Scope everything to a team, and route alerts by integration key

The core of #4, and what #1 is for: terdut stops being one shared space. A team owns its incidents, alerts, schedule and integrations; a user sees exactly the teams they are in. Everything that existed moves into one Default team and every existing user becomes an owner of it, so the upgrade is a no-op for the people using it. Ingestion is the load-bearing half. An alert arrives on a team's integration key, and the key is both the credential and the routing: it says that the sender may post, and which team the alerts belong to. That also closes the unauthenticated webhook -- the old path stays for one release, deprecated and routed to the oldest team, so an upgrade does not stop delivering while somebody edits the Alertmanager config. Scoping is enforced in as few places as possible, because the failure mode is silent. serveAs loads the caller's memberships once; list queries carry `team_id = ANY(...)`; and every incident route goes through incidentIDParam, which now parses the id AND checks the team in the same call, so a new handler cannot remember the first half and forget the second. Anything in another team is 404, never 403: whether an incident exists is that team's business. Two bugs this found, both of which would have been silent: * upsertAlerts decided "is this a new occurrence" by looking up the fingerprint alone. Across teams that made team B's first alert look like a re-send of team A's, so it opened no incident at all. The lookups are keyed on (team_id, fingerprint) now, as the index is. * Every uniqueness rule was written for one tenant. Two teams watching two clusters legitimately see the same fingerprint, the same groupKey, and want somebody on call on the same day; all three constraints move to include team_id. Roles inside a team are separate from the system administrator flag: an owner configures the team, a member works its incidents, and an admin is NOT implicitly in every team -- administration is about accounts, not about reading other people's incidents. An admin can still repair a team whose owner has left, which is why requireTeamOwner lets them through. A shift can only be given to somebody in the team. Paging a person who cannot open the incident is worse than paging nobody. The UI is updated only as far as keeping it working: it loads the viewer's teams with the session and uses the first one, since nobody has a second yet. "On call now" shows every team the viewer is in, named only when there is more than one, so the common case reads exactly as before. The team switcher, badges and per-team settings pages are the next step. Breaking for API clients: the schedule endpoints moved under the team, and /api/schedule/current returns an array rather than an object or a 404. terdut-tui will need a version for that. Per-team dead-man configuration is deliberately not here. A heartbeat's incident already opens in the team whose key received it, which is the part that matters for isolation; moving the matchers out of env into per-team rows is a change to how deadman.go is configured rather than to who sees what. Claude-Session: https://claude.ai/code/session_01RHPj4ggeFdEjKKfm4SHbD7
2026-09-20 13:36:24 +02:00
parent 1377d9005b
commit a4fbd60441
27 changed files with 1549 additions and 150 deletions
@@ -0,0 +1,473 @@
+package api
+
+import (
+	"context"
+	"database/sql"
+	"errors"
+	"net/http"
+	"strconv"
+	"strings"
+	"time"
+
+	"git.ryuvia.com/niklas/terdut-server/internal/models"
+	"github.com/go-chi/chi/v5"
+)
+
+// handleListTeams lists the caller's own teams, each with their role in it. An
+// administrator listing every team goes through the admin endpoint instead:
+// this one answers "what am I part of", which is what the UI's team filter and
+// the combined queue are built from.
+func handleListTeams(db *sql.DB) http.HandlerFunc {
+	return func(w http.ResponseWriter, r *http.Request) {
+		caller, _ := userFromContext(r.Context())
+		rows, err := db.QueryContext(r.Context(), `
+			SELECT t.id, t.name, t.created_at, m.role
+			FROM   teams t
+			JOIN   team_members m ON m.team_id = t.id
+			WHERE  m.user_id = $1
+			ORDER  BY t.name`, caller.ID)
+		if err != nil {
+			respond(w, http.StatusInternalServerError, errResp("internal error"))
+			return
+		}
+		defer rows.Close()
+
+		teams := []models.Team{}
+		for rows.Next() {
+			var t models.Team
+			var created int64
+			if err := rows.Scan(&t.ID, &t.Name, &created, &t.Role); err != nil {
+				respond(w, http.StatusInternalServerError, errResp("internal error"))
+				return
+			}
+			t.CreatedAt = time.Unix(created, 0).UTC()
+			teams = append(teams, t)
+		}
+		if err := rows.Err(); err != nil {
+			respond(w, http.StatusInternalServerError, errResp("internal error"))
+			return
+		}
+		respond(w, http.StatusOK, teams)
+	}
+}
+
+// handleCreateTeam creates a team and makes its creator the first owner. A team
+// with no owner would need an administrator to repair before anybody could use
+// it, so the two happen in one transaction.
