Files
webhooker/internal/delivery/export_test.go
T
clawbot 3c7b7ebf59
check / check (push) Waiting to run
Use one recovery routine at start and on every sweep tick (closes #542)
Start-up recovery and the 60-second sweep were two parallel sets of
functions doing the same job. recoverDeliveries now does it, run once at
start and then on every tick from one goroutine. A retrying delivery is
scheduled after what is left of its backoff, now if nothing is left, so
backoffElapsed is gone. The run at start still takes every pending
delivery and opens a webhook database whose file is missing; a tick
still takes only pending deliveries untouched for 15 minutes, at most
500, and skips a missing file. A retrying delivery is taken before its
event is read. The README describes one routine.

Model: opus-5-5
2026-10-15 19:05:14 +00:00

484 lines
13 KiB
Go

package delivery
import (
"context"
"log/slog"
"net"
"net/http"
"net/netip"
"net/url"
"time"
"github.com/prometheus/client_golang/prometheus"
"go.uber.org/fx"
"gorm.io/gorm"
"sneak.berlin/go/webhooker/internal/archive"
"sneak.berlin/go/webhooker/internal/database"
"sneak.berlin/go/webhooker/internal/metrics"
)
// Exported constants for test access.
const (
ExportDeliveryChannelSize = deliveryChannelSize
ExportRetryChannelSize = retryChannelSize
ExportDefaultFailureThreshold = defaultFailureThreshold
ExportDefaultCooldown = defaultCooldown
// ExportMaxBodyLog is the cap the engine applies to a
// recorded response body. The event log's handling of a cut
// response is written against this number, so a test has to
// be able to name it.
ExportMaxBodyLog = maxBodyLog
// ExportPendingSweepMinAge is how long a delivery must sit at
// pending before the sweep treats it as stranded. A test has to
// name it to age a row past the bound.
ExportPendingSweepMinAge = pendingSweepMinAge
)
// NewTestGuard builds an SSRF Guard from an explicit egress
// allowlist, without going through config. Passing no prefixes
// yields the default guard, which blocks every private/reserved
// range.
func NewTestGuard(allowed ...netip.Prefix) *Guard {
return &Guard{allowed: allowed}
}
// ExportCheckIP exposes the guard's single decision point, so a
// test can assert the policy both the validator and the dialer
// inherit without needing a live destination.
func (g *Guard) ExportCheckIP(ip net.IP) error {
return g.checkIP(ip)
}
// ExportAlwaysBlockedNetworks exposes alwaysBlockedNetworks.
func ExportAlwaysBlockedNetworks() []*net.IPNet {
return alwaysBlockedNetworks
}
// ExportBlockedNetworks exposes blockedNetworks.
func ExportBlockedNetworks() []*net.IPNet {
return blockedNetworks
}
// ExportBlockedPublicNetworks exposes blockedPublicNetworks.
func ExportBlockedPublicNetworks() []*net.IPNet {
return blockedPublicNetworks
}
// ExportIsForwardableHeader exposes isForwardableHeader.
func ExportIsForwardableHeader(name string) bool {
return isForwardableHeader(name)
}
// ExportApplyRequestHeaders exposes applyRequestHeaders, so a test
// can inspect the header set an outbound delivery actually carries
// and the origin-scoped names it reports for the redirect policy.
func ExportApplyRequestHeaders(
req *http.Request,
event *database.Event,
cfg *HTTPTargetConfig,
userAgent string,
) []string {
return applyRequestHeaders(req, event, cfg, userAgent)
}
// ExportTruncate exposes truncate for testing.
func ExportTruncate(s string, maxLen int) string {
return truncate(s, maxLen)
}
// ExportDeliverHTTP delivers via the http target for testing.
func (e *Engine) ExportDeliverHTTP(
ctx context.Context,
webhookDB *gorm.DB,
d *database.Delivery,
task *Task,
) {
e.httpTarget.Deliver(ctx, webhookDB, d, task, e)
}
// ExportDeliverHTTPWithScheduler delivers via the http target, handing
// any retry to sched instead of the engine, so a test can see the
// delay each retry is given.
