Finished · first durable deployment

infra-weekly · 2026-W37-20260911 · round 2 heat 1 · attempt 2

builder-one won: first durable deployment

Winnerbuilder-one
Durable in0:47
Recorded cost$0.0442
Tokens9,701
Match replay

Watch the race unfold

Play the referee's event stream or scrub directly to any moment.

0:00
Start0:47

How they fought

Deterministic analysis of observable tool calls. Private model reasoning is never parsed.

AgentFirst changeDiscoveryChangesLifecycleChecksErrorsArchitecture seen
kimimoonshotai/kimi-k30:3402220
Pythonsystemdbuilder-app.serviceetc/systemd/system/builder-app.service
lunaopenai/gpt-5.6-luna0:2311120
Pythonsystemdbuilder-app.service
minimaxminimax/minimax-m3n/a60012
Pythonsystemdbuilder-app.service
kimi6 observed tool calls
  1. ValidationInspect builder-app service and environmentsystemctl status builder-app.service 2>&1; ls -la /opt/builder/ 2>&1; python3 --version; cat /etc/systemd/system/builder-app.service 2>/dev/null || systemctl cat builder-app.service 2>&1
  2. MutationWrite /opt/builder/app.pyWrite /opt/builder/app.py
  3. MutationEdit /opt/builder/app.pyEdit /opt/builder/app.py
  4. LifecycleStart the servicesystemctl reset-failed builder-app.service && systemctl start builder-app.service && sleep 1 && systemctl status builder-app.service --no-pager | head -5
  5. ValidationVerify endpointscurl -s -o /dev/null -w 'health:%{http_code}:' http://localhost:8080/health; curl -s http://localhost:8080/health; echo; curl -s -o /dev/null -w 'put:%{http_code}\n' -X PUT --data 'hello-world-123' http://localhost:8080/records/abc; curl -s -w '\nget:%{http_code}\n' http://localhost:8080/records/abc; curl -s -o /dev/null -w 'missing:%{http_code}\n' http://localhost:8080/records/nope
  6. LifecycleVerify record survives service restartsystemctl restart builder-app.service && sleep 1 && curl -s -w '\nget-after-restart:%{http_code}\n' http://localhost:8080/records/abc
luna5 observed tool calls
  1. ValidationInspect existing systemd unitsystemctl cat builder-app.service && printf '\n--- status ---\n' && systemctl status builder-app.service --no-pager || true
  2. DiscoveryInspect application directory and OSls -la /opt /opt/builder 2>&1 || true; printf '\n--- OS ---\n'; cat /etc/os-release | head -5
  3. ValidationInspect listening portsss -ltnp | head -30
  4. MutationWrite /opt/builder/app.pyWrite /opt/builder/app.py
  5. LifecycleInstall and start the application servicechmod 0755 /opt/builder/app.py && python3 -m py_compile /opt/builder/app.py && systemctl reset-failed builder-app.service && systemctl enable --now builder-app.service && systemctl is-enabled builder-app.service && systemctl is-active builder-app.service
minimax7 observed tool calls
  1. DiscoveryCheck environmentwhoami && uname -a && cat /etc/os-release | head -20
  2. DiscoveryCheck for builder-app servicesystemctl list-unit-files | grep -i builder
  3. DiscoveryCheck /opt/builder directoryls -la /opt/builder/ 2>&1; ls -la /opt/ 2>&1
  4. ValidationCheck listening ports and processesss -tlnp 2>&1 | head -20; echo "---"; ps aux | head -20
  5. DiscoveryShow builder-app.service definitionsystemctl cat builder-app.service
  6. DiscoveryShow service propertiessystemctl show builder-app.service
  7. DiscoveryCheck Python availabilitywhich python3 && python3 --version; which python; which pip3

Territories

The referee-owned result frozen when the first deployment became durable.

TerritoryStateMilestonesPointsDurable at
builder-onelunadurable4/41000:47
builder-threeminimaxverifying0/10—
builder-twokimiverifying0/10—

Agents

Exact model, harness, reasoning configuration, and cumulative usage recorded for this match.

AgentModelHarnessReasoningOutcomeInputOutputCostArtifact
kimibuilder-twomoonshotai/kimi-k3clauxhighfailed3,3581,817$0.0390transcript · analysis
lunabuilder-oneopenai/gpt-5.6-lunaclauxhighinterrupted152,101$0.0037transcript · analysis
minimaxbuilder-threeminimax/minimax-m3clauxhighincomplete1,947463$0.0014transcript · analysis

Match provenance

Immutable identifiers for reproducing and comparing this result.

EngineAgents of Empires v20260816.0.1
Source revisionb6c1903f84da
Arenafirst-build-realbuildrace · schema v1
Compatibility keyf8704375ceff
Manifest631e19bf4682
Verifier06a2813a43a0
Harness adaptersclauxd05839f7b662

Event timeline

138 immutable events. The match clock remains frozen during post-match collection.

