mirror of
https://github.com/J3vb/OwnCord.git
synced 2026-09-03 03:50:00 +03:00
* docs: add infrastructure roadmap plan Records the verified recommendations from an infrastructure review in three tracks: raising the single-instance ceiling, cheap seams for a possible multi-instance future, and ops hygiene. Includes explicit anti-recommendations and sequencing. Security-sensitive detail is intentionally excluded per docs/security.md. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_017RtDNHSYWwPKArL8MsRdbj * feat(server): real health checks and saturation metrics /api/v1/metrics now exposes signals that were already computed in memory but never surfaced: reconnect replay tier hits, event-persister counters, SQLite writer-pool wait stats, aggregate per-client backpressure counters (including previously invisible low-priority drops), and permission-cache hit/miss. /health now returns a real verdict: hub dispatch-loop liveness, a bounded database ping, and a free-disk check, returning 503 with a subsystem reason when degraded. Checks are cached so the unauthenticated endpoint cannot amplify load. The hub's panic breaker now exits the process so a supervisor can restart it, instead of leaving broadcast delivery silently dead while clients still appear online. OTel instruments that were declared but never recorded are now wired (ws_active_connections, ws_broadcast_latency_seconds, ws_messages_total, ws_events_dropped_total, voice gauges) or removed (db_query_duration_seconds). Also corrects the docs/api.md description of broadcast_drops, which counts hub-queue overflow, not client send-queue overflow. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_017RtDNHSYWwPKArL8MsRdbj * feat(server): implement scheduled backups, retention, and backup verification The backup_schedule and backup_retention settings have existed in the admin panel and API since the initial schema but were never read by any code. The 15-minute maintenance loop now enforces them: a scheduled backup is taken when the newest backup on disk is older than the schedule interval (manual backups reset the clock), and retention prunes backups older than the configured days while always keeping the newest one. Backups are now verified with PRAGMA integrity_check immediately after VACUUM INTO (a failed backup is removed rather than listed as restorable) and again before a restore may overwrite the live database. A failed VACUUM INTO also cleans up its partial output file — but never a pre-existing one. The backup directory is configurable via a new backup.dir key (default data/backups) so operators can point backups at another disk or an off-host mount, mirroring the SetDatabasePath plumb. Restore-handler tests now use real SQLite fixtures (the integrity gate correctly refuses text files) with the mid-copy failure injected through a test-only copy hook. Also adds audited gosec suppressions to the Windows disk-free syscall added in the previous commit, which the Windows lint leg flagged. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_017RtDNHSYWwPKArL8MsRdbj * feat(server): capacity and failure-mode guardrails - server.max_ws_connections: optional cap on concurrent WebSocket clients, checked before the upgrade with a 503 + Retry-After; rejections are counted and exposed as ws_conn_rejects in /api/v1/metrics. - Single-process database lock: an OS-level advisory lock (flock / exclusive handle) beside the SQLite file makes a second server process fail fast with a clear message instead of silently fighting the first over process-local state. A bounded retry covers the self-update/restore restart handoff, and the lock mechanism failing (e.g. network filesystems) only warns. - Disk-space awareness: boot-time warnings for the data and backup volumes, plus a disk_free_mb metrics field, via a small cross-platform diskutil package (already used by /health). - Upload storage failures: storage.Save now marks server-side filesystem failures with a sentinel (storage.ErrIO); handlers return 507 for those instead of blaming the client with a 400, and the emoji route stops echoing raw storage errors (which embed absolute paths) into responses. - Unknown config keys now warn at startup — a typo like admin_alowed_cidrs previously kept the default silently while the operator believed the setting changed. Never fatal: newer servers tolerate older configs. - Admin settings honesty: the three stored-but-inert settings (server_icon, max_upload_bytes, voice_quality) are shown read-only with a note pointing at the real config.yaml keys, instead of pretending to apply. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_017RtDNHSYWwPKArL8MsRdbj * perf(db): write-path efficiency and capacity knobs - channel_focus/mark_read now skip the read-state UPSERT when the stored row already matches (same last_message_id, no mentions) — refocus events fire at up to 10/s/user and every no-op write still occupied the single SQLite writer connection. The extra existence check runs on the reader pool, which doesn't serialize. Same shape as the session-touch throttle. - DeleteExpiredSessions is now sargable: migration 031 normalizes legacy expiry formats to the RFC3339-Z layout the server writes and indexes expires_at, replacing the strftime full-table scan that ran on the writer every 15 minutes. - Boot-time ANALYZE runs only when a migration actually applied; unchanged schemas get the cheap PRAGMA optimize instead (which also covers crash-restarts that never reached the shutdown optimize). - The read/write SQL router gets a table-driven test with explicit expected values (INSERT ... RETURNING must hit the writer despite being :one). - New knobs, all defaulting to current behavior: database.max_readers, security.auth_rate_limit_multiplier (for shared-NAT communities), event_persistence.replay_ring_size and replay_cold_limit. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_017RtDNHSYWwPKArL8MsRdbj * fix(server): shutdown lifecycle ordering - The event pruner and maintenance loop are now joined (bounded) before the database closes: bgCtx cancellation used to run AFTER database.Close via LIFO defers, contradicting its own comment, and neither goroutine was ever waited on — a mid-tick scheduled backup or prune could still hold the writer while the pool tore down. StartEventPruner returns a done channel with the same join contract EventPersister.Stop already had. - srv.Shutdown now runs before hub.GracefulStop, so in-flight HTTP handlers' broadcasts still reach a live hub and the event persister instead of vanishing from the replay/event store across a restart. Shutdown does not wait on hijacked WebSocket connections, so the swap adds no delay. - GracefulStopContext threads the 30s shutdown budget into the hub: the 5s client-notice window (matching the countdown clients are shown) ends early when the budget expires, and is skipped entirely when nobody is connected — early-return startup paths and idle servers no longer sleep 5s for an audience of zero. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_017RtDNHSYWwPKArL8MsRdbj * build(deploy): systemd unit, compose hardening, boot-smoked releases, CI polish - deploy/owncord.service: hardened systemd unit template with the two verified caveats encoded (install dir stays writable for self-update under ProtectSystem=strict; CAP_NET_BIND_SERVICE for ACME's :80), plus a 'Linux (systemd)' deployment docs section — the Linux service story was previously 'Docker or nothing'. - New 'Reverse Proxy Topology' docs section with a working nginx snippet and the correct signaling-vs-media distinction: /livekit/* is already proxied by the server, only WebRTC media ports must be directly reachable. - docker-compose: log rotation, commented resource limits, and a healthcheck backed by a new 'chatserver healthcheck' subcommand (the distroless image has no shell) that probes /health without config side effects. - release.yml: a concurrency group (queue, never cancel), and boot-smoke gates — the freshly built server binaries and the Docker image are cold booted and probed healthy BEFORE anything is signed or pushed. The release feed drives signed self-updates, so a binary that compiles but dies on boot previously would have shipped itself to every auto-updating instance. - ci.yml: client-check/client-tests move to ubuntu with the reasoning recorded (no win32 code paths, LF enforced repo-wide); admin-e2e gets a written graduation criterion instead of an open-ended non-blocking status. - docs: Tailscale guide notes the CGNAT range vs the default admin CIDRs; architecture overview records presence/voice state as the fifth single-instance blocker and the macOS client scope decision. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_017RtDNHSYWwPKArL8MsRdbj * perf(server): measured load tooling, narrowed invalidation, presence coalescing, storage and CIDR seams - Fix scripts/k6/ws-load.js against the real wire protocol: envelope-wrapped frames, correct message types (typing_start, presence_update), the correct /api/v1/ws path, and thresholds that fail a run where nobody authenticated or went ready — the script had drifted to pre-envelope framing and reported 100% green while every auth failed on the first frame. A new workflow_dispatch-only load-baseline workflow boots a real server, seeds users through the setup/invite APIs, runs the script, and uploads the k6 summary plus a metrics snapshot for before/after comparison. - Role-scoped channel-override changes now evict only the affected role's members from the permission cache (fail-safe: unreadable member list still flushes everything). InvalidateAll here repopulated every connected user — two reads each — synchronously inside the admin request via RefreshChannelVisibility, a stampede that scaled with total population rather than the