Files
multica/server/internal/middleware/auth.go
Bohan Jiang 86e7de3e41 feat(server/auth): cache auth token lookups in Redis with 10m TTL
* feat(server/auth): cache PAT lookups in Redis with 60s TTL

Personal access tokens used to hit Postgres on every request: a SELECT
to resolve token_hash → user_id, plus a fire-and-forget UPDATE of
last_used_at. For a CLI / daemon making many requests per second this
is wasted DB load — the token is the same and the answer hasn't changed.

Add a Redis-backed cache (auth.PATCache) keyed by token hash, TTL 60s:

- On cache hit, the auth middleware skips both the SELECT and the
  last_used_at UPDATE. last_used_at is now refreshed at most once per
  TTL window per token, not per request.
- On cache miss the middleware falls back to today's behavior: query
  Postgres, populate the cache, async-update last_used_at.
- On revoke, the handler invalidates the cache entry so revocation
  takes effect immediately rather than waiting for the TTL to expire.
  This required changing RevokePersonalAccessToken from :exec to :one
  RETURNING token_hash.

The cache is nil-safe: when REDIS_URL isn't configured, NewPATCache
returns nil and the middleware degrades to today's always-hit-DB
behavior. JWT validation is untouched (already DB-free).

Tested with REDIS_TEST_URL — same gating pattern the rest of the
suite uses for Redis-backed tests. New tests cover nil-safety, set/
get/invalidate, TTL, and the middleware short-circuit on cache hit.

* fix(server/auth): clamp PAT cache TTL to token's remaining lifetime

GPT-Boy review caught: a PAT expiring in <60s would still be cached
for the full PATCacheTTL window, so the token could continue passing
auth on cache hit for up to ~60s after its expires_at. The DB query
filters expired tokens (revoked = FALSE AND expires_at > now()), but
that filter never ran on a cache hit.

Make Set take an explicit ttl, and add TTLForExpiry to compute it:
  - no expires_at      → full PATCacheTTL
  - expires_at far     → full PATCacheTTL
  - expires_at <60s    → time until expiry
  - already expired    → 0, Set skips caching (TOCTOU defense between
                         the SELECT and the Set, since the SELECT
                         already filters expired rows)

Regression test pins the clamp behavior end-to-end against Redis.

* feat(server/auth): cache daemon-token + PAT lookups in DaemonAuth, bump TTL to 10m

Daemon /api/daemon/* requests (heartbeat, claim task) hit DaemonAuth
which previously did its own GetDaemonTokenByHash on every request and
*also* duplicated the PAT lookup on the mul_ fallback — bypassing the
cache added in 1cdd674c. Today's daemons authenticate via mul_ PATs
(mdt_ minting isn't wired up yet), so the duplicate PAT path is the one
that actually matters for hot-path DB load.

Three changes:

1. New auth.DaemonTokenCache mirrors PATCache for the mdt_ path
   (key = mul:auth:daemon:<sha256>, JSON value = {workspace_id, daemon_id}).
   Forward-looking infrastructure for when daemon tokens get minted; the
   middleware short-circuits the DB SELECT on cache hit. TTL clamped to
   the token's expires_at via the shared TTLForExpiry helper.

2. DaemonAuth now also consults PATCache on its mul_ fallback, sharing
   the same cache as the regular Auth middleware. A daemon making 4 hb/min
   collapses from 4 GetPersonalAccessTokenByHash + 4 last_used_at writes
   per minute to ~1 of each per AuthCacheTTL window (~10 minutes).

3. Rename PATCacheTTL → AuthCacheTTL and bump from 60s to 10 minutes.
   The constant is now shared between PAT and daemon caches; 10m matches
   the user-requested longer TTL for further DB write reduction. Revoke
   latency on the happy path is still instant via active invalidation;
   the worst-case (Redis Del miss / direct-DB revoke) grows from ~60s to
   ~10m.

Tests cover nil-safety, set/get/invalidate, TTL, clamped TTL on near-
expiry tokens, and the middleware short-circuit for both cache paths
(mdt_ via DaemonTokenCache, mul_ fallback via PATCache).

* feat(server/auth): cache PAT lookups on the WebSocket auth path

The third place a PAT is resolved — patResolver.ResolveToken used by
realtime.HandleWebSocket — was still hitting Postgres on every /ws
auth and firing an unconditional last_used_at UPDATE, bypassing the
cache added in 1cdd674c. Wire it through the same shared PATCache so
revoking a token through any path (Auth middleware, DaemonAuth PAT
fallback, or WS auth) hits all three caches with one Invalidate.

