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

"""Phase 14 E2E (Playwright): the chat conversation survives a refresh.

Story: ``.agents/user_stories/chat-persistence.md``
Run in isolation (DB must be up: ``podman compose up -d db``):

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

The conversation is a durable LOCAL session (localStorage key
``bor.chat.v1`` — A10 keeps the API stateless). Each test gets a fresh
browser context (the shared conftest's ``page`` fixture calls
``browser.new_page``), so localStorage is clean by construction: the
fresh-context tests start with the empty state exactly as before phase 14.

Test → story mapping (Playwright Mapping Rule):
1. ``test_conversation_survives_reload``
2. ``test_deflected_turn_restores_styling``
3. ``test_new_chat_clears_conversation``
4. ``test_persists_across_page_navigation``
"""
from __future__ import annotations

import asyncio
import json
import re
from pathlib import Path
from threading import Thread
from typing import Any

from playwright.sync_api import Page, expect
from sqlalchemy import text

from app.config import Settings
from app.db import SessionLocal
from app.rag.importer import ImportSummary, import_sources
from app.rag.llm import LLMClient
from e2e.auth_helpers import login

REPO = Path(__file__).resolve().parents[2]
FIXTURES = REPO / "tests" / "fixtures" / "docs"
QUESTION = "How is my Kubernetes cluster set up?"
OFF_TOPIC = "How do I bake sourdough bread?"
MOCK_ANSWER_MARKER = "Deterministic mock answer for E2E"
DEFLECT_PHRASE = r"haven't done anything like that"
STORAGE_KEY = "bor.chat.v1"


async def _import_fixtures(mock_port: int) -> ImportSummary:
    kwargs: dict[str, Any] = {"_env_file": None, "llm_base_url": f"http://127.0.0.1:{mock_port}/v1"}
    settings = Settings(**kwargs)  # pyright: ignore[reportCallIssue]
    return await import_sources([FIXTURES], LLMClient(settings))


def _run_in_thread(coro: Any) -> Any:
    """Run a coroutine on a worker thread.

    Playwright's sync API keeps an asyncio loop running on the test thread,
    so ``asyncio.run`` cannot be called directly from a test body.
    """
    box: dict[str, Any] = {}

    def runner() -> None:
        try:
            box["value"] = asyncio.run(coro)
        except BaseException as e:  # noqa: BLE001 — re-raised on the test thread
            box["error"] = e

    t = Thread(target=runner)
    t.start()
    t.join()
    if "error" in box:
        raise box["error"]
    return box["value"]


def _reset_db(mock_port: int, seed: bool) -> ImportSummary | None:
    """Truncate the KB (and query log), then optionally re-import fixtures."""
    with SessionLocal() as db:
        db.execute(text("TRUNCATE chunks, documents, query_log"))
        db.commit()
    if not seed:
        return None
    return _run_in_thread(_import_fixtures(mock_port))


def _stored(page: Page) -> str | None:
    """Raw localStorage payload for the chat (None when the key is absent)."""
    return page.evaluate(f"() => localStorage.getItem('{STORAGE_KEY}')")


def _stored_parsed(page: Page) -> dict[str, Any]:
    raw = _stored(page)
    assert raw is not None, "the conversation key must exist in localStorage"
    return json.loads(raw)


def _ask(page: Page, question: str) -> None:
    """Send one turn and wait until the grounded answer has fully landed."""
    page.fill("#message-input", question)
    page.click("#send-btn")
    expect(page.locator(".msg.user .bubble").last).to_contain_text(question)
    expect(page.locator(".msg.brain .bubble").last).to_contain_text(
        MOCK_ANSWER_MARKER, timeout=30_000
    )
    expect(page.locator("#send-btn")).to_be_enabled()
    expect(page.locator("#send-label")).to_have_text("Send")


def _ask_deflected(page: Page, question: str) -> None:
    """Send an off-topic turn and wait until the deflected answer landed."""
    page.fill("#message-input", question)
    page.click("#send-btn")
    bubble = page.locator(".msg.brain.is-deflected .bubble").first
    bubble.wait_for(state="visible", timeout=30_000)
    expect(bubble).to_contain_text(re.compile(DEFLECT_PHRASE, re.IGNORECASE), timeout=30_000)
    expect(page.locator("#send-btn")).to_be_enabled()
    expect(page.locator("#send-label")).to_have_text("Send")


