mirror of
https://github.com/lukaszraczylo/traefik-llmgateway.git
synced 2026-10-12 04:54:45 +00:00
Add resp.go: a minimal stdlib-only RESP2 client (respClient) for a single Redis-compatible server. It lazily dials one mutex-guarded connection, applies 2s dial/read/write deadlines, sends AUTH (if a password is set) then SELECT on every new connection, and reconnects once on any I/O error before giving up. do and pipeline encode commands as "*N\r\n$len\r\n..." and decode +/-/:/$/* replies. Add redis_store.go: redisStore implements counterStore over respClient. incrBy pipelines INCRBY and EXPIRE in one round trip and returns INCRBY's value; get treats a missing key (RESP null bulk) as 0. Wire the limiter's fail-open/fail-closed policy in limits.go, which Task 5 stored but never read: a configured store's error now routes through storeIncrBy/storeGet. failOpen=true falls back to the in-process memoryStore transparently; failOpen=false makes checkAndCount return a storeDown violation and makes account drop the sample. Both paths log through an injectable, 30s-rate-limited logf. Wire newGateway (llmgateway.go) to build a redisStore-backed limiter when Config.Redis is set (password through resolveSecret, failOpen defaulting to true unless RedisConfig.FailOpen says otherwise) and a memory-only limiter otherwise, and to route pricing.go's unknown-model warnings through the gateway's own logf. Validate LimitsConfig at construction: a new LimitsConfig.validate rejects a negative int64 count limit or a negative/NaN/Inf cost limit, called from newAuthStore for every group and every user (inline and file-sourced) so a malformed limit is a constructor error instead of silently behaving as unlimited. Add RequestsPerDay, TokensPerMonth, and CostPerMonthUSD enforcement tests alongside the existing per-minute/day/cost-per-day cases, plus an erroringStore-backed test pair proving the fail-open (fallback counted) and fail-closed (storeDown violation) branches directly. Folded the validation work into this single commit rather than a second one: it interleaves with the fail-open changes across limits.go, limits_test.go, and llmgateway_test.go closely enough that splitting by hunk would be artificial.
139 lines
4.8 KiB
Go
139 lines
4.8 KiB
Go
package traefikllmgateway
|
|
|
|
import (
|
|
"testing"
|
|
"time"
|
|
)
|
|
|
|
// TestRedisStore_IncrBy_PipelinesIncrbyAndExpire is the brief's Step-1
|
|
// pipeline case: incrBy sends INCRBY and EXPIRE as one pipeline and
|
|
// returns INCRBY's reply value.
|
|
func TestRedisStore_IncrBy_PipelinesIncrbyAndExpire(t *testing.T) {
|
|
ln := newFakeListener(t)
|
|
runFakeRESPServer(t, ln, []respStep{
|
|
{wantArgs: []string{"SELECT", "0"}, reply: []byte("+OK\r\n")},
|
|
{wantArgs: []string{"INCRBY", "llmgw:user:a:req:day:20260820", "1"}, reply: []byte(":5\r\n")},
|
|
{wantArgs: []string{"EXPIRE", "llmgw:user:a:req:day:20260820", "60"}, reply: []byte(":1\r\n")},
|
|
})
|
|
|
|
store := newRedisStore(newRESPClient(ln.Addr().String(), "", 0))
|
|
v, err := store.incrBy("llmgw:user:a:req:day:20260820", 1, 60*time.Second)
|
|
if err != nil {
|
|
t.Fatalf("incrBy: %v", err)
|
|
}
|
|
if v != 5 {
|
|
t.Errorf("incrBy = %d, want 5", v)
|
|
}
|
|
}
|
|
|
|
// TestRedisStore_IncrBy_RoundsSubSecondTTLUp asserts a ttl under one
|
|
// second is never sent to EXPIRE as 0 (which would delete the key
|
|
// immediately) — it is rounded up to a 1s floor.
|
|
func TestRedisStore_IncrBy_RoundsSubSecondTTLUp(t *testing.T) {
|
|
ln := newFakeListener(t)
|
|
runFakeRESPServer(t, ln, []respStep{
|
|
{wantArgs: []string{"SELECT", "0"}, reply: []byte("+OK\r\n")},
|
|
{wantArgs: []string{"INCRBY", "k", "1"}, reply: []byte(":1\r\n")},
|
|
{wantArgs: []string{"EXPIRE", "k", "1"}, reply: []byte(":1\r\n")},
|
|
})
|
|
|
|
store := newRedisStore(newRESPClient(ln.Addr().String(), "", 0))
|
|
if _, err := store.incrBy("k", 1, 10*time.Millisecond); err != nil {
|
|
t.Fatalf("incrBy: %v", err)
|
|
}
|
|
}
|
|
|
|
// TestRedisStore_Get_MissingKeyReturnsZero is the brief's Step-1 GET case:
|
|
// a null bulk reply ("$-1") decodes to 0 with no error.
