Merge remote-tracking branch 'gitea-ssh/main' into codex/p0-obs-002-credential-20260722
All checks were successful
CD Pipeline / select-latest-carrier (push) Successful in 49s
CD Pipeline / workflow-shape (push) Successful in 0s
CD Pipeline / cancel-stale-cd (push) Has been skipped
CD Pipeline / tests (push) Successful in 2m34s
CD Pipeline / revalidate-deploy-carrier (push) Successful in 41s
CD Pipeline / build-and-deploy (push) Successful in 14m46s
AWOOOI Harbor 110 Local Repair / workflow-shape (push) Successful in 1s
AWOOOI Harbor 110 Local Repair / harbor-110-local-repair (push) Successful in 21s
CD Pipeline / revalidate-post-deploy-carrier (push) Successful in 39s
CD Pipeline / post-deploy-checks (push) Successful in 2m50s
All checks were successful
CD Pipeline / select-latest-carrier (push) Successful in 49s
CD Pipeline / workflow-shape (push) Successful in 0s
CD Pipeline / cancel-stale-cd (push) Has been skipped
CD Pipeline / tests (push) Successful in 2m34s
CD Pipeline / revalidate-deploy-carrier (push) Successful in 41s
CD Pipeline / build-and-deploy (push) Successful in 14m46s
AWOOOI Harbor 110 Local Repair / workflow-shape (push) Successful in 1s
AWOOOI Harbor 110 Local Repair / harbor-110-local-repair (push) Successful in 21s
CD Pipeline / revalidate-post-deploy-carrier (push) Successful in 39s
CD Pipeline / post-deploy-checks (push) Successful in 2m50s
This commit is contained in:
@@ -15,10 +15,15 @@ Environment=TEXTFILE_DIR=/home/wooo/node_exporter_textfiles
|
||||
Environment=LOG_DIR=/home/wooo/reboot-recovery
|
||||
Environment=TARGET_MINUTES=10
|
||||
Environment=AI_LOG_TRIAGE_AUTO_RECOVERY_MODE=apply
|
||||
Environment=AI_LOG_TRIAGE_AUTO_RECOVERY_TIMEOUT_SECONDS=420
|
||||
Environment=AI_LOG_TRIAGE_AUTO_RECOVERY_POST_APPLY_SETTLE_SECONDS=20
|
||||
Environment=AI_LOG_TRIAGE_AUTO_RECOVERY_TIMEOUT_SECONDS=60
|
||||
Environment=AI_LOG_TRIAGE_AUTO_RECOVERY_POST_APPLY_SETTLE_SECONDS=5
|
||||
Environment=SSH_COMMAND_TIMEOUT_SECONDS=8
|
||||
Environment=POST_REBOOT_READINESS_TIMEOUT_SECONDS=60
|
||||
Environment=STOCK_READBACK_TIMEOUT_SECONDS=10
|
||||
Environment=PUBLIC_MAINTENANCE_READBACK_TIMEOUT_SECONDS=5
|
||||
Environment=WINDOWS99_REMOTE_VERIFY_TIMEOUT=30
|
||||
ExecStart=/usr/local/bin/awoooi-reboot-auto-recovery-slo.sh
|
||||
TimeoutStartSec=600
|
||||
TimeoutStartSec=330
|
||||
StandardOutput=journal
|
||||
StandardError=journal
|
||||
|
||||
|
||||
@@ -17,8 +17,8 @@ LOCK_FILE="${LOCK_FILE:-${LOG_DIR}/reboot_auto_recovery_slo.lock}"
|
||||
STOCK_FRESHNESS_URL="${STOCK_FRESHNESS_URL:-https://stock.wooo.work/api/v1/system/freshness}"
|
||||
STOCK_INGESTION_URL="${STOCK_INGESTION_URL:-https://stock.wooo.work/api/v1/system/ingestion}"
|
||||
STOCK_READBACK_TIMEOUT_SECONDS="${STOCK_READBACK_TIMEOUT_SECONDS:-10}"
|
||||
POST_REBOOT_READINESS_TIMEOUT_SECONDS="${POST_REBOOT_READINESS_TIMEOUT_SECONDS:-120}"
|
||||
