| # | Role | Agent ID | Public IP | Private IP |
|---|---|---|---|---|
| 1 | agent | ai:alice | 104.131.187.8 | 10.11.0.4 |
| 2 | agent | ai:bob | 138.197.28.227 | 10.11.0.5 |
| 3 | agent | ai:charlie | 167.172.243.204 | 10.11.0.2 |
| 4 | memory-only | — | 104.248.9.75 | 10.11.0.3 |
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 | hermes Hermes Agent v0.12.0 (2026.4.30) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | — | 12f99ec56116 | PASS |
| node-2 | ai:bob | hermes Hermes Agent v0.12.0 (2026.4.30) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | — | 889c475f0926 | PASS |
| node-3 | ai:charlie | hermes Hermes Agent v0.12.0 (2026.4.30) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | — | 00622f57d71b | PASS |
{
"baseline_pass": true,
"per_node": [
{
"spec_version": "1.4.0",
"agent_type": "hermes",
"agent_id": "ai:alice",
"node_index": "1",
"framework_version": "Hermes Agent v0.12.0 (2026.4.30)",
"ai_memory_version": "0.6.3.1",
"peer_urls": "http://10.11.0.5:9077,http://10.11.0.2:9077,http://10.11.0.3:9077",
"config_file_sha256": "12f99ec56116dbd03748777fabc1697dbcc89bd41e0a1470c0dae152987998de",
"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": "2caebd64-d94d-4dd9-8028-eda1ffcbfe73",
"agent_mcp_canary_f2b": false,
"agent_mcp_canary_uuid": "8cc0e77c-6cf5-44ca-a7f8-118f55590f65",
"agent_canary_response_head": "",
"_f2b_note": "F2b is LLM-dependent and non-blocking. F2a (deterministic HTTP substrate) gates baseline_pass.",
"hermes_peer_a2a_repro_f3b": false,
"hermes_peer_a2a_repro_uuid": "",
"_f3b_note": "F3b is hermes-only and observed (non-blocking). Asserts the agent-driven mcp_memory_memory_store path actually lands a row through the hermes_cli tool dispatcher, distinct from the workflow-level F3 which probes substrate-only HTTP federation. False here while F2b is true => allowlist filter regression in hermes_cli/mcp_tools.py.",
"mesh_connectivity_f4": true,
"mesh_edges_ok": 3,
"mesh_edges_total": 3,
"mesh_edges_detail": "10.11.0.5:9077:OK,10.11.0.2:9077:OK,10.11.0.3:9077: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": "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": "2caebd64-d94d-4dd9-8028-eda1ffcbfe73",
"canary_namespace": "_baseline_canary_f2a"
},
"baseline_pass": true
},
{
"spec_version": "1.4.0",
"agent_type": "hermes",
"agent_id": "ai:bob",
"node_index": "2",
"framework_version": "Hermes Agent v0.12.0 (2026.4.30)",
"ai_memory_version": "0.6.3.1",
"peer_urls": "http://10.11.0.4:9077,http://10.11.0.2:9077,http://10.11.0.3:9077",
"config_file_sha256": "889c475f0926686ffdc3827accbd19cba3d820a90c5ae908eb1ac33f71eb0098",
"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": "d4328bbc-d64f-4c55-9966-dddae305572e",
"agent_mcp_canary_f2b": false,
"agent_mcp_canary_uuid": "eee26f26-caf9-4b6a-a847-1f624eb546bd",
"agent_canary_response_head": "",
"_f2b_note": "F2b is LLM-dependent and non-blocking. F2a (deterministic HTTP substrate) gates baseline_pass.",
"hermes_peer_a2a_repro_f3b": false,
"hermes_peer_a2a_repro_uuid": "",
"_f3b_note": "F3b is hermes-only and observed (non-blocking). Asserts the agent-driven mcp_memory_memory_store path actually lands a row through the hermes_cli tool dispatcher, distinct from the workflow-level F3 which probes substrate-only HTTP federation. False here while F2b is true => allowlist filter regression in hermes_cli/mcp_tools.py.",
"mesh_connectivity_f4": true,
"mesh_edges_ok": 3,
"mesh_edges_total": 3,
"mesh_edges_detail": "10.11.0.4:9077:OK,10.11.0.2:9077:OK,10.11.0.3:9077: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": "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": "d4328bbc-d64f-4c55-9966-dddae305572e",
