Let an operator authenticate with a seeded key, and reset the schema
CI / chart (pull_request) Successful in 2s
CI / security (pull_request) Failing after 19s
CI / test (pull_request) Successful in 5m34s

- TERDUT_OPERATOR_KEY creates or re-keys the instance-scoped service account
  "terdut-operator" at every start, so terdut-operator needs no bootstrap
  handshake. An instance-scoped account now acts as owner of every team's
  configuration, but is not a member of any team.
- POST /api/teams takes an external_id (instance service accounts only) and
  is idempotent on it, so automation finds its own team again after a crash
  instead of adopting by display name. GET /api/teams?name= is removed.
- Integration and dead man's switch names are unique per team (409). The
  escalation PUT accepts usernames and resolves them itself.
- The 18 migrations are squashed into 001_schema.sql, with no Default team.
  TERDUT_DEADMAN_* and the env seeding of switches are removed: teams carry
  their own. Existing development databases must be recreated.

Security and robustness:
- GET /api/users no longer returns other people's email or ntfy topic to
  non-admins.
- The access log records the route pattern, so integration keys and ack
  tokens in the path are not written to the log. Server errors are logged.
- Rate limits take the client address TERDUT_TRUSTED_PROXIES hops from the
  right of X-Forwarded-For instead of trusting the first, forgeable entry.
- /api/bootstrap runs in a transaction under an advisory lock, so two
  concurrent calls cannot both create an administrator.
- API key last_used_at is written at most every five minutes.

Cleanup: remove GET /api/incidents/{id}/alerts, unused exports, SQLite
remnants in comments and config.

Claude-Session: https://claude.ai/code/session_016mBLURvJoMuUEr9cB2RpUN
This commit is contained in:
Niklas Ye
2026-10-09 14:56:13 +02:00
parent 44b2eb2cc3
commit 9029d48584
46 changed files with 1445 additions and 655 deletions
+11 -8
View File
@@ -50,6 +50,9 @@ func callerIsAdmin(ctx context.Context) bool {
// writing a response: callers here need to combine it with other ways of
// being allowed, not stop at the first no.
func callerOwnsTeam(ctx context.Context, teamID int64) bool {
if c, _ := callerFromContext(ctx); c.IsInstanceServiceAccount() {
return true
}
role, ok := callerRole(ctx, teamID)
return ok && role == models.RoleOwner
}
@@ -132,7 +135,7 @@ func handleCreateServiceAccount(db *sql.DB) http.HandlerFunc {
key, err := mintServiceAccountKey(r.Context(), db, sa.ID, "initial")
if err != nil {
respond(w, http.StatusInternalServerError, errResp("internal error"))
serverError(w, r, err)
return
}
respond(w, http.StatusCreated, map[string]any{"service_account": sa, "key": key})
@@ -233,7 +236,7 @@ func handleCreateServiceAccountKey(db *sql.DB) http.HandlerFunc {
return
}
if err != nil {
respond(w, http.StatusInternalServerError, errResp("internal error"))
serverError(w, r, err)
return
}
if !callerMayManageServiceAccount(r.Context(), sa) {
@@ -255,7 +258,7 @@ func handleCreateServiceAccountKey(db *sql.DB) http.HandlerFunc {
key, err := mintServiceAccountKey(r.Context(), db, sa.ID, req.Name)
if err != nil {
respond(w, http.StatusInternalServerError, errResp("internal error"))
serverError(w, r, err)
return
}
respond(w, http.StatusCreated, key)
@@ -274,7 +277,7 @@ func handleDeleteServiceAccountKey(db *sql.DB) http.HandlerFunc {
return
}
if err != nil {
respond(w, http.StatusInternalServerError, errResp("internal error"))
serverError(w, r, err)
return
}
if !callerMayManageServiceAccount(r.Context(), sa) {
@@ -290,7 +293,7 @@ func handleDeleteServiceAccountKey(db *sql.DB) http.HandlerFunc {
res, err := db.ExecContext(r.Context(),
"DELETE FROM service_account_keys WHERE id = $1 AND service_account_id = $2", keyID, sa.ID)
if err != nil {
respond(w, http.StatusInternalServerError, errResp("internal error"))
serverError(w, r, err)
return
}
if n, _ := res.RowsAffected(); n == 0 {
@@ -325,7 +328,7 @@ func handleListServiceAccounts(db *sql.DB) http.HandlerFunc {
rows, err := db.QueryContext(r.Context(), query, args...)
if err != nil {
respond(w, http.StatusInternalServerError, errResp("internal error"))
serverError(w, r, err)
return
}
defer rows.Close()
@@ -335,14 +338,14 @@ func handleListServiceAccounts(db *sql.DB) http.HandlerFunc {
var sa models.ServiceAccount
var created int64
if err := rows.Scan(&sa.ID, &sa.Name, &sa.Scope, &sa.TeamID, &sa.CreatedBy, &created); err != nil {
respond(w, http.StatusInternalServerError, errResp("internal error"))
serverError(w, r, err)
return
}
sa.CreatedAt = time.Unix(created, 0).UTC()
accounts = append(accounts, sa)
}
if err := rows.Err(); err != nil {
respond(w, http.StatusInternalServerError, errResp("internal error"))
serverError(w, r, err)
return
}
respond(w, http.StatusOK, accounts)