|
|
func TestRedisStore_Get_MissingKeyReturnsZero(t *testing.T) {
|
|
ln := newFakeListener(t)
|
|
runFakeRESPServer(t, ln, []respStep{
|
|
{wantArgs: []string{"SELECT", "0"}, reply: []byte("+OK\r\n")},
|
|
{wantArgs: []string{"GET", "llmgw:user:a:req:day:20260820"}, reply: []byte("$-1\r\n")},
|
|
})
|
|
|
|
store := newRedisStore(newRESPClient(ln.Addr().String(), "", 0))
|
|
v, err := store.get("llmgw:user:a:req:day:20260820")
|
|
if err != nil {
|
|
t.Fatalf("get: %v", err)
|
|
}
|
|
if v != 0 {
|
|
t.Errorf("get = %d, want 0", v)
|
|
}
|
|
}
|
|
|
|
// TestRedisStore_Get_ParsesIntegerValue asserts a present key's bulk-string
|
|
// value is parsed as a base-10 integer.
|
|
func TestRedisStore_Get_ParsesIntegerValue(t *testing.T) {
|
|
ln := newFakeListener(t)
|
|
runFakeRESPServer(t, ln, []respStep{
|
|
{wantArgs: []string{"SELECT", "0"}, reply: []byte("+OK\r\n")},
|
|
{wantArgs: []string{"GET", "k"}, reply: []byte("$3\r\n123\r\n")},
|
|
})
|
|
|
|
store := newRedisStore(newRESPClient(ln.Addr().String(), "", 0))
|
|
v, err := store.get("k")
|
|
if err != nil {
|
|
t.Fatalf("get: %v", err)
|
|
}
|
|
if v != 123 {
|
|
t.Errorf("get = %d, want 123", v)
|
|
}
|
|
}
|
|
|
|
// TestLimiter_FailOpenFalse_DeadRedisAddress_ReturnsStoreDownViolation is
|
|
// the brief's Step-1 case: a limiter backed by a redisStore pointed at an
|
|
// address nothing listens on, with failOpen=false, must refuse the
|
|
// request with a storeDown violation rather than silently falling back to
|
|
// an in-process counter or panicking.
|
|
func TestLimiter_FailOpenFalse_DeadRedisAddress_ReturnsStoreDownViolation(t *testing.T) {
|
|
ln := newFakeListener(t)
|
|
deadAddr := ln.Addr().String()
|
|
if err := ln.Close(); err != nil {
|
|
t.Fatalf("Close: %v", err)
|
|
} // nothing listens at deadAddr from here on
|
|
|
|
store := newRedisStore(newRESPClient(deadAddr, "", 0))
|
|
l := newLimiter(store, false)
|
|
scopes := []limitScope{{kind: "user", id: "u", limits: &LimitsConfig{RequestsPerMinute: 100}}}
|
|
|
|
v := l.checkAndCount(scopes)
|
|
if v == nil {
|
|
t.Fatal("want a violation when the store is unreachable and failOpen is false")
|
|
}
|
|
if !v.storeDown {
|
|
t.Errorf("v.storeDown = false, want true")
|
|
}
|
|
if v.message != "limit store unavailable" {
|
|
t.Errorf("v.message = %q, want %q", v.message, "limit store unavailable")
|
|
}
|
|
}
|
|
|
|
// TestLimiter_FailOpenTrue_DeadRedisAddress_FallsBackAndAllows mirrors the
|
|
// fail-closed case above with failOpen=true: the same dead address must
|
|
// not block the request — the limiter transparently counts against its
|
|
// in-process fallback instead.
|
|
func TestLimiter_FailOpenTrue_DeadRedisAddress_FallsBackAndAllows(t *testing.T) {
|
|
ln := newFakeListener(t)
|
|
deadAddr := ln.Addr().String()
|
|
if err := ln.Close(); err != nil {
|
|
t.Fatalf("Close: %v", err)
|
|
}
|
|
|
|
store := newRedisStore(newRESPClient(deadAddr, "", 0))
|
|
l := newLimiter(store, true)
|
|
scopes := []limitScope{{kind: "user", id: "u", limits: &LimitsConfig{RequestsPerMinute: 100}}}
|
|
|
|
if v := l.checkAndCount(scopes); v != nil {
|
|
t.Fatalf("want no violation with failOpen=true and a dead store, got %+v", v)
|
|
}
|
|
|
|
got, err := l.fallback.get(windowKey("user", "u", metricReq, windowDay, l.now()))
|
|
if err != nil {
|
|
t.Fatalf("fallback.get: %v", err)
|
|
}
|
|
if got != 1 {
|
|
t.Errorf("fallback req:day counter = %d, want 1 (the request must have been counted in the fallback)", got)
|
|
}
|
|
}
|