../ runs index

Campaign a2a-hermes-v0.6.0-r14 FAIL

Agent group
hermes (homogeneous)
ai-memory ref
v0.6.0
Completed at
2026-04-21T02:56:30Z
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
2026-04-21T02:46:37Z
Scenarios ended
2026-04-21T02:56:30Z
Dispatched by
alphaonedev
Harness SHA
922fd981e627
Workflow run
https://github.com/alphaonedev/ai-memory-ai2ai-gate/actions/runs/24701083213

Node roster

#RoleAgent IDPublic IPPrivate IP
1agentai:alice157.245.219.20510.252.0.5
2agentai:bob167.172.234.17510.252.0.2
3agentai:charlie68.183.145.11010.252.0.4
4memory-only—167.71.181.16810.252.0.3

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": "0.6.0",
			"peer_urls": "http://10.252.0.2:9077,http://10.252.0.4:9077,http://10.252.0.3:9077",
			"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": "f028b7f1-8f94-4cb7-9d57-5e1224aa1073",
				"agent_mcp_canary_f2b": false,
				"agent_mcp_canary_uuid": "ecf89ed9-a3ed-443a-a904-c2f59a34b133",
				"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 8487, in main     args.func(args)   File \"/root/.hermes/hermes-agent/hermes_cli/main.py\", line 1071, in cmd_chat     if not _has_any_provider_configured():            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^   File \"/root/.hermes/hermes-agent/hermes_cli/main.py\", line 209, 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.",
				"agent_mcp_ai_memory_canary": true,
				"canary_uuid": "f028b7f1-8f94-4cb7-9d57-5e1224aa1073",
				"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": "0.6.0",
			"peer_urls": "http://10.252.0.5:9077,http://10.252.0.4:9077,http://10.252.0.3:9077",
			"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": "903fb38f-b04c-44df-bc52-82f54d57880b",
				"agent_mcp_canary_f2b": false,
				"agent_mcp_canary_uuid": "85411d61-9049-475a-bbc3-8c3d3fdcbdfc",
				"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 8487, in main     args.func(args)   File \"/root/.hermes/hermes-agent/hermes_cli/main.py\", line 1071, in cmd_chat     if not _has_any_provider_configured():            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^   File \"/root/.hermes/hermes-agent/hermes_cli/main.py\", line 209, 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.",
				"agent_mcp_ai_memory_canary": true,
				"canary_uuid": "903fb38f-b04c-44df-bc52-82f54d57880b",
				"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": "0.6.0",
			"peer_urls": "http://10.252.0.5:9077,http://10.252.0.2:9077,http://10.252.0.3:9077",
			"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": "9f89dce1-64c5-4777-aa3a-620221a21431",
				"agent_mcp_canary_f2b": false,
				"agent_mcp_canary_uuid": "121baf7b-9271-4d5f-ab23-2375e6232f8d",
				"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 8487, in main     args.func(args)   File \"/root/.hermes/hermes-agent/hermes_cli/main.py\", line 1071, in cmd_chat     if not _has_any_provider_configured():            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^   File \"/root/.hermes/hermes-agent/hermes_cli/main.py\", line 209, 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.",
				"agent_mcp_ai_memory_canary": true,
				"canary_uuid": "9f89dce1-64c5-4777-aa3a-620221a21431",
				"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 91e8dcc0-8031-438c-95c4-1e47bcb59b17 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": "91e8dcc0-8031-438c-95c4-1e47bcb59b17",
	"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 + curation?
S6Contradiction detection?
S9Mutation round-trip?
S10Deletion propagation?
S11Link integrity?
S12Agent registration?
S13Concurrent write contention?
S14Partition tolerance?
S15Read-your-writesPASS
S16Tier promotion?
S17Stats consistency?
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 (157.245.219.205)
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 8487, in main
    args.func(args)
  File "/root/.hermes/hermes-agent/hermes_cli/main.py", line 1071, in cmd_chat
    if not _has_any_provider_configured():
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/.hermes/hermes-agent/hermes_cli/main.py", line 209, 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 (157.245.219.205)
[scenario-1b hermes]   agent ai:bob on node-b (167.172.234.175)
[scenario-1b hermes]   agent ai:charlie on node-c (68.183.145.110)
[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": "0336ff7c-dd35-4e4c-b69b-3671def65e6a",
	"ack_uuid": "eca0b1a5-4233-49f6-8fae-6c7792d8deb4",
	"reasons": []
}


          
raw file

        

        
scenario-2.log (console trace)
          