func (e *Engine) ExportDeliverHTTPWithScheduler(
ctx context.Context,
webhookDB *gorm.DB,
d *database.Delivery,
task *Task,
sched Scheduler,
) {
e.httpTarget.Deliver(ctx, webhookDB, d, task, sched)
}
// ExportDeliverDatabase delivers via the database target.
func (e *Engine) ExportDeliverDatabase(
webhookDB *gorm.DB, d *database.Delivery,
) {
e.targets[database.TargetTypeDatabase].Deliver(
context.Background(), webhookDB, d, &Task{}, e,
)
}
// ExportDeliverLog delivers via the log target for testing.
func (e *Engine) ExportDeliverLog(
webhookDB *gorm.DB, d *database.Delivery,
) {
e.targets[database.TargetTypeLog].Deliver(
context.Background(), webhookDB, d, &Task{}, e,
)
}
// ExportDeliverSlack delivers via the slack target for
// testing.
func (e *Engine) ExportDeliverSlack(
ctx context.Context,
webhookDB *gorm.DB,
d *database.Delivery,
) {
task := &Task{
DeliveryID: d.ID,
TargetID: d.TargetID,
MaxAttempts: d.Target.MaxAttempts,
AttemptNum: 1,
}
e.targets[database.TargetTypeSlack].Deliver(
ctx, webhookDB, d, task, e,
)
}
// ExportUpdateDeliveryStatus exposes updateDeliveryStatus. It passes no
// target type, so no metric moves.
func (e *Engine) ExportUpdateDeliveryStatus(
webhookDB *gorm.DB,
d *database.Delivery,
status database.DeliveryStatus,
) error {
return e.updateDeliveryStatus(webhookDB, d, "", status)
}
// ExportProcessNewTask exposes processNewTask.
func (e *Engine) ExportProcessNewTask(
ctx context.Context, task *Task,
) {
e.processNewTask(ctx, task)
}
// ExportProcessRetryTask exposes processRetryTask.
func (e *Engine) ExportProcessRetryTask(
ctx context.Context, task *Task,
) {
e.processRetryTask(ctx, task)
}
// ExportEventForTask exposes the event reconstruction the delivery
// paths run: buildEventFromTask followed by hydrateEvent.
func (e *Engine) ExportEventForTask(
webhookDB *gorm.DB, task *Task,
) (database.Event, error) {
return e.hydrateEvent(
webhookDB, buildEventFromTask(task), task,
)
}
// ExportProcessDelivery exposes processDelivery.
func (e *Engine) ExportProcessDelivery(
ctx context.Context,
webhookDB *gorm.DB,
d *database.Delivery,
task *Task,
) {
e.processDelivery(ctx, webhookDB, d, task)
}
// ExportGetCircuitBreaker exposes the http target's
// getCircuitBreaker.
func (e *Engine) ExportGetCircuitBreaker(
targetID string,
) *CircuitBreaker {
return e.httpTarget.getCircuitBreaker(targetID)
}
// ExportSetCircuitBreaker makes cb the http target's circuit breaker
// for targetID, so a test can use one with a short cooldown.
func (e *Engine) ExportSetCircuitBreaker(
targetID string, cb *CircuitBreaker,
) {
e.httpTarget.circuitBreakers.Store(targetID, cb)
}
// ExportSetSlackCircuitBreaker is ExportSetCircuitBreaker for the
// slack target.
func (e *Engine) ExportSetSlackCircuitBreaker(
targetID string, cb *CircuitBreaker,
) {
e.slackTarget.circuitBreakers.Store(targetID, cb)
}
// ExportParseHTTPConfig exposes parseHTTPConfig.
func (e *Engine) ExportParseHTTPConfig(
configJSON string,
) (*HTTPTargetConfig, error) {
return parseHTTPConfig(configJSON)
}
// ExportParseSlackConfig exposes parseSlackConfig.
