.history import FileHistory ModuleNotFoundError: No module named 'prompt_toolkit' ",
"_f2b_note": "F2b is LLM-dependent and non-blocking. F2a (deterministic HTTP substrate) gates baseline_pass.",
"mesh_connectivity_f4": false,
"mesh_edges_ok": 1,
"mesh_edges_total": 3,
"mesh_edges_detail": "10.11.2.4:9077:FAIL(health=false,sync=false),10.11.2.5:9077:FAIL(health=false,sync=false),10.11.2.2:9077:OK",
"_f4_note": "F4 verifies this local nodes N-1 OUTBOUND mesh edges to every peer via both GET health and POST sync_push dry_run. Aggregator ANDs across N nodes to confirm full N*(N-1) bidirectional reachability. Gates baseline_pass.",
"ai_memory_mcp_stdio_f5": true,
"ai_memory_mcp_stdio_init_ok": true,
"ai_memory_mcp_stdio_tools_ok": true,
"ai_memory_mcp_stdio_tools_found": "memory_agent_list,memory_agent_register,memory_archive_list,memory_archive_purge,memory_archive_restore,memory_archive_stats,memory_auto_tag,memory_capabilities,memory_consolidate,memory_delete,memory_detect_contradiction,memory_expand_query,memory_forget,memory_gc,memory_get,memory_get_links,memory_inbox,memory_link,memory_list,memory_list_subscriptions,memory_namespace_clear_standard,memory_namespace_get_standard,memory_namespace_set_standard,memory_notify,memory_pending_approve,memory_pending_list,memory_pending_reject,memory_promote,memory_recall,memory_search,memory_session_start,memory_stats,memory_store,memory_subscribe,memory_unsubscribe,memory_update",
"_f5_note": "F5 spawns the ai-memory stdio MCP subprocess using the framework-configured invocation and verifies initialize + tools/list return memory_store, memory_recall, memory_list. Deterministic (no LLM). Gates baseline_pass.",
"tls_mode": "mtls",
"tls_handshake_f6": true,
"tls_handshake_f6_reason": "",
"mtls_enforcement_f7": true,
"mtls_enforcement_f7_reason": "",
"_f6_f7_note": "F6 verifies the TLS 1.3 handshake against the local serve + CA chain. F7 verifies mTLS enforcement — anonymous client rejected, whitelisted client accepted. Both gate baseline_pass when tls_mode != off / mtls respectively.",
"agent_mcp_ai_memory_canary": true,
"canary_uuid": "13ab798a-1777-4e7a-8a85-343d22e22c66",
"canary_namespace": "_baseline_canary_f2a"
},
"baseline_pass": false
}
],
"failure_mode": "baseline-violation"
}
Run focus
What this campaign tested: Attempted to exercise 35 scenarios covering transport (mTLS), framework (federation mesh), and primitives like memory sharing, but no reports were recovered.
What it demonstrated: The run demonstrated a critical failure in the testing harness, as no scenario results were collected or reported.
AI NHI analysis · Claude Opus 4.7
FAIL — no scenario reports recovered
This test run didn't work because no results from any of the planned checks were collected. We couldn't determine if agents can reliably share memories with each other. The problem seems to be in how the tests were set up or run.
High risk due to complete campaign failure from missing reports, blocking validation of v0.6.2 under mTLS for production. Customer-facing claims on reliable AI memory federation remain unproven. Represents a CI reliability regression compared to prior runs.
No per-scenario reports recovered, indicating a harness failure in artifact collection (harness_sha: 89ac1adba1de2a6909ed00d21d62f2c9d11ff051). All 35 requested scenarios (S1, S1b, S2, S4-S6, S9-S18, S22-S25, S28-S42) effectively skipped. Probable root cause is a CI workflow issue in retrieving outputs from the 4-node federation mesh; no specific primitives or failure modes observable.
Fix the report recovery and artifact upload logic in the CI workflow before re-running.