1
0
forked from wrenn/wrenn

Implement host registration, JWT refresh tokens, and multi-host scheduling

Replaces the hardcoded CP_HOST_AGENT_ADDR single-agent setup with a
DB-driven registration system supporting multiple host agents (BYOC).

Key changes:
- Host agents register via one-time token, receive a 7-day JWT + 60-day
  refresh token; heartbeat loop auto-refreshes on 401/403 and pauses all
  sandboxes if refresh fails
- HostClientPool: lazy Connect RPC client cache keyed by host ID, replacing
  the single static agent client throughout the API and service layers
- RoundRobinScheduler: picks an online host for each new sandbox via
  ListActiveHosts; extensible for future scheduling strategies
- HostMonitor (replaces Reconciler): passive heartbeat staleness check marks
  hosts unreachable and sandboxes missing after 90s; active reconciliation
  per online host restores missing-but-alive sandboxes and stops orphans
- Graceful host delete: returns 409 with affected sandbox list without
  ?force=true; force-delete destroys sandboxes then evicts pool client
- Snapshot delete broadcasts to all online hosts (templates have no host_id)
- sandbox.Manager.PauseAll: pauses all running VMs on CP connectivity loss
- New migration: host_refresh_tokens table with token rotation (issue-then-
  revoke ordering to prevent lockout on mid-rotation crash)
- New sandbox status 'missing' (reversible, unlike 'stopped') and host
  status 'unreachable'; both reflected in OpenAPI spec
- Fix: refresh token auth failure now returns 401 (was 400 via generic
  'invalid' substring match in serviceErrToHTTP)
This commit is contained in:
2026-03-24 18:32:05 +06:00
parent f968da9768
commit 9bf67aa7f7
33 changed files with 1567 additions and 318 deletions

View File

@ -14,17 +14,17 @@ import (
"git.omukk.dev/wrenn/sandbox/internal/db"
"git.omukk.dev/wrenn/sandbox/internal/id"
"git.omukk.dev/wrenn/sandbox/internal/lifecycle"
pb "git.omukk.dev/wrenn/sandbox/proto/hostagent/gen"
"git.omukk.dev/wrenn/sandbox/proto/hostagent/gen/hostagentv1connect"
)
var teamNameRE = regexp.MustCompile(`^[A-Za-z0-9 _\-@']{1,128}$`)
// TeamService provides team management operations.
type TeamService struct {
DB *db.Queries
Pool *pgxpool.Pool
Agent hostagentv1connect.HostAgentServiceClient
DB *db.Queries
Pool *pgxpool.Pool
HostPool *lifecycle.HostClientPool
}
// TeamWithRole pairs a team with the calling user's role in it.
@ -177,10 +177,16 @@ func (s *TeamService) DeleteTeam(ctx context.Context, teamID, callerUserID strin
var stopIDs []string
for _, sb := range sandboxes {
if _, err := s.Agent.DestroySandbox(ctx, connect.NewRequest(&pb.DestroySandboxRequest{
SandboxId: sb.ID,
})); err != nil && connect.CodeOf(err) != connect.CodeNotFound {
slog.Warn("team delete: failed to destroy sandbox", "sandbox_id", sb.ID, "error", err)
host, hostErr := s.DB.GetHost(ctx, sb.HostID)
if hostErr == nil {
agent, agentErr := s.HostPool.GetForHost(host)
if agentErr == nil {
if _, err := agent.DestroySandbox(ctx, connect.NewRequest(&pb.DestroySandboxRequest{
SandboxId: sb.ID,
})); err != nil && connect.CodeOf(err) != connect.CodeNotFound {
slog.Warn("team delete: failed to destroy sandbox", "sandbox_id", sb.ID, "error", err)
}
}
}
stopIDs = append(stopIDs, sb.ID)
}