Files
brain-of-reese/tests/unit/test_chat_persistence.py
T
ducoterra 7c6763319b fix(chat): stop autoscrolling while a reply streams (owner direction)
TODO.md L5: "Get rid of the chat reply autoscroll, it's breaking things
like making it impossible for the user to scroll while a reply
generates." Owner direction 2026-08-27 (roadmap A1) revises the
phase-18 follow-the-bottom choice: the page NEVER auto-scrolls while a
turn streams. Kept (owner decision): the submit reveal (the user's own
message) and the one-shot phase-14 restore landing.

- frontend/assets/app.js: delete NEAR_BOTTOM_PX + isNearBottom;
  scrollReveal becomes the one unconditional scrollIntoView (still
  smooth, still "auto" under prefers-reduced-motion via SCROLL);
  addMessage(who, html, scroll = false) carries an explicit scroll
  intent — only the submit (", true") and the two restore landings
  scroll. The thinking/tool/delta handlers and the typing indicator
  drop their page-scroll calls; the thinking block's INTERNAL
  bottom-pin (textEl.scrollTop, phase 17 — reworked separately in
  phase 43) and the turn-end focus({ preventScroll: true }) survive.
- tests/unit/test_frontend_scroll.py: rewritten pin for the new
  contract — phase-18 gate absent, helper unconditional, explicit
  intent at submit/restore, no page-scroll call in the streaming
  handlers, typing bubble scroll-free, SCROLL reduced-motion intact.
- tests/unit/test_chat_persistence.py: restore-landing pin updated to
  the new signature (the old forced "auto" is gone; the landing
  rides the default SCROLL — noted at the call site).
- tests/e2e/test_no_reply_autoscroll.py (new, replaces the deleted
  test_follow_bottom_scroll.py): no autoscroll across >=10 samples
  (1px tolerance) during a long answer and during the thinking stream;
  submit-from-the-top still reveals the user message; the restore
  landing lands one-shot on the latest message and stays; long answer
  + sources and the collapsed thinking block persist and restore.

E2E (isolation): test_no_reply_autoscroll.py 5/5; regressions
test_chat_rag 3/3, test_thinking_display 5/5,
test_chat_persistence 4/4, test_long_answers 2/2, test_smoke 3/3;
unit+integration 723 passed, app/ coverage 99%; ruff + pyright clean.
2026-08-28 00:29:25 -04:00

268 lines
12 KiB
Python

"""Unit: the chat-persistence contract in the static frontend (phase 14).
The browser behavior itself is E2E-covered (tests/e2e/test_chat_persistence.py);
here we pin the localStorage persistence markers in app.js/index.html/
styles.css so a silent regression (key rename, dropped try/catch, missing
restore, New chat control lost) is caught without a browser.
Pinned design (PLAN §7.4 note / phase 14):
* versioned key ``bor.chat.v1`` → ``{v: 1, messages: [...]}``, raw text only;
* save points: user message on send, brain message on ``done``;
* every ``localStorage`` access wrapped in try/catch (failure-safe);
* size budget ~700k chars, oldest dropped first;
* ``#new-chat-btn`` in the shared header bar (chat, sources, viewer —
phase 19, owner permission 2026-08-23), ≥44px, ghost pill.
"""
from __future__ import annotations
import re
from pathlib import Path
FRONTEND = Path(__file__).resolve().parents[2] / "frontend"
APP_JS = FRONTEND / "assets" / "app.js"
INDEX_HTML = FRONTEND / "index.html"
SOURCES_HTML = FRONTEND / "sources.html"
DOCUMENT_HTML = FRONTEND / "document.html"
STYLES_CSS = FRONTEND / "assets" / "styles.css"
def _js() -> str:
return APP_JS.read_text(encoding="utf-8")
def _css() -> str:
return STYLES_CSS.read_text(encoding="utf-8")
def _index() -> str:
return INDEX_HTML.read_text(encoding="utf-8")
def test_versioned_storage_key_and_v1_payload() -> None:
"""`bor.chat.v1` (versioned — a format bump is a clean start) with the
{v, messages} payload shape (A11: raw localStorage JSON, no library)."""
js = _js()
assert 'const STORAGE_KEY = "bor.chat.v1"' in js
assert "export const STORAGE_VERSION = 1" in js
# The payload written to the key is always {v: STORAGE_VERSION, messages}
# (two write paths: saveConversation and the trimToBudget size probe).
assert js.count("v: STORAGE_VERSION, messages") >= 2
# Restore validates the version before trusting anything.
assert "data.v !== STORAGE_VERSION" in js
def test_storage_size_budget_drops_oldest_first() -> None:
"""~700k-char serialized budget (far under the ~5MB quota); the loop
drops messages from the FRONT (oldest) until the state fits."""
