mirror of
https://github.com/shankar0123/certctl.git
synced 2026-06-07 13:51:36 +00:00
feat(M48): continuous TLS health monitoring — endpoint state machine, shared tlsprobe, 8 API endpoints, GUI
Adds continuous TLS endpoint health monitoring that closes the deploy→verify→monitor loop. After M25 verifies a deployment succeeded once, M48 continuously confirms it stays healthy. Key components: - Shared `internal/tlsprobe/` package extracted from network scanner for reuse - Health status state machine: healthy → degraded (2 failures) → down (5 failures), plus cert_mismatch when served fingerprint differs from expected - 8th scheduler loop (60s tick, per-endpoint configurable intervals) - PostgreSQL migration 000011: endpoint_health_checks + endpoint_health_history tables - 8 REST API endpoints (CRUD, history, acknowledge, summary) - Health Monitor GUI page with summary bar, status table, create modal, auto-refresh - 38 new tests (5 tlsprobe + 11 domain + 10 service + 8 handler + 4 frontend) - All coverage thresholds maintained (service 68%, handler 83%, domain 87%, middleware 63%) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
shankar0123
@@ -62,6 +62,8 @@ tags:
|
||||
description: Certificate discovery — filesystem scanning by agents and network TLS probing
|
||||
- name: Network Scan
|
||||
description: Network scan target management for active TLS certificate discovery
|
||||
- name: Health Monitoring
|
||||
description: Continuous TLS endpoint health checks with status tracking and probe history
|
||||
- name: Digest
|
||||
description: Scheduled certificate digest email notifications
|
||||
|
||||
@@ -2388,6 +2390,256 @@ paths:
|
||||
"500":
|
||||
$ref: "#/components/responses/InternalError"
|
||||
|
||||
# ─── Health Monitoring ─────────────────────────────────────────────
|
||||
/api/v1/health-checks:
|
||||
get:
|
||||
tags: [Health Monitoring]
|
||||
summary: List endpoint health checks
|
||||
description: |
|
||||
Lists all TLS endpoint health checks with optional filtering by status, certificate, or network scan target.
|
||||
Includes current status, last probe results, and probe history summary.
|
||||
operationId: listHealthChecks
|
||||
parameters:
|
||||
- name: status
|
||||
in: query
|
||||
schema:
|
||||
type: string
|
||||
enum: [Healthy, Degraded, Down, CertMismatch]
|
||||
description: Filter by health status
|
||||
- name: certificate_id
|
||||
in: query
|
||||
schema:
|
||||
type: string
|
||||
description: Filter by certificate ID
|
||||
- name: network_scan_target_id
|
||||
in: query
|
||||
schema:
|
||||
type: string
|
||||
description: Filter by network scan target ID
|
||||
- name: enabled
|
||||
in: query
|
||||
schema:
|
||||
type: boolean
|
||||
description: Filter by enabled/disabled state
|
||||
- $ref: "#/components/parameters/page"
|
||||
- $ref: "#/components/parameters/per_page"
|
||||
responses:
|
||||
"200":
|
||||
description: List of health checks
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
type: object
|
||||
properties:
|
||||
data:
|
||||
type: array
|
||||
items:
|
||||
$ref: "#/components/schemas/EndpointHealthCheck"
|
||||
total:
|
||||
type: integer
|
||||
page:
|
||||
type: integer
|
||||
per_page:
|
||||
type: integer
|
||||
"500":
|
||||
$ref: "#/components/responses/InternalError"
|
||||
|
||||
post:
|
||||
tags: [Health Monitoring]
|
||||
summary: Create health check
|
||||
description: Creates a new manual health check for an endpoint.
|
||||
operationId: createHealthCheck
|
||||
requestBody:
|
||||
required: true
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
type: object
|
||||
required: [endpoint, check_interval_seconds]
|
||||
properties:
|
||||
endpoint:
|
||||
type: string
|
||||
description: "host:port to monitor"
|
||||
example: "api.example.com:443"
|
||||
expected_fingerprint:
|
||||
type: string
|
||||
description: Expected certificate SHA-256 fingerprint (optional)
|
||||
check_interval_seconds:
|
||||
type: integer
|
||||
minimum: 30
|
||||
description: Probe frequency in seconds (default 300)
|
||||
timeout_ms:
|
||||
type: integer
|
||||
description: TLS connection timeout in milliseconds
|
||||
responses:
|
||||
"201":
|
||||
description: Health check created
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: "#/components/schemas/EndpointHealthCheck"
|
||||
"400":
|
||||
$ref: "#/components/responses/BadRequest"
|
||||
"500":
|
||||
$ref: "#/components/responses/InternalError"
|
||||
|
||||
/api/v1/health-checks/summary:
|
||||
get:
|
||||
tags: [Health Monitoring]
|
||||
summary: Health check summary
|
||||
description: Returns aggregate status counts for all health checks.
