admin
c393d8529a
The dead-app check (source of app_start_failed and app_stopped_unhealthy) now gates on a crash-aware
boot grace (internal/crashboot): 15 min when the host crash guard's last boot was UNCLEAN and within
30 min of the controller start, otherwise 90 s. The fact is read from the agent's local API
(GET /host/crash-guard, agentapi.Client.CrashGuard). UNKNOWN - no agent, an older agent's 404, no
crash-guard state - is a normal boot. The decision is logged once ("boot grace ...: ... (R-856)").
NEEDS AN AGENT CHANGE to take effect: GET /host/crash-guard serving the guard's state.json fields
(present, last_boot_at, last_boot_unclean, tripped). Until then every box keeps 90 s.
Tests: TestR856_CrashBootHoldsTheMailsForTheLongGrace, TestR856_NormalBootKeeps90s,
TestR856_FactReadLateInTheNormalGraceStillCounts, TestR856_AgentProbeReadsTheCrashGuardState,
TestR856_CrashGuardDecodesAndAnOlderAgentIs404, TestR856_DeadAppCheckWaitsOnTheCrashAwareGrace,
TestR856_NormalGraceIsTheDeadAppBootGrace.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0159rPz1ZhFKsS53msqPYxtS
38 lines
1.2 KiB
Go
38 lines
1.2 KiB
Go
package agentapi
|
|
|
|
import (
|
|
"context"
|
|
"errors"
|
|
"net/http"
|
|
"net/http/httptest"
|
|
"strings"
|
|
"testing"
|
|
)
|
|
|
|
// R-856: GET /host/crash-guard decodes the crash guard's fields, and an agent that predates the route
|
|
// surfaces as a typed 404 (the caller reads it as unknown → the normal boot grace).
|
|
func TestR856_CrashGuardDecodesAndAnOlderAgentIs404(t *testing.T) {
|
|
mux := http.NewServeMux()
|
|
mux.HandleFunc("GET /host/crash-guard", func(w http.ResponseWriter, r *http.Request) {
|
|
_, _ = w.Write([]byte(`{"ok":true,"data":{"present":true,"last_boot_at":"2026-10-04T12:00:00Z","last_boot_unclean":true,"tripped":false}}`))
|
|
})
|
|
s := httptest.NewTLSServer(mux)
|
|
defer s.Close()
|
|
c := clientFor(t, s, strings.TrimPrefix(s.URL, "https://"))
|
|
st, err := c.CrashGuard(context.Background())
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
if !st.Present || !st.LastBootUnclean || st.LastBootAt != "2026-10-04T12:00:00Z" || st.Tripped {
|
|
t.Fatalf("state = %+v", st)
|
|
}
|
|
|
|
old := httptest.NewTLSServer(http.NewServeMux())
|
|
defer old.Close()
|
|
_, err = clientFor(t, old, strings.TrimPrefix(old.URL, "https://")).CrashGuard(context.Background())
|
|
var se *StatusError
|
|
if !errors.As(err, &se) || se.Code != http.StatusNotFound {
|
|
t.Fatalf("an older agent must answer a typed 404, got %v", err)
|
|
}
|
|
}
|