| # | Role | Agent ID | Public IP | Private IP |
|---|---|---|---|---|
| 1 | agent | ai:alice | 159.65.245.73 | 10.10.0.3 |
| 2 | agent | ai:bob | 45.55.72.145 | 10.10.0.4 |
| 3 | agent | ai:charlie | 104.236.38.105 | 10.10.0.5 |
| 4 | memory-only | — | 68.183.53.38 | 10.10.0.2 |
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 | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | — | 0942520714b6 | PASS |
| node-2 | ai:bob | ironclaw ironclaw 0.26.0 | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | — | ad4105738b4c | PASS |
| node-3 | ai:charlie | ironclaw ironclaw 0.26.0 | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | — | 06d9c01655a2 | PASS |
{
"baseline_pass": true,
"per_node": [
{
"spec_version": "1.4.0",
"agent_type": "ironclaw",
"agent_id": "ai:alice",
"node_index": "1",
"framework_version": "ironclaw 0.26.0",
"ai_memory_version": "v0.6.2",
"peer_urls": "http://10.10.0.4:9077,http://10.10.0.5:9077,http://10.10.0.2:9077",
"config_file_sha256": "0942520714b6156f0c727a1470fb0fad8c0e258a16ed6f6301edce2d6fabcfab",
"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": "b24893a7-1221-4731-acac-5325f172483e",
"agent_mcp_canary_f2b": false,
"agent_mcp_canary_uuid": "c07bf611-988b-4291-853e-f5ba6377e58f",
"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": "10.10.0.4:9077:OK,10.10.0.5:9077:OK,10.10.0.2:9077: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": "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.",
"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": "b24893a7-1221-4731-acac-5325f172483e",
"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": "v0.6.2",
"peer_urls": "http://10.10.0.3:9077,http://10.10.0.5:9077,http://10.10.0.2:9077",
"config_file_sha256": "ad4105738b4c3c792046282490135a5fd57073c639f0eb2bed43a8e11978dc7e",
"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": "489b4441-1f41-46bd-a225-28beeaead003",
"agent_mcp_canary_f2b": false,
"agent_mcp_canary_uuid": "b27bbdf8-1584-4e3a-9a9f-517c46810da7",
"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": "10.10.0.3:9077:OK,10.10.0.5:9077:OK,10.10.0.2:9077: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": "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.",
"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": "489b4441-1f41-46bd-a225-28beeaead003",
"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 0.26.0",
"ai_memory_version": "v0.6.2",
"peer_urls": "http://10.10.0.3:9077,http://10.10.0.4:9077,http://10.10.0.2:9077",
"config_file_sha256": "06d9c01655a2bdbc525b1cb2081e089df4c92293938581095e910876f8328acc",
"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": "88a56393-d4db-4bf2-8790-bb0408cf582e",
"agent_mcp_canary_f2b": false,
"agent_mcp_canary_uuid": "89e452f0-28c6-4b4d-950a-b05fafbf5f85",
"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": "10.10.0.3:9077:OK,10.10.0.4:9077:OK,10.10.0.2:9077: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": "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.",
"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": "88a56393-d4db-4bf2-8790-bb0408cf582e",
"canary_namespace": "_baseline_canary_f2a"
},
"baseline_pass": true
}
]
}
Workflow-level probe answering "can agents communicate through ai-memory?". Writer ai:alice posted canary UUID 18017cd1-bdd8-4027-9b82-5d03bde2f85c to namespace _baseline_peer_canary via node-1's local ai-memory serve HTTP. After W=2 fanout settle, probe confirmed the canary on each of the 3 peer nodes via their local GET /api/v1/memories.
{
"probe": "F3",
"name": "peer-a2a-via-shared-memory",
"description": "Writer agent posts a canary via local ai-memory HTTP on node-1; verifies the row propagates to the 3 peer nodes (W=2/N=4 quorum) before scenarios run.",
"canary_uuid": "18017cd1-bdd8-4027-9b82-5d03bde2f85c",
"canary_namespace": "_baseline_peer_canary",
"writer_agent": "ai:alice",
"pass": true
}
Run focus
What this campaign tested: Tested scenario 18 exercising hybrid recall mode with semantic querying across agents in a 4-node federated mesh without TLS, covering recall primitives and federation transport.
What it demonstrated: Demonstrated that hybrid recall in semantic mode failed to retrieve Bob's relevant memory, resulting in incomplete sharing visible to Charlie.
AI NHI analysis · Claude Opus 4.7
FAIL — semantic query missed Bob's memory
In this test, two agents shared memories about morning exercise routines, but a third agent only saw one of them when asking about it. This means the system isn't reliably sharing all related memories between agents. It's like a group chat where some messages get lost.
This isolated test on scenario 18 failed, indicating a high-risk regression in hybrid memory recall that undermines production readiness. Customer-facing claims about seamless AI-to-AI memory sharing are not viable until fixed; this patch likely introduced the issue compared to stable v0.6.2 baseline.
Scenario S18 failed with hybrid recall not surfacing Bob's memory (marker bob-daybreak-2ec9df21) in semantic query, as seen_by_charlie=0 despite diag_list presence. Impacts semantic search primitive in federated mesh (W=2/N=4); probable root cause is embedding similarity threshold or quorum read failure in recall mode. Investigate probe F# for hybrid semantics and re-test post-fix.
Apply fix for semantic query in hybrid mode and expand to full scenario suite for validation.
Every scenario that produced a JSON report in this campaign, in testbook order. Click a row's scenario id to jump to its full report below. See the Every test performed page for the authoritative catalog.
| ID | Title | Result | Reason |
|---|---|---|---|
| S18 | Semantic query expansion | ? | semantic query did not surface bob's memory |
Reasons: semantic query did not surface bob's memory
{
"agent_group": "ironclaw",
"diag_list_alice_present": 1,
"diag_list_bob_present": 1,
"pass": false,
"query": "morning outdoor exercise routine",
"reason": "semantic query did not surface bob's memory",
"reasons": [
"semantic query did not surface bob's memory"
],
"recall_mode": "hybrid",
"rows_in_recall": 1,
"scenario": "18",
"skipped": false,
"tls_mode": "off",
"writers": [
{
"agent": "ai:alice",
"marker": "alice-sunrise-40e174e1",
"seen_by_charlie": 1
},
{
"agent": "ai:bob",
"marker": "bob-daybreak-2ec9df21",
"seen_by_charlie": 0
}
]
}
alice writes A on node-1 bob writes B on node-2 polling node-3 for both writes to propagate (max 30 s) both writes visible after 1 s settle 3s for embedder + HNSW catch-up charlie queries on node-3 with semantically-related prompt recall mode=hybrid returned 1 rows charlie sees alice's memory: 1 (expected >=1) charlie sees bob's memory: 0 (expected >=1)