P2 redesign · phase 2: store rewrite — sources, slim schedules, repo maintenance
CI / Test (linux/amd64) (push) Has been cancelled
CI / Lint (push) Has been cancelled
CI / Build (windows/amd64) (push) Has been cancelled
CI / Build (linux/amd64) (push) Has been cancelled
CI / Build (linux/arm64) (push) Has been cancelled

Go-side data model rebuilt against migration 0008. The fat-Schedule
shape (paths/excludes/tags/retention/manual/kind/options/hooks) is
gone; that surface lives on source_groups now.

* store/types.go
  - Schedule slimmed to {id, host_id, cron, enabled, source_group_ids,
    timestamps}. SourceGroupIDs populated by Get/List, accepted on
    Create/Update so callers pass desired junction state in one shape.
  - SourceGroup added: name (= snapshot tag), includes/excludes,
    retention_policy, retry_max + retry_backoff_seconds, cached
    conflict_dimension.
  - HostRepoMaintenance added: forget/prune/check cadences + enabled.
  - PendingRun added: offline-retry queue.
  - Host loses RepoInitialisedAt; gains BandwidthUpKBps + BandwidthDownKBps.
  - RetentionPolicy moves home from "schedule field" to "source group
    field" but the type itself + Summary() method unchanged.

* store/sources.go (new) — CRUD + GetByName + ConflictDimension cache.
  Group writes bump host_schedule_version; conflict cache writes don't
  (server-internal projection, agent doesn't see it).
* store/maintenance.go (new) — CreateDefault is idempotent (INSERT OR
  IGNORE). UpdateRepoMaintenance doesn't bump schedule version because
  these run on the server's own ticker, not the agent's local cron.
* store/pending.go (new) — Enqueue / DueRunsForRetry / Bump / Delete.
* store/schedules.go — rewritten for slim shape + junction CRUD.
  Update wipes the schedule_source_groups junction wholesale and
  re-inserts (simpler than diffing). Adds SchedulesUsingGroup for
  retention-conflict detection + UI labels.
* store/hosts.go — drops repo_initialised_at scan, adds bandwidth scan.
  New SetHostBandwidth helper.

* HTTP layer — temporarily stubbed during this rewrite (501 returns
  with redesign_in_progress error code). Phase 3 fills these in
  against the new shape:
    - schedules.go REST CRUD
    - schedule_push.go agent reconciliation
    - ui_schedules.go HTML form CRUD
  Run-now-per-host + Init-repo handlers in ui_handlers.go also stubbed
  — both go away in the new model (Run-now per source group; auto-init
  at host enrolment).

* enrollment.go — replaces "seed manual schedule from typed paths"
  with "seed default source group + repo-maintenance row." The default
  group gets the typed paths as its includes; operator edits later
  via Sources tab.

* ws/handler.go — drops the MarkHostRepoInitialised projection (column
  is gone; auto-init makes it derivable from latest init job's status).

Tests:
* store: existing schedule test rewritten for slim shape + junction;
  new sources_test.go covers source-group CRUD, name uniqueness,
  conflict cache, repo-maintenance defaults + idempotent seed,
  pending-runs queue lifecycle.
* http: schedules_test.go and schedule_push_test.go deleted — both
  exercised the obsolete fat-schedule API. Phase 3 rewrites them
  against the new endpoints.