+func handleCreateTeam(db *sql.DB) http.HandlerFunc {
+	return func(w http.ResponseWriter, r *http.Request) {
+		var req struct {
+			Name string `json:"name"`
+		}
+		if err := decodeJSON(r, &req); err != nil {
+			respond(w, http.StatusBadRequest, errResp("invalid request body"))
+			return
+		}
+		req.Name = strings.TrimSpace(req.Name)
+		if req.Name == "" {
+			respond(w, http.StatusBadRequest, errResp("name is required"))
+			return
+		}
+
+		caller, _ := userFromContext(r.Context())
+
+		tx, err := db.BeginTx(r.Context(), nil)
+		if err != nil {
+			respond(w, http.StatusInternalServerError, errResp("internal error"))
+			return
+		}
+		defer tx.Rollback() //nolint:errcheck
+
+		var team models.Team
+		var created int64
+		if err := tx.QueryRowContext(r.Context(),
+			"INSERT INTO teams (name) VALUES ($1) RETURNING id, name, created_at",
+			req.Name).Scan(&team.ID, &team.Name, &created); err != nil {
+			if isUniqueViolation(err) {
+				respond(w, http.StatusConflict, errResp("a team with that name already exists"))
+				return
+			}
+			respond(w, http.StatusInternalServerError, errResp("internal error"))
+			return
+		}
+		if _, err := tx.ExecContext(r.Context(),
+			"INSERT INTO team_members (team_id, user_id, role) VALUES ($1, $2, $3)",
+			team.ID, caller.ID, models.RoleOwner); err != nil {
+			respond(w, http.StatusInternalServerError, errResp("internal error"))
+			return
+		}
+		if err := tx.Commit(); err != nil {
+			respond(w, http.StatusInternalServerError, errResp("internal error"))
+			return
+		}
+
+		team.CreatedAt = time.Unix(created, 0).UTC()
+		team.Role = models.RoleOwner
+		respond(w, http.StatusCreated, team)
+	}
+}
+
+// handleDeleteTeam removes a team and, by cascade, its incidents, alerts,
+// schedule and integrations.
+//
+// Refused while the team still has open incidents: deleting a team is tidying
+// up, and tidying up should never be how an unacknowledged page disappears.
+// Resolve or archive them first, deliberately.
+func handleDeleteTeam(db *sql.DB) http.HandlerFunc {
+	return func(w http.ResponseWriter, r *http.Request) {
+		teamID, ok := teamParam(w, r)
+		if !ok {
+			return
+		}
+		if !requireTeamOwner(w, r, teamID) {
+			return
+		}
+
+		var open int
+		if err := db.QueryRowContext(r.Context(),
+			"SELECT COUNT(*) FROM incidents WHERE team_id = $1 AND resolved_at IS NULL", teamID).
+			Scan(&open); err != nil {
+			respond(w, http.StatusInternalServerError, errResp("internal error"))
+			return
+		}
+		if open > 0 {
+			respond(w, http.StatusConflict, errResp("team still has open incidents"))
+			return
+		}
+
+		res, err := db.ExecContext(r.Context(), "DELETE FROM teams WHERE id = $1", teamID)
+		if err != nil {
+			respond(w, http.StatusInternalServerError, errResp("internal error"))
+			return
+		}
+		if n, _ := res.RowsAffected(); n == 0 {
+			respond(w, http.StatusNotFound, errResp("not found"))
+			return
+		}
+		w.WriteHeader(http.StatusNoContent)
+	}
+}
+
+// handleListTeamMembers names everybody in a team. Visible to any member: you
+// can see who else is on the rota you are on.