"canary_namespace": "_baseline_canary_f2a"
},
"baseline_pass": true
},
{
"spec_version": "1.4.0",
"agent_type": "hermes",
"agent_id": "ai:charlie",
"node_index": "3",
"framework_version": "Hermes Agent v0.12.0 (2026.4.30)",
"ai_memory_version": "0.6.3.1",
"peer_urls": "http://10.11.0.4:9077,http://10.11.0.5:9077,http://10.11.0.3:9077",
"config_file_sha256": "00622f57d71b6fd1a9018469eff1efa71f7ec334eda63f58017c4ce34744c35f",
"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": "Icannotcomplywithrequeststhatappeartoinitiatejail",
"substrate_http_canary_f2a": true,
"substrate_http_canary_uuid": "bfada7f3-fbdf-44ce-8486-e3e88f67221f",
"agent_mcp_canary_f2b": false,
"agent_mcp_canary_uuid": "67594dbb-8956-47f3-8aab-b96536a94d80",
"agent_canary_response_head": "",
"_f2b_note": "F2b is LLM-dependent and non-blocking. F2a (deterministic HTTP substrate) gates baseline_pass.",
"hermes_peer_a2a_repro_f3b": false,
"hermes_peer_a2a_repro_uuid": "",
"_f3b_note": "F3b is hermes-only and observed (non-blocking). Asserts the agent-driven mcp_memory_memory_store path actually lands a row through the hermes_cli tool dispatcher, distinct from the workflow-level F3 which probes substrate-only HTTP federation. False here while F2b is true => allowlist filter regression in hermes_cli/mcp_tools.py.",
"mesh_connectivity_f4": true,
"mesh_edges_ok": 3,
"mesh_edges_total": 3,
"mesh_edges_detail": "10.11.0.4:9077:OK,10.11.0.5:9077:OK,10.11.0.3:9077: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": "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": "bfada7f3-fbdf-44ce-8486-e3e88f67221f",
"canary_namespace": "_baseline_canary_f2a"
},
"baseline_pass": true
}
]
}
Workflow-level probe answering "can agents communicate through ai-memory?". Writer ai:alice posted canary UUID 0f37cf3f-b42b-49d3-87d0-b42de2aade4e 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": "0f37cf3f-b42b-49d3-87d0-b42de2aade4e",
"canary_namespace": "_baseline_peer_canary",
"writer_agent": "ai:alice",
"pass": true
}
Run focus
What this campaign tested: Attempted to exercise 35 scenarios covering various transports, frameworks, and primitives in a 4-node federation mesh, but none produced reports.
What it demonstrated: The run demonstrated a critical failure in the testing harness, as no scenario results were collected or parsed successfully.
AI NHI analysis · Claude Opus 4.7
FAIL — no scenario reports recovered
This test run didn't produce any results because no reports from the scenarios were recovered. We couldn't check if agents can reliably share memories with each other. It looks like there was a problem in how the tests were set up or run.
This complete test failure indicates high risk in the infrastructure, blocking production readiness and any customer-facing claims about agent memory sharing. No progress or changes can be assessed versus prior runs due to lack of data. Immediate investigation into the harness is needed to restore testing cadence.
No scenarios completed successfully, with only one skipped report noted as 'scenario-1.json:unparseable' and all others missing. This impacts all requested scenarios (S1 to S42, excluding some gaps), likely due to a root cause in the harness failing to collect or parse reports (harness_sha: aecab95805c959750fa44015ae62374ce8486f7d). No specific failure modes or primitives can be analyzed without results; probe identifiers are unavailable.
Debug the testing harness to ensure scenario reports are generated, collected, and parsed correctly before the next campaign.
