Campaign a2a-hermes-v0.6.2-rc.0-r3 PASS

Agent group: hermes (homogeneous)
ai-memory ref: v0.6.2-rc.0
Completed at: 2026-04-21T22:16:11Z
Overall pass: true
Skipped reports: 3

Infrastructure

Provider: digitalocean
Region: nyc3
Droplet size: s-2vcpu-4gb
Topology: 4-node federation mesh (W=2/N=4)
Scenarios started: 2026-04-21T21:25:58Z
Scenarios ended
Dispatched by: alphaonedev
Harness SHA: 4c34fb036794
Workflow run: https://github.com/alphaonedev/ai-memory-ai2ai-gate/actions/runs/24746837313

Node roster

#	Role	Agent ID	Public IP	Private IP
1	agent	`ai:alice`	`104.236.45.117`	`10.252.0.4`
2	agent	`ai:bob`	`138.197.29.64`	`10.252.0.3`
3	agent	`ai:charlie`	`138.197.38.214`	`10.252.0.5`
4	memory-only	`—`	`165.227.117.181`	`10.252.0.2`

Baseline attestation BASELINE OK

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: 1.3.0 — 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 v0.10.0 (2026.4.16)`	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	—	`fa358f9a9059`	PASS
node-2	`ai:bob`	`hermes Hermes Agent v0.10.0 (2026.4.16)`	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	—	`21635cf63640`	PASS
node-3	`ai:charlie`	`hermes Hermes Agent v0.10.0 (2026.4.16)`	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	—	`ce52d772ef5a`	PASS

a2a-baseline.json

{
	"baseline_pass": true,
	"per_node": [
		{
			"spec_version": "1.3.0",
			"agent_type": "hermes",
			"agent_id": "ai:alice",
			"node_index": "1",
			"framework_version": "Hermes Agent v0.10.0 (2026.4.16)",
			"ai_memory_version": "0.6.2-rc.0",
			"peer_urls": "http://10.252.0.3:9077,http://10.252.0.5:9077,http://10.252.0.2:9077",
			"config_file_sha256": "fa358f9a90597243fb96224babd541399bd7b1e972f364605308ab1e2d9dd2c7",
			"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": "117f9e84-bb22-4d1e-ab6d-969332a3dd56",
				"agent_mcp_canary_f2b": false,
				"agent_mcp_canary_uuid": "fdb664e0-30a7-408d-ad58-08c8a8125474",
				"agent_canary_response_head": "Traceback (most recent call last):   File \"/usr/local/bin/hermes\", line 11, in <module>     main()   File \"/root/.hermes/hermes-agent/hermes_cli/main.py\", line 8679, in main     args.func(args)   File \"/root/.hermes/hermes-agent/hermes_cli/main.py\", line 1083, in cmd_chat     if not _has_any_provider_configured():            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^   File \"/root/.hermes/hermes-agent/hermes_cli/main.py\", line 222, in _has_any_provider_configured     from hermes_cli.auth import get_auth_sta",
				"_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": "10.252.0.3:9077:OK,10.252.0.5:9077:OK,10.252.0.2:9077: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.",
				"agent_mcp_ai_memory_canary": true,
				"canary_uuid": "117f9e84-bb22-4d1e-ab6d-969332a3dd56",
				"canary_namespace": "_baseline_canary_f2a"
			},
			"baseline_pass": true
		},
		{
			"spec_version": "1.3.0",
			"agent_type": "hermes",
			"agent_id": "ai:bob",
			"node_index": "2",
			"framework_version": "Hermes Agent v0.10.0 (2026.4.16)",
			"ai_memory_version": "0.6.2-rc.0",
			"peer_urls": "http://10.252.0.4:9077,http://10.252.0.5:9077,http://10.252.0.2:9077",
			"config_file_sha256": "21635cf6364057fd2a004d28aac89abf8438671d85f9fd2ed1e654d812d23ff1",
			"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": "d3d725fa-7fdb-4d6e-b6f0-231f520d2367",
				"agent_mcp_canary_f2b": false,
				"agent_mcp_canary_uuid": "02ec1fd8-e5e0-4683-ab97-e4c429d184f6",
				"agent_canary_response_head": "Traceback (most recent call last):   File \"/usr/local/bin/hermes\", line 11, in <module>     main()   File \"/root/.hermes/hermes-agent/hermes_cli/main.py\", line 8679, in main     args.func(args)   File \"/root/.hermes/hermes-agent/hermes_cli/main.py\", line 1083, in cmd_chat     if not _has_any_provider_configured():            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^   File \"/root/.hermes/hermes-agent/hermes_cli/main.py\", line 222, in _has_any_provider_configured     from hermes_cli.auth import get_auth_sta",
				"_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": "10.252.0.4:9077:OK,10.252.0.5:9077:OK,10.252.0.2:9077: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.",
				"agent_mcp_ai_memory_canary": true,
				"canary_uuid": "d3d725fa-7fdb-4d6e-b6f0-231f520d2367",
				"canary_namespace": "_baseline_canary_f2a"
			},
			"baseline_pass": true
		},
		{
			"spec_version": "1.3.0",
			"agent_type": "hermes",
			"agent_id": "ai:charlie",
			"node_index": "3",
			"framework_version": "Hermes Agent v0.10.0 (2026.4.16)",
			"ai_memory_version": "0.6.2-rc.0",
			"peer_urls": "http://10.252.0.4:9077,http://10.252.0.3:9077,http://10.252.0.2:9077",
			"config_file_sha256": "ce52d772ef5a00968db29fb80eea7a14206b0a258a00ff2165db725405474618",
			"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": "00520c4f-79ba-413b-b470-a7e8a50378e1",
				"agent_mcp_canary_f2b": false,
				"agent_mcp_canary_uuid": "657216c5-14c7-426a-853e-6dea1099f044",
				"agent_canary_response_head": "Traceback (most recent call last):   File \"/usr/local/bin/hermes\", line 11, in <module>     main()   File \"/root/.hermes/hermes-agent/hermes_cli/main.py\", line 8679, in main     args.func(args)   File \"/root/.hermes/hermes-agent/hermes_cli/main.py\", line 1083, in cmd_chat     if not _has_any_provider_configured():            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^   File \"/root/.hermes/hermes-agent/hermes_cli/main.py\", line 222, in _has_any_provider_configured     from hermes_cli.auth import get_auth_sta",
				"_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": "10.252.0.4:9077:OK,10.252.0.3:9077:OK,10.252.0.2:9077: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.",
				"agent_mcp_ai_memory_canary": true,
				"canary_uuid": "00520c4f-79ba-413b-b470-a7e8a50378e1",
				"canary_namespace": "_baseline_canary_f2a"
			},
			"baseline_pass": true
		}
	]
}