+func handleListTeamMembers(db *sql.DB) http.HandlerFunc {
+	return func(w http.ResponseWriter, r *http.Request) {
+		teamID, ok := teamParam(w, r)
+		if !ok {
+			return
+		}
+		if !requireTeamMember(w, r, teamID) {
+			return
+		}
+
+		rows, err := db.QueryContext(r.Context(), `
+			SELECT m.team_id, m.user_id, u.username, m.role, m.joined_at
+			FROM   team_members m
+			JOIN   users u ON u.id = m.user_id
+			WHERE  m.team_id = $1
+			ORDER  BY u.username`, teamID)
+		if err != nil {
+			respond(w, http.StatusInternalServerError, errResp("internal error"))
+			return
+		}
+		defer rows.Close()
+
+		members := []models.TeamMember{}
+		for rows.Next() {
+			var m models.TeamMember
+			var joined int64
+			if err := rows.Scan(&m.TeamID, &m.UserID, &m.Username, &m.Role, &joined); err != nil {
+				respond(w, http.StatusInternalServerError, errResp("internal error"))
+				return
+			}
+			m.JoinedAt = time.Unix(joined, 0).UTC()
+			members = append(members, m)
+		}
+		if err := rows.Err(); err != nil {
+			respond(w, http.StatusInternalServerError, errResp("internal error"))
+			return
+		}
+		respond(w, http.StatusOK, members)
+	}
+}
+
+// handleAddTeamMember adds a user to a team, or changes the role of somebody
+// already in it.
+func handleAddTeamMember(db *sql.DB) http.HandlerFunc {
+	return func(w http.ResponseWriter, r *http.Request) {
+		teamID, ok := teamParam(w, r)
+		if !ok {
+			return
+		}
+		if !requireTeamOwner(w, r, teamID) {
+			return
+		}
+
+		var req struct {
+			UserID int64  `json:"user_id"`
+			Role   string `json:"role"`
+		}
+		if err := decodeJSON(r, &req); err != nil || req.UserID == 0 {
+			respond(w, http.StatusBadRequest, errResp("user_id is required"))
+			return
+		}
+		if req.Role == "" {
+			req.Role = models.RoleMember
+		}
+		if req.Role != models.RoleOwner && req.Role != models.RoleMember {
+			respond(w, http.StatusBadRequest, errResp("role must be owner or member"))
+			return
+		}
+
+		_, err := db.ExecContext(r.Context(), `
+			INSERT INTO team_members (team_id, user_id, role)
+			VALUES ($1, $2, $3)
+			ON CONFLICT (team_id, user_id) DO UPDATE SET role = excluded.role`,
+			teamID, req.UserID, req.Role)
+		if err != nil {
+			// The only foreign key that can fail here is the user: the team was
+			// resolved from the caller's own membership.
+			respond(w, http.StatusNotFound, errResp("user not found"))
+			return
+		}
+		w.WriteHeader(http.StatusNoContent)
+	}
+}
+
+// handleRemoveTeamMember takes a user out of a team.
+//
+// A team must keep an owner, for the same reason the install must keep an
+// administrator: otherwise nobody can configure it, and repairing that needs
+// somebody with more access than the team has.