js = _js()
assert "export const STORAGE_BUDGET_CHARS = 700_000" in js
assert "out.length <= 1" in js, "never drop the last remaining message"
assert "out = out.slice(1)" in js, "oldest-first drop (slice(1), not pop)"
assert "STORAGE_BUDGET_CHARS" in js
def test_every_storage_access_is_failure_safe() -> None:
"""AC4: every localStorage access (getItem/setItem/removeItem) must be
inside a try/ that is closer than the enclosing function boundary —
private mode or quota exhaustion must never throw into the UI."""
js = _js()
accesses = list(re.finditer(r"localStorage\.(?:getItem|setItem|removeItem)", js))
assert len(accesses) == 3, f"expected exactly 3 localStorage accesses, got {len(accesses)}"
for m in accesses:
try_idx = js.rfind("try {", 0, m.start())
fn_idx = js.rfind("function ", 0, m.start())
assert try_idx != -1, f"no try before {m.group(0)!r}"
assert try_idx > fn_idx, (
f"{m.group(0)!r} is not inside its function's try block "
f"(function boundary at {fn_idx} is after try at {try_idx})"
)
# Each access has its own catch that degrades silently.
assert js.count("} catch {") >= len(accesses)
def test_raw_text_only_stored_and_re_rendered_on_restore() -> None:
"""The value is raw text (re-rendered through the escape-first markdown
on restore) — no HTML is ever stored. Restore re-applies the full
brain-message chrome: is-deflected styling, maybe-try chips, sources."""
js = _js()
# Phase 42 (owner direction 2026-08-27): the reply autoscroll is gone;
# restore landings keep their one-shot load-time scroll via the
# explicit intent (scroll=true) — the new addMessage signature has no
# per-call behavior override (default SCROLL instead of forced
# "auto" — documented at the call site).
assert 'addMessage("user", renderMarkdown(m.text), true)' in js
assert 'addMessage("brain", renderMarkdown(m.text), true)' in js
assert "wrap.classList.add(\"is-deflected\")" in js
assert "appendMaybeTry(wrap, m.suggestions)" in js
assert "appendSources(wrap, m.sources)" in js
# Restore runs on load (module scope, after the handlers are wired).
assert "restoreConversation();" in js
# Corrupt/legacy payloads degrade to a clean start, never a crash.
assert "Array.isArray(data.messages)" in js
def test_save_points_user_on_send_and_brain_on_done() -> None:
"""Save points: the user message is stored the moment it is sent (BEFORE
the fetch — a failed turn keeps the question); the brain message is
stored on `done` with the done metadata (sources/deflected/suggestions)."""
js = _js()
user_push = js.find('conversation.push({ who: "user", text })')
assert user_push != -1
assert user_push < js.find('fetch("/api/chat"'), (
"the user message must be saved before the turn starts"
)
# Brain save point is wired into the done handler with full metadata
# (phase 17: the persisted text is finalText — the empty-answer
# fallback substitution — and the optional thinking field rides along
# in the same meta object).
done_idx = js.find('ev.type === "done"')
assert done_idx != -1
# Window: the whole done branch (up to the error branch) — the meta
# object legitimately grows with phases (phase 17: thinking, phase
# 37: tools), so a fixed char offset would false-fail.
done_block = js[done_idx : js.find('ev.type === "error"')]
assert "rememberBrainTurn(finalText || acc" in done_block
assert "thinking: thinkingAcc || undefined" in done_block
assert "deflected: !!ev.deflected" in done_block
assert "sources: ev.sources" in done_block
assert "suggestions: ev.suggestions" in done_block
# rememberBrainTurn stores raw text and saves immediately.
assert "text: rawText ||" in js
body = js[js.find("function rememberBrainTurn") :]
assert "saveConversation()" in body[: body.find("\n}\n") + 3]
def test_new_chat_clears_key_and_ui() -> None:
"""New chat: clears the stored key, the rendered list, restores the
empty state, and reuses the #send-status live region for the
confirmation. A live turn is never hijacked."""
js = _js()
fn_start = js.find("function startNewChat")
assert fn_start != -1
body = js[fn_start : js.find("\n}\n", fn_start)]
assert "clearStoredConversation()" in body
assert 'querySelectorAll(".msg")' in body
assert "emptyState.hidden = false" in body
assert "setUiState(UI_STATE.idle)" in body
assert "sendStatus.textContent" in body, "confirmation via the live region"
assert "UI_STATE.thinking" in body and "UI_STATE.streaming" in body, (
"new chat must be ignored while a turn is in flight"
)
assert "removeItem(STORAGE_KEY)" in js
def test_new_chat_button_in_the_shared_header_bar() -> None:
"""#new-chat-btn is a real type=button with an accessible name in the
chat header (index.html). Phase 19 (owner permission 2026-08-23): it
is part of the SHARED bar — it also appears in sources.html and the
document viewer, where it means "go to the chat, fresh" (the
clear-storage + navigate binding is pinned in test_shared_header.py)."""
