US07-02: Harden API Authorization and Path Boundaries

README.md

@@ -17,6 +17,25 @@ python -m photo_pipeline serve     # start the API + static review UI (127.0.0.1
 Configuration comes from `PHOTO_PIPELINE_*` environment variables (see
 `photo_pipeline/config.py`); secrets are referenced, never logged.
 
+### API access (US07-02)
+
+The app listens on loopback, so its attacker is another page in the same browser.
+Every `/api/v1` route except `health/live`, `health/ready`, and `session` requires
+the application session, and every mutation requires its CSRF token as well:
+
+```bash
+BASE=http://127.0.0.1:8000
+TOKEN=$(curl -sc /tmp/pp.jar $BASE/api/v1/session | python -c 'import json,sys; print(json.load(sys.stdin)["csrf_token"])')
+curl -sb /tmp/pp.jar -H "X-CSRF-Token: $TOKEN" -X POST $BASE/api/v1/albums/proposals -d '{}' -H 'Content-Type: application/json'
+```
+
+The session is per server process — restarting `serve` invalidates it, and the
+browser client re-bootstraps by itself. Requests are also refused when the `Host` is
+not a loopback name (DNS rebinding), when `Origin` is any other origin, when
+`Sec-Fetch-Site` says the request came from another site (an `<img>` pointed at a
+thumbnail), or when the body exceeds `PHOTO_PIPELINE_MAX_REQUEST_BYTES`. There is no
+CORS middleware at all, so no other origin can read a response.
+
 ## Testing
 
 One offline command runs the whole suite (unit, integration, and browser

frontend/js/api.js

@@ -2,14 +2,43 @@
 // cancellation. Every method accepts an optional { signal } from cancellable().
 export const BASE = "/api/v1";
 
+// The API refuses every request without the session cookie, and every mutation
+// without this token echoed back. The token is readable only same-origin, which is
+// what makes it proof that the caller is this app and not another page.
+let csrfToken = null;
+
+async function session() {
+  if (csrfToken === null) {
+    const response = await fetch(BASE + "/session", { credentials: "same-origin" });
+    const body = await response.json().catch(() => null);
+    csrfToken = (body && body.csrf_token) || null;
+  }
+  return csrfToken || "";
+}
+
+async function send(path, { signal, ...options }) {
+  return fetch(BASE + path, {
+    credentials: "same-origin",
+    signal,
+    ...options,
+    headers: {
+      "Content-Type": "application/json",
+      "X-CSRF-Token": await session(),
+      ...(options.headers || {}),
+    },
+  });
+}
+
 async function request(path, { signal, ...options } = {}) {
   let response;
   try {
-    response = await fetch(BASE + path, {
-      headers: { "Content-Type": "application/json" },
-      signal,
-      ...options,
-    });
+    response = await send(path, { signal, ...options });
+    // A restarted server issues a new session; re-bootstrap once rather than
+    // stranding an open tab on 401.
+    if (response.status === 401) {
+      csrfToken = null;
+      response = await send(path, { signal, ...options });
+    }
   } catch (error) {
     // A caller-cancelled fetch is not a failure; tag it so views can ignore it.
     if (error.name === "AbortError") {

frontend/js/tests/unit.js

@@ -29,6 +29,10 @@ function jsonResponse(status, body) {
 const tick = (ms = 0) => new Promise((r) => setTimeout(r, ms));
 
 async function run() {
+  // The client fetches its CSRF token once, lazily (US07-02). Do that against the
+  // real server first, so the stubbed fetch below only ever sees the call under test.
+  await api.workflow().catch(() => {});
+
   // ── store ────────────────────────────────────────────────────────────────
   {
     const store = createStore({ n: 0 });

photo_pipeline/api/app.py

@@ -8,11 +8,15 @@ and exposes the versioned ``/api/v1`` surface; US01-02 ships only health.
 
 from __future__ import annotations
 
+import logging
 from contextlib import asynccontextmanager
 from pathlib import Path
 
-from fastapi import FastAPI
+from fastapi import FastAPI, Request
+from fastapi.exceptions import RequestValidationError
+from fastapi.responses import JSONResponse
 from fastapi.staticfiles import StaticFiles
+from starlette.exceptions import HTTPException as StarletteHTTPException
 
 from photo_pipeline.api.routes import (
     albums,
@@ -25,10 +29,12 @@ from photo_pipeline.api.routes import (
     library,
     renames,
     safety,
+    session as session_routes,
     thumbnails,
     uploads,
     workflow,
 )
+from photo_pipeline.api.security import DEFAULT_HEADERS, SecurityMiddleware, Session
 
 # Registers the safety_score / analysis job handlers on import.
 import photo_pipeline.jobs.domain_handlers  # noqa: F401
@@ -39,6 +45,41 @@ from photo_pipeline.services.upload_batches import UploadBatchService
 
 FRONTEND_DIR = Path(__file__).resolve().parents[2] / "frontend"
 
+log = logging.getLogger(__name__)
+
+
+def _envelope(status: int, code: str, message: str) -> JSONResponse:
+    return JSONResponse(
+        status_code=status,
+        content={"error": {"code": code, "message": message}},
+        headers=DEFAULT_HEADERS,
+    )
+
+
+def _install_error_handlers(app: FastAPI) -> None:
+    """One JSON error envelope everywhere, and nothing behind it.
+
+    An unhandled exception carries the library's absolute paths, SQL, and sometimes
+    a credential in its text; the client gets a code, the operator gets the traceback
+    in the server log (US07-02).
+    """
+
+    @app.exception_handler(StarletteHTTPException)
+    async def _http_error(request: Request, exc: StarletteHTTPException):
+        return _envelope(exc.status_code, "http_error", str(exc.detail))
+
+    @app.exception_handler(RequestValidationError)
+    async def _validation_error(request: Request, exc: RequestValidationError):
+        # Field locations only: the echoed input can be the caller's own data, but it
+        # is also what ends up in shared logs and screenshots.
+        fields = sorted(".".join(str(part) for part in error["loc"]) for error in exc.errors())
+        return _envelope(422, "invalid_request", f"invalid request fields: {', '.join(fields)}")
+
+    @app.exception_handler(Exception)
+    async def _unhandled(request: Request, exc: Exception):
+        log.exception("unhandled error serving %s", request.url.path)
+        return _envelope(500, "internal_error", "internal error")
+
 
 def create_app(config: Config | None = None) -> FastAPI:
     config = config or Config.from_env()
@@ -62,6 +103,12 @@ def create_app(config: Config | None = None) -> FastAPI:
             app.state.engine = None
 
     app = FastAPI(title="Photo Pipeline", version="0.1.0", lifespan=lifespan)
+    # One session per process: the browser exchanges it for a cookie + CSRF token,
+    # and every other origin is refused before a route ever runs (US07-02).
+    app.state.session = Session.create()
+    app.add_middleware(SecurityMiddleware, session=app.state.session, config=config)
+    _install_error_handlers(app)
+    app.include_router(session_routes.router, prefix="/api/v1")
     app.include_router(health.router, prefix="/api/v1")
     app.include_router(inventory.router, prefix="/api/v1")
     app.include_router(duplicates.router, prefix="/api/v1")