role's size. Same pattern the per-user override endpoints already used. - Connect/disconnect presence broadcasts now pass through a 300ms latest-wins coalescer (QueuePresence): each un-coalesced presence change is a sequenced global broadcast (an O(clients) fan-out under seqMu), so a reconnect storm fired O(users) of them from the connect critical path. A flap inside the window collapses to its final state; the wire format, seq ordering, and replay behaviour are unchanged, and the delivery path (BroadcastPresence) is untouched. - Storage seam: api handlers now consume a FileStore interface (consumer-side, same pattern as service.Store) with Open returning a seekable storage.File — writing down the contract (range-request seeks included) an alternative backend would have to meet, without building one. - The metrics surfaces and the LiveKit webhook/health endpoints get their own allowlist keys (metrics_allowed_cidrs, livekit_webhook_allowed_cidrs, both defaulting to admin_allowed_cidrs), so a central Prometheus scraper or an externally-hosted LiveKit no longer requires widening the admin panel's perimeter. Startup now also warns when admin_allowed_cidrs is customized while trusted_proxies is empty — behind a proxy or container network the check would otherwise compare the proxy's private address, not the client's. - The container healthcheck probe now PINS the server's own certificate from disk (VerifyConnection, exact-match) instead of skipping TLS verification, addressing the CodeQL finding on the previous commit; WebPKI verification is used when no local cert exists (ACME). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_017RtDNHSYWwPKArL8MsRdbj * fix(server): address self-review findings on the hardening branch Seven fixes from a high-effort review of the full branch diff: - healthcheck CLI now works under tls.mode acme: it overrides ServerName with the configured domain for WebPKI verification instead of pinning a cert that doesn't exist (or is stale) in that mode. Previously an ACME deployment's container healthcheck failed forever. - /health pings the READER pool (new db.PingRead): the writer ping queued behind a scheduled backup's VACUUM INTO and reported the server degraded for the whole backup — which an autoheal watchdog would turn into a nightly mid-backup restart. - /health runs its cached checks under context.WithoutCancel so a probe that disconnects mid-request cannot poison the shared cache with a false degraded verdict for the next 5 seconds. - The token CLI uses a new db.OpenShared that skips the single-process lock: minting a token against a running server is safe under WAL and was a documented workflow the lock had broken. - The per-user TOTP failure cap is no longer scaled by security.auth_rate_limit_multiplier — that knob exists for per-IP limits; scaling the only cross-IP brute-force defence multiplied an attacker's distributed guess budget. Mirrors the unscaled per-user login threshold. - A direct presence_update now drops the user's queued entry in the connect/disconnect coalescer, so a stale connect-time presence can no longer flush 300ms later over the user's fresher chosen status. - The scheduled-backup filename collision loop breaks on any stat error and bounds its suffix probing, instead of spinning the maintenance goroutine forever on a persistent EACCES. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_017RtDNHSYWwPKArL8MsRdbj * test(admin): real SQLite fixture for the merged Close-failure restore test TestHandleRestoreBackup_RestartsWhenCloseFails arrived from main (#1375) with a plain-text backup fixture; this branch's restore handler verifies backups with integrity_check before touching the live database, so the text fixture was (correctly) refused with 400 before the Close-failure branch under test was reached. Use a real backup via BackupToSafe, matching the other restore tests. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_017RtDNHSYWwPKArL8MsRdbj --------- Co-authored-by: Claude <noreply@anthropic.com>
465 lines
18 KiB
Go
465 lines
18 KiB
Go
package db
|
|
|
|
import (
|
|
"context"
|
|
"database/sql"
|
|
"errors"
|
|
"fmt"
|
|
"os"
|
|
"path/filepath"
|
|
"strings"
|
|
|
|
"github.com/owncord/server/db/dbgen"
|
|
)
|
|
|
|
// ─── Setup ───────────────────────────────────────────────────────────────────
|
|
|
|
// UserCount returns the total number of registered users.
|
|
func (d *DB) UserCount(ctx context.Context) (int64, error) {
|
|
count, err := d.q.UserCount(ctx)
|
|
if err != nil {
|
|
return 0, fmt.Errorf("UserCount: %w", err)
|
|
}
|
|
return count, nil
|
|
}
|
|
|
|
// ─── Server Stats ─────────────────────────────────────────────────────────────
|
|
|
|
// GetServerStats returns aggregate counts for the admin dashboard.
|
|
// DBSizeBytes is 0 for in-memory databases (page_count * page_size returns
|
|
// a meaningful value only for file-backed databases).
