Finished · first durable deployment

infra-weekly · 2026-W37-fixed-20260910-153524 · round 2 heat 1 · attempt 2

rollout-one won: first durable deployment

Winnerrollout-one
Durable in1:56
Recorded cost$0.0795
Tokens55,731
Match replay

Watch the race unfold

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

0:00
Start1:56

How they fought

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

AgentFirst changeDiscoveryChangesLifecycleChecksErrorsArchitecture seen
deepseekdeepseek/deepseek-v4.1-flash0:0431021
PythonSQLitesystemdetc/systemd/system/rollout-proxy.serviceetc/systemd/system/rollout-seed.serviceetc/systemd/system/rollout-v1.serviceetc/systemd/system/rollout-v2.servicerollout-proxy.service
glmz-ai/glm-5.30:0667133
PythonSQLitesystemdetc/systemd/system/rollout-proxy.serviceetc/systemd/system/rollout-v1.serviceetc/systemd/system/rollout-v2.servicerollout-proxy.servicerollout-v1.service
lunaopenai/gpt-5.6-luna0:0748133
PythonSQLitesystemdrollout-proxy.servicerollout-v1.servicerollout-v2.service
deepseek6 observed tool calls
  1. ValidationInspect rollout directories and service statusls -la /opt/rollout/ /var/lib/rollout/ 2>&1; echo "---SERVICES---"; systemctl status rollout-v1.service rollout-v2.service rollout-proxy.service --no-pager 2>&1
  2. DiscoveryRead systemd unit filesecho "=== v1 unit ==="; cat /etc/systemd/system/rollout-v1.service 2>&1; echo "=== v2 unit ==="; cat /etc/systemd/system/rollout-v2.service 2>&1; echo "=== proxy unit ==="; cat /etc/systemd/system/rollout-proxy.service 2>&1
  3. DiscoveryRead proxy and v1 sourceecho "=== PROXY SOURCE ==="; cat /nix/store/08ib8hkpsxizx3zrsv266idphl0r1hgb-rollout-proxy.py; echo; echo "=== V1 SOURCE ==="; cat /nix/store/13qi755lbgrlrh6c5jqjdlpf1f7nvffv-rollout-v1.py
  4. MutationCheck upstream file, seed service, and records dbecho "=== upstream ==="; cat /var/lib/rollout/upstream; echo; echo "=== seed service ==="; cat /etc/systemd/system/rollout-seed.service 2>&1; echo "=== records schema ==="; sqlite3 /var/lib/rollout/records.sqlite3 ".schema" 2>&1; echo "=== records ==="; sqlite3 /var/lib/rollout/records.sqlite3 "SELECT * FROM records;" 2>&1
  5. DiscoveryRead seed scriptcat /nix/store/44ql83wxi6z28pk20x4179khgs5i5anf-unit-script-rollout-seed-start/bin/rollout-seed-start 2>&1
  6. ValidationList rollout units and listening portsecho "=== all rollout units ==="; ls -la /etc/systemd/system/ | grep -i rollout; echo "=== is-enabled ==="; systemctl is-enabled rollout-v1.service rollout-v2.service rollout-proxy.service rollout-seed.service 2>&1; echo "=== listening ports ==="; ss -tlnp 2>/dev/null | grep -E '8080|8081|8082' || netstat -tlnp 2>/dev/null | grep -E '8080|8081|8082'
glm17 observed tool calls
  1. ValidationInspect rollout service state and filesls -la /opt/rollout/ 2>/dev/null; echo "---"; ls -la /var/lib/rollout/ 2>/dev/null; echo "---"; cat /var/lib/rollout/upstream 2>/dev/null; echo "---"; systemctl status rollout-v1.service rollout-proxy.service rollout-v2.service --no-pager 2>&1 | head -50
  2. DiscoveryRead systemd unit filescat /etc/systemd/system/rollout-v1.service /etc/systemd/system/rollout-v2.service /etc/systemd/system/rollout-proxy.service
  3. DiscoveryRead v1 and proxy source codecat /nix/store/13qi755lbgrlrh6c5jqjdlpf1f7nvffv-rollout-v1.py; echo "=== PROXY ==="; cat /nix/store/08ib8hkpsxizx3zrsv266idphl0r1hgb-rollout-proxy.py
  4. MutationInspect sqlite schema and recordscommand -v sqlite3 || python3 -c " import sqlite3 c = sqlite3.connect('/var/lib/rollout/records.sqlite3') print(c.execute(\"select name, sql from sqlite_master\").fetchall()) print(c.execute(\"select * from records limit 10\").fetchall()) "