func (e *Engine) ExportParseSlackConfig(
configJSON string,
) (*SlackTargetConfig, error) {
return parseSlackConfig(configJSON)
}
// ExportDoHTTPRequest exposes the http target's
// doHTTPRequest.
func (e *Engine) ExportDoHTTPRequest(
ctx context.Context,
cfg *HTTPTargetConfig,
event *database.Event,
) (int, string, int64, error) {
return e.httpTarget.doHTTPRequest(ctx, cfg, event)
}
// ExportClientForRequest exposes the http target's
// clientForRequest.
func (e *Engine) ExportClientForRequest(
cfg *HTTPTargetConfig,
originScoped []string,
) *http.Client {
return e.httpTarget.clientForRequest(cfg, originScoped)
}
// ErrExportTooManyRedirects exposes the sentinel the redirect
// policy returns once a chain exceeds the hop cap. It carries the
// Err prefix rather than this file's usual Export one because it
// is a sentinel error.
var ErrExportTooManyRedirects = errTooManyRedirects
// ExportMaxDeliveryRedirects exposes the redirect hop cap.
const ExportMaxDeliveryRedirects = maxDeliveryRedirects
// ExportSameDeliveryOrigin exposes sameDeliveryOrigin.
func ExportSameDeliveryOrigin(origin, dest *url.URL) bool {
return sameDeliveryOrigin(origin, dest)
}
// ExportClient returns the http target's shared HTTP client.
func (e *Engine) ExportClient() *http.Client {
return e.httpTarget.client
}
// ExportScheduleRetry exposes ScheduleRetry.
func (e *Engine) ExportScheduleRetry(
task Task, delay time.Duration,
) {
e.ScheduleRetry(task, delay)
}
// ExportRecoverPendingDeliveries exposes
// recoverPendingDeliveries.
func (e *Engine) ExportRecoverPendingDeliveries(
ctx context.Context,
webhookDB *gorm.DB,
webhookID string,
atStart bool,
) {
e.recoverPendingDeliveries(
ctx, webhookDB, webhookID, atStart,
)
}
// ExportRecoverWebhookDeliveries exposes
// recoverWebhookDeliveries.
func (e *Engine) ExportRecoverWebhookDeliveries(
ctx context.Context, webhookID string, atStart bool,
) {
e.recoverWebhookDeliveries(ctx, webhookID, atStart)
}
// ExportRecoverDeliveries exposes recoverDeliveries, the recovery
// routine.
func (e *Engine) ExportRecoverDeliveries(
ctx context.Context, atStart bool,
) {
e.recoverDeliveries(ctx, atStart)
}
// ExportStart exposes start for testing.
func (e *Engine) ExportStart() {
e.start()
}
// ExportRegisterHooks registers the engine's real fx lifecycle
// hooks on a lifecycle supplied by a test, so a test can drive
// the exact OnStart/OnStop functions the application runs and
// hand OnStart the kind of context fx actually supplies.
func (e *Engine) ExportRegisterHooks(lc fx.Lifecycle) {
e.registerHooks(lc)
}
// ExportStop exposes stop for testing.
func (e *Engine) ExportStop(ctx context.Context) error {
return e.stop(ctx)
}
// ExportWedgeWorker adds a goroutine to the engine's WaitGroup
// that never observes cancellation and returns only when release
// is closed. It stands in for a worker stuck inside a delivery
// target that never returns, which is the only way stop can be
// made to outlast its context.
func (e *Engine) ExportWedgeWorker(release <-chan struct{}) {
e.wg.Go(func() {
<-release
})
}
// ExportInflightHeld reports how many deliveries the engine currently
// owns, so a test can prove ownership is released rather than leaked.
func (e *Engine) ExportInflightHeld() int {
return e.inflight.held()
}
// ExportRetainDelivery takes the first reference on a delivery, as the
// queueing side does. It lets a test put a delivery into the state a
// worker or a full channel would, without running the pool.
func (e *Engine) ExportRetainDelivery(deliveryID string) bool {
return e.inflight.retainIdle(deliveryID)
}
// ExportRecoverRetryingDeliveries exposes recoverRetryingDeliveries.
