Node agent: say what it holds today in its answer, so a seed that holds the same is the same; pin mesh-sdk b03bf4c (issue 1126)

This commit is contained in:
2026-10-28 22:15:24 +01:00
parent 4f6b389a37
commit b7159d71a6
5 changed files with 64 additions and 11 deletions
+15
View File
@@ -17,6 +17,7 @@ import (
"encoding/json"
"errors"
"fmt"
"slices"
"sort"
"strings"
"sync"
@@ -100,6 +101,9 @@ type Composer struct {
sealedOwn map[string]ownSealed
said string
refusal string
// held is what the composer's last pass held: each module refused alone, and the node's own ("node") when it could
// compose none (heldNow).
held []string
// doing is what the composer waits on now (waiting), for a running answer to say (issue 1126, T2); its own lock, so
// it is read while c.mu is held.
doingMu sync.Mutex
@@ -621,12 +625,23 @@ func (c *Composer) refused(why string, held map[string]string) {
c.mu.Lock()
same := c.refusal == said
c.refusal = said
c.held = heldModules(held)
if why != "" {
c.held = append(c.held, delivery.HaveNodeWord)
}
c.mu.Unlock()
if !same && c.env.Refused != nil {
c.env.Refused(why, held)
}
}
// heldNow is what the composer's last pass held, sorted.
func (c *Composer) heldNow() []string {
c.mu.Lock()
defer c.mu.Unlock()
return slices.Clone(c.held)
}
// keepRunning is comp with each sealed value the node already runs at the same slot kept, where it opens to the same
// value (delivery.KeepSeals, issue 1126, C1): of what runs (running, the agent's), else of what its module's have says
// it runs (Held). A have written before slots names no slot: its boxes are reused within their own module alone, at a
+12 -3
View File
@@ -1401,12 +1401,16 @@ func TestAHaveSaysWhetherItsModuleRunsInsideTheNodesOwn(t *testing.T) {
name string
have delivery.Have
in bool
// heldToday says the shadow counts the module held today (issue 1126: a seed holding it too holds it as today).
heldToday bool
}{
{"failed, naming nothing it runs", delivery.Have{Phase: delivery.PhaseFailed, Health: delivery.HealthFailed,
Detail: "the node cannot compose it, and keeps running what it ran: no build"}, false},
Detail: "the node cannot compose it, and keeps running what it ran: no build"}, false, false},
{"failed at a build fingerprint", delivery.Have{FP: "build-0123abcd", Composed: "sha256:" + strings.Repeat("c", 64), Phase: delivery.PhaseFailed,
Health: delivery.HealthFailed, Detail: "the node cannot compose it, and keeps running what it ran: no build"}, true},
{"running with no fingerprint (mesh-wireguard)", delivery.Have{Phase: delivery.PhaseRunning, Health: delivery.HealthOK}, true},
Health: delivery.HealthFailed, Detail: "the node cannot compose it, and keeps running what it ran: no build"}, true, false},
{"running with no fingerprint (mesh-wireguard)", delivery.Have{Phase: delivery.PhaseRunning, Health: delivery.HealthOK}, true, false},
{"held today", delivery.Have{FP: "build-0123abcd", Composed: "sha256:" + strings.Repeat("c", 64), Phase: delivery.PhaseHeld,
Health: delivery.HealthWaits, Detail: "held: a required config value is unset"}, true, true},
} {
t.Run(row.name, func(t *testing.T) {
c := New(Env{Node: "n1"})
@@ -1422,6 +1426,11 @@ func TestAHaveSaysWhetherItsModuleRunsInsideTheNodesOwn(t *testing.T) {
if c.inOwn["web"] != row.in {
t.Errorf("web counted inside the node's own composition: %v, want %v", c.inOwn["web"], row.in)
}
s := &Shadow{c: c, ran: map[string]string{}}
s.takeRan(agent.Update{Key: key, Value: value})
if got := slices.Contains(s.heldToday(), "web"); got != row.heldToday {
t.Errorf("web held today: %v, want %v", got, row.heldToday)
}
})
}
}
+34 -3
View File
@@ -40,6 +40,9 @@ type Shadow struct {
// ran is, by module, the digest the module's have says runs: what runs, where the agent's list holds only the copy
// from the declaration kept before the switch (issue 1126, probe #532 on shanks).
ran map[string]string
// heldNow is, by module, whether its have says the node holds it today (phase held): a candidate holding it too holds
// it as today (frombus.Scope.HeldToday, issue 1126).
heldNow map[string]bool
// answered is, by proposal, the candidate revisions and the input changes (moved) each answer was composed at: a proposal
// is answered again only when either moved (issue 1126, 2026-10-28: shanks answered probe/1126-seed-7 at revision 84
// every 13-17 s, woken by its own modules' haves whose health words changed at every look).
@@ -614,7 +617,7 @@ func (s *Shadow) answerProposal(ctx context.Context, proposal string) (delivery.
c.wants = held
c.mu.Unlock()
a := frombus.Answer(ctx, reader{c: c}, c.env.Mesh, frombus.Scope{Node: node, KeptAt: kept, Placements: given, InOwn: inOwn,
SameValue: c.sameValue}, fps, running, proposal, rev)
SameValue: c.sameValue, HeldToday: s.heldToday()}, fps, running, proposal, rev)
s.mu.Lock()
ran := make(map[string]string, len(s.ran))
for m, d := range s.ran {
@@ -624,6 +627,28 @@ func (s *Shadow) answerProposal(ctx context.Context, proposal string) (delivery.
return asHavesSay(a, ran), true
}
// heldToday is what the node holds today: each module whose have's phase is held, and what its own composer holds, the
// node's own composition ("node") among them when it composes none of its own.
func (s *Shadow) heldToday() []string {
set := map[string]bool{}
s.mu.Lock()
for m, held := range s.heldNow {
if held {
set[m] = true
}
}
s.mu.Unlock()
for _, m := range s.c.heldNow() {
set[m] = true
}
out := make([]string, 0, len(set))
for m := range set {
out = append(out, m)
}
sort.Strings(out)
return out
}
// takeRan keeps the digest one of this node's module haves says runs, and says whether it changed: a have whose health
// or words alone moved runs the same.
func (s *Shadow) takeRan(u agent.Update) bool {
@@ -635,12 +660,18 @@ func (s *Shadow) takeRan(u agent.Update) bool {
defer s.mu.Unlock()
before, had := s.ran[module]
h, err := delivery.DecodeHave(u.Value)
if s.heldNow == nil {
s.heldNow = map[string]bool{}
}
wasHeld := s.heldNow[module]
s.heldNow[module] = !u.Deleted && err == nil && h.Phase == delivery.PhaseHeld
holdMoved := wasHeld != s.heldNow[module] // a hold's start or end changes the answer too
if u.Deleted || err != nil || h.Composed == "" || h.Phase == delivery.PhaseRemoved {
delete(s.ran, module)
return had
return had || holdMoved
}
s.ran[module] = h.Composed
return !had || before != h.Composed
return !had || before != h.Composed || holdMoved
}
// asHavesSay is a with each module that differs only from the copy the agent keeps of the declaration before the switch