  5. MutationDump existing recordssqlite3 /var/lib/rollout/records.sqlite3 ".schema" "select id, value from records;"
  6. ValidationBaseline public endpoint health and versionecho "health: $(curl -s -o /dev/null -w '%{http_code}' http://127.0.0.1:8080/health) body=$(curl -s http://127.0.0.1:8080/health)"; echo "version: $(curl -s -o /dev/null -w '%{http_code}' http://127.0.0.1:8080/version) body=$(curl -s http://127.0.0.1:8080/version)"
  7. MutationWrite /opt/rollout/v2.pyWrite /opt/rollout/v2.py
  8. LifecycleStart rollout-v2 servicesystemctl reset-failed rollout-v2.service && systemctl start rollout-v2.service && sleep 1 && systemctl is-active rollout-v2.service
  9. ValidationVerify v2 directly on port 8082echo "health: $(curl -s -w '|%{http_code}' http://127.0.0.1:8082/health)"; echo "version: $(curl -s -w '|%{http_code}' http://127.0.0.1:8082/version)"; echo "alpha: $(curl -s -w '|%{http_code}' http://127.0.0.1:8082/records/customer-alpha-73c)"; echo "beta: $(curl -s -w '|%{http_code}' http://127.0.0.1:8082/records/customer-beta-a19)"; echo "absent: $(curl -s -o /dev/null -w '%{http_code}' http://127.0.0.1:8082/records/no-such-id)"
  10. MutationTest v2 PUT/GET round-trip then clean upcurl -s -o /dev/null -w 'put:%{http_code} ' -X PUT --data-binary 'test-payload-Δ' http://127.0.0.1:8082/records/__cutover_probe__; curl -s -w '|%{http_code}\n' http://127.0.0.1:8082/records/__cutover_probe__; sqlite3 /var/lib/rollout/records.sqlite3 "delete from records where id='__cutover_probe__';" && echo "probe removed"
  11. MutationCreate zero-downtime monitor scriptcat > /tmp/cutover-monitor.sh <<'EOF' #!/bin/bash LOG=/tmp/cutover-monitor.log : > "$LOG" fails=0; total=0 end=$((SECONDS+20)) while [ $SECONDS -lt $end ]; do for path in /health /version /records/customer-alpha-73c /records/customer-beta-a19; do body=$(curl -s --max-time 2 "http://127.0.0.1:8080$path") code=$(curl -s -o /dev/null -w '%{http_code}' --max-time 2 "http://127.0.0.1:8080$path") total=$((total+1)) case "$path:$code:$body" in "/health:200:ready"|"/version:200:v1"|"/version:200:v2"|"/records/customer-alpha-73c:200:alpha-original"|"/records/customer-beta-a19:200:beta-original") ;; *) fails=$((fails+1)); echo "FAIL $path code=$code body=$body at $(date +…
  12. DiscoveryRun public endpoint monitor during cutover/tmp/cutover-monitor.sh
  13. DiscoveryLaunch monitor detached via nohupnohup /tmp/cutover-monitor.sh >/dev/null 2>&1 & disown; echo "monitor pid $!"; sleep 2; tail -5 /tmp/cutover-monitor.log
  14. DiscoveryCheck monitor process and log existenceps aux | grep -F cutover-monitor | grep -v grep; ls -la /tmp/cutover-monitor.*
  15. MutationRun monitored atomic cutover from v1 to v2cat > /tmp/cutover-monitor.sh <<'EOF' #!/bin/bash LOG=/tmp/cutover-monitor.log : > "$LOG" fails=0; total=0 check() { local path="$1" expect="$2" local out code body out=$(curl -s -w '\n%{http_code}' --max-time 2 "http://127.0.0.1:8080$path") code="${out##*$'\n'}"; body="${out%$'\n'*}" total=$((total+1)) if [ "$code" = "200" ] && [ "$body" = "$expect" ]; then return 0; fi fails=$((fails+1)); echo "FAIL $path code=$code body=$body at $(date +%s.%N)" >> "$LOG" } for i in $(seq 1 60); do check /health ready check /records/customer-alpha-73c alpha-original check /records/customer-beta-a19 beta-original if [ "$i" -eq 20 ]; then printf '8082' > /var/lib/rollout/upstream.tm…
  16. DiscoveryLocate bash and available shellscommand -v bash sh; ls /bin/ 2>/dev/null | head; ls /run/current-system/sw/bin/ | head -30