Also leaves a comment on DeleteDaemonTokensByWorkspaceAndDaemon —
the query has no caller today, but a future deregister/rotate flow
must remember to call DaemonTokenCache.Invalidate(hash) for each
deleted row, otherwise deleted daemon tokens stay valid until TTL.
2026-04-29 17:07:54 +08:00

145 lines
4.8 KiB
Go

package middleware
import (
"context"
"log/slog"
"net/http"
"strings"
"time"
"github.com/golang-jwt/jwt/v5"
"github.com/jackc/pgx/v5/pgtype"
"github.com/multica-ai/multica/server/internal/auth"
"github.com/multica-ai/multica/server/internal/util"
db "github.com/multica-ai/multica/server/pkg/db/generated"
)
func uuidToString(u pgtype.UUID) string { return util.UUIDToString(u) }
// Auth middleware validates JWT tokens or Personal Access Tokens.
// Token sources (in priority order):
// 1. Authorization: Bearer <token> header (PAT or JWT)
// 2. multica_auth HttpOnly cookie (JWT) — requires valid CSRF token for state-changing requests
//
// Sets X-User-ID and X-User-Email headers on the request for downstream handlers.
//
// patCache is optional; when non-nil, PAT lookups are cached with a short
// TTL (auth.AuthCacheTTL). On cache hit the middleware skips both the DB
// SELECT and the last_used_at UPDATE — last_used_at is therefore refreshed
// at most once per TTL window per token, not per request.
func Auth(queries *db.Queries, patCache *auth.PATCache) func(http.Handler) http.Handler {
return func(next http.Handler) http.Handler {
return http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
tokenString, fromCookie := extractToken(r)
if tokenString == "" {
slog.Debug("auth: no token found", "path", r.URL.Path)
http.Error(w, `{"error":"missing authorization"}`, http.StatusUnauthorized)
return
}
// Cookie-based auth requires CSRF validation for state-changing methods.
if fromCookie && !auth.ValidateCSRF(r) {
slog.Debug("auth: CSRF validation failed", "path", r.URL.Path)
http.Error(w, `{"error":"CSRF validation failed"}`, http.StatusForbidden)
return
}
// PAT: tokens starting with "mul_"
if strings.HasPrefix(tokenString, "mul_") {
hash := auth.HashToken(tokenString)
// Cache hit: TTL has not expired, the token was valid the
// last time we looked, and nothing has invalidated the
// entry since. Skip the DB SELECT and the last_used_at
// UPDATE — last_used_at is bumped once per TTL window.
if userID, ok := patCache.Get(r.Context(), hash); ok {
r.Header.Set("X-User-ID", userID)
next.ServeHTTP(w, r)
return
}
if queries == nil {
http.Error(w, `{"error":"invalid token"}`, http.StatusUnauthorized)
return
}
pat, err := queries.GetPersonalAccessTokenByHash(r.Context(), hash)
if err != nil {
slog.Warn("auth: invalid PAT", "path", r.URL.Path, "error", err)
http.Error(w, `{"error":"invalid token"}`, http.StatusUnauthorized)
return
}
userID := uuidToString(pat.UserID)
r.Header.Set("X-User-ID", userID)
// Clamp cache TTL to the token's remaining lifetime so a
// PAT expiring in <AuthCacheTTL can't continue passing
// auth on a cache hit after expires_at.
var expiresAt time.Time
if pat.ExpiresAt.Valid {
expiresAt = pat.ExpiresAt.Time
}
patCache.Set(r.Context(), hash, userID, auth.TTLForExpiry(time.Now(), expiresAt))
// Cache miss = TTL expired (or first use after revoke /
// process restart). Refresh last_used_at; subsequent hits
// within the TTL window skip this write entirely.
go queries.UpdatePersonalAccessTokenLastUsed(context.Background(), pat.ID)
next.ServeHTTP(w, r)
return
}
// JWT
token, err := jwt.Parse(tokenString, func(token *jwt.Token) (any, error) {
if _, ok := token.Method.(*jwt.SigningMethodHMAC); !ok {
return nil, jwt.ErrSignatureInvalid
}
return auth.JWTSecret(), nil
})
if err != nil || !token.Valid {
slog.Warn("auth: invalid token", "path", r.URL.Path, "error", err)
http.Error(w, `{"error":"invalid token"}`, http.StatusUnauthorized)
return
}
claims, ok := token.Claims.(jwt.MapClaims)
if !ok {
slog.Warn("auth: invalid claims", "path", r.URL.Path)
http.Error(w, `{"error":"invalid claims"}`, http.StatusUnauthorized)
return
}
sub, ok := claims["sub"].(string)
if !ok || strings.TrimSpace(sub) == "" {
slog.Warn("auth: invalid claims", "path", r.URL.Path)
http.Error(w, `{"error":"invalid claims"}`, http.StatusUnauthorized)
return
}
r.Header.Set("X-User-ID", sub)
if email, ok := claims["email"].(string); ok {
r.Header.Set("X-User-Email", email)
}
next.ServeHTTP(w, r)
})
}
}
// extractToken returns the bearer token and whether it came from a cookie.
// Priority: Authorization header > multica_auth cookie.
func extractToken(r *http.Request) (token string, fromCookie bool) {
if authHeader := r.Header.Get("Authorization"); authHeader != "" {
tokenString := strings.TrimPrefix(authHeader, "Bearer ")
if tokenString != authHeader {
return tokenString, false
}
}
if cookie, err := r.Cookie(auth.AuthCookieName); err == nil && cookie.Value != "" {
return cookie.Value, true
}
return "", false
}