v0.83.0: observability pass — always-DEBUG capture ring + GET /debug/logs + heartbeat log-pull + gap-fill sweep

Capture layer: applog.New returns (logger, Ring) — slog fan-out, stderr at the
configured level, ~1000-entry ring fixed at LevelDebug (remote diagnostics
without a config flip). GET /debug/logs (token-authed, ?raw=1) + request-level
DEBUG middleware. Heartbeat log-pull mirrors the report logtail pattern:
envelope log_tail_requested -> next heartbeat carries log_tail (128KB cap,
consume-once, failed-push retry proven). Gap-fill sweep over netverify/
netstorage/netmount/signedjobs/selfupdate/disks/controller-swap/desired/loop.
Red-proofs: ring-at-emit-level FAILs capture test; drain removed FAILs
consume-once; dropped phase line FAILs the S7 log-sequence smoke.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PSK5g6qYLknKj8u3QAFEr6
This commit is contained in:
2026-07-11 16:24:07 +02:00
parent 461eaf42c1
commit cb692f8788
20 changed files with 902 additions and 29 deletions
+13
View File
@@ -14,6 +14,7 @@ import (
"fmt"
"log/slog"
"sync"
"time"
"gitea.dooplex.hu/admin/felhom-agent/internal/authz"
"gitea.dooplex.hu/admin/felhom-agent/internal/hub"
@@ -98,10 +99,17 @@ func (r *Runner) RunOnce(ctx context.Context) (int, error) {
r.mu.Unlock()
defer func() { r.mu.Lock(); r.running = false; r.mu.Unlock() }()
start := time.Now()
jobs, err := r.source.Jobs(ctx)
if err != nil {
return 0, fmt.Errorf("signedjobs: fetch jobs: %w", err)
}
ids := make([]string, len(jobs))
for i, j := range jobs {
ids[i] = j.JobID
}
r.logger.Debug("signedjobs: jobs fetched", "count", len(jobs), "ids", ids,
"duration_ms", time.Since(start).Milliseconds())
processed := 0
for _, j := range jobs {
if r.processJob(ctx, j) {
@@ -122,6 +130,11 @@ func (r *Runner) processJob(ctx context.Context, j hub.JobWire) bool {
return true
}
// Op received — class/target/expiry only, NEVER the signature or nonce material.
r.logger.Debug("signedjobs: op received",
"job", j.JobID, "op", ob.Op, "target_host", ob.Target.HostID,
"issued_at", ob.IssuedAt.Format(time.RFC3339), "expires_at", ob.ExpiresAt.Format(time.RFC3339))
intent := reconcile.Intent{
Class: reconcile.OpClass(ob.Op),
HostID: ob.Target.HostID,