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

"""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, chatId: string | null,
  messages: [...]}`` (phase 55 A2: the shape extends IN PLACE with the
  saved_chats row link — a pre-55 record without it reads as null),
  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`` chat-page only — phase 19 shipped it in the shared
  bar (chat, sources, viewer, owner permission 2026-08-23); it moved
  from the navbar to index.html's .chat-shell at owner request
  (2026-08-28). ≥44px, solid brand 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"
DOCUMENT_HTML = FRONTEND / "document.html"
LOGIN_HTML = FRONTEND / "login.html"
SHARED_HTML = FRONTEND / "shared.html"
DOC_EDIT_HTML = FRONTEND / "doc-edit.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, chatId, messages} payload shape (A11: raw localStorage JSON, no
    library). Phase 55 (A2): the shape extends IN PLACE with `chatId` —
    the saved_chats row link (null when unlinked), so a reload restores
    the conversation AND its link; the trimToBudget size probe measures
    the same shape."""
    js = _js()
    assert 'const STORAGE_KEY = "bor.chat.v1"' in js
    assert "export const STORAGE_VERSION = 1" in js
    # The write carries the version, the row link, and the trimmed
    # messages (the single write path — saveConversation).
    save_start = js.find("function saveConversation")
    save_body = js[save_start : js.find("\n}\n", save_start)]
    assert "v: STORAGE_VERSION" in save_body
    assert "chatId: currentChatId" in save_body, (
        "phase 55: the link is written with the record (null when unlinked)"
    )
    assert "trimToBudget(conversation)" in save_body
    # The size probe measures the same shape (the link is a fixed-length
    # field — null stands in for the size estimate).
    probe_start = js.find("function trimToBudget")
    probe = js[probe_start : js.find("\n}\n", probe_start)]
    assert "v: STORAGE_VERSION" in probe and "chatId: null" in probe
    # 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_lives_only_on_the_chat_page() -> None:
    """#new-chat-btn is a real type=button with an accessible name. Moved
    from the shared header bar to the chat page at owner request
    (2026-08-28): it lives ONLY in index.html — inside <main>, in
    .chat-shell. Phase 65 (2026-09-01, `TODO.md` L3, owner confirmation)
    relocated the .chat-actions row from the top of the column to the
    bottom: the button now sits BELOW the #messages section, directly
    above the composer (the single module binding + the no-op guard are
    pinned in test_shared_header.py).

    Phase 76 (task 01) — the final shell form, converted in ONE step so
    the later fold tasks (02/03) leave this pin alone: the file-level
    "only on the chat page" semantics die with the shell — the button
    must sit inside the shell's CHAT VIEW section (#view-chat; the
    hidden views' elements remain in the DOM, so a per-file negative
    check is meaningless inside the shell), and it must be absent from
    the SURVIVING separate documents (the flow pages that are not
    navbar views)."""
    html = _index()
    btn = re.search(r'<button[^>]*id="new-chat-btn"[^>]*>', html)
    assert btn, "index.html must contain #new-chat-btn"
    tag = btn.group(0)
    assert 'type="button"' in tag
    assert 'aria-label="New chat"' in tag
    main_idx = html.find('main id="main"')
    assert main_idx != -1 and btn.start() > main_idx, "the button belongs inside <main>"
    # The button sits inside the shell's chat view section (phase 76):
    # after the #view-chat open, before the #view-tuning section starts
    # (the chat section closes before it — hidden views are separate).
    view_chat_idx = html.find('id="view-chat"')
    view_tuning_idx = html.find('id="view-tuning"')
    assert -1 < view_chat_idx < btn.start() < view_tuning_idx, (
        "the button belongs inside the #view-chat section"
    )
    shell_idx = html.find('class="container chat-shell"')
    assert shell_idx != -1 and shell_idx < btn.start(), "the button belongs in .chat-shell"
    messages_idx = html.find('id="messages"')
    messages_end = html.find("</section>", messages_idx)
    composer_idx = html.find('<form class="composer" id="composer"')
    assert -1 < messages_idx < messages_end < btn.start() < composer_idx, (
        "the button sits below the #messages section, above the composer"
    )
    # No SURVIVING separate document carries the button (owner request
    # 2026-08-28, final shell form: the folded navbar views are GONE
    # from this check — they are views of the shell now).
    for other in (DOCUMENT_HTML, LOGIN_HTML, SHARED_HTML, DOC_EDIT_HTML):
        assert 'id="new-chat-btn"' not in other.read_text(encoding="utf-8"), (
            f"{other.name}: the New chat button is chat-view only"
        )


def test_new_chat_button_style_contract() -> None:
    """Solid brand pill (the 2026-08-28 rebrand; it was a ghost): --bg
    text on --brand (5.2:1 per the token note — WCAG AA), borderless,
    ≥44px target; hover lightens the brand fill; focus-visible via the
    global rule. On the chat page the label stays visible even ≤640px
    (the button is in .chat-shell, not the navbar) with the plus icon
    hidden (aria-label keeps the accessible name either way)."""
    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 "border: 0" in body
    assert "background: var(--brand)" in body, "solid brand fill (the rebrand)"
    assert "color: var(--bg)" in body, "--bg text on --brand = 5.2:1 (AA)"
    hover = re.search(r"\.new-chat-btn:hover \{([\s\S]*?)\n\}", css)
    assert hover and "#f55a72" in hover.group(1), "hover lightens the brand fill"
    # Mobile (≤640px): the button sits in .chat-shell, not the navbar —
    # the label stays visible and the plus icon is hidden (room in the
    # body); the pill stays ≥44px via min-height.
    mobile = re.search(r"@media \(max-width: 640px\) \{([\s\S]*?)\n\}", css)
    assert mobile, "mobile media query missing"
    assert ".chat-shell .new-chat-label { display: inline; }" in mobile.group(1)
    assert ".chat-shell .new-chat-btn svg { 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 scratchpad
    (ink-soft ≈6.9:1 on surface, 320px cap; user-scrollable again since
    phase 43 — owner direction 2026-08-27, TODO.md L7)."""
    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 43 (owner direction 2026-08-27): user-scrollable window again;
    # the phase-17 bottom-pin (gated in app.js) is the autoscroll.
    assert "overflow-y: auto" in tbody
    assert "overflow-y: hidden" not in tbody