brain-of-reese/tests/unit/test_stale_ui_copy.py

"""Unit: phase-61 text pins — the retired homelab-era copy is GONE, the
locked neutral replacements are PRESENT (house pattern: read the files
as text, assert substrings — no browser, cf. test_frontend_brand.py).

The browser-visible layer is gated by the story suite
(``tests/e2e/test_stale_ui_copy.py``); these pins catch a silent
regression in the templates / the ``Settings`` defaults without it.
"""
from __future__ import annotations

import re
from pathlib import Path

FRONTEND = Path(__file__).resolve().parents[2] / "frontend"
ROOT = FRONTEND.parent
CONFIG_PY = ROOT / "app" / "config.py"

#: Every page in the app ships a footer (the phase-39 ``HTML_PAGES``
#: tuple, repeated here so this file stands alone).
HTML_PAGES = (
    "index.html",
    "sources.html",
    "tuning.html",
    "document.html",
    "login.html",
    "git-sources.html",
    "history.html",
    "shared.html",
    "doc-edit.html",
)

# --- the locked replacement copy (owner-locked A1 / A2) ----------------

META = "Ask anything about your indexed documents — every answer cites the exact doc."
EMPTY_SUB = (
    "I've read through your documents — ask me anything, and I'll point "
    "you at the exact doc. You've got this."
)
PLACEHOLDER = "Ask me anything…"
PAGE_SUB = (
    "Every file indexed from your configured sources — git repositories, "
    "local directories, and uploaded archives. Press <strong>Sync "
    "sources</strong> to pull the latest and re-import."
)
FOOTER = "Powered by self-hosted models"

CHIPS = [
    "What documents are in the knowledge base?",
    "Which source does each answer come from?",
    "How do I add a new source?",
    "Summarize the most recent document.",
]

# --- the retired homelab-era copy (must be nowhere) --------------------

OLD_META_FRAG = "the homelab and deployments"
OLD_SUB_FRAG = "the homelab and deployment notes"
OLD_PLACEHOLDER_FRAG = "Ask me about the homelab"
OLD_FOOTER = "Reese's self-hosted models"
OLD_GIT_EXAMPLE = "github.com/you/homelab"

OLD_CHIPS = [
    "How is my Kubernetes cluster set up?",
    "What's my backup strategy?",
    "How do I deploy a new service?",
    "What's currently running in the homelab?",
]


def _text(path: Path) -> str:
    return path.read_text(encoding="utf-8")


def _norm(text: str) -> str:
    """Collapse whitespace runs — the templates wrap long lines, so the
    locked copy is pinned against the normalized text."""
    return re.sub(r"\s+", " ", text).strip()


def test_chat_page_old_copy_is_gone() -> None:
    """index.html: the old meta fragment, the old empty-state sub
    fragment, the old composer placeholder and the old footer are all
    retired. (The L176 code comment still says 'homelab' — A3: comments
    are not user-visible and stay untouched, so only the exact old
    user-visible strings are pinned.)"""
    html = _text(FRONTEND / "index.html")
    for frag in (OLD_META_FRAG, OLD_SUB_FRAG, OLD_PLACEHOLDER_FRAG, OLD_FOOTER):
        assert frag not in html, f"retired chat copy still present: {frag!r}"


def test_sources_page_old_copy_is_gone() -> None:
    """sources.html: the ~/Homelab + ~/Deployments page-sub citations and
    the old footer are retired."""
    html = _text(FRONTEND / "sources.html")
    for frag in ("~/Homelab", "~/Deployments", OLD_FOOTER):
        assert frag not in html, f"retired sources copy still present: {frag!r}"


def test_git_sources_page_old_copy_is_gone() -> None:
    """git-sources.html: the old example repo URL (A3) and the old
    footer are retired."""
    html = _text(FRONTEND / "git-sources.html")
    for frag in (OLD_GIT_EXAMPLE, OLD_FOOTER):
        assert frag not in html, f"retired git-sources copy still present: {frag!r}"


def test_chat_page_locked_copy_present_exactly_once() -> None:
    """The three locked (A1) chat strings, each exactly once in
    index.html (a second copy could drift out of sync)."""
    html = _norm(_text(FRONTEND / "index.html"))
    assert html.count(META) == 1, "the locked meta description"
    assert html.count(EMPTY_SUB) == 1, "the locked empty-state sub"
    assert html.count(PLACEHOLDER) == 1, "the locked composer placeholder"


def test_sources_page_sub_is_the_locked_copy() -> None:
    """The KB .page-sub (the string the TODO cited by name) reads the
    locked (A1) copy, including the <strong> around Sync sources —
    pinned inside the .page-sub element, not anywhere in the file."""
    html = _text(FRONTEND / "sources.html")
    m = re.search(r'<p class="page-sub">(.*?)</p>', html, re.DOTALL)
    assert m, "sources.html must keep the .page-sub"
    assert _norm(m.group(1)) == PAGE_SUB


def test_all_nine_footers_are_the_locked_neutral_default() -> None:
    """Every page carries the locked (A1) footer inside exactly one
    ``class="footer-text"`` span (the stable hook phase 62's
    BOR_FOOTER_TEXT env var drives)."""
    span = f'<span class="footer-text">{FOOTER}</span>'
    for page in HTML_PAGES:
        html = _text(FRONTEND / page)
        assert html.count('class="footer-text"') == 1, (
            f"{page}: exactly one .footer-text span"
        )
        assert html.count(span) == 1, f"{page}: the locked neutral footer"


def test_config_default_chips_are_the_locked_list_in_order() -> None:
    """The ``Settings.suggestions`` default (app/config.py) is exactly
    the four locked (A2) chips, in order (the E2E conftest derives the
    app-under-test env from this field — it can never drift)."""
    config = _text(CONFIG_PY)
    m = re.search(r"suggestions: list\[str\] = \[(.*?)\]", config, re.DOTALL)
    assert m, "the suggestions default list must exist in app/config.py"
    block = m.group(1)
    positions = []
    for chip in CHIPS:
        assert f'"{chip}"' in block, f"locked chip missing from the default: {chip!r}"
        positions.append(block.index(f'"{chip}"'))
    assert positions == sorted(positions), "the chips must keep the locked order"


def test_old_chips_are_retired_not_relocated() -> None:
    """The four old default chips are retired, not relocated: they must
    appear NOWHERE in the app source (app/ + frontend/) — config.py
    included (the scan covers it)."""
    for base in (ROOT / "app", FRONTEND):
        for path in sorted(base.rglob("*")):
            if not path.is_file() or "__pycache__" in path.parts:
                continue
            text = path.read_text(encoding="utf-8")
            for chip in OLD_CHIPS:
                assert chip not in text, (
                    f"retired chip {chip!r} relocated to {path.relative_to(ROOT)}"
                )