../ runs index

Campaign a2a-hermes-v0.6.1-r16 FAIL

Agent group
hermes (homogeneous)
ai-memory ref
v0.6.1
Completed at
2026-04-21T16:43:48Z
Overall pass
false
Skipped reports
2

Infrastructure

Provider
digitalocean
Region
nyc3
Droplet size
s-2vcpu-4gb
Topology
4-node federation mesh (W=2/N=4)
Scenarios started
2026-04-21T16:33:55Z
Scenarios ended
2026-04-21T16:43:48Z
Dispatched by
alphaonedev
Harness SHA
d4dc21e0f280
Workflow run
https://github.com/alphaonedev/ai-memory-ai2ai-gate/actions/runs/24733764767

Node roster

#RoleAgent IDPublic IPPrivate IP
1agentai:alice45.55.136.5110.252.0.3
2agentai:bob165.227.101.010.252.0.2
3agentai:charlie143.198.31.210.252.0.5
4memory-only—165.227.191.21410.252.0.4

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: 1.2.0 — see authoritative baseline.

NodeAgentFrameworkAuthenticMCP ai-memoryxAI cfgxAI defaultAgent IDFederationUFW offiptablesdead-manF1 xAIF2a substrateF2b agent (non-gating)Config SHAPass
node-1ai:alicehermes Hermes Agent v0.10.0 (2026.4.16)✅✅✅✅✅✅✅✅✅✅✅—fa358f9a9059PASS
node-2ai:bobhermes Hermes Agent v0.10.0 (2026.4.16)✅✅✅✅✅✅✅✅✅✅✅—21635cf63640PASS
node-3ai:charliehermes Hermes Agent v0.10.0 (2026.4.16)✅✅✅✅✅✅✅✅✅✅✅—ce52d772ef5aPASS
a2a-baseline.json 
{
	"baseline_pass": true,
	"per_node": [
		{
			"spec_version": "1.2.0",
			"agent_type": "hermes",
			"agent_id": "ai:alice",
			"node_index": "1",
			"framework_version": "Hermes Agent v0.10.0 (2026.4.16)",
			"ai_memory_version": "0.6.1",
			"peer_urls": "http://10.252.0.2:9077,http://10.252.0.5:9077,http://10.252.0.4:9077",
			"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": "Imustdeclinethisrequestasitappearstobe",
				"substrate_http_canary_f2a": true,
				"substrate_http_canary_uuid": "6f42f6c7-931b-4c1e-a61e-f57da9044fd1",
				"agent_mcp_canary_f2b": false,
				"agent_mcp_canary_uuid": "9c53eed0-5e1e-4889-895b-84f9d59ecef8",
				"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": "10.252.0.2:9077:OK,10.252.0.5:9077:OK,10.252.0.4:9077: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.",
				"agent_mcp_ai_memory_canary": true,
				"canary_uuid": "6f42f6c7-931b-4c1e-a61e-f57da9044fd1",
				"canary_namespace": "_baseline_canary_f2a"
			},
			"baseline_pass": true
		},
		{
			"spec_version": "1.2.0",
			"agent_type": "hermes",
			"agent_id": "ai:bob",
			"node_index": "2",
			"framework_version": "Hermes Agent v0.10.0 (2026.4.16)",
			"ai_memory_version": "0.6.1",
			"peer_urls": "http://10.252.0.3:9077,http://10.252.0.5:9077,http://10.252.0.4:9077",
			"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": "9ebcc76e-18d4-4a86-9ce2-fe053879631b",
				"agent_mcp_canary_f2b": false,
				"agent_mcp_canary_uuid": "7a8c26d7-1062-4ec9-b076-652ee15f0059",
				"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,10.252.0.4:9077: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.",
				"agent_mcp_ai_memory_canary": true,
				"canary_uuid": "9ebcc76e-18d4-4a86-9ce2-fe053879631b",
				"canary_namespace": "_baseline_canary_f2a"
			},
			"baseline_pass": true
		},
		{
			"spec_version": "1.2.0",
			"agent_type": "hermes",
			"agent_id": "ai:charlie",
			"node_index": "3",
			"framework_version": "Hermes Agent v0.10.0 (2026.4.16)",
			"ai_memory_version": "0.6.1",
			"peer_urls": "http://10.252.0.3:9077,http://10.252.0.2:9077,http://10.252.0.4:9077",
			"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": "9897fcb3-acd4-41a6-bac2-af51ab6082d1",
				"agent_mcp_canary_f2b": false,
				"agent_mcp_canary_uuid": "29a55346-a64a-4e9a-8863-d23e87e82121",
				"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,10.252.0.2:9077:OK,10.252.0.4:9077: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.",
				"agent_mcp_ai_memory_canary": true,
				"canary_uuid": "9897fcb3-acd4-41a6-bac2-af51ab6082d1",
				"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 4fb3ca99-23f5-4ed9-be8f-931fa5d5fa7d 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": "4fb3ca99-23f5-4ed9-be8f-931fa5d5fa7d",
	"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.