# ---------------------------------------------------------------------------
# 1. Refresh: the whole conversation comes back exactly as left
# ---------------------------------------------------------------------------


def test_conversation_survives_reload(
    page: Page, app_url: str, mock_llm: int, db_ready: None
) -> None:
    summary = _reset_db(mock_llm, seed=True)
    assert summary is not None and summary.added == 13  # A9 formats (phase 47 added quadlet+j2)
    page.set_default_timeout(30_000)
    login(page, app_url, next="/")
    _ask(page, QUESTION)

    # The turn is persisted: versioned payload, RAW text (no HTML), and the
    # brain message carries the done metadata.
    stored = _stored_parsed(page)
    assert stored["v"] == 1
    assert [m["who"] for m in stored["messages"]] == ["user", "brain"]
    assert stored["messages"][0]["text"] == QUESTION
    brain = stored["messages"][1]
    assert MOCK_ANSWER_MARKER in brain["text"]
    assert "<" not in brain["text"], "persisted brain text must be raw, not rendered HTML"
    assert brain["deflected"] is False
    # Phase 119 (LOCKED A1): the turn read nothing, so its done sources
    # — and the persisted record — are EMPTY (the suggested kubernetes
    # doc is context, not a citation; the retired phase-118 A4 union is
    # gone).

    # Refresh — the same context keeps its localStorage.
    page.reload()
    expect(page.locator("#empty-state")).to_be_hidden()

    # Both bubbles restored: the answer text, and ZERO citation chips
    # (the zero-read turn persisted an empty sources list — phase 119,
    # LOCKED A1; the retired phase-118 A4 chip pin is gone).
    expect(page.locator(".msg.user .bubble")).to_have_count(1)
    expect(page.locator(".msg.user .bubble")).to_contain_text(QUESTION)
    bubble = page.locator(".msg.brain .bubble")
    expect(bubble).to_have_count(1)
    expect(bubble).to_contain_text(MOCK_ANSWER_MARKER)
    expect(page.locator(".msg.brain .source-chip")).to_have_count(0)

    # The restore is read-only: storage still holds the same two messages.
    assert [m["who"] for m in _stored_parsed(page)["messages"]] == ["user", "brain"]

    # And the restored chat is live: a follow-up turn extends it.
    _ask(page, "What about the nodes?")
    expect(page.locator(".msg.user .bubble")).to_have_count(2)
    assert len(_stored_parsed(page)["messages"]) == 4


# ---------------------------------------------------------------------------
# 2. Deflected turn: amber styling + "Maybe try" chips survive a refresh
# ---------------------------------------------------------------------------


def test_deflected_turn_restores_styling(
    page: Page, app_url: str, mock_llm: int, db_ready: None
) -> None:
    _reset_db(mock_llm, seed=True)
    page.set_default_timeout(30_000)
    login(page, app_url, next="/")
    _ask_deflected(page, OFF_TOPIC)

    # The deflected metadata (suggestions) is persisted with the answer.
    stored = _stored_parsed(page)
    brain = stored["messages"][-1]
    assert brain["who"] == "brain"
    assert brain["deflected"] is True
    assert len(brain["suggestions"]) >= 2

    page.reload()

    # Amber deflected bubble + "Maybe try" chips come back, styled.
    expect(page.locator("#empty-state")).to_be_hidden()
    expect(page.locator(".msg.user .bubble")).to_contain_text(OFF_TOPIC)
    restored = page.locator(".msg.brain.is-deflected .bubble")
    expect(restored).to_have_count(1)
    expect(restored.first).to_contain_text(re.compile(DEFLECT_PHRASE, re.IGNORECASE))
    style = restored.first.evaluate("el => getComputedStyle(el)")
    assert style["backgroundColor"] == "rgb(43, 33, 16)"  # --accent-bg (dark theme)
    assert style["borderTopColor"] == "rgb(245, 158, 11)"  # --accent-line

    # The chips are restored from the stored suggestions — same texts, order,
    # and still one-tap-submittable (the shared chip component).
    chips = page.locator(".msg.brain.is-deflected .maybe-try .suggestion-chip")
    expect(chips.first).to_be_visible()
    restored_texts = [chips.nth(i).inner_text() for i in range(chips.count())]
    assert restored_texts == [s.strip() for s in brain["suggestions"] if s.strip()]

    chips.first.click()
    expect(page.locator("#message-input")).to_have_value("")
    expect(page.locator(".msg.user .bubble")).to_have_count(2, timeout=30_000)
    expect(page.locator(".msg.brain .bubble").nth(1)).to_contain_text(
        MOCK_ANSWER_MARKER, timeout=30_000
    )