raw file

F3 — peer A2A via shared memory F3 OK

Workflow-level probe answering "can agents communicate through ai-memory?". Writer ai:alice posted canary UUID cf0467a7-1c72-4e2b-a8a9-99bda5a6147c 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.

f3-peer-a2a.json

{
	"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": "cf0467a7-1c72-4e2b-a8a9-99bda5a6147c",
	"canary_namespace": "_baseline_peer_canary",
	"writer_agent": "ai:alice",
	"pass": true
}

raw file

AI NHI analysis

No per-campaign narrative recorded yet. scripts/analyze_run.py will generate one on the next dispatch.

Tests performed in this run

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
S1	Per-agent write + read (MCP stdio)	?
S1b	Per-agent write + read (HTTP)	PASS
S2	Shared-context handoff	PASS
S4	Federation-aware concurrent writes	PASS
S5	Consolidation + curation	PASS
S6	Contradiction detection	PASS
S9	Mutation round-trip	PASS
S10	Deletion propagation	PASS
S11	Link integrity	PASS
S12	Agent registration	?
S13	Concurrent write contention	PASS
S14	Partition tolerance	?

Scenario 1 — Per-agent write + read (MCP stdio) UNKNOWN

scenario-1.json (report)

raw file

scenario-1.log (console trace)

[scenario-1 hermes] phase A: each agent writes 10 memories via MCP
[scenario-1 hermes]   agent ai:alice on node-a (104.236.45.117)
Traceback (most recent call last):
  File "/usr/local/bin/hermes", line 11, in <module>
    main()
  File "/root/.hermes/hermes-agent/hermes_cli/main.py", line 8679, in main
    args.func(args)
  File "/root/.hermes/hermes-agent/hermes_cli/main.py", line 1083, in cmd_chat
    if not _has_any_provider_configured():
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/.hermes/hermes-agent/hermes_cli/main.py", line 222, in _has_any_provider_configured
    from hermes_cli.auth import get_auth_status
  File "/root/.hermes/hermes-agent/hermes_cli/auth.py", line 38, in <module>
    import httpx
ModuleNotFoundError: No module named 'httpx'

raw file

Scenario 1b — Per-agent write + read (HTTP) PASS

scenario-1b.json (report)