  1. Match state changed
    event #0
    {
      "elapsed_ms": 0,
      "from": "preparing",
      "kind": "match_state_changed",
      "schema_version": 1,
      "sequence": 0,
      "to": "running"
    }
  2. Competitor state changedbuilder-one
    event #1
    {
      "elapsed_ms": 0,
      "from": "preparing",
      "kind": "competitor_state_changed",
      "reason": "SSH preflight passed",
      "schema_version": 1,
      "sequence": 1,
      "territory": "builder-one",
      "to": "building"
    }
  3. Competitor state changedbuilder-three
    event #2
    {
      "elapsed_ms": 0,
      "from": "preparing",
      "kind": "competitor_state_changed",
      "reason": "SSH preflight passed",
      "schema_version": 1,
      "sequence": 2,
      "territory": "builder-three",
      "to": "building"
    }
  4. Competitor state changedbuilder-two
    event #3
    {
      "elapsed_ms": 0,
      "from": "preparing",
      "kind": "competitor_state_changed",
      "reason": "SSH preflight passed",
      "schema_version": 1,
      "sequence": 3,
      "territory": "builder-two",
      "to": "building"
    }
  5. Territory registeredbuilder-one
    event #4
    {
      "agent": "luna",
      "class": "builder",
      "elapsed_ms": 0,
      "kind": "territory_registered",
      "schema_version": 1,
      "sequence": 4,
      "territory": "builder-one"
    }
  6. Territory registeredbuilder-two
    event #5
    {
      "agent": "kimi",
      "class": "builder",
      "elapsed_ms": 0,
      "kind": "territory_registered",
      "schema_version": 1,
      "sequence": 5,
      "territory": "builder-two"
    }
  7. Territory registeredbuilder-three
    event #6
    {
      "agent": "minimax",
      "class": "builder",
      "elapsed_ms": 0,
      "kind": "territory_registered",
      "schema_version": 1,
      "sequence": 6,
      "territory": "builder-three"
    }
  8. Agent startedbuilder-one
    event #7
    {
      "agent": "luna",
      "elapsed_ms": 0,
      "kind": "agent_started",
      "model": "openai/gpt-5.6-luna",
      "schema_version": 1,
      "sequence": 7,
      "territory": "builder-one"
    }
  9. Agent startedbuilder-three
    event #8
    {
      "agent": "minimax",
      "elapsed_ms": 0,
      "kind": "agent_started",
      "model": "minimax/minimax-m3",
      "schema_version": 1,
      "sequence": 8,
      "territory": "builder-three"
    }
  10. Agent startedbuilder-two
    event #9
    {
      "agent": "kimi",
      "elapsed_ms": 0,
      "kind": "agent_started",
      "model": "moonshotai/kimi-k3",
      "schema_version": 1,
      "sequence": 9,
      "territory": "builder-two"
    }
  11. Competitor state changedbuilder-one
    event #10
    {
      "elapsed_ms": 2000,
      "from": "building",
      "kind": "competitor_state_changed",
      "reason": "milestone verification began",
      "schema_version": 1,
      "sequence": 10,
      "territory": "builder-one",
      "to": "verifying"
    }
  12. Milestone evaluation startedbuilder-one
    event #11
    {
      "elapsed_ms": 2000,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 11,
      "territory": "builder-one"
    }
  13. Competitor state changedbuilder-two
    event #12
    {
      "elapsed_ms": 2000,
      "from": "building",
      "kind": "competitor_state_changed",
      "reason": "milestone verification began",
      "schema_version": 1,
      "sequence": 12,
      "territory": "builder-two",
      "to": "verifying"
    }
  14. Milestone evaluation startedbuilder-two
    event #13
    {
      "elapsed_ms": 2000,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 13,
      "territory": "builder-two"
    }
  15. Competitor state changedbuilder-three
    event #14
    {
      "elapsed_ms": 2000,
      "from": "building",
      "kind": "competitor_state_changed",
      "reason": "milestone verification began",
      "schema_version": 1,
      "sequence": 14,
      "territory": "builder-three",
      "to": "verifying"
    }
  16. Milestone evaluation startedbuilder-three
    event #15
    {
      "elapsed_ms": 2000,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 15,
      "territory": "builder-three"
    }
  17. Milestone failedbuilder-three
    event #16
    {
      "category": "verification_failed",
      "detail": "curl: (56) Recv failure: Connection reset by peer",
      "elapsed_ms": 2011,
      "kind": "milestone_failed",
      "milestone": "service-up",
      "retryable": true,
      "schema_version": 1,
      "sequence": 16,
      "territory": "builder-three"
    }
  18. Milestone failedbuilder-one
    event #17
    {
      "category": "verification_failed",
      "detail": "curl: (56) Recv failure: Connection reset by peer",
      "elapsed_ms": 2011,
      "kind": "milestone_failed",
      "milestone": "service-up",
      "retryable": true,
      "schema_version": 1,
      "sequence": 17,
      "territory": "builder-one"
    }
  19. Milestone failedbuilder-two
    event #18
    {
      "category": "verification_failed",
      "detail": "curl: (56) Recv failure: Connection reset by peer",
      "elapsed_ms": 2011,
      "kind": "milestone_failed",
      "milestone": "service-up",
      "retryable": true,
      "schema_version": 1,
      "sequence": 18,
      "territory": "builder-two"
    }
  20. Milestone evaluation startedbuilder-one
    event #19
    {
      "elapsed_ms": 4012,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 19,
      "territory": "builder-one"
    }
  21. Milestone evaluation startedbuilder-two
    event #20
    {
      "elapsed_ms": 4012,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 20,
