Merge pull request 'Release v1.2.0 — fleet updates and reliability' (#49) from release-v1.2.0 into main
This commit is contained in:
+40
-1
@@ -6,6 +6,40 @@ and the project follows [Semantic Versioning](https://semver.org/).
|
||||
|
||||
## [Unreleased]
|
||||
|
||||
## [1.2.0] - 2026-08-22
|
||||
|
||||
### Added
|
||||
|
||||
- Fleet-wide agent updates are now discoverable from Settings and the
|
||||
dashboard, with arbitrary host subsets, name/tag/version/eligibility
|
||||
filtering, explicit exclusion reasons, server-side membership validation,
|
||||
and a canary-first pause after the first verified reconnect. Halted rolls
|
||||
expose retry and resume actions. ([#43])
|
||||
- Running jobs with no recent persisted activity are detected server-side and
|
||||
surfaced through deduplicated alerts. Kind-aware thresholds protect normal
|
||||
long-running work, terminal jobs self-resolve, and Prometheus exports stuck
|
||||
job count and oldest inactivity age. ([#41])
|
||||
- Snapshot projections now retain host-level refresh timestamps—including
|
||||
authoritative empty reports—expose a derived stale flag, refresh after
|
||||
backup, forget, and prune, and support an explicit operator reconciliation
|
||||
endpoint. ([#40])
|
||||
|
||||
### Fixed
|
||||
|
||||
- Raised the bounded WebSocket read limit on both peers so ordinary large
|
||||
snapshot reports and restic events no longer disconnect otherwise healthy
|
||||
agents. Regression coverage exercises payloads beyond the library's former
|
||||
32 KiB default in both directions. ([#44])
|
||||
- Fleet-update timeout verification now performs a final authoritative read of
|
||||
the agent version delivered by the reconnect `hello`, avoiding a poll/deadline
|
||||
race and reporting the last observed version when verification fails. ([#43])
|
||||
|
||||
### Changed
|
||||
|
||||
- CI runner images and release images use the anonymous-pull `public`
|
||||
namespace at `docker.dcglab.co.uk`; registry authentication remains required
|
||||
only for publishing.
|
||||
|
||||
## [1.1.1] - 2026-08-22
|
||||
|
||||
### Fixed
|
||||
@@ -140,7 +174,8 @@ with a web UI, JSON API, and self-updating agent fleet.
|
||||
go vet, golangci-lint).
|
||||
- Threat model published (`docs/threat-model.md`).
|
||||
|
||||
[Unreleased]: https://gitea.dcglab.co.uk/steve/restic-manager/compare/v1.1.1...HEAD
|
||||
[Unreleased]: https://gitea.dcglab.co.uk/steve/restic-manager/compare/v1.2.0...HEAD
|
||||
[1.2.0]: https://gitea.dcglab.co.uk/steve/restic-manager/compare/v1.1.1...v1.2.0
|
||||
[1.1.1]: https://gitea.dcglab.co.uk/steve/restic-manager/compare/v1.1.0...v1.1.1
|
||||
[1.1.0]: https://gitea.dcglab.co.uk/steve/restic-manager/releases/tag/v1.1.0
|
||||
[1.0.0]: https://gitea.dcglab.co.uk/steve/restic-manager/releases/tag/v1.0.0
|
||||
@@ -148,3 +183,7 @@ with a web UI, JSON API, and self-updating agent fleet.
