Files
mesh-tools/node-tools/internal/bus/wait.go
T
mesh-toolsandClaude Opus 5.5 21d038d339
mesh/merge-gate head 21d038d3397c merged into trunk 5d70eb3e35a9 — pass, with a note: builds mesh-tools, node-tools (+39 dependent(s)) → ace, g14, novox, s…
mesh/repo-check head 21d038d3397c merged into trunk 5d70eb3e35a9 — pass: THE CHANGE ALTERS ITS OWN CHECK (merge-check.sh): main's version judged it; the ch…
mesh/delivery delivered
End every wait in flight when the tool runner stops (issue 745)
Closing the console shut its server down with a context that never ends, so a stop or restart of
the tool runner waited on any mesh_wait in flight for up to ten minutes. The server's base context
is now cancelled first, ending every wait at once, with a five-second shutdown as a backstop
(second review of issue 745).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-15 00:47:59 +00:00

133 lines
4.1 KiB
Go

package bus
import (
"context"
"encoding/json"
"fmt"
"strings"
"time"
"github.com/nats-io/nats.go"
)
// Waiting on the bus for one event (novox/hq ADR 0367): what the mesh MCP server's `mesh_wait` does.
//
// **A subscription for the call, and nothing kept** (§2): no durable consumer, no queue, no stream. It
// subscribes the subjects when called and unsubscribes them before it answers, so an event published
// between two calls is not heard — a session reads the state from its owner after every wake (§4).
// WaitIssued is one event family the mesh issued this account to wait on (ADR 0367 §2): the name a session
// asks for, and the subject it lands on. Only the tool runner's membership carries any.
type WaitIssued struct {
Event string `json:"event"`
Subject string `json:"subject"`
}
// Heard is one event a wait heard: the subject it arrived on, its body and when it arrived.
type Heard struct {
Subject string
Body json.RawMessage
At time.Time
}
// HearFirst subscribes the subjects for this call alone and answers the first message whose body match
// accepts (every one, when match is nil), or ok false once `within` has passed. Every subscription is
// closed before it returns. A subscription the bus refuses is said as an error naming the subject, at once;
// a caller gone — ctx done — ends the wait at once with ctx's error, so nothing waits on for nobody.
func (c *Conn) HearFirst(ctx context.Context, subjects []string, within time.Duration, match func(json.RawMessage) bool) (heard Heard, ok bool, err error) {
if len(subjects) == 0 {
return Heard{}, false, fmt.Errorf("a wait names at least one subject")
}
got := make(chan Heard, 1)
refused := make(chan string, len(subjects))
var subs []*nats.Subscription
defer func() {
for _, s := range subs {
_ = s.Unsubscribe()
}
c.mu.Lock()
for _, subject := range subjects {
delete(c.waits[subject], refused)
if len(c.waits[subject]) == 0 {
delete(c.waits, subject)
}
}
c.mu.Unlock()
}()
c.mu.Lock()
if c.waits == nil {
c.waits = map[string]map[chan string]bool{}
}
for _, subject := range subjects {
if c.waits[subject] == nil {
c.waits[subject] = map[chan string]bool{}
}
c.waits[subject][refused] = true
}
c.mu.Unlock()
for _, subject := range subjects {
sub, err := c.nc.Subscribe(subject, func(msg *nats.Msg) {
body := json.RawMessage(msg.Data)
if !json.Valid(body) {
quoted, _ := json.Marshal(string(msg.Data))
body = quoted
}
if match != nil && !match(body) {
return
}
select {
case got <- Heard{Subject: msg.Subject, Body: body, At: time.Now().UTC()}:
default:
}
})
if err != nil {
return Heard{}, false, fmt.Errorf("could not wait on %s: %w", subject, err)
}
subs = append(subs, sub)
}
// The bus has every subscription — or has said which it refused — once this returns.
if err := c.nc.FlushTimeout(5 * time.Second); err != nil {
return Heard{}, false, fmt.Errorf("the bus did not take the wait: %w", err)
}
timer := time.NewTimer(within)
defer timer.Stop()
select {
case h := <-got:
return h, true, nil
case subject := <-refused:
return Heard{}, false, fmt.Errorf("the bus refused this account a subscription on %s: it is not in the "+
"account's wait grant (novox/hq ADR 0367 §2)", subject)
case <-timer.C:
return Heard{}, false, nil
case <-ctx.Done():
return Heard{}, false, ctx.Err()
}
}
// waitRefused tells every wait on a subject the bus refused that it was refused; true when one was waiting.
func (c *Conn) waitRefused(subject string) bool {
c.mu.Lock()
defer c.mu.Unlock()
told := false
for ch := range c.waits[subject] {
select {
case ch <- subject:
default:
}
told = true
}
return told
}
// Subscriptions is how many subscriptions this connection holds now: what a wait leaves behind is none.
func (c *Conn) Subscriptions() int { return c.nc.NumSubscriptions() }
// subjectRefused is the subject a subscription refusal names, or "".
func subjectRefused(err error) string {
m := refusedSubject.FindStringSubmatch(err.Error())
if len(m) < 2 {
return ""
}
return strings.Trim(m[1], `"`)
}