fix(web): retire the stale homelab-era copy — neutral, accurate defaults on every page

Fixed: index.html meta description, empty-state sub and composer
placeholder (A1); app/config.py default suggestion chips → the four
neutral A2 defaults (BOR_SUGGESTIONS override unchanged); sources.html
KB page-sub → the current source model (git repos + local dirs +
uploaded archives, Sync pulls/imports); git-sources.html example URL
→ your-repo.git (A3); all 9 footers → neutral default in
span.footer-text (the phase-62 hook); E2E/unit conftests force the
code defaults so a local .env cannot leak corpus copy into tests;
new unit text pins + dedicated E2E suite.

Task 02 verification read-through — no change needed:
- sources.html sync result/error copy (matches the real sync behavior)
- tuning.html page-sub (accurate as written)
- history.html page-sub (accurate as written)
- doc-edit.html page-sub (accurate as written)
- git-sources.html page-sub (accurate as written)
- #sources-gate anonymous copy (accurate as written)
This commit is contained in:
2026-09-01 10:54:50 -04:00
parent 4971e2859d
commit baefcde668
16 changed files with 344 additions and 23 deletions
+15
View File
@@ -1,6 +1,7 @@
"""Shared fixtures for unit + integration tests."""
from __future__ import annotations
import json
import os
from collections.abc import Iterator
@@ -23,6 +24,20 @@ SESSION_SECRET = "test-session-secret-0123456789abcdef0123456789abcdef"
os.environ.setdefault("BOR_ADMIN_PASSWORD", ADMIN_PASSWORD)
os.environ.setdefault("BOR_SESSION_SECRET", SESSION_SECRET)
# Phase 61 (defect fix): the app under test must see the code DEFAULTS,
# not an operator's local (gitignored) ``.env`` — ``Settings`` loads
# ``env_file=".env"`` from the repo root, and a machine-specific corpus
# (e.g. ``BOR_SUGGESTIONS``, ``BOR_DOCS_REPO``) leaked into the tests
# broke the default-metadata pins. pydantic-settings ranks process env
# vars ABOVE the ``.env`` file, so force the defaults explicitly here,
# before ``app.main`` (below) caches settings. The suggestions default
# is derived from the class field so this can never drift from
# ``app/config.py``; docs-push stays inert (empty repo).
from app.config import Settings as _Settings # noqa: E402
os.environ["BOR_DOCS_REPO"] = ""
os.environ["BOR_SUGGESTIONS"] = json.dumps(_Settings.model_fields["suggestions"].default)
from app.db import SessionLocal, db_available # noqa: E402
from app.main import app as fastapi_app # noqa: E402
+13
View File
@@ -14,6 +14,7 @@ Prerequisite for story tests that touch the database:
"""
from __future__ import annotations
import json
import os
import subprocess
import sys
@@ -25,6 +26,8 @@ import httpx
import pytest
from playwright.sync_api import Browser, Page, sync_playwright
from app.config import Settings as _Settings
REPO = Path(__file__).resolve().parents[2]
APP_PORT = int(os.environ.get("E2E_APP_PORT", "8123"))
MOCK_PORT = int(os.environ.get("E2E_MOCK_PORT", "8901"))
@@ -99,6 +102,16 @@ def app_server(mock_llm: int) -> Iterator[str]:
# Phase 16: admin auth must be set or create_app() refuses to boot.
env["BOR_ADMIN_PASSWORD"] = ADMIN_PASSWORD
env["BOR_SESSION_SECRET"] = SESSION_SECRET
# Phase 61 (defect fix): force the code DEFAULTS so an operator's local
# (gitignored) ``.env`` — loaded by pydantic-settings from ``cwd=REPO``
# — cannot leak corpus-specific chips / a docs repo into the app under
# test: process env ranks above the ``.env`` file. The suggestions
# default is derived from the class field (never drifts from
# ``app/config.py``); docs-push stays inert (empty repo).
env["BOR_DOCS_REPO"] = ""
env["BOR_SUGGESTIONS"] = json.dumps(
_Settings.model_fields["suggestions"].default
)
proc = subprocess.Popen(
[sys.executable, "-m", "uvicorn", "app.main:app",
"--host", "127.0.0.1", "--port", str(APP_PORT), "--log-level", "warning"],
+5
View File
@@ -216,6 +216,11 @@ def _spawn_app(port: int, mock_port: int, docs_env: dict[str, str] | None) -> su
"BOR_DOCS_WORK_DIR",
):
env.pop(var, None)
# Phase 61 (defect fix): the pop only clears the process env —
# pydantic-settings would still pick up ``BOR_DOCS_REPO`` from an
# operator's local (gitignored) ``.env`` (``cwd=REPO``). Force
# empty so the "unconfigured" boot really is the inert default.
env["BOR_DOCS_REPO"] = ""
else:
env.update(docs_env)
return subprocess.Popen(
+117
View File
@@ -0,0 +1,117 @@
"""Phase 61 E2E (Playwright): the retired homelab-era copy is gone — the
visitor SEES the locked neutral copy on the shared default server.
Story: n/a (TODO-derived — TODO.md L4 "Clean up the UI, there's text
that references old features…"). Run in isolation (DB must be up:
``podman compose up -d db``):
uv run pytest tests/e2e/test_stale_ui_copy.py -v --no-cov
The shared conftest server boots with the default env — and the code
defaults are exactly this phase's locked copy (A1/A2; the conftest
forces ``BOR_SUGGESTIONS`` from the ``Settings`` field so an operator's
local ``.env`` cannot leak corpus-specific chips). Every assertion is a
settled-state check: static HTML + one ``GET /api/suggestions`` fetch;
Playwright's ``expect`` retries ride out the chip rendering.