1 more actions in analysis.json

luna16 observed tool calls
  1. ValidationInspect rollout service status and upstreamsystemctl status --no-pager rollout-v1.service rollout-v2.service rollout-proxy.service; printf '\n--- upstream ---\n'; stat /var/lib/rollout/upstream; printf 'value='; tr -d '\n' </var/lib/rollout/upstream; printf '\n'
  2. DiscoveryGlob {"include_build_dirs":true,"include_hidden":true,"path":"/opt/rollout","pattern":"**/*"}Glob {"include_build_dirs":true,"include_hidden":true,"path":"/opt/rollout","pattern":"**/*"}
  3. MutationInspect rollout database and statels -la /var/lib/rollout; sqlite3 /var/lib/rollout/records.sqlite3 '.schema' 2>&1; printf '\n--- records ---\n'; sqlite3 /var/lib/rollout/records.sqlite3 'select quote(id), length(body) from records order by id;' 2>&1
  4. ValidationInspect listeners and unit definitionsss -ltnp | grep -E ':(8080|8081|8082)\b' || true; printf '\n--- units ---\n'; systemctl cat rollout-v1.service rollout-v2.service rollout-proxy.service
  5. DiscoveryRead /opt/rollout/v2.pyRead /opt/rollout/v2.py
  6. DiscoveryRead /nix/store/13qi755lbgrlrh6c5jqjdlpf1f7nvffv-rollout-v1.pyRead /nix/store/13qi755lbgrlrh6c5jqjdlpf1f7nvffv-rollout-v1.py
  7. DiscoveryRead /nix/store/08ib8hkpsxizx3zrsv266idphl0r1hgb-rollout-proxy.pyRead /nix/store/08ib8hkpsxizx3zrsv266idphl0r1hgb-rollout-proxy.py
  8. MutationInspect v2 failure and existing recordsjournalctl -u rollout-v2.service -n 80 --no-pager; printf '\n--- data ---\n'; sqlite3 /var/lib/rollout/records.sqlite3 'select quote(id), quote(value), length(value) from records order by id;'
  9. MutationWrite /opt/rollout/v2.pyWrite /opt/rollout/v2.py
  10. LifecycleValidate and start v2 serviceset -eu python3 -m py_compile /opt/rollout/v2.py systemctl reset-failed rollout-v2.service systemctl start rollout-v2.service systemctl enable rollout-v2.service systemctl is-active rollout-v2.service systemctl is-enabled rollout-v2.service ss -ltnp | grep -E ':8082\b'
  11. MutationVerify v2 contract before cutoverset -eu check() { expected_status=$1 expected_body=$2 url=$3 tmp=$(mktemp) status=$(curl --noproxy '*' -sS -o "$tmp" -w '%{http_code}' "$url") test "$status" = "$expected_status" test "$(cat "$tmp")" = "$expected_body" rm -f "$tmp" } check 200 ready http://127.0.0.1:8082/health check 200 v2 http://127.0.0.1:8082/version check 200 alpha-original http://127.0.0.1:8082/records/customer-alpha-73c check 200 beta-original http://127.0.0.1:8082/records/customer-beta-a19 check 404 '' http://127.0.0.1:8082/records/does-not-exist-preflight id=rollout-v2-preflight body='UTF-8 snowman ☃ and newline exact bytes' status=$(printf '%s' "$body" | curl --noproxy '*' -sS -o /tmp/rollout-v2-put-resp…