|
|
func (d *DB) GetServerStats(ctx context.Context) (*ServerStats, error) {
|
|
stats := &ServerStats{}
|
|
var err error
|
|
|
|
if stats.UserCount, err = d.q.CountUsers(ctx); err != nil {
|
|
return nil, fmt.Errorf("GetServerStats users: %w", err)
|
|
}
|
|
if stats.MessageCount, err = d.q.CountActiveMessages(ctx); err != nil {
|
|
return nil, fmt.Errorf("GetServerStats messages: %w", err)
|
|
}
|
|
if stats.ChannelCount, err = d.q.CountChannels(ctx); err != nil {
|
|
return nil, fmt.Errorf("GetServerStats channels: %w", err)
|
|
}
|
|
if stats.InviteCount, err = d.q.CountActiveInvites(ctx); err != nil {
|
|
return nil, fmt.Errorf("GetServerStats invites: %w", err)
|
|
}
|
|
|
|
// page_count * page_size gives the database size in bytes. PRAGMAs are not
|
|
// expressible as sqlc queries, so they stay on the raw connection.
|
|
// For :memory: databases this still works (returns the in-memory size).
|
|
// Both values are DB-wide, so reading them on the reader pool is fine.
|
|
var pageCount, pageSize int64
|
|
if err := d.reader.QueryRowContext(ctx, `PRAGMA page_count`).Scan(&pageCount); err != nil {
|
|
return nil, fmt.Errorf("GetServerStats page_count: %w", err)
|
|
}
|
|
if err := d.reader.QueryRowContext(ctx, `PRAGMA page_size`).Scan(&pageSize); err != nil {
|
|
return nil, fmt.Errorf("GetServerStats page_size: %w", err)
|
|
}
|
|
stats.DBSizeBytes = pageCount * pageSize
|
|
|
|
return stats, nil
|
|
}
|
|
|
|
// ─── User Management ──────────────────────────────────────────────────────────
|
|
|
|
// ListAllUsers returns users joined with their role name, ordered by ID.
|
|
// limit=0 returns no rows.
|
|
func (d *DB) ListAllUsers(ctx context.Context, limit, offset int) ([]UserWithRole, error) {
|
|
rows, err := d.q.ListAllUsers(ctx, dbgen.ListAllUsersParams{
|
|
Limit: int64(limit),
|
|
Offset: int64(offset),
|
|
})
|
|
if err != nil {
|
|
return nil, fmt.Errorf("ListAllUsers: %w", err)
|
|
}
|
|
result := make([]UserWithRole, 0, len(rows))
|
|
for _, r := range rows {
|
|
result = append(result, UserWithRole{
|
|
User: User{
|
|
ID: r.ID,
|
|
Username: r.Username,
|
|
Avatar: r.Avatar,
|
|
RoleID: r.RoleID,
|
|
Status: r.Status,
|
|
CreatedAt: r.CreatedAt,
|
|
LastSeen: r.LastSeen,
|
|
Banned: r.Banned != 0,
|
|
BanReason: r.BanReason,
|
|
BanExpires: r.BanExpires,
|
|
},
|
|
RoleName: r.RoleName,
|
|
})
|
|
}
|
|
return result, nil
|
|
}
|
|
|
|
// UpdateUserRole changes the role_id of a user.
|
|
func (d *DB) UpdateUserRole(ctx context.Context, userID, roleID int64) error {
|
|
if err := d.q.UpdateUserRole(ctx, dbgen.UpdateUserRoleParams{
|
|
RoleID: roleID,
|
|
ID: userID,
|
|
}); err != nil {
|
|
return fmt.Errorf("UpdateUserRole: %w", err)
|
|
}
|
|
return nil
|
|
}
|
|
|
|
// ForceLogoutUser deletes all sessions for the given user ID.
|
|
func (d *DB) ForceLogoutUser(ctx context.Context, userID int64) error {
|
|
if err := d.q.ForceLogoutUser(ctx, userID); err != nil {
|
|
return fmt.Errorf("ForceLogoutUser: %w", err)
|
|
}
|
|
return nil
|
|
}
|
|
|
|
// GetUserSessions returns all active sessions for the given user ID.