      "territory": "builder-two"
    }
  22. Milestone evaluation startedbuilder-three
    event #21
    {
      "elapsed_ms": 4012,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 21,
      "territory": "builder-three"
    }
  23. Milestone failedbuilder-two
    event #22
    {
      "category": "verification_failed",
      "detail": "curl: (56) Recv failure: Connection reset by peer",
      "elapsed_ms": 4047,
      "kind": "milestone_failed",
      "milestone": "service-up",
      "retryable": true,
      "schema_version": 1,
      "sequence": 22,
      "territory": "builder-two"
    }
  24. Milestone failedbuilder-one
    event #23
    {
      "category": "verification_failed",
      "detail": "curl: (56) Recv failure: Connection reset by peer",
      "elapsed_ms": 4047,
      "kind": "milestone_failed",
      "milestone": "service-up",
      "retryable": true,
      "schema_version": 1,
      "sequence": 23,
      "territory": "builder-one"
    }
  25. Milestone failedbuilder-three
    event #24
    {
      "category": "verification_failed",
      "detail": "curl: (56) Recv failure: Connection reset by peer",
      "elapsed_ms": 4047,
      "kind": "milestone_failed",
      "milestone": "service-up",
      "retryable": true,
      "schema_version": 1,
      "sequence": 24,
      "territory": "builder-three"
    }
  26. Milestone evaluation startedbuilder-one
    event #25
    {
      "elapsed_ms": 6050,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 25,
      "territory": "builder-one"
    }
  27. Milestone evaluation startedbuilder-two
    event #26
    {
      "elapsed_ms": 6050,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 26,
      "territory": "builder-two"
    }
  28. Milestone evaluation startedbuilder-three
    event #27
    {
      "elapsed_ms": 6050,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 27,
      "territory": "builder-three"
    }
  29. Milestone failedbuilder-two
    event #28
    {
      "category": "verification_failed",
      "detail": "curl: (56) Recv failure: Connection reset by peer",
      "elapsed_ms": 6087,
      "kind": "milestone_failed",
      "milestone": "service-up",
      "retryable": true,
      "schema_version": 1,
      "sequence": 28,
      "territory": "builder-two"
    }
  30. Milestone failedbuilder-three
    event #29
    {
      "category": "verification_failed",
      "detail": "curl: (56) Recv failure: Connection reset by peer",
      "elapsed_ms": 6087,
      "kind": "milestone_failed",
      "milestone": "service-up",
      "retryable": true,
      "schema_version": 1,
      "sequence": 29,
      "territory": "builder-three"
    }
  31. Milestone failedbuilder-one
    event #30
    {
      "category": "verification_failed",
      "detail": "curl: (56) Recv failure: Connection reset by peer",
      "elapsed_ms": 6089,
      "kind": "milestone_failed",
      "milestone": "service-up",
      "retryable": true,
      "schema_version": 1,
      "sequence": 30,
      "territory": "builder-one"
    }
  32. Usage chargedkimi
    event #31
    {
      "agent": "kimi",
      "cost_microusd": null,
      "elapsed_ms": 6089,
      "input_tokens": 0,
      "kind": "usage_charged",
      "output_tokens": 0,
      "resource_units": 1,
      "schema_version": 1,
      "sequence": 31
    }
  33. Usage chargedluna
    event #32
    {
      "agent": "luna",
      "cost_microusd": 0,
      "elapsed_ms": 6089,
      "input_tokens": 0,
      "kind": "usage_charged",
      "output_tokens": 0,
      "resource_units": 1,
      "schema_version": 1,
      "sequence": 32
    }
  34. Usage chargedminimax
    event #33
    {
      "agent": "minimax",
      "cost_microusd": null,
      "elapsed_ms": 6089,
      "input_tokens": 0,
      "kind": "usage_charged",
      "output_tokens": 0,
      "resource_units": 1,
      "schema_version": 1,
      "sequence": 33
    }
  35. Milestone evaluation startedbuilder-one
    event #34
    {
      "elapsed_ms": 8090,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 34,
      "territory": "builder-one"
    }
  36. Milestone evaluation startedbuilder-two
    event #35
    {
      "elapsed_ms": 8091,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 35,
      "territory": "builder-two"
    }
  37. Milestone evaluation startedbuilder-three
    event #36
    {
      "elapsed_ms": 8091,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 36,
      "territory": "builder-three"
    }
  38. Milestone failedbuilder-one
    event #37
    {
      "category": "verification_failed",
      "detail": "curl: (56) Recv failure: Connection reset by peer",
      "elapsed_ms": 8128,
      "kind": "milestone_failed",
      "milestone": "service-up",
      "retryable": true,
      "schema_version": 1,
      "sequence": 37,
      "territory": "builder-one"
    }
  39. Milestone failedbuilder-three
    event #38
    {
      "category": "verification_failed",
      "detail": "curl: (56) Recv failure: Connection reset by peer",
      "elapsed_ms": 8129,
      "kind": "milestone_failed",
      "milestone": "service-up",
      "retryable": true,
      "schema_version": 1,
      "sequence": 38,
      "territory": "builder-three"
    }
  40. Milestone failedbuilder-two
    event #39
    {
      "category": "verification_failed",
      "detail": "curl: (56) Recv failure: Connection reset by peer",
      "elapsed_ms": 8131,
      "kind": "milestone_failed",
      "milestone": "service-up",
      "retryable": true,
      "schema_version": 1,
      "sequence": 39,
      "territory": "builder-two"