  12. MutationConfirm public v1 remains healthy before cutoverset -eu for pair in 'health ready' 'version v1' 'records/customer-alpha-73c alpha-original' 'records/customer-beta-a19 beta-original'; do set -- $pair tmp=$(mktemp) status=$(curl --noproxy '*' -sS -o "$tmp" -w '%{http_code}' "http://127.0.0.1:8080/$1") test "$status" = 200 test "$(cat "$tmp")" = "$2" rm -f "$tmp" done printf 'public v1 pre-cutover checks passed\n'
  13. ValidationConfirm all rollout slots are healthysystemctl is-active rollout-v1.service rollout-proxy.service rollout-v2.service; printf 'pids: '; systemctl show -p MainPID --value rollout-v1.service rollout-proxy.service rollout-v2.service | tr '\n' ' '; printf '\n'
  14. MutationAtomically switch stable proxy traffic to v2set -eu stop=/tmp/rollout-cutover-stop.$$ failure=/tmp/rollout-cutover-failure.$$ rm -f "$stop" "$failure" monitor() { while [ ! -e "$stop" ]; do for spec in 'health|ready' 'records/customer-alpha-73c|alpha-original' 'records/customer-beta-a19|beta-original'; do endpoint=${spec%%|*} expected=${spec#*|} response=$(mktemp) status=$(curl --noproxy '*' --max-time 1 -sS -o "$response" -w '%{http_code}' "http://127.0.0.1:8080/$endpoint" 2>/dev/null || printf '000') if [ "$status" != 200 ] || [ "$(cat "$response")" != "$expected" ]; then printf '%s status=%s body=%q\n' "$endpoint" "$status" "$(cat "$response")" >> "$failure" fi rm -f "$respons…
  15. MutationVerify public v2 contract and preserved recordsset -eu check() { expected_status=$1 expected_body=$2 url=$3 tmp=$(mktemp) status=$(curl --noproxy '*' -sS -o "$tmp" -w '%{http_code}' "$url") test "$status" = "$expected_status" test "$(cat "$tmp")" = "$expected_body" rm -f "$tmp" } check 200 ready http://127.0.0.1:8080/health check 200 v2 http://127.0.0.1:8080/version check 200 alpha-original http://127.0.0.1:8080/records/customer-alpha-73c check 200 beta-original http://127.0.0.1:8080/records/customer-beta-a19 check 404 '' http://127.0.0.1:8080/records/does-not-exist-postcutover id=rollout-v2-public-preflight body='public UTF-8 payload ☃' status=$(printf '%s' "$body" | curl --noproxy '*' -sS -o /tmp/rollout-public-put-response…
  16. MutationRecheck public v2 contract and preserved recordsset -eu check() { expected_status=$1 expected_body=$2 url=$3 tmp=$(mktemp) status=$(curl --noproxy '*' -sS -o "$tmp" -w '%{http_code}' "$url") test "$status" = "$expected_status" test "$(cat "$tmp")" = "$expected_body" rm -f "$tmp" } check 200 ready http://127.0.0.1:8080/health check 200 v2 http://127.0.0.1:8080/version check 200 alpha-original http://127.0.0.1:8080/records/customer-alpha-73c check 200 beta-original http://127.0.0.1:8080/records/customer-beta-a19 check 404 '' http://127.0.0.1:8080/records/does-not-exist-postcutover check 404 '' http://127.0.0.1:8080/records/rollout-v2-public-preflight test "$(sqlite3 /var/lib/rollout/records.sqlite3 'select quote(id)||char(58)||q…