|
|
func (d *DB) GetUserSessions(ctx context.Context, userID int64) ([]Session, error) {
|
|
rows, err := d.q.GetUserSessions(ctx, userID)
|
|
if err != nil {
|
|
return nil, fmt.Errorf("GetUserSessions: %w", err)
|
|
}
|
|
sessions := make([]Session, 0, len(rows))
|
|
for _, s := range rows {
|
|
sessions = append(sessions, sessionFromGen(s))
|
|
}
|
|
return sessions, nil
|
|
}
|
|
|
|
// ─── Channel Management (admin) ───────────────────────────────────────────────
|
|
|
|
// AdminCreateChannel creates a channel with full field control including position.
|
|
// No sqlc query covers this exact INSERT shape, so it stays on raw SQL.
|
|
func (d *DB) AdminCreateChannel(ctx context.Context, name, chanType, category, topic string, position int) (int64, error) {
|
|
res, err := d.writer.ExecContext(ctx,
|
|
`INSERT INTO channels (name, type, category, topic, position)
|
|
VALUES (?, ?, ?, ?, ?)`,
|
|
name, chanType, strToNullPtr(category), strToNullPtr(topic), position,
|
|
)
|
|
if err != nil {
|
|
return 0, fmt.Errorf("AdminCreateChannel: %w", err)
|
|
}
|
|
return res.LastInsertId()
|
|
}
|
|
|
|
// ChannelUpdate is the full set of mutable channel fields an admin edit writes.
|
|
//
|
|
// A struct rather than a positional argument list: the update covers nine
|
|
// fields now, four of them ints, and `AdminUpdateChannel(ctx, id, name, topic,
|
|
// category, slowMode, position, archived, nsfw, maxUsers, maxVideo)` invites
|
|
// exactly the silent transposition (slow mode into user limit) that no test
|
|
// would catch. Every field is written unconditionally, so callers must start
|
|
// from the channel's current values — the handler does, which is what makes a
|
|
// partial PATCH body safe.
|
|
type ChannelUpdate struct {
|
|
Name string
|
|
Topic string
|
|
Category string
|
|
SlowMode int
|
|
Position int
|
|
Archived bool
|
|
// NSFW is stored and broadcast only; it drives no server-side content
|
|
// behaviour (see migration 025).
|
|
NSFW bool
|
|
// VoiceMaxUsers / VoiceMaxVideo are the voice capacity limits the ws
|
|
// voice-join path already enforces (0 = unlimited). They are meaningless
|
|
// on a text channel but are still written there, because refusing them
|
|
// would make the value depend on a type that can never change anyway.
|
|
VoiceMaxUsers int
|
|
VoiceMaxVideo int
|
|
}
|
|
|
|
// AdminUpdateChannel updates all mutable channel fields, category included —
|
|
// moving a channel between categories is a rename of free text, not a
|
|
// structural change, so it rides on the ordinary update.
|
|
func (d *DB) AdminUpdateChannel(ctx context.Context, id int64, u ChannelUpdate) error {
|
|
if err := d.q.AdminUpdateChannel(ctx, dbgen.AdminUpdateChannelParams{
|
|
Name: u.Name,
|
|
Topic: strToNullPtr(u.Topic),
|
|
Category: strToNullPtr(u.Category),
|
|
SlowMode: int64(u.SlowMode),
|
|
Position: int64(u.Position),
|
|
Archived: b2i64(u.Archived),
|
|
Nsfw: b2i64(u.NSFW),
|
|
VoiceMaxUsers: int64(u.VoiceMaxUsers),
|
|
VoiceMaxVideo: int64(u.VoiceMaxVideo),
|
|
ID: id,
|
|
}); err != nil {
|
|
return fmt.Errorf("AdminUpdateChannel: %w", err)
|
|
}
|
|
return nil
|
|
}
|
|
|
|
// AdminDeleteChannel removes a channel by ID (cascades to messages, etc.).
|
|
func (d *DB) AdminDeleteChannel(ctx context.Context, id int64) error {
|
|
if err := d.q.DeleteChannel(ctx, id); err != nil {
|
|
return fmt.Errorf("AdminDeleteChannel: %w", err)
|
|
}
|
|
return nil
|
|
}
|
|
|
|
// ─── Audit Log ────────────────────────────────────────────────────────────────
|
|
|
|
// LogAudit inserts an audit log entry.
