mesh-controller/cmd/mesh-builder/holder_test.go

package main

import (
	"context"
	"encoding/json"
	"errors"
	"strings"
	"testing"

	"github.com/novox/mesh-controller/internal/link"
)

// A holder paused stays paused across its restart: the flag is kept in its workspace (novox/hq ADR
// 0219), and what it says about itself follows.
func TestAPausedHolderStaysPausedAcrossARestart(t *testing.T) {
	workspace := t.TempDir()
	var said []link.HolderState
	h := newHolder("ace", link.TheBuildMachine, workspace, func(s link.HolderState) error {
		said = append(said, s)
		return nil
	})
	if h.Paused() {
		t.Fatal("a new holder starts paused")
	}
	if _, err := h.handlers()["pause"](context.Background(), json.RawMessage(`{}`)); err != nil {
		t.Fatal(err)
	}
	if !h.Paused() || len(said) != 1 || !said[0].Paused || said[0].On != "ace" {
		t.Fatalf("paused: %v, said %+v", h.Paused(), said)
	}
	again := newHolder("ace", link.TheBuildMachine, workspace, nil)
	if !again.Paused() {
		t.Fatal("restarted, the holder forgot it was paused")
	}
	if _, err := again.handlers()["resume"](context.Background(), json.RawMessage(`{}`)); err != nil {
		t.Fatal(err)
	}
	if newHolder("ace", link.TheBuildMachine, workspace, nil).Paused() {
		t.Fatal("resumed, the holder came back paused")
	}
}

// kill ends the build with that id — its context, which ends its commands — removes what it left by
// label, and refuses an id it is not building.
func TestKillEndsTheBuildRunningHereAndNoOther(t *testing.T) {
	h := newHolder("ace", link.TheBuildMachine, t.TempDir(), nil)
	var removed []string
	h.remove = func(_ context.Context, _ string, name string, args ...string) (string, error) {
		removed = append(removed, name+" "+strings.Join(args, " "))
		if args[0] == "ps" {
			return "c1\n", nil
		}
		return "", nil
	}
	kill := h.handlers()["kill"]
	if _, err := kill(context.Background(), json.RawMessage(`{"id":"build-1"}`)); err == nil {
		t.Fatal("killed a build while none ran")
	}

	building, cancel := context.WithCancel(context.Background())
	r := h.begin(link.BuildRequest{ID: "build-1", Repository: "novox/a"}, cancel)
	h.stepped(r, "image")
	if c := h.current(); c.Running == nil || c.Running.ID != "build-1" || c.Running.Step != "image" {
		t.Fatalf("current says %+v", c)
	}
	if _, err := kill(context.Background(), json.RawMessage(`{"id":"build-2"}`)); err == nil ||
		!strings.Contains(err.Error(), "build-1") {
		t.Fatalf("killed another id: %v", err)
	}
	// The build's own goroutine: it ends when its context does, as a build's commands do, and
	// announces what came of it.
	go func() {
		<-building.Done()
		if h.returned(r) {
			h.said(r, link.KilledByHand, true)
		}
		h.end(r)
	}()
	answer, err := kill(context.Background(), json.RawMessage(`{"id":"build-1"}`))
	if err != nil {
		t.Fatal(err)
	}
	if building.Err() == nil {
		t.Fatal("the build's context was not cancelled")
	}
	if !r.killed {
		t.Error("the build is not marked killed, so it would be announced as an ordinary failure")
	}
	said := answer.(map[string]any)["said"].(string)
	if !strings.Contains(said, "2 container(s)") || !strings.Contains(said, "announced as failed") || !strings.Contains(said, link.KilledByHand) {
		t.Errorf("kill said %q", said)
	}
	// Removed at the kill and again once the build had ended: a container made in between is caught.
	if len(removed) != 4 || !strings.Contains(removed[0], "label=mesh.build=build-1") || !strings.Contains(removed[2], "label=mesh.build=build-1") {
		t.Errorf("removed %v", removed)
	}
	if c := h.current(); c.Running != nil {
		t.Errorf("after the kill current says %+v", c)
	}
}