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 |
|---|---|---|---|
| S1 | Per-agent write + read (MCP stdio) | ? |
phase A: each agent writes 10 memories via MCP ai:alice on 104.131.187.8 !! ssh timeout (60s): root@104.131.187.8 source /etc/ai-memory-a2a/env 2>/dev/null; bash /root/drive_agent.sh store w1-ai:alice 'scenario1 write 1 from ai:alice' scenario1-ai:alice !! drive_agent store failed for ai:alice i=1: __TIMEOUT_60s__ !! ssh timeout (60s): root@104.131.187.8 source /etc/ai-memory-a2a/env 2>/dev/null; bash /root/drive_agent.sh store w2-ai:alice 'scenario1 write 2 from ai:alice' scenario1-ai:alice !! drive_agent store failed for ai:alice i=2: __TIMEOUT_60s__ !! ssh timeout (60s): root@104.131.187.8 source /etc/ai-memory-a2a/env 2>/dev/null; bash /root/drive_agent.sh store w3-ai:alice 'scenario1 write 3 from ai:alice' scenario1-ai:alice !! drive_agent store failed for ai:alice i=3: __TIMEOUT_60s__ !! ssh timeout (60s): root@104.131.187.8 source /etc/ai-memory-a2a/env 2>/dev/null; bash /root/drive_agent.sh store w6-ai:alice 'scenario1 write 6 from ai:alice' scenario1-ai:alice !! drive_agent store failed for ai:alice i=6: __TIMEOUT_60s__ !! ssh timeout (60s): root@104.131.187.8 source /etc/ai-memory-a2a/env 2>/dev/null; bash /root/drive_agent.sh store w7-ai:alice 'scenario1 write 7 from ai:alice' scenario1-ai:alice !! drive_agent store failed for ai:alice i=7: __TIMEOUT_60s__ ai:bob on 138.197.28.227 !! ssh timeout (60s): root@138.197.28.227 source /etc/ai-memory-a2a/env 2>/dev/null; bash /root/drive_agent.sh store w1-ai:bob 'scenario1 write 1 from ai:bob' scenario1-ai:bob !! drive_agent store failed for ai:bob i=1: __TIMEOUT_60s__ !! ssh timeout (60s): root@138.197.28.227 source /etc/ai-memory-a2a/env 2>/dev/null; bash /root/drive_agent.sh store w2-ai:bob 'scenario1 write 2 from ai:bob' scenario1-ai:bob !! drive_agent store failed for ai:bob i=2: __TIMEOUT_60s__ !! ssh timeout (60s): root@138.197.28.227 source /etc/ai-memory-a2a/env 2>/dev/null; bash /root/drive_agent.sh store w3-ai:bob 'scenario1 write 3 from ai:bob' scenario1-ai:bob !! drive_agent store failed for ai:bob i=3: __TIMEOUT_60s__ !! ssh timeout (60s): root@138.197.28.227 source /etc/ai-memory-a2a/env 2>/dev/null; bash /root/drive_agent.sh store w4-ai:bob 'scenario1 write 4 from ai:bob' scenario1-ai:bob !! drive_agent store failed for ai:bob i=4: __TIMEOUT_60s__ !! ssh timeout (60s): root@138.197.28.227 source /etc/ai-memory-a2a/env 2>/dev/null; bash /root/drive_agent.sh store w10-ai:bob 'scenario1 write 10 from ai:bob' scenario1-ai:bob !! drive_agent store failed for ai:bob i=10: __TIMEOUT_60s__ ai:charlie on 167.172.243.204 !! ssh timeout (60s): root@167.172.243.204 source /etc/ai-memory-a2a/env 2>/dev/null; bash /root/drive_agent.sh store w1-ai:charlie 'scenario1 write 1 from ai:charlie' scenario1-ai:charlie !! drive_agent store failed for ai:charlie i=1: __TIMEOUT_60s__ !! ssh timeout (60s): root@167.172.243.204 source /etc/ai-memory-a2a/env 2>/dev/null; bash /root/drive_agent.sh store w2-ai:charlie 'scenario1 write 2 from ai:charlie' scenario1-ai:charlie !! drive_agent store failed for ai:charlie i=2: __TIMEOUT_60s__ !! ssh timeout (60s): root@167.172.243.204 source /etc/ai-memory-a2a/env 2>/dev/null; bash /root/drive_agent.sh store w3-ai:charlie 'scenario1 write 3 from ai:charlie' scenario1-ai:charlie !! drive_agent store failed for ai:charlie i=3: __TIMEOUT_60s__ !! ssh timeout (60s): root@167.172.243.204 source /etc/ai-memory-a2a/env 2>/dev/null; bash /root/drive_agent.sh store w4-ai:charlie 'scenario1 write 4 from ai:charlie' scenario1-ai:charlie !! drive_agent store failed for ai:charlie i=4: __TIMEOUT_60s__ !! ssh timeout (60s): root@167.172.243.204 source /etc/ai-memory-a2a/env 2>/dev/null; bash /root/drive_agent.sh store w5-ai:charlie 'scenario1 write 5 from ai:charlie' scenario1-ai:charlie !! drive_agent store failed for ai:charlie i=5: __TIMEOUT_60s__