Files
finance-duck/internal/classification/rate_limit_test.go
T

397 lines
14 KiB
Go

package classification
import (
"bytes"
"context"
"encoding/json"
"errors"
"io"
"net/http"
"strings"
"sync"
"sync/atomic"
"testing"
"time"
"finance-duck/internal/ratelimit"
)
func TestProductionRatePolicyAcrossModelSnapshots(t *testing.T) {
t.Run("successful classifications stay paced", func(t *testing.T) {
f, d := fixture()
arrivals := make(chan time.Time, 2)
c := mockClient(t, func(w http.ResponseWriter, r *http.Request) {
arrivals <- time.Now()
reply(w, validAnswer)
})
// Remove only the fixture's fast policy, exercising real lazy production
// initialization and the same shared controller used by previews.
c.rate.Store(nil)
snapshot := c.WithModel("test/preview-model")
ctx, cancel := context.WithTimeout(context.Background(), 6*time.Second)
defer cancel()
for _, client := range []*Client{c, snapshot} {
p, err := client.Classify(ctx, f, d, true)
if err != nil || p.Enrichment.Classification.Source != "openrouter" {
t.Fatalf("production-paced classification failed: %+v, %v", p, err)
}
}
first, second := <-arrivals, <-arrivals
if gap := second.Sub(first); gap < 3*time.Second-25*time.Millisecond {
t.Fatalf("model snapshots burst after success: %v", gap)
}
})
t.Run("first failure retains conservative retry deadline", func(t *testing.T) {
f, d := fixture()
var calls atomic.Int32
c := mockClient(t, func(w http.ResponseWriter, r *http.Request) {
calls.Add(1)
w.WriteHeader(http.StatusTooManyRequests)
})
c.rate.Store(nil)
snapshot := c.WithModel("test/preview-model")
ctx, cancel := context.WithTimeout(context.Background(), 100*time.Millisecond)
defer cancel()
_, err := c.Classify(ctx, f, d, true)
var limit *ratelimit.RateLimitError
if !errors.Is(err, context.DeadlineExceeded) || !errors.As(err, &limit) {
t.Fatalf("production retry wait lost cancellation or quota identity: %v", err)
}
if delay := time.Until(limit.RetryAt()); delay < 14*time.Second {
t.Fatalf("production retry used a short per-record fallback: %v", delay)
}
probeCtx, probeCancel := context.WithTimeout(context.Background(), time.Second)
defer probeCancel()
_, err = snapshot.Classify(probeCtx, f, d, true)
if !errors.As(err, &limit) || errors.Is(err, context.DeadlineExceeded) || calls.Load() != 1 {
t.Fatalf("preview discarded production cooldown: %v, calls=%d", err, calls.Load())
}
})
}
func TestRateLimitRetryPreservesPrivateRequest(t *testing.T) {
f, d := fixture()
f.Counterparty = "Alice Privateperson"
f.CounterpartyIBAN = "DE89370400440532013000"
f.RawDescription = "Coffee House Alice Privateperson DE89370400440532013000 private_external -918.27 reference secretpayment"
var requests [][]byte
var arrivals []time.Time
var mu sync.Mutex
c := mockClient(t, func(w http.ResponseWriter, r *http.Request) {
mu.Lock()
defer mu.Unlock()
arrivals = append(arrivals, time.Now())
body, err := io.ReadAll(r.Body)
if err != nil {
t.Error(err)
}
requests = append(requests, body)
if r.Method != http.MethodPost || r.URL.Path != "/chat/completions" || r.Header.Get("Authorization") != "Bearer test-secret" || r.Header.Get("Content-Type") != "application/json" {
t.Error("retry changed authenticated JSON endpoint")
}
if len(requests) == 1 {
w.Header().Set("Retry-After", "2")
w.WriteHeader(http.StatusTooManyRequests)
_, _ = io.WriteString(w, "sensitive-provider-response")
return
}
reply(w, validAnswer)
})
ctx, cancel := context.WithTimeout(context.Background(), 8*time.Second)
