notify.webhooks existed and setup never asked for one, so a new site learnt of a parked model or a lost node from its users. `llmgw server init --webhook URL` (repeatable) and a Notification webhooks field on both setup screens take them now. Slack's address, Mattermost's and Rocket.Chat's /hooks/ and Discord's …/slack are sent Slack's text, any other the event as JSON; slack: or json: in front says which. Once the control plane runs, they are added to the cluster's settings beside the webhooks already there, none twice, and setup waits for the control planes to start again on the change before sending each a test, saying which answered. A webhook's path is its secret, so it is shown by host only. A failure is said, not fatal: the cluster serves without its alerts, and ctl notify test tries again. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
327 lines
12 KiB
Go
327 lines
12 KiB
Go
package cli
|
|
|
|
import (
|
|
"encoding/json"
|
|
"net/http"
|
|
"net/http/httptest"
|
|
"os"
|
|
"path/filepath"
|
|
"slices"
|
|
"strings"
|
|
"testing"
|
|
|
|
tea "github.com/charmbracelet/bubbletea"
|
|
|
|
"gitea.mynodes.xyz/ilker/llmgw/internal/control/adminapi"
|
|
"gitea.mynodes.xyz/ilker/llmgw/internal/preflight"
|
|
)
|
|
|
|
func press(m tea.Model, keys ...string) tea.Model {
|
|
for _, k := range keys {
|
|
var msg tea.KeyMsg
|
|
switch k {
|
|
case "enter":
|
|
msg = tea.KeyMsg{Type: tea.KeyEnter}
|
|
case "tab":
|
|
msg = tea.KeyMsg{Type: tea.KeyTab}
|
|
case "down":
|
|
msg = tea.KeyMsg{Type: tea.KeyDown}
|
|
case "esc":
|
|
msg = tea.KeyMsg{Type: tea.KeyEsc}
|
|
case "right":
|
|
msg = tea.KeyMsg{Type: tea.KeyRight}
|
|
default:
|
|
msg = tea.KeyMsg{Type: tea.KeyRunes, Runes: []rune(k)}
|
|
}
|
|
m, _ = m.Update(msg)
|
|
}
|
|
return m
|
|
}
|
|
|
|
func TestTheSetupAsksForWhatHighAvailabilityNeedsAndRefusesWhatWillNotDo(t *testing.T) {
|
|
m := tea.Model(newSetupModel("ctl", []string{"10.0.0.5"}))
|
|
m = press(m, "down", "enter")
|
|
if s := m.(setupModel); s.page != pAdmin {
|
|
t.Fatalf("high availability did not lead to the administrator: page %d", s.page)
|
|
}
|
|
// No email: refused, with a reason.
|
|
m = press(m, "tab", "tab", "tab", "enter")
|
|
if s := m.(setupModel); s.page != pAdmin || !strings.Contains(s.formErr, "email") {
|
|
t.Fatalf("went on without an administrator: %+v", s.formErr)
|
|
}
|
|
// The refusal is a dialog; a key closes it, and the cursor is back on
|
|
// the email.
|
|
if !strings.Contains(m.View(), "Not yet") {
|
|
t.Error("the refusal was not shown as a dialog")
|
|
}
|
|
m = press(m, "x", "a@example.com", "tab", "tab", "tab", "enter")
|
|
s := m.(setupModel)
|
|
if s.page != pMachines {
|
|
t.Fatalf("page %d: %s", s.page, s.formErr)
|
|
}
|
|
// This machine's own address is not a database machine.