    }
  41. Usage chargedluna
    event #40
    {
      "agent": "luna",
      "cost_microusd": 212,
      "elapsed_ms": 8131,
      "input_tokens": 3,
      "kind": "usage_charged",
      "output_tokens": 136,
      "resource_units": 0,
      "schema_version": 1,
      "sequence": 40
    }
  42. Milestone evaluation startedbuilder-one
    event #41
    {
      "elapsed_ms": 10132,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 41,
      "territory": "builder-one"
    }
  43. Milestone evaluation startedbuilder-two
    event #42
    {
      "elapsed_ms": 10132,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 42,
      "territory": "builder-two"
    }
  44. Milestone evaluation startedbuilder-three
    event #43
    {
      "elapsed_ms": 10132,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 43,
      "territory": "builder-three"
    }
  45. Milestone failedbuilder-one
    event #44
    {
      "category": "verification_failed",
      "detail": "curl: (56) Recv failure: Connection reset by peer",
      "elapsed_ms": 10169,
      "kind": "milestone_failed",
      "milestone": "service-up",
      "retryable": true,
      "schema_version": 1,
      "sequence": 44,
      "territory": "builder-one"
    }
  46. Milestone failedbuilder-two
    event #45
    {
      "category": "verification_failed",
      "detail": "curl: (56) Recv failure: Connection reset by peer",
      "elapsed_ms": 10169,
      "kind": "milestone_failed",
      "milestone": "service-up",
      "retryable": true,
      "schema_version": 1,
      "sequence": 45,
      "territory": "builder-two"
    }
  47. Milestone failedbuilder-three
    event #46
    {
      "category": "verification_failed",
      "detail": "curl: (56) Recv failure: Connection reset by peer",
      "elapsed_ms": 10170,
      "kind": "milestone_failed",
      "milestone": "service-up",
      "retryable": true,
      "schema_version": 1,
      "sequence": 46,
      "territory": "builder-three"
    }
  48. Usage chargedluna
    event #47
    {
      "agent": "luna",
      "cost_microusd": 318,
      "elapsed_ms": 10170,
      "input_tokens": 3,
      "kind": "usage_charged",
      "output_tokens": 180,
      "resource_units": 0,
      "schema_version": 1,
      "sequence": 47
    }
  49. Milestone evaluation startedbuilder-one
    event #48
    {
      "elapsed_ms": 12171,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 48,
      "territory": "builder-one"
    }
  50. Milestone evaluation startedbuilder-two
    event #49
    {
      "elapsed_ms": 12171,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 49,
      "territory": "builder-two"
    }
  51. Milestone evaluation startedbuilder-three
    event #50
    {
      "elapsed_ms": 12171,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 50,
      "territory": "builder-three"
    }
  52. Milestone failedbuilder-two
    event #51
    {
      "category": "verification_failed",
      "detail": "curl: (56) Recv failure: Connection reset by peer",
      "elapsed_ms": 12214,
      "kind": "milestone_failed",
      "milestone": "service-up",
      "retryable": true,
      "schema_version": 1,
      "sequence": 51,
      "territory": "builder-two"
    }
  53. Milestone failedbuilder-one
    event #52
    {
      "category": "verification_failed",
      "detail": "curl: (56) Recv failure: Connection reset by peer",
      "elapsed_ms": 12214,
      "kind": "milestone_failed",
      "milestone": "service-up",
      "retryable": true,
      "schema_version": 1,
      "sequence": 52,
      "territory": "builder-one"
    }
  54. Milestone failedbuilder-three
    event #53
    {
      "category": "verification_failed",
      "detail": "curl: (56) Recv failure: Connection reset by peer",
      "elapsed_ms": 12214,
      "kind": "milestone_failed",
      "milestone": "service-up",
      "retryable": true,
      "schema_version": 1,
      "sequence": 53,
      "territory": "builder-three"
    }
  55. Usage chargedkimi
    event #54
    {
      "agent": "kimi",
      "cost_microusd": 3543,
      "elapsed_ms": 12214,
      "input_tokens": 124,
      "kind": "usage_charged",
      "output_tokens": 190,
      "resource_units": 0,
      "schema_version": 1,
      "sequence": 54
    }
  56. Milestone evaluation startedbuilder-one
    event #55
    {
      "elapsed_ms": 14215,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 55,
      "territory": "builder-one"
    }
  57. Milestone evaluation startedbuilder-two
    event #56
    {
      "elapsed_ms": 14215,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 56,
      "territory": "builder-two"
    }
  58. Milestone evaluation startedbuilder-three
    event #57
    {
      "elapsed_ms": 14215,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 57,
      "territory": "builder-three"
    }
  59. Milestone failedbuilder-one
    event #58
    {
      "category": "verification_failed",
      "detail": "curl: (56) Recv failure: Connection reset by peer",
      "elapsed_ms": 14252,
      "kind": "milestone_failed",
      "milestone": "service-up",
      "retryable": true,
      "schema_version": 1,
      "sequence": 58,
      "territory": "builder-one"
    }
  60. Milestone failedbuilder-two
    event #59
    {
      "category": "verification_failed",
      "detail": "curl: (56) Recv failure: Connection reset by peer",
      "elapsed_ms": 14252,
      "kind": "milestone_failed",
      "milestone": "service-up",
      "retryable": true,
      "schema_version": 1,
      "sequence": 59,
      "territory": "builder-two"
    }
  61. Milestone failedbuilder-three