func (e *Engine) ExportRecoverRetryingDeliveries(
ctx context.Context, webhookDB *gorm.DB, webhookID string,
) {
e.recoverRetryingDeliveries(ctx, webhookDB, webhookID)
}
// ExportFailMissingTarget exposes failMissingTarget, so a test can hand
// it a delivery as a batch read it earlier.
func (e *Engine) ExportFailMissingTarget(
webhookDB *gorm.DB,
webhookID string,
d *database.Delivery,
) {
e.failMissingTarget(webhookDB, webhookID, d)
}
// ExportSendRecoveredDeliveries exposes sendRecoveredDeliveries, so a
// test can hand it a target map that lacks a delivery's target.
func (e *Engine) ExportSendRecoveredDeliveries(
ctx context.Context,
webhookDB *gorm.DB,
deliveries []database.Delivery,
webhookID string,
targetMap map[string]database.Target,
settled map[string]struct{},
) {
e.sendRecoveredDeliveries(
ctx, webhookDB, deliveries, webhookID, targetMap, settled,
)
}
// ExportDeliveryCh returns the delivery channel.
func (e *Engine) ExportDeliveryCh() chan Task {
return e.deliveryCh
}
// ExportRetryCh returns the retry channel.
func (e *Engine) ExportRetryCh() chan Task {
return e.retryCh
}
// NewTestEngine creates an Engine for unit tests without
// database dependencies. Its archive writers have no data
// directory, so a delivery to a database target fails.
func NewTestEngine(
log *slog.Logger,
client *http.Client,
workers int,
) *Engine {
e := &Engine{
log: log,
deliveryCh: make(chan Task, deliveryChannelSize),
retryCh: make(chan Task, retryChannelSize),
workers: workers,
mtr: metrics.New(prometheus.NewRegistry()),
archives: archive.NewWriters(archive.WritersParams{Logger: log}),
}
e.initTargets(client)
return e
}
// NewTestEngineSmallRetry creates an Engine with a tiny
// retry channel buffer for overflow testing.
func NewTestEngineSmallRetry(
log *slog.Logger,
) *Engine {
e := &Engine{
log: log,
retryCh: make(chan Task, 1),
mtr: metrics.New(prometheus.NewRegistry()),
archives: archive.NewWriters(archive.WritersParams{Logger: log}),
}
e.initTargets(nil)
return e
}
// NewTestEngineWithDB creates an Engine with a real
// database and dbManager for integration tests, and archive
// writers of its own over the same two.
func NewTestEngineWithDB(
db *database.Database,
dbMgr *database.WebhookDBManager,
log *slog.Logger,
client *http.Client,
workers int,
) *Engine {
e := &Engine{
database: db,
dbManager: dbMgr,
log: log,
deliveryCh: make(chan Task, deliveryChannelSize),
retryCh: make(chan Task, retryChannelSize),
workers: workers,
mtr: metrics.New(prometheus.NewRegistry()),
archives: archive.NewWriters(archive.WritersParams{
Database: db,
DBManager: dbMgr,
Logger: log,
}),
}
e.initTargets(client)
return e
}
// ExportArchives returns the engine's archive writers.
func (e *Engine) ExportArchives() *archive.Writers {
return e.archives
}
// ExportSetMetrics substitutes the engine's metric set, so a test can
// assert on collectors registered on a registry it holds.
func (e *Engine) ExportSetMetrics(mtr *metrics.Set) {
e.mtr = mtr
}
// ExportSampleQueueDepths runs one queue depth sample synchronously.
func (e *Engine) ExportSampleQueueDepths(ctx context.Context) {
e.sampleQueueDepths(ctx)
}
// NewTestCircuitBreaker creates a CircuitBreaker with
// custom settings for testing.
func NewTestCircuitBreaker(
threshold int, cooldown time.Duration,
) *CircuitBreaker {
return &CircuitBreaker{
state: CircuitClosed,
threshold: threshold,
cooldown: cooldown,
}
}