PUBLIC_MAINTENANCE_READBACK_TIMEOUT_SECONDS="${PUBLIC_MAINTENANCE_READBACK_TIMEOUT_SECONDS:-8}"
|
||||
POST_REBOOT_READINESS_TIMEOUT_SECONDS="${POST_REBOOT_READINESS_TIMEOUT_SECONDS:-60}"
|
||||
PUBLIC_MAINTENANCE_READBACK_TIMEOUT_SECONDS="${PUBLIC_MAINTENANCE_READBACK_TIMEOUT_SECONDS:-5}"
|
||||
PUBLIC_MAINTENANCE_URLS="${PUBLIC_MAINTENANCE_URLS:-https://awoooi.wooo.work/api/v1/health https://awoooi.wooo.work/ https://stock.wooo.work/api/v1/system/freshness https://mo.wooo.work/health https://bitan.wooo.work/ https://www.tsenyang.com/}"
|
||||
WINDOWS99_VMWARE_FALLBACK_MAX_AGE_SECONDS="${WINDOWS99_VMWARE_FALLBACK_MAX_AGE_SECONDS:-900}"
|
||||
# Host 111 is a physical MacBook/Ollama node. It remains in whole-host probes,
|
||||
@@ -26,8 +26,8 @@ WINDOWS99_VMWARE_FALLBACK_MAX_AGE_SECONDS="${WINDOWS99_VMWARE_FALLBACK_MAX_AGE_S
|
||||
WINDOWS99_REQUIRED_VM_ALIASES="${WINDOWS99_REQUIRED_VM_ALIASES:-110 188 120 121 112}"
|
||||
POST_REBOOT_READINESS_FALLBACK_MAX_AGE_SECONDS="${POST_REBOOT_READINESS_FALLBACK_MAX_AGE_SECONDS:-900}"
|
||||
AI_LOG_TRIAGE_AUTO_RECOVERY_MODE="${AI_LOG_TRIAGE_AUTO_RECOVERY_MODE:-check}"
|
||||
AI_LOG_TRIAGE_AUTO_RECOVERY_TIMEOUT_SECONDS="${AI_LOG_TRIAGE_AUTO_RECOVERY_TIMEOUT_SECONDS:-420}"
|
||||
AI_LOG_TRIAGE_AUTO_RECOVERY_POST_APPLY_SETTLE_SECONDS="${AI_LOG_TRIAGE_AUTO_RECOVERY_POST_APPLY_SETTLE_SECONDS:-20}"
|
||||
AI_LOG_TRIAGE_AUTO_RECOVERY_TIMEOUT_SECONDS="${AI_LOG_TRIAGE_AUTO_RECOVERY_TIMEOUT_SECONDS:-60}"
|
||||
AI_LOG_TRIAGE_AUTO_RECOVERY_POST_APPLY_SETTLE_SECONDS="${AI_LOG_TRIAGE_AUTO_RECOVERY_POST_APPLY_SETTLE_SECONDS:-5}"
|
||||
|
||||
mkdir -p "$TEXTFILE_DIR" "$LOG_DIR"
|
||||
|
||||
|
||||
@@ -836,7 +836,7 @@ def source_controls() -> dict[str, bool]:
|
||||
"slo_systemd_service_ai_log_triage_apply_source_present": file_contains(
|
||||
source_file("scripts/reboot-recovery/awoooi-reboot-auto-recovery-slo.service"),
|
||||
"AI_LOG_TRIAGE_AUTO_RECOVERY_MODE=apply",
|
||||
"AI_LOG_TRIAGE_AUTO_RECOVERY_TIMEOUT_SECONDS=420",
|
||||
"AI_LOG_TRIAGE_AUTO_RECOVERY_TIMEOUT_SECONDS=60",
|
||||
),
|
||||
"full_host_reboot_orchestrator_source_present": file_contains(
|
||||
source_file("scripts/reboot-recovery/full-host-reboot-orchestrator.sh"),
|
||||
|
||||
@@ -92,6 +92,19 @@ def test_coordinator_covers_all_hosts_and_full_recovery_evidence() -> None:
|
||||
assert field in control
|
||||
|
||||
|
||||
def test_host188_hygiene_is_advisory_not_a_recovery_completion_gate() -> None:
|
||||
control = read("agent99-control-plane.ps1")
|
||||
conversion = control.split("function Convert-AgentRecoveryReadback", 1)[1]
|
||||
conversion = conversion.split("function Invoke-AgentRecoveryCoordinatorReadback", 1)[0]
|
||||
|
||||
advisory = conversion.split("$advisoryChecks = @(", 1)[1].split("$checks = @(", 1)[0]
|
||||
mandatory = conversion.split("$checks = @(", 1)[1].split("$sloChecks = @()", 1)[0]
|
||||
assert 'name = "host_188_hygiene_green"' in advisory
|
||||
assert 'name = "host_188_hygiene_green"' not in mandatory