    event #60
    {
      "category": "verification_failed",
      "detail": "curl: (56) Recv failure: Connection reset by peer",
      "elapsed_ms": 14252,
      "kind": "milestone_failed",
      "milestone": "service-up",
      "retryable": true,
      "schema_version": 1,
      "sequence": 60,
      "territory": "builder-three"
    }
  62. Milestone evaluation startedbuilder-one
    event #61
    {
      "elapsed_ms": 16254,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 61,
      "territory": "builder-one"
    }
  63. Milestone evaluation startedbuilder-two
    event #62
    {
      "elapsed_ms": 16254,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 62,
      "territory": "builder-two"
    }
  64. Milestone evaluation startedbuilder-three
    event #63
    {
      "elapsed_ms": 16254,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 63,
      "territory": "builder-three"
    }
  65. Milestone failedbuilder-one
    event #64
    {
      "category": "verification_failed",
      "detail": "curl: (56) Recv failure: Connection reset by peer",
      "elapsed_ms": 16288,
      "kind": "milestone_failed",
      "milestone": "service-up",
      "retryable": true,
      "schema_version": 1,
      "sequence": 64,
      "territory": "builder-one"
    }
  66. Milestone failedbuilder-three
    event #65
    {
      "category": "verification_failed",
      "detail": "curl: (56) Recv failure: Connection reset by peer",
      "elapsed_ms": 16289,
      "kind": "milestone_failed",
      "milestone": "service-up",
      "retryable": true,
      "schema_version": 1,
      "sequence": 65,
      "territory": "builder-three"
    }
  67. Milestone failedbuilder-two
    event #66
    {
      "category": "verification_failed",
      "detail": "curl: (56) Recv failure: Connection reset by peer",
      "elapsed_ms": 16289,
      "kind": "milestone_failed",
      "milestone": "service-up",
      "retryable": true,
      "schema_version": 1,
      "sequence": 66,
      "territory": "builder-two"
    }
  68. Milestone evaluation startedbuilder-one
    event #67
    {
      "elapsed_ms": 18290,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 67,
      "territory": "builder-one"
    }
  69. Milestone evaluation startedbuilder-two
    event #68
    {
      "elapsed_ms": 18290,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 68,
      "territory": "builder-two"
    }
  70. Milestone evaluation startedbuilder-three
    event #69
    {
      "elapsed_ms": 18290,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 69,
      "territory": "builder-three"
    }
  71. Milestone failedbuilder-three
    event #70
    {
      "category": "verification_failed",
      "detail": "curl: (56) Recv failure: Connection reset by peer",
      "elapsed_ms": 18319,
      "kind": "milestone_failed",
      "milestone": "service-up",
      "retryable": true,
      "schema_version": 1,
      "sequence": 70,
      "territory": "builder-three"
    }
  72. Milestone failedbuilder-one
    event #71
    {
      "category": "verification_failed",
      "detail": "curl: (56) Recv failure: Connection reset by peer",
      "elapsed_ms": 18319,
      "kind": "milestone_failed",
      "milestone": "service-up",
      "retryable": true,
      "schema_version": 1,
      "sequence": 71,
      "territory": "builder-one"
    }
  73. Milestone failedbuilder-two
    event #72
    {
      "category": "verification_failed",
      "detail": "curl: (56) Recv failure: Connection reset by peer",
      "elapsed_ms": 18320,
      "kind": "milestone_failed",
      "milestone": "service-up",
      "retryable": true,
      "schema_version": 1,
      "sequence": 72,
      "territory": "builder-two"
    }
  74. Milestone evaluation startedbuilder-one
    event #73
    {
      "elapsed_ms": 20322,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 73,
      "territory": "builder-one"
    }
  75. Milestone evaluation startedbuilder-two
    event #74
    {
      "elapsed_ms": 20322,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 74,
      "territory": "builder-two"
    }
  76. Milestone evaluation startedbuilder-three
    event #75
    {
      "elapsed_ms": 20322,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 75,
      "territory": "builder-three"
    }
  77. Milestone failedbuilder-three
    event #76
    {
      "category": "verification_failed",
      "detail": "curl: (56) Recv failure: Connection reset by peer",
      "elapsed_ms": 20331,
      "kind": "milestone_failed",
      "milestone": "service-up",
      "retryable": true,
      "schema_version": 1,
      "sequence": 76,
      "territory": "builder-three"
    }
  78. Milestone failedbuilder-one
    event #77
    {
      "category": "verification_failed",
      "detail": "curl: (56) Recv failure: Connection reset by peer",
      "elapsed_ms": 20331,
      "kind": "milestone_failed",
      "milestone": "service-up",
      "retryable": true,
      "schema_version": 1,
      "sequence": 77,
      "territory": "builder-one"
    }
  79. Milestone failedbuilder-two
    event #78
    {
      "category": "verification_failed",
      "detail": "curl: (56) Recv failure: Connection reset by peer",
      "elapsed_ms": 20332,
      "kind": "milestone_failed",
      "milestone": "service-up",
      "retryable": true,
      "schema_version": 1,
      "sequence": 78,
      "territory": "builder-two"
    }
  80. Usage chargedluna
    event #79
    {
      "agent": "luna",
      "cost_microusd": 1228,
      "elapsed_ms": 20332,
      "input_tokens": 3,
      "kind": "usage_charged",
