[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
+17 -7
View File
@@ -843,10 +843,14 @@ type SyncResponse struct {
NetworkMap *NetworkMap `protobuf:"bytes,5,opt,name=NetworkMap,proto3" json:"NetworkMap,omitempty"`
// Posture checks to be evaluated by client
Checks []*Checks `protobuf:"bytes,6,rep,name=Checks,proto3" json:"Checks,omitempty"`
// Absolute UTC instant at which the peer's SSO session expires.
// Unset when the peer is not SSO-registered or login expiration is disabled.
// Carried on every Sync snapshot so admin-side changes propagate live without
// a client reconnect.
// 3-state session deadline. Carried on every Sync snapshot so admin-side
// changes propagate live without a client reconnect.
//
// field unset (nil) → snapshot carries no info; client keeps the
// deadline it already had
// set, seconds=0 nanos=0 → explicit "expiry disabled" or peer is not
// SSO-registered; client clears its anchor
// set, valid timestamp → new absolute UTC deadline
SessionExpiresAt *timestamppb.Timestamp `protobuf:"bytes,7,opt,name=sessionExpiresAt,proto3" json:"sessionExpiresAt,omitempty"`
}
@@ -1608,8 +1612,11 @@ type LoginResponse struct {
PeerConfig *PeerConfig `protobuf:"bytes,2,opt,name=peerConfig,proto3" json:"peerConfig,omitempty"`
// Posture checks to be evaluated by client
Checks []*Checks `protobuf:"bytes,3,rep,name=Checks,proto3" json:"Checks,omitempty"`
// Absolute UTC instant at which the peer's SSO session expires.
// Unset when the peer is not SSO-registered or login expiration is disabled.
// 3-state session deadline; same encoding as SyncResponse.sessionExpiresAt.
//
// field unset (nil) → no info; client keeps any deadline it had
// set, seconds=0 nanos=0 → explicit "expiry disabled" / non-SSO peer
// set, valid timestamp → new absolute UTC deadline
SessionExpiresAt *timestamppb.Timestamp `protobuf:"bytes,4,opt,name=sessionExpiresAt,proto3" json:"sessionExpiresAt,omitempty"`
}
@@ -1739,7 +1746,10 @@ type ExtendAuthSessionResponse struct {
sizeCache protoimpl.SizeCache
unknownFields protoimpl.UnknownFields
// Absolute UTC instant at which the peer's SSO session now expires.
// 3-state session deadline; same encoding as SyncResponse.sessionExpiresAt.
// In practice ExtendAuthSession only succeeds for SSO peers with expiry
// enabled, so this carries a valid timestamp on the success path. The
// 3-state encoding is documented here for symmetry with Login/Sync.
SessionExpiresAt *timestamppb.Timestamp `protobuf:"bytes,1,opt,name=sessionExpiresAt,proto3" json:"sessionExpiresAt,omitempty"`
}