// A holder announces this machine's verbs of the seat as the console reads a seat's verb, and no more.
func TestAHolderAnnouncesItsMachinesVerbsForTheConsole(t *testing.T) {
	info := announcement(link.TheBuildMachine, moduleOf("ace.build-agent"), "ace")
	if info.Name != "node-build-agent" || info.ID != "ace" || len(info.Endpoints) != 4 {
		t.Fatalf("announced %s/%s with %d endpoints", info.Name, info.ID, len(info.Endpoints))
	}
	kill := info.Endpoints[1]
	md := kill.Metadata
	if kill.Subject != "mesh.seat.node-build-agent.tool.kill.ace" || kill.QueueGroup != "seat.node-build-agent" || md["kind"] != "seat" || md["seat"] != "node-build-agent" ||
		md["scope"] != "node" || md["node"] != "ace" || md["tool"] != "kill" || md["module"] != "build-agent" ||
		!strings.Contains(md["description"], "killed by hand") || !strings.Contains(md["schema"], `"id"`) {
		t.Fatalf("kill is announced as %+v", kill)
	}
	body, err := json.Marshal(info)
	if err != nil || len(body) > 8*1024 {
		t.Fatalf("the answer is %d bytes (%v)", len(body), err)
	}
}

// A build that ended on its own as the kill arrived says what it did: the kill is refused, and its
// own error is its outcome. One whose outcome could not be announced is not said to be settled.
func TestAKillArrivingAfterTheBuildEndedIsRefusedAndAnUnannouncedKillSaysSo(t *testing.T) {
	h := newHolder("ace", link.TheBuildMachine, t.TempDir(), nil)
	h.remove = func(context.Context, string, string, ...string) (string, error) { return "", nil }
	_, cancel := context.WithCancel(context.Background())
	r := h.begin(link.BuildRequest{ID: "build-1"}, cancel)
	if killed := h.returned(r); killed {
		t.Fatal("a build nobody killed reads as killed")
	}
	if _, err := h.kill("build-1"); err == nil || !strings.Contains(err.Error(), "ended on its own") {
		t.Fatalf("killed a build that had ended: %v", err)
	}
	h.end(r)

	building, cancel := context.WithCancel(context.Background())
	r = h.begin(link.BuildRequest{ID: "build-2"}, cancel)
	go func() {
		<-building.Done()
		if h.returned(r) {
			h.said(r, link.KilledByHand, false)
		}
		h.end(r)
	}()
	said, err := h.kill("build-2")
	if err != nil || strings.Contains(said, "announced as failed") || !strings.Contains(said, "could not be announced") {
		t.Fatalf("kill said %q (%v)", said, err)
	}
}

// **Issue 306**: a holder starting removes the containers earlier builds left on its machine, through
// the runner a kill uses, and a runtime that cannot be asked does not stop it.
func TestAHolderStartingRemovesWhatEarlierBuildsLeftHere(t *testing.T) {
	h := newHolder("novox", link.TheBuildMachine, t.TempDir(), nil)
	var removed []string
	h.remove = func(_ context.Context, _ string, name string, args ...string) (string, error) {
		removed = append(removed, name+" "+strings.Join(args, " "))
		if args[0] == "ps" {
			return "c1 build-1\nc2 build-1\nc3 check-here-2\n", nil
		}
		return "", nil
	}
	if n := h.removeLeftBehind(); n != 2 || len(removed) != 2 || removed[1] != "docker rm -f c1 c2" {
		t.Fatalf("removed %d: %v", n, removed)
	}
	h.remove = func(context.Context, string, string, ...string) (string, error) {
		return "", errors.New("no runtime")
	}
	if n := h.removeLeftBehind(); n != 0 {
		t.Errorf("a runtime that cannot be asked removed %d", n)
	}
}