photo_pipeline/api/routes/analysis.py

@@ -18,7 +18,10 @@ router = APIRouter(tags=["analysis"])
 
 
 def _service(request: Request) -> AnalysisService:
-    return AnalysisService(request.app.state.session_factory)
+    return AnalysisService(
+        request.app.state.session_factory,
+        library_roots=tuple(request.app.state.config.library_roots),
+    )
 
 
 def _error(status: int, code: str, message: str) -> JSONResponse:

photo_pipeline/api/routes/session.py

@@ -0,0 +1,30 @@
+"""Session bootstrap: the one endpoint reachable without a session (US07-02).
+
+It sets the ``HttpOnly``/``SameSite=Strict`` session cookie and returns the CSRF
+token in the body. A foreign page can call this — it just cannot read the answer,
+because the app sends no CORS headers — and the cookie it received is never attached
+to a request that foreign page initiates.
+"""
+
+from __future__ import annotations
+
+from fastapi import APIRouter, Request
+from fastapi.responses import JSONResponse
+
+from photo_pipeline.api.security import SESSION_COOKIE
+
+router = APIRouter(tags=["session"])
+
+
+@router.get("/session")
+def start_session(request: Request) -> JSONResponse:
+    session = request.app.state.session
+    response = JSONResponse({"csrf_token": session.csrf_token})
+    response.set_cookie(
+        SESSION_COOKIE,
+        session.id,
+        httponly=True,
+        samesite="strict",
+        path="/",
+    )
+    return response

photo_pipeline/api/routes/thumbnails.py

@@ -31,5 +31,7 @@ def get_thumbnail(asset_id: str, request: Request, size: int = Query(512)):
     return FileResponse(
         path,
         media_type="image/webp",
-        headers={"Cache-Control": "public, max-age=31536000, immutable"},
+        # private: the URL is versioned and immutable, but these bytes are the user's
+        # photos and must never sit in a shared cache (US07-02).
+        headers={"Cache-Control": "private, max-age=31536000, immutable"},
     )

photo_pipeline/api/security.py

@@ -0,0 +1,192 @@
+"""Local-web attack surface: session, CSRF, Origin/Host checks, default headers.
+
+The app binds to 127.0.0.1, so the attacker is not a remote client but another page
+in the user's browser (concept §15, "Local web attack"): any site can issue requests
+to ``http://127.0.0.1:8000`` and can embed ``<img src=...>`` against media endpoints.
+The defenses stack, because each one alone has a hole:
+
+* **Host** must be a loopback name — a DNS rebinding host that resolves to 127.0.0.1
+  passes the browser's origin rules but not this check.
+* **Origin**, when the browser sends one, must be this exact origin (scheme, host,
+  port). There is no CORS middleware at all, so a foreign page can never *read* a
+  response even if it manages to send a request.
+* **Sec-Fetch-Site** rejects cross-site loads that carry no Origin, which is what an
+  ``<img>`` or ``<script>`` against a media endpoint looks like.
+* A **session cookie** (``SameSite=Strict``, ``HttpOnly``) is required by every
+  ``/api/v1`` route except liveness/readiness and the bootstrap itself. Strict means
+  the browser never attaches it to a request another site initiated.
+* A **CSRF token** must be echoed in a header on every mutation. It is handed out
+  only in the bootstrap response body, which a foreign page cannot read (no CORS) —
+  so possessing it proves the caller is same-origin.
+
+``evaluate`` is a pure function over the request metadata: the whole policy is one
+table that a unit test can enumerate, and the middleware only applies its verdict.
+"""
+
+from __future__ import annotations
+
+import secrets
+from collections.abc import Mapping
+from dataclasses import dataclass
+from urllib.parse import urlsplit
+
+from starlette.datastructures import Headers, MutableHeaders
+from starlette.responses import JSONResponse
+
+SESSION_COOKIE = "pp_session"
+CSRF_HEADER = "x-csrf-token"
+API_PREFIX = "/api/v1"
+SAFE_METHODS = frozenset({"GET", "HEAD", "OPTIONS"})
+# Reachable without a session: liveness/readiness (an orchestrator has no cookie)
+# and the bootstrap that issues the session in the first place.
+PUBLIC_PATHS = frozenset(
+    {f"{API_PREFIX}/health/live", f"{API_PREFIX}/health/ready", f"{API_PREFIX}/session"}
+)
+LOOPBACK_HOSTS = frozenset({"127.0.0.1", "localhost", "::1", "[::1]"})
+
+# Applied to every response. No inline script/style is used by the frontend, so the
+# policy can stay strict; `frame-ancestors 'none'` and CORP keep other pages from
+# embedding the app or its thumbnails.
+DEFAULT_HEADERS = {
+    "x-content-type-options": "nosniff",
+    "x-frame-options": "DENY",
+    "referrer-policy": "no-referrer",
+    "cross-origin-resource-policy": "same-origin",
+    "cross-origin-opener-policy": "same-origin",
+    "content-security-policy": (
+        "default-src 'self'; img-src 'self' data:; style-src 'self'; script-src 'self'; "
+        "connect-src 'self'; frame-ancestors 'none'; base-uri 'none'; form-action 'none'"
+    ),
+}
+
+
+@dataclass(frozen=True)
+class Session:
+    """One process, one session. A local app has exactly one user; a session store
+    would be bookkeeping without a second subject to distinguish.
+
+    ponytail: per-session rows if the app ever serves more than one operator.
+    """
+
+    id: str
+    csrf_token: str
+
+    @classmethod
+    def create(cls) -> Session:
+        return cls(secrets.token_urlsafe(32), secrets.token_urlsafe(32))
+
+
+@dataclass(frozen=True)
+class Refusal:
+    status: int
+    code: str
+    message: str
+
+
+def split_host(value: str) -> tuple[str, str]:
+    """``"127.0.0.1:8000"`` -> ``("127.0.0.1", "8000")``; bracketed IPv6 aware."""
+    value = value.strip()
+    if value.startswith("["):
+        host, _, port = value.partition("]")
+        return host + "]", port.lstrip(":")
+    host, _, port = value.partition(":")
+    return host, port
+
+
+def evaluate(
+    *,
+    method: str,
+    path: str,
+    headers: Mapping[str, str],
+    session: Session,
+    allowed_hosts: frozenset[str] = LOOPBACK_HOSTS,
+    max_request_bytes: int,
+) -> Refusal | None:
+    """Why this request must be refused, or ``None`` when it may proceed."""
+    host_header = headers.get("host", "")
+    host, port = split_host(host_header)
+    if host.lower() not in allowed_hosts:
+        return Refusal(403, "host_not_allowed", "request host is not a local address")
+
+    origin = headers.get("origin")
+    if origin is not None and origin != "":
+        parts = urlsplit(origin)
+        origin_host, origin_port = split_host(parts.netloc)
+        if (
+            parts.scheme not in ("http", "https")
+            or origin_host.lower() not in allowed_hosts
+            or origin_port != port
+        ):
+            return Refusal(403, "origin_not_allowed", "request origin is not this application")
+
+    # Absent means a non-browser client; "none" is a user-initiated navigation.
+    fetch_site = headers.get("sec-fetch-site")
+    if fetch_site is not None and fetch_site not in ("same-origin", "none"):
+        return Refusal(403, "cross_site_blocked", "cross-site requests are not accepted")
+
+    length = headers.get("content-length")
+    if length and length.isdigit() and int(length) > max_request_bytes:
+        return Refusal(413, "payload_too_large", "request body exceeds the configured limit")
+
+    protected = path.startswith(API_PREFIX) and path not in PUBLIC_PATHS
+    if not protected:
+        return None
+
+    if headers.get("cookie-session") != session.id:
+        return Refusal(401, "unauthenticated", "a valid application session is required")
+    if method.upper() not in SAFE_METHODS and headers.get(CSRF_HEADER) != session.csrf_token:
+        return Refusal(403, "csrf_failed", "missing or invalid CSRF token")
+    return None
+
+
+class SecurityMiddleware:
+    """Pure-ASGI so the SSE stream keeps streaming (BaseHTTPMiddleware buffers)."""
+
+    def __init__(self, app, *, session: Session, config) -> None:
+        self.app = app
+        self.session = session
+        self.max_request_bytes = config.max_request_bytes
+        self.allowed_hosts = frozenset(LOOPBACK_HOSTS | {str(config.host).lower()})
+
+    async def __call__(self, scope, receive, send) -> None:
+        if scope["type"] != "http":
+            await self.app(scope, receive, send)
+            return
+        headers = Headers(scope=scope)
+        # The cookie is read here and handed to the pure policy as one value, so the
+        # policy never has to parse a Cookie header.
+        lookup = dict(headers)
+        lookup["cookie-session"] = _cookie(headers.get("cookie", ""), SESSION_COOKIE)
+        refusal = evaluate(
+            method=scope.get("method", "GET"),
+            path=scope.get("path", "/"),
+            headers=lookup,
+            session=self.session,
+            allowed_hosts=self.allowed_hosts,
+            max_request_bytes=self.max_request_bytes,
+        )
+        if refusal is not None:
+            response = JSONResponse(
+                status_code=refusal.status,
+                content={"error": {"code": refusal.code, "message": refusal.message}},
+                headers=DEFAULT_HEADERS,
+            )
+            await response(scope, receive, send)
+            return
+
+        async def send_with_headers(message):
+            if message["type"] == "http.response.start":
+                out = MutableHeaders(scope=message)
+                for name, value in DEFAULT_HEADERS.items():
+                    out.setdefault(name, value)
+            await send(message)
+
+        await self.app(scope, receive, send_with_headers)
+
+
+def _cookie(header: str, name: str) -> str:
+    for part in header.split(";"):
+        key, _, value = part.strip().partition("=")
+        if key == name:
+            return value
+    return ""