{
	"scenario": "1b",
	"pass": true,
	"agent_group": "hermes",
	"path": "serve-http",
	"expected_per_reader": 20,
	"per_agent": {
		"ai:alice": {
			"recall": 20
		},
		"ai:bob": {
			"recall": 20
		},
		"ai:charlie": {
			"recall": 20
		}
	},
	"reasons": []
}

raw file

scenario-1b.log (console trace)

[scenario-1b hermes] phase A: each agent POSTs 10 memories to local serve
[scenario-1b hermes]   agent ai:alice on node-a (104.236.45.117)
[scenario-1b hermes]   agent ai:bob on node-b (138.197.29.64)
[scenario-1b hermes]   agent ai:charlie on node-c (138.197.38.214)
[scenario-1b hermes] settle 15s for W=2/N=4 convergence
[scenario-1b hermes] phase B: each reader counts rows in the OTHER two namespaces via local serve
[scenario-1b hermes]   ai:alice sees 20 rows from the other two namespaces
[scenario-1b hermes]   ai:bob sees 20 rows from the other two namespaces
[scenario-1b hermes]   ai:charlie sees 20 rows from the other two namespaces
[scenario-1b hermes] phase C: cross-cluster identity verification via node-4
[scenario-1b hermes]   ns=scenario1b-ai:alice count=10 wrong_agent_id=0
[scenario-1b hermes]   ns=scenario1b-ai:bob count=10 wrong_agent_id=0
[scenario-1b hermes]   ns=scenario1b-ai:charlie count=10 wrong_agent_id=0

raw file

Scenario 2 — Shared-context handoff PASS

scenario-2.json (report)

{
	"scenario": "2",
	"pass": true,
	"agent_group": "hermes",
	"path": "serve-http",
	"per_agent": {
		"ai:bob": {
			"sees_handoff": 1
		},
		"ai:alice": {
			"sees_ack": 1
		}
	},
	"handoff_uuid": "b68dbea8-5b93-4151-86da-7fa04c01c77f",
	"ack_uuid": "419947b5-4740-455a-922e-3da020b79dc0",
	"reasons": []
}

raw file

scenario-2.log (console trace)

[scenario-2 hermes] phase A: ai:alice writes handoff to ai:bob (uuid=b68dbea8-5b93-4151-86da-7fa04c01c77f)
[scenario-2 hermes] settle 8s for quorum fanout
[scenario-2 hermes] phase B: ai:bob reads handoff on node-2
[scenario-2 hermes]   ai:bob sees 1 handoff memories from ai:alice
[scenario-2 hermes] phase C: ai:bob writes acknowledgement (uuid=419947b5-4740-455a-922e-3da020b79dc0)
[scenario-2 hermes] settle 8s for reverse-direction fanout
[scenario-2 hermes] phase D: ai:alice reads ack on node-1
[scenario-2 hermes]   ai:alice sees 1 ack memories from ai:bob

raw file

Scenario 4 — Federation-aware concurrent writes PASS

scenario-4.json (report)

{
	"scenario": "4",
	"pass": true,
	"agent_group": "hermes",
	"expected_per_agent": 30,
	"per_agent": {
		"ai:alice": {
			"count": 30,
			"wrong_agent_id": 0
		},
		"ai:bob": {
			"count": 30,
			"wrong_agent_id": 0
		},
		"ai:charlie": {
			"count": 30,
			"wrong_agent_id": 0
		}
	},
	"reasons": []
}

raw file

scenario-4.log (console trace)

[scenario-4 hermes] phase A: launching concurrent 30-row bursts from 3 agents
[scenario-4 hermes] all 3 bursts complete; settle 20s for W=2 fanout convergence
[scenario-4 hermes] phase B: querying node-4 aggregator for per-agent counts
[scenario-4 hermes]   ai:alice: count=30 (expected 30) wrong_agent_id=0
[scenario-4 hermes]   ai:bob: count=30 (expected 30) wrong_agent_id=0
[scenario-4 hermes]   ai:charlie: count=30 (expected 30) wrong_agent_id=0

raw file

Scenario 5 — Consolidation + curation PASS

scenario-5.json (report)

{
	"scenario": "5",
	"pass": true,
	"agent_group": "hermes",
	"consolidated_id": "76dce9ed-c61f-4a13-a2a6-27a628dae5e7",
	"consolidate_http_code": "201",
	"consolidated_from_agents": "[\"ai:charlie\",\"ai:bob\",\"ai:alice\"]",
	"reasons": []
}

raw file

scenario-5.log (console trace)

