feat(swarm): autonomous agent containers, Swarm Manager with auto-stop, /nodes UI overhaul

## 1. Fix /nodes Swarm Status Display
- Add SwarmStatusBanner component: clear green/red/loading state
- Shows nodeId, managerAddr, isManager badge
- Error state explains what to check (docker.sock mount)
- Header now shows 'swarm unreachable — check gateway' vs 'active'
- swarmOk now checks nodeId presence, not just data existence

## 2. Autonomous Agent Container
- New docker/Dockerfile.agent — builds Go agent binary from gateway/cmd/agent/
- New gateway/cmd/agent/main.go — standalone HTTP microservice:
  * GET /health — liveness probe with idle time info
  * POST /task — receives task, forwards to Gateway orchestrator
  * GET /info  — agent metadata (id, hostname, gateway url)
  * Idle watchdog: calls /api/swarm/agents/{name}/stop after IdleTimeoutMinutes
  * Connects to Swarm overlay network (goclaw-net) → reaches DB/Gateway by DNS
  * Env: AGENT_ID, GATEWAY_URL, DATABASE_URL, IDLE_TIMEOUT_MINUTES

## 3. Swarm Manager Agent (auto-stop after 15min idle)
- New gateway/internal/api/swarm_manager.go:
  * SwarmManager goroutine checks every 60s
  * Scales idle GoClaw agent services to 0 replicas after 15 min
  * Tracks lastActivity from task UpdatedAt timestamps
- New REST endpoints in gateway:
  * GET  /api/swarm/agents           — list agents with idleMinutes
  * POST /api/swarm/agents/{name}/start — scale up agent
  * POST /api/swarm/agents/{name}/stop  — scale to 0
  * DELETE /api/swarm/services/{id}     — remove service permanently
- SwarmManager started as background goroutine in main.go with context cancel

## 4. Docker Client Enhancements
- Added NetworkAttachment type and Networks field to ServiceSpec
- CreateAgentServiceFull(opts) — supports overlay networks, custom labels
- CreateAgentService() delegates to CreateAgentServiceFull for backward compat
- RemoveService(id) — DELETE /v1.44/services/{id}
- GetServiceLastActivity(id) — finds latest task UpdatedAt for idle detection

## 5. tRPC & Gateway Proxy
- New functions: removeSwarmService, listSwarmAgents, startSwarmAgent, stopSwarmAgent
- SwarmAgentInfo type with idleMinutes, lastActivity, desiredReplicas
- createAgentService now accepts networks[] parameter
- New tRPC endpoints: nodes.removeService, nodes.listAgents, nodes.startAgent, nodes.stopAgent

## 6. Nodes.tsx UI Overhaul
- SwarmStatusBanner component at top — no more silent 'connecting…'
- New 'Agents' tab with AgentManagerRow: idle time, auto-stop warning, start/stop/remove buttons
- IdleColor coding: green < 5m, yellow 5-10m, red 10m+ with countdown to auto-stop
- ServiceRow: added Remove button with confirmation dialog
- RemoveConfirmDialog component
- DeployAgentDialog: added overlay networks field, default env includes GATEWAY_URL
- All queries refetch after agent start/stop/remove
This commit is contained in:
bboxwtf
2026-03-21 20:37:21 +00:00
parent 12b8332b2f
commit a8a8ea1ee2
9 changed files with 1168 additions and 194 deletions