photo_pipeline/config.py

@@ -30,6 +30,10 @@ class Config(BaseModel):
     log_level: str = "INFO"
     log_format: str = "json"  # "json" or "text"
 
+    # Largest request body the API accepts. Every endpoint takes small JSON commands;
+    # anything larger is a mistake or an attempt to exhaust memory (US07-02).
+    max_request_bytes: int = 1_048_576
+
     # Library boundary for path validation (os.pathsep-separated in the env var).
     library_roots: tuple[Path, ...] = ()
     thumbnail_cache_quota_bytes: int = 500_000_000

photo_pipeline/jobs/domain_handlers.py

@@ -38,7 +38,8 @@ def _safety_score_item(asset_id: str, ctx: JobContext) -> None:
 def _analysis_item(asset_id: str, ctx: JobContext) -> None:
     from photo_pipeline.services.analysis import AnalysisService
 
-    AnalysisService(ctx.session_factory).run([asset_id])
+    roots = tuple(getattr(ctx.config, "library_roots", ()) or ())
+    AnalysisService(ctx.session_factory, library_roots=roots).run([asset_id])
 
 
 def _upload_batch_item(batch_id: str, ctx: JobContext) -> None:

photo_pipeline/path_policy.py

@@ -49,6 +49,29 @@ def resolve_within(root: Path, path: os.PathLike | str) -> Path:
     return resolved
 
 
+def resolve_in_roots(roots: Iterable[os.PathLike | str], path: os.PathLike | str) -> Path:
+    """The resolved path, proven to be inside one of ``roots`` and not excluded.
+
+    Callers must use the **returned** path for whatever they do next: validating one
+    name and then opening another is the symlink race this exists to close (US07-02).
+    The message names no path — it reaches API responses.
+
+    With no roots configured there is no boundary to check; that is a property of the
+    configuration, not permission granted to this call.
+    """
+    if is_excluded(path):
+        raise PathPolicyError("path is inside an excluded (_IGNORE/) tree")
+    roots = list(roots)
+    if not roots:
+        return Path(path)
+    for root in roots:
+        try:
+            return resolve_within(Path(root), path)
+        except PathPolicyError:
+            continue
+    raise PathPolicyError("path is outside the configured library roots")
+
+
 def iter_supported_files(root: os.PathLike | str) -> Iterator[Path]:
     """Yield supported, non-excluded files under ``root`` in deterministic order.
 

photo_pipeline/services/analysis.py

@@ -25,6 +25,7 @@ from typing import Protocol
 from sqlalchemy import func, select
 from sqlalchemy.orm import sessionmaker
 
+from photo_pipeline import path_policy
 from photo_pipeline.integrations import exiftool
 from photo_pipeline.models import AnalysisResult, Asset, SafetyReview
 from photo_pipeline.services import hashing
@@ -59,9 +60,16 @@ def _now() -> datetime:
 
 
 class AnalysisService:
-    def __init__(self, session_factory: sessionmaker, *, provider: VisionProvider | None = None) -> None:
+    def __init__(
+        self,
+        session_factory: sessionmaker,
+        *,
+        provider: VisionProvider | None = None,
+        library_roots: tuple = (),
+    ) -> None:
         self._session_factory = session_factory
         self._provider = provider
+        self._roots = tuple(library_roots)
 
     def _sfw_asset_ids(self, session) -> set[str]:
         """Asset ids whose latest safety decision is ``sfw`` — the ONLY assets that
@@ -136,6 +144,18 @@ class AnalysisService:
             if not path:
                 skipped += 1
                 continue
+            # Second gate, at the moment of use: the database says where the file
+            # was, the filesystem decides what that name means now. A link swapped
+            # under an asset after the scan would otherwise send bytes from outside
+            # the library — the one place that leaves this machine (US07-02).
+            try:
+                path = str(path_policy.resolve_in_roots(self._roots, path))
+            except path_policy.PathPolicyError as error:
+                self._store(
+                    asset_id, status="error", result=None, error=str(error), tokens=0, raw=""
+                )
+                errors += 1
+                continue
             try:
                 result = provider.analyze(path, album_hint=_album_hint(path))
             except Exception as error:  # provider/validation failure is per-asset

photo_pipeline/services/thumbnails.py

@@ -129,7 +129,10 @@ class ThumbnailService:
                 raise ThumbnailUnavailable(f"asset {asset_id} has no readable file")
             source = str(source)
             if source == asset.current_path:
-                self._validate_path(source)  # archive roots lie outside the library
+                # Render the *resolved* path the check approved: revalidating and then
+                # reopening the original name would let a symlink swapped in between
+                # the two steps decide which bytes are served (US07-02).
+                source = str(self._validate_path(source))  # archive roots lie outside
 