|
|
s.db[0].addr.SetValue("10.0.0.5")
|
|
s.db[0].user.SetValue("ubuntu")
|
|
s.db[0].auth = authAgent
|
|
s.db[1].addr.SetValue("10.0.0.7")
|
|
s.db[1].user.SetValue("ubuntu")
|
|
s.db[1].auth = authPassword
|
|
if err := s.validateMachines(); !strings.Contains(err, "this machine") {
|
|
t.Errorf("this machine as a database machine: %q", err)
|
|
}
|
|
s.db[0].addr.SetValue("10.0.0.6")
|
|
if err := s.validateMachines(); !strings.Contains(err, "password") {
|
|
t.Errorf("a password login with no password: %q", err)
|
|
}
|
|
s.db[1].secret.SetValue("pw")
|
|
if err := s.validateMachines(); err != "" {
|
|
t.Errorf("a valid pair refused: %s", err)
|
|
}
|
|
cmd := s.command()
|
|
for _, want := range []string{"--admin a@example.com", "--patroni ubuntu@10.0.0.6", "--patroni ubuntu@10.0.0.7", "--no-node"} {
|
|
if !strings.Contains(cmd, want) {
|
|
t.Errorf("command lacks %q:\n%s", want, cmd)
|
|
}
|
|
}
|
|
if strings.Contains(cmd, "pw") {
|
|
t.Error("the password is in the command line")
|
|
}
|
|
}
|
|
|
|
func TestChoosingOneMachineHandsOverToInit(t *testing.T) {
|
|
m := press(tea.Model(newSetupModel("ctl", nil)), "enter").(setupModel)
|
|
if !m.single {
|
|
t.Error("one machine did not hand over")
|
|
}
|
|
}
|
|
|
|
func TestTheChecksHoldTheSetupBackOnlyForAFailure(t *testing.T) {
|
|
m := newSetupModel("ctl", nil)
|
|
m.choice, m.page = 1, pCheck
|
|
m.report = preflight.Report{Findings: []preflight.Finding{{Machine: "a", Check: "disk", Level: preflight.Fail, Fix: "more"}}}
|
|
if s := press(m, "enter").(setupModel); s.page != pCheck {
|
|
t.Error("went on past a failed check")
|
|
}
|
|
m.report.Findings[0].Level = preflight.Warn
|
|
if s := press(m, "enter").(setupModel); s.page != pPlan {
|
|
t.Error("a warning held it back")
|
|
}
|
|
}
|
|
|
|
func TestTheConsoleOffersToReplicateOnlyAStoreThatIsNot(t *testing.T) {
|
|
m := consoleModel{}
|
|
if !m.entryOK(cReplicate) {
|
|
t.Error("a single store is not offered replication")
|
|
}
|
|
m.data.sum.Store = []adminapi.StoreMember{{Name: "a", Role: "leader"}}
|
|
if m.entryOK(cReplicate) {
|
|
t.Error("a replicated store is offered replication")
|
|
}
|
|
// A node is asked for in a dialog, then the console closes with it to do.
|
|
var mm tea.Model = consoleModel{menu: cAddNode, loaded: true, width: 100, height: 30}
|
|
mm = press(mm, "enter", "ubuntu@10.0.0.9", "enter")
|
|
if a := mm.(consoleModel).action; a.kind != "node" || a.targets[0] != "ubuntu@10.0.0.9" {
|
|
t.Errorf("%+v", a)
|
|
}
|
|
}
|
|
|
|
func TestTheConsoleWatchesTheClusterAndEditsItsSettings(t *testing.T) {
|
|
dir := t.TempDir()
|
|
file := filepath.Join(dir, "server.yaml")
|
|
if err := os.WriteFile(file, []byte("# mine\nlisten: \":8080\"\n"), 0o644); err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
m := newConsoleModel("127.0.0.1:1", file)
|
|
m.width, m.height, m.loaded = 120, 40, true
|
|
m.data.nodes = []adminapi.NodeView{{ID: "cuda01", State: "ready", GPUTotal: 1, GPUs: []adminapi.GPUView{{Index: 0, Name: "Quadro RTX 6000"}}}}
|
|
m.data.replicas = []adminapi.ReplicaView{{ID: "r1", Model: "coder-14b", State: "ready",
|
|
Shards: []adminapi.ShardView{{Node: "cuda01", GPUs: []int{0}}}}}
|
|
|
|
// Watching: the GPUs view says which model holds each card.
|
|
m.menu = cGPUs
|
|
if v := m.View(); !strings.Contains(v, "Quadro RTX 6000") || !strings.Contains(v, "coder-14b") {
|
|
t.Errorf("the GPUs view:\n%s", v)
|
|
}
|
|
|
|
// Settings: into router, change retries, save.
|
|
var mm tea.Model = m
|
|
mm.(consoleModel).View()
|
|
cm := mm.(consoleModel)
|
|
cm.menu, cm.inPanel = cSettings, true
|
|
for i, r := range cm.settingsRows() {
|
|
if r.label == "router" {
|
|
cm.row = i
|
|
}
|
|
}
|
|
mm = press(cm, "enter") // into router
|
|
cm = mm.(consoleModel)
|
|
for i, r := range cm.settingsRows() {
|
|
if r.label == "retries" {
|
|
cm.row = i
|
|
}
|
|
}
|
|
if v := cm.View(); !strings.Contains(v, "(default)") {
|
|
t.Errorf("an unset key does not show its default:\n%s", v)
|
|
}
|
|
mm = press(cm, "enter") // the edit dialog
|
|
cm = mm.(consoleModel)
|
|
cm.prompt.SetValue("5")
|
|
mm = press(cm, "enter", "s")
|
|
if d := mm.(consoleModel).dialog; d != "note" {
|
|
t.Fatalf("after saving the dialog is %q: %s", d, mm.(consoleModel).dialogText)
|
|
}
|
|
b, _ := os.ReadFile(file)
|
|
if !strings.Contains(string(b), "retries: 5") || !strings.Contains(string(b), "# mine") {
|
|
t.Errorf("server.yaml:\n%s", b)
|
|
}
|
|
}
|
|
|
|
func TestTheConsoleAddsAControlPlaneWithAFloatingAddress(t *testing.T) {
|
|
replicated := consoleModel{menu: cAddControl, loaded: true, width: 100, height: 30}
|
|
replicated.data.sum.Store = []adminapi.StoreMember{{Name: "a", Role: "leader"}}
|
|
|
|
// The address, then the floating address; the console closes to run it.
