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
+34 -8
View File
@@ -3,6 +3,7 @@ package api
import (
"context"
"database/sql"
"errors"
"log"
"net/http"
"strconv"
@@ -343,12 +344,12 @@ func handleGetEscalation(db *sql.DB) http.HandlerFunc {
policy, err := loadEscalationPolicy(r.Context(), db, teamID)
if err != nil {
respond(w, http.StatusInternalServerError, errResp("internal error"))
serverError(w, r, err)
return
}
view, err := escalationStatus(r.Context(), db, teamID, policy)
if err != nil {
respond(w, http.StatusInternalServerError, errResp("internal error"))
serverError(w, r, err)
return
}
respond(w, http.StatusOK, view)
@@ -543,6 +544,10 @@ type escalationLevelJSON struct {
type escalationTargetJSON struct {
Kind string `json:"kind"`
UserID *int64 `json:"user_id,omitempty"`
// Username is accepted in place of user_id on a PUT, and resolved to the
// id before anything is stored. It is never returned: the stored form is
// the id, which survives a rename.
Username string `json:"username,omitempty"`
}
type escalationJSON struct {
@@ -600,6 +605,27 @@ func handleSetEscalation(db *sql.DB) http.HandlerFunc {
return
}
for i, l := range req.Levels {
for j, t := range l.Targets {
if t.Username == "" {
continue
}
if t.Kind != "user" || t.UserID != nil {
respond(w, http.StatusBadRequest, errResp("username belongs on a user target, instead of user_id"))
return
}
var id int64
err := db.QueryRowContext(r.Context(), "SELECT id FROM users WHERE username = $1", t.Username).Scan(&id)
if errors.Is(err, sql.ErrNoRows) {
respond(w, http.StatusBadRequest, errResp("unknown user "+strconv.Quote(t.Username)))
return
}
if err != nil {
serverError(w, r, err)
return
}
req.Levels[i].Targets[j].UserID = &id
req.Levels[i].Targets[j].Username = ""
}
if l.TimeoutSeconds <= 0 {
respond(w, http.StatusBadRequest, errResp("every level needs a timeout"))
return
@@ -632,7 +658,7 @@ func handleSetEscalation(db *sql.DB) http.HandlerFunc {
tx, err := db.BeginTx(r.Context(), nil)
if err != nil {
respond(w, http.StatusInternalServerError, errResp("internal error"))
serverError(w, r, err)
return
}
defer tx.Rollback() //nolint:errcheck
@@ -645,13 +671,13 @@ func handleSetEscalation(db *sql.DB) http.HandlerFunc {
fallback_topic = excluded.fallback_topic,
updated_at = excluded.updated_at`,
teamID, req.RepeatCount, req.FallbackTopic); err != nil {
respond(w, http.StatusInternalServerError, errResp("internal error"))
serverError(w, r, err)
return
}
// The levels are replaced, not merged; the cascade takes the targets.
if _, err := tx.ExecContext(r.Context(),
"DELETE FROM escalation_levels WHERE team_id = $1", teamID); err != nil {
respond(w, http.StatusInternalServerError, errResp("internal error"))
serverError(w, r, err)
return
}
@@ -661,7 +687,7 @@ func handleSetEscalation(db *sql.DB) http.HandlerFunc {
INSERT INTO escalation_levels (team_id, position, timeout_seconds)
VALUES ($1, $2, $3) RETURNING id`,
teamID, int64(i+1), l.TimeoutSeconds).Scan(&levelID); err != nil {
respond(w, http.StatusInternalServerError, errResp("internal error"))
serverError(w, r, err)
return
}
for _, t := range l.Targets {
@@ -676,13 +702,13 @@ func handleSetEscalation(db *sql.DB) http.HandlerFunc {
}
if err := tx.Commit(); err != nil {
respond(w, http.StatusInternalServerError, errResp("internal error"))
serverError(w, r, err)
return
}
policy, err := loadEscalationPolicy(r.Context(), db, teamID)
if err != nil {
respond(w, http.StatusInternalServerError, errResp("internal error"))
serverError(w, r, err)
return
}
respond(w, http.StatusOK, escalationResponse(policy, teamID))