IDTitleResultReason
S1Per-agent write + read (MCP stdio)?
S1bPer-agent write + read (HTTP)PASS
S2Shared-context handoffPASS
S4Federation-aware concurrent writesPASS
S5Consolidation + curationPASS
S6Contradiction detectionPASS
S9Mutation round-tripPASS
S10Deletion propagationPASS
S11Link integrity?
S12Agent registration?
S13Concurrent write contentionPASS
S14Partition tolerancePASS
S15Read-your-writesPASS
S16Tier promotionPASS
S17Stats consistencyPASS
S18Semantic query expansion?

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 (45.55.136.51)
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 (45.55.136.51)
[scenario-1b hermes]   agent ai:bob on node-b (165.227.101.0)
[scenario-1b hermes]   agent ai:charlie on node-c (143.198.31.2)
[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": "8fc9b3dd-5ee0-42b9-af34-a489a5e7c769",
	"ack_uuid": "fa41fefb-5f19-4256-8de8-0d350928b7ed",
	"reasons": []
}


          
raw file

        

        
scenario-2.log (console trace)
          
[scenario-2 hermes] phase A: ai:alice writes handoff to ai:bob (uuid=8fc9b3dd-5ee0-42b9-af34-a489a5e7c769)
[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=fa41fefb-5f19-4256-8de8-0d350928b7ed)
[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": "55cba3dd-21d4-4e9b-b56d-995bd23be3df",
	"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 45.55.136.51
[scenario-5 hermes]   ai:bob on 165.227.101.0
[scenario-5 hermes]   ai:charlie on 143.198.31.2
[scenario-5 hermes] phase B: collect source memory IDs on node-1, then trigger consolidate
[scenario-5 hermes]   source ids: ["43c854fe-6d2b-41cd-a8ba-0bfefb1a8703","4667e5c4-e574-46d3-9651-23698abe47de","9dfc0ec7-9543-4047-a1df-d89f8240841e","ef041825-db43-48e0-b2de-55d8404b4ab9","feb01b98-c2d2-4f3d-9386-28cfeece6e5c","636261f9-8b49-47f5-a80d-f2b1fb508538","d73415e6-040a-4793-bb5f-bab166e3eeed","f34e685b-3626-4cee-aa1b-1996cedf72da","71500484-13bf-4775-8cda-b7dcc3d3dbb0"]
[scenario-5 hermes]   consolidate returned HTTP 201
[scenario-5 hermes]   consolidated memory id=55cba3dd-21d4-4e9b-b56d-995bd23be3df
[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-6bc88509",
	"alice_id": "200d1875-d926-45ea-8710-489aef9b09d4",
	"bob_id": "1c3af1d4-62ad-49ba-8f78-699321178596",
	"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-6bc88509 is blue" on node-1
[scenario-6 hermes] bob writes contradicting claim: "sky-color-6bc88509 is red" on node-2
[scenario-6 hermes]   alice.id=200d1875-d926-45ea-8710-489aef9b09d4 bob.id=1c3af1d4-62ad-49ba-8f78-699321178596
[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": "f8ed7aa1-ba60-4e1a-88c5-eee429ce158d",
	"v1_uuid": "d21dd521-a2df-460e-a3bc-f3112cc93506",
	"v2_uuid": "69d5f9f7-0aef-4b99-9704-c66e1f490793",
	"put_http_code": "200",
	"charlie_view": {
		"content": "69d5f9f7-0aef-4b99-9704-c66e1f490793",
		"agent_id": "ai:alice"
	},
	"reasons": []
}


          
raw file

        

        
scenario-9.log (console trace)
          
