| # | Role | Agent ID | Public IP | Private IP |
|---|---|---|---|---|
| 1 | agent | ai:alice | 167.71.104.54 | 10.10.1.3 |
| 2 | agent | ai:bob | 104.131.126.221 | 10.10.1.5 |
| 3 | agent | ai:charlie | 138.197.91.173 | 10.10.1.4 |
| 4 | memory-only | — | 159.203.175.186 | 10.10.1.2 |
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-1 | ai:alice | ironclaw ironclaw 0.26.0 | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | — | 707ba0878d74 | PASS |
| node-2 | ai:bob | ironclaw ironclaw 0.26.0 | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | — | dd9a246aa10a | FAIL |
| node-3 | ai:charlie | ironclaw ironclaw 0.26.0 | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | — | 4cbecd5180ff | PASS |
{
"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": "develop",
"peer_urls": "https://10.10.1.5:9077,https://10.10.1.4:9077,https://10.10.1.2:9077",
"config_file_sha256": "707ba0878d74ee88797684d4af888d48ce1130da687f8b69af032a1b4ff3bd9b",
"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": "223cf7db-759d-461e-98c1-8923d1955da4",
"agent_mcp_canary_f2b": false,
"agent_mcp_canary_uuid": "c0ce5048-a8d2-4dbf-b722-bb0e76a30a81",
"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": true,
"mesh_edges_ok": 3,
"mesh_edges_total": 3,
"mesh_edges_detail": "10.10.1.5:9077:OK,10.10.1.4:9077:OK,10.10.1.2:9077: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": "tls",
"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": "223cf7db-759d-461e-98c1-8923d1955da4",
"canary_namespace": "_baseline_canary_f2a"
},
"baseline_pass": true
},
{
"spec_version": "1.4.0",
"agent_type": "ironclaw",
"agent_id": "ai:bob",
"node_index": "2",
"framework_version": "ironclaw 0.26.0",
"ai_memory_version": "develop",
"peer_urls": "https://10.10.1.3:9077,https://10.10.1.4:9077,https://10.10.1.2:9077",
"config_file_sha256": "dd9a246aa10a01df616a5d7fce7efaf33fb2810a7cbeb25a013fb34f274205a0",
"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": "d186d765-0b61-4abc-9f8d-5c8c1fdd39da",
"agent_mcp_canary_f2b": false,
"agent_mcp_canary_uuid": "41cfe4e3-ba46-4675-b182-6e03f16d76d4",
"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": 1,
"mesh_edges_total": 3,
"mesh_edges_detail": "10.10.1.3:9077:FAIL(health=false,sync=false),10.10.1.4:9077:FAIL(health=false,sync=false),10.10.1.2:9077: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": "tls",
"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": "d186d765-0b61-4abc-9f8d-5c8c1fdd39da",
"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": "develop",
"peer_urls": "https://10.10.1.3:9077,https://10.10.1.5:9077,https://10.10.1.2:9077",
"config_file_sha256": "4cbecd5180ff31b96fcf07e9a7988c94a7b4961b0a2655f2df7feed5b7b40070",
"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": "f38e6f82-5c4e-4d55-929e-9703e0acfb28",
"agent_mcp_canary_f2b": false,
"agent_mcp_canary_uuid": "c01fef53-3153-45c0-a290-cc18ff5eccaa",
"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": true,
"mesh_edges_ok": 3,
"mesh_edges_total": 3,
"mesh_edges_detail": "10.10.1.3:9077:OK,10.10.1.5:9077:OK,10.10.1.2:9077: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": "tls",
"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": "f38e6f82-5c4e-4d55-929e-9703e0acfb28",
"canary_namespace": "_baseline_canary_f2a"
},
"baseline_pass": true
}
],
"failure_mode": "baseline-violation"
}
Run focus
What this campaign tested: The campaign requested 35 scenarios to exercise coverage across transport, framework, and primitive axes but recovered no reports.
What it demonstrated: The run demonstrated a complete failure in the testing harness to generate or recover any scenario results.
AI NHI analysis · Claude Opus 4.7
FAIL — no scenario reports recovered
This test run didn't produce any results because no reports were collected from the scenarios. As a result, we couldn't determine if the AI agents can reliably share memories with each other. The testing process itself needs to be fixed before we can evaluate the system's performance.
This complete test failure indicates high risk and blocks production readiness, as no data supports reliability claims for agent memory sharing. Customer-facing assertions about federation stability remain unvalidated. This represents a regression in CI reliability compared to prior successful runs.
No per-scenario results were recovered, pointing to a harness failure in report collection or upload (harness_sha: 6d3fe7aff9ac948a4ca4b8126e7e95452cedc6dc). All 35 requested scenarios (e.g., S1, S1b, S2 through S42) are effectively skipped with no pass/fail data. Probable root cause is a CI workflow issue in artifact handling; no specific primitives or failure modes (F#) observable due to lack of reports.
Investigate and resolve the report recovery failure in the CI harness to ensure artifact collection works in the next campaign.