feat(cag): CAG integration — memory adapter, warmup semaphore, cache-aware routing (#47)
CI / CI (push) Successful in 3m20s
CI / CI (push) Successful in 3m20s
## Summary Three issues in one PR. Implements Cache-Augmented Generation (CAG) support in the api-gw. --- ### #44 — Memory ServiceAdapter: standing-context resource - Code-registers `memory` adapter with `standing-context` resource (`POST /memory/standing-context`) - Fixes dispatcher bug: method-level `Auth.Capability` override now respected (was always using verb-derived capability) - Auth: `memory:read` required via method-level override; `memory:write` for ingest - `MEMORY_UPSTREAM_URL` env configures upstream ### #45 — Continuous batching: warmup deprioritisation + per-backend semaphore - In-memory bounded queue per backend: `VLLM_MAX_QUEUE_DEPTH` slots (default 20) - Concurrency limiter: `VLLM_MAX_NUM_SEQS` slots (default 4) - `X-Poimen-Warmup: true` → sleep `WARMUP_DELAY_MS` (default 500ms) before queue entry, strip header, add `X-Priority: low` - Queue full → 503 immediately, no goroutine pile-up - Metrics: `warmup_requests_delayed_total`, `queue_full_requests_total` at `/metrics` ### #46 — Cache-aware routing: rendezvous hash + prefix cache hit logging - `addresses: [...]` YAML field for multi-backend models (backward-compat with `address`) - `X-Poimen-Cache-Key` header → rendezvous-hash backend selection (same key = same GPU) - No cache key → round-robin - Failed backend excluded 30s; next-highest-score fallback - `vllm-num-cached-tokens` response header captured → `vllm_prefix_cache_hit_tokens_total` counter + structured log --- ## Verification ``` go build ./... ✅ go vet ./... ✅ go test -race ./... ✅ (all packages, 0 races) ``` ## Reviewer verdicts - reviewer-sre: SIGN-OFF - reviewer-quality: SIGN-OFF ## Non-blocking findings (🟡🔵 only) - `getOrCreateTransport` not goroutine-safe by design; pre-population invariant documented - `time.Sleep(warmupDelay)` holds goroutine; context-cancel alternative left as TODO - OTel trace_id not propagated into CAG log events (existing gap) Closes #44 Closes #45 Closes #46 --------- Co-authored-by: Admin Bot <[email protected]> Reviewed-on: #47
This commit was merged in pull request #47.
This commit is contained in:
@@ -33,7 +33,11 @@ type ModelUpstream struct {
|
||||
// Name is the model name clients send (e.g., "reasoning", "ornith:35b").
|
||||
Name string
|
||||
// Address is the upstream server address (host:port).
|
||||
// When Addresses is set, this holds Addresses[0] for backward compatibility.
|
||||
Address string
|
||||
// Addresses holds all backend addresses for multi-backend cache-aware routing.
|
||||
// Populated from the 'addresses' YAML field; backward-compat with single 'address'.
|
||||
Addresses []string
|
||||
// Path is the upstream path for this model (e.g., "/v1/chat/completions").
|
||||
Path string
|
||||
// UpstreamModel is the model name to send to the upstream server.
|
||||
@@ -116,6 +120,18 @@ func (c *Config) ModelNames() []string {
|
||||
return names
|
||||
}
|
||||
|
||||
// AllAddresses returns all configured backend addresses for the model.
|
||||
// Returns Addresses if non-empty; otherwise wraps Address in a slice.
|
||||
func (m *ModelUpstream) AllAddresses() []string {
|
||||
if len(m.Addresses) > 0 {
|
||||
return m.Addresses
|
||||
}
|
||||
if m.Address != "" {
|
||||
return []string{m.Address}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// Load reads configuration from environment variables with defaults.
|
||||
func Load() (*Config, error) {
|
||||
listenAddr := "127.0.0.1:8080"
|
||||
|
||||
@@ -37,9 +37,10 @@ type rawRoute struct {
|
||||
|
||||
// rawModel represents a single model entry in the YAML configuration.