+func handleRemoveTeamMember(db *sql.DB) http.HandlerFunc {
+	return func(w http.ResponseWriter, r *http.Request) {
+		teamID, ok := teamParam(w, r)
+		if !ok {
+			return
+		}
+		if !requireTeamOwner(w, r, teamID) {
+			return
+		}
+		userID, err := strconv.ParseInt(chi.URLParam(r, "userID"), 10, 64)
+		if err != nil {
+			respond(w, http.StatusBadRequest, errResp("invalid user id"))
+			return
+		}
+
+		last, err := isLastTeamOwner(r.Context(), db, teamID, userID)
+		if err != nil {
+			respond(w, http.StatusInternalServerError, errResp("internal error"))
+			return
+		}
+		if last {
+			respond(w, http.StatusConflict, errResp("cannot remove the last owner of a team"))
+			return
+		}
+
+		res, err := db.ExecContext(r.Context(),
+			"DELETE FROM team_members WHERE team_id = $1 AND user_id = $2", teamID, userID)
+		if err != nil {
+			respond(w, http.StatusInternalServerError, errResp("internal error"))
+			return
+		}
+		if n, _ := res.RowsAffected(); n == 0 {
+			respond(w, http.StatusNotFound, errResp("not a member of this team"))
+			return
+		}
+		w.WriteHeader(http.StatusNoContent)
+	}
+}
+
+func isLastTeamOwner(ctx context.Context, db *sql.DB, teamID, userID int64) (bool, error) {
+	var last bool
+	err := db.QueryRowContext(ctx, `
+		SELECT EXISTS (SELECT 1 FROM team_members
+		                WHERE team_id = $1 AND user_id = $2 AND role = 'owner')
+		   AND NOT EXISTS (SELECT 1 FROM team_members
+		                    WHERE team_id = $1 AND user_id <> $2 AND role = 'owner')`,
+		teamID, userID).Scan(&last)
+	return last, err
+}
+
+// ---------------------------------------------------------------------------
+// Integrations
+// ---------------------------------------------------------------------------
+
+// handleListIntegrations lists a team's integrations. Never the keys: those
+// exist in plaintext only in the response that created them.
+func handleListIntegrations(db *sql.DB) http.HandlerFunc {
+	return func(w http.ResponseWriter, r *http.Request) {
+		teamID, ok := teamParam(w, r)
+		if !ok {
+			return
+		}
+		if !requireTeamMember(w, r, teamID) {
+			return
+		}
+
+		rows, err := db.QueryContext(r.Context(), `
+			SELECT id, team_id, kind, name, created_at, last_used_at
+			FROM   integrations
+			WHERE  team_id = $1
+			ORDER  BY id`, teamID)
+		if err != nil {
+			respond(w, http.StatusInternalServerError, errResp("internal error"))
+			return
+		}
+		defer rows.Close()
+
+		integrations := []models.Integration{}
+		for rows.Next() {
+			var i models.Integration
+			var created int64
+			var lastUsed *int64
+			if err := rows.Scan(&i.ID, &i.TeamID, &i.Kind, &i.Name, &created, &lastUsed); err != nil {
+				respond(w, http.StatusInternalServerError, errResp("internal error"))
+				return
+			}
+			i.CreatedAt = time.Unix(created, 0).UTC()
+			i.LastUsedAt = unixPtr(lastUsed)
+			integrations = append(integrations, i)
+		}
+		if err := rows.Err(); err != nil {
+			respond(w, http.StatusInternalServerError, errResp("internal error"))
+			return
+		}
+		respond(w, http.StatusOK, integrations)
+	}
+}
+
+// handleCreateIntegration mints an integration key. The key is returned once,
+// in this response, and only its hash is kept — the same handling as an API key
+// or an acknowledgement token.
+func handleCreateIntegration(db *sql.DB, publicURL string) http.HandlerFunc {
+	return func(w http.ResponseWriter, r *http.Request) {
+		teamID, ok := teamParam(w, r)
+		if !ok {
+			return
+		}
+		if !requireTeamOwner(w, r, teamID) {
+			return
+		}
+
+		var req struct {
+			Name string `json:"name"`
+			Kind string `json:"kind"`
+		}
+		if err := decodeJSON(r, &req); err != nil {
+			respond(w, http.StatusBadRequest, errResp("invalid request body"))
+			return
+		}
+		req.Name = strings.TrimSpace(req.Name)
+		if req.Name == "" {
+			respond(w, http.StatusBadRequest, errResp("name is required"))
+			return
+		}
+		if req.Kind == "" {
+			req.Kind = models.IntegrationAlertmanager
+		}
+		if req.Kind != models.IntegrationAlertmanager {
+			respond(w, http.StatusBadRequest, errResp("unsupported integration kind"))
+			return
+		}
+
+		raw, hash, err := randomToken()
+		if err != nil {
+			respond(w, http.StatusInternalServerError, errResp("internal error"))
+			return
+		}
+
+		var i models.Integration
+		var created int64
+		if err := db.QueryRowContext(r.Context(), `
+			INSERT INTO integrations (team_id, kind, name, key_hash)
+			VALUES ($1, $2, $3, $4)
+			RETURNING id, team_id, kind, name, created_at`,
+			teamID, req.Kind, req.Name, hash).