|
||||
assert "advisoryFailedChecks = $advisoryFailedChecks" in conversion
|
||||
assert "verified = [bool]($failedChecks.Count -eq 0)" in conversion
|
||||
|
||||
|
||||
def test_fresh_reboot_claim_requires_fresh_artifact_and_zero_blockers() -> None:
|
||||
control = read("agent99-control-plane.ps1")
|
||||
|
||||
|
||||
@@ -87,7 +87,33 @@ def test_service_uses_deployed_source_root_and_bounded_oneshot() -> None:
|
||||
assert "Environment=TEXTFILE_DIR=/home/wooo/node_exporter_textfiles" in text
|
||||
assert "Environment=LOG_DIR=/home/wooo/reboot-recovery" in text
|
||||
assert "ExecStart=/usr/local/bin/awoooi-reboot-auto-recovery-slo.sh" in text
|
||||
assert "TimeoutStartSec=600" in text
|
||||
assert "TimeoutStartSec=330" in text
|
||||
|
||||
|
||||
def test_service_worst_case_probe_budget_finishes_before_agent99_freshness_window() -> None:
|
||||
text = SERVICE.read_text(encoding="utf-8")
|
||||
|
||||
def environment_seconds(name: str) -> int:
|
||||
match = re.search(rf"^Environment={name}=([0-9]+)$", text, re.MULTILINE)
|
||||
assert match is not None, name
|
||||
return int(match.group(1))
|
||||
|
||||
service_timeout_match = re.search(r"^TimeoutStartSec=([0-9]+)$", text, re.MULTILINE)
|
||||
assert service_timeout_match is not None
|
||||
service_timeout = int(service_timeout_match.group(1))
|
||||
agent99_freshness_wait = 420
|
||||
worst_case_budget = (
|
||||
environment_seconds("AI_LOG_TRIAGE_AUTO_RECOVERY_TIMEOUT_SECONDS")
|
||||
+ environment_seconds("AI_LOG_TRIAGE_AUTO_RECOVERY_POST_APPLY_SETTLE_SECONDS")
|
||||
+ environment_seconds("SSH_COMMAND_TIMEOUT_SECONDS") * 6
|
||||
+ environment_seconds("POST_REBOOT_READINESS_TIMEOUT_SECONDS")
|
||||
+ environment_seconds("STOCK_READBACK_TIMEOUT_SECONDS") * 2
|
||||
+ environment_seconds("PUBLIC_MAINTENANCE_READBACK_TIMEOUT_SECONDS") * 6
|
||||
+ environment_seconds("WINDOWS99_REMOTE_VERIFY_TIMEOUT")
|
||||
)
|
||||
|
||||
assert worst_case_budget <= service_timeout - 30
|
||||
assert service_timeout < agent99_freshness_wait
|
||||
|
||||
|
||||
def test_timer_waits_after_completion_instead_of_running_back_to_back() -> None:
|
||||
@@ -136,7 +162,7 @@ def test_exporter_projects_each_scorecard_blocker_to_textfile_metric() -> None:
|
||||
assert "windows99_vmware_verify_fallback_max_age_seconds" in text
|
||||
assert "find \"$LOG_DIR\" -mindepth 2 -maxdepth 2" in text
|
||||
assert "POST_REBOOT_READINESS_TIMEOUT_SECONDS" in text
|
||||
assert 'POST_REBOOT_READINESS_TIMEOUT_SECONDS="${POST_REBOOT_READINESS_TIMEOUT_SECONDS:-120}"' in text
|
||||
assert 'POST_REBOOT_READINESS_TIMEOUT_SECONDS="${POST_REBOOT_READINESS_TIMEOUT_SECONDS:-60}"' in text
|
||||
assert "POST_REBOOT_SKIP_RUNNER_GUARD=1" in text
|
||||
assert "POST_REBOOT_READINESS_SUMMARY_TIMEOUT=1" in text
|
||||
assert "POST_REBOOT_READINESS_PARTIAL_FROM_POST_START=1" in text
|
||||
|
||||
Reference in New Issue
Block a user