hermes-agent/hermes_cli/dashboard_auth/middleware.py

"""Auth-gate middleware for the dashboard.

Engaged when ``app.state.auth_required is True``. The gate's job:

  1. Allow a small set of routes through unauthenticated (login page,
     ``/auth/*`` OAuth round trip, ``/api/auth/providers``, static
     assets).
  2. For everything else, demand a valid session cookie and attach the
     verified :class:`Session` to ``request.state.session``.
  3. On HTML routes, redirect missing/invalid cookies to ``/login``.
     On ``/api/*`` routes, return 401 JSON.

The middleware is a no-op when ``auth_required`` is False (loopback
mode); the legacy ``_SESSION_TOKEN`` ``auth_middleware`` handles those
binds.
"""
from __future__ import annotations

import logging
from typing import Awaitable, Callable

from fastapi import Request
from fastapi.responses import JSONResponse, RedirectResponse, Response

from hermes_cli.dashboard_auth import list_providers
from hermes_cli.dashboard_auth.audit import AuditEvent, audit_log
from hermes_cli.dashboard_auth.base import ProviderError
from hermes_cli.dashboard_auth.cookies import read_session_cookies

_log = logging.getLogger(__name__)

# Paths that bypass the auth gate. Order matters: prefix match.
_GATE_PUBLIC_PREFIXES: tuple[str, ...] = (
    "/auth/login",
    "/auth/callback",
    "/auth/logout",
    "/login",
    "/api/auth/providers",
    "/assets/",
    "/favicon.ico",
    "/ds-assets/",
    "/fonts/",
    "/fonts-terminal/",
)


def _path_is_public(path: str) -> bool:
    return any(
        path == prefix or path.startswith(prefix)
        for prefix in _GATE_PUBLIC_PREFIXES
    )


def _client_ip(request: Request) -> str:
    fwd = request.headers.get("x-forwarded-for", "")
    if fwd:
        return fwd.split(",")[0].strip()
    return request.client.host if request.client else ""


def _unauth_response(request: Request, *, reason: str) -> Response:
    """API routes → 401 JSON with ``login_url``; HTML routes → 302 → /login.

    The JSON envelope carries a ``login_url`` field with a ``next=`` query
    string so the SPA's global 401 handler can drop the user back where
    they were after re-auth. The contract is intentionally simple so any
    fetch-wrapper can implement the redirect without parsing details:

        if response.status === 401 && body.error in ("unauthenticated",
                                                       "session_expired"):
            window.location.assign(body.login_url);

    HTML redirects also carry the ``next=`` query string so direct
    navigation to ``/sessions`` (etc.) without a cookie comes back to
    ``/sessions`` after login.
    """
    path = request.url.path
    next_param = _safe_next_target(request)
    login_url = f"/login?next={next_param}" if next_param else "/login"

    if path.startswith("/api/"):
        # API routes never get redirects: the browser fetch() API would
        # follow a 302 into the cross-origin OAuth dance opaquely. Return
        # 401 with a structured envelope so the SPA can full-page-navigate
        # to login_url.
        error_code = (
            "session_expired"
            if reason == "invalid_or_expired_session"
            else "unauthenticated"
        )
        return JSONResponse(
            {
                "error": error_code,
                "detail": "Unauthorized",
                "reason": reason,
                "login_url": login_url,
            },
            status_code=401,
        )
    return RedirectResponse(url=login_url, status_code=302)


def _safe_next_target(request: Request) -> str:
    """Build the URL-encoded ``next`` query value, or empty string.

    Only same-origin relative paths are accepted; absolute URLs or
    ``//evil.com`` open-redirect attempts are silently dropped. The empty
    string return means the caller produces a bare ``/login`` URL — fine,
    user lands at the dashboard root after re-auth.
    """
    path = request.url.path
    # Reject anything that doesn't start with "/" or starts with "//"
    # (protocol-relative URL — would open-redirect to an attacker host).
    if not path or not path.startswith("/") or path.startswith("//"):
        return ""
    # Don't redirect back to the auth routes themselves — that loops.
    if any(
        path == p or path.startswith(p)
        for p in ("/login", "/auth/", "/api/auth/")
    ):
        return ""
    # Preserve query string if present (e.g. /sessions?page=2).
    query = request.url.query
    target = f"{path}?{query}" if query else path
    # urlencode the whole thing as a single value.
    from urllib.parse import quote
    return quote(target, safe="")


async def gated_auth_middleware(
    request: Request,
    call_next: Callable[[Request], Awaitable[Response]],
) -> Response:
    """Engaged only when ``app.state.auth_required is True``.

    No-op pass-through in loopback mode so the legacy auth_middleware can
    handle those binds via ``_SESSION_TOKEN``.
    """
    if not getattr(request.app.state, "auth_required", False):
        return await call_next(request)

    path = request.url.path
    if _path_is_public(path):
        return await call_next(request)

    at, _rt = read_session_cookies(request)
    if not at:
        return _unauth_response(request, reason="no_cookie")

    # Try every registered provider's verify_session in turn. Providers
    # MUST return None for tokens they don't recognise (not raise). This
    # lets multiple providers stack — the first one that recognises a
    # token wins.
    session = None
    for provider in list_providers():
        try:
            session = provider.verify_session(access_token=at)
        except ProviderError as e:
            _log.warning(
                "dashboard-auth: provider %r unreachable during verify: %s",
                provider.name, e,
            )
            audit_log(
                AuditEvent.SESSION_VERIFY_FAILURE,
                provider=provider.name,
                reason="provider_unreachable",
                ip=_client_ip(request),
            )
            return JSONResponse(
                {"detail": f"Auth provider {provider.name!r} unreachable"},
                status_code=503,
            )
        if session is not None:
            break

    if session is None:
        audit_log(
            AuditEvent.SESSION_VERIFY_FAILURE,
            reason="no_provider_recognises",
            ip=_client_ip(request),
        )
        response = _unauth_response(request, reason="invalid_or_expired_session")
        # Clear the dead cookie so the browser doesn't keep sending it.
        # Contract v1: no refresh token to retry with, so the only correct
        # next step is full re-auth via /login. Importing locally avoids a
        # cycle with cookies → middleware at module load.
        from hermes_cli.dashboard_auth.cookies import clear_session_cookies
        clear_session_cookies(response)
        return response

    request.state.session = session
    return await call_next(request)