View File

@@ -158,11 +158,17 @@ type SwarmService struct {
}
type ServiceSpec struct {
Name string `json:"Name"`
Mode ServiceMode `json:"Mode"`
TaskTemplate TaskTemplate `json:"TaskTemplate"`
EndpointSpec *EndpointSpec `json:"EndpointSpec,omitempty"`
Labels map[string]string `json:"Labels"`
Name string `json:"Name"`
Mode ServiceMode `json:"Mode"`
TaskTemplate TaskTemplate `json:"TaskTemplate"`
EndpointSpec *EndpointSpec `json:"EndpointSpec,omitempty"`
Labels map[string]string `json:"Labels"`
Networks []NetworkAttachment `json:"Networks,omitempty"`
}
type NetworkAttachment struct {
Target string `json:"Target"`
Aliases []string `json:"Aliases,omitempty"`
}
type ServiceMode struct {
@@ -443,34 +449,67 @@ func (c *DockerClient) ListAllTasks() ([]SwarmTask, error) {
// CreateAgentService deploys a new swarm service for an AI agent.
// image: container image, name: service name, replicas: initial count,
// env: environment variables, port: optional published port (0 = none).
// CreateAgentServiceOpts holds options for deploying an agent Swarm service.
type CreateAgentServiceOpts struct {
Name string
Image string
Replicas int
Env []string
Port int
Networks []string // overlay network names/IDs to attach
Labels map[string]string
}
func (c *DockerClient) CreateAgentService(name, image string, replicas int, env []string, port int) (*SwarmService, error) {
return c.CreateAgentServiceFull(CreateAgentServiceOpts{
Name: name,
Image: image,
Replicas: replicas,
Env: env,
Port: port,
})
}
func (c *DockerClient) CreateAgentServiceFull(opts CreateAgentServiceOpts) (*SwarmService, error) {
labels := map[string]string{
"goclaw.agent": "true",
"goclaw.name": opts.Name,
}
for k, v := range opts.Labels {
labels[k] = v
}
spec := ServiceSpec{
Name: name,
Name: opts.Name,
Mode: ServiceMode{
Replicated: &ReplicatedService{Replicas: replicas},
Replicated: &ReplicatedService{Replicas: opts.Replicas},
},
TaskTemplate: TaskTemplate{
ContainerSpec: ContainerSpec{
Image: image,
Env: env,
Image: opts.Image,
Env: opts.Env,
},
},
Labels: map[string]string{
"goclaw.agent": "true",
"goclaw.name": name,
},
Labels: labels,
}
if port > 0 {
if opts.Port > 0 {
spec.EndpointSpec = &EndpointSpec{
Ports: []PortConfig{
{
Protocol: "tcp",
TargetPort: port,
TargetPort: opts.Port,
PublishMode: "ingress",
},
},
}
}
if len(opts.Networks) > 0 {
for _, net := range opts.Networks {
spec.Networks = append(spec.Networks, NetworkAttachment{
Target: net,
Aliases: []string{opts.Name},
})
}
}
var created struct {
ID string `json:"ID"`
}
@@ -480,6 +519,40 @@ func (c *DockerClient) CreateAgentService(name, image string, replicas int, env
return c.GetService(created.ID)
}
// RemoveService removes a swarm service by ID or name.
func (c *DockerClient) RemoveService(idOrName string) error {
req, err := http.NewRequest(http.MethodDelete, c.baseURL+"/v1.44/services/"+urlEncode(idOrName), nil)
if err != nil {
return err
}
resp, err := c.httpClient.Do(req)
if err != nil {
return fmt.Errorf("docker DELETE service %s: %w", idOrName, err)
}
defer resp.Body.Close()
if resp.StatusCode >= 400 {
body, _ := io.ReadAll(resp.Body)
return fmt.Errorf("docker DELETE service %s: status %d: %s", idOrName, resp.StatusCode, string(body))
}
return nil
}
// GetServiceLastActivity returns the most recent task update time for a service.
// Used to determine whether a service is idle.
func (c *DockerClient) GetServiceLastActivity(serviceID string) (time.Time, error) {
tasks, err := c.ListServiceTasks(serviceID)
if err != nil {
return time.Time{}, err
}
var latest time.Time
for _, t := range tasks {
if t.UpdatedAt.After(latest) {
latest = t.UpdatedAt
}
}
return latest, nil
}
// ─── Methods: Containers ─────────────────────────────────────────────────────
func (c *DockerClient) ListContainers() ([]Container, error) {