mirror of
https://github.com/netbirdio/netbird.git
synced 2026-09-22 14:49:10 +02:00
[management,proxy] Agent network: per-account LLM gateway (policy, metering, multi-provider) (#6555)
* [agent-network] Shared proto, OpenAPI schema, and generated types * [agent-network] Management: store, manager, synthesizer, policy engine, provider catalog, HTTP/gRPC API Adds the account-scoped agent-network module: provider/policy/budget CRUD and store, the reverse-proxy service synthesizer, policy selection + limit enforcement, the provider catalog (incl. Vertex AI and AWS Bedrock entries), and the management HTTP + proxy gRPC surfaces. * [management] Fix agent-network proxy-peer fan-out on affected-peer recompute The affected-peers resolver loaded only persisted reverse-proxy services, but agent-network services are synthesized on demand and never persisted. As a result the embedded proxy peer was never folded into the affected set when a client's group changed, so the proxy received no network-map update for a newly authorised client and rejected its handshake until a full resync (restart). loadProxyServices now merges the synthesized agent-network services (injected via a registration hook to avoid an import cycle), so proxy peers learn newly authorised clients immediately. * [proxy] Reverse-proxy middleware framework, chain, and request plumbing The per-target middleware chain (slots, dispatcher, mutation gate, metadata merger), body capture, access-log terminal sink, and the proxy wiring that builds + runs chains for synthesized agent-network services. * [proxy] LLM parsers, pricing, and builtin middlewares (OpenAI, Anthropic, Vertex AI, AWS Bedrock) Request/response parsers and SSE/event-stream metering, the embedded pricing table, and the builtin middleware set: request parser, router, policy limit-check/record, cost meter, guardrail, identity inject, response parser. Includes the path-routed providers — Google Vertex AI (keyfile:: service-account OAuth minting) and AWS Bedrock (bearer auth, invoke/converse/streaming, optional /bedrock prefix) — plus the Models allowlist and unmeterable-publisher deny. * [proxy] IPv6 in-place apply and TCP accept-loop hardening on netstack listeners * [agent-network] End-to-end test suite, module docs, and deployment preset * [agent-network] Fix codespell typos and exclude false positives - labelgen word pool: vermillion -> vermilion, racoon -> raccoon. - codespell ignore list: add flate (Go compress/flate package), recordin (a test-local identifier), and unparseable (a valid alternative spelling used consistently across identifiers + a metadata-value constant). * [management] Set LastSeen on injected proxy peer in realstack test (MySQL strict-mode) The injected embedded proxy peer had a PeerStatus with a zero LastSeen, which serializes to '0000-00-00' and is rejected by MySQL in strict mode (SQLite tolerates it). Set LastSeen to a valid time so SaveAccount succeeds on both engines. * [agent-network] Remove e2e shell-script suite from this branch The end-to-end shell scripts under scripts/e2e/ are maintained in a separate testing suite and are not part of this change set. * [agent-network] Polish module docs: remove internal review scaffolding, fix links, verify diagrams Strip PR-review framing, commit references, absolute paths, and stale internal references from the agent-network module docs; fix broken relative links; verify all diagrams against the current architecture. Remove the internal AI-reviewer prompt file. * [management] Refine session expiration handling to support 3-state encoding for SSO deadlines * [agent-network] Relocate agentnetwork package to internals/modules Move management/server/agentnetwork (and its catalog/, labelgen/, types/ subpackages) to management/internals/modules/agentnetwork, alongside the reverse-proxy module, and rewrite all importers. Pure relocation: package names, the synthesizer + affectedpeers registration hook, and store access (shared store.Store) are unchanged, so no import cycle is introduced (affectedpeers still depends only on the agentnetwork/types leaf). * [agent-network] Co-locate HTTP handlers in the module (RegisterEndpoints) Move the agent-network HTTP handlers from server/http/handlers/agentnetwork into the module at internals/modules/agentnetwork/handlers (package handlers) and rename the entrypoint AddEndpoints -> RegisterEndpoints, matching the reverse-proxy module convention. Wiring in http/handler.go updated accordingly.
This commit is contained in:
@@ -533,3 +533,125 @@ MHcCAQEEIIrYSSNQFaA2Hwf1duRSxKtLYX5CB04fSeQ6tF1aY/PuoAoGCCqGSM49
|
||||
AwEHoUQDQgAEPR3tU2Fta9ktY+6P9G0cWO+0kETA6SFs38GecTyudlHz6xvCdz8q
|
||||
EKTcWGekdmdDPsHloRNtsiCa697B2O9IFA==
|
||||
-----END EC PRIVATE KEY-----`)
|
||||
|
||||
// scriptedAcceptListener returns pre-scripted errors from Accept(). Used
|
||||
// to drive the feedRouterFromListener tests without binding a real
|
||||
// socket — the production code path is a netstack-backed listener that
|
||||
// returns gVisor's "endpoint is in invalid state" forever after its
|
||||
// endpoint is destroyed.