      "output_tokens": 649,
      "resource_units": 0,
      "schema_version": 1,
      "sequence": 79
    }
  81. Milestone evaluation startedbuilder-one
    event #80
    {
      "elapsed_ms": 22334,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 80,
      "territory": "builder-one"
    }
  82. Milestone evaluation startedbuilder-two
    event #81
    {
      "elapsed_ms": 22334,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 81,
      "territory": "builder-two"
    }
  83. Milestone evaluation startedbuilder-three
    event #82
    {
      "elapsed_ms": 22334,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 82,
      "territory": "builder-three"
    }
  84. Milestone failedbuilder-two
    event #83
    {
      "category": "verification_failed",
      "detail": "curl: (56) Recv failure: Connection reset by peer",
      "elapsed_ms": 22343,
      "kind": "milestone_failed",
      "milestone": "service-up",
      "retryable": true,
      "schema_version": 1,
      "sequence": 83,
      "territory": "builder-two"
    }
  85. Milestone failedbuilder-one
    event #84
    {
      "category": "verification_failed",
      "detail": "curl: (56) Recv failure: Connection reset by peer",
      "elapsed_ms": 22343,
      "kind": "milestone_failed",
      "milestone": "service-up",
      "retryable": true,
      "schema_version": 1,
      "sequence": 84,
      "territory": "builder-one"
    }
  86. Milestone failedbuilder-three
    event #85
    {
      "category": "verification_failed",
      "detail": "curl: (56) Recv failure: Connection reset by peer",
      "elapsed_ms": 22343,
      "kind": "milestone_failed",
      "milestone": "service-up",
      "retryable": true,
      "schema_version": 1,
      "sequence": 85,
      "territory": "builder-three"
    }
  87. Milestone evaluation startedbuilder-one
    event #86
    {
      "elapsed_ms": 24344,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 86,
      "territory": "builder-one"
    }
  88. Milestone evaluation startedbuilder-two
    event #87
    {
      "elapsed_ms": 24344,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 87,
      "territory": "builder-two"
    }
  89. Milestone evaluation startedbuilder-three
    event #88
    {
      "elapsed_ms": 24344,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 88,
      "territory": "builder-three"
    }
  90. Milestone failedbuilder-two
    event #89
    {
      "category": "verification_failed",
      "detail": "curl: (56) Recv failure: Connection reset by peer",
      "elapsed_ms": 24362,
      "kind": "milestone_failed",
      "milestone": "service-up",
      "retryable": true,
      "schema_version": 1,
      "sequence": 89,
      "territory": "builder-two"
    }
  91. Milestone failedbuilder-three
    event #90
    {
      "category": "verification_failed",
      "detail": "curl: (56) Recv failure: Connection reset by peer",
      "elapsed_ms": 24362,
      "kind": "milestone_failed",
      "milestone": "service-up",
      "retryable": true,
      "schema_version": 1,
      "sequence": 90,
      "territory": "builder-three"
    }
  92. Milestone failedbuilder-one
    event #91
    {
      "category": "verification_failed",
      "detail": "curl: (56) Recv failure: Connection reset by peer",
      "elapsed_ms": 24363,
      "kind": "milestone_failed",
      "milestone": "service-up",
      "retryable": true,
      "schema_version": 1,
      "sequence": 91,
      "territory": "builder-one"
    }
  93. Usage chargedminimax
    event #92
    {
      "agent": "minimax",
      "cost_microusd": 532,
      "elapsed_ms": 24363,
      "input_tokens": 93,
      "kind": "usage_charged",
      "output_tokens": 297,
      "resource_units": 0,
      "schema_version": 1,
      "sequence": 92
    }
  94. Milestone evaluation startedbuilder-one
    event #93
    {
      "elapsed_ms": 26365,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 93,
      "territory": "builder-one"
    }
  95. Milestone evaluation startedbuilder-two
    event #94
    {
      "elapsed_ms": 26365,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 94,
      "territory": "builder-two"
    }
  96. Milestone evaluation startedbuilder-three
    event #95
    {
      "elapsed_ms": 26365,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 95,
      "territory": "builder-three"
    }
  97. Milestone failedbuilder-three
    event #96
    {
      "category": "verification_failed",
      "detail": "curl: (56) Recv failure: Connection reset by peer",
      "elapsed_ms": 26401,
      "kind": "milestone_failed",
      "milestone": "service-up",
      "retryable": true,
      "schema_version": 1,
      "sequence": 96,
      "territory": "builder-three"
    }
  98. Milestone failedbuilder-one
    event #97
    {
      "category": "verification_failed",
      "detail": "curl: (56) Recv failure: Connection reset by peer",
      "elapsed_ms": 26401,
      "kind": "milestone_failed",
      "milestone": "service-up",
      "retryable": true,
      "schema_version": 1,
      "sequence": 97,
      "territory": "builder-one"
    }
  99. Milestone failedbuilder-two
    event #98
    {
      "category": "verification_failed",
      "detail": "curl: (56) Recv failure: Connection reset by peer",
      "elapsed_ms": 26402,
      "kind": "milestone_failed",
      "milestone": "service-up",
      "retryable": true,
      "schema_version": 1,
      "sequence": 98,
      "territory": "builder-two"
    }
  100. Milestone evaluation startedbuilder-one
    event #99
    {
      "elapsed_ms": 28404,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 99,
