Harden production workflows and agent admission

This commit is contained in:
Stanislav Rossovskii
2026-05-28 14:19:27 +04:00
parent a2e88b4e76
commit 37b1a1d6d6
109 changed files with 4927 additions and 894 deletions

View File

@@ -5,6 +5,7 @@ from sqlalchemy import (
JSON,
Boolean,
CheckConstraint,
Computed,
DateTime,
ForeignKey,
Index,
@@ -51,11 +52,57 @@ class Agent(Base):
created_at: Mapped[datetime] = mapped_column(
DateTime(timezone=True), nullable=False, server_default=func.now()
)
accepted_key_hash: Mapped[str | None] = mapped_column(Text, nullable=True)
accepted_key_fingerprint: Mapped[str | None] = mapped_column(Text, nullable=True)
accepted_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True), nullable=True)
pending_key_hash: Mapped[str | None] = mapped_column(Text, nullable=True)
pending_key_fingerprint: Mapped[str | None] = mapped_column(Text, nullable=True)
pending_hostname: Mapped[str | None] = mapped_column(Text, nullable=True)
pending_seen_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True), nullable=True)
pending_features: Mapped[dict | None] = mapped_column(_jsonb(), nullable=True)
pending_labels: Mapped[dict | None] = mapped_column(_jsonb(), nullable=True)
admission_rank: Mapped[int] = mapped_column(
Integer,
Computed("CASE WHEN pending_key_hash IS NOT NULL THEN 0 ELSE 1 END", persisted=True),
nullable=False,
)
__table_args__ = (
CheckConstraint("status IN ('alive','stale','dead')", name="agents_status_chk"),
Index("agents_status_idx", "status"),
Index("agents_last_seen_idx", "last_seen_at"),
Index("agents_admission_rank_idx", "admission_rank", "agent_id"),
Index("agents_hostname_idx", "hostname", unique=True),
Index(
"agents_accepted_key_hash_idx",
"accepted_key_hash",
unique=True,
postgresql_where=text("accepted_key_hash IS NOT NULL"),
),
Index(
"agents_pending_key_hash_idx",
"pending_key_hash",
unique=True,
postgresql_where=text("pending_key_hash IS NOT NULL"),
),
)
class AgentBlacklist(Base):
__tablename__ = "agent_blacklist"
key_hash: Mapped[str] = mapped_column(Text, primary_key=True)
key_fingerprint: Mapped[str] = mapped_column(Text, nullable=False)
agent_id: Mapped[str] = mapped_column(Text, nullable=False)
hostname: Mapped[str] = mapped_column(Text, nullable=False)
created_at: Mapped[datetime] = mapped_column(
DateTime(timezone=True), nullable=False, server_default=func.now()
)
last_seen_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), nullable=False)
__table_args__ = (
Index("agent_blacklist_fingerprint_idx", "key_fingerprint"),
Index("agent_blacklist_last_seen_idx", "last_seen_at"),
)
@@ -117,6 +164,19 @@ class Event(Base):
),
Index("events_observed_at_idx", text("observed_at DESC")),
Index("events_received_at_idx", text("received_at DESC")),
Index("events_received_event_idx", text("received_at DESC"), text("event_id DESC")),
Index(
"events_agent_received_event_idx",
"agent_id",
text("received_at DESC"),
text("event_id DESC"),
),
Index(
"events_check_received_event_idx",
"check_id",
text("received_at DESC"),
text("event_id DESC"),
),
)
@@ -144,6 +204,25 @@ class Incident(Base):
resolved_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True), nullable=True)
summary: Mapped[str | None] = mapped_column(Text, nullable=True)
last_event_id: Mapped[UUID] = mapped_column(_uuid(), nullable=False)
# PH-review: stored generated column so the default UI sort
# (status_rank, opened_at, id) is served by a plain B-tree index without
# planner mismatches between query-time and index-time CASE expressions.
# Keep aligned with `_STATUS_RANK` in api/incidents.py.
status_rank: Mapped[int] = mapped_column(
Integer,
Computed(
"CASE "
"WHEN state = 'open' AND severity = 'critical' THEN 5 "
"WHEN state = 'open' AND severity = 'warning' THEN 4 "
"WHEN state = 'open' AND severity = 'unknown' THEN 3 "
"WHEN state = 'resolved' AND severity = 'critical' THEN 2 "
"WHEN state = 'resolved' AND severity = 'warning' THEN 1 "
"WHEN state = 'resolved' AND severity = 'unknown' THEN 0 "
"END",
persisted=True,
),
nullable=False,
)
__table_args__ = (
CheckConstraint("state IN ('open','resolved')", name="incidents_state_chk"),
@@ -156,7 +235,12 @@ class Incident(Base):
unique=True,
postgresql_where=text("state = 'open'"),
),
Index("incidents_state_opened_idx", "state", text("opened_at DESC")),
Index(
"incidents_status_rank_idx",
text("status_rank DESC"),
text("opened_at DESC"),
text("id DESC"),
),
)
@@ -193,4 +277,6 @@ class NotificationOutbox(Base):
"next_attempt_at",
postgresql_where=text("state IN ('pending','retry')"),
),
Index("outbox_created_at_idx", text("created_at DESC"), text("id DESC")),
Index("outbox_updated_at_idx", text("updated_at DESC"), text("id DESC")),
)