         # Rendering happens outside the DB session (no transaction held during I/O).
         try:
@@ -195,20 +198,16 @@ class ThumbnailService:
                 session.commit()
 
     # ── path safety ──────────────────────────────────────────────────────────
-    def _validate_path(self, current_path: str) -> None:
-        path = Path(current_path)
-        if path_policy.is_excluded(path):
-            raise PathNotAllowed(f"excluded path: {current_path}")
-        roots = self._config.library_roots
-        if not roots:
-            return
-        for root in roots:
-            try:
-                path_policy.resolve_within(Path(root), path)
-                return
-            except path_policy.PathPolicyError:
-                continue
-        raise PathNotAllowed(f"path outside configured roots: {current_path}")
+    def _validate_path(self, current_path: str) -> Path:
+        """The resolved path to read, or ``PathNotAllowed``.
+
+        The message names no path: a refusal is returned to the browser, and where
+        the library lives is not the caller's business (US07-02).
+        """
+        try:
+            return path_policy.resolve_in_roots(self._config.library_roots, current_path)
+        except path_policy.PathPolicyError as error:
+            raise PathNotAllowed(str(error)) from None
 
     # ── cache key + rendering ──────────────────────────────────────────────────
     @staticmethod

tests/conftest.py

@@ -1,4 +1,15 @@
-"""Make the repository root importable for the pipeline test suites."""
+"""Make the repository root importable for the pipeline test suites, and give every
+suite the application session the API requires since US07-02.
+
+The suites drive the API the way the browser does — module-level ``httpx`` calls and
+``TestClient`` — so instead of threading a cookie through several hundred call sites,
+both clients bootstrap the session themselves exactly like ``frontend/js/api.js``:
+fetch ``/api/v1/session`` once, then send the cookie plus the CSRF header, and
+re-bootstrap once on 401 (a restarted server issues a new session).
+
+Security tests deliberately bypass this by constructing their own ``httpx.Client``;
+only the module-level helpers are wrapped.
+"""
 
 import sys
 from pathlib import Path
@@ -6,3 +17,85 @@ from pathlib import Path
 REPO = Path(__file__).resolve().parents[1]
 if str(REPO) not in sys.path:
     sys.path.insert(0, str(REPO))
+
+import httpx
+import httpx._api  # httpx.get/post resolve `request` in this module
+import pytest
+from starlette.testclient import TestClient
+
+from photo_pipeline.api.security import CSRF_HEADER, SESSION_COOKIE
+
+_SESSIONS: dict[str, tuple[str, str]] = {}  # base url -> (session id, csrf token)
+
+
+def _base(url) -> str:
+    parts = httpx.URL(str(url))
+    return f"{parts.scheme}://{parts.netloc.decode()}"
+
+
+def _bootstrap(base: str) -> tuple[str, str]:
+    if base not in _SESSIONS:
+        response = httpx.Client(timeout=10).get(f"{base}/api/v1/session")
+        _SESSIONS[base] = (
+            response.cookies.get(SESSION_COOKIE, ""),
+            response.json().get("csrf_token", ""),
+        )
+    return _SESSIONS[base]
+
+
+def session_client(base_url: str, **kwargs) -> httpx.Client:
+    """An ``httpx.Client`` that has bootstrapped its own application session.
+
+    For suites that keep one client for a whole journey; it holds its own cookie, so
+    a client made after a server restart picks up the new session by construction.
+    """
+    client = httpx.Client(base_url=base_url, **kwargs)
+    client.headers[CSRF_HEADER] = client.get("/api/v1/session").json()["csrf_token"]
+    return client
+
+
+def _authorized(url, headers, cookies):
+    session_id, token = _bootstrap(_base(url))
+    headers = dict(headers or {})
+    headers.setdefault(CSRF_HEADER, token)
+    cookies = dict(cookies or {})
+    cookies.setdefault(SESSION_COOKIE, session_id)
+    return headers, cookies
+
+
+@pytest.fixture(autouse=True, scope="session")
+def _api_session():
+    real_request, real_stream = httpx._api.request, httpx._api.stream
+    real_client_request, real_client_init = TestClient.request, TestClient.__init__
+
+    def request(method, url, *, headers=None, cookies=None, **kwargs):
+        sent, jar = _authorized(url, headers, cookies)
+        response = real_request(method, url, headers=sent, cookies=jar, **kwargs)
+        if response.status_code == 401:
+            _SESSIONS.pop(_base(url), None)
+            sent, jar = _authorized(url, headers, cookies)
+            response = real_request(method, url, headers=sent, cookies=jar, **kwargs)
+        return response
+
+    def stream(method, url, *, headers=None, cookies=None, **kwargs):
+        sent, jar = _authorized(url, headers, cookies)
+        return real_stream(method, url, headers=sent, cookies=jar, **kwargs)
+
+    def client_init(self, app, *args, base_url="http://127.0.0.1", **kwargs):
+        # The default "http://testserver" is not a local host, which is exactly what
+        # the Host check refuses; in-process tests are still same-origin callers.
+        real_client_init(self, app, *args, base_url=base_url, **kwargs)
+
+    def client_request(self, method, url, *, headers=None, **kwargs):
+        if CSRF_HEADER not in self.headers:
+            response = real_client_request(self, "GET", "/api/v1/session")
+            self.headers[CSRF_HEADER] = response.json()["csrf_token"]
+        return real_client_request(self, method, url, headers=headers, **kwargs)
+
+    httpx._api.request, httpx.request = request, request
+    httpx._api.stream, httpx.stream = stream, stream
+    TestClient.request, TestClient.__init__ = client_request, client_init
+    yield
+    httpx._api.request, httpx.request = real_request, real_request
+    httpx._api.stream, httpx.stream = real_stream, real_stream
+    TestClient.request, TestClient.__init__ = real_client_request, real_client_init

tests/e2e/test_phase_a_pipeline.py

@@ -22,6 +22,8 @@ import numpy as np
 import pytest
 from PIL import Image
 
+from tests.conftest import session_client
+
 REPO = Path(__file__).resolve().parents[2]
 
 
@@ -92,7 +94,7 @@ class ServerController:
                 pytest.fail(f"server exited: {err.decode(errors='replace')}")
             try:
                 if httpx.get(f"{self.base}/api/v1/health/ready", timeout=1).status_code == 200:
-                    self.client = httpx.Client(base_url=self.base, timeout=10)
+                    self.client = session_client(self.base, timeout=10)
                     return
             except httpx.HTTPError:
                 time.sleep(0.2)

tests/e2e/test_review_ui.py

@@ -17,6 +17,9 @@ import httpx
 import numpy as np
 import pytest
 from PIL import Image
+from playwright.sync_api import expect
+
+from tests.conftest import session_client
 