[scenario-2 hermes] phase A: ai:alice writes handoff to ai:bob (uuid=0336ff7c-dd35-4e4c-b69b-3671def65e6a)
[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=eca0b1a5-4233-49f6-8fae-6c7792d8deb4)
[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 FAIL

        
Reasons: consolidate endpoint returned HTTP 405 — may not exist in this ai-memory version | consolidate did not return a new memory id

        
scenario-5.json (report)
          
{
	"scenario": "5",
	"pass": false,
	"agent_group": "hermes",
	"consolidated_id": "",
	"consolidate_http_code": "405",
	"consolidated_from_agents": "",
	"reasons": [
		"consolidate endpoint returned HTTP 405 — may not exist in this ai-memory version",
		"consolidate did not return a new memory id"
	]
}


          
raw file

        

        
scenario-5.log (console trace)
          
[scenario-5 hermes] phase A: each agent writes 3 related memories
[scenario-5 hermes]   ai:alice on 157.245.219.205
[scenario-5 hermes]   ai:bob on 167.172.234.175
[scenario-5 hermes]   ai:charlie on 68.183.145.110
[scenario-5 hermes] phase B: trigger memory_consolidate on node-1
[scenario-5 hermes]   consolidate returned HTTP 405
[scenario-5 hermes]   consolidated memory id=
[scenario-5 hermes] phase C: verifying consolidated_from_agents on node-4
[scenario-5 hermes]   consolidated_from_agents=


          
raw file

        

      

      

        
Scenario 6 — Contradiction detection FAIL

        
Reasons: detect_contradiction endpoint returned HTTP 404 — may not exist in this ai-memory version | response did not include both memories | response did not include a contradicts relation

        
scenario-6.json (report)
          
{
	"scenario": "6",
	"pass": false,
	"agent_group": "hermes",
	"topic": "sky-color-0e2fdf4c",
	"alice_id": "2be31495-67c1-4d76-b691-a3ce44210c94",
	"bob_id": "2be31495-67c1-4d76-b691-a3ce44210c94",
	"detect_http_code": "404",
	"charlie_sees_both_memories": 0,
	"charlie_sees_contradicts_link": 0,
	"reasons": [
		"detect_contradiction endpoint returned HTTP 404 — may not exist in this ai-memory version",
		"response did not include both memories",
		"response did not include a contradicts relation"
	]
}


          
raw file

        

        
scenario-6.log (console trace)
          
[scenario-6 hermes] alice writes claim: "sky-color-0e2fdf4c is blue" on node-1
[scenario-6 hermes] bob writes contradicting claim: "sky-color-0e2fdf4c is red" on node-2
[scenario-6 hermes]   alice.id=2be31495-67c1-4d76-b691-a3ce44210c94 bob.id=2be31495-67c1-4d76-b691-a3ce44210c94
[scenario-6 hermes] charlie queries memory_detect_contradiction on node-3
[scenario-6 hermes]   HTTP 404; body length=0
[scenario-6 hermes]   sees both memories: 0; sees contradicts link: 0


          
raw file

        

      

      

        
Scenario 9 — Mutation round-trip FAIL

        
Reasons: charlie expected content=601ba75b-2873-4b81-ac9d-aab507640133 got "" (update didn't propagate or PATCH unsupported) | metadata.agent_id changed from ai:alice to "" — Task 1.2 immutability breach

        
scenario-9.json (report)
          