Territories

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

TerritoryStateMilestonesPointsDurable at
rollout-onelunadurable5/51001:56
rollout-threedeepseekverifying1/25
rollout-twoglmverifying1/25

Agents

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

AgentModelHarnessReasoningOutcomeInputOutputCostArtifact
deepseekrollout-threedeepseek/deepseek-v4.1-flashclauxhighfailed18,4173,069$0.0093transcript · analysis
glmrollout-twoz-ai/glm-5.3clauxhighincomplete22,3223,988$0.0551transcript · analysis
lunarollout-oneopenai/gpt-5.6-lunaclauxhighinterrupted397,896$0.0152transcript · analysis

Match provenance

Immutable identifiers for reproducing and comparing this result.

EngineAgents of Empires v20260816.0.1
Source revisionb8ce1d258adb
Arenazero-downtime-rolloutbuildrace · schema v1
Compatibility key8b3407ef8851
Manifest2fab28a72324
Verifier4636814c82b6
Harness adaptersclauxd05839f7b662

Event timeline

45 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 changedrollout-one
    event #1
    {
      "elapsed_ms": 0,
      "from": "preparing",
      "kind": "competitor_state_changed",
      "reason": "SSH preflight passed",
      "schema_version": 1,
      "sequence": 1,
      "territory": "rollout-one",
      "to": "building"
    }
  3. Competitor state changedrollout-three
    event #2
    {
      "elapsed_ms": 0,
      "from": "preparing",
      "kind": "competitor_state_changed",
      "reason": "SSH preflight passed",
      "schema_version": 1,
      "sequence": 2,
      "territory": "rollout-three",
      "to": "building"
    }
  4. Competitor state changedrollout-two
    event #3
    {
      "elapsed_ms": 0,
      "from": "preparing",
      "kind": "competitor_state_changed",
      "reason": "SSH preflight passed",
      "schema_version": 1,
      "sequence": 3,
      "territory": "rollout-two",
      "to": "building"
    }
  5. Territory registeredrollout-one
    event #4
    {
      "agent": "luna",
      "class": "rollout-engineer",
      "elapsed_ms": 0,
      "kind": "territory_registered",
      "schema_version": 1,
      "sequence": 4,
      "territory": "rollout-one"
    }
  6. Territory registeredrollout-two
    event #5
    {
      "agent": "glm",
      "class": "rollout-engineer",
      "elapsed_ms": 0,
      "kind": "territory_registered",
      "schema_version": 1,
      "sequence": 5,
      "territory": "rollout-two"
    }
  7. Territory registeredrollout-three
    event #6
    {
      "agent": "deepseek",
      "class": "rollout-engineer",
      "elapsed_ms": 0,
      "kind": "territory_registered",
      "schema_version": 1,
      "sequence": 6,
      "territory": "rollout-three"
    }
  8. Agent startedrollout-one
    event #7
    {
      "agent": "luna",
      "elapsed_ms": 0,
      "kind": "agent_started",
      "model": "openai/gpt-5.6-luna",
      "schema_version": 1,
      "sequence": 7,
      "territory": "rollout-one"
    }
  9. Agent startedrollout-three
    event #8
    {
      "agent": "deepseek",
      "elapsed_ms": 0,
      "kind": "agent_started",
      "model": "deepseek/deepseek-v4.1-flash",
      "schema_version": 1,
      "sequence": 8,
      "territory": "rollout-three"
    }
  10. Agent startedrollout-two
    event #9
    {
      "agent": "glm",
      "elapsed_ms": 0,
      "kind": "agent_started",
      "model": "z-ai/glm-5.3",
      "schema_version": 1,
      "sequence": 9,
      "territory": "rollout-two"
    }
  11. Competitor state changedrollout-one
    event #10
    {
      "elapsed_ms": 251,
      "from": "building",
      "kind": "competitor_state_changed",