 REPO = Path(__file__).resolve().parents[2]
 
@@ -111,7 +114,7 @@ def server(tmp_path):
         proc.terminate()
         pytest.fail("server never became ready")
 
-    client = httpx.Client(base_url=base, timeout=5)
+    client = session_client(base, timeout=5)
 
     def cluster_by_method(method):
         clusters = client.get("/api/v1/duplicates/clusters").json()["items"]
@@ -148,9 +151,9 @@ def test_fuzzy_decision_requires_confirmation(page, server):
     page.get_by_test_id("confirm").wait_for()
     assert "open" in page.get_by_test_id("cluster-state").inner_text()
     page.get_by_test_id("confirm-yes").click()
-    page.wait_for_function(
-        "document.querySelector('[data-testid=cluster-state]').innerText.includes('dismissed')"
-    )
+    # A locator assertion, not wait_for_function: the app's CSP forbids eval, and
+    # Playwright's polling predicate is evaluated as a string in the page (US07-02).
+    expect(page.get_by_test_id("cluster-state")).to_contain_text("dismissed")
 
 
 def test_stale_version_shows_conflict(page, server):
@@ -176,9 +179,9 @@ def test_decision_persists_after_reload(page, server):
     page.goto(f"{server.base}/app/#/duplicates/{cluster['id']}")
     page.get_by_test_id("not-duplicate").click()
     page.get_by_test_id("confirm-yes").click()
-    page.wait_for_function(
-        "document.querySelector('[data-testid=cluster-state]').innerText.includes('dismissed')"
-    )
+    # A locator assertion, not wait_for_function: the app's CSP forbids eval, and
+    # Playwright's polling predicate is evaluated as a string in the page (US07-02).
+    expect(page.get_by_test_id("cluster-state")).to_contain_text("dismissed")
     page.reload()
     page.get_by_test_id("cluster-state").wait_for()
     assert "dismissed" in page.get_by_test_id("cluster-state").inner_text()