      "territory": "builder-one"
    }
  101. Milestone evaluation startedbuilder-two
    event #100
    {
      "elapsed_ms": 28404,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 100,
      "territory": "builder-two"
    }
  102. Milestone evaluation startedbuilder-three
    event #101
    {
      "elapsed_ms": 28404,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 101,
      "territory": "builder-three"
    }
  103. Milestone failedbuilder-two
    event #102
    {
      "category": "verification_failed",
      "detail": "curl: (56) Recv failure: Connection reset by peer",
      "elapsed_ms": 28442,
      "kind": "milestone_failed",
      "milestone": "service-up",
      "retryable": true,
      "schema_version": 1,
      "sequence": 102,
      "territory": "builder-two"
    }
  104. Milestone failedbuilder-one
    event #103
    {
      "category": "verification_failed",
      "detail": "curl: (56) Recv failure: Connection reset by peer",
      "elapsed_ms": 28442,
      "kind": "milestone_failed",
      "milestone": "service-up",
      "retryable": true,
      "schema_version": 1,
      "sequence": 103,
      "territory": "builder-one"
    }
  105. Milestone failedbuilder-three
    event #104
    {
      "category": "verification_failed",
      "detail": "curl: (56) Recv failure: Connection reset by peer",
      "elapsed_ms": 28444,
      "kind": "milestone_failed",
      "milestone": "service-up",
      "retryable": true,
      "schema_version": 1,
      "sequence": 104,
      "territory": "builder-three"
    }
  106. Milestone evaluation startedbuilder-one
    event #105
    {
      "elapsed_ms": 30445,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 105,
      "territory": "builder-one"
    }
  107. Milestone evaluation startedbuilder-two
    event #106
    {
      "elapsed_ms": 30445,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 106,
      "territory": "builder-two"
    }
  108. Milestone evaluation startedbuilder-three
    event #107
    {
      "elapsed_ms": 30445,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 107,
      "territory": "builder-three"
    }
  109. Milestone failedbuilder-one
    event #108
    {
      "category": "verification_failed",
      "detail": "curl: (56) Recv failure: Connection reset by peer",
      "elapsed_ms": 30453,
      "kind": "milestone_failed",
      "milestone": "service-up",
      "retryable": true,
      "schema_version": 1,
      "sequence": 108,
      "territory": "builder-one"
    }
  110. Milestone failedbuilder-three
    event #109
    {
      "category": "verification_failed",
      "detail": "curl: (56) Recv failure: Connection reset by peer",
      "elapsed_ms": 30453,
      "kind": "milestone_failed",
      "milestone": "service-up",
      "retryable": true,
      "schema_version": 1,
      "sequence": 109,
      "territory": "builder-three"
    }
  111. Milestone failedbuilder-two
    event #110
    {
      "category": "verification_failed",
      "detail": "curl: (56) Recv failure: Connection reset by peer",
      "elapsed_ms": 30453,
      "kind": "milestone_failed",
      "milestone": "service-up",
      "retryable": true,
      "schema_version": 1,
      "sequence": 110,
      "territory": "builder-two"
    }
  112. Usage chargedluna
    event #111
    {
      "agent": "luna",
      "cost_microusd": 1432,
      "elapsed_ms": 30453,
      "input_tokens": 3,
      "kind": "usage_charged",
      "output_tokens": 973,
      "resource_units": 0,
      "schema_version": 1,
      "sequence": 111
    }
  113. Milestone evaluation startedbuilder-one
    event #112
    {
      "elapsed_ms": 32456,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 112,
      "territory": "builder-one"
    }
  114. Milestone evaluation startedbuilder-two
    event #113
    {
      "elapsed_ms": 32456,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 113,
      "territory": "builder-two"
    }
  115. Milestone evaluation startedbuilder-three
    event #114
    {
      "elapsed_ms": 32456,
      "kind": "milestone_evaluation_started",
      "milestone": "service-up",
      "schema_version": 1,
      "sequence": 114,
      "territory": "builder-three"
    }
  116. Milestone failedbuilder-three
    event #115
    {
      "category": "verification_failed",
      "detail": "curl: (56) Recv failure: Connection reset by peer",
      "elapsed_ms": 32496,
      "kind": "milestone_failed",
      "milestone": "service-up",
      "retryable": true,
      "schema_version": 1,
      "sequence": 115,
      "territory": "builder-three"
    }
  117. Milestone failedbuilder-two
    event #116
    {
      "category": "verification_failed",
      "detail": "curl: (56) Recv failure: Connection reset by peer",
      "elapsed_ms": 32498,
      "kind": "milestone_failed",
      "milestone": "service-up",
      "retryable": true,
      "schema_version": 1,
      "sequence": 116,
      "territory": "builder-two"
    }
  118. Milestone passedbuilder-one
    event #117
    {
      "elapsed_ms": 32505,
      "evidence": {
        "health": "ready"
      },
      "kind": "milestone_passed",
      "milestone": "service-up",
      "points": 10,
      "schema_version": 1,
      "sequence": 117,
      "territory": "builder-one"
    }
  119. Milestone evaluation startedbuilder-one
    event #118
    {
      "elapsed_ms": 32505,
      "kind": "milestone_evaluation_started",
      "milestone": "write-read",
      "schema_version": 1,
      "sequence": 118,
      "territory": "builder-one"
    }
  120. Milestone passedbuilder-one