|
||||
type rawModel struct {
|
||||
Name string `yaml:"name"`
|
||||
Address string `yaml:"address"`
|
||||
Path string `yaml:"path"`
|
||||
Name string `yaml:"name"`
|
||||
Address string `yaml:"address"`
|
||||
Addresses []string `yaml:"addresses"`
|
||||
Path string `yaml:"path"`
|
||||
UpstreamModel string `yaml:"upstreamModel"`
|
||||
AuthRequired *bool `yaml:"authRequired"`
|
||||
}
|
||||
@@ -121,11 +122,18 @@ func LoadRoutesAndModelsFromFile(path string) (map[string]*Route, map[string]*Mo
|
||||
if _, exists := models[rawModel.Name]; exists {
|
||||
return nil, nil, nil, AuthConfig{}, fmt.Errorf("duplicate model: \"%s\"", rawModel.Name)
|
||||
}
|
||||
if rawModel.Address == "" {
|
||||
return nil, nil, nil, AuthConfig{}, fmt.Errorf("model \"%s\": field 'address' is required", rawModel.Name)
|
||||
// Support both 'address' (single) and 'addresses' (multi-backend) YAML fields.
|
||||
addresses := rawModel.Addresses
|
||||
if len(addresses) == 0 && rawModel.Address != "" {
|
||||
addresses = []string{rawModel.Address}
|
||||
}
|
||||
if _, _, err := net.SplitHostPort(rawModel.Address); err != nil {
|
||||
return nil, nil, nil, AuthConfig{}, fmt.Errorf("model \"%s\": invalid address \"%s\": %w", rawModel.Name, rawModel.Address, err)
|
||||
if len(addresses) == 0 {
|
||||
return nil, nil, nil, AuthConfig{}, fmt.Errorf("model \"%s\": 'address' or 'addresses' is required", rawModel.Name)
|
||||
}
|
||||
for _, addr := range addresses {
|
||||
if _, _, err := net.SplitHostPort(addr); err != nil {
|
||||
return nil, nil, nil, AuthConfig{}, fmt.Errorf("model \"%s\": invalid address \"%s\": %w", rawModel.Name, addr, err)
|
||||
}
|
||||
}
|
||||
// Default authRequired to global auth.enabled if not specified per-model
|
||||
authRequired := false
|
||||
@@ -134,7 +142,8 @@ func LoadRoutesAndModelsFromFile(path string) (map[string]*Route, map[string]*Mo
|
||||
}
|
||||
models[rawModel.Name] = &ModelUpstream{
|
||||
Name: rawModel.Name,
|
||||
Address: rawModel.Address,
|
||||
Address: addresses[0],
|
||||
Addresses: addresses,
|
||||
Path: rawModel.Path,
|
||||
UpstreamModel: rawModel.UpstreamModel,
|
||||
AuthRequired: authRequired,
|
||||
|
||||
@@ -161,7 +161,7 @@ models:
|
||||
if err == nil {
|
||||
t.Errorf("expected error for missing address, got nil")
|
||||
}
|
||||
if err.Error() != "model \"reasoning\": field 'address' is required" {
|
||||
if err.Error() != "model \"reasoning\": 'address' or 'addresses' is required" {
|
||||
t.Errorf("expected missing address error, got: %v", err)
|
||||
}
|
||||
}
|
||||
@@ -283,3 +283,139 @@ models:
|
||||
t.Errorf("expected different ModelUpstream objects even for same address")
|
||||
}
|
||||
}
|
||||
|
||||
// minimalRouteYAML is a valid routes block required by LoadRoutesAndModelsFromFile.
|
||||
const minimalRouteYAML = `
|
||||
routes:
|
||||
- name: test-route
|
||||
upstream:
|
||||
address: "localhost:8000"
|
||||
pathRewrite: ""
|
||||
connectTimeout: "10s"
|
||||
readTimeout: "30s"
|
||||
writeTimeout: "30s"
|
||||
maxBodySize: 1048576
|
||||
authRequired: false
|
||||
`
|
||||
|
||||
// TestLoadModelsAddressesField verifies address / addresses YAML field handling.
|
||||
func TestLoadModelsAddressesField(t *testing.T) {
|
||||
tests := []struct {
|
||||
name string
|
||||
modelsYAML string
|
||||
wantErr bool
|
||||
errContains string
|
||||
wantAddresses []string
|
||||
wantAddress string
|
||||
}{
|
||||
{
|
||||
name: "single address field",
|
||||
modelsYAML: `
|
||||
models:
|
||||
- name: "mymodel"
|
||||
address: "host:8080"
|
||||
path: "/v1/chat"
|
||||
`,
|
||||
wantErr: false,
|
||||
wantAddresses: []string{"host:8080"},
|
||||
wantAddress: "host:8080",
|
||||
},
|
||||
{
|
||||
name: "multi addresses field",
|
||||
modelsYAML: `
|
||||
models:
|
||||
- name: "mymodel"
|
||||
addresses:
|
||||
- "a:80"
|
||||
- "b:80"
|
||||
path: "/v1/chat"
|
||||
`,
|
||||
wantErr: false,
|
||||
wantAddresses: []string{"a:80", "b:80"},
|
||||
wantAddress: "a:80",
|
||||
},
|
||||
{
|
||||
name: "neither field",
|
||||
modelsYAML: `
|
||||
models:
|
||||
- name: "mymodel"
|
||||
path: "/v1/chat"
|
||||
`,
|
||||
wantErr: true,
|
||||
errContains: "mymodel",
|
||||
},
|
||||
{
|
||||
name: "invalid address format",
|
||||
modelsYAML: `
|
||||
models:
|
||||
- name: "mymodel"
|
||||
address: "notavalidhostport"
|
||||
path: "/v1/chat"
|
||||
`,
|
||||
wantErr: true,
|
||||
errContains: "mymodel",
|
||||
},
|
||||
}
|
||||
|
||||
for _, tc := range tests {
|
||||
t.Run(tc.name, func(t *testing.T) {
|
||||
data := minimalRouteYAML + tc.modelsYAML
|
||||
|
||||
tmpFile, err := os.CreateTemp("", "config-*.yaml")
|
||||
if err != nil {
|
||||
t.Fatalf("CreateTemp: %v", err)
|
||||
}
|
||||
defer os.Remove(tmpFile.Name())
|
||||
tmpFile.WriteString(data)
|
||||
tmpFile.Close()
|
||||
|
||||
_, models, _, _, loadErr := LoadRoutesAndModelsFromFile(tmpFile.Name())
|
||||
|
||||
if tc.wantErr {
|
||||
if loadErr == nil {
|
||||
t.Fatalf("expected error, got nil")
|
||||
}
|
||||
if tc.errContains != "" && !containsStr(loadErr.Error(), tc.errContains) {
|
||||
t.Errorf("error %q does not contain %q", loadErr.Error(), tc.errContains)
|
||||
}
|
||||
return
|
||||
}
|
||||
|
||||
if loadErr != nil {
|
||||
t.Fatalf("unexpected error: %v", loadErr)
|
||||
}
|
||||
|
||||
m, ok := models["mymodel"]
|
||||
if !ok {
|
||||
t.Fatalf("model 'mymodel' not found in result")
|
||||
}
|
||||
|
||||
if m.Address != tc.wantAddress {
|
||||
t.Errorf("Address: want %q, got %q", tc.wantAddress, m.Address)
|
||||
}
|
||||
|
||||
if len(m.Addresses) != len(tc.wantAddresses) {
|
||||
t.Errorf("Addresses len: want %d, got %d (%v)", len(tc.wantAddresses), len(m.Addresses), m.Addresses)
|
||||
} else {
|
||||
for i, a := range tc.wantAddresses {
|
||||
if m.Addresses[i] != a {
|
||||
t.Errorf("Addresses[%d]: want %q, got %q", i, a, m.Addresses[i])
|
||||
}
|
||||
}
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// containsStr is a helper to avoid importing strings just for Contains.
|
||||
func containsStr(s, sub string) bool {
|
||||
return len(s) >= len(sub) && (s == sub || len(sub) == 0 ||
|
||||
func() bool {
|
||||
for i := 0; i <= len(s)-len(sub); i++ {
|
||||
if s[i:i+len(sub)] == sub {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}())
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user