| # | Role | Agent ID | Public IP | Private IP |
|---|---|---|---|---|
| 1 | agent | ai:alice | 68.183.52.1 | 10.10.2.2 |
| 2 | agent | ai:bob | 64.225.10.188 | 10.10.2.4 |
| 3 | agent | ai:charlie | 174.138.50.20 | 10.10.2.3 |
| 4 | memory-only | — | 159.203.172.51 | 10.10.2.5 |
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 0.27.0 | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | — | cdd26e09c4cc | PASS |
| node-2 | ai:bob | ironclaw ironclaw 0.27.0 | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | — | 92a0cff86532 | PASS |
| node-3 | ai:charlie | ironclaw ironclaw 0.27.0 | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | — | e7119aaef868 | PASS |
{
"baseline_pass": true,
"per_node": [
{
"spec_version": "1.4.0",
"agent_type": "ironclaw",
"agent_id": "ai:alice",
"node_index": "1",
"framework_version": "ironclaw 0.27.0",
"ai_memory_version": "0.6.3.1",
"peer_urls": "https://10.10.2.4:9077,https://10.10.2.3:9077,https://10.10.2.5:9077",
"config_file_sha256": "cdd26e09c4ccacdd127cb75fb88e1c6b536fddc9124d995b5db4d8502e0e4710",
"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": "7cc580ad-e7b2-4219-a74c-a3bfaf2ac6c9",
"agent_mcp_canary_f2b": false,
"agent_mcp_canary_uuid": "69785b62-958c-422d-8b27-0afca399ac37",
"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": "10.10.2.4:9077:OK,10.10.2.3:9077:OK,10.10.2.5:9077: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_check_duplicate,memory_consolidate,memory_delete,memory_detect_contradiction,memory_entity_get_by_alias,memory_entity_register,memory_expand_query,memory_forget,memory_gc,memory_get,memory_get_links,memory_get_taxonomy,memory_inbox,memory_kg_invalidate,memory_kg_query,memory_kg_timeline,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.",
"embedder_loaded_f8": true,
"embedder_loaded_f8_reason": "",
"_f8_note": "F8 verifies /api/v1/capabilities reports features.embedder_loaded=true — i.e. the MiniLM embedder initialised at serve startup. Gates baseline_pass unconditionally. Without this, scenario-18 silently black-holes (semantic recall returns 0 rows).",
"agent_mcp_ai_memory_canary": true,
"canary_uuid": "7cc580ad-e7b2-4219-a74c-a3bfaf2ac6c9",
"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 0.27.0",
"ai_memory_version": "0.6.3.1",
"peer_urls": "https://10.10.2.2:9077,https://10.10.2.3:9077,https://10.10.2.5:9077",
"config_file_sha256": "92a0cff8653225fdeda3ba62ee5e08e786cd1eba91d63258a37ba97d07412456",
"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": "71547b37-fd66-4407-99c1-76e3ba7f68b1",
"agent_mcp_canary_f2b": false,
"agent_mcp_canary_uuid": "067171bf-ee56-4387-b564-b46c83cb549d",
"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": "10.10.2.2:9077:OK,10.10.2.3:9077:OK,10.10.2.5:9077: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_check_duplicate,memory_consolidate,memory_delete,memory_detect_contradiction,memory_entity_get_by_alias,memory_entity_register,memory_expand_query,memory_forget,memory_gc,memory_get,memory_get_links,memory_get_taxonomy,memory_inbox,memory_kg_invalidate,memory_kg_query,memory_kg_timeline,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.",
"embedder_loaded_f8": true,
"embedder_loaded_f8_reason": "",
"_f8_note": "F8 verifies /api/v1/capabilities reports features.embedder_loaded=true — i.e. the MiniLM embedder initialised at serve startup. Gates baseline_pass unconditionally. Without this, scenario-18 silently black-holes (semantic recall returns 0 rows).",
"agent_mcp_ai_memory_canary": true,
"canary_uuid": "71547b37-fd66-4407-99c1-76e3ba7f68b1",
"canary_namespace": "_baseline_canary_f2a"
},
"baseline_pass": true
},
{
"spec_version": "1.4.0",
"agent_type": "ironclaw",
"agent_id": "ai:charlie",
"node_index": "3",
"framework_version": "ironclaw 0.27.0",
"ai_memory_version": "0.6.3.1",
"peer_urls": "https://10.10.2.2:9077,https://10.10.2.4:9077,https://10.10.2.5:9077",
"config_file_sha256": "e7119aaef86870907ac397de6923f5b4c1c4f5f13641f60f946c2c2483b93f41",
"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": "52b33693-f455-40ca-87da-95739e27bd06",
"agent_mcp_canary_f2b": false,
"agent_mcp_canary_uuid": "c73032c2-162e-43ec-bb99-54da34a45c71",
"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": "10.10.2.2:9077:OK,10.10.2.4:9077:OK,10.10.2.5:9077: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_check_duplicate,memory_consolidate,memory_delete,memory_detect_contradiction,memory_entity_get_by_alias,memory_entity_register,memory_expand_query,memory_forget,memory_gc,memory_get,memory_get_links,memory_get_taxonomy,memory_inbox,memory_kg_invalidate,memory_kg_query,memory_kg_timeline,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.",
"embedder_loaded_f8": true,
"embedder_loaded_f8_reason": "",
"_f8_note": "F8 verifies /api/v1/capabilities reports features.embedder_loaded=true — i.e. the MiniLM embedder initialised at serve startup. Gates baseline_pass unconditionally. Without this, scenario-18 silently black-holes (semantic recall returns 0 rows).",
"agent_mcp_ai_memory_canary": true,
"canary_uuid": "52b33693-f455-40ca-87da-95739e27bd06",
"canary_namespace": "_baseline_canary_f2a"
},
"baseline_pass": true
}
]
}
Run focus
What this campaign tested: The campaign requested 30 scenarios (1,1b,2,4-6,9-18,22-25,28-42) covering transport protocols, framework integrations, and memory primitives in a 4-node DigitalOcean federation mesh, but executed zero due to reporting failure.
What it demonstrated: The testing infrastructure failed to capture or retrieve any scenario results, demonstrating a critical gap in CI/CD pipeline reliability rather than in the ai-memory system itself.
AI NHI analysis · Claude Opus 4.7
FAIL — no scenario reports recovered
This test run aimed to check if AI agents can reliably share memories across a network, but it didn't work because no results were recorded. We couldn't verify if the memory sharing holds up under different conditions. Overall, it shows the testing setup needs fixing before we can trust the system's performance.
This run exposes a high-risk failure in the testing pipeline, with zero scenarios yielding results, blocking assessment of production readiness for ai-memory v0.6.3.1. Customer claims about reliable agent memory federation remain unviable without resolved CI issues; no change from prior runs, but urgency increases for infra stability to avoid deployment delays.
No per-scenario results available (scenarios array empty), with overall_pass=false and reason 'no scenario reports recovered'; likely root cause in harness (SHA 2be65a28431fcd5993bfcdf476e27b87b46b0012) failing to aggregate or persist outputs from the 4-node mesh (W=2/N=4 on DigitalOcean nyc3). All requested scenarios (30 total, e.g., S1-S42 subsets) untested, impacting coverage of transports (e.g., mTLS in S9-18), frameworks (e.g., Ironclaw primitives in S22-25), and core memory ops (S28-42). No specific failure modes observable without reports.
Fix CI harness reporting pipeline to ensure scenario results are captured and aggregated before re-running the full scenario set.