    event #119
    {
      "elapsed_ms": 32567,
      "evidence": {
        "record": "record-4bb8d4d21e5db07a",
        "value": "opaque-43eaeb7f3d412c286e87cdea9b8c4b10"
      },
      "kind": "milestone_passed",
      "milestone": "write-read",
      "points": 20,
      "schema_version": 1,
      "sequence": 119,
      "territory": "builder-one"
    }
  121. Milestone evaluation startedbuilder-one
    event #120
    {
      "elapsed_ms": 32567,
      "kind": "milestone_evaluation_started",
      "milestone": "service-restart",
      "schema_version": 1,
      "sequence": 120,
      "territory": "builder-one"
    }
  122. Milestone passedbuilder-one
    event #121
    {
      "elapsed_ms": 33511,
      "evidence": {
        "record": "record-4bb8d4d21e5db07a",
        "restart": true,
        "value": "opaque-43eaeb7f3d412c286e87cdea9b8c4b10"
      },
      "kind": "milestone_passed",
      "milestone": "service-restart",
      "points": 30,
      "schema_version": 1,
      "sequence": 121,
      "territory": "builder-one"
    }
  123. Milestone evaluation startedbuilder-one
    event #122
    {
      "elapsed_ms": 33511,
      "kind": "milestone_evaluation_started",
      "milestone": "host-reboot",
      "schema_version": 1,
      "sequence": 122,
      "territory": "builder-one"
    }
  124. Milestone passedbuilder-one
    event #123
    {
      "elapsed_ms": 47051,
      "evidence": {
        "reboot": true,
        "record": "record-4bb8d4d21e5db07a",
        "value": "opaque-43eaeb7f3d412c286e87cdea9b8c4b10"
      },
      "kind": "milestone_passed",
      "milestone": "host-reboot",
      "points": 40,
      "schema_version": 1,
      "sequence": 123,
      "territory": "builder-one"
    }
  125. Competitor state changedbuilder-one
    event #124
    {
      "elapsed_ms": 47051,
      "from": "verifying",
      "kind": "competitor_state_changed",
      "reason": "completion milestone passed",
      "schema_version": 1,
      "sequence": 124,
      "territory": "builder-one",
      "to": "durable"
    }
  126. Durable deployment completedbuilder-one
    event #125
    {
      "elapsed_ms": 47051,
      "kind": "durable_deployment_completed",
      "schema_version": 1,
      "sequence": 125,
      "territory": "builder-one"
    }
  127. Match state changed
    event #126
    {
      "elapsed_ms": 47051,
      "from": "running",
      "kind": "match_state_changed",
      "schema_version": 1,
      "sequence": 126,
      "to": "finished"
    }
  128. Match finished
    event #127
    {
      "elapsed_ms": 47051,
      "kind": "match_finished",
      "reason": "first durable deployment",
      "schema_version": 1,
      "sequence": 127,
      "winner": "builder-one"
    }
  129. Usage chargedkimi
    event #128
    {
      "agent": "kimi",
      "cost_microusd": 15168,
      "elapsed_ms": 47055,
      "input_tokens": 1245,
      "kind": "usage_charged",
      "output_tokens": 867,
      "resource_units": 0,
      "schema_version": 1,
      "sequence": 128
    }
  130. Usage chargedluna
    event #129
    {
      "agent": "luna",
      "cost_microusd": 542,
      "elapsed_ms": 47055,
      "input_tokens": 3,
      "kind": "usage_charged",
      "output_tokens": 163,
      "resource_units": 0,
      "schema_version": 1,
      "sequence": 129
    }
  131. Usage chargedminimax
    event #130
    {
      "agent": "minimax",
      "cost_microusd": 881,
      "elapsed_ms": 47055,
      "input_tokens": 1854,
      "kind": "usage_charged",
      "output_tokens": 166,
      "resource_units": 0,
      "schema_version": 1,
      "sequence": 130
    }
  132. Post match drain started
    event #131
    {
      "elapsed_ms": 47055,
      "kind": "post_match_drain_started",
      "pending_agents": 3,
      "schema_version": 1,
      "sequence": 131,
      "timeout_ms": 30000
    }
  133. Agent interruptedluna
    event #132
    {
      "agent": "luna",
      "detail": "agent session was interrupted by the referee's host reboot",
      "elapsed_ms": 47055,
      "kind": "agent_interrupted",
      "schema_version": 1,
      "sequence": 132,
      "source": "arena"
    }
  134. Usage chargedluna
    event #133
    {
      "agent": "luna",
      "cost_microusd": 0,
      "elapsed_ms": 47055,
      "input_tokens": 0,
      "kind": "usage_charged",
      "output_tokens": 0,
      "resource_units": 0,
      "schema_version": 1,
      "sequence": 133
    }
  135. Agent finishedkimi
    event #134
    {
      "agent": "kimi",
      "detail": "Claux SSH session disconnected (exit status 255); retained transcript and usage, disconnect cause unknown",
      "elapsed_ms": 47055,
      "kind": "agent_finished",
      "schema_version": 1,
      "sequence": 134,
      "source": "harness",
      "success": false
    }
  136. Usage chargedkimi
    event #135
    {
      "agent": "kimi",
      "cost_microusd": 20313,
      "elapsed_ms": 47055,
      "input_tokens": 1989,
      "kind": "usage_charged",
      "output_tokens": 760,
      "resource_units": 0,
      "schema_version": 1,
      "sequence": 135
    }
  137. Agent outracedminimax
    event #136
    {
      "agent": "minimax",
      "elapsed_ms": 47055,
      "kind": "agent_outraced",
      "reason": "builder-one reached durable first; build ended at the frozen clock",
      "schema_version": 1,
      "sequence": 136
    }
  138. Post match drain finished
    event #137
    {
      "captured_agents": 2,
      "elapsed_ms": 47055,
      "kind": "post_match_drain_finished",
      "schema_version": 1,
      "sequence": 137,
      "terminated_agents": 1
    }