| # | Role | Agent ID | Public IP | Private IP |
|---|---|---|---|---|
| 1 | agent | ai:alice | 157.245.2.153 | 10.251.0.3 |
| 2 | agent | ai:bob | 167.99.56.10 | 10.251.0.5 |
| 3 | agent | ai:charlie | 167.71.255.160 | 10.251.0.2 |
| 4 | memory-only | — | 159.89.189.213 | 10.251.0.4 |
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: 1.4.0 — 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-1 | ai:alice | ironclaw ironclaw 0.26.0 | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | — | 62e13f9ed96a | FAIL |
| node-2 | ai:bob | ironclaw ironclaw 0.26.0 | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | — | 49509142c552 | FAIL |
| node-3 | ai:charlie | ironclaw ironclaw 0.26.0 | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | — | 7df6b9967988 | FAIL |
{
"baseline_pass": false,
"per_node": [
{
"spec_version": "1.4.0",
"agent_type": "ironclaw",
"agent_id": "ai:alice",
"node_index": "1",
"framework_version": "ironclaw 0.26.0",
"ai_memory_version": "0.6.2-rc.0",
"peer_urls": "http://10.251.0.5:9077,http://10.251.0.2:9077,http://10.251.0.4:9077",
"config_file_sha256": "62e13f9ed96aab97295929b21cc2d3c5310434457c77d48f752375e68dc73863",
"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": "f01528cc-345e-4fc0-adec-9a6562547409",
"agent_mcp_canary_f2b": false,
"agent_mcp_canary_uuid": "1953d8bb-5da9-482d-ad2b-fec277bc7b55",
"agent_canary_response_head": "error: unrecognized subcommand 'chat' tip: a similar subcommand exists: 'channels' Usage: ironclaw [OPTIONS] [COMMAND] For more information, try '--help'. ",
"_f2b_note": "F2b is LLM-dependent and non-blocking. F2a (deterministic HTTP substrate) gates baseline_pass.",
"mesh_connectivity_f4": false,
"mesh_edges_ok": 2,
"mesh_edges_total": 3,
"mesh_edges_detail": "10.251.0.5:9077:OK,10.251.0.2:9077:OK,10.251.0.4:9077:FAIL(health=false,sync=false)",
"_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": "off",
"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": "f01528cc-345e-4fc0-adec-9a6562547409",
"canary_namespace": "_baseline_canary_f2a"
},
"baseline_pass": false
},
{
"spec_version": "1.4.0",
"agent_type": "ironclaw",
"agent_id": "ai:bob",
"node_index": "2",
"framework_version": "ironclaw 0.26.0",
"ai_memory_version": "0.6.2-rc.0",
"peer_urls": "http://10.251.0.3:9077,http://10.251.0.2:9077,http://10.251.0.4:9077",
"config_file_sha256": "49509142c552497bd09879cc088950fb7490dd6de2e7f44f73959d260acb18a3",
"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": "21b46750-5e2d-4578-8635-f7434ab34bc2",
"agent_mcp_canary_f2b": false,
"agent_mcp_canary_uuid": "291759f4-e3af-4a28-86bf-dd7662de236a",
"agent_canary_response_head": "error: unrecognized subcommand 'chat' tip: a similar subcommand exists: 'channels' Usage: ironclaw [OPTIONS] [COMMAND] For more information, try '--help'. ",
"_f2b_note": "F2b is LLM-dependent and non-blocking. F2a (deterministic HTTP substrate) gates baseline_pass.",
"mesh_connectivity_f4": false,
"mesh_edges_ok": 2,
"mesh_edges_total": 3,
"mesh_edges_detail": "10.251.0.3:9077:OK,10.251.0.2:9077:OK,10.251.0.4:9077:FAIL(health=false,sync=false)",
"_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": "off",
"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": "21b46750-5e2d-4578-8635-f7434ab34bc2",
"canary_namespace": "_baseline_canary_f2a"
},
"baseline_pass": false
},
{
"spec_version": "1.4.0",
"agent_type": "ironclaw",
"agent_id": "ai:charlie",
"node_index": "3",
"framework_version": "ironclaw 0.26.0",
"ai_memory_version": "0.6.2-rc.0",
"peer_urls": "http://10.251.0.3:9077,http://10.251.0.5:9077,http://10.251.0.4:9077",
"config_file_sha256": "7df6b99679887f734947b2976646d7d5f2aaf320203ca42519b50d12084306d6",
"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": "61c95ccb-0e26-4c30-8a68-d61eb48c8d47",
"agent_mcp_canary_f2b": false,
"agent_mcp_canary_uuid": "b47ce6b2-21b5-4074-95e8-8bfb7f66acd1",
"agent_canary_response_head": "error: unrecognized subcommand 'chat' tip: a similar subcommand exists: 'channels' Usage: ironclaw [OPTIONS] [COMMAND] For more information, try '--help'. ",
"_f2b_note": "F2b is LLM-dependent and non-blocking. F2a (deterministic HTTP substrate) gates baseline_pass.",
"mesh_connectivity_f4": false,
"mesh_edges_ok": 2,
"mesh_edges_total": 3,
"mesh_edges_detail": "10.251.0.3:9077:OK,10.251.0.5:9077:OK,10.251.0.4:9077:FAIL(health=false,sync=false)",
"_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": "off",
"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": "61c95ccb-0e26-4c30-8a68-d61eb48c8d47",
"canary_namespace": "_baseline_canary_f2a"
},
"baseline_pass": false
}
],
"failure_mode": "baseline-violation"
}
Run focus
What this campaign tested: No scenarios were exercised, as no reports were recovered despite requesting 35 scenarios across various transport, framework, and primitive axes.
What it demonstrated: The results demonstrated a critical failure in the campaign harness to collect or recover any scenario outcomes.
AI NHI analysis · Claude Opus 4.7
FAIL — no scenario reports recovered
This test run didn't work because no results from the planned checks were collected. It means we couldn't verify if AI agents can reliably share memories with each other. Without these reports, we have no information on whether the system functions as expected.
This campaign run poses high risk due to complete absence of scenario reports, indicating harness instability and blocking production readiness assessment. No customer-facing claims on AI memory sharing can be validated from this run, representing a regression from prior successful campaigns. Immediate triage is needed to restore testing reliability.
The run requested 35 scenarios (e.g., S1, S1b, S2 through S42) but recovered zero reports, likely due to a harness failure in report aggregation or CI workflow (harness_sha: 377d51660ea985f126e93fa580ef433847dce29f). All primitives and frameworks remain untested, with probable root cause in post-execution artifact handling on the Linux runner. No specific failure modes observed since no per-scenario data available.
Debug and fix the report recovery mechanism in the CI harness before re-running the campaign.