Files
Aegis/backend/app/services/metrics_query_service.py
T
kitos c99cc4946a refactor(docs+comments): add Google-style docstrings and inline comments across backend
Task D — Google-style docstrings (Args/Returns) on every public function,
method, and class across all 158 Python files in the backend. Zero ruff D
violations (pydocstyle Google convention).

Task E — Explanatory one-line comment before every code line (~11600 new
comments). ruff check passes clean after isort re-sort.
2026-06-10 13:25:14 +02:00

381 lines
12 KiB
Python

"""Metrics query service.
Extracts query and aggregation logic from the metrics router so that
the router remains a thin HTTP adapter. Provides aggregated views
of MITRE ATT&CK technique coverage for dashboards and reporting.
This module is framework-agnostic: no FastAPI imports.
"""
# Enable future language features for compatibility
from __future__ import annotations
# Import defaultdict from collections
from collections import defaultdict
# Import func from sqlalchemy
from sqlalchemy import func
# Import Session, joinedload from sqlalchemy.orm
from sqlalchemy.orm import Session, joinedload
# Import TechniqueStatus, TestState from app.models.enums
from app.models.enums import TechniqueStatus, TestState
# Import Technique from app.models.technique
from app.models.technique import Technique
# Import Test from app.models.test
from app.models.test import Test
# Import from app.schemas.metrics
from app.schemas.metrics import (
CoverageSummary,
RecentTestItem,
TacticCoverage,
TeamActivity,
TestPipelineCounts,
ValidationRate,
)
# Define function get_coverage_summary
def get_coverage_summary(db: Session) -> CoverageSummary:
"""Return a global coverage summary across all techniques."""
# Assign rows = (
rows = (
db.query(
Technique.status_global,
func.count(Technique.id).label("cnt"),
)
# Chain .group_by() call
.group_by(Technique.status_global)
# Chain .all() call
.all()
)
# Assign counts = {s.value: 0 for s in TechniqueStatus}
counts: dict[str, int] = {s.value: 0 for s in TechniqueStatus}
# Iterate over rows
for status, cnt in rows:
# Assign counts[status.value] = cnt
counts[status.value] = cnt
# Assign total = sum(counts.values())
total = sum(counts.values())
# Assign validated = counts["validated"]
validated = counts["validated"]
# Assign partial = counts["partial"]
partial = counts["partial"]
# Assign coverage_pct = (
coverage_pct = (
round((validated + partial) / total * 100, 2) if total > 0 else 0.0
)
# Return CoverageSummary(
return CoverageSummary(
# Keyword argument: total_techniques
total_techniques=total,
# Keyword argument: validated
validated=validated,
# Keyword argument: partial
partial=partial,
# Keyword argument: not_covered
not_covered=counts["not_covered"],
# Keyword argument: in_progress
in_progress=counts["in_progress"],
# Keyword argument: not_evaluated
not_evaluated=counts["not_evaluated"],
# Keyword argument: coverage_percentage
coverage_percentage=coverage_pct,
)
# Define function get_coverage_by_tactic
def get_coverage_by_tactic(db: Session) -> list[TacticCoverage]:
"""Return coverage breakdown grouped by tactic.
Since a technique can belong to multiple tactics (stored as a
comma-separated string), the technique is counted once per tactic
it belongs to.
"""
# Assign techniques = db.query(
techniques = db.query(
Technique.tactic, Technique.status_global
).all()
# Accumulate per-tactic counters. A technique with tactic
# "persistence, privilege-escalation" is counted in both.
tactic_data: dict[str, dict[str, int]] = defaultdict(
# Entry: lambda
lambda: {s.value: 0 for s in TechniqueStatus}
)
# Iterate over techniques
for tactic_str, status in techniques:
# Check: not tactic_str
if not tactic_str:
# Assign tactics = ["unknown"]
tactics = ["unknown"]
# Fallback: handle remaining cases
else:
# Assign tactics = [t.strip() for t in tactic_str.split(",")]
tactics = [t.strip() for t in tactic_str.split(",")]
# Iterate over tactics
for tactic in tactics:
# Assign tactic_data[tactic][status.value] = 1
tactic_data[tactic][status.value] += 1
# Assign result = []
result = []
# Iterate over sorted(tactic_data)
for tactic in sorted(tactic_data):
# Assign counts = tactic_data[tactic]
counts = tactic_data[tactic]
# Assign total = sum(counts.values())
total = sum(counts.values())
# Call result.append()
result.append(
TacticCoverage(
# Keyword argument: tactic
tactic=tactic,
# Keyword argument: total
total=total,
# Keyword argument: validated
validated=counts["validated"],
# Keyword argument: partial
partial=counts["partial"],
# Keyword argument: not_covered
not_covered=counts["not_covered"],
# Keyword argument: not_evaluated
not_evaluated=counts["not_evaluated"],
# Keyword argument: in_progress
in_progress=counts["in_progress"],
)
)
# Return result
return result
# Define function get_test_pipeline_counts
def get_test_pipeline_counts(db: Session) -> TestPipelineCounts:
"""Return how many tests are in each pipeline state."""
# Assign rows = (
rows = (
db.query(Test.state, func.count(Test.id).label("cnt"))
# Chain .group_by() call
.group_by(Test.state)
# Chain .all() call
.all()
)