      "reason": "milestone verification began",
      "schema_version": 1,
      "sequence": 10,
      "territory": "rollout-one",
      "to": "verifying"
    }
  12. Milestone evaluation startedrollout-one
    event #11
    {
      "elapsed_ms": 251,
      "kind": "milestone_evaluation_started",
      "milestone": "baseline-ready",
      "schema_version": 1,
      "sequence": 11,
      "territory": "rollout-one"
    }
  13. Competitor state changedrollout-two
    event #12
    {
      "elapsed_ms": 251,
      "from": "building",
      "kind": "competitor_state_changed",
      "reason": "milestone verification began",
      "schema_version": 1,
      "sequence": 12,
      "territory": "rollout-two",
      "to": "verifying"
    }
  14. Milestone evaluation startedrollout-two
    event #13
    {
      "elapsed_ms": 251,
      "kind": "milestone_evaluation_started",
      "milestone": "baseline-ready",
      "schema_version": 1,
      "sequence": 13,
      "territory": "rollout-two"
    }
  15. Competitor state changedrollout-three
    event #14
    {
      "elapsed_ms": 251,
      "from": "building",
      "kind": "competitor_state_changed",
      "reason": "milestone verification began",
      "schema_version": 1,
      "sequence": 14,
      "territory": "rollout-three",
      "to": "verifying"
    }
  16. Milestone evaluation startedrollout-three
    event #15
    {
      "elapsed_ms": 251,
      "kind": "milestone_evaluation_started",
      "milestone": "baseline-ready",
      "schema_version": 1,
      "sequence": 15,
      "territory": "rollout-three"
    }
  17. Milestone passedrollout-three
    event #16
    {
      "elapsed_ms": 346,
      "evidence": {
        "baseline": "v1",
        "records": [
          "customer-alpha-73c",
          "customer-beta-a19"
        ]
      },
      "kind": "milestone_passed",
      "milestone": "baseline-ready",
      "points": 5,
      "schema_version": 1,
      "sequence": 16,
      "territory": "rollout-three"
    }
  18. Milestone passedrollout-two
    event #17
    {
      "elapsed_ms": 346,
      "evidence": {
        "baseline": "v1",
        "records": [
          "customer-alpha-73c",
          "customer-beta-a19"
        ]
      },
      "kind": "milestone_passed",
      "milestone": "baseline-ready",
      "points": 5,
      "schema_version": 1,
      "sequence": 17,
      "territory": "rollout-two"
    }
  19. Milestone passedrollout-one
    event #18
    {
      "elapsed_ms": 355,
      "evidence": {
        "baseline": "v1",
        "records": [
          "customer-alpha-73c",
          "customer-beta-a19"
        ]
      },
      "kind": "milestone_passed",
      "milestone": "baseline-ready",
      "points": 5,
      "schema_version": 1,
      "sequence": 18,
      "territory": "rollout-one"
    }
  20. Milestone evaluation startedrollout-one
    event #19
    {
      "elapsed_ms": 355,
      "kind": "milestone_evaluation_started",
      "milestone": "uninterrupted-cutover",
      "schema_version": 1,
      "sequence": 19,
      "territory": "rollout-one"
    }
  21. Milestone evaluation startedrollout-two
    event #20
    {
      "elapsed_ms": 355,
      "kind": "milestone_evaluation_started",
      "milestone": "uninterrupted-cutover",
      "schema_version": 1,
      "sequence": 20,
      "territory": "rollout-two"
    }
  22. Milestone evaluation startedrollout-three
    event #21
    {
      "elapsed_ms": 356,
      "kind": "milestone_evaluation_started",
      "milestone": "uninterrupted-cutover",
      "schema_version": 1,