[scenario-5 hermes] phase A: each agent writes 3 related memories
[scenario-5 hermes]   ai:alice on 104.236.45.117
[scenario-5 hermes]   ai:bob on 138.197.29.64
[scenario-5 hermes]   ai:charlie on 138.197.38.214
[scenario-5 hermes] phase B: collect source memory IDs on node-1, then trigger consolidate
[scenario-5 hermes]   source ids: ["35a4ee8d-9826-4110-95b1-6d0770c96169","939bed89-712d-40a9-adc8-153f8d3a35bc","604388c6-1eee-4fb9-8c67-96e030b5f022","4f423c92-a453-4b75-bbf9-aabdac474f5c","d6b13b2b-f4fd-496b-beee-f7fee99385a6","320d92f9-b677-4dac-ae2c-dd01da546622","18161682-bbf5-4619-b1d6-7daae01b3d0e","7dadb9f9-b43c-440d-b4d7-8ea547ff9feb","4292a9ce-7ed6-4927-9cea-81831adc6871"]
[scenario-5 hermes]   consolidate returned HTTP 201
[scenario-5 hermes]   consolidated memory id=76dce9ed-c61f-4a13-a2a6-27a628dae5e7
[scenario-5 hermes] phase C: verifying consolidated_from_agents on node-4
[scenario-5 hermes]   consolidated_from_agents=["ai:charlie","ai:bob","ai:alice"]

raw file

Scenario 6 — Contradiction detection PASS

scenario-6.json (report)

{
	"scenario": "6",
	"pass": true,
	"agent_group": "hermes",
	"topic": "sky-color-1265bf74",
	"alice_id": "ffb0fa27-5fb8-4e98-8450-75210500a424",
	"bob_id": "998fa3a8-2fb4-48c9-b468-25cdd30aa29a",
	"detect_http_code": "200",
	"charlie_sees_both_memories": 1,
	"charlie_sees_contradicts_link": 1,
	"reasons": []
}

raw file

scenario-6.log (console trace)

[scenario-6 hermes] alice writes claim: "sky-color-1265bf74 is blue" on node-1
[scenario-6 hermes] bob writes contradicting claim: "sky-color-1265bf74 is red" on node-2
[scenario-6 hermes]   alice.id=ffb0fa27-5fb8-4e98-8450-75210500a424 bob.id=998fa3a8-2fb4-48c9-b468-25cdd30aa29a
[scenario-6 hermes] charlie queries memory_detect_contradiction on node-3
[scenario-6 hermes]   HTTP 200; body length=1117
[scenario-6 hermes]   sees both memories: 1; sees contradicts link: 1

raw file

Scenario 9 — Mutation round-trip PASS

scenario-9.json (report)

{
	"scenario": "9",
	"pass": true,
	"agent_group": "hermes",
	"m1_id": "d06833d7-ea57-4c6a-9b72-37bd315f2bdd",
	"v1_uuid": "091cc57b-8a0a-474c-870d-263d85296700",
	"v2_uuid": "73e71b44-7c60-4f85-91e0-c5369d0fd89f",
	"put_http_code": "200",
	"charlie_view": {
		"content": "73e71b44-7c60-4f85-91e0-c5369d0fd89f",
		"agent_id": "ai:alice"
	},
	"reasons": []
}

raw file

scenario-9.log (console trace)

[scenario-9 hermes] alice writes M1 content=091cc57b-8a0a-474c-870d-263d85296700 on node-1
[scenario-9 hermes]   created memory id=d06833d7-ea57-4c6a-9b72-37bd315f2bdd
[scenario-9 hermes] bob updates M1 content=73e71b44-7c60-4f85-91e0-c5369d0fd89f on node-2 via PUT
[scenario-9 hermes]   PUT returned HTTP 200
[scenario-9 hermes] charlie reads M1 on node-3 and checks content + provenance
[scenario-9 hermes]   charlie sees content="73e71b44-7c60-4f85-91e0-c5369d0fd89f" agent_id="ai:alice"

raw file

Scenario 10 — Deletion propagation PASS

scenario-10.json (report)

{
	"scenario": "10",
	"pass": true,
	"agent_group": "hermes",
	"m1_id": "0087e671-75de-404c-955f-6c4ee8117048",
	"uuid": "1fa147b2-c2e4-4398-89f7-2b080fd263bb",
	"delete_http_code": "200",
	"pre_delete_visible_peers": 3,
	"post_delete_still_visible_peers": 0,
	"reasons": []
}

raw file

scenario-10.log (console trace)

