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

"""Story: mid-stream navigation — the phase-76 SPA shell fix (phase 20
story, re-purposed by phase 76 task 02).

Run in isolation (DB must be up: ``podman compose up -d db``):

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

Phase 20 (bug 24) pinned a REAL departure from the chat mid-answer: a
full page navigation (the "Sources" navbar link → /sources.html) aborted
the stream via the unload, and a single ``pagehide`` save point in
app.js persisted the partial raw answer (``rememberBrainTurn``) so the
user came back to their question WITH the partial, rendered as
"Partial answer — navigation interrupted the stream."

Phase 76 (task 02) folded /sources.html (and /git-sources.html) into
the ONE-document shell: from this phase on, a navbar click is a
CLIENT-SIDE view switch — the document (and its in-flight SSE reader)
survive, so the pinned behavior is "the stream survives and the answer
COMPLETES." The phase-20 pagehide partial-persist REMAINS for REAL
departures only (a cross-document navigation still aborts the fetch),
and its coverage home is scenario 1 below in its renamed form.

Timing is deterministic by construction:

* scenario 1 keys off the mock's ``write a long answer`` trigger — a
  ~5400-char / ~450-frame / ~9s content stream, so the departure lands
  mid-stream with a wide margin;
* scenarios 2–3 key off the same long stream (mid-stream view switch)
  and the ``think out loud then hesitate`` trigger — the phase-17
  thinking stream followed by a 4s silence before the first content
  frame, so the switch lands inside pure thinking;
* scenario 4 (the pre-token real-departure pin) uses the same
  hesitate trigger; scenarios 5 and 6 settle the turn fully (send
  button re-enabled) before any navigation.

Test → story mapping (Playwright Mapping Rule):
1. ``test_partial_answer_survives_real_departure_midstream``
2. ``test_full_answer_completes_after_rag_nav_midstream``
3. ``test_nav_switch_before_first_token_completes``
4. ``test_no_orphan_brain_message_when_navigated_before_first_token``
5. ``test_completed_turn_unaffected``
6. ``test_new_chat_still_clears_conversation``
"""
from __future__ import annotations

import asyncio
import json
import re
from collections.abc import Iterator
from pathlib import Path
from threading import Thread
from typing import Any

import pytest
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
from e2e.mock_llm import LONG_ANSWER_END, LONG_ANSWER_LINES, long_answer

REPO = Path(__file__).resolve().parents[2]
FIXTURES = REPO / "tests" / "fixtures" / "docs"
QUESTION = "How is my Kubernetes cluster set up?"
MOCK_ANSWER_MARKER = "Deterministic mock answer for E2E"
STORAGE_KEY = "bor.chat.v1"

# --- scenario 1: a turn that is guaranteed to still be in flight --------
#: The mock's long-answer trigger (~9s content stream at 0.02s/frame).
LONG_QUESTION = "write a long answer about how my kubernetes cluster is set up"
FULL_LONG = long_answer()
#: The mock's first 12-char content slice (the same cut ``_sse_stream``
#: makes) — the stored partial must START with it (raw text, pre-render).
FIRST_CHUNK_RAW = re.findall(r".{1,12}", FULL_LONG, re.S)[0]
#: The rendered form of those first frames: the shared escape-first
#: markdown renderer converts the "1. " numbered line into a list item,
#: dropping the marker (pinned by test_long_answers).
FIRST_LINE_DOM = "Step 1: configure node-1"

# --- scenario 3: navigation during pure thinking (no answer tokens) -----
HESITATE_QUESTION = (
    "think out loud then hesitate — how is my kubernetes cluster set up?"
)
#: Tail of the mock's deterministic scratchpad (mock_llm.compose_thinking)
#: — when it is rendered, the thinking stream has just ended and the 4s
#: pre-content pause (SLOW_PRETOKEN_TRIGGER) is running.
THINKING_TAIL = "nothing is invented"


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 _query_log_count() -> int:
    """The settled-row count over the whole (truncated) log.

