Authenticate with a seeded operator key; fold escalation and switches into TerdutTeam

Credentials: the TerdutServer controller generates <name>-operator-key in
the server's own namespace (owned by it) and hands it to the pods as
TERDUT_OPERATOR_KEY; the server creates its instance-scoped account from it
at every start. A replaced Secret rolls the pods. The bootstrap handshake,
the checkpoint Secret, per-team service accounts and credentials Secrets,
BootstrapStateLost and credentials.deletionPolicy are gone.

CRDs: TerdutServer, TerdutTeam and TerdutAlertSource. TerdutEscalationRule
and TerdutDeadmanSwitch become spec.escalation and spec.deadmanSwitches[]
on the team (matched by name, extras removed); team invites are removed.
A team is created under the identity <namespace>/<name> (external_id), so a
retry, a lost status or a deleted team heal by repeating the same call, and
a display name owned by another team is TeamNameTaken instead of an
adoption. The server resolves escalation usernames (UnknownUser condition).
OIDC claim names and trustEmail are spec fields.

Fixes: query values are URL-escaped; every delete treats 404 as success;
deleting a team no longer depends on allowedTeams consent; a switch or
integration deleted on the server is recreated; unnamed switches take the
CR's name.

Cleanup: scaffold e2e test, AGENTS.md, devcontainer, unused config/ pieces
and Client.Version() removed; DESIGN.md, README, ROADMAP and the demo
(run-demo.sh, manifests) rewritten for the new design. Secret RBAC stays
cluster-wide, now stated in DESIGN.md section 9.

Claude-Session: https://claude.ai/code/session_016mBLURvJoMuUEr9cB2RpUN
This commit is contained in:
Niklas Ye
2026-10-09 14:56:22 +02:00
parent b0a431f2a4
commit e1103f2b7d
92 changed files with 2082 additions and 7561 deletions
@@ -2,7 +2,9 @@ package controller
import (
"context"
"errors"
"fmt"
"net/http"
"strconv"
"time"
@@ -39,9 +41,8 @@ type TerdutAlertSourceReconciler struct {
client.Client
Scheme *runtime.Scheme
OperatorNamespace string
Recorder recorder.EventRecorder
NewClient func(endpoint string) *tdclient.Client
Recorder recorder.EventRecorder
NewClient func(endpoint string) *tdclient.Client
}
// +kubebuilder:rbac:groups=terdut.ryuvia.com,resources=terdutalertsources,verbs=get;list;watch;create;update;patch;delete
@@ -79,7 +80,7 @@ func (r *TerdutAlertSourceReconciler) Reconcile(ctx context.Context, req ctrl.Re
return ctrl.Result{}, nil
}
team, tc, resolveErr := resolveTeamAndClient(ctx, r.Client, r.OperatorNamespace, as.Namespace, as.Spec.TeamRef, newClient)
team, tc, resolveErr := resolveTeamAndClient(ctx, r.Client, as.Namespace, as.Spec.TeamRef, newClient)
if resolveErr != nil {
return r.setNotReady(ctx, &as, resolveErr.reason, resolveErr.message, waitInterval)
}
@@ -111,7 +112,27 @@ func (r *TerdutAlertSourceReconciler) Reconcile(ctx context.Context, req ctrl.Re
return ctrl.Result{}, err
}
} else if err := tc.RenameIntegration(ctx, teamID, as.Status.IntegrationID, as.Spec.Name); err != nil {
return ctrl.Result{}, fmt.Errorf("PATCH /api/teams/%d/integrations/%d: %w", teamID, as.Status.IntegrationID, err)
se, ok := errors.AsType[*tdclient.StatusError](err)
if !ok || se.Code != http.StatusNotFound {
return ctrl.Result{}, fmt.Errorf("PATCH /api/teams/%d/integrations/%d: %w", teamID, as.Status.IntegrationID, err)
}
// Deleted on the server behind our back, so the webhook URL
// already stopped working: recreate it (a new URL, in the same
// Secret) rather than fail forever. reconcileCreate trusts the
// Secret's existence as "already created", so drop it first.
lostID := as.Status.IntegrationID
if err := r.Delete(ctx, &secret); err != nil && !apierrors.IsNotFound(err) {
return ctrl.Result{}, fmt.Errorf("deleting stale webhook Secret %s/%s: %w", as.Namespace, secretName, err)
}
as.Status.IntegrationID = 0
if err := r.reconcileCreate(ctx, &as, tc, teamID); err != nil {
return ctrl.Result{}, err
}
if r.Recorder != nil {
r.Recorder.Eventf(&as, nil, corev1.EventTypeWarning, "IntegrationRecreated", "IntegrationRecreated",
"integration %d no longer exists on the server; created %d with a new webhook URL (Secret %s)",
lostID, as.Status.IntegrationID, secretName)
}
}
}
@@ -279,7 +300,7 @@ func (r *TerdutAlertSourceReconciler) reconcileDelete(
if as.Status.IntegrationID != 0 {
if team, tc, resolveErr := resolveTeamAndClient(
ctx, r.Client, r.OperatorNamespace, as.Namespace, as.Spec.TeamRef, newClient,
ctx, r.Client, as.Namespace, as.Spec.TeamRef, newClient,
); resolveErr == nil {
if err := tc.DeleteIntegration(ctx, team.Status.TeamID, as.Status.IntegrationID); err != nil {
if r.Recorder != nil {