[scenario-10 hermes] alice writes M1 content=1fa147b2-c2e4-4398-89f7-2b080fd263bb on node-1
[scenario-10 hermes]   created memory id=0087e671-75de-404c-955f-6c4ee8117048
[scenario-10 hermes] pre-delete: verifying M1 is visible on all peers
[scenario-10 hermes]   pre-delete node-2 sees 1
[scenario-10 hermes]   pre-delete node-3 sees 1
[scenario-10 hermes]   pre-delete node-4 sees 1
[scenario-10 hermes] alice deletes M1 on node-1
[scenario-10 hermes]   DELETE returned HTTP 200
[scenario-10 hermes] post-delete: verifying M1 is GONE from all peers
[scenario-10 hermes]   post-delete node-2 sees 0 (expected 0)
[scenario-10 hermes]   post-delete node-3 sees 0 (expected 0)
[scenario-10 hermes]   post-delete node-4 sees 0 (expected 0)

raw file

Scenario 11 — Link integrity PASS

scenario-11.json (report)

{
	"scenario": "11",
	"pass": true,
	"agent_group": "hermes",
	"m1_id": "b01a7380-6fa5-4ed5-bb1f-0f134e0056b4",
	"m2_id": "d069ab93-e247-4694-941d-75ff4181691f",
	"relation": "related_to",
	"link_http_code": "201",
	"charlie_sees_link": 1,
	"reasons": []
}

raw file

scenario-11.log (console trace)

[scenario-11 hermes] alice writes M1 on node-1
[scenario-11 hermes] bob writes M2 on node-2
[scenario-11 hermes]   M1=b01a7380-6fa5-4ed5-bb1f-0f134e0056b4 M2=d069ab93-e247-4694-941d-75ff4181691f
[scenario-11 hermes] alice links M1 -> M2 with relation=related_to
[scenario-11 hermes]   link POST returned HTTP 201
[scenario-11 hermes] charlie queries links of M1 on node-3
[scenario-11 hermes]   charlie sees M1->M2 link: 1 (expected >=1)

raw file

Scenario 12 — Agent registration UNKNOWN

scenario-12.json (report)

raw file

scenario-12.log (console trace)

[scenario-12 hermes] alice registers new agent ai:dave-probe-decc26a6 on node-1
[scenario-12 hermes]   POST /api/v1/agents returned HTTP 422

raw file

Scenario 13 — Concurrent write contention PASS

scenario-13.json (report)

{
	"scenario": "13",
	"pass": true,
	"agent_group": "hermes",
	"m1_id": "6ee89f3e-963f-40f4-bf70-c73dfa946d4f",
	"submitted": {
		"v0": "5c5a3e7c-9f58-4438-9333-cef6d69c14ae",
		"vA_alice": "2f758745-f59b-4684-a50c-0165140ac19f",
		"vB_bob": "5f40919a-4f65-43aa-b0ab-5134aaf285d9"
	},
	"peer_view": {
		"node_1": "2f758745-f59b-4684-a50c-0165140ac19f",
		"node_2": "2f758745-f59b-4684-a50c-0165140ac19f",
		"node_3": "2f758745-f59b-4684-a50c-0165140ac19f",
		"node_4": "2f758745-f59b-4684-a50c-0165140ac19f"
	},
	"reasons": []
}

raw file

scenario-13.log (console trace)

[scenario-13 hermes] alice writes M1 content=v0 on node-1
[scenario-13 hermes]   M1 id=6ee89f3e-963f-40f4-bf70-c73dfa946d4f
[scenario-13 hermes] alice + bob issue concurrent PUTs (vA=2f758745-f59b-4684-a50c-0165140ac19f from alice, vB=5f40919a-4f65-43aa-b0ab-5134aaf285d9 from bob)
[scenario-13 hermes] settle 10s for quorum convergence
[scenario-13 hermes]   node-1 sees content=2f758745-f59b-4684-a50c-0165140ac19f
[scenario-13 hermes]   node-2 sees content=2f758745-f59b-4684-a50c-0165140ac19f
[scenario-13 hermes]   node-3 sees content=2f758745-f59b-4684-a50c-0165140ac19f
[scenario-13 hermes]   node-4 sees content=2f758745-f59b-4684-a50c-0165140ac19f

raw file

Scenario 14 — Partition tolerance UNKNOWN

scenario-14.json (report)

raw file

scenario-14.log (console trace)

[scenario-14 hermes] suspending ai-memory on node-3 (SIGSTOP)

raw file

All artifacts

Generated by scripts/generate_run_html.sh. Methodology: alphaonedev.github.io/ai-memory-ai2ai-gate/methodology. Analysis source: analysis/run-insights.json.