go test ./... green. cmd/server + cmd/agent build. The UI is broken
end-to-end (schedules / sources / repo tabs all hit 501 stubs); Phase 3
restores REST + on-the-wire reconciliation; Phase 4 rewires the UI
templates against the new model.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-05-02 21:30:41 +01:00
parent 666af41f46
commit 5667cdf13a
16 changed files with 1076 additions and 1928 deletions
+28 -23
View File
@@ -42,7 +42,7 @@ func (s *Store) LookupHostByAgentToken(ctx context.Context, tokenHash string) (*
enrolled_at, last_seen_at, status, repo_id, tags,
current_job_id, last_backup_at, last_backup_status,
repo_size_bytes, snapshot_count, open_alert_count,
applied_schedule_version, repo_initialised_at
applied_schedule_version, bandwidth_up_kbps, bandwidth_down_kbps
FROM hosts WHERE agent_token_hash = ?`,
tokenHash)
return scanHost(row)
@@ -55,7 +55,7 @@ func (s *Store) GetHost(ctx context.Context, id string) (*Host, error) {
enrolled_at, last_seen_at, status, repo_id, tags,
current_job_id, last_backup_at, last_backup_status,
repo_size_bytes, snapshot_count, open_alert_count,
applied_schedule_version, repo_initialised_at
applied_schedule_version, bandwidth_up_kbps, bandwidth_down_kbps
FROM hosts WHERE id = ?`, id)
return scanHost(row)
}
@@ -116,7 +116,7 @@ func (s *Store) ListHosts(ctx context.Context) ([]Host, error) {
enrolled_at, last_seen_at, status, repo_id, tags,
current_job_id, last_backup_at, last_backup_status,
repo_size_bytes, snapshot_count, open_alert_count,
applied_schedule_version, repo_initialised_at
applied_schedule_version, bandwidth_up_kbps, bandwidth_down_kbps
FROM hosts ORDER BY name`)
if err != nil {
return nil, fmt.Errorf("store: list hosts: %w", err)
@@ -154,14 +154,14 @@ func scanHostRow(s hostScanner) (*Host, error) {
repoID, currentJob, lastBkSt sql.NullString
enrolled string
tags string
repoInitAt sql.NullString
bwUp, bwDown sql.NullInt64
)
err := s.Scan(&h.ID, &h.Name, &h.OS, &h.Arch,
&h.AgentVersion, &h.ResticVersion, &h.ProtocolVersion,
&enrolled, &lastSeen, &h.Status, &repoID, &tags,
&currentJob, &lastBackupAt, &lastBkSt,
&h.RepoSizeBytes, &h.SnapshotCount, &h.OpenAlertCount,
&h.AppliedScheduleVersion, &repoInitAt)
&h.AppliedScheduleVersion, &bwUp, &bwDown)
if err != nil {
if errors.Is(err, sql.ErrNoRows) {
return nil, ErrNotFound
@@ -202,28 +202,33 @@ func scanHostRow(s hostScanner) (*Host, error) {
if tags != "" {
_ = json.Unmarshal([]byte(tags), &h.Tags)
}
if repoInitAt.Valid {
t, err := time.Parse(time.RFC3339Nano, repoInitAt.String)
if err != nil {
return nil, fmt.Errorf("store: parse repo_initialised_at: %w", err)
}
h.RepoInitialisedAt = &t
if bwUp.Valid {
v := int(bwUp.Int64)
h.BandwidthUpKBps = &v
}
if bwDown.Valid {
v := int(bwDown.Int64)
h.BandwidthDownKBps = &v
}
return &h, nil
}
// MarkHostRepoInitialised sets repo_initialised_at to `when` if it is
// currently NULL. Idempotent: re-firing for an already-initialised
// host is a no-op (we never want to clobber the original timestamp).
// Returns true if the row was updated, false if it was already set.
func (s *Store) MarkHostRepoInitialised(ctx context.Context, hostID string, when time.Time) (bool, error) {
res, err := s.db.ExecContext(ctx,
`UPDATE hosts SET repo_initialised_at = ?
WHERE id = ? AND repo_initialised_at IS NULL`,
when.UTC().Format(time.RFC3339Nano), hostID)
// SetHostBandwidth replaces the host's upload/download caps. Pass nil
// to clear a cap. Caller decides validation; non-positive caps are
// treated as "no cap" by the agent regardless.
func (s *Store) SetHostBandwidth(ctx context.Context, hostID string, upKBps, downKBps *int) error {
_, err := s.db.ExecContext(ctx,
`UPDATE hosts SET bandwidth_up_kbps = ?, bandwidth_down_kbps = ? WHERE id = ?`,
nullableInt(upKBps), nullableInt(downKBps), hostID)
if err != nil {
return false, fmt.Errorf("store: mark repo initialised: %w", err)
return fmt.Errorf("store: set host bandwidth: %w", err)
}
n, _ := res.RowsAffected()
return n > 0, nil
return nil
}
func nullableInt(p *int) any {
if p == nil {
return nil
}
return *p
}