|
|
var mm tea.Model = replicated
|
|
mm = press(mm, "enter", "ubuntu@10.0.0.150", "enter", "10.0.0.161/24", "enter")
|
|
want := []string{"server", "add", "ubuntu@10.0.0.150", "--vip", "10.0.0.161/24"}
|
|
if a := mm.(consoleModel).action; a.kind != "run" || !slices.Equal(a.targets, want) {
|
|
t.Errorf("%+v", a)
|
|
}
|
|
|
|
// No floating address is an answer too.
|
|
mm = press(replicated, "enter", "ubuntu@10.0.0.150", "enter", "enter")
|
|
if a := mm.(consoleModel).action; !slices.Equal(a.targets, want[:3]) {
|
|
t.Errorf("without one: %+v", a)
|
|
}
|
|
|
|
// A mistyped one is caught here rather than half way through.
|
|
mm = press(replicated, "enter", "ubuntu@10.0.0.150", "enter", "10.0.0.161", "enter")
|
|
if c := mm.(consoleModel); c.action.kind != "" || !strings.Contains(c.dialogText, "prefix") {
|
|
t.Errorf("an address without its prefix went through: %+v", c.action)
|
|
}
|
|
|
|
// On a store on one machine it says what to do first.
|
|
mm = press(consoleModel{menu: cAddControl, loaded: true, width: 100, height: 30}, "enter")
|
|
if c := mm.(consoleModel); c.dialog != "error" || !strings.Contains(c.dialogText, "Replicate the store") {
|
|
t.Errorf("dialog %q: %s", c.dialog, c.dialogText)
|
|
}
|
|
}
|
|
|
|
func TestTheConsoleOnAStandbySaysWhoseClusterItShows(t *testing.T) {
|
|
m := consoleModel{menu: cOverview, loaded: true, width: 120, height: 40}
|
|
m.data.sum.ControlPlanes = adminapi.ControlPlanes{Members: []adminapi.ControlPlane{
|
|
{Name: "llmgw-ctl", State: "leading"},
|
|
{Name: "llmgw-ctl02", State: "standing by", This: true},
|
|
}}
|
|
if v := m.View(); !strings.Contains(v, "Standing by. Shown, and changed, on the leader: llmgw-ctl") {
|
|
t.Errorf("the overview on a standby:\n%s", v)
|
|
}
|
|
m.data.sum.ControlPlanes.Members[0].This, m.data.sum.ControlPlanes.Members[1].This = true, false
|
|
if v := m.View(); strings.Contains(v, "Standing by.") {
|
|
t.Error("the leader's console says it is standing by")
|
|
}
|
|
}
|
|
|
|
func TestTheConsoleShowsTheGuardrails(t *testing.T) {
|
|
m := consoleModel{menu: cGuard, loaded: true, width: 140, height: 60}
|
|
m.data.models = []adminapi.ModelView{{Name: "llama-guard-3-1b", Ready: 2, Desired: 2}}
|
|
m.guard.view = adminapi.GuardView{
|
|
Policies: []string{"baseline"}, Default: []string{"baseline"},
|
|
Details: []adminapi.GuardPolicyView{{Name: "baseline", Mode: "enforce", Fail: "closed", Judge: "llama-guard-3-1b",
|
|
Checks: []string{"input: pii email → redact"}}},
|
|
Attachments: []adminapi.GuardAttachmentView{{Name: "acme/ml"}},
|
|
}
|
|
m.guard.view.Attachments[0].Scope, m.guard.view.Attachments[0].Policy = "team", "baseline"
|
|
m.guard.events = adminapi.GuardEventsView{Counts: []adminapi.GuardCountView{{Action: "block", Policy: "baseline", Category: "S1", Count: 7}}}
|
|
v := m.View()
|
|
for _, want := range []string{"Guardrails", "baseline", "fail closed", "judge llama-guard-3-1b (2/2 ready)",
|
|
"input: pii email → redact", "acme/ml", "IN THE LAST 24H", "S1"} {
|
|
if !strings.Contains(v, want) {
|
|
t.Errorf("%q missing:\n%s", want, v)
|
|
}
|
|
}
|
|
// W moves the window, and asks again.