|
|
func (d *DB) LogAudit(ctx context.Context, actorID int64, action, targetType string, targetID int64, detail string) error {
|
|
if err := d.q.LogAudit(ctx, dbgen.LogAuditParams{
|
|
ActorID: actorID,
|
|
Action: action,
|
|
TargetType: targetType,
|
|
TargetID: targetID,
|
|
Detail: detail,
|
|
}); err != nil {
|
|
return fmt.Errorf("LogAudit: %w", err)
|
|
}
|
|
return nil
|
|
}
|
|
|
|
// PersistAudits inserts a batch of audit entries in a single transaction with
|
|
// one prepared insert, so the audit writer's flush pays for one fsync instead
|
|
// of one per entry. Only the LogAudit-shaped fields are written — ID, ActorName
|
|
// and CreatedAt on the input rows are ignored (the id autoincrements, the
|
|
// created_at column defaults, and actor_name is a join product).
|
|
//
|
|
// Best-effort semantics mirror PersistEvents: if the batched transaction fails,
|
|
// it falls back to per-row inserts so the good rows still land. Returns the
|
|
// number of rows persisted and, when any row was lost, the first per-row error.
|
|
func (d *DB) PersistAudits(ctx context.Context, entries []AuditEntry) (int, error) {
|
|
if len(entries) == 0 {
|
|
return 0, nil
|
|
}
|
|
if err := d.persistAuditsTx(ctx, entries); err == nil {
|
|
return len(entries), nil
|
|
}
|
|
// Fallback: insert rows individually so one bad row doesn't drop the batch.
|
|
persisted := 0
|
|
var firstErr error
|
|
for _, e := range entries {
|
|
if err := d.LogAudit(ctx, e.ActorID, e.Action, e.TargetType, e.TargetID, e.Detail); err != nil {
|
|
if firstErr == nil {
|
|
firstErr = err
|
|
}
|
|
continue
|
|
}
|
|
persisted++
|
|
}
|
|
return persisted, firstErr
|
|
}
|
|
|
|
// persistAuditsTx inserts all entries inside one transaction; any failure
|
|
// rolls the whole batch back.
|
|
func (d *DB) persistAuditsTx(ctx context.Context, entries []AuditEntry) error {
|
|
tx, err := d.writer.BeginTx(ctx, nil)
|
|
if err != nil {
|
|
return fmt.Errorf("PersistAudits begin tx: %w", err)
|
|
}
|
|
stmt, err := tx.PrepareContext(ctx,
|
|
`INSERT INTO audit_log (actor_id, action, target_type, target_id, detail) VALUES (?, ?, ?, ?, ?)`,
|
|
)
|
|
if err != nil {
|
|
_ = tx.Rollback()
|
|
return fmt.Errorf("PersistAudits prepare: %w", err)
|
|
}
|
|
defer func() { _ = stmt.Close() }()
|
|
for _, e := range entries {
|
|
if _, err := stmt.ExecContext(ctx, e.ActorID, e.Action, e.TargetType, e.TargetID, e.Detail); err != nil {
|
|
_ = tx.Rollback()
|
|
return fmt.Errorf("PersistAudits insert action %q: %w", e.Action, err)
|
|
}
|
|
}
|
|
if err := tx.Commit(); err != nil {
|
|
return fmt.Errorf("PersistAudits commit: %w", err)
|
|
}
|
|
return nil
|
|
}
|
|
|
|
// GetAuditLog returns audit log entries ordered newest-first with pagination.
|
|
func (d *DB) GetAuditLog(ctx context.Context, limit, offset int) ([]AuditEntry, error) {
|
|
rows, err := d.q.GetAuditLog(ctx, dbgen.GetAuditLogParams{
|
|
Limit: int64(limit),
|
|
Offset: int64(offset),
|
|
})
|
|
if err != nil {
|
|
return nil, fmt.Errorf("GetAuditLog: %w", err)
|
|
}
|
|
entries := make([]AuditEntry, 0, len(rows))
|
|
for _, r := range rows {
|
|
entries = append(entries, AuditEntry{
|
|
ID: r.ID,
|
|
ActorID: r.ActorID,
|
|
ActorName: r.ActorName,
|
|
Action: r.Action,
|
|
TargetType: r.TargetType,
|
|
TargetID: r.TargetID,
|
|
Detail: r.Detail,
|
|
CreatedAt: r.CreatedAt,
|
|
})
|
|
}
|
|
return entries, nil
|
|
}
|
|
|
|
// ─── Settings ─────────────────────────────────────────────────────────────────
|
|
|
|
// GetSetting returns the value for the given settings key.
