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

"""Phase 33 E2E (Playwright): cache busting — what the browser actually
receives and requests.

Story: ``.agent/user_stories/cache-busting.md``
Run in isolation (DB must be up: ``podman compose up -d db``):

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

The assertions are against the wire: the HTML document responses carry
``Cache-Control: no-cache``; every asset request URL the browser actually
makes carries ``?v=<token>`` (one token per process — the git short SHA of
this checkout, i.e. the deploy); the asset responses are immutable for a
year; and the API — the SSE chat stream in particular — is untouched. The
mock LLM keeps the SSE check deterministic (no live aipi).
"""
from __future__ import annotations

import json
import re
from pathlib import Path
from typing import Any

import httpx
from playwright.sync_api import Page

from e2e.auth_helpers import login

REPO = Path(__file__).resolve().parents[2]
CHAT_QUESTION = "How is my Kubernetes cluster set up?"
SHARE_URL_RE = re.compile(r"^/shared/[0-9a-f-]{36}$")


def _expected_token() -> str:
    """The token the app process appends to its asset URLs.

    Computed exactly the way the app does (``asset_version`` over the same
    static dir): the git short SHA of this checkout in a git repo (a commit
    is a deploy), so the browser's asset requests must carry it.
    """
    from app.core.caching import asset_version

    return asset_version(str(REPO / "frontend"))


def _version_token(url: str) -> str:
    """Extract the ``?v=`` token from a versioned asset URL (asserts one)."""
    assert "?v=" in url, f"asset request is not versioned: {url}"
    return url.rsplit("?v=", 1)[1]


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


def _stream_chat_frames(app_url: str, message: str) -> list[dict[str, Any]]:
    """Minimal SSE chat request (same pattern as ``test_chat_rag.py``):
    POST /api/chat and collect the ``data:`` frames until the stream ends."""
    frames: list[dict[str, Any]] = []
    with httpx.stream(
        "POST", f"{app_url}/api/chat", json={"message": message}, timeout=60.0
    ) as r:
        assert r.status_code == 200
        assert r.headers["content-type"].startswith("text/event-stream")
        buf = ""
        for part in r.iter_text():
            buf += part
            while "\n\n" in buf:
                frame, buf = buf.split("\n\n", 1)
                if frame.strip().startswith("data:"):
                    frames.append(
                        json.loads(frame.strip().removeprefix("data:").strip())
                    )
    return frames


def test_html_pages_are_no_cache_and_versioned(page: Page, app_url: str) -> None:
    """`/`: the document revalidates (no-cache); the CSS/JS request URLs
    the browser actually makes carry the process token; the asset
    responses are immutable for a year; the served HTML carries no
    unversioned asset references."""
    token = _expected_token()
    assert token, "the version token must be non-empty"

    with (
        page.expect_response(lambda r: "/assets/styles.css" in r.url) as css_info,
        page.expect_response(lambda r: "/assets/app.js" in r.url) as js_info,
    ):
        doc = page.goto(app_url)

    # The document: always revalidated, never served from cache unchecked.
    assert doc is not None
    assert doc.headers["cache-control"] == "no-cache"

    # CSS: versioned request URL + immutable-for-a-year response.
    css = css_info.value
    assert _version_token(css.url) == token
    css_cc = css.headers["cache-control"]
    assert "immutable" in css_cc
    assert "max-age=31536000" in css_cc

    # JS: the SAME token (one per process — the URL identifies the
    # content, which is what makes the 1-year cache safe).
    assert _version_token(js_info.value.url) == _version_token(css.url)

    # The served HTML carries the versioned reference and no unversioned
    # one (the "sticky" reference is gone from the page the browser sees).
    html = page.content()
    assert f'href="/assets/styles.css?v={token}"' in html
    assert '/assets/styles.css"' not in html


def test_other_pages_share_the_token(page: Page, app_url: str) -> None:
    """/sources.html, /login.html, /history.html (phase 50) and
    /doc-edit.html (phase 59): each document revalidates, and all four
    pages' stylesheet requests carry the same process token."""
    token = _expected_token()
    assert token

    def navigate(path: str) -> str:
        with page.expect_response(
            lambda r: "/assets/styles.css" in r.url
        ) as css_info:
            doc = page.goto(f"{app_url}{path}")
        assert doc is not None
        assert doc.headers["cache-control"] == "no-cache"
        return _version_token(css_info.value.url)

    sources_token = navigate("/sources.html")
    login_token = navigate("/login.html")
    history_token = navigate("/history.html")  # phase 50: the new page
    docedit_token = navigate("/doc-edit.html")  # phase 59: the doc edit screen
    assert sources_token == login_token == history_token == docedit_token == token


def test_shared_page_is_no_cache_and_versioned(
    page: Page, app_url: str, db_ready: None
) -> None:
    """`/shared/<token>` (phase 51, the dynamic share page): the same
    contract as the static HTML pages — the document revalidates
    (no-cache) and the served HTML's asset refs are `?v=`-tagged (the
    middleware's prefix extension, task 01). The chat is created +
    shared via the admin API for the test."""
    token = _expected_token()
    assert token, "the version token must be non-empty"

    login(page, app_url, next="/")
    cookies = _admin_cookies(page)
    r = httpx.post(
        f"{app_url}/api/chats",
        json={
            "messages": [
                {"who": "user", "text": "cache-busting shared-page probe"},
                {"who": "brain", "text": "Shared for the cache contract."},
            ],
            "share": True,
        },
        timeout=10,
        cookies=cookies,
    )
    assert r.status_code == 201
    body = r.json()
    assert SHARE_URL_RE.fullmatch(body["share_url"]), body["share_url"]
    try:
        with page.expect_response(lambda r: "/assets/styles.css" in r.url) as css_info:
            doc = page.goto(app_url + body["share_url"])

        # The document: always revalidated, like every HTML page.
        assert doc is not None
        assert doc.headers["cache-control"] == "no-cache"

        # The CSS request the browser actually makes carries the
        # process token…
        assert _version_token(css_info.value.url) == token

        # …and the served HTML references its assets versioned (the
        # page uses ABSOLUTE /assets refs — required for the nested
        # /shared/<token> path).
        html = page.content()
        assert f'href="/assets/styles.css?v={token}"' in html
        assert f'src="/assets/brand.js?v={token}"' in html
        assert f'src="/assets/markdown.js?v={token}"' in html
        assert f'src="/assets/shared.js?v={token}"' in html

        # No unversioned reference survives the rewrite.
        assert 'href="/assets/styles.css"' not in html
        assert 'src="/assets/shared.js"' not in html
    finally:
        httpx.delete(f"{app_url}/api/chats/{body['id']}", timeout=10, cookies=cookies)


def test_api_responses_unaffected(page: Page, app_url: str, db_ready: None) -> None:
    """`/api/*` passes through untouched: no injected Cache-Control on the
    health endpoint, and the SSE chat stream still streams to done."""
    r = page.request.get(f"{app_url}/api/health")
    assert r.status == 200
    # Baseline (pre-middleware) behavior: FastAPI's JSON responses ship no
    # Cache-Control header — the middleware must not inject one.
    assert "cache-control" not in r.headers

    # The SSE contract (PLAN §4) survives the middleware: deltas, then a
    # final done — the stream is neither read nor rewritten by it.
    frames = _stream_chat_frames(app_url, CHAT_QUESTION)
    assert frames, "the SSE stream must deliver events"
    assert any(f["type"] == "delta" for f in frames), "answer must be streamed"
    assert frames[-1]["type"] == "done", "the stream must complete with done"