    The query log finalizes a row ONLY when the LLM finished AND the
    persistence succeeded (phase 48); a cancelled turn — a real
    departure mid-stream, or one before the first token — leaves no
    settled row, so the count IS the settled-row signal (0 = cancelled,
    1 = settled; the house pattern from tests/e2e/test_hidden_tab_
    stream.py).
    """
    with SessionLocal() as db:
        return db.execute(text("SELECT count(*) FROM query_log")).scalar_one()


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 _no_error_banner(page: Page) -> None:
    """The never-stale contract: a restored/partial state must never
    present an error banner (role=alert) — the turn is simply partial.
    Phase 76 (task 02): the shell's hidden views carry their own
    ship-hidden role=alert surfaces (sync banner, upload banner, …),
    so the pin is VIEW-SCOPED IN EFFECT — NO alert may be VISIBLE,
    whatever the document carries hidden."""
    expect(page.locator('[role="alert"]:visible')).to_have_count(0)


@pytest.fixture()
def seeded_kb(mock_llm: int, db_ready: None) -> Iterator[None]:
    """A fresh KB seeded from ``tests/fixtures/docs`` (13 docs since phase
    47, A9 formats), truncated again on teardown. ``db_ready`` (conftest)
    skips with clear instructions when Postgres is down."""
    summary = _reset_db(mock_llm, seed=True)
    assert summary is not None and summary.added == 13
    yield
    _reset_db(mock_llm, seed=False)


# ---------------------------------------------------------------------------
# 1. REAL departure mid-stream (pagehide partial persist — the phase-20
#    contract, now exercised via a genuine cross-document navigation;
#    a navbar click is no longer a departure — that is scenario 2)
# ---------------------------------------------------------------------------


def test_partial_answer_survives_real_departure_midstream(
    page: Page, app_url: str, seeded_kb: None
) -> None:
    page.set_default_timeout(30_000)
    # Admin (phase 16/19): only the admin sees the #nav-sources link.
    login(page, app_url, next="/")
    expect(page.locator("#nav-sources")).to_be_visible()

    # Start the ~9s long answer.
    page.fill("#message-input", LONG_QUESTION)
    page.click("#send-btn")
    expect(page.locator(".msg.user .bubble").last).to_contain_text(LONG_QUESTION)

    # Wait until the first streamed frames have rendered (the first line,
    # in its list-rendered form) — the turn is now provably mid-stream.
    bubble = page.locator(".msg.brain .bubble").last
    expect(bubble).to_contain_text(FIRST_LINE_DOM, timeout=30_000)
    # The turn is still in flight (the stream runs ~9s; navigation takes
    # well under that) — phase 48: the in-flight button is the enabled
    # Stop control, not the old disabled busy state.
    expect(page.locator("#send-btn")).to_be_enabled()
    expect(page.locator("#send-label")).to_have_text("Stop")

    # THE DEPARTURE, in its phase-76 form: a REAL cross-document
    # navigation — page.goto to a genuine other document. /shared.html
    # is a plain document (stable for every session state) and — unlike
    # /login.html, which auto-redirects a signed-in session straight
    # back into the shell — it is a real departure, so the in-flight SSE
    # fetch is aborted by the unload (the point).
    page.goto(app_url + "/shared.html")
    expect(page).to_have_url(app_url + "/shared.html")
    expect(page.locator("#shared-title")).to_be_visible(timeout=15_000)

    # The turn was CANCELLED — the phase-48 query_log row only lands
    # when the LLM finished AND the persistence succeeded, so a
    # cancelled mid-stream turn must leave NO settled row.
    assert _query_log_count() == 0, (
        "a cancelled mid-stream turn must not finalize a query_log row"
    )

    # Return to the chat.
    page.goto(app_url + "/")

    # The question AND the already-streamed partial answer are both
    # rendered — no empty state, no error banner.
    expect(page.locator("#empty-state")).to_be_hidden()
    expect(page.locator(".msg.user .bubble")).to_have_count(1)
    expect(page.locator(".msg.user .bubble").first).to_contain_text(LONG_QUESTION)
    restored = page.locator(".msg.brain .bubble")
    expect(restored).to_have_count(1)
    expect(restored.first).to_contain_text(FIRST_LINE_DOM)
    _no_error_banner(page)

    # Storage holds the partial as a plain brain message: raw text starting
    # with the first streamed chunk — and SHORTER than the full answer
    # (navigation landed mid-stream), with no done metadata (no
    # sources/deflected/suggestions/thinking: this turn had none and a
    # partial never carries the done fields).
    msgs = _stored_parsed(page)["messages"]
    assert [m["who"] for m in msgs] == ["user", "brain"]
    assert msgs[0]["text"] == LONG_QUESTION
    brain = msgs[1]
    assert brain["text"].startswith(FIRST_CHUNK_RAW)
    assert len(brain["text"]) < len(FULL_LONG), "the stored answer must be partial"
    assert brain["text"] != FULL_LONG
    assert "sources" not in brain
    assert "deflected" not in brain
    assert "suggestions" not in brain
    assert "thinking" not in brain

    # The partial renders like any brain message (the existing
    # bubble contract — no new surface) and is tunable like one.
    expect(page.locator("details.thinking")).to_have_count(0)
    expect(page.locator(".msg.brain .source-chip")).to_have_count(0)


# ---------------------------------------------------------------------------
# 2. Navbar click to RAG mid-stream = a client-side VIEW SWITCH (phase 76,
#    task 02): the in-flight stream keeps running while the RAG view
#    shows, and the answer COMPLETES — the phase-20 "answer cut short"
#    outcome is impossible now (the fetch was never cancelled)
# ---------------------------------------------------------------------------


def test_full_answer_completes_after_rag_nav_midstream(
    page: Page, app_url: str, seeded_kb: None
) -> None:
    page.set_default_timeout(30_000)
    login(page, app_url, next="/")
    expect(page.locator("#nav-sources")).to_be_visible()

    # Start the ~9s long answer and wait until visible streaming (the
    # house pattern: first line rendered + the enabled Stop control).
    page.fill("#message-input", LONG_QUESTION)
    page.click("#send-btn")
    expect(page.locator(".msg.user .bubble").last).to_contain_text(LONG_QUESTION)
    bubble = page.locator(".msg.brain .bubble").last
    expect(bubble).to_contain_text(FIRST_LINE_DOM, timeout=30_000)
    expect(page.locator("#send-btn")).to_be_enabled()
    expect(page.locator("#send-label")).to_have_text("Stop")

    # Same-document proof: a window sentinel set before the click is
    # still readable after — no load happened (the navigation-entries
    # length is NOT used: it resets on a real load).
    page.evaluate("() => { window.__shell_boot = 'phase76'; }")
    page.click("#nav-sources")
    expect(page).to_have_url(app_url + "/sources.html")
    assert page.evaluate("() => window.__shell_boot") == "phase76"
    # The RAG view actually mounted (the source rows are listed — phase
    # 97: the top level lists the sources; the file table is per-level
    # and hidden at the top).
    expect(page.locator("#folders-tbody tr").first).to_be_visible(timeout=15_000)

    # Stay on the RAG view while the stream keeps running in the
    # background (the switch is ~t+2s; the full answer needs ~9s).
    page.wait_for_timeout(2000)
    # Back to the chat (the header link — a router-intercepted switch).
    page.click('a.nav-link[href="/"]')
    expect(page).to_have_url(app_url + "/")

    # The answer COMPLETED — the final sentinel line is in the bubble
    # (not a partial), no error banner.
    bubble = page.locator(".msg.brain .bubble").last
    expect(bubble).to_contain_text(LONG_ANSWER_END, timeout=30_000)
    text_now = bubble.inner_text()
    for i in range(1, LONG_ANSWER_LINES + 1):
        assert f"Step {i}: configure node-{i}" in text_now
    _no_error_banner(page)

    # Settle, then storage: EXACTLY ONE brain turn — the FULL answer,
    # with done metadata (the settle, not a partial).
    page.wait_for_timeout(500)
    msgs = _stored_parsed(page)["messages"]
    assert [m["who"] for m in msgs] == ["user", "brain"]
    brain = msgs[1]
    assert brain["text"] == FULL_LONG
    assert brain["deflected"] is False
    # Phase 119 (LOCKED A1): the turn read nothing, so its done sources
    # — and the persisted record — are EMPTY (the retired phase-118 A4
    # union is gone).
    assert brain["sources"] == []