tests/e2e/test_security.py

@@ -0,0 +1,280 @@
+"""US07-02 black-box security tests: authorization and path boundaries.
+
+Everything here talks to a real ``photo_pipeline serve`` child process over HTTP with
+its own ``httpx.Client``, deliberately outside the session helper the rest of the
+suite uses — an attacker does not get a bootstrapped client.
+
+The threat is a page in the user's browser, not a remote attacker: the app listens on
+127.0.0.1, so any site the user visits can send requests to it and can point an
+``<img>`` at its media endpoints. Each journey below is one of those attempts.
+"""
+
+from __future__ import annotations
+
+import json
+from contextlib import contextmanager
+from pathlib import Path
+
+import httpx
+import pytest
+
+from tests.e2e._pipeline_harness import Server, image, seed_library
+
+TIMEOUT = 20
+SENTINEL_KEY = "immich-sentinel-9f3a2b"
+SESSION_COOKIE = "pp_session"
+CSRF_HEADER = "X-CSRF-Token"
+
+# A GET, a mutation, and a media endpoint: the three shapes the policy must cover.
+PROTECTED = [
+    ("GET", "/api/v1/workflow", None),
+    ("POST", "/api/v1/albums/proposals", {}),
+    ("GET", "/api/v1/assets/{asset}/thumbnail?size=256", None),
+]
+
+
+@pytest.fixture(scope="module")
+def stack(tmp_path_factory):
+    """One server, one album of two photos, and a credential sentinel in its config."""
+    tmp_path = tmp_path_factory.mktemp("security")
+    seeded = seed_library(tmp_path, {"a": 1, "b": 2}, {"a": "sfw", "b": "sfw"})
+    outside = tmp_path / "outside"
+    outside.mkdir()
+    image(outside / "secret.jpg", 99)
+    server = Server(
+        seeded,
+        extra_env={
+            "PHOTO_PIPELINE_IMMICH_API_KEY": SENTINEL_KEY,
+            "PHOTO_PIPELINE_IMMICH_SERVER_URL": "http://127.0.0.1:1",
+        },
+    ).start()
+    yield server, seeded, outside
+    server.stop()
+
+
+@contextmanager
+def anonymous(server):
+    with httpx.Client(base_url=server.base, timeout=TIMEOUT) as client:
+        yield client
+
+
+@contextmanager
+def authenticated(server):
+    """A browser that has loaded the app: session cookie in the jar, token in a header."""
+    with httpx.Client(base_url=server.base, timeout=TIMEOUT) as client:
+        client.headers[CSRF_HEADER] = client.get("/api/v1/session").json()["csrf_token"]
+        yield client
+
+
+def call(client, method, path, body, asset):
+    return client.request(method, path.format(asset=asset), json=body)
+
+
+def test_the_api_refuses_every_caller_without_a_session(stack):
+    server, seeded, _ = stack
+    with anonymous(server) as client:
+        for method, path, body in PROTECTED:
+            response = call(client, method, path, body, seeded.asset_ids["a"])
+            assert response.status_code == 401, path
+            assert response.json()["error"]["code"] == "unauthenticated"
+        # Liveness and readiness stay open: an orchestrator holds no session.
+        assert client.get("/api/v1/health/ready").status_code == 200
+        assert client.get("/api/v1/health/live").status_code == 200
+
+
+def test_a_guessed_session_cookie_is_refused(stack):
+    server, _, _ = stack
+    with anonymous(server) as client:
+        client.cookies.set(SESSION_COOKIE, "guessed", domain="127.0.0.1")
+        response = client.get("/api/v1/workflow")
+        assert response.status_code == 401
+        assert response.json()["error"]["code"] == "unauthenticated"
+
+
+def test_the_bootstrap_issues_a_strict_httponly_cookie(stack):
+    server, _, _ = stack
+    with anonymous(server) as client:
+        response = client.get("/api/v1/session")
+        cookie = response.headers["set-cookie"].lower()
+        assert "httponly" in cookie and "samesite=strict" in cookie and "path=/" in cookie
+        assert response.json()["csrf_token"]
+        # The token is in the body, which no other origin may read: no CORS header
+        # grants access to it.
+        assert "access-control-allow-origin" not in response.headers
+
+
+def test_a_session_without_the_csrf_token_may_read_but_not_mutate(stack):
+    server, _, _ = stack
+    with authenticated(server) as client:
+        del client.headers[CSRF_HEADER]
+        assert client.get("/api/v1/albums/proposals").status_code == 200
+
+        response = client.post("/api/v1/albums/proposals", json={})
+        assert response.status_code == 403
+        assert response.json()["error"]["code"] == "csrf_failed"
+
+        response = client.post(
+            "/api/v1/albums/proposals", json={}, headers={CSRF_HEADER: "guessed"}
+        )
+        assert response.status_code == 403
+    # And nothing was created behind the refusal.
+    with authenticated(server) as client:
+        assert client.get("/api/v1/albums/proposals").json()["items"] == []
+
+
+def test_a_foreign_origin_cannot_mutate_even_with_a_session(stack):
+    server, _, _ = stack
+    with authenticated(server) as client:
+        for origin in ("http://evil.example", "http://127.0.0.1:1", "null"):
+            response = client.post(
+                "/api/v1/albums/proposals", json={}, headers={"Origin": origin}
+            )
+            assert response.status_code == 403, origin
+            assert response.json()["error"]["code"] == "origin_not_allowed"
+        # This app's own origin is accepted, so the check is not simply refusing all.
+        allowed = client.post(
+            "/api/v1/albums/proposals", json={}, headers={"Origin": server.base}
+        )
+        assert allowed.status_code == 200
+
+
+def test_a_rebinding_host_is_refused(stack):
+    """A name that resolves to 127.0.0.1 makes the browser treat the attacker's page
+    as same-origin. The Host header still carries that name, so it is checked."""
+    server, _, _ = stack
+    with authenticated(server) as client:
+        response = client.get("/api/v1/workflow", headers={"Host": "photos.evil.example"})
+        assert response.status_code == 403
+        assert response.json()["error"]["code"] == "host_not_allowed"
+
+
+def test_media_cannot_be_embedded_by_another_page(stack):
+    server, seeded, _ = stack
+    url = f"/api/v1/assets/{seeded.asset_ids['a']}/thumbnail?size=256"
+    with authenticated(server) as client:
+        # What an <img> on another site produces: no Origin, but a cross-site marker.
+        blocked = client.get(url, headers={"Sec-Fetch-Site": "cross-site"})
+        assert blocked.status_code == 403
+        assert blocked.json()["error"]["code"] == "cross_site_blocked"
+
+        served = client.get(url, headers={"Sec-Fetch-Site": "same-origin"})
+        assert served.status_code == 200
+        assert served.headers["content-type"] == "image/webp"
+        assert served.headers["cross-origin-resource-policy"] == "same-origin"
+        # Photos must never land in a shared cache.
+        assert served.headers["cache-control"].startswith("private")
+
+
+def test_every_response_carries_the_default_headers_and_no_cors(stack):
+    server, seeded, _ = stack
+    with authenticated(server) as client:
+        responses = [
+            client.get("/api/v1/workflow"),
+            client.get(f"/api/v1/assets/{seeded.asset_ids['a']}/thumbnail?size=256"),
+            client.get("/app/"),
+            client.get("/api/v1/does-not-exist"),
+        ]
+    for response in responses:
+        assert response.headers["x-content-type-options"] == "nosniff"
+        assert response.headers["x-frame-options"] == "DENY"
+        assert response.headers["referrer-policy"] == "no-referrer"
+        assert "frame-ancestors 'none'" in response.headers["content-security-policy"]
+        assert "access-control-allow-origin" not in response.headers
+        assert "access-control-allow-credentials" not in response.headers
+
+
+def test_a_traversal_attempt_addresses_nothing(stack):
+    """Identifiers are database keys, not paths: traversal has nowhere to land."""
+    server, _, _ = stack
+    with authenticated(server) as client:
+        for path in (
+            "/api/v1/albums/proposals/..%2F..%2F..%2Fetc%2Fpasswd",
+            "/api/v1/albums/proposals/../../../etc/passwd",
+            "/api/v1/assets/..%2F..%2Fetc%2Fpasswd/thumbnail?size=256",
+            "/api/v1/assets/%2Fetc%2Fpasswd/thumbnail?size=256",
+        ):
+            response = client.get(path)
+            assert response.status_code in (404, 422), path
+            assert "root:" not in response.text, path
+
+
+def test_an_oversized_request_is_refused_before_it_is_parsed(stack):
+    server, _, _ = stack
+    with authenticated(server) as client:
+        response = client.post(
+            "/api/v1/albums/proposals",
+            content=json.dumps({"albums": ["x" * 2_000_000]}),
+            headers={"Content-Type": "application/json"},
+        )
+        assert response.status_code == 413
+        assert response.json()["error"]["code"] == "payload_too_large"
+
+
+def test_a_malformed_request_reports_the_field_and_nothing_else(stack):
+    server, _, _ = stack
+    with authenticated(server) as client:
+        for content in ("{", '{"albums": 5}', ""):
+            response = client.post(
+                "/api/v1/albums/proposals",
+                content=content,
+                headers={"Content-Type": "application/json"},
+            )
+            assert response.status_code == 422, content
+            error = response.json()["error"]
+            assert error["code"] == "invalid_request"
+            assert "Traceback" not in response.text and "photo_pipeline/" not in response.text
+
+
+def test_errors_reveal_neither_the_credential_nor_an_internal(stack):
+    """The API key is configured but must appear nowhere; failures additionally say
+    nothing about where the library lives or how the server is built.
+
+    Successful responses are a different matter: path previews are the point of the
+    rename and archive views, and the operator is the one who owns those paths.
+    """
+    server, seeded, _ = stack
+    with authenticated(server) as client:
+        responses = [
+            client.post("/api/v1/upload-preflight", json={}),
+            client.get("/api/v1/workflow"),
+            client.get("/api/v1/upload-batches"),
+            client.get("/api/v1/assets/unknown-asset/thumbnail?size=256"),
+            client.get("/api/v1/archive-plans/unknown-plan"),
+            client.post("/api/v1/archive-locations", json={"name": "x", "root": "/nope"}),
+            client.get("/api/v1/does-not-exist"),
+        ]
+    for response in responses:
+        assert SENTINEL_KEY not in response.text
+        assert "Traceback" not in response.text
+        if response.status_code >= 400:
+            assert str(seeded.lib) not in response.text
+            assert "photo_pipeline/" not in response.text
+            assert "sqlite" not in response.text.lower()
+
+
+def test_a_symlink_swapped_under_an_asset_cannot_be_served(stack):
+    """TOCTOU on the media path: the file the database points at is replaced by a
+    link to something outside the library between the scan and the request."""
+    server, seeded, outside = stack
+    secret = outside / "secret.jpg"
+    original = seeded.lib / "b.jpg"
+    original.unlink()
+    original.symlink_to(secret)
+
+    with authenticated(server) as client:
+        response = client.get(f"/api/v1/assets/{seeded.asset_ids['b']}/thumbnail?size=256")
+    assert response.status_code == 403
+    assert response.json()["error"]["code"] == "path_not_allowed"
+    # The refusal names no filesystem location, and no bytes escaped with it.
+    assert str(outside) not in response.text and str(seeded.lib) not in response.text
+    assert secret.read_bytes()[:16] not in response.content
+
+
+def test_the_frontend_shell_stays_reachable_without_a_session(stack):
+    """It must load before any JavaScript can ask for a session."""
+    server, _, _ = stack
+    with anonymous(server) as client:
+        response = client.get("/app/", headers={"Sec-Fetch-Site": "none"})
+        assert response.status_code == 200
+        assert response.headers["content-type"].startswith("text/html")
+        assert Path("frontend/index.html").exists()

