feat(cag): memory standing-context adapter, warmup semaphore, cache-aware routing

Issue #44: code-register memory adapter with standing-context resource; fix
dispatcher method-level Auth.Capability override (was always using verb-derived
capability, ignoring per-method Auth field).

Issue #45: per-backend bounded in-memory queue (VLLM_MAX_QUEUE_DEPTH=20) +
concurrency semaphore (VLLM_MAX_NUM_SEQS=4); warmup requests (X-Poimen-Warmup:
true) sleep WARMUP_DELAY_MS before queue entry; /metrics endpoint wired.

Issue #46: rendezvous-hash backend selection on X-Poimen-Cache-Key; round-robin
fallback; MarkFailed excludes unhealthy backends 30s; ModifyResponse captures
vllm-num-cached-tokens + emits structured log + increments counter.

Closes #44 Closes #45 Closes #46

internal/config/config.go

@@ -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"