1 files changed, 32 insertions, 15 deletions

diff --git a/packages/meshbay-hub/src/meshbay_hub/api/users.py b/packages/meshbay-hub/src/meshbay_hub/api/users.py
index 53238de..5a0f9dc 100644
--- a/packages/meshbay-hub/src/meshbay_hub/api/users.py
+++ b/packages/meshbay-hub/src/meshbay_hub/api/users.py
@@ -5,7 +5,7 @@ import uuid
 from datetime import datetime, timezone, timedelta
 
 from fastapi import APIRouter, Depends, HTTPException, Request, status
-from pydantic import BaseModel, EmailStr, field_validator
+from pydantic import BaseModel, field_validator
 from sqlalchemy import select
 from sqlalchemy.ext.asyncio import AsyncSession
 
@@ -22,6 +22,7 @@ from meshbay_hub.auth import (
     verify_password,
 )
 from meshbay_hub.api.middleware import limiter
+from meshbay_hub.api.netutil import client_ip
 from meshbay_hub.config import HubConfig
 from meshbay_hub.db.engine import get_db
 from meshbay_hub.db.models import GroupMember, IPLog, RefreshToken, User
@@ -62,6 +63,24 @@ class RegisterRequest(BaseModel):
             raise ValueError("username: only letters, digits, -, _, .")
         return v
 
+    @field_validator("email")
+    @classmethod
+    def email_valid(cls, v: str) -> str:
+        """
+        Sanity-check the address (L6): the field was plain `str`, so any junk was
+        accepted and stored encrypted forever. Deliberately not RFC 5322 — full
+        validation would pull in the email-validator dependency for little gain,
+        and the address is only ever used for recovery and legal contact.
+        """
+        v = v.strip()
+        local, sep, domain = v.partition("@")
+        if (not sep or not local or not domain
+                or "." not in domain
+                or len(v) > 254
+                or any(c.isspace() or ord(c) < 32 for c in v)):
+            raise ValueError("invalid email address")
+        return v
+
 
 class LoginRequest(BaseModel):
     username: str
@@ -106,21 +125,24 @@ async def register(
         hub_id=hub_id,
     )
     db.add(user)
+    # flush assigns user.id so the log row can be attributed directly.
+    #
+    # Finding M6: this used to insert the row with a NULL user_id and then run
+    #   UPDATE ip_logs SET user_id = <new user> WHERE user_id IS NULL
+    # which claimed *every* unattributed row in the table — failed logins for other
+    # usernames, other registrations racing this one — and stamped them with the
+    # account just created. For logs retained a year to answer legal requests, that
+    # attributed other people's connections to the wrong person.
+    await db.flush()
     db.add(IPLog(
+        user_id=user.id,
         event="account_create",
-        ip_address=_client_ip(request),
+        ip_address=client_ip(request),
         detail=body.username,
     ))
     await db.commit()
     await db.refresh(user)
 
-    # Set user_id in IPLog after commit
-    await db.execute(
-        IPLog.__table__.update()
-        .where(IPLog.user_id == None)  # noqa: E711
-        .values(user_id=user.id))
-    await db.commit()
-
     return {"user_id": user.id}
 
 
@@ -135,7 +157,7 @@ async def login(
         select(User).where(User.username == body.username))
     user = result.scalar_one_or_none()
 
-    ip = _client_ip(request)
+    ip = client_ip(request)
 
     if not body.auth_key and not body.password:
         raise HTTPException(status_code=401, detail="No credentials provided")
@@ -358,8 +380,3 @@ async def get_user_pubkeys(
     return resp
 
 
-def _client_ip(request: Request) -> str:
-    forwarded = request.headers.get("X-Forwarded-For")
-    if forwarded:
-        return forwarded.split(",")[0].strip()
-    return request.client.host if request.client else "unknown"