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
This commit is contained in:
Admin Bot
2026-09-27 18:21:41 +08:00
parent ea7bd8336b
commit fc5c0e967d
16 changed files with 861 additions and 17 deletions
+7 -4
View File
@@ -75,7 +75,7 @@ func (d *Dispatcher) Dispatch(w http.ResponseWriter, r *http.Request) {
// JWT auth enforcement for adapters that require it
if adapter.Spec.Auth.Required && d.jwtValidator != nil {
if !d.authenticate(w, r, serviceName, method.Verb) {
if !d.authenticate(w, r, serviceName, method) {
return
}
}
@@ -98,7 +98,7 @@ func (d *Dispatcher) Dispatch(w http.ResponseWriter, r *http.Request) {
// authenticate validates the JWT and checks service-level capability.
// Returns false (and writes error response) if auth fails.
func (d *Dispatcher) authenticate(w http.ResponseWriter, r *http.Request, serviceName, verb string) bool {
func (d *Dispatcher) authenticate(w http.ResponseWriter, r *http.Request, serviceName string, method *Method) bool {
authHeader := r.Header.Get("Authorization")
if authHeader == "" {
d.writeError(w, problem.NewProblem(http.StatusUnauthorized,
@@ -115,8 +115,11 @@ func (d *Dispatcher) authenticate(w http.ResponseWriter, r *http.Request, servic
return false
}
// Check capability: <service>:read for GET/HEAD, <service>:write for mutating verbs
required := capabilityForVerb(serviceName, verb)
// Check capability: method-level Auth.Capability if set; else derive from verb.
required := capabilityForVerb(serviceName, method.Verb)
if method.Auth != nil && method.Auth.Capability != "" {
required = method.Auth.Capability
}
if !d.jwtValidator.CheckPermissions(claims, required, "*") {
d.writeError(w, problem.NewProblem(http.StatusForbidden,
"about:blank#insufficient-permissions", "Insufficient Permissions",