[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:
Maycon Santos
2026-06-27 13:41:00 +02:00
committed by GitHub
parent 615631567a
commit b416063bcc
187 changed files with 36835 additions and 660 deletions
+43
View File
@@ -19,6 +19,7 @@ import (
"github.com/stretchr/testify/require"
"github.com/netbirdio/netbird/proxy/auth"
"github.com/netbirdio/netbird/proxy/internal/middleware"
"github.com/netbirdio/netbird/proxy/internal/roundtrip"
"github.com/netbirdio/netbird/proxy/internal/types"
"github.com/netbirdio/netbird/proxy/web"
@@ -1407,3 +1408,45 @@ func TestStampNetBirdIdentity_CapturedDataPresentButEmpty(t *testing.T) {
assert.Empty(t, pr.Out.Header.Get(headerNetBirdGroups),
"X-NetBird-Groups must be stripped when CapturedData has no groups")
}
// TestBuildRequestInput_PropagatesIdentityAndGroups locks the final wiring link
// between auth and the middleware chain: CapturedData identity (user, groups,
// auth method, client IP) and the target's AgentNetwork flag must land on the
// middleware Input the chain runs against. If UserGroups stops flowing here,
// llm_router denies every request with no_authorised_provider.
func TestBuildRequestInput_PropagatesIdentityAndGroups(t *testing.T) {
cd := NewCapturedData("req-123")
cd.SetUserID("user-1")
cd.SetUserEmail("user@example.com")
cd.SetUserGroups([]string{"grp-admins", "grp-users"})
cd.SetUserGroupNames([]string{"Admins", "Users"})
cd.SetAuthMethod("oidc")
cd.SetClientIP(netip.MustParseAddr("100.90.1.14"))
r := httptest.NewRequest(http.MethodPost, "http://agent.example.com/v1/chat/completions", nil)
r.Header.Set("Content-Type", "application/json")
result := targetResult{
target: &PathTarget{AgentNetwork: true},
matchedPath: "/",
serviceID: types.ServiceID("svc-1"),
accountID: types.AccountID("acct-1"),
}
body := []byte(`{"model":"gpt-5.4"}`)
in := buildRequestInput(r, result, cd, body, false, int64(len(body)))
require.NotNil(t, in, "buildRequestInput must return an envelope")
assert.Equal(t, middleware.SlotOnRequest, in.Slot, "request input runs in the on-request slot")
assert.Equal(t, "svc-1", in.ServiceID, "service id must propagate")
assert.Equal(t, "acct-1", in.AccountID, "account id must propagate")
assert.Equal(t, "user-1", in.UserID, "user id must propagate")
assert.Equal(t, "user@example.com", in.UserEmail, "user email must propagate")
assert.Equal(t, []string{"grp-admins", "grp-users"}, in.UserGroups,
"CapturedData groups MUST reach the middleware Input — llm_router authorises against this")
assert.Equal(t, []string{"Admins", "Users"}, in.UserGroupNames, "group names must propagate")
assert.Equal(t, "oidc", in.AuthMethod, "auth method must propagate")
assert.Equal(t, "100.90.1.14", in.SourceIP, "client IP must propagate")
assert.True(t, in.AgentNetwork, "agent-network target flag must reach the Input")
assert.Equal(t, body, in.Body, "captured body must reach the Input")
}