{
	"scenario": "9",
	"pass": false,
	"agent_group": "hermes",
	"m1_id": "a529116a-8f3d-4a64-9117-6a80dbf6ff7a",
	"v1_uuid": "b444df51-0306-460d-ab52-1b038ec03618",
	"v2_uuid": "601ba75b-2873-4b81-ac9d-aab507640133",
	"patch_http_code": "405",
	"charlie_view": {
		"content": "",
		"agent_id": ""
	},
	"reasons": [
		"charlie expected content=601ba75b-2873-4b81-ac9d-aab507640133 got \"\" (update didn't propagate or PATCH unsupported)",
		"metadata.agent_id changed from ai:alice to \"\" — Task 1.2 immutability breach"
	]
}


          
raw file

        

        
scenario-9.log (console trace)
          
[scenario-9 hermes] alice writes M1 content=b444df51-0306-460d-ab52-1b038ec03618 on node-1
[scenario-9 hermes]   created memory id=a529116a-8f3d-4a64-9117-6a80dbf6ff7a
[scenario-9 hermes] bob updates M1 content=601ba75b-2873-4b81-ac9d-aab507640133 on node-2
[scenario-9 hermes]   PATCH returned HTTP 405
[scenario-9 hermes] charlie reads M1 on node-3 and checks content + provenance
[scenario-9 hermes]   charlie sees content="" agent_id=""


          
raw file

        

      

      

        
Scenario 10 — Deletion propagation FAIL

        
Reasons: 3/3 peers still see M1 after delete — tombstone not propagated

        
scenario-10.json (report)
          
{
	"scenario": "10",
	"pass": false,
	"agent_group": "hermes",
	"m1_id": "3ac9d19f-c921-484f-bfc7-a6b203594820",
	"uuid": "e8078d3b-9f1c-4c8d-9506-c0231ba82a62",
	"delete_http_code": "200",
	"pre_delete_visible_peers": 3,
	"post_delete_still_visible_peers": 3,
	"reasons": [
		"3/3 peers still see M1 after delete — tombstone not propagated"
	]
}


          
raw file

        

        
scenario-10.log (console trace)
          
[scenario-10 hermes] alice writes M1 content=e8078d3b-9f1c-4c8d-9506-c0231ba82a62 on node-1
[scenario-10 hermes]   created memory id=3ac9d19f-c921-484f-bfc7-a6b203594820
[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 1 (expected 0)
[scenario-10 hermes]   post-delete node-3 sees 1 (expected 0)
[scenario-10 hermes]   post-delete node-4 sees 1 (expected 0)


          
raw file

        

      

      

        
Scenario 11 — Link integrity FAIL

        
Reasons: link POST returned HTTP 404 — endpoint may not exist in this ai-memory version | charlie could not see M1->M2 link after settle

        
scenario-11.json (report)
          
{
	"scenario": "11",
	"pass": false,
	"agent_group": "hermes",
	"m1_id": "27bac32c-9a46-4770-b68d-15f19bad393d",
	"m2_id": "a4c1fa9c-fd0d-4345-b8ac-d892924be426",
	"relation": "related_to",
	"link_http_code": "404",
	"charlie_sees_link": 0,
	"reasons": [
		"link POST returned HTTP 404 — endpoint may not exist in this ai-memory version",
		"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=27bac32c-9a46-4770-b68d-15f19bad393d M2=a4c1fa9c-fd0d-4345-b8ac-d892924be426
[scenario-11 hermes] alice links M1 -> M2 with relation=related_to
[scenario-11 hermes]   link POST returned HTTP 404
[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-3b1f2786 on node-1
[scenario-12 hermes]   POST /api/v1/agents returned HTTP 422


          
raw file

        

      

      

        
Scenario 13 — Concurrent write contention FAIL

        
Reasons: winning content is not one of the submitted PATCH values: got "(none)"

        
scenario-13.json (report)
          
{
	"scenario": "13",
	"pass": false,
	"agent_group": "hermes",
	"m1_id": "2b58b0f7-0d7f-425e-9685-52e2e83957a0",
	"submitted": {
		"v0": "8c2af31f-427f-4b8b-92e3-671ec11a4c9c",
		"vA_alice": "11835b27-bb8c-4614-841f-e927accc847f",
		"vB_bob": "8c67014c-b589-47f7-90f5-362d5af8b178"
	},
	"peer_view": {
		"node_1": "(none)",
		"node_2": "(none)",
		"node_3": "(none)",
		"node_4": "(none)"
	},
	"reasons": [
		"winning content is not one of the submitted PATCH values: got \"(none)\""
	]
}


          
raw file

        

        
scenario-13.log (console trace)
          