|
|
// Returns an error (wrapping sql.ErrNoRows) when the key does not exist.
|
|
func (d *DB) GetSetting(ctx context.Context, key string) (string, error) {
|
|
value, err := d.q.GetSetting(ctx, key)
|
|
if errors.Is(err, sql.ErrNoRows) {
|
|
return "", fmt.Errorf("GetSetting: key %q: %w", key, ErrNotFound)
|
|
}
|
|
if err != nil {
|
|
return "", fmt.Errorf("GetSetting: %w", err)
|
|
}
|
|
return value, nil
|
|
}
|
|
|
|
// SetSetting upserts a setting value for the given key.
|
|
func (d *DB) SetSetting(ctx context.Context, key, value string) error {
|
|
if err := d.q.SetSetting(ctx, dbgen.SetSettingParams{
|
|
Key: key,
|
|
Value: value,
|
|
}); err != nil {
|
|
return fmt.Errorf("SetSetting: %w", err)
|
|
}
|
|
return nil
|
|
}
|
|
|
|
// GetAllSettings returns all settings as a key→value map.
|
|
func (d *DB) GetAllSettings(ctx context.Context) (map[string]string, error) {
|
|
rows, err := d.q.GetAllSettings(ctx)
|
|
if err != nil {
|
|
return nil, fmt.Errorf("GetAllSettings: %w", err)
|
|
}
|
|
result := make(map[string]string, len(rows))
|
|
for _, s := range rows {
|
|
result[s.Key] = s.Value
|
|
}
|
|
return result, nil
|
|
}
|
|
|
|
// CountUsersWithoutTOTP returns the number of non-banned users that do not
|
|
// currently have a confirmed TOTP secret.
|
|
func (d *DB) CountUsersWithoutTOTP(ctx context.Context) (int, error) {
|
|
count, err := d.q.CountUsersWithoutTOTP(ctx)
|
|
if err != nil {
|
|
return 0, fmt.Errorf("CountUsersWithoutTOTP: %w", err)
|
|
}
|
|
return int(count), nil
|
|
}
|
|
|
|
// ─── Backup ───────────────────────────────────────────────────────────────────
|
|
|
|
// BackupTo creates an online backup of the database using SQLite's VACUUM INTO.
|
|
// The destination path must not already exist.
|
|
//
|
|
// Security: VACUUM INTO does not support bind parameters, so the path is
|
|
// interpolated into SQL. To prevent injection we enforce two structural guards:
|
|
// 1. The path must resolve to a location under safeRoot (after filepath.Clean
|
|
// and filepath.Abs).
|
|
// 2. After structural validation, any single-quote, semicolon, double-dash,
|
|
// or null byte in the cleaned path causes rejection as defence-in-depth.
|
|
//
|
|
// The caller in handleBackup constructs the path from a hardcoded directory
|
|
// and a timestamp — no user input reaches this function.
|
|
func (d *DB) BackupTo(ctx context.Context, path string) error {
|
|
return d.BackupToSafe(ctx, path, filepath.Join("data", "backups"))
|
|
}
|
|
|
|
// BackupToSafe is the internal implementation that accepts an explicit safe
|
|
// root directory. Exported for testing with isolated directories.
|
|
func (d *DB) BackupToSafe(ctx context.Context, path, safeRoot string) error {
|
|
clean := filepath.Clean(path)
|
|
|
|
absRoot, err := filepath.Abs(safeRoot)
|
|
if err != nil {
|
|
return fmt.Errorf("BackupToSafe: resolving safe root: %w", err)
|
|
}
|
|
absClean, err := filepath.Abs(clean)
|
|
if err != nil {
|
|
return fmt.Errorf("BackupToSafe: resolving path: %w", err)
|
|
}
|
|
|
|
// Structural guard: path must be under the safe root directory.
|
|
if !strings.HasPrefix(absClean, absRoot+string(filepath.Separator)) {
|
|
return fmt.Errorf("BackupToSafe: path %q is not under safe root %q", absClean, absRoot)
|
|
}
|
|
|
|
// Defence-in-depth: only allow safe characters (alphanumeric, path separators,
|
|
// hyphen, underscore, dot, space, colon, tilde). This is a strict allowlist —
|
|
// anything else is rejected to prevent SQL injection via the interpolated path.