for html in (INDEX_HTML, SOURCES_HTML, DOCUMENT_HTML):
text = html.read_text(encoding="utf-8")
btn = re.search(r'<button[^>]*id="new-chat-btn"[^>]*>', text)
assert btn, f"{html.name} must contain #new-chat-btn"
tag = btn.group(0)
assert 'type="button"' in tag
assert 'aria-label="New chat"' in tag
# Chat page specifics: the button sits after the nav, inside the header.
html = _index()
btn = re.search(r'<button[^>]*id="new-chat-btn"[^>]*>', html)
assert btn, "index.html must contain #new-chat-btn"
nav_idx = html.find('<nav class="app-nav"')
assert nav_idx != -1 and btn.start() > nav_idx, (
"the button belongs after the nav, inside .header-inner"
)
main_idx = html.find('main id="main"')
assert main_idx != -1 and btn.start() < main_idx, "the button belongs in the header"
def test_new_chat_button_style_contract() -> None:
"""Ghost pill like a nav link: Phase-08 tokens, ≥44px target, hover like
.nav-link, focus-visible via the global rule; icon-only on phones with
the label hidden (aria-label keeps the accessible name)."""
css = _css()
block = re.search(r"\.new-chat-btn \{([\s\S]*?)\n\}", css)
assert block, "styles.css must style .new-chat-btn"
body = block.group(1)
assert "min-height: 44px" in body
assert "border-radius: 999px" in body
assert "var(--line)" in body, "ghost: 1px line border, transparent background"
assert "background: transparent" in body
assert "var(--ink-soft)" in body
hover = re.search(r"\.new-chat-btn:hover \{([\s\S]*?)\n\}", css)
assert hover and "--brand-soft" in hover.group(1) and "--brand-ink" in hover.group(1), (
"hover must match the nav-link brand pair"
)
# Mobile (≤640px): label hidden, icon shown — the pill stays ≥44px via
# min-height and never breaks the fixed-height header bar.
mobile = re.search(r"@media \(max-width: 640px\) \{([\s\S]*?)\n\}", css)
assert mobile, "mobile media query missing"
assert ".new-chat-label { display: none; }" in mobile.group(1)
assert ".new-chat-btn svg { display: block; }" in mobile.group(1)
def test_brain_turn_persists_optional_thinking_field() -> None:
"""Phase 17: the done save point carries `thinking: thinkingAcc ||
undefined` — `undefined` drops the key from the JSON, so turns without
thinking persist byte-identical to before (no version bump). A
thinking-without-answer turn (reasoning exhausts max_tokens) renders
+ persists the shared empty-answer fallback: what the user saw is what
is stored."""
js = _js()
done_idx = js.find('ev.type === "done"')
error_idx = js.find('ev.type === "error"')
assert -1 < done_idx < error_idx, "done branch missing from the turn handler"
branch = js[done_idx:error_idx]
assert "thinking: thinkingAcc || undefined" in branch
assert (
'const finalText = acc || (sawThinking ? EMPTY_ANSWER_FALLBACK : "")'
in branch
)
assert "renderMarkdown(finalText)" in branch, (
"the substituted fallback must render into the bubble"
)
def test_restore_renders_collapsed_thinking_block() -> None:
"""Phase 17: a stored brain message carrying `thinking` re-renders the
block COLLAPSED above its bubble (escape-first markdown, as everywhere
else in the persistence contract); messages without the field render
exactly as before — no block."""
js = _js()
fn_start = js.find("function renderStoredMessage")
assert fn_start != -1
body = js[fn_start : js.find("\n}\n", fn_start)]
assert "if (m.thinking)" in body
assert "ensureThinkingBlock(wrap)" in body
assert "block.open = false" in body, "restored blocks must be collapsed"
assert "renderMarkdown(m.thinking)" in body
def test_thinking_block_css_uses_phase08_tokens() -> None:
"""Phase 17 styling (Phase-08 tokens, WCAG AA): the block frame, the
≥44px summary control (brand-ink ≈8.7:1 on surface) and the live-tail
scratchpad (ink-soft ≈6.9:1 on surface, 320px cap; phase 21 removed the
user scroll — owner choice 2026-08-24)."""
css = _css()
block = re.search(r"details\.thinking \{([\s\S]*?)\n\}", css)
assert block, "styles.css must style details.thinking"
body = block.group(1)
assert "var(--surface)" in body
assert "var(--line)" in body
assert "var(--brand-soft)" in body
assert "var(--radius-sm)" in body
summary = re.search(r"details\.thinking summary \{([\s\S]*?)\n\}", css)
assert summary, "the summary must be a styled focusable control"
sbody = summary.group(1)
assert "min-height: 44px" in sbody
assert "var(--brand-ink)" in sbody
assert "cursor: pointer" in sbody
text = re.search(r"details\.thinking \.thinking-text \{([\s\S]*?)\n\}", css)
assert text, "the .thinking-text live-tail area must be styled"
tbody = text.group(1)
assert "var(--ink-soft)" in tbody
assert "max-height: 320px" in tbody
# Phase 21: no user scroll back — the window is a live tail only.
assert "overflow-y: hidden" in tbody
assert "overflow-y: auto" not in tbody