|
||||
operationId: getHealthCheckSummary
|
||||
responses:
|
||||
"200":
|
||||
description: Health check summary
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
type: object
|
||||
properties:
|
||||
healthy:
|
||||
type: integer
|
||||
degraded:
|
||||
type: integer
|
||||
down:
|
||||
type: integer
|
||||
cert_mismatch:
|
||||
type: integer
|
||||
"500":
|
||||
$ref: "#/components/responses/InternalError"
|
||||
|
||||
/api/v1/health-checks/{id}:
|
||||
get:
|
||||
tags: [Health Monitoring]
|
||||
summary: Get health check
|
||||
operationId: getHealthCheck
|
||||
parameters:
|
||||
- $ref: "#/components/parameters/resourceId"
|
||||
responses:
|
||||
"200":
|
||||
description: Health check detail
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: "#/components/schemas/EndpointHealthCheck"
|
||||
"404":
|
||||
$ref: "#/components/responses/NotFound"
|
||||
"500":
|
||||
$ref: "#/components/responses/InternalError"
|
||||
|
||||
put:
|
||||
tags: [Health Monitoring]
|
||||
summary: Update health check
|
||||
description: Update thresholds, interval, or expected fingerprint.
|
||||
operationId: updateHealthCheck
|
||||
parameters:
|
||||
- $ref: "#/components/parameters/resourceId"
|
||||
requestBody:
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
type: object
|
||||
properties:
|
||||
expected_fingerprint:
|
||||
type: string
|
||||
check_interval_seconds:
|
||||
type: integer
|
||||
timeout_ms:
|
||||
type: integer
|
||||
enabled:
|
||||
type: boolean
|
||||
responses:
|
||||
"200":
|
||||
description: Health check updated
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: "#/components/schemas/EndpointHealthCheck"
|
||||
"400":
|
||||
$ref: "#/components/responses/BadRequest"
|
||||
"404":
|
||||
$ref: "#/components/responses/NotFound"
|
||||
"500":
|
||||
$ref: "#/components/responses/InternalError"
|
||||
|
||||
delete:
|
||||
tags: [Health Monitoring]
|
||||
summary: Delete health check
|
||||
operationId: deleteHealthCheck
|
||||
parameters:
|
||||
- $ref: "#/components/parameters/resourceId"
|
||||
responses:
|
||||
"204":
|
||||
description: Health check deleted
|
||||
"404":
|
||||
$ref: "#/components/responses/NotFound"
|
||||
"500":
|
||||
$ref: "#/components/responses/InternalError"
|
||||
|
||||
/api/v1/health-checks/{id}/history:
|
||||
get:
|
||||
tags: [Health Monitoring]
|
||||
summary: Get probe history
|
||||
description: Returns historical probe records with status, response times, and errors.
|
||||
operationId: getHealthCheckHistory
|
||||
parameters:
|
||||
- $ref: "#/components/parameters/resourceId"
|
||||
- name: limit
|
||||
in: query
|
||||
schema:
|
||||
type: integer
|
||||
default: 100
|
||||
minimum: 1
|
||||
maximum: 1000
|
||||
description: Max number of records to return
|
||||
responses:
|
||||
"200":
|
||||
description: Probe history
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
type: object
|
||||
properties:
|
||||
data:
|
||||
type: array
|
||||
items:
|
||||
$ref: "#/components/schemas/HealthHistoryEntry"
|
||||
total:
|
||||
type: integer
|
||||
"404":
|
||||
$ref: "#/components/responses/NotFound"
|
||||
"500":
|
||||
$ref: "#/components/responses/InternalError"
|
||||
|
||||
/api/v1/health-checks/{id}/acknowledge:
|
||||
post:
|
||||
tags: [Health Monitoring]
|
||||
summary: Acknowledge incident
|
||||
description: Mark a health check incident as acknowledged by the operator.