    # The turn SETTLED — the phase-48 query_log row exists (a
    # cancelled turn would leave no row at all).
    assert _query_log_count() == 1, "a completed turn must finalize its query_log row"


# ---------------------------------------------------------------------------
# 3. Navbar switch in the pre-first-token window (pure thinking — no
#    content frame yet): the surviving reader completes the answer, and
#    bor.chat.v1 holds exactly ONE brain turn (the no-orphan invariant
#    in its new form — a pre-token view switch neither kills the turn
#    nor persists a partial)
# ---------------------------------------------------------------------------


def test_nav_switch_before_first_token_completes(
    page: Page, app_url: str, seeded_kb: None
) -> None:
    page.set_default_timeout(30_000)
    login(page, app_url, next="/")
    expect(page.locator("#nav-sources")).to_be_visible()

    page.fill("#message-input", HESITATE_QUESTION)
    page.click("#send-btn")
    expect(page.locator(".msg.user .bubble").last).to_contain_text(HESITATE_QUESTION)

    # The pre-first-token window, pinned the same way as scenario 4:
    # the scratchpad's tail is rendered (the thinking stream has just
    # ended) and the 4s pre-content pause (SLOW_PRETOKEN_TRIGGER) is
    # running — NO content frame has landed yet. (The .msg.brain bubble
    # element exists from turn start with its thinking block — the
    # pre-token state is "no content text", not "no bubble element".)
    # 690fd98 refinement: the live thinking block is a plain div.thinking
    # RUN (never folding mid-turn) inside the details.reasoning container.
    thinking = page.locator(".msg.brain").last.locator("div.thinking")
    thinking.wait_for(state="attached", timeout=10_000)
    expect(thinking.locator(".thinking-text").last).to_contain_text(
        THINKING_TAIL, timeout=30_000
    )
    # Still pre-token: the button is the enabled Stop control (phase 48
    # — the old disabled "Thinking…" busy state is gone).
    expect(page.locator("#send-btn")).to_be_enabled()
    expect(page.locator("#send-label")).to_have_text("Stop")

    # Switch to the RAG view NOW — mid-pause, still before the first
    # content token.
    page.evaluate("() => { window.__shell_boot = 'phase76'; }")
    page.click("#nav-sources")
    expect(page).to_have_url(app_url + "/sources.html")
    assert page.evaluate("() => window.__shell_boot") == "phase76"
    # Phase 97: the source rows are the top-level catalog-rendered
    # signal (the file table is per-level, hidden at the top).
    expect(page.locator("#folders-tbody tr").first).to_be_visible(timeout=15_000)

    # Let the 4s pre-token pause elapse WHILE the RAG view is up — the
    # first content frames land while the chat view is still hidden —
    # then return to the chat: the surviving reader completes the
    # answer.
    page.wait_for_timeout(4500)
    page.click('a.nav-link[href="/"]')
    expect(page).to_have_url(app_url + "/")

    # The answer COMPLETED (full text — the deterministic mock answer),
    # no error banner.
    bubble = page.locator(".msg.brain .bubble").last
    expect(bubble).to_contain_text(MOCK_ANSWER_MARKER, timeout=30_000)
    _no_error_banner(page)

    # Storage: EXACTLY ONE brain turn — the completed answer with done
    # metadata (no partial, no orphan, no duplicate).
    page.wait_for_timeout(500)
    msgs = _stored_parsed(page)["messages"]
    assert [m["who"] for m in msgs] == ["user", "brain"]
    assert MOCK_ANSWER_MARKER in msgs[1]["text"]
    assert msgs[1]["deflected"] is False
    # Phase 119 (LOCKED A1): the turn read nothing, so its done sources
    # — the stored record's sources list — are EMPTY (the retired
    # phase-118 A4 suggested-citation is gone; the full retrieval
    # stays in query_log, pinned below).
    assert msgs[1]["sources"] == []

    # The turn settled — one finalized row (a cancelled turn would
    # leave no row at all).
    assert _query_log_count() == 1


