Wait out a forge not served for a moment when registering a build (novox/hq issue 486)
mesh/merge-gate pass: builds build-agent, mesh-controller → ace, g14, novox, shanks; no bus step; every machine composes with the change as it did without …
mesh/repo-check pass: its merge-check.sh passed
mesh/delivery superseded: a newer head of the same pull request

A registration asked the forge while node-tools re-served after a tool-runner
rollout, heard "nothing serves gitea.gitea_api", and failed a good build's
plan. The bus's not-served answer is now link.ErrNothingServes (and a timeout
link.ErrNoAnswer), and the registration asks again for up to 90 s on those
alone, never on a refusal; past the bound it fails saying how long it waited.
This commit is contained in:
2026-10-12 11:23:03 +02:00
parent da1473e9db
commit 47205403d3
5 changed files with 227 additions and 7 deletions
+17 -4
View File
@@ -16,6 +16,19 @@ type Answer struct {
Error string `json:"error,omitempty"`
}
// ErrNoAnswer is a tool asked that did not answer within the asker's wait: nothing refused, and asking again
// may be answered. With ErrNothingServes, what an asker may wait out (novox/hq issue 486).
var ErrNoAnswer = errors.New("no answer within the wait")
// saidAs is an error said in its own words that is still the error it is a case of, for errors.Is.
type saidAs struct {
text string
is error
}
func (e saidAs) Error() string { return e.text }
func (e saidAs) Unwrap() error { return e.is }
// Ask calls one of a module's tools over the broker and waits for its answer.
//
// **The control plane is the way in** (novox/hq 04-ISSUES/049, ADR 0095). A module's broker
@@ -37,16 +50,16 @@ func Ask(ctx context.Context, bus Bus, module, tool string, args json.RawMessage
reply, err := bus.AskTool(ctx, module, tool, args, timeout)
if err != nil {
if errors.Is(err, nats.ErrNoResponders) {
return Answer{}, fmt.Errorf(
return Answer{}, saidAs{fmt.Sprintf(
"nothing serves %s: no runtime has bound %q on the bus. The module is not "+
"assigned, its runtime is not up, or it serves no such tool — `status` says "+
"whether the machine carrying it has applied", module, key)
"whether the machine carrying it has applied", module, key), ErrNothingServes}
}
if errors.Is(err, context.DeadlineExceeded) || errors.Is(err, nats.ErrTimeout) {
return Answer{}, fmt.Errorf(
return Answer{}, saidAs{fmt.Sprintf(
"%s did not answer within %s. Its runtime serves %q when it is up and has bound "+
"the bus — `status` says whether the machine carrying it has applied",
module, timeout, key)
module, timeout, key), ErrNoAnswer}
}
return Answer{}, fmt.Errorf("cannot ask %s: %w", key, err)
}
+3 -2
View File
@@ -206,8 +206,9 @@ func (b OverNATS) AskTool(ctx context.Context, module, tool string, args []byte,
if err != nil {
if errors.Is(err, nats.ErrNoResponders) {
// Said at once rather than after the whole wait: nothing is subscribed to that
// subject, which is a different fact from a tool being slow.
return nil, fmt.Errorf("nothing serves %s.%s", module, tool)
// subject, which is a different fact from a tool being slow. Said as ErrNothingServes, so an
// asker can tell a tool not served now from one that refused (novox/hq issue 486).
return nil, saidAs{fmt.Sprintf("nothing serves %s.%s", module, tool), ErrNothingServes}
}
return nil, fmt.Errorf("asking %s.%s: %w", module, tool, err)
}
+10
View File
@@ -3,6 +3,7 @@ package link
import (
"context"
"encoding/json"
"errors"
"strings"
"testing"
"time"
@@ -115,6 +116,15 @@ func TestAskingAToolNobodyServesFailsAtOnce(t *testing.T) {
if !strings.Contains(err.Error(), "nothing serves") {
t.Errorf("the refusal does not say nobody is there: %v", err)
}
// And it is ErrNothingServes, through Ask too, so an asker can wait out a tool runner re-serving and
// never a refusal (novox/hq issue 486).
if !errors.Is(err, ErrNothingServes) {
t.Errorf("nothing serving the tool is not ErrNothingServes: %v", err)
}
if _, err := Ask(context.Background(), bus, "nobody", "home", nil, 30*time.Second); !errors.Is(err, ErrNothingServes) ||
!strings.Contains(err.Error(), "nothing serves nobody.home") {
t.Errorf("Ask does not say ErrNothingServes in its words: %v", err)
}
}
// And a served tool answers, with no reply queue to declare and no correlation to check.