defer cancel()
p, err := c.Classify(ctx, f, d, true)
if err != nil || p.Enrichment.Classification.Source != "openrouter" || p.Enrichment.Classification.Error != "" {
t.Fatalf("retry did not recover: %+v, %v", p, err)
}
mu.Lock()
defer mu.Unlock()
if len(requests) != 2 || !bytes.Equal(requests[0], requests[1]) {
t.Fatalf("retry did not reuse identical serialized request: %d attempts", len(requests))
}
if gap := arrivals[1].Sub(arrivals[0]); gap < 1950*time.Millisecond {
t.Fatalf("retried before provider's two-second delay: %v", gap)
}
var request struct {
Provider struct {
DataCollection string `json:"data_collection"`
ZDR bool `json:"zdr"`
Require bool `json:"require_parameters"`
} `json:"provider"`
Messages []struct{ Role, Content string } `json:"messages"`
ResponseFormat struct {
Type string `json:"type"`
Schema struct {
Strict bool `json:"strict"`
} `json:"json_schema"`
} `json:"response_format"`
Plugins json.RawMessage `json:"plugins"`
}
if err := json.Unmarshal(requests[0], &request); err != nil {
t.Fatal(err)
}
if request.Provider.DataCollection != "deny" || !request.Provider.ZDR || !request.Provider.Require || request.ResponseFormat.Type != "json_schema" || !request.ResponseFormat.Schema.Strict || len(request.Plugins) != 0 {
t.Fatal("retry relaxed private structured routing")
}
if len(request.Messages) != 2 {
t.Fatalf("unexpected message count: %d", len(request.Messages))
}
for _, secret := range []string{"alice", "privateperson", "3704", "private_external", "918", "secretpayment", "tx_private", "account_private"} {
if strings.Contains(strings.ToLower(request.Messages[1].Content), secret) {
t.Errorf("retried prompt leaked %q", secret)
}
}
}
func TestRateLimitBackoffExhaustionRetainsSharedCooldown(t *testing.T) {
f, d := fixture()
var arrivals []time.Time
var mu sync.Mutex
c := mockClient(t, func(w http.ResponseWriter, r *http.Request) {
mu.Lock()
defer mu.Unlock()
arrivals = append(arrivals, time.Now())
// An invalid hint must not bypass exponential fallback delays.
w.Header().Set("Retry-After", "not-a-delay")
w.WriteHeader(http.StatusTooManyRequests)
_, _ = io.WriteString(w, "sensitive-provider-response")
})
snapshot := c.WithModel("test/preview-model")
ctx, cancel := context.WithTimeout(context.Background(), 15*time.Second)
defer cancel()
p, err := c.Classify(ctx, f, d, true)
assertSafeRateLimit(t, err, p.Enrichment.Classification.Error)
mu.Lock()
observed := append([]time.Time(nil), arrivals...)
mu.Unlock()
if len(observed) != 4 {
t.Fatalf("expected four bounded attempts, got %d", len(observed))
}
for i, delay := range []time.Duration{time.Second, 2 * time.Second, 4 * time.Second} {
if gap := observed[i+1].Sub(observed[i]); gap < delay-50*time.Millisecond {
t.Errorf("backoff %d retried too early: %v, need %v", i+1, gap, delay)
}
}
for _, client := range []*Client{snapshot, c} {
probeCtx, probeCancel := context.WithTimeout(context.Background(), time.Second)
p, err := client.Classify(probeCtx, f, d, true)
probeCancel()
assertSafeRateLimit(t, err, p.Enrichment.Classification.Error)
mu.Lock()
calls := len(arrivals)
mu.Unlock()
if errors.Is(err, context.DeadlineExceeded) || calls != 4 {
t.Fatalf("retained cooldown waited or contacted provider: %v, attempts=%d", err, calls)
}
}
}
func TestRateLimitHTTPDateDoesNotRetryEarly(t *testing.T) {
f, d := fixture()
var retryAt time.Time
var arrivals []time.Time
var mu sync.Mutex
c := mockClient(t, func(w http.ResponseWriter, r *http.Request) {