|
||||
type scriptedAcceptListener struct {
|
||||
errs chan error
|
||||
closed chan struct{}
|
||||
}
|
||||
|
||||
func newScriptedAcceptListener(errs ...error) *scriptedAcceptListener {
|
||||
s := &scriptedAcceptListener{
|
||||
errs: make(chan error, len(errs)+1),
|
||||
closed: make(chan struct{}),
|
||||
}
|
||||
for _, e := range errs {
|
||||
s.errs <- e
|
||||
}
|
||||
return s
|
||||
}
|
||||
|
||||
func (s *scriptedAcceptListener) Accept() (net.Conn, error) {
|
||||
select {
|
||||
case <-s.closed:
|
||||
return nil, net.ErrClosed
|
||||
case err := <-s.errs:
|
||||
return nil, err
|
||||
}
|
||||
}
|
||||
|
||||
func (s *scriptedAcceptListener) Close() error {
|
||||
select {
|
||||
case <-s.closed:
|
||||
default:
|
||||
close(s.closed)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
func (s *scriptedAcceptListener) Addr() net.Addr {
|
||||
return &net.TCPAddr{IP: net.IPv4(127, 0, 0, 1), Port: 0}
|
||||
}
|
||||
|
||||
// errSentinel carries a literal error message so tests can synthesise
|
||||
// the exact gVisor text without importing the netstack package.
|
||||
type errSentinel string
|
||||
|
||||
func (e errSentinel) Error() string { return string(e) }
|
||||
|
||||
// TestFeedRouterFromListener_ExitsOnGVisorInvalidEndpoint is the
|
||||
// regression guard for the inbound side of the tight-loop bug. The
|
||||
// per-account plain-HTTP feeder must recognise gVisor's "endpoint is in
|
||||
// invalid state" and exit, otherwise it pegs a CPU core and floods the
|
||||
// account-scoped log with the same accept error every iteration.
|
||||
func TestFeedRouterFromListener_ExitsOnGVisorInvalidEndpoint(t *testing.T) {
|
||||
logger := log.StandardLogger()
|
||||
addr := &net.TCPAddr{IP: net.IPv4(127, 0, 0, 1), Port: 80}
|
||||
router := nbtcp.NewRouter(logger, nil, addr)
|
||||
|
||||
gvisorErr := &net.OpError{
|
||||
Op: "accept",
|
||||
Net: "tcp",
|
||||
Addr: addr,
|
||||
Err: errSentinel("endpoint is in invalid state"),
|
||||
}
|
||||
ln := newScriptedAcceptListener(gvisorErr)
|
||||
defer ln.Close()
|
||||
|
||||
done := make(chan struct{})
|
||||
go func() {
|
||||
defer close(done)
|
||||
feedRouterFromListener(context.Background(), ln, router, logger, "acct-1")
|
||||
}()
|
||||
|
||||
select {
|
||||
case <-done:
|
||||
// Expected: loop recognised the gVisor error and returned.
|
||||
case <-time.After(2 * time.Second):
|
||||
t.Fatal("feedRouterFromListener did not exit on gVisor 'endpoint is in invalid state' — accept loop is spinning")
|
||||
}
|
||||
}
|
||||
|
||||
// TestFeedRouterFromListener_BacksOffOnTransientError asserts the
|
||||
// defence-in-depth path: an unknown sticky Accept error must NOT cause
|
||||
// CPU spin. The loop backs off and exits cleanly when ctx is cancelled.
|
||||
func TestFeedRouterFromListener_BacksOffOnTransientError(t *testing.T) {
|
||||
logger := log.StandardLogger()
|
||||
addr := &net.TCPAddr{IP: net.IPv4(127, 0, 0, 1), Port: 80}
|
||||
router := nbtcp.NewRouter(logger, nil, addr)
|
||||
|
||||
const transientCount = 5
|
||||
errs := make([]error, transientCount)
|
||||
for i := range errs {
|
||||
errs[i] = errSentinel("transient: temporary network error")
|
||||
}
|
||||
ln := newScriptedAcceptListener(errs...)
|
||||
defer ln.Close()
|
||||
|
||||
ctx, cancel := context.WithCancel(context.Background())
|
||||
start := time.Now()
|
||||
done := make(chan struct{})
|
||||
go func() {
|
||||
defer close(done)
|
||||
feedRouterFromListener(ctx, ln, router, logger, "acct-1")
|
||||
}()
|
||||
time.AfterFunc(150*time.Millisecond, cancel)
|
||||
|
||||
select {
|
||||
case <-done:
|
||||
// Expected.
|
||||
case <-time.After(2 * time.Second):
|
||||
t.Fatal("feedRouterFromListener did not exit on ctx cancellation — backoff or exit path broken")
|
||||
}
|
||||
|
||||
// Without backoff the 5 scripted errors would burn in microseconds.
|
||||
// With backoff the first delay alone is 5ms, so the loop must take
|
||||
// at least that long even though ctx fires at 150ms.
|
||||
elapsed := time.Since(start)
|
||||
assert.GreaterOrEqual(t, elapsed, 5*time.Millisecond,
|
||||
"loop ran without backing off — would burn CPU in production")
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user