Say when the node composes again after a seat that did not answer, say what a long pass waits on, and serve the verb compose (issue 774)

On 2026-10-31 ace's route-proxy said only that the vault could not be asked, and ace said nothing for five minutes
while a pass waited after the vault restarted; the retry that already existed was invisible. A refusal for a seat or
a read that did not answer now says when the node composes again ("the node composes again at HH:MM:SS (try N)"), a
retry pass says it starts, a pass that runs on says every minute what it waits on, and the node-engine's verb
compose makes a pass now and says how it went, so a person recovers without a restart.
This commit is contained in:
2026-10-31 00:56:47 +01:00
parent 91fb323ce0
commit 9c15610f70
7 changed files with 255 additions and 17 deletions
+34
View File
@@ -18,6 +18,7 @@ import (
"github.com/novox/mesh-host/internal/accounts"
"github.com/novox/mesh-host/internal/apply"
"github.com/novox/mesh-host/internal/link"
"github.com/novox/mesh-host/internal/selfcompose"
"github.com/novox/mesh-host/internal/store"
)
@@ -292,3 +293,36 @@ func compositionFrom(current *agentNow) func(module, digest string, diff bool) (
return ag.Composition(ctx, module, digest, diff)
}
}
// composeReadFor bounds the verb compose's wait for its pass: a pass that waits on a seat longer says what it waits on.
const composeReadFor = 2 * time.Minute
// composeFrom answers the verb compose (issue 774): a pass of the composer that runs now, and with module that module's
// apply tried again by the node agent; refused in words while the node composes nothing of its own.
func composeFrom(current *agentNow, composer *atomic.Pointer[selfcompose.Composer]) func(module string) (any, error) {
return func(module string) (any, error) {
c := composer.Load()
if c == nil {
return nil, errors.New("this node composes none of its own modules now (it applies the controller's " +
"compositions, or its node agent is starting), so there is no pass to make")
}
ag := current.get()
if module != "" {
if ag == nil || !ag.Placed("")[module] {
return nil, fmt.Errorf("%s has no want on this machine, so there is no apply of it to try again", module)
}
}
ctx, cancel := context.WithTimeout(context.Background(), composeReadFor)
defer cancel()
pass, err := c.ComposeNow(ctx)
if err != nil {
return nil, err
}
out := map[string]any{"pass": pass}
if module != "" {
ag.Retry(module)
out["retried"] = module
}
return out, nil
}
}
+1
View File
@@ -1142,6 +1142,7 @@ func runLink(ctx context.Context, opts options) error {
go reconcileActs(ctx, queue.Acts)
current := &agentNow{}
queue.Acts.Composition = compositionFrom(current)
queue.Acts.Compose = composeFrom(current, &composerNow)
setRunsHere(runsFromAgent(current))
factsOfNow := func(ctx context.Context, ag *agent.Agent) {
sayFacts(ctx, opts, mine.Membership.Signer, queue, say, ag)
+6
View File
@@ -668,6 +668,7 @@ func nodeAgent(ctx context.Context, opts options, signer ed25519.PublicKey, trus
}
if composer != nil {
machinesNow.Store(composer) // the machines a failing network part points at, by the placements (issue 774)
composerNow.Store(composer) // what the verb compose asks a pass of, this run's alone
composes.set(delivery.ComposesOwn)
env.Composed, env.SelfComposed, env.Trusted, env.Policy = composer, true, nil, composer.Policy
env.HoldsData = composer.HoldsData // what runs from the kept declaration says Data as its manifest does
@@ -692,6 +693,7 @@ func nodeAgent(ctx context.Context, opts options, signer ed25519.PublicKey, trus
stopRun()
cancel()
current.set(nil)
composerNow.Store(nil)
if ctx.Err() != nil {
return
}
@@ -814,6 +816,10 @@ func busyModules() []string {
// (writeHealthReport); nil on a node that does not compose its own, whose parts then name no target.
var machinesNow atomic.Pointer[selfcompose.Composer]
// composerNow is the composer of the run that composes the node's own now, nil while the node applies the controller's
// compositions or no run is going: what the verb compose asks a pass of (issue 774).
var composerNow atomic.Pointer[selfcompose.Composer]
// keptRetired says the kept declaration is read no more: every module the seat's placement puts on this node has a have of
// its own (placedAllHave), so what runs is the agent's alone (ADR 0550 §2, design 47's L3 s9).
var keptRetired atomic.Bool