brain-of-reese/tests/e2e/test_chat_save_payload_limits.py

"""Phase 83 E2E (Playwright): the anonymous saved-chat payload
boundary (SEC-05) — the audit vector through a real browser's network
layer.

Run in isolation (DB must be up: ``podman compose up -d db``):

    uv run pytest tests/e2e/test_chat_save_payload_limits.py -v --no-cov

The contract under test (phase 83 — boundary-only hardening of the
PUBLIC write surface ``POST/PUT /api/chats``; the caps live in
``app/schemas.py`` and FastAPI rejects before the handler runs, A2):

* **Oversized save 422s, anonymously** — the exact audit vector (one
  40_000-char message, NO session, driven through the page's
  ``page.request`` context — the browser's own network layer) is
  rejected at the schema boundary with a 422 and NOTHING is stored
  (the admin list carries no row for the probe's distinctive
  auto-title — the shared e2e DB may hold other suites' rows, so the
  "nothing stored" proof is title-scoped, the house convention);
* **Small save still 201s** — a normal in-cap save through the same
  anonymous network layer lands 201 with a valid ``id``: the boundary
  tightened the DoS surface without breaking the real (in-cap) flow
  the UI produces.

No LLM dependency — both endpoints are DB-only (the session-scoped
mock LLM stays up as an ``app_server`` dependency but is never
called).
"""
from __future__ import annotations

import uuid

import httpx
from playwright.sync_api import Page, expect

from e2e.auth_helpers import login

#: The probe's distinctive marker: if the oversized row had been
#: stored, its auto-title (first user message, whitespace-collapsed,
#: 120-char cap) would start with exactly this string — unique in the
#: shared e2e DB.
PROBE_MARKER = "payload-limit-probe (phase 83 e2e)"


def _admin_cookies(page: Page) -> dict[str, str]:
    """The signed session cookies the browser holds after a form login."""
    return {
        c["name"]: c["value"]
        for c in page.context.cookies()
        if "name" in c and "value" in c
    }


def _settled_anonymous(page: Page, app_url: str) -> None:
    """Land on the chat page in the settled anonymous state (fresh
    context — no login): the whoami round-trip has landed, so the
    ``page.request`` calls below carry no session cookie (the write
    surface is public — anonymity is the audit vector)."""
    page.goto(app_url + "/")
    expect(page.locator("#sign-in-link")).to_be_visible(timeout=15_000)


def test_anonymous_oversized_save_422s_and_stores_nothing(
    page: Page, app_url: str, db_ready: None
) -> None:
    page.set_default_timeout(30_000)
    _settled_anonymous(page, app_url)

    text = PROBE_MARKER + " " + "x" * (40_000 - len(PROBE_MARKER) - 1)
    assert len(text) == 40_000
    # The audit vector, end-to-end and anonymous: one 40_000-char
    # message through the page's request context (no session cookie).
    r = page.request.post(
        app_url + "/api/chats",
        data={
            "messages": [
                {"who": "user", "text": text},
                {"who": "brain", "text": "ok"},
            ]
        },
    )
    assert r.status == 422, (
        f"the oversized body must 422 at the schema boundary: {r.text()}"
    )

    # Nothing stored: the list surface is admin-only, so sign in now
    # (the 422 above happened BEFORE any session existed — the write
    # surface is public, exactly the audit vector) and prove no row
    # carries the probe's distinctive auto-title.
    login(page, app_url, next="/")
    cookies = _admin_cookies(page)
    body = httpx.get(f"{app_url}/api/chats", timeout=10, cookies=cookies)
    assert body.status_code == 200
    rows = body.json()["chats"]
    assert not any(c["title"].startswith(PROBE_MARKER) for c in rows), (
        f"the oversized probe must not have been stored: {rows}"
    )


def test_small_anonymous_save_still_201s(
    page: Page, app_url: str, db_ready: None
) -> None:
    page.set_default_timeout(30_000)
    _settled_anonymous(page, app_url)

    q = "How do I prune deleted docs? (phase 83 e2e small save)"
    created: str | None = None
    try:
        # The happy path from the same anonymous network layer: the
        # boundary tightened the DoS surface without breaking the
        # real (in-cap) save flow the UI produces.
        r = page.request.post(
            app_url + "/api/chats",
            data={
                "messages": [
                    {"who": "user", "text": q},
                    {"who": "brain", "text": "Use --prune. (phase 83 e2e)"},
                ]
            },
        )
        assert r.status == 201, f"the in-cap save must still land: {r.text()}"
        body = r.json()
        uuid.UUID(body["id"])  # a valid row id
        assert body["title"] == q  # auto-title = first user message
        assert body["message_count"] == 2
        created = body["id"]
    finally:
        if created is not None:
            login(page, app_url, next="/")
            httpx.delete(
                f"{app_url}/api/chats/{created}", timeout=10, cookies=_admin_cookies(page)
            )