mu.Lock()
defer mu.Unlock()
arrivals = append(arrivals, time.Now())
if len(arrivals) == 1 {
retryAt = time.Now().UTC().Add(3 * time.Second).Truncate(time.Second)
w.Header().Set("Retry-After", retryAt.Format(http.TimeFormat))
w.WriteHeader(http.StatusTooManyRequests)
return
}
reply(w, validAnswer)
})
ctx, cancel := context.WithTimeout(context.Background(), 8*time.Second)
defer cancel()
if p, err := c.Classify(ctx, f, d, true); err != nil || p.Enrichment.Classification.Source != "openrouter" {
t.Fatalf("HTTP-date retry failed: %+v, %v", p, err)
}
mu.Lock()
defer mu.Unlock()
if len(arrivals) != 2 {
t.Fatalf("expected one HTTP-date retry, got %d attempts", len(arrivals))
}
if arrivals[1].Before(retryAt.Add(-25 * time.Millisecond)) {
t.Fatalf("retried at %v before HTTP-date %v", arrivals[1], retryAt)
}
}
func TestRateLimitLongHintsFailFastAndLocalRulesBypassCooldown(t *testing.T) {
for _, hint := range []string{"600", time.Now().UTC().Add(10 * time.Minute).Format(http.TimeFormat), "9223372036854775807"} {
t.Run(hint, func(t *testing.T) {
f, d := fixture()
var calls atomic.Int32
c := mockClient(t, func(w http.ResponseWriter, r *http.Request) {
calls.Add(1)
w.Header().Set("Retry-After", hint)
w.WriteHeader(http.StatusTooManyRequests)
_, _ = io.WriteString(w, "sensitive-provider-response")
})
snapshot := c.WithModel("test/preview-model")
for _, client := range []*Client{c, snapshot} {
ctx, cancel := context.WithTimeout(context.Background(), time.Second)
p, err := client.Classify(ctx, f, d, true)
cancel()
assertSafeRateLimit(t, err, p.Enrichment.Classification.Error)
if errors.Is(err, context.DeadlineExceeded) || calls.Load() != 1 {
t.Fatalf("long hint waited or permitted an early request: %v, attempts=%d", err, calls.Load())
}
}
d.Merchants[0].UseDefaults = true
ctx, cancel := context.WithTimeout(context.Background(), time.Second)
defer cancel()
p, err := snapshot.Classify(ctx, f, d, false)
if err != nil || p.Enrichment.Classification.Source != "rule" || p.Enrichment.MerchantID != "mer_coffee" || calls.Load() != 1 {
t.Fatalf("cooldown blocked local rule: %+v, %v, attempts=%d", p, err, calls.Load())
}
})
}
}
func TestRateLimitCancellationClosesBodyAndRetainsCooldown(t *testing.T) {
f, d := fixture()
var calls atomic.Int32
lateRequest := make(chan struct{}, 4)
c := mockClient(t, func(w http.ResponseWriter, r *http.Request) {
if calls.Add(1) > 1 {
lateRequest <- struct{}{}
}
w.Header().Set("Retry-After", "1")
w.WriteHeader(http.StatusTooManyRequests)
_, _ = io.WriteString(w, "sensitive-provider-response")
})
closed := make(chan struct{})
var closeOnce sync.Once
transport := c.HTTPClient.Transport
c.HTTPClient.Transport = rateLimitRoundTripFunc(func(r *http.Request) (*http.Response, error) {
response, err := transport.RoundTrip(r)
if err == nil && response.StatusCode == http.StatusTooManyRequests {
response.Body = &rateLimitNotifyingBody{ReadCloser: response.Body, closed: closed, once: &closeOnce}
}
return response, err
})
ctx, cancel := context.WithCancel(context.Background())
defer cancel()
done := make(chan error, 1)
go func() {
_, err := c.Classify(ctx, f, d, true)
done <- err
}()
select {
case <-closed:
case <-time.After(2 * time.Second):
t.Fatal("429 response body was not closed before retry waiting")
}
cancel()
select {
case err := <-done:
if !errors.Is(err, context.Canceled) || strings.Contains(err.Error(), "sensitive") {
t.Fatalf("waiting cancellation did not preserve safe context identity: %v", err)