[scenario-13 hermes] alice writes M1 content=v0 on node-1
[scenario-13 hermes]   M1 id=2b58b0f7-0d7f-425e-9685-52e2e83957a0
[scenario-13 hermes] alice + bob issue concurrent PATCHes (vA=11835b27-bb8c-4614-841f-e927accc847f from alice, vB=8c67014c-b589-47f7-90f5-362d5af8b178 from bob)
[scenario-13 hermes] settle 10s for quorum convergence
[scenario-13 hermes]   node-1 sees content=(none)
[scenario-13 hermes]   node-2 sees content=(none)
[scenario-13 hermes]   node-3 sees content=(none)
[scenario-13 hermes]   node-4 sees content=(none)


          
raw file

        

      

      

        
Scenario 14 — Partition tolerance FAIL

        
Reasons: node-3 only saw 2/20 writes after partition recovery — catchup failed or W=2 wasn't satisfied during outage

        
scenario-14.json (report)
          
{
	"scenario": "14",
	"pass": false,
	"agent_group": "hermes",
	"partition_target": "node-3",
	"expected_post_recovery": 20,
	"node3_saw": 2,
	"reasons": [
		"node-3 only saw 2/20 writes after partition recovery — catchup failed or W=2 wasn't satisfied during outage"
	]
}


          
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 2 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": "52f404cc-35d5-4148-94eb-7f9f9dd48cb3",
	"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=52f404cc-35d5-4148-94eb-7f9f9dd48cb3)
[scenario-15 hermes]   alice sees 1 (expected 1) immediately after write


          
raw file

        

      

      

        
Scenario 16 — Tier promotion FAIL

        
Reasons: bob sees tier="(missing)", expected "long"

        
scenario-16.json (report)
          
{
	"scenario": "16",
	"pass": false,
	"agent_group": "hermes",
	"m1_id": "bf433251-c3c3-4efc-8576-62dc38d0a99c",
	"promote_http_code": "200",
	"bob_sees_tier": "(missing)",
	"reasons": [
		"bob sees tier=\"(missing)\", expected \"long\""
	]
}


          
raw file

        

        
scenario-16.log (console trace)
          
[scenario-16 hermes] alice writes M1 tier=short on node-1
[scenario-16 hermes]   M1 id=bf433251-c3c3-4efc-8576-62dc38d0a99c
[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=(missing) (expected long)


          
raw file

        

      

      

        
Scenario 17 — Stats consistency FAIL

        
Reasons: node-1 count=5 != expected 15 | node-2 count=5 != expected 15 | node-3 count=5 != expected 15 | node-4 count=5 != expected 15

        
scenario-17.json (report)
          
{
	"scenario": "17",
	"pass": false,
	"agent_group": "hermes",
	"expected_count": 15,
	"per_peer": {
		"node_1": 5,
		"node_2": 5,
		"node_3": 5,
		"node_4": 5
	},
	"reasons": [
		"node-1 count=5 != expected 15",
		"node-2 count=5 != expected 15",
		"node-3 count=5 != expected 15",
		"node-4 count=5 != expected 15"
	]
}


          
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 157.245.219.205
[scenario-17 hermes]   ai:bob on 167.172.234.175
[scenario-17 hermes]   ai:charlie on 68.183.145.110
[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=5 (expected 15)
[scenario-17 hermes]   node-2 count=5 (expected 15)
[scenario-17 hermes]   node-3 count=5 (expected 15)
[scenario-17 hermes]   node-4 count=5 (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-7d4b72be-017f-42d4-aff9-7f58975394d0",
			"seen_by_charlie": 0
		},
		{
			"agent": "ai:bob",
			"marker": "bob-daybreak-c918391a-8539-45ad-b5ca-0fa13d972838",
			"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