[scenario-9 hermes] alice writes M1 content=d21dd521-a2df-460e-a3bc-f3112cc93506 on node-1
[scenario-9 hermes]   created memory id=f8ed7aa1-ba60-4e1a-88c5-eee429ce158d
[scenario-9 hermes] bob updates M1 content=69d5f9f7-0aef-4b99-9704-c66e1f490793 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="69d5f9f7-0aef-4b99-9704-c66e1f490793" agent_id="ai:alice"


          
raw file

        

      

      

        
Scenario 10 — Deletion propagation PASS

        
scenario-10.json (report)
          
{
	"scenario": "10",
	"pass": true,
	"agent_group": "hermes",
	"m1_id": "a8416a30-d7f4-420c-bed4-8d744242b7f8",
	"uuid": "60e3a644-b1e4-4e18-99ad-119ae062b648",
	"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=60e3a644-b1e4-4e18-99ad-119ae062b648 on node-1
[scenario-10 hermes]   created memory id=a8416a30-d7f4-420c-bed4-8d744242b7f8
[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 FAIL

        
Reasons: charlie could not see M1->M2 link after settle

        
scenario-11.json (report)
          
{
	"scenario": "11",
	"pass": false,
	"agent_group": "hermes",
	"m1_id": "30da1735-9a47-4690-bc4d-4d6548fb4b97",
	"m2_id": "de6b77b9-9197-403e-942f-16514d939f42",
	"relation": "related_to",
	"link_http_code": "201",
	"charlie_sees_link": 0,
	"reasons": [
		"charlie could not see M1->M2 link after settle"
	]
}


          
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=30da1735-9a47-4690-bc4d-4d6548fb4b97 M2=de6b77b9-9197-403e-942f-16514d939f42
[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: 0 (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-b623daf4 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": "c7fea25f-da2f-4c7d-94ad-098f0c78f897",
	"submitted": {
		"v0": "b5f59556-8449-4cfc-9dd7-4b937eef91d7",
		"vA_alice": "705e1fc9-4ce6-4fd8-9923-b1e3d2f6b1ff",
		"vB_bob": "9c988d5d-4b8f-4812-aa92-0eb47f751f0b"
	},
	"peer_view": {
		"node_1": "9c988d5d-4b8f-4812-aa92-0eb47f751f0b",
		"node_2": "9c988d5d-4b8f-4812-aa92-0eb47f751f0b",
		"node_3": "9c988d5d-4b8f-4812-aa92-0eb47f751f0b",
		"node_4": "9c988d5d-4b8f-4812-aa92-0eb47f751f0b"
	},
	"reasons": []
}


          
raw file

        

        
scenario-13.log (console trace)
          
[scenario-13 hermes] alice writes M1 content=v0 on node-1
[scenario-13 hermes]   M1 id=c7fea25f-da2f-4c7d-94ad-098f0c78f897
[scenario-13 hermes] alice + bob issue concurrent PUTs (vA=705e1fc9-4ce6-4fd8-9923-b1e3d2f6b1ff from alice, vB=9c988d5d-4b8f-4812-aa92-0eb47f751f0b from bob)
[scenario-13 hermes] settle 10s for quorum convergence
[scenario-13 hermes]   node-1 sees content=9c988d5d-4b8f-4812-aa92-0eb47f751f0b
[scenario-13 hermes]   node-2 sees content=9c988d5d-4b8f-4812-aa92-0eb47f751f0b
[scenario-13 hermes]   node-3 sees content=9c988d5d-4b8f-4812-aa92-0eb47f751f0b
[scenario-13 hermes]   node-4 sees content=9c988d5d-4b8f-4812-aa92-0eb47f751f0b


          
raw file

        

      

      

        
Scenario 14 — Partition tolerance PASS

        
scenario-14.json (report)
          
{
	"scenario": "14",
	"pass": true,
	"agent_group": "hermes",
	"partition_target": "node-3",
	"expected_post_recovery": 20,
	"node3_saw": 20,
	"reasons": []
}


          
raw file

        

        
scenario-14.log (console trace)
          
[scenario-14 hermes] suspending ai-memory on node-3 (SIGSTOP)
[scenario-14 hermes] writing 10 memories each from alice + bob during node-3 outage
[scenario-14 hermes] resuming ai-memory on node-3 (SIGCONT)
[scenario-14 hermes] settle 20s for post-partition catchup
[scenario-14 hermes] checking node-3 caught up
[scenario-14 hermes]   node-3 sees 20 memories in scenario14-partition (expected 20)


          
raw file

        

