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
+59 -34
View File
@@ -15,6 +15,10 @@ import (
"github.com/go-chi/chi/v5"
)
// bootstrapLockKey is the transaction-scoped advisory lock handleBootstrap
// holds; distinct from the migration and notifier keys.
const bootstrapLockKey = 0x7465726475744254
func handleBootstrap(db *sql.DB) http.HandlerFunc {
return func(w http.ResponseWriter, r *http.Request) {
var req struct {
@@ -40,15 +44,30 @@ func handleBootstrap(db *sql.DB) http.HandlerFunc {
}
h, err := hashPassword(req.Password)
if err != nil {
respond(w, http.StatusInternalServerError, errResp("internal error"))
serverError(w, r, err)
return
}
passwordHash = &h
}
// Check-then-insert has to be one atomic step: two concurrent calls on
// an empty install would otherwise both see zero users and both create
// an admin. The transaction-scoped lock serialises them, and the loser
// sees the winner's row.
tx, err := db.BeginTx(r.Context(), nil)
if err != nil {
serverError(w, r, err)
return
}
defer tx.Rollback() //nolint:errcheck
if _, err := tx.ExecContext(r.Context(), "SELECT pg_advisory_xact_lock($1)", bootstrapLockKey); err != nil {
serverError(w, r, err)
return
}
var count int
if err := db.QueryRowContext(r.Context(), "SELECT COUNT(*) FROM users").Scan(&count); err != nil {
respond(w, http.StatusInternalServerError, errResp("internal error"))
if err := tx.QueryRowContext(r.Context(), "SELECT COUNT(*) FROM users").Scan(&count); err != nil {
serverError(w, r, err)
return
}
if count > 0 {
@@ -57,34 +76,29 @@ func handleBootstrap(db *sql.DB) http.HandlerFunc {
}
var userID int64
if err := db.QueryRowContext(r.Context(),
if err := tx.QueryRowContext(r.Context(),
"INSERT INTO users (username, email, password_hash, is_admin) VALUES ($1, $2, $3, true) RETURNING id",
req.Username, req.Email, passwordHash).Scan(&userID); err != nil {
respond(w, http.StatusInternalServerError, errResp("internal error"))
serverError(w, r, err)
return
}
raw, hash, err := randomToken()
if err != nil {
respond(w, http.StatusInternalServerError, errResp("internal error"))
serverError(w, r, err)
return
}
var keyID int64
if err := db.QueryRowContext(r.Context(),
if err := tx.QueryRowContext(r.Context(),
"INSERT INTO api_keys (user_id, key_hash, name) VALUES ($1, $2, $3) RETURNING id",
userID, hash, "bootstrap").Scan(&keyID); err != nil {
respond(w, http.StatusInternalServerError, errResp("internal error"))
serverError(w, r, err)
return
}
// The default team exists from migration 003, on a fresh install too.
// Without a membership the first user signs in to a working server with
// no queue, no schedule and nowhere for an integration to hang off.
if teamID, err := defaultTeamID(r.Context(), db); err == nil {
db.ExecContext(r.Context(), //nolint:errcheck
"INSERT INTO team_members (team_id, user_id, role) VALUES ($1, $2, $3) "+
"ON CONFLICT (team_id, user_id) DO NOTHING",
teamID, userID, models.RoleOwner)
if err := tx.Commit(); err != nil {
serverError(w, r, err)
return
}
user, _ := fetchUser(r.Context(), db, userID)
@@ -93,12 +107,19 @@ func handleBootstrap(db *sql.DB) http.HandlerFunc {
}
}
// handleListUsers is readable by anyone signed in, because the assignment
// control and the schedule need to name people. What it returns about other
// people is therefore only what naming them takes: email and ntfy_topic are
// blanked unless the caller is an admin or the row is their own. The topic in
// particular is a publish secret.
func handleListUsers(db *sql.DB) http.HandlerFunc {
return func(w http.ResponseWriter, r *http.Request) {
caller, _ := userFromContext(r.Context())
seeAll := caller.IsAdmin
rows, err := db.QueryContext(r.Context(),
"SELECT id, username, email, created_at, ntfy_topic, is_admin, admin_source, disabled_at FROM users ORDER BY id")
if err != nil {
respond(w, http.StatusInternalServerError, errResp("internal error"))
serverError(w, r, err)
return
}
defer rows.Close()
@@ -109,15 +130,19 @@ func handleListUsers(db *sql.DB) http.HandlerFunc {
var ts int64
var disabled *int64
if err := rows.Scan(&u.ID, &u.Username, &u.Email, &ts, &u.NtfyTopic, &u.IsAdmin, &u.AdminSource, &disabled); err != nil {
respond(w, http.StatusInternalServerError, errResp("internal error"))
serverError(w, r, err)
return
}
u.CreatedAt = time.Unix(ts, 0).UTC()
u.DisabledAt = unixPtr(disabled)
if !seeAll && u.ID != caller.ID {
u.Email = ""
u.NtfyTopic = nil
}
users = append(users, u)
}
if err := rows.Err(); err != nil {
respond(w, http.StatusInternalServerError, errResp("internal error"))
serverError(w, r, err)
return
}
respond(w, http.StatusOK, users)
@@ -147,7 +172,7 @@ func handleCreateUser(db *sql.DB) http.HandlerFunc {