|
||||
operationId: acknowledgeHealthCheckIncident
|
||||
parameters:
|
||||
- $ref: "#/components/parameters/resourceId"
|
||||
requestBody:
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
type: object
|
||||
properties:
|
||||
acknowledged_by:
|
||||
type: string
|
||||
description: Operator name or ID
|
||||
responses:
|
||||
"200":
|
||||
description: Incident acknowledged
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: "#/components/schemas/EndpointHealthCheck"
|
||||
"404":
|
||||
$ref: "#/components/responses/NotFound"
|
||||
"500":
|
||||
$ref: "#/components/responses/InternalError"
|
||||
|
||||
# ─── Digest ────────────────────────────────────────────────────────
|
||||
/api/v1/digest/preview:
|
||||
get:
|
||||
@@ -3342,3 +3594,133 @@ components:
|
||||
timeout_ms:
|
||||
type: integer
|
||||
default: 5000
|
||||
|
||||
EndpointHealthCheck:
|
||||
type: object
|
||||
properties:
|
||||
id:
|
||||
type: string
|
||||
description: Health check ID
|
||||
endpoint:
|
||||
type: string
|
||||
description: "Target endpoint (host:port)"
|
||||
example: "api.example.com:443"
|
||||
certificate_id:
|
||||
type: string
|
||||
nullable: true
|
||||
description: Associated managed certificate ID (if from deployment)
|
||||
network_scan_target_id:
|
||||
type: string
|
||||
nullable: true
|
||||
description: Associated network scan target ID (if auto-created)
|
||||
expected_fingerprint:
|
||||
type: string
|
||||
nullable: true
|
||||
description: Expected certificate SHA-256 fingerprint
|
||||
status:
|
||||
type: string
|
||||
enum: [Healthy, Degraded, Down, CertMismatch]
|
||||
description: Current health status
|
||||
enabled:
|
||||
type: boolean
|
||||
check_interval_seconds:
|
||||
type: integer
|
||||
description: Frequency of TLS probes (seconds)
|
||||
timeout_ms:
|
||||
type: integer
|
||||
description: TLS connection timeout (milliseconds)
|
||||
consecutive_failures:
|
||||
type: integer
|
||||
description: Number of consecutive probe failures
|
||||
last_checked_at:
|
||||
type: string
|
||||
format: date-time
|
||||
nullable: true
|
||||
description: Timestamp of last probe
|
||||
last_success_at:
|
||||
type: string
|
||||
format: date-time
|
||||
nullable: true
|
||||
description: Timestamp of last successful probe
|
||||
last_failure_at:
|
||||
type: string
|
||||
format: date-time
|
||||
nullable: true
|
||||
description: Timestamp of last failed probe
|
||||
last_transition_at:
|
||||
type: string
|
||||
format: date-time
|
||||
nullable: true
|
||||
description: Timestamp of last status transition
|
||||
failure_reason:
|
||||
type: string
|
||||
nullable: true
|
||||
description: Reason for last failure
|
||||
acknowledged:
|
||||
type: boolean
|
||||
description: Whether the current status has been acknowledged
|
||||
acknowledged_by:
|
||||
type: string
|
||||
nullable: true
|
||||
description: Operator name who acknowledged (if applicable)
|
||||
acknowledged_at:
|
||||
type: string
|
||||
format: date-time
|
||||
nullable: true
|
||||
created_at:
|
||||
type: string
|
||||
format: date-time
|
||||
updated_at:
|
||||
type: string
|
||||
format: date-time
|
||||
|
||||
HealthHistoryEntry:
|
||||
type: object
|
||||
properties:
|
||||
id:
|
||||
type: string
|
||||
health_check_id:
|
||||
type: string
|
||||
status:
|
||||
type: string
|
||||
enum: [Healthy, Degraded, Down, CertMismatch]
|
||||
response_time_ms:
|
||||
type: integer
|
||||
nullable: true
|
||||
description: Time to connect and complete TLS handshake (milliseconds)
|
||||
observed_fingerprint:
|
||||
type: string
|
||||
nullable: true
|
||||
description: SHA-256 fingerprint of certificate observed on endpoint
|
||||
tls_version:
|
||||
type: string
|
||||
nullable: true
|
||||
description: TLS version (e.g., TLSv1.3)
|
||||
cipher_suite:
|
||||
type: string
|
||||
nullable: true
|
||||
description: Cipher suite used in TLS handshake
|
||||
cert_subject:
|
||||
type: string
|
||||
nullable: true
|
||||
description: Subject DN of observed certificate
|
||||
cert_issuer:
|
||||
type: string
|
||||
nullable: true
|
||||
description: Issuer DN of observed certificate
|
||||
cert_not_before:
|
||||
type: string
|
||||
format: date-time
|
||||
nullable: true
|
||||
cert_not_after:
|
||||
type: string
|
||||
format: date-time
|
||||
nullable: true
|
||||
failure_reason:
|
||||
type: string
|
||||
nullable: true
|
||||
description: Error message if probe failed
|
||||
checked_at:
|
||||
type: string
|
||||
format: date-time
|
||||
description: Timestamp of this probe
|
||||
|
||||
Reference in New Issue
Block a user