feat(recovery): surface runner systemd timeout receipt
Some checks failed
CD Pipeline / workflow-shape (push) Successful in 0s
CD Pipeline / cancel-stale-cd (push) Has been skipped
CD Pipeline / tests (push) Successful in 35s
CD Pipeline / build-and-deploy (push) Failing after 2m37s
CD Pipeline / post-deploy-checks (push) Has been skipped
E2E Health Check / e2e-health (push) Failing after 39s
AI 技術雷達監控 / ai-technology-watch (push) Successful in 44s
AWOOOI Harbor 110 Local Repair / workflow-shape (push) Successful in 0s
AWOOOI Harbor 110 Local Repair / harbor-110-local-repair (push) Has been cancelled

This commit is contained in:
Your Name
2026-06-30 23:48:00 +08:00
parent b09b103a59
commit f9ad460ff2
4 changed files with 63 additions and 1 deletions

View File

@@ -148,6 +148,9 @@ def validate_harbor_registry_controlled_recovery_receipt(
"ssh_publickey_server_accepts_key_then_timeout_seen": (
ssh_diagnosis["server_accepts_key_then_timeout_seen"]
),
"ssh_publickey_runner_systemctl_show_timeout_seen": (
ssh_diagnosis["runner_systemctl_show_timeout_seen"]
),
"ssh_publickey_node_exporter_ok": ssh_diagnosis["node_exporter_ok"],
"ssh_publickey_port_tcp_open": ssh_diagnosis["ssh_port_tcp_open"],
"ssh_local_repair_receipt_seen": ssh_local["receipt_seen"],
@@ -337,6 +340,7 @@ def _parse_ssh_publickey_diagnosis_output(output: str) -> dict[str, Any]:
fields = _parse_key_values(output)
marker_seen = "AWOOOI_110_SSH_PUBLICKEY_AUTH_DIAGNOSIS" in output
auth_attempts = _ssh_auth_attempts(output)
systemd_units = _systemd_unit_signals(output)
wooo_publickey = _auth_classification(
auth_attempts,
user="wooo",
@@ -358,6 +362,11 @@ def _parse_ssh_publickey_diagnosis_output(output: str) -> dict[str, Any]:
permission_denied_count = sum(
1 for item in auth_attempts if item["classification"] == "permission_denied"
)
runner_systemctl_show_timeout_seen = any(
item["unit"].startswith("actions.runner")
and item["classifier"] == "systemctl_show_timeout"
for item in systemd_units
)
ssh_port_tcp_open = str(fields.get("SSH_PORT") or "") == "tcp_open"
node_exporter_ok = str(fields.get("NODE_EXPORTER") or "") == "ok"
return {
@@ -370,6 +379,9 @@ def _parse_ssh_publickey_diagnosis_output(output: str) -> dict[str, Any]:
"ssh_banner_seen": "SSH_BANNER=SSH-" in output,
"auth_attempt_count": len(auth_attempts),
"auth_classifications": auth_attempts,
"systemd_unit_signal_count": len(systemd_units),
"systemd_unit_signals": systemd_units,
"runner_systemctl_show_timeout_seen": runner_systemctl_show_timeout_seen,
"wooo_publickey_classification": wooo_publickey,
"publickey_offer_timeout_seen": publickey_offer_timeout_seen,
"server_accepts_key_then_timeout_seen": (
@@ -400,6 +412,22 @@ def _ssh_auth_attempts(output: str) -> list[dict[str, Any]]:
return attempts
def _systemd_unit_signals(output: str) -> list[dict[str, str]]:
signals: list[dict[str, str]] = []
for line in output.splitlines():
if not line.startswith("SYSTEMD_UNIT "):
continue
fields = _parse_key_values(line)
signals.append(
{
"unit": str(fields.get("unit") or ""),
"active_state": str(fields.get("active_state") or ""),
"classifier": str(fields.get("classifier") or ""),
}
)
return signals
def _auth_classification(
attempts: list[dict[str, Any]],
*,
@@ -792,6 +820,8 @@ def _active_blockers(
and not ssh_local["control_channel_metadata_ready"]
):
blockers.append("ssh_publickey_server_accepts_key_then_timeout_on_wooo")
if ssh_diagnosis["runner_systemctl_show_timeout_seen"]:
blockers.append("runner_systemctl_show_timeout_on_110")
if ssh_local["receipt_seen"] and not ssh_local["control_channel_metadata_ready"]:
blockers.append("ssh_local_repair_receipt_metadata_not_ready")
if not watchdog_check["receipt_seen"]:

View File

@@ -119,6 +119,7 @@ def test_harbor_recovery_receipt_accepts_ssh_publickey_diagnosis() -> None:
assert "ssh_publickey_server_accepts_key_then_timeout_on_wooo" in payload[
"active_blockers"
]
assert "runner_systemctl_show_timeout_on_110" in payload["active_blockers"]
diagnosis = payload["readback"]["ssh_publickey_diagnosis"]
assert diagnosis["diagnosis_ready"] is True
assert diagnosis["node_exporter_ok"] is True
@@ -128,6 +129,10 @@ def test_harbor_recovery_receipt_accepts_ssh_publickey_diagnosis() -> None:
"server_accepts_key_then_timeout"
)
assert diagnosis["server_accepts_key_then_timeout_seen"] is True
assert diagnosis["runner_systemctl_show_timeout_seen"] is True
assert diagnosis["systemd_unit_signals"][0]["classifier"] == (
"systemctl_show_timeout"
)
assert diagnosis["raw_output_returned"] is False
phases = {
phase["phase_id"]: phase
@@ -141,6 +146,10 @@ def test_harbor_recovery_receipt_accepts_ssh_publickey_diagnosis() -> None:
assert payload["rollups"]["ssh_publickey_wooo_publickey_classification"] == (
"server_accepts_key_then_timeout"
)
assert (
payload["rollups"]["ssh_publickey_runner_systemctl_show_timeout_seen"]
is True
)
assert payload["input_redaction"]["ssh_publickey_diagnosis_output"][
"line_count"
] > 0
@@ -385,6 +394,7 @@ SSH_AUTH user=root mode=publickey rc=255 classification=permission_denied
SSH_AUTH user=git mode=publickey rc=255 classification=preauth_timeout
SSH_AUTH user=ollama mode=publickey rc=255 classification=preauth_timeout
SSH_AUTH user=wooo mode=password_disabled rc=255 classification=permission_denied
SYSTEMD_UNIT unit=actions.runner.owenhytsai-awoooi.awoooi-110.service active_state=scrape_error classifier=systemctl_show_timeout
INTERPRETATION=server_accepts_key_then_timeout_on_wooo_means_check_110_session_pam_account_or_shell_path
"""