feat(saas): multi-tenant isolation (Phase 1) + rate-limit/audit/org-scoped export (Phase 2)

Phase 1 (tenant isolation):
- g.org_id set on require_auth; assert_tenant()/current_org_id() choke-point helpers.
- Multi-org provisioning: POST /api/admin/users {new_org:true} (super_admin) creates a
  new org + its first admin; GET /api/admin/orgs (super_admin sees all, admin own).
- Fixed latent create_org double-id bug (dict id != store key).
- test_saas_tenant.py: org2 admin blocked from org1 group (403), can't list org1
  groups/users, sees only own org; super_admin sees all.

Phase 2 (hardening):
- Rate limit login (per-IP + per-username) + chat send (per-user) to protect LLM cost
  and slow brute force; services/rate_limit.py (in-memory + disk, no external deps).
- Audit log data/audit/audit.jsonl on org.create, user.promote_super_admin, analytics.export.
- CSV export now org-scoped (admin exports only own org).
All 8 backend suites pass.
This commit is contained in:
Macky
2026-08-09 09:35:26 +07:00
parent e1d61e1e1e
commit 056753e8cb
9 changed files with 312 additions and 8 deletions

View File

@@ -16,6 +16,43 @@ def _store():
return current_app.extensions["user_store"]
def _log_audit(action: str, subject: str, *, detail: dict | None = None) -> None:
"""Append a line to the audit log (sensitive platform actions)."""
import json
import time
from ..config import Config
entry = {
"ts": time.strftime("%Y-%m-%dT%H:%M:%SZ", time.gmtime()),
"actor": (current_user() or {}).get("username") or (current_user() or {}).get("id"),
"action": action,
"subject": subject,
"detail": detail or {},
}
try:
log_dir = Config.DATA_DIR / "audit"
log_dir.mkdir(parents=True, exist_ok=True)
with open(log_dir / "audit.jsonl", "a", encoding="utf-8") as fh:
fh.write(json.dumps(entry, ensure_ascii=False) + "\n")
except Exception:
# Audit logging must never break the request.
pass
@admin_bp.get("/orgs")
@require_auth
@require_roles("admin")
def list_orgs():
"""Platform view: all organizations (super_admin). Admin sees only their own."""
actor = current_user()
if actor.get("role") == "super_admin":
orgs = list(_store().orgs.all())
return jsonify({"orgs": orgs})
# plain admin: only their own org
org = _store().orgs.get_or_none(actor.get("org_id"))
return jsonify({"orgs": [org] if org else []})
@admin_bp.post("/users")
@require_auth
@require_roles("admin")
@@ -36,13 +73,26 @@ def create_user():
actor_role = current_user().get("role")
if role in ("admin", "super_admin") and actor_role != "super_admin":
raise ApiError("only super_admin can grant admin roles", 403)
# Multi-tenant: provisioning a brand-new org (super_admin only). The created user
# becomes that org's first admin (tenant owner). Everything is isolated per org.
new_org = bool(data.get("new_org"))
if new_org:
if actor_role != "super_admin":
raise ApiError("only super_admin can create a new organization", 403)
if role != "admin":
raise ApiError("new-org first user must be role=admin", 400)
org = _store().create_org(name or username)
org_id = org["id"]
_log_audit("org.create", org_id, detail={"name": name or username})
try:
user = _store().create_user(
org_id=org_id, username=username, password=password, name=name, role=role
)
except AuthError as exc:
raise ApiError(str(exc))
return jsonify({"user": _store().public_user(user)}), 201
return jsonify({"user": _store().public_user(user), "org_id": org_id}), 201
@admin_bp.get("/users")
@@ -76,6 +126,8 @@ def update_user(username: str):
if actor.get("role") != "super_admin":
raise ApiError("only super_admin can change roles")
_store().set_role(username, role)
if role == "super_admin":
_log_audit("user.promote_super_admin", username)
if "active" in data:
if actor.get("role") != "super_admin":

View File

@@ -19,6 +19,30 @@ def _stores():
}
def _log_audit(action: str, subject: str, *, detail: dict | None = None) -> None:
import json
import time
from ..config import Config
from .helpers import current_user as _cu
actor = _cu()
entry = {
"ts": time.strftime("%Y-%m-%dT%H:%M:%SZ", time.gmtime()),
"actor": (actor or {}).get("username") or (actor or {}).get("id"),
"action": action,
"subject": subject,
"detail": detail or {},
}
try:
log_dir = Config.DATA_DIR / "audit"
log_dir.mkdir(parents=True, exist_ok=True)
with open(log_dir / "audit.jsonl", "a", encoding="utf-8") as fh:
fh.write(json.dumps(entry, ensure_ascii=False) + "\n")
except Exception:
pass
def _parse_date_iso(value: str | None, *, end: bool = False) -> str | None:
"""Parse a YYYY-MM-DD into an ISO datetime bound for created_at filtering."""
if not value:
@@ -124,11 +148,14 @@ def export_csv():
from flask import Response, current_app
s = _stores()
actor = current_user()
# Tenant: an admin exports only their own org's sessions; super_admin sees all.
export_org = actor.get("org_id") if actor.get("role") != "super_admin" else None
users = {}
try:
user_store = current_app.extensions.get("user_store")
if user_store and hasattr(user_store, "list_users"):
for rec in user_store.list_users():
for rec in user_store.list_users(org_id=export_org):
users[rec.get("id") or rec.get("username")] = rec.get("username") or rec.get("id")
except Exception:
pass
@@ -138,9 +165,9 @@ def export_csv():
grp_store = s["groups"]
sess_store = s["sessions"]
if hasattr(grp_store, "groups"):
group_ids = [g.get("id") for g in grp_store.groups.all()]
group_ids = [g.get("id") for g in grp_store.groups.all() if export_org is None or g.get("org_id") == export_org]
elif hasattr(grp_store, "all"):
group_ids = [g.get("id") for g in grp_store.all()]
group_ids = [g.get("id") for g in grp_store.all() if export_org is None or g.get("org_id") == export_org]
else:
group_ids = []
for gid in group_ids:
@@ -154,6 +181,8 @@ def export_csv():
except Exception:
pass
_log_audit("analytics.export", actor.get("org_id") or "?", detail={"rows": len(sessions)})
buf = io.StringIO()
w = csv.writer(buf)
w.writerow(["username", "persona", "scenario", "outcome", "score", "created_at"])