|
|
for _, ch := range absClean {
|
|
switch {
|
|
case ch >= 'a' && ch <= 'z',
|
|
ch >= 'A' && ch <= 'Z',
|
|
ch >= '0' && ch <= '9',
|
|
ch == '/' || ch == '\\' || ch == '-' || ch == '_' || ch == '.' || ch == ' ' || ch == ':' || ch == '~':
|
|
// allowed (colon for Windows drive letters, tilde for temp paths)
|
|
default:
|
|
return fmt.Errorf("BackupToSafe: path contains forbidden character %q", string(ch))
|
|
}
|
|
}
|
|
|
|
// Reject SQL comment sequences that could break the VACUUM INTO statement,
|
|
// even though individual hyphens are allowed for filenames.
|
|
if strings.Contains(absClean, "--") {
|
|
return fmt.Errorf("BackupToSafe: path contains forbidden sequence %q", "--")
|
|
}
|
|
|
|
// VACUUM INTO refuses to write over an existing destination on its own,
|
|
// but only after it has already created (and, on failure below, would
|
|
// otherwise abandon) the file. Check explicitly and return before the
|
|
// exec so the failure branch below can tell "this call created the file"
|
|
// (safe to remove) from "the file was already there" (a same-second
|
|
// timestamp collision, or an operator-chosen name) without ever deleting
|
|
// something that predates this call.
|
|
if _, statErr := os.Stat(absClean); statErr == nil {
|
|
return fmt.Errorf("BackupToSafe: destination %q already exists", absClean)
|
|
} else if !errors.Is(statErr, os.ErrNotExist) {
|
|
return fmt.Errorf("BackupToSafe: checking destination %q: %w", absClean, statErr)
|
|
}
|
|
|
|
_, err = d.writer.ExecContext(ctx, fmt.Sprintf("VACUUM INTO '%s'", absClean))
|
|
if err != nil {
|
|
// An interrupted VACUUM INTO (ENOSPC, EIO, a canceled/expired ctx, ...)
|
|
// leaves a truncated file at absClean. Since the existence check above
|
|
// already proved nothing was there before this call, whatever exists
|
|
// now was created by this exec and is safe to remove — leaving it
|
|
// behind would let handleListBackups offer a truncated, unrestorable
|
|
// .db as a normal backup (OC-0212).
|
|
_ = os.Remove(absClean)
|
|
return fmt.Errorf("BackupToSafe: %w", err)
|
|
}
|
|
return nil
|
|
}
|
|
|
|
// CheckBackupIntegrity opens the SQLite file at path read-only and runs
|
|
// PRAGMA integrity_check against it. It returns nil only when SQLite reports
|
|
// "ok". Use it to verify a backup right after it is written and again before
|
|
// it is restored over the live database — a truncated or corrupt file must
|
|
// never be presented (or accepted) as restorable.
|
|
//
|
|
// The path travels into a file: URI, so it is restricted with the same
|
|
// character allowlist BackupToSafe enforces; callers always pass paths that
|
|
// already passed that gate.
|
|
func CheckBackupIntegrity(ctx context.Context, path string) error {
|
|
abs, err := filepath.Abs(filepath.Clean(path))
|
|
if err != nil {
|
|
return fmt.Errorf("CheckBackupIntegrity: resolving path: %w", err)
|
|
}
|
|
if _, err := os.Stat(abs); err != nil {
|
|
return fmt.Errorf("CheckBackupIntegrity: %w", err)
|
|
}
|
|
conn, err := sql.Open("sqlite", "file:"+filepath.ToSlash(abs)+"?mode=ro&_pragma=busy_timeout(2000)")
|
|
if err != nil {
|
|
return fmt.Errorf("CheckBackupIntegrity: open: %w", err)
|
|
}
|
|
defer conn.Close() //nolint:errcheck
|
|
var result string
|
|
if err := conn.QueryRowContext(ctx, "PRAGMA integrity_check(10)").Scan(&result); err != nil {
|
|
return fmt.Errorf("CheckBackupIntegrity: %w", err)
|
|
}
|
|
if result != "ok" {
|
|
return fmt.Errorf("CheckBackupIntegrity: integrity_check reported %q", result)
|
|
}
|
|
return nil
|
|
}
|