+			Scan(&i.ID, &i.TeamID, &i.Kind, &i.Name, &created); err != nil {
+			respond(w, http.StatusInternalServerError, errResp("internal error"))
+			return
+		}
+		i.CreatedAt = time.Unix(created, 0).UTC()
+		i.Key = raw
+		i.URL = strings.TrimSuffix(publicURL, "/") + integrationPath(raw, i.Kind)
+		respond(w, http.StatusCreated, i)
+	}
+}
+
+func handleDeleteIntegration(db *sql.DB) http.HandlerFunc {
+	return func(w http.ResponseWriter, r *http.Request) {
+		teamID, ok := teamParam(w, r)
+		if !ok {
+			return
+		}
+		if !requireTeamOwner(w, r, teamID) {
+			return
+		}
+		id, err := strconv.ParseInt(chi.URLParam(r, "integrationID"), 10, 64)
+		if err != nil {
+			respond(w, http.StatusBadRequest, errResp("invalid integration id"))
+			return
+		}
+
+		res, err := db.ExecContext(r.Context(),
+			"DELETE FROM integrations WHERE id = $1 AND team_id = $2", id, teamID)
+		if err != nil {
+			respond(w, http.StatusInternalServerError, errResp("internal error"))
+			return
+		}
+		if n, _ := res.RowsAffected(); n == 0 {
+			respond(w, http.StatusNotFound, errResp("not found"))
+			return
+		}
+		w.WriteHeader(http.StatusNoContent)
+	}
+}
+
+// integrationPath is where a sender of this kind posts. Built in one place so
+// the URL handed out at creation and the route the router registers cannot
+// drift apart.
+func integrationPath(key, kind string) string {
+	return "/api/integrations/" + key + "/" + kind
+}
+
+// teamIDForKey resolves an integration key to its team, and stamps the key's
+// last use. An unknown key is not an error worth distinguishing: the caller is
+// told nothing beyond "no".
+func teamIDForKey(ctx context.Context, db *sql.DB, key string) (int64, error) {
+	var teamID int64
+	err := db.QueryRowContext(ctx,
+		"SELECT team_id FROM integrations WHERE key_hash = $1", hashToken(key)).Scan(&teamID)
+	if errors.Is(err, sql.ErrNoRows) {
+		return 0, errUnknownIntegration
+	}
+	if err != nil {
+		return 0, err
+	}
+	// Best effort, like an API key's: a failed stamp must not reject an alert.
+	db.ExecContext(ctx, //nolint:errcheck
+		"UPDATE integrations SET last_used_at = $1 WHERE key_hash = $2",
+		time.Now().Unix(), hashToken(key))
+	return teamID, nil
+}
+
+var errUnknownIntegration = errors.New("unknown integration key")
+
+// teamParam reads {teamID} from the path.
+func teamParam(w http.ResponseWriter, r *http.Request) (int64, bool) {
+	id, err := strconv.ParseInt(chi.URLParam(r, "teamID"), 10, 64)
+	if err != nil {
+		respond(w, http.StatusBadRequest, errResp("invalid team id"))
+		return 0, false
+	}
+	return id, true
+}
+
+// defaultTeamID is the team the deprecated unauthenticated webhook routes to:
+// the oldest one, which on an upgraded install is the "Default" team every
+// pre-teams row was moved into.
+func defaultTeamID(ctx context.Context, db *sql.DB) (int64, error) {
+	var id int64
+	err := db.QueryRowContext(ctx, "SELECT id FROM teams ORDER BY id LIMIT 1").Scan(&id)
+	return id, err
+}