}
case <-time.After(time.Second):
t.Fatal("retry wait ignored cancellation")
}
probeCtx, probeCancel := context.WithTimeout(context.Background(), time.Second)
defer probeCancel()
p, err := c.WithModel("test/preview-model").Classify(probeCtx, f, d, true)
assertSafeRateLimit(t, err, p.Enrichment.Classification.Error)
if errors.Is(err, context.DeadlineExceeded) || calls.Load() != 1 {
t.Fatalf("cancelled retry lost cooldown or made a late request: %v, attempts=%d", err, calls.Load())
}
select {
case <-lateRequest:
t.Fatal("cancelled retry made a request after its timer expired")
case <-time.After(1200 * time.Millisecond):
}
}
func TestRateLimitQueuedSnapshotCancellationMakesNoLateRequest(t *testing.T) {
f, d := fixture()
entered := make(chan struct{})
release := make(chan struct{})
var releaseOnce sync.Once
unblock := func() { releaseOnce.Do(func() { close(release) }) }
var calls atomic.Int32
models := make(chan string, 4)
c := mockClient(t, func(w http.ResponseWriter, r *http.Request) {
var request struct{ Model string }
if err := json.NewDecoder(r.Body).Decode(&request); err != nil {
t.Error(err)
}
models <- request.Model
if calls.Add(1) == 1 {
close(entered)
select {
case <-release:
case <-r.Context().Done():
return
}
}
reply(w, validAnswer)
})
defer unblock()
snapshot := c.WithModel("test/preview-model")
activeCtx, activeCancel := context.WithTimeout(context.Background(), 5*time.Second)
defer activeCancel()
activeDone := make(chan error, 1)
go func() {
_, err := c.Classify(activeCtx, f, d, true)
activeDone <- err
}()
select {
case <-entered:
case <-time.After(time.Second):
t.Fatal("first AI request did not start")
}
queueCtx, queueCancel := context.WithTimeout(context.Background(), 100*time.Millisecond)
_, err := snapshot.Classify(queueCtx, f, d, true)
queueCancel()
if !errors.Is(err, context.DeadlineExceeded) || calls.Load() != 1 {
t.Fatalf("queued snapshot contacted provider or ignored cancellation: %v, attempts=%d", err, calls.Load())
}
unblock()
select {
case err := <-activeDone:
if err != nil {
t.Fatalf("queued cancellation disrupted active request: %v", err)
}
case <-time.After(time.Second):
t.Fatal("active request did not complete")
}
ctx, cancel := context.WithTimeout(context.Background(), 2*time.Second)
defer cancel()
p, err := snapshot.Classify(ctx, f, d, true)
if err != nil || p.Enrichment.Classification.Model != "test/preview-model" || calls.Load() != 2 {
t.Fatalf("cancelled waiter leaked a request or blocked successor: %+v, %v, attempts=%d", p, err, calls.Load())
}
if original, preview := <-models, <-models; original != "test/strict-model" || preview != "test/preview-model" {
t.Fatalf("serialized requests used wrong models: %q, %q", original, preview)
}
}
func assertSafeRateLimit(t *testing.T, err error, provenance string) {
t.Helper()
if err == nil || !strings.Contains(err.Error(), "429") || provenance == "" || strings.Contains(err.Error(), "sensitive") || strings.Contains(provenance, "sensitive") {
t.Fatalf("unsafe or missing rate-limit failure: %v, provenance=%q", err, provenance)
}
}
type rateLimitRoundTripFunc func(*http.Request) (*http.Response, error)
func (f rateLimitRoundTripFunc) RoundTrip(r *http.Request) (*http.Response, error) {
return f(r)
}
type rateLimitNotifyingBody struct {
io.ReadCloser
closed chan struct{}
once *sync.Once
}
func (b *rateLimitNotifyingBody) Close() error {
err := b.ReadCloser.Close()
b.once.Do(func() { close(b.closed) })
return err
}