Test → lock mapping (Playwright Mapping Rule):
1. ``test_chat_page_placeholder_meta_footer_are_the_locked_copy``
2. ``test_chat_page_shows_no_homelab_or_deployment_text``
3. ``test_chat_page_suggestion_chips_are_the_locked_list``
4. ``test_sources_page_sub_describes_the_current_source_model``
5. ``test_git_sources_example_url_is_neutral``
"""
from __future__ import annotations
from playwright.sync_api import Page, expect
# The locked replacement copy (owner-locked A1 / A2 / A3 — same literals
# as tests/unit/test_stale_ui_copy.py; the unit pins guard the files,
# this suite guards what the visitor actually sees).
META = "Ask anything about your indexed documents — every answer cites the exact doc."
PLACEHOLDER = "Ask me anything…"
FOOTER = "Powered by self-hosted models"
GIT_EXAMPLE = "https://github.com/you/your-repo.git"
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.",
]
def test_chat_page_placeholder_meta_footer_are_the_locked_copy(
page: Page, app_url: str, db_ready: None
) -> None:
"""The composer placeholder, the <meta description> content and the
footer span all read the locked (A1) copy — read from the DOM a
visitor gets."""
page.goto(f"{app_url}/")
expect(page.locator("#message-input")).to_have_attribute(
"placeholder", PLACEHOLDER
)
meta = page.eval_on_selector('meta[name="description"]', "el => el.content")
assert meta == META, "the rendered meta description must be the locked copy"
expect(page.locator(".footer-text").first).to_have_text(FOOTER)
def test_chat_page_shows_no_homelab_or_deployment_text(
page: Page, app_url: str, db_ready: None
) -> None:
"""The entire rendered chat page (nav, empty state, composer, footer)
shows no homelab-era text — the empty-state sub AND the four
rendered suggestion chips are covered by this body scan (case-
insensitive; a fresh page context has no saved chats, so the empty
state is what renders)."""
page.goto(f"{app_url}/")
expect(page.locator("#suggestions .suggestion-chip")).to_have_count(len(CHIPS))
body = page.evaluate("() => document.body.innerText.toLowerCase()")
assert "homelab" not in body, f"homelab-era text rendered on the chat page: {body!r}"
assert "deployment" not in body, (
f"homelab-era text rendered on the chat page: {body!r}"
)
def test_chat_page_suggestion_chips_are_the_locked_list(
page: Page, app_url: str, db_ready: None
) -> None:
"""The four rendered empty-state chips (from ``GET
/api/suggestions``, the code default) are the locked (A2) list, in
order."""
page.goto(f"{app_url}/")
chips = page.locator("#suggestions .suggestion-chip")
expect(chips).to_have_count(len(CHIPS))
for i, chip in enumerate(CHIPS):
expect(chips.nth(i)).to_have_text(chip)
def test_sources_page_sub_describes_the_current_source_model(
page: Page, app_url: str, db_ready: None
) -> None:
"""The KB page-sub (the string the TODO cited by name) no longer
names ~/Homelab or ~/Deployments and describes the current source
model. The page is anonymously viewable — the catalog gate hides
the table, not the page-head."""
page.goto(f"{app_url}/sources.html")
sub = page.locator(".page-sub").first
expect(sub).to_be_visible()
text = sub.inner_text().lower()
assert "homelab" not in text, f"retired copy in the page-sub: {text!r}"
assert "deployments" not in text, f"retired copy in the page-sub: {text!r}"
assert "configured sources" in text, (
f"the page-sub must name the current source model: {text!r}"
)
def test_git_sources_example_url_is_neutral(
page: Page, app_url: str, db_ready: None
) -> None:
"""The repo-URL form example (A3) is the neutral your-repo.git —
read from the DOM; the element exists even while
``#git-sources-content`` is hidden for an anonymous visitor (no
sign-in needed)."""
page.goto(f"{app_url}/git-sources.html")
expect(page.locator("#git-source-url")).to_have_attribute(
"placeholder", GIT_EXAMPLE
)
+166
View File
@@ -0,0 +1,166 @@
"""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)}"
)
+8 -3
View File
@@ -102,13 +102,18 @@ def test_sync_error_banner_is_a_hidden_alert() -> None:
def test_page_sub_copy_mentions_the_button() -> None:
"""The page-sub copy names the button as the one-click way to clone
the repos and re-import (the import CLI docs live elsewhere)."""
"""The page-sub copy names the button as the one-click way to pull
the latest and re-import (the import CLI docs live elsewhere).
Phase 61: the copy describes the current source model (git repos +
local directories + uploaded archives), not the old ~/Homelab +
~/Deployments clone."""
sub = re.search(r'<p class="page-sub">(.*?)</p>', _text(SOURCES_HTML), re.DOTALL)
assert sub, "sources.html must keep the .page-sub copy"
copy = re.sub(r"\s+", " ", sub.group(1)) # the markup wraps lines
assert "Press <strong>Sync sources</strong>" in copy
assert "clone the repos and re-import" in copy
assert "pull the latest and re-import" in copy
assert "git repositories," in copy
assert "local directories, and uploaded archives" in copy
def test_sources_page_stays_cdn_free() -> None: