#5059 "Alert state machine: acknowledgement holds until resolve; N consecutive OK to resolve; editing, disabling or deleting a rule resets it". - The state machine is now next_step(), a pure function of one sample. An acknowledged alert stays acknowledged while breached; before, the next breaching sample re-fired it. Firing and acknowledged alerts resolve after consecutive_ok_required OK checks in a row (new rule column, default 1; rule form, rules list and MCP create/update_alert_rule clear_after_checks). - Changing what a rule watches (source, resource, metric, operator, threshold) or disabling it resets its alert to inactive; a firing or acknowledged one records a resolved event whose new note says why, and nobody is notified. Web and MCP edits share alerts.service.apply_rule_change. - Migration 0028: consecutive_ok_required, consecutive_ok_count, alert_events.note, and metric_value nullable (a reset has no sample). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
32 lines
1.3 KiB
Python
32 lines
1.3 KiB
Python
"""Alerts resolve after N OK checks; rule changes reset state with a note
|
|
|
|
Revision ID: 0028_alert_resolve_and_reset
|
|
Revises: 0027_user_auth_source
|
|
Create Date: 2026-10-06
|
|
"""
|
|
from typing import Sequence, Union
|
|
from alembic import op
|
|
import sqlalchemy as sa
|
|
|
|
revision: str = "0028_alert_resolve_and_reset"
|
|
down_revision: Union[str, None] = "0027_user_auth_source"
|
|
branch_labels: Union[str, Sequence[str], None] = None
|
|
depends_on: Union[str, Sequence[str], None] = None
|
|
|
|
|
|
def upgrade() -> None:
|
|
op.add_column("alert_rules", sa.Column("consecutive_ok_required", sa.Integer,
|
|
nullable=False, server_default="1"))
|
|
op.add_column("alert_states", sa.Column("consecutive_ok_count", sa.Integer,
|
|
nullable=False, server_default="0"))
|
|
op.alter_column("alert_events", "metric_value", existing_type=sa.Float, nullable=True)
|
|
op.add_column("alert_events", sa.Column("note", sa.Text, nullable=True))
|
|
|
|
|
|
def downgrade() -> None:
|
|
op.drop_column("alert_events", "note")
|
|
op.execute("UPDATE alert_events SET metric_value = 0 WHERE metric_value IS NULL")
|
|
op.alter_column("alert_events", "metric_value", existing_type=sa.Float, nullable=False)
|
|
op.drop_column("alert_states", "consecutive_ok_count")
|
|
op.drop_column("alert_rules", "consecutive_ok_required")
|