feat(builder): every boot through the node-agent, every lost file counted, Steam cache

What a builder boot sees is now what a node does:
- First boots (untouched, or -as-deployed with exactly a new server's
  settings) are deployed by the node-agent's BootTest in keep mode; the
  builder only watches the console and inspects what's left. The Go copy of
  the deploy (its own docker run, mounts and startup prefix) is gone. It had
  drifted: it gave the image's VOLUME folders their own volumes, which nodes
  don't, so saves there looked safe while every start loses them.
- Files written outside /server and /data are counted whatever their type
  (it only counted config-like extensions, so .sav or .db saves went
  unseen), including the image's VOLUME folders; logs, pid and lock files
  and system folders are left out.
- Boot tests ask the server to stay up holdSec (60 s, test.yaml can set it)
  after its ready line and to listen on every published container port
  (needs the node-agent's matching BootTest).
- Steam apps are downloaded once per build into a gbr.cache volume and copied
  into each boot, so later boots only check the files (STEAM_CACHE=off).
- RUNNER.md no longer suggests docker system prune, which deletes the
  gbr-boottest network when nothing is using it.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
gregandClaude Opus 5.5 committed 2026-10-26 00:00:50 -04:00
1 parent e07025f03d
commit 04967a8a16
10 files changed
+424 -171

No files matched your search

+10 -39
View File
@@ -7,7 +7,6 @@ import (
"flag"
"fmt"
"os"
"os/exec"
"path/filepath"
"sort"
"strings"
@@ -298,46 +297,18 @@ func bootCheck(gamesDir, id, agentImage string, wantOutside bool) (problems, ver
// CI. fillBlank also fills blank password-like settings, only to find out whether they are why a draft
// fails. problems is set when the template can't be boot-tested at all.
func agentBoot(gamesDir, id, agentImage string, fillBlank bool) (output string, passed bool, problems []string, err error) {
self, err := os.Executable()
payload, err := bootTestPayload(gamesDir, id, fillBlank)
var missing *missingSecretError
if errors.As(err, &missing) {
// The builder has no CI secrets: that's the template's problem to fix, not a reason to stop
return "", false, []string{"the boot test can't run: " + missing.Error() + ". Remove 'secrets' from " +
"test.yaml; boot tests run with exactly what a new server gets"}, nil
}
if err != nil {
return "", false, nil, err
}
// A boot test that was killed (worker restarted mid-build) leaves its container and volume behind,
// and the next deploy under the same name would trip over them
runCmd("docker", "rm", "-f", "boottest-"+id)
runCmd("docker", "volume", "rm", "-f", "boottest-"+id+"-data")
args := []string{"boottest-payload", "-games", gamesDir, id}
if fillBlank {
args = []string{"boottest-payload", "-fill-blank-passwords", "-games", gamesDir, id}
}
payloadCmd := exec.Command(self, args...)
var stderr bytes.Buffer
payloadCmd.Stderr = &stderr
payload, err := payloadCmd.Output()
if err != nil {
var exitErr *exec.ExitError
if errors.As(err, &exitErr) && exitErr.ExitCode() == exitMissingSecret {
// The builder has no CI secrets: that's the template's problem to fix, not a reason to stop
return "", false, []string{"the boot test can't run: " + strings.TrimSpace(stderr.String()) + ". Remove 'secrets' from " +
"test.yaml; boot tests run with exactly what a new server gets"}, nil
}
return "", false, nil, fmt.Errorf("boottest-payload: %v: %s", err, strings.TrimSpace(stderr.String()))
}
cmd := exec.Command("docker", "run", "--rm", "-i", "-v", "/var/run/docker.sock:/var/run/docker.sock",
"--entrypoint", "java", agentImage, "-Dloader.main=com.gbreed.gbr.nodeagent.BootTest", "-cp", "app.jar",
"org.springframework.boot.loader.launch.PropertiesLauncher")
cmd.Stdin = bytes.NewReader(payload)
var out bytes.Buffer
cmd.Stdout = &teeWriter{&out}
cmd.Stderr = cmd.Stdout
if runErr := cmd.Run(); runErr != nil {
var exitErr *exec.ExitError
if !errors.As(runErr, &exitErr) {
return "", false, nil, runErr
}
return out.String(), false, nil, nil
}
return out.String(), true, nil, nil
output, passed, err = runAgentBootTest(payload, agentImage)
return output, passed, nil, err
}
// blankRequiredLooking lists the settings a new server gets empty that look like a server might need a
@@ -372,7 +343,7 @@ func emptySettingsProblem(keys []string, verdict string) string {
func firstBootGame(gamesDir, id string) (*bootReport, error) {
outDir := filepath.Join("firstboot-out", id+"-draft")
if err := runFirstBoot([]string{"-games", gamesDir, "-game", id, "-out", outDir}); err != nil {
if err := runFirstBoot([]string{"-games", gamesDir, "-game", id, "-as-deployed", "-out", outDir}); err != nil {
return nil, err
}
return readBootReport(filepath.Join(outDir, "report.json"))