|
|
m.inPanel = true
|
|
mm, cmd := m.Update(tea.KeyMsg{Type: tea.KeyRunes, Runes: []rune("w")})
|
|
if c := mm.(consoleModel); guardWindows[c.guard.window] != "7d" || cmd == nil {
|
|
t.Errorf("window %q", guardWindows[c.guard.window])
|
|
}
|
|
}
|
|
|
|
func TestTheConsoleEditsTheClustersSettingsInTheStore(t *testing.T) {
|
|
dir := t.TempDir()
|
|
file := filepath.Join(dir, "server.yaml")
|
|
if err := os.WriteFile(file, []byte("listen: \":8080\"\n"), 0o644); err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
var put adminapi.SettingsRequest
|
|
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
|
switch {
|
|
case r.Method == "GET" && r.URL.Path == "/api/v1/settings":
|
|
_ = json.NewEncoder(w).Encode(adminapi.SettingsView{Version: 7, Body: "router:\n retries: 2\n"})
|
|
case r.Method == "PUT" && r.URL.Path == "/api/v1/settings":
|
|
_ = json.NewDecoder(r.Body).Decode(&put)
|
|
_ = json.NewEncoder(w).Encode(adminapi.SettingsView{Version: 8, Body: put.Body})
|
|
default:
|
|
http.NotFound(w, r)
|
|
}
|
|
}))
|
|
defer srv.Close()
|
|
m := newConsoleModel(strings.TrimPrefix(srv.URL, "http://"), file)
|
|
m.width, m.height, m.loaded = 120, 40, true
|
|
m.menu, m.inPanel = cSettings, true
|
|
m.loadSettings()
|
|
for i, r := range m.settingsRows() {
|
|
if r.label == "router" {
|
|
m.row = i
|
|
}
|
|
}
|
|
var mm tea.Model = press(m, "enter")
|
|
cm := mm.(consoleModel)
|
|
for i, r := range cm.settingsRows() {
|
|
if r.label == "retries" {
|
|
cm.row = i
|
|
}
|
|
}
|
|
if v := cm.View(); !strings.Contains(v, "2") {
|
|
t.Errorf("the cluster's value is not shown:\n%s", v)
|
|
}
|
|
mm = press(cm, "enter")
|
|
cm = mm.(consoleModel)
|
|
cm.prompt.SetValue("5")
|
|
mm = press(cm, "enter", "s")
|
|
if d := mm.(consoleModel).dialog; d != "note" || !strings.Contains(mm.(consoleModel).dialogText, "version 8") {
|
|
t.Fatalf("after saving: %q %s", d, mm.(consoleModel).dialogText)
|
|
}
|
|
if put.Base != 7 || !strings.Contains(put.Body, "retries: 5") {
|
|
t.Errorf("sent %+v", put)
|
|
}
|
|
if b, _ := os.ReadFile(file); string(b) != "listen: \":8080\"\n" {
|
|
t.Errorf("the cluster's key went into the machine's file:\n%s", b)
|
|
}
|
|
}
|
|
|
|
func TestTheConsoleWipesOnlyOnTheMachinesName(t *testing.T) {
|
|
m := newConsoleModel("127.0.0.1:1", filepath.Join(t.TempDir(), "server.yaml"))
|
|
m.width, m.height, m.loaded = 120, 40, true
|
|
m.menu = cWipe
|
|
m.dialog, m.dialogTitle, m.dialogText = "wipe", "Wipe this machine", m.wipeQuestion()
|
|
m.prompt = newTextField()
|
|
m.prompt.Focus()
|
|
if v := m.View(); !strings.Contains(v, "Type the machine's name") {
|
|
t.Errorf("the dialog does not ask for the name:\n%s", v)
|
|
}
|
|
m.prompt.SetValue("not-this-one")
|
|
mm := press(m, "enter")
|
|
if a := mm.(consoleModel).action; a.kind != "" {
|
|
t.Fatalf("a wrong name wiped: %+v", a)
|
|
}
|
|
cm := mm.(consoleModel)
|
|
host, _ := os.Hostname()
|
|
cm.prompt.SetValue(host)
|
|
mm = press(cm, "enter")
|
|
if a := mm.(consoleModel).action; a.kind != "wipe" {
|
|
t.Errorf("the right name did not: %+v", a)
|
|
}
|
|
}
|