tests/integration/test_security_boundaries.py

@@ -0,0 +1,136 @@
+"""US07-02: what an unhandled failure says, and where the library ends.
+
+Two boundaries that only show up below the HTTP surface:
+
+* Exception text is where internals leak — absolute paths, SQL, and occasionally a
+  credential passed to the call that blew up. The first tests drive the real
+  application with a route that raises such an exception (no production route does)
+  and assert the client sees only a code.
+* The path the database recorded is not the path the filesystem will open a moment
+  later. Analysis is the one stage whose bytes leave this machine, so it resolves
+  the source against the library roots immediately before the provider call.
+"""
+
+from __future__ import annotations
+
+import logging
+import uuid
+from datetime import datetime, timezone
+
+import pytest
+from PIL import Image
+from starlette.testclient import TestClient
+
+from photo_pipeline.api.app import create_app
+from photo_pipeline.config import Config
+from photo_pipeline.db import create_db_engine, create_session_factory, run_migrations
+from photo_pipeline.models import AnalysisResult, Asset
+from photo_pipeline.services.analysis import AnalysisService
+from photo_pipeline.services.safety import SafetyService
+
+BOOM = "sqlite:///Users/someone/Pictures/private.db failed with key sk-secret-123"
+
+
+@pytest.fixture
+def client(tmp_path):
+    app = create_app(Config(data_dir=tmp_path / "data"))
+
+    @app.get("/api/v1/boom")
+    def boom():
+        raise RuntimeError(BOOM)
+
+    with TestClient(app, raise_server_exceptions=False) as test_client:
+        yield test_client
+
+
+def test_an_unhandled_error_returns_a_bare_envelope(client, caplog):
+    with caplog.at_level(logging.ERROR):
+        response = client.get("/api/v1/boom")
+
+    assert response.status_code == 500
+    assert response.json() == {"error": {"code": "internal_error", "message": "internal error"}}
+    assert BOOM not in response.text and "Traceback" not in response.text
+    # The operator still gets the whole story, on the server side.
+    assert BOOM in caplog.text
+
+
+def test_a_refusal_response_still_carries_the_default_headers(client):
+    """A 500 escaping the middleware's response path would also escape its headers."""
+    response = client.get("/api/v1/boom")
+    assert response.headers["x-content-type-options"] == "nosniff"
+    assert response.headers["x-frame-options"] == "DENY"
+
+
+# ── the library boundary, revalidated at the moment of use ───────────────────
+
+
+class RecordingProvider:
+    def __init__(self):
+        self.calls = []
+
+    def analyze(self, path, *, album_hint):
+        self.calls.append(path)
+        return {"description": "a photo", "tags": []}
+
+
+def _library(tmp_path):
+    lib = tmp_path / "lib"
+    lib.mkdir()
+    outside = tmp_path / "outside"
+    outside.mkdir()
+    for path in (lib / "inside.jpg", outside / "private.jpg"):
+        Image.new("RGB", (8, 8), "blue").save(path)
+    (tmp_path / "data").mkdir()
+    config = Config.from_env({"PHOTO_PIPELINE_DATA_DIR": str(tmp_path / "data")})
+    run_migrations(config.database_url)
+    return lib, outside, create_session_factory(create_db_engine(config.database_url))
+
+
+def _sfw_asset(sf, path):
+    asset = Asset(
+        id=str(uuid.uuid4()),
+        original_path=str(path),
+        current_path=str(path),
+        discovered_at=datetime.now(timezone.utc),
+        hash_version=1,
+    )
+    with sf() as session:
+        session.add(asset)
+        session.commit()
+    SafetyService(sf).decide(asset.id, "sfw", write_exif=False)
+    return asset.id
+
+
+def test_analysis_will_not_send_a_file_that_left_the_library(tmp_path):
+    """A link swapped under an asset after the scan points at something the user
+    never put in the library. Those bytes must not reach the vision provider — it is
+    the one place in the pipeline where content leaves this machine."""
+    lib, outside, sf = _library(tmp_path)
+    inside = lib / "inside.jpg"
+    asset_id = _sfw_asset(sf, inside)
+    inside.unlink()
+    inside.symlink_to(outside / "private.jpg")
+
+    provider = RecordingProvider()
+    result = AnalysisService(sf, provider=provider, library_roots=(lib,)).run([asset_id])
+
+    assert provider.calls == [], "the provider must never have been constructed a request"
+    assert result == {"analyzed": 0, "skipped": 0, "errors": 1}
+    with sf() as session:
+        row = session.get(AnalysisResult, asset_id)
+    # The failure is visible and names no path.
+    assert row.status == "error"
+    assert "outside the configured library roots" in row.error_message
+    assert str(outside) not in row.error_message
+
+
+def test_analysis_still_reads_a_file_that_stayed_inside(tmp_path):
+    """The guard must resolve real paths, not refuse everything."""
+    lib, _, sf = _library(tmp_path)
+    asset_id = _sfw_asset(sf, lib / "inside.jpg")
+
+    provider = RecordingProvider()
+    result = AnalysisService(sf, provider=provider, library_roots=(lib,)).run([asset_id])
+
+    assert result["analyzed"] == 1
+    assert provider.calls == [str((lib / "inside.jpg").resolve())]

tests/story_traceability.json

@@ -147,6 +147,11 @@
     "US07-01": [
       "tests/unit/test_legacy_archive.py",
       "tests/integration/test_legacy_import.py"
+    ],
+    "US07-02": [
+      "tests/unit/test_security_policy.py",
+      "tests/integration/test_security_boundaries.py",
+      "tests/e2e/test_security.py"
     ]
   }
 }

tests/unit/test_path_policy.py

@@ -81,3 +81,42 @@ def test_symlink_within_root_is_allowed(tmp_path):
         pytest.skip("cannot create symlink on this platform")
     found = path_policy.discover([root])
     assert target in found and link in found
+
+
+def test_resolve_in_roots_returns_the_path_the_caller_must_use(tmp_path):
+    """The resolved path is the answer, not a yes/no: a caller that revalidates one
+    name and then opens another has an open symlink race (US07-02)."""
+    root = tmp_path / "lib"
+    (root / "sub").mkdir(parents=True)
+    target = root / "sub" / "real.jpg"
+    target.write_bytes(b"x")
+    link = root / "alias.jpg"
+    os.symlink(target, link)
+
+    assert path_policy.resolve_in_roots([root], link) == target.resolve()
+    assert path_policy.resolve_in_roots([root], target) == target.resolve()
+
+
+def test_resolve_in_roots_refuses_escapes_without_naming_them(tmp_path):
+    root = tmp_path / "lib"
+    root.mkdir()
+    outside = tmp_path / "outside.jpg"
+    outside.write_bytes(b"x")
+    link = root / "alias.jpg"
+    os.symlink(outside, link)
+
+    for candidate in (link, outside, root / "_IGNORE" / "a.jpg"):
+        with pytest.raises(path_policy.PathPolicyError) as raised:
+            path_policy.resolve_in_roots([root], candidate)
+        assert str(outside) not in str(raised.value)
+
+
+def test_resolve_in_roots_checks_every_configured_root(tmp_path):
+    first, second = tmp_path / "one", tmp_path / "two"
+    first.mkdir()
+    second.mkdir()
+    photo = second / "b.jpg"
+    photo.write_bytes(b"x")
+    assert path_policy.resolve_in_roots([first, second], photo) == photo.resolve()
+    # No configured boundary means nothing to check against.
+    assert path_policy.resolve_in_roots([], photo) == photo