|
||||
[#37]: https://gitea.dcglab.co.uk/steve/restic-manager/issues/37
|
||||
[#36]: https://gitea.dcglab.co.uk/steve/restic-manager/issues/36
|
||||
[#34]: https://gitea.dcglab.co.uk/steve/restic-manager/issues/34
|
||||
[#40]: https://gitea.dcglab.co.uk/steve/restic-manager/issues/40
|
||||
[#41]: https://gitea.dcglab.co.uk/steve/restic-manager/issues/41
|
||||
[#43]: https://gitea.dcglab.co.uk/steve/restic-manager/issues/43
|
||||
[#44]: https://gitea.dcglab.co.uk/steve/restic-manager/issues/44
|
||||
|
||||
@@ -61,9 +61,20 @@ type Engine struct {
|
||||
stuckThresholds map[string]time.Duration
|
||||
|
||||
closeOnce sync.Once
|
||||
notifyWG sync.WaitGroup
|
||||
done chan struct{}
|
||||
}
|
||||
|
||||
func (e *Engine) dispatchNotification(ctx context.Context, payload notification.Payload) {
|
||||
e.notifyWG.Add(1)
|
||||
go func() {
|
||||
defer e.notifyWG.Done()
|
||||
e.hub.Dispatch(ctx, payload)
|
||||
}()
|
||||
}
|
||||
|
||||
func (e *Engine) waitNotifications() { e.notifyWG.Wait() }
|
||||
|
||||
// NewEngine builds the engine. agentOfflineFloor + tickPeriod default
|
||||
// to 15min and 60s respectively when zero.
|
||||
func NewEngine(st *store.Store, hub *notification.Hub) *Engine {
|
||||
|
||||
@@ -60,7 +60,7 @@ func (e *Engine) raiseAndNotify(ctx context.Context, hostID, kind, dedupKey, sev
|
||||
if err == nil {
|
||||
hostName = host.Name
|
||||
}
|
||||
go e.hub.Dispatch(ctx, notification.Payload{
|
||||
e.dispatchNotification(ctx, notification.Payload{
|
||||
Event: notification.EventRaised,
|
||||
AlertID: id,
|
||||
Severity: severity,
|
||||
@@ -85,7 +85,7 @@ func (e *Engine) Acknowledge(ctx context.Context, alertID, userID string, when t
|
||||
return nil //nolint:nilerr
|
||||
}
|
||||
p := alertPayload(ctx, e.store, notification.EventAcknowledged, a)
|
||||
go e.hub.Dispatch(context.WithoutCancel(ctx), p)
|
||||
e.dispatchNotification(context.WithoutCancel(ctx), p)
|
||||
return nil
|
||||
}
|
||||
|
||||
@@ -99,7 +99,7 @@ func (e *Engine) Resolve(ctx context.Context, alertID string, when time.Time) er
|
||||
return nil
|
||||
}
|
||||
p := alertPayload(ctx, e.store, notification.EventResolved, a)
|
||||
go e.hub.Dispatch(context.WithoutCancel(ctx), p)
|
||||
e.dispatchNotification(context.WithoutCancel(ctx), p)
|
||||
return nil
|
||||
}
|
||||
|
||||
@@ -164,7 +164,7 @@ func (e *Engine) resolveAndNotify(ctx context.Context, hostID, kind, dedupKey st
|
||||
if a.Kind != kind || a.DedupKey != dedupKey {
|
||||
continue
|
||||
}
|
||||
go e.hub.Dispatch(ctx, notification.Payload{
|
||||
e.dispatchNotification(ctx, notification.Payload{
|
||||
Event: notification.EventResolved,
|
||||
AlertID: a.ID,
|
||||
Severity: a.Severity,
|
||||
|
||||
@@ -25,6 +25,7 @@ func setupEngine(t *testing.T) (*Engine, *store.Store, string) {
|
||||
aead, _ := crypto.NewAEAD(key)
|
||||
hub := notification.NewHub(st, aead, "https://rm.example")
|
||||
eng := NewEngine(st, hub)
|
||||
t.Cleanup(eng.waitNotifications)
|
||||
hostID := ulid.Make().String()
|
||||
if err := st.CreateHost(context.Background(), store.Host{
|
||||
ID: hostID, Name: "alfa-01", OS: "linux", Arch: "amd64",
|
||||
|
||||
Reference in New Issue
Block a user