feat(sense): add reconciliation safety controls [T-012]
Harness governance / validate (push) Has been cancelled
Harness governance / validate (pull_request) Has been cancelled

This commit is contained in:
QiuSW
2026-08-07 23:00:03 +08:00
parent 677ed732f7
commit 12857fdf32
35 changed files with 2817 additions and 124 deletions
+38 -10
View File
@@ -15,8 +15,10 @@ import (
"yovision/sense/internal/auth"
"yovision/sense/internal/config"
"yovision/sense/internal/controlapi"
"yovision/sense/internal/metrics"
"yovision/sense/internal/mtx"
"yovision/sense/internal/onvif"
"yovision/sense/internal/orphan"
"yovision/sense/internal/probe"
"yovision/sense/internal/reconcile"
"yovision/sense/internal/store"
@@ -37,6 +39,14 @@ func run(logger *slog.Logger) error {
if err != nil {
return fmt.Errorf("load configuration: %w", err)
}
instanceID := cfg.InstanceID
if instanceID == "" {
instanceID, err = metrics.GenerateInstanceID()
if err != nil {
return err
}
}
registry := metrics.New(instanceID, version)
ctx, stop := signal.NotifyContext(context.Background(), os.Interrupt, syscall.SIGTERM)
defer stop()
@@ -76,22 +86,36 @@ func run(logger *slog.Logger) error {
})
}
discovery := onvif.NewRouter(cameraAdapter, credentials)
reconciler := reconcile.New(repository, discovery, mediaClient)
reconciler := reconcile.NewWithOptions(repository, discovery, mediaClient, reconcile.Options{
InstanceID: instanceID, LeaseDuration: cfg.ReconcileLeaseDuration,
OperationTimeout: cfg.ReconcileOperationTimeout, Metrics: registry,
})
checker := probe.New(repository, mediaClient)
var orphanScanner *orphan.Manager
if cfg.OrphanScanEnabled {
orphanStore, ok := repository.(store.OrphanRepository)
if !ok {
return errors.New("selected repository does not support orphan scanning")
}
orphanScanner = orphan.New(orphanStore, mediaClient, instanceID, registry)
}
report := func(err error) {
// Domain and MediaMTX errors intentionally omit stream URIs and credentials.
logger.Warn("background convergence error", "error", err)
}
var background sync.WaitGroup
background.Add(2)
go func() {
defer background.Done()
reconciler.Run(ctx, cfg.ReconcileInterval, report)
}()
go func() {
defer background.Done()
checker.Run(ctx, cfg.ProbeInterval, report)
}()
startBackground := func(run func()) {
background.Add(1)
go func() {
defer background.Done()
run()
}()
}
startBackground(func() { reconciler.Run(ctx, cfg.ReconcileInterval, report) })
startBackground(func() { checker.Run(ctx, cfg.ProbeInterval, report) })
if orphanScanner != nil {
startBackground(func() { orphanScanner.Run(ctx, cfg.OrphanScanInterval, report) })
}
mux := http.NewServeMux()
mux.HandleFunc("GET /healthz", func(writer http.ResponseWriter, _ *http.Request) {
@@ -104,6 +128,9 @@ func run(logger *slog.Logger) error {
writer.WriteHeader(http.StatusOK)
_, _ = writer.Write([]byte(`{"status":"ready"}`))
})
if cfg.MetricsEnabled {
mux.Handle("GET /metrics", registry.Handler())
}
if cfg.ControlAPIEnabled {
mux.Handle("/api/v1/", controlHandler)
}
@@ -118,6 +145,7 @@ func run(logger *slog.Logger) error {
serverErrors := make(chan error, 1)
go func() {
logger.Info("Sense listening", "address", cfg.HTTPAddress, "version", version,
"instance_id", instanceID,
"control_api_enabled", cfg.ControlAPIEnabled)
serverErrors <- server.ListenAndServe()
}()
+94
View File
@@ -0,0 +1,94 @@
// sense-orphan is a local, PostgreSQL-backed operational command. Report is
// read-only; apply requires a fresh scan ID, actor and exact confirmation.
package main
import (
"context"
"encoding/json"
"errors"
"flag"
"fmt"
"net/http"
"os"
"os/signal"
"strings"
"syscall"
"yovision/sense/internal/config"
"yovision/sense/internal/metrics"
"yovision/sense/internal/mtx"
"yovision/sense/internal/orphan"
"yovision/sense/internal/store"
)
func main() {
if err := run(); err != nil {
_, _ = fmt.Fprintln(os.Stderr, "sense-orphan failed:", err)
os.Exit(1)
}
}
func run() error {
mode := flag.String("mode", "report", "report or apply")
scanID := flag.String("scan-id", "", "fresh scan ID required by apply")
actor := flag.String("actor", "", "operator identifier required by apply")
confirm := flag.String("confirm", "", "exact confirmation: DELETE <scan-id>")
flag.Parse()
cfg, err := config.Load()
if err != nil {
return err
}
if !strings.EqualFold(strings.TrimSpace(cfg.DatabaseDriver), store.DriverPostgres) {
return errors.New("sense-orphan requires SENSE_DB_DRIVER=postgres")
}
ctx, stop := signal.NotifyContext(context.Background(), os.Interrupt, syscall.SIGTERM)
defer stop()
repository, err := store.OpenPostgres(ctx, cfg.DatabaseDSN)
if err != nil {
return err
}
defer repository.Close()
media, err := mtx.NewClient(cfg.MediaMTXURL, &http.Client{Timeout: cfg.ReconcileOperationTimeout})
if err != nil {
return err
}
instanceID := cfg.InstanceID
if instanceID == "" {
instanceID, err = metrics.GenerateInstanceID()
if err != nil {
return err
}
}
manager := orphan.New(repository, media, instanceID, metrics.New(instanceID, "operator"))
encoder := json.NewEncoder(os.Stdout)
switch *mode {
case "report":
scan, err := manager.Report(ctx)
if err != nil {
return err
}
return encoder.Encode(struct {
ScanID string `json:"scan_id"`
Observed int `json:"observed"`
OwnedStale int `json:"owned_stale"`
Unowned int `json:"unowned"`
SafetyAllowed bool `json:"safety_allowed"`
SafetyReason string `json:"safety_reason"`
ExpiresAt string `json:"expires_at"`
}{
ScanID: scan.ID, Observed: scan.ObservedCount,
OwnedStale: scan.OwnedStaleCount, Unowned: scan.UnownedCount,
SafetyAllowed: scan.SafetyAllowed, SafetyReason: scan.SafetyReason,
ExpiresAt: scan.ExpiresAt.UTC().Format("2006-01-02T15:04:05Z07:00"),
})
case "apply":
result, err := manager.Apply(ctx, *scanID, *actor, *confirm)
if encodeErr := encoder.Encode(result); encodeErr != nil {
return encodeErr
}
return err
default:
return errors.New("mode must be report or apply")
}
}