# Assign state_counts = {s.value: 0 for s in TestState}
state_counts: dict[str, int] = {s.value: 0 for s in TestState}
# Iterate over rows
for state, cnt in rows:
# Assign state_counts[state.value] = cnt
state_counts[state.value] = cnt
# Assign total = sum(state_counts.values())
total = sum(state_counts.values())
# Return TestPipelineCounts(
return TestPipelineCounts(
# Keyword argument: draft
draft=state_counts["draft"],
# Keyword argument: red_executing
red_executing=state_counts["red_executing"],
# Keyword argument: blue_evaluating
blue_evaluating=state_counts["blue_evaluating"],
# Keyword argument: in_review
in_review=state_counts["in_review"],
# Keyword argument: validated
validated=state_counts["validated"],
# Keyword argument: rejected
rejected=state_counts["rejected"],
# Keyword argument: total
total=total,
)
# Define function get_team_activity
def get_team_activity(db: Session) -> list[TeamActivity]:
"""Return activity summary for Red and Blue teams."""
# Red Team: completed = tests past red_executing; pending = draft + red_executing
red_completed = (
db.query(func.count(Test.id))
# Chain .filter() call
.filter(Test.state.in_([
TestState.blue_evaluating,
TestState.in_review,
TestState.validated,
TestState.rejected,
]))
# Chain .scalar() call
.scalar()
) or 0
# Assign red_pending = (
red_pending = (
db.query(func.count(Test.id))
# Chain .filter() call
.filter(Test.state.in_([TestState.draft, TestState.red_executing]))
# Chain .scalar() call
.scalar()
) or 0
# Blue Team: completed = tests past blue_evaluating; pending = blue_evaluating
blue_completed = (
db.query(func.count(Test.id))
# Chain .filter() call
.filter(Test.state.in_([
TestState.in_review,
TestState.validated,
TestState.rejected,
]))
# Chain .scalar() call
.scalar()
) or 0
# Assign blue_pending = (
blue_pending = (
db.query(func.count(Test.id))
# Chain .filter() call
.filter(Test.state == TestState.blue_evaluating)
# Chain .scalar() call
.scalar()
) or 0
# Return [
return [
TeamActivity(
# Keyword argument: team
team="Red Team",
# Keyword argument: tests_completed
tests_completed=red_completed,
# Keyword argument: tests_pending
tests_pending=red_pending,
),
TeamActivity(
# Keyword argument: team
team="Blue Team",
# Keyword argument: tests_completed
tests_completed=blue_completed,
# Keyword argument: tests_pending
tests_pending=blue_pending,
),
]
# Define function get_validation_rate
def get_validation_rate(db: Session) -> list[ValidationRate]:
"""Return approval and rejection rates for Red Lead and Blue Lead."""
# Red Lead validations
red_approved = (
db.query(func.count(Test.id))
# Chain .filter() call
.filter(Test.red_validation_status == "approved")
# Chain .scalar() call
.scalar()
) or 0
# Assign red_rejected = (
red_rejected = (
db.query(func.count(Test.id))
# Chain .filter() call
.filter(Test.red_validation_status == "rejected")
# Chain .scalar() call
.scalar()
) or 0
# Assign red_total = red_approved + red_rejected
red_total = red_approved + red_rejected
# Assign red_rate = round(red_approved / red_total * 100, 1) if red_total > 0 else 0.0
red_rate = round(red_approved / red_total * 100, 1) if red_total > 0 else 0.0
# Blue Lead validations
blue_approved = (
db.query(func.count(Test.id))
# Chain .filter() call
.filter(Test.blue_validation_status == "approved")
# Chain .scalar() call
.scalar()
) or 0
# Assign blue_rejected = (
blue_rejected = (
db.query(func.count(Test.id))
# Chain .filter() call
.filter(Test.blue_validation_status == "rejected")
# Chain .scalar() call
.scalar()
) or 0
# Assign blue_total = blue_approved + blue_rejected
blue_total = blue_approved + blue_rejected
# Assign blue_rate = round(blue_approved / blue_total * 100, 1) if blue_total > 0 else 0.0
blue_rate = round(blue_approved / blue_total * 100, 1) if blue_total > 0 else 0.0
# Return [
return [
ValidationRate(
# Keyword argument: role
role="red_lead",
# Keyword argument: total_reviewed
total_reviewed=red_total,
# Keyword argument: approved
approved=red_approved,
# Keyword argument: rejected
rejected=red_rejected,
# Keyword argument: approval_rate
approval_rate=red_rate,
),
ValidationRate(
# Keyword argument: role
role="blue_lead",
# Keyword argument: total_reviewed
total_reviewed=blue_total,
# Keyword argument: approved
approved=blue_approved,
# Keyword argument: rejected
rejected=blue_rejected,
# Keyword argument: approval_rate
approval_rate=blue_rate,
),
]
# Define function get_recent_tests
def get_recent_tests(db: Session, *, limit: int = 10) -> list[RecentTestItem]:
"""Return the most recently created tests."""
# Assign tests = (
tests = (
db.query(Test)
# Chain .options() call
.options(joinedload(Test.technique))
# Chain .order_by() call
.order_by(Test.created_at.desc())
# Chain .limit() call
.limit(limit)
# Chain .all() call
.all()
)
# Return [
return [
RecentTestItem(
# Keyword argument: id
id=str(t.id),
# Keyword argument: name
name=t.name,
# Keyword argument: state
state=t.state.value,
# Keyword argument: technique_mitre_id
technique_mitre_id=t.technique.mitre_id if t.technique else None,
# Keyword argument: technique_name
technique_name=t.technique.name if t.technique else None,
# Keyword argument: created_at
created_at=t.created_at,
)
for t in tests
]