respond(w, http.StatusConflict, errResp("username or email already exists"))
return
}
respond(w, http.StatusInternalServerError, errResp("internal error"))
serverError(w, r, err)
return
}
user, _ := fetchUser(r.Context(), db, id)
@@ -185,7 +210,7 @@ func handleSetNotifyTarget(db *sql.DB) http.HandlerFunc {
res, err := db.ExecContext(r.Context(),
"UPDATE users SET ntfy_topic = $1 WHERE id = $2", topic, id)
if err != nil {
respond(w, http.StatusInternalServerError, errResp("internal error"))
serverError(w, r, err)
return
}
if n, _ := res.RowsAffected(); n == 0 {
@@ -195,7 +220,7 @@ func handleSetNotifyTarget(db *sql.DB) http.HandlerFunc {
user, err := fetchUser(r.Context(), db, id)
if err != nil {
respond(w, http.StatusInternalServerError, errResp("internal error"))
serverError(w, r, err)
return
}
respond(w, http.StatusOK, user)
@@ -217,7 +242,7 @@ func handleDeleteUser(db *sql.DB) http.HandlerFunc {
return
}
if last, err := isLastAdmin(r.Context(), db, id); err != nil {
respond(w, http.StatusInternalServerError, errResp("internal error"))
serverError(w, r, err)
return
} else if last {
respond(w, http.StatusConflict, errResp("cannot delete the last administrator"))
@@ -226,7 +251,7 @@ func handleDeleteUser(db *sql.DB) http.HandlerFunc {
res, err := db.ExecContext(r.Context(), "DELETE FROM users WHERE id = $1", id)
if err != nil {
respond(w, http.StatusInternalServerError, errResp("internal error"))
serverError(w, r, err)
return
}
n, _ := res.RowsAffected()
@@ -283,7 +308,7 @@ func handleCreateAPIKey(db *sql.DB) http.HandlerFunc {
raw, hash, err := randomToken()
if err != nil {
respond(w, http.StatusInternalServerError, errResp("internal error"))
serverError(w, r, err)
return
}
var expiresAt *int64
@@ -298,7 +323,7 @@ func handleCreateAPIKey(db *sql.DB) http.HandlerFunc {
if err := db.QueryRowContext(r.Context(),
"INSERT INTO api_keys (user_id, key_hash, name, expires_at) VALUES ($1, $2, $3, $4) RETURNING id",
userID, hash, req.Name, expiresAt).Scan(&keyID); err != nil {
respond(w, http.StatusInternalServerError, errResp("internal error"))
serverError(w, r, err)
return
}
key := models.APIKey{
@@ -329,7 +354,7 @@ func handleListAPIKeys(db *sql.DB) http.HandlerFunc {
`SELECT id, name, created_at, last_used_at, expires_at
FROM api_keys WHERE user_id = $1 ORDER BY created_at DESC`, userID)
if err != nil {
respond(w, http.StatusInternalServerError, errResp("internal error"))
serverError(w, r, err)
return
}
defer rows.Close()
@@ -340,7 +365,7 @@ func handleListAPIKeys(db *sql.DB) http.HandlerFunc {
var created int64
var lastUsed, expires *int64
if err := rows.Scan(&k.ID, &k.Name, &created, &lastUsed, &expires); err != nil {
respond(w, http.StatusInternalServerError, errResp("internal error"))
serverError(w, r, err)
return
}
k.UserID = userID
@@ -350,7 +375,7 @@ func handleListAPIKeys(db *sql.DB) http.HandlerFunc {
keys = append(keys, k)
}
if err := rows.Err(); err != nil {
respond(w, http.StatusInternalServerError, errResp("internal error"))
serverError(w, r, err)
return
}
respond(w, http.StatusOK, keys)
@@ -376,7 +401,7 @@ func handleDeleteAPIKey(db *sql.DB) http.HandlerFunc {
res, err := db.ExecContext(r.Context(),
"DELETE FROM api_keys WHERE id = $1 AND user_id = $2", keyID, userID)
if err != nil {
respond(w, http.StatusInternalServerError, errResp("internal error"))
serverError(w, r, err)
return
}
n, _ := res.RowsAffected()
@@ -442,7 +467,7 @@ func handleSetAdmin(db *sql.DB) http.HandlerFunc {
if err := db.QueryRowContext(r.Context(),
"SELECT EXISTS (SELECT 1 FROM users WHERE id = $1 AND is_admin AND admin_source = 'oidc')",
id).Scan(&managed); err != nil {
respond(w, http.StatusInternalServerError, errResp("internal error"))
serverError(w, r, err)
return
}
if managed {
@@ -456,7 +481,7 @@ func handleSetAdmin(db *sql.DB) http.HandlerFunc {
return
}
if last, err := isLastAdmin(r.Context(), db, id); err != nil {
respond(w, http.StatusInternalServerError, errResp("internal error"))
serverError(w, r, err)
return
} else if last {
respond(w, http.StatusConflict, errResp("cannot revoke the last administrator"))
@@ -467,7 +492,7 @@ func handleSetAdmin(db *sql.DB) http.HandlerFunc {
res, err := db.ExecContext(r.Context(),
"UPDATE users SET is_admin = $1 WHERE id = $2", *req.IsAdmin, id)
if err != nil {
respond(w, http.StatusInternalServerError, errResp("internal error"))
serverError(w, r, err)
return
}
if n, _ := res.RowsAffected(); n == 0 {
@@ -477,7 +502,7 @@ func handleSetAdmin(db *sql.DB) http.HandlerFunc {
user, err := fetchUser(r.Context(), db, id)
if err != nil {
respond(w, http.StatusInternalServerError, errResp("internal error"))
serverError(w, r, err)
return
}
respond(w, http.StatusOK, user)