View File

@@ -27,6 +27,14 @@ def login():
password = data.get("password") or ""
if not username or not password:
raise ApiError("username and password are required")
# Slow down brute-force / abuse: per-IP + per-username window.
from ..services.rate_limit import check as ratelimit
client_ip = request.remote_addr or "?"
if not ratelimit("login:ip", client_ip, limit=15, window=300):
raise ApiError("too many attempts, try again later", 429)
if not ratelimit("login:user", username, limit=8, window=300):
raise ApiError("too many attempts, try again later", 429)
try:
user = _store().verify(username, password)
token = _store().issue_token(user)

View File

@@ -220,6 +220,13 @@ def send_message(gid: str, pid: str):
if len(text) > 2000:
raise ApiError("message too long")
# Protect LLM cost: per-user chat-send window.
from ..services.rate_limit import check as ratelimit
actor_rl = current_user()
if not ratelimit("chat:user", actor_rl.get("id") or actor_rl.get("username") or "?", limit=30, window=60):
raise ApiError("slow down — too many messages", 429)
group = s["groups"].get_or_none(gid)
persona = s["groups"].get_persona(gid, pid) if group else None
if not group or not persona:

View File

@@ -27,6 +27,20 @@ def current_user() -> dict[str, Any]:
return g.user
def current_org_id() -> str:
return getattr(g, "org_id", None) or (g.user or {}).get("org_id") or "org-default"
def assert_tenant(org_id: str | None) -> None:
"""Raise 403 if the object's org does not belong to the actor's tenant.
super_admin is the platform operator and is exempt (can see all orgs)."""
if (g.user or {}).get("role") == "super_admin":
return
if (org_id or "org-default") != current_org_id():
raise ApiError("permission denied", 403)
def require_auth(fn: Callable) -> Callable:
@functools.wraps(fn)
def wrapper(*args, **kwargs):
@@ -43,6 +57,9 @@ def require_auth(fn: Callable) -> Callable:
raise ApiError("account is inactive", 401)
g.user = user
g.token_payload = payload
# Tenant context: every request carries the actor's org id so downstream guards
# can enforce per-org isolation without re-reading the user each time.
g.org_id = (user or {}).get("org_id") or "org-default"
return fn(*args, **kwargs)
return wrapper

View File

@@ -31,10 +31,8 @@ class UserStore:
# ── org ────────────────────────────────────────────────────────────
def create_org(self, name: str, *, org_id: str | None = None) -> dict[str, Any]:
return self.orgs.create(
{"name": name, "id": org_id or new_id("org")},
key=org_id or new_id("org"),
)
oid = org_id or new_id("org")
return self.orgs.create({"name": name, "id": oid}, key=oid)
def get_org(self, org_id: str) -> dict[str, Any]:
return self.orgs.get(org_id)

View File

@@ -0,0 +1,64 @@
"""Lightweight server-side rate limiter (no external deps).
Per-key (user/IP + action) sliding-window counter, persisted to disk so restarts
don't fully reset abuse protection. In-memory fast path + on-disk snapshot.
"""
from __future__ import annotations
import json
import os
import threading
import time
from ..config import Config
_lock = threading.Lock()
_mem: dict[str, list[float]] = {} # key -> list of recent timestamps
def _key(action: str, ident: str) -> str:
return f"{action}:{ident}"
def _load():
p = Config.DATA_DIR / "ratelimit.json"
try:
if p.exists():
with open(p, encoding="utf-8") as fh:
return json.load(fh)
except Exception:
pass
return {}
def _save():
try:
p = Config.DATA_DIR / "ratelimit.json"
p.parent.mkdir(parents=True, exist_ok=True)
tmp = p.with_suffix(".json.tmp")
with open(tmp, "w", encoding="utf-8") as fh:
json.dump(_mem, fh)
os.replace(tmp, p)
except Exception:
pass
def check(action: str, ident: str, *, limit: int, window: int) -> bool:
"""Return True if allowed; False if the limit in `window` seconds was exceeded."""
key = _key(action, ident)
now = time.time()
with _lock:
rec = list(_mem.get(key) or _load().get(key) or [])
rec = [t for t in rec if now - t < window]
if len(rec) >= limit:
_mem[key] = rec
return False
rec.append(now)
_mem[key] = rec
# opportunistically persist (bounded writes)
try:
if int(now) % 5 == 0:
_save()
except Exception:
pass
return True