      "sequence": 21,
      "territory": "rollout-three"
    }
  23. Milestone passedrollout-one
    event #22
    {
      "elapsed_ms": 67392,
      "evidence": {
        "samples": 684,
        "uninterrupted": true,
        "version": "v2"
      },
      "kind": "milestone_passed",
      "milestone": "uninterrupted-cutover",
      "points": 45,
      "schema_version": 1,
      "sequence": 22,
      "territory": "rollout-one"
    }
  24. Milestone failedrollout-three
    event #23
    {
      "category": "verification_failed",
      "detail": "public endpoint never cut over to v2",
      "elapsed_ms": 101508,
      "kind": "milestone_failed",
      "milestone": "uninterrupted-cutover",
      "retryable": true,
      "schema_version": 1,
      "sequence": 23,
      "territory": "rollout-three"
    }
  25. Milestone failedrollout-two
    event #24
    {
      "category": "verification_failed",
      "detail": "public endpoint never cut over to v2",
      "elapsed_ms": 101508,
      "kind": "milestone_failed",
      "milestone": "uninterrupted-cutover",
      "retryable": true,
      "schema_version": 1,
      "sequence": 24,
      "territory": "rollout-two"
    }
  26. Milestone evaluation startedrollout-one
    event #25
    {
      "elapsed_ms": 101508,
      "kind": "milestone_evaluation_started",
      "milestone": "write-new",
      "schema_version": 1,
      "sequence": 25,
      "territory": "rollout-one"
    }
  27. Milestone passedrollout-one
    event #26
    {
      "elapsed_ms": 101597,
      "evidence": {
        "record": "rollout-b494f488b52a321b",
        "value": "opaque-46831a05500348d93d1d49d3"
      },
      "kind": "milestone_passed",
      "milestone": "write-new",
      "points": 15,
      "schema_version": 1,
      "sequence": 26,
      "territory": "rollout-one"
    }
  28. Milestone evaluation startedrollout-one
    event #27
    {
      "elapsed_ms": 101597,
      "kind": "milestone_evaluation_started",
      "milestone": "v2-restart",
      "schema_version": 1,
      "sequence": 27,
      "territory": "rollout-one"
    }
  29. Milestone passedrollout-one
    event #28
    {
      "elapsed_ms": 102427,
      "evidence": {
        "record": "rollout-b494f488b52a321b",
        "v2_restart": true,
        "value": "opaque-46831a05500348d93d1d49d3"
      },
      "kind": "milestone_passed",
      "milestone": "v2-restart",
      "points": 15,
      "schema_version": 1,
      "sequence": 28,
      "territory": "rollout-one"
    }
  30. Milestone evaluation startedrollout-one
    event #29
    {
      "elapsed_ms": 102427,
      "kind": "milestone_evaluation_started",
      "milestone": "host-reboot",
      "schema_version": 1,
      "sequence": 29,
      "territory": "rollout-one"
    }
  31. Milestone passedrollout-one
    event #30
    {
      "elapsed_ms": 116019,
      "evidence": {
        "reboot": true,
        "record": "rollout-b494f488b52a321b",
        "value": "opaque-46831a05500348d93d1d49d3",
        "version": "v2"
      },
      "kind": "milestone_passed",
      "milestone": "host-reboot",
      "points": 20,
      "schema_version": 1,
      "sequence": 30,
      "territory": "rollout-one"
    }
  32. Competitor state changedrollout-one
    event #31
    {
      "elapsed_ms": 116019,
      "from": "verifying",
      "kind": "competitor_state_changed",
      "reason": "completion milestone passed",
      "schema_version": 1,
      "sequence": 31,
      "territory": "rollout-one",
      "to": "durable"
    }
  33. Durable deployment completedrollout-one