# ---------------------------------------------------------------------------
# 4. REAL departure BEFORE the first answer token (pure thinking): nothing
#    brain-side is persisted — the pre-token no-orphan convention,
#    unchanged (a direct page.goto to /sources.html REMAINS a real
#    departure in the SPA — the shell is served, the fetch is aborted
#    by the unload)
# ---------------------------------------------------------------------------


def test_no_orphan_brain_message_when_navigated_before_first_token(
    page: Page, app_url: str, seeded_kb: None
) -> None:
    page.set_default_timeout(30_000)
    login(page, app_url, next="/")  # phase 79: chat is require_user-gated
    page.fill("#message-input", HESITATE_QUESTION)
    page.click("#send-btn")
    expect(page.locator(".msg.user .bubble").last).to_contain_text(HESITATE_QUESTION)

    # Wait until the scratchpad's tail is rendered (phase-17 thinking body,
    # ~2 700 chars / ≈4.5s, lengthened in phase 21) — the 4s pre-content
    # pause (SLOW_PRETOKEN_TRIGGER) is now running, so the navigation below
    # lands inside pure thinking with a wide margin. Explicit timeout:
    # the mock streams the tail at ≈12 chars / 0.02s (≈4.7s end-to-end),
    # which outruns Playwright's 5s assertion auto-wait on a loaded host
    # (the wait started at the FIRST thinking frame — the pre-existing
    # race, phase 55 task 02 fix).
    # 690fd98 refinement: the live thinking block is a plain div.thinking
    # RUN (never folding mid-turn) inside the details.reasoning container.
    thinking = page.locator(".msg.brain").last.locator("div.thinking")
    thinking.wait_for(state="attached", timeout=10_000)
    expect(thinking.locator(".thinking-text").last).to_contain_text(
        THINKING_TAIL, timeout=30_000
    )
    # Still pre-token: the button is the enabled Stop control (phase 48 —
    # the old disabled "Thinking…" busy state is gone).
    expect(page.locator("#send-btn")).to_be_enabled()
    expect(page.locator("#send-label")).to_have_text("Stop")

    # Leave during the pause via a REAL cross-document departure (no
    # answer token has streamed — acc is empty, so the pagehide save
    # point must persist nothing brain-side).
    page.goto(app_url + "/sources.html")

    # Return to the chat.
    page.goto(app_url + "/")

    # The question is restored — with NO brain message behind it: no empty
    # bubble, no partial, no thinking block (owner-confirmed A1.2).
    expect(page.locator("#empty-state")).to_be_hidden()
    expect(page.locator(".msg.user .bubble")).to_have_count(1)
    expect(page.locator(".msg.user .bubble").first).to_contain_text(HESITATE_QUESTION)
    expect(page.locator(".msg")).to_have_count(1)
    expect(page.locator(".msg.brain")).to_have_count(0)
    expect(page.locator("details.thinking")).to_have_count(0)
    _no_error_banner(page)

    # Storage agrees: exactly the user message, nothing brain-side.
    msgs = _stored_parsed(page)["messages"]
    assert len(msgs) == 1
    assert msgs[0] == {"who": "user", "text": HESITATE_QUESTION}


# ---------------------------------------------------------------------------
# 5. Completed turn: the done save point is byte-identical to before —
#    the new pagehide save point must not duplicate or alter it (the
#    direct gotos are real departures — unaffected by the fold)
# ---------------------------------------------------------------------------


def test_completed_turn_unaffected(
    page: Page, app_url: str, seeded_kb: None
) -> None:
    page.set_default_timeout(30_000)
    login(page, app_url, next="/")  # phase 79: chat is require_user-gated
    _ask(page, QUESTION)

    # The done save point: full answer + metadata, exactly as phase 14.
    before = _stored_parsed(page)
    assert [m["who"] for m in before["messages"]] == ["user", "brain"]
    brain = before["messages"][1]
    assert MOCK_ANSWER_MARKER in brain["text"]
    assert brain["deflected"] is False
    # Phase 119 (LOCKED A1): the turn read nothing, so its done sources
    # — and the persisted record — are EMPTY (the retired phase-118 A4
    # union is gone).
    assert brain["sources"] == []

    # A trip to Sources and back (the turn finished long ago — uiState is
    # idle, so the pagehide save point must be a no-op).
    page.goto(app_url + "/sources.html")
    page.goto(app_url + "/")

    # Full answer rendered with 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); no error banner.
    expect(page.locator("#empty-state