      

      

        
Scenario 15 — Read-your-writes PASS

        
scenario-15.json (report)
          
{
	"scenario": "15",
	"pass": true,
	"agent_group": "hermes",
	"uuid": "39372635-7d3a-4ed9-b45c-2000e95044ed",
	"writer_sees_own_write": 1,
	"reasons": []
}


          
raw file

        

        
scenario-15.log (console trace)
          
[scenario-15 hermes] alice writes + immediately reads M1 on node-1 (uuid=39372635-7d3a-4ed9-b45c-2000e95044ed)
[scenario-15 hermes]   alice sees 1 (expected 1) immediately after write


          
raw file

        

      

      

        
Scenario 16 — Tier promotion PASS

        
scenario-16.json (report)
          
{
	"scenario": "16",
	"pass": true,
	"agent_group": "hermes",
	"m1_id": "87a78de8-7abb-45a9-b8c9-8c020ca4121a",
	"promote_http_code": "200",
	"bob_sees_tier": "long",
	"reasons": []
}


          
raw file

        

        
scenario-16.log (console trace)
          
[scenario-16 hermes] alice writes M1 tier=short on node-1
[scenario-16 hermes]   M1 id=87a78de8-7abb-45a9-b8c9-8c020ca4121a
[scenario-16 hermes] alice promotes M1 to tier=long
[scenario-16 hermes]   promote returned HTTP 200
[scenario-16 hermes] bob reads M1 on node-2 and checks tier
[scenario-16 hermes]   bob sees tier=long (expected long)


          
raw file

        

      

      

        
Scenario 17 — Stats consistency PASS

        
scenario-17.json (report)
          
{
	"scenario": "17",
	"pass": true,
	"agent_group": "hermes",
	"expected_count": 15,
	"per_peer": {
		"node_1": 15,
		"node_2": 15,
		"node_3": 15,
		"node_4": 15
	},
	"reasons": []
}


          
raw file

        

        
scenario-17.log (console trace)
          
[scenario-17 hermes] phase A: each of 3 agents writes 5 memories to scenario17-stats
[scenario-17 hermes]   ai:alice on 45.55.136.51
[scenario-17 hermes]   ai:bob on 165.227.101.0
[scenario-17 hermes]   ai:charlie on 143.198.31.2
[scenario-17 hermes] settle 15s for W=2 fanout
[scenario-17 hermes] phase B: querying count on every peer
[scenario-17 hermes]   node-1 count=15 (expected 15)
[scenario-17 hermes]   node-2 count=15 (expected 15)
[scenario-17 hermes]   node-3 count=15 (expected 15)
[scenario-17 hermes]   node-4 count=15 (expected 15)


          
raw file

        

      

      

        
Scenario 18 — Semantic query expansion FAIL

        
Reasons: semantic query did not surface alice's memory | semantic query did not surface bob's memory

        
scenario-18.json (report)
          
{
	"scenario": "18",
	"pass": false,
	"agent_group": "hermes",
	"query": "morning outdoor exercise routine",
	"writers": [
		{
			"agent": "ai:alice",
			"marker": "alice-sunrise-4c2a4cfc-f0a5-49a9-b091-84c2c2fbb18f",
			"seen_by_charlie": 0
		},
		{
			"agent": "ai:bob",
			"marker": "bob-daybreak-e1ae71c6-6203-478e-a441-2db887fdcb4b",
			"seen_by_charlie": 0
		}
	],
	"reasons": [
		"semantic query did not surface alice's memory",
		"semantic query did not surface bob's memory"
	]
}


          
raw file

        

        
scenario-18.log (console trace)
          
[scenario-18 hermes] alice writes A on node-1
[scenario-18 hermes] bob writes B on node-2
[scenario-18 hermes] settle 15s for fanout + index rebuild
[scenario-18 hermes] charlie queries on node-3 with semantically-related prompt
[scenario-18 hermes]   charlie sees alice's memory: 0 (expected >=1)
[scenario-18 hermes]   charlie sees bob's memory: 0 (expected >=1)


          
raw file

        

      

    

      
All artifacts