    event #32
    {
      "elapsed_ms": 116019,
      "kind": "durable_deployment_completed",
      "schema_version": 1,
      "sequence": 32,
      "territory": "rollout-one"
    }
  34. Match state changed
    event #33
    {
      "elapsed_ms": 116019,
      "from": "running",
      "kind": "match_state_changed",
      "schema_version": 1,
      "sequence": 33,
      "to": "finished"
    }
  35. Match finished
    event #34
    {
      "elapsed_ms": 116019,
      "kind": "match_finished",
      "reason": "first durable deployment",
      "schema_version": 1,
      "sequence": 34,
      "winner": "rollout-one"
    }
  36. Usage chargeddeepseek
    event #35
    {
      "agent": "deepseek",
      "cost_microusd": 9266,
      "elapsed_ms": 116024,
      "input_tokens": 18417,
      "kind": "usage_charged",
      "output_tokens": 3069,
      "resource_units": 1,
      "schema_version": 1,
      "sequence": 35
    }
  37. Usage chargedglm
    event #36
    {
      "agent": "glm",
      "cost_microusd": 55059,
      "elapsed_ms": 116024,
      "input_tokens": 22322,
      "kind": "usage_charged",
      "output_tokens": 3988,
      "resource_units": 1,
      "schema_version": 1,
      "sequence": 36
    }
  38. Usage chargedluna
    event #37
    {
      "agent": "luna",
      "cost_microusd": 15185,
      "elapsed_ms": 116024,
      "input_tokens": 39,
      "kind": "usage_charged",
      "output_tokens": 7896,
      "resource_units": 1,
      "schema_version": 1,
      "sequence": 37
    }
  39. Post match drain started
    event #38
    {
      "elapsed_ms": 116024,
      "kind": "post_match_drain_started",
      "pending_agents": 3,
      "schema_version": 1,
      "sequence": 38,
      "timeout_ms": 30000
    }
  40. Agent finisheddeepseek
    event #39
    {
      "agent": "deepseek",
      "detail": "Claux reported rate_limited (exit status 11): openrouter API error (429 Too Many Requests) for model 'deepseek/deepseek-v4.1-flash': Provider returned error. Retry later or choose another model/provider",
      "elapsed_ms": 116024,
      "kind": "agent_finished",
      "schema_version": 1,
      "sequence": 39,
      "source": "provider",
      "success": false
    }
  41. Usage chargeddeepseek
    event #40
    {
      "agent": "deepseek",
      "cost_microusd": 0,
      "elapsed_ms": 116024,
      "input_tokens": 0,
      "kind": "usage_charged",
      "output_tokens": 0,
      "resource_units": 0,
      "schema_version": 1,
      "sequence": 40
    }
  42. Agent interruptedluna
    event #41
    {
      "agent": "luna",
      "detail": "agent session was interrupted by the referee's host reboot",
      "elapsed_ms": 116024,
      "kind": "agent_interrupted",
      "schema_version": 1,
      "sequence": 41,
      "source": "arena"
    }
  43. Usage chargedluna
    event #42
    {
      "agent": "luna",
      "cost_microusd": 0,
      "elapsed_ms": 116024,
      "input_tokens": 0,
      "kind": "usage_charged",
      "output_tokens": 0,
      "resource_units": 0,
      "schema_version": 1,
      "sequence": 42
    }
  44. Agent outracedglm
    event #43
    {
      "agent": "glm",
      "elapsed_ms": 116024,
      "kind": "agent_outraced",
      "reason": "rollout-one reached durable first; build ended at the frozen clock",
      "schema_version": 1,
      "sequence": 43
    }
  45. Post match drain finished
    event #44
    {
      "captured_agents": 2,
      "elapsed_ms": 116024,
      "kind": "post_match_drain_finished",
      "schema_version": 1,
      "sequence": 44,
      "terminated_agents": 1
    }