# ---------------------------------------------------------------------------
# 3. "New chat": clear the conversation, back to the empty state
# ---------------------------------------------------------------------------


def test_new_chat_clears_conversation(
    page: Page, app_url: str, mock_llm: int, db_ready: None
) -> None:
    _reset_db(mock_llm, seed=True)
    page.set_default_timeout(30_000)
    login(page, app_url, next="/")
    _ask(page, QUESTION)
    expect(page.locator(".msg")).to_have_count(2)
    assert _stored(page) is not None

    # The reset control: ghost pill in the chat header, ≥44px, accessible name.
    btn = page.locator("#new-chat-btn")
    expect(btn).to_be_visible()
    expect(btn).to_have_attribute("type", "button")
    expect(btn).to_have_attribute("aria-label", "New chat")
    box = btn.bounding_box()
    assert box is not None and box["height"] >= 44

    btn.click()

    # Conversation gone, empty state + suggestions back, storage key cleared.
    expect(page.locator(".msg")).to_have_count(0)
    expect(page.locator("#empty-state")).to_be_visible()
    expect(page.locator("#suggestions .suggestion-chip").first).to_be_visible(timeout=15_000)
    assert _stored(page) is None, "New chat must clear the localStorage key"

    # Confirmation via the existing live region (#send-status, aria-live=polite).
    expect(page.locator("#send-status")).to_contain_text("New chat started")

    # And it is a clean slate: a fresh turn starts a fresh conversation.
    _ask(page, QUESTION)
    stored = _stored_parsed(page)
    assert [m["who"] for m in stored["messages"]] == ["user", "brain"]
    assert stored["messages"][0]["text"] == QUESTION


# ---------------------------------------------------------------------------
# 4. Navigation: a trip to Sources and back keeps the conversation
# ---------------------------------------------------------------------------


def test_persists_across_page_navigation(
    page: Page, app_url: str, mock_llm: int, db_ready: None
) -> None:
    _reset_db(mock_llm, seed=True)
    page.set_default_timeout(30_000)
    login(page, app_url, next="/")
    _ask(page, QUESTION)
    _ask_deflected(page, OFF_TOPIC)  # mixed conversation: grounded + deflected

    # A trip to Sources (phase 16: the catalog is admin-only — the
    # test's form login above already holds the session, so the trip is
    # a plain navigation). Phase 76 (task 02): the shell
    # carries the chat view (with its New chat button) in the DOM on
    # EVERY view — hidden + inert — so the button EXISTS here but must
    # be HIDDEN (the view-scoped absence pattern; it left the shared
    # bar at owner request, 2026-08-28 — pinned in
    # tests/e2e/test_shared_header.py).
    page.goto(f"{app_url}/sources.html")
    # Phase 97: the top level lists the sources (the file table is
    # per-level, hidden at the top) — the source row is the
    # catalog-rendered signal.
    expect(page.locator("#folders-tbody tr").first).to_be_visible(timeout=15_000)
    expect(page.locator("#new-chat-btn")).to_be_hidden()

    # Back to the chat: the conversation is exactly as left — both turns,
    # the source chip, and the amber deflected bubble with its chips.
    page.goto(app_url + "/")
    expect(page.locator("#empty-state")).to_be_hidden()
    expect(page.locator(".msg.user .bubble")).to_have_count(2)
    expect(page.locator(".msg.user .bubble").first).to_contain_text(QUESTION)
    expect(page.locator(".msg.user .bubble").nth(1)).to_contain_text(OFF_TOPIC)
    expect(page.locator(".msg.brain .bubble").first).to_contain_text(MOCK_ANSWER_MARKER)
    # Zero citation chips (phase 119, LOCKED A1 — the grounded turn read
    # nothing; the retired phase-118 A4 union is gone).
    expect(page.locator(".msg.brain .source-chip")).to_have_count(0)
    deflected = page.locator(".msg.brain.is-deflected .bubble")
    expect(deflected).to_have_count(1)
    expect(deflected.first).to_contain_text(re.compile(DEFLECT_PHRASE, re.IGNORECASE))
    maybe_chip = page.locator(".msg.brain.is-deflected .maybe-try .suggestion-chip")
    expect(maybe_chip.first).to_be_visible()

    # The New chat control is back on the chat page.
    expect(page.locator("#new-chat-btn")).to_be_visible()