tests/unit/test_security_policy.py

@@ -0,0 +1,169 @@
+"""US07-02: the request-admission policy, enumerated.
+
+``evaluate`` decides every refusal the API can make before a route runs, so the
+whole local-web threat model is one table here: who may call, from where, with what
+proof. The middleware and the endpoints are covered black box in
+``tests/e2e/test_security.py``; this file pins the rules themselves, including the
+combinations a browser can produce but a test client rarely does.
+"""
+
+from __future__ import annotations
+
+import pytest
+
+from photo_pipeline.api.security import (
+    CSRF_HEADER,
+    PUBLIC_PATHS,
+    Session,
+    evaluate,
+    split_host,
+)
+
+SESSION = Session(id="session-id", csrf_token="csrf-token")
+HOST = "127.0.0.1:8000"
+LIMIT = 1024
+
+
+def check(method="GET", path="/api/v1/workflow", **headers):
+    """Evaluate a request that is authenticated and same-origin unless overridden."""
+    sent = {
+        "host": HOST,
+        "cookie-session": SESSION.id,
+        CSRF_HEADER: SESSION.csrf_token,
+    }
+    sent.update({name.replace("_", "-"): value for name, value in headers.items()})
+    sent = {name: value for name, value in sent.items() if value is not None}
+    return evaluate(
+        method=method,
+        path=path,
+        headers=sent,
+        session=SESSION,
+        max_request_bytes=LIMIT,
+    )
+
+
+def test_an_authenticated_same_origin_request_is_admitted():
+    assert check() is None
+    assert check(method="POST", origin="http://127.0.0.1:8000") is None
+    assert check(sec_fetch_site="same-origin") is None
+
+
+@pytest.mark.parametrize("host", ["evil.example", "evil.example:8000", "192.168.1.10:8000", ""])
+def test_a_non_loopback_host_is_refused(host):
+    """DNS rebinding: the browser thinks it is talking to the attacker's name, which
+    resolves to 127.0.0.1. The name is the evidence, so the name is checked."""
+    refusal = check(host=host)
+    assert (refusal.status, refusal.code) == (403, "host_not_allowed")
+
+
+@pytest.mark.parametrize("host", ["127.0.0.1:8000", "localhost:8000", "[::1]:8000", "localhost"])
+def test_loopback_hosts_are_accepted(host):
+    assert check(host=host) is None
+
+
+@pytest.mark.parametrize(
+    "origin",
+    [
+        "http://evil.example",
+        "https://evil.example:8000",
+        "http://127.0.0.1:9999",  # another local app is still another origin
+        "http://localhost.evil.example:8000",
+        "null",
+        "file://",
+    ],
+)
+def test_a_foreign_origin_is_refused(origin):
+    refusal = check(method="POST", origin=origin)
+    assert (refusal.status, refusal.code) == (403, "origin_not_allowed")
+
+
+@pytest.mark.parametrize("origin", ["http://127.0.0.1:8000", "http://localhost:8000"])
+def test_this_applications_origin_is_accepted(origin):
+    assert check(method="POST", origin=origin) is None
+
+
+@pytest.mark.parametrize("site", ["cross-site", "same-site"])
+def test_a_cross_site_fetch_is_refused_even_without_an_origin(site):
+    """What ``<img src="http://127.0.0.1:8000/...">`` on another page looks like."""
+    refusal = check(path="/api/v1/assets/a1/thumbnail", sec_fetch_site=site)
+    assert (refusal.status, refusal.code) == (403, "cross_site_blocked")
+
+
+def test_a_user_initiated_navigation_is_accepted():
+    assert check(sec_fetch_site="none") is None
+
+
+def test_a_request_without_a_session_is_unauthenticated():
+    for method, path in [
+        ("GET", "/api/v1/workflow"),
+        ("POST", "/api/v1/jobs"),
+        ("GET", "/api/v1/assets/a1/thumbnail"),
+    ]:
+        refusal = check(method=method, path=path, cookie_session=None)
+        assert (refusal.status, refusal.code) == (401, "unauthenticated"), path
+
+
+def test_a_forged_session_is_unauthenticated():
+    refusal = check(cookie_session="guessed")
+    assert (refusal.status, refusal.code) == (401, "unauthenticated")
+
+
+@pytest.mark.parametrize("path", sorted(PUBLIC_PATHS))
+def test_health_and_the_bootstrap_stay_reachable_without_a_session(path):
+    assert check(path=path, cookie_session=None) is None
+
+
+def test_the_static_shell_needs_no_session():
+    """It has to load before any JavaScript can ask for one."""
+    assert check(path="/app/index.html", cookie_session=None) is None
+
+
+@pytest.mark.parametrize("method", ["POST", "PUT", "PATCH", "DELETE"])
+def test_a_mutation_without_a_valid_csrf_token_is_refused(method):
+    for token in (None, "guessed"):
+        refusal = check(method=method, path="/api/v1/jobs", **{CSRF_HEADER: token})
+        assert (refusal.status, refusal.code) == (403, "csrf_failed")
+
+
+@pytest.mark.parametrize("method", ["GET", "HEAD", "OPTIONS"])
+def test_reads_need_no_csrf_token(method):
+    assert check(method=method, **{CSRF_HEADER: None}) is None
+
+
+def test_an_oversized_body_is_refused_before_it_is_read():
+    refusal = check(method="POST", path="/api/v1/jobs", content_length=str(LIMIT + 1))
+    assert (refusal.status, refusal.code) == (413, "payload_too_large")
+    assert check(method="POST", path="/api/v1/jobs", content_length=str(LIMIT)) is None
+
+
+def test_the_host_check_precedes_authentication():
+    """A refusal must not tell a foreign caller whether its session guess was right."""
+    refusal = check(host="evil.example", cookie_session="guessed")
+    assert refusal.code == "host_not_allowed"
+
+
+def test_refusals_name_no_path_secret_or_internal():
+    refusals = [
+        check(host="evil.example"),
+        check(method="POST", origin="http://evil.example"),
+        check(cookie_session=None),
+        check(method="POST", **{CSRF_HEADER: None}),
+    ]
+    for refusal in refusals:
+        assert SESSION.id not in refusal.message
+        assert SESSION.csrf_token not in refusal.message
+        assert "/" not in refusal.message
+
+
+@pytest.mark.parametrize(
+    "value,expected",
+    [
+        ("127.0.0.1:8000", ("127.0.0.1", "8000")),
+        ("localhost", ("localhost", "")),
+        ("[::1]:8000", ("[::1]", "8000")),
+        ("[::1]", ("[::1]", "")),
+        ("", ("", "")),
+    ],
+)
+def test_split_host(value, expected):
+    assert split_host(value) == expected