Files
FabledSteward/steward/models/alerts.py
T
bvandeusen 4771d17f6d
CI / lint (push) Successful in 2s
CI / unit (push) Successful in 8s
CI / integration (push) Failing after 2m16s
feat(alerts): run an Ansible playbook on alert firing (task 250)
Rebuilds the deleted NUT/UPS automation as a general alert action: any metric
can drive a playbook run on transition-to-firing.

- models/alerts.py + migration 0014: AlertRule.ansible_action (JSON, admin-only,
  reuses the #546 param shape); AlertEvent.ansible_run_id links a firing event to
  the run it triggered
- core/alerts.py: pure alert_extra_vars() injects steward_alert_* context; on
  ('firing', event) with an action set, schedule _run_ansible_action (deferred
  after commit, same pattern as notifications) — fires once per transition,
  consecutive_failures_required is the debounce; system-triggered AnsibleRun
- alerts/routes.py: admin-only parse/validate of the action (source must be
  configured, playbook must exist); operators keep editing rules, action preserved
- rules_form.html: admin-only 'On firing -> run a playbook' section
- tests: unit for alert_extra_vars; integration drives record_metric to firing
  and asserts a system AnsibleRun ran the playbook with the injected var and the
  event linked to it

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-02 14:22:29 -04:00

107 lines
4.8 KiB
Python

from __future__ import annotations
import enum
import uuid
from datetime import datetime, timezone
from sqlalchemy import JSON, Boolean, DateTime, Enum, Float, ForeignKey, Integer, String, Text
from sqlalchemy.orm import Mapped, mapped_column
from .base import Base
class AlertOperator(str, enum.Enum):
gt = ">"
lt = "<"
gte = ">="
lte = "<="
eq = "=="
ne = "!="
class AlertStateEnum(str, enum.Enum):
inactive = "inactive"
pending = "pending"
firing = "firing"
acknowledged = "acknowledged"
resolved = "resolved"
class AlertRule(Base):
__tablename__ = "alert_rules"
id: Mapped[str] = mapped_column(String(36), primary_key=True, default=lambda: str(uuid.uuid4()))
name: Mapped[str] = mapped_column(String(128), nullable=False)
source_module: Mapped[str] = mapped_column(String(64), nullable=False)
resource_name: Mapped[str] = mapped_column(String(255), nullable=False)
metric_name: Mapped[str] = mapped_column(String(128), nullable=False)
operator: Mapped[AlertOperator] = mapped_column(Enum(AlertOperator), nullable=False)
threshold: Mapped[float] = mapped_column(Float, nullable=False)
consecutive_failures_required: Mapped[int] = mapped_column(Integer, nullable=False, default=1)
enabled: Mapped[bool] = mapped_column(Boolean, nullable=False, default=True)
# Optional admin-only action: run an Ansible playbook on transition-to-firing.
# Shape: {source, playbook, inventory, extra_vars, limit, tags, check}. NULL = none.
ansible_action: Mapped[dict | None] = mapped_column(JSON, nullable=True)
created_by: Mapped[str] = mapped_column(String(36), ForeignKey("users.id", ondelete="RESTRICT"), nullable=False)
created_at: Mapped[datetime] = mapped_column(
DateTime(timezone=True), nullable=False, default=lambda: datetime.now(timezone.utc)
)
class AlertState(Base):
__tablename__ = "alert_states"
id: Mapped[str] = mapped_column(String(36), primary_key=True, default=lambda: str(uuid.uuid4()))
rule_id: Mapped[str] = mapped_column(
String(36), ForeignKey("alert_rules.id", ondelete="CASCADE"), nullable=False, unique=True
)
state: Mapped[AlertStateEnum] = mapped_column(
Enum(AlertStateEnum), nullable=False, default=AlertStateEnum.inactive
)
consecutive_failure_count: Mapped[int] = mapped_column(Integer, nullable=False, default=0)
last_transition_at: Mapped[datetime] = mapped_column(
DateTime(timezone=True), nullable=False, default=lambda: datetime.now(timezone.utc)
)
acknowledged_by: Mapped[str | None] = mapped_column(
String(36), ForeignKey("users.id", ondelete="SET NULL"), nullable=True
)
acknowledged_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True), nullable=True)
class MaintenanceWindow(Base):
__tablename__ = "maintenance_windows"
id: Mapped[str] = mapped_column(String(36), primary_key=True, default=lambda: str(uuid.uuid4()))
name: Mapped[str] = mapped_column(String(128), nullable=False)
start_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), nullable=False)
end_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), nullable=False)
# Scope — null means "all". scope_resource requires scope_source to be set.
scope_source: Mapped[str | None] = mapped_column(String(64), nullable=True)
scope_resource: Mapped[str | None] = mapped_column(String(255), nullable=True)
created_by: Mapped[str] = mapped_column(
String(36), ForeignKey("users.id", ondelete="RESTRICT"), nullable=False
)
created_at: Mapped[datetime] = mapped_column(
DateTime(timezone=True), nullable=False, default=lambda: datetime.now(timezone.utc)
)
class AlertEvent(Base):
__tablename__ = "alert_events"
id: Mapped[str] = mapped_column(String(36), primary_key=True, default=lambda: str(uuid.uuid4()))
rule_id: Mapped[str] = mapped_column(
String(36), ForeignKey("alert_rules.id", ondelete="CASCADE"), nullable=False
)
from_state: Mapped[str] = mapped_column(String(32), nullable=False)
to_state: Mapped[str] = mapped_column(String(32), nullable=False)
metric_value: Mapped[float] = mapped_column(Float, nullable=False)
transitioned_at: Mapped[datetime] = mapped_column(
DateTime(timezone=True), nullable=False, default=lambda: datetime.now(timezone.utc)
)
email_sent: Mapped[bool | None] = mapped_column(Boolean, nullable=True)
email_error: Mapped[str | None] = mapped_column(Text, nullable=True)
webhook_sent: Mapped[bool | None] = mapped_column(Boolean, nullable=True)
webhook_error: Mapped[str | None] = mapped_column(Text, nullable=True)
# Set when this firing event triggered an Ansible action run (audit link).
ansible_run_id: Mapped[str | None] = mapped_column(
String(36), ForeignKey("ansible_runs.id", ondelete="SET NULL"), nullable=True
)