Files
tiny-forge/internal/api/health_probes.go
T
alexei.dolgolyov 410a131cec feat(apps): stepped creation wizard, branch previews, and app-creation fixes
This session (frontend focus):
- Rebuild /apps/new as a 4-step wizard (Basics → Configure → Trigger → Review):
  WizardRail, SourceKindPicker card grid, AppManifest review, per-step validation,
  ConfirmDialog-based unsaved-changes guard.
- Extract lib/workload/sourceForms.ts (single source of truth for source_config)
  + {Image,Compose,Static,Dockerfile}SourceForm + StaticDiscoveryWizard; fold the
  /apps/[id] edit form onto the same components (removes the duplication). Add
  vitest + sourceForms unit tests.
- Branch preview environments UI: /chain is_preview/preview_branch + a Preview
  environments panel on /apps/[id] (per-branch URLs, ConfirmDialog teardown, armed
  state); RegistryImagePicker on the registry trigger and the image source.
- Fixes: image-inspect 404 -> admin-gated POST /api/discovery/image/inspect;
  conflict-panel blur flicker; friendly localized discovery errors; CPU/Memory
  label hints; dashboard + /apps "Total workloads" count only source_kind workloads
  (drop stale trigger_kind gate); NPM cert/access-list name cache; EntityPicker
  empty-list guard.
- Update CLAUDE.md frontend conventions + add a Build & Test section.

Also captures pre-existing in-progress platform work (not from this session):
workload notifications, Prometheus metrics export, store lockfile, health probes,
backup hardening, and related store/webhook/scheduler changes.
2026-05-29 02:09:54 +03:00

65 lines
2.5 KiB
Go

package api
import (
"context"
"log/slog"
"net/http"
"time"
"github.com/alexei/tinyforge/internal/metrics"
)
// livez always returns 200 if the process is up. Used by container
// orchestrators / load balancers / Docker HEALTHCHECK as the "is the
// binary alive" probe. Intentionally does NOT touch the DB or Docker —
// a slow DB must not cause restart loops.
func (s *Server) livez(w http.ResponseWriter, _ *http.Request) {
w.Header().Set("Content-Type", "text/plain; charset=utf-8")
_, _ = w.Write([]byte("ok\n"))
}
// readyz returns 200 only when the process can actually serve traffic:
// SQLite is reachable, the encryption key is loaded, the deployer is
// not draining. The response body is intentionally minimal — the
// specific failing probe name is recorded in slog (operator-visible)
// rather than returned to unauthenticated callers. This avoids handing
// reconnaissance to an attacker who can hit /readyz during an outage
// ("DB down" vs "encryption key missing" leaks operational state).
func (s *Server) readyz(w http.ResponseWriter, r *http.Request) {
ctx, cancel := context.WithTimeout(r.Context(), 2*time.Second)
defer cancel()
// DB ping: cheap and exact — exercises the connection pool, file
// lock, and busy-timeout. A failing ping means SQLite WAL is wedged
// or the data dir is gone.
if err := s.store.DB().PingContext(ctx); err != nil {
slog.Warn("readyz: db ping failed", "error", err)
w.Header().Set("Content-Type", "text/plain; charset=utf-8")
w.WriteHeader(http.StatusServiceUnavailable)
_, _ = w.Write([]byte("not ready\n"))
return
}
// Encryption key sanity: if it's zero we cannot decrypt any stored
// secret, so the deployer paths will all explode at first use.
if s.encKey == ([32]byte{}) {
slog.Warn("readyz: encryption key not loaded")
w.Header().Set("Content-Type", "text/plain; charset=utf-8")
w.WriteHeader(http.StatusServiceUnavailable)
_, _ = w.Write([]byte("not ready\n"))
return
}
w.Header().Set("Content-Type", "text/plain; charset=utf-8")
_, _ = w.Write([]byte("ready\n"))
}
// metricsExport writes the process-wide metrics registry in Prometheus
// text format. Admin-only by router placement; surface is intentionally
// thin (no histograms / quantiles, only counters) to keep the binary
// dependency-free.
func (s *Server) metricsExport(w http.ResponseWriter, _ *http.Request) {
w.Header().Set("Content-Type", "text/plain; version=0.0.4; charset=utf-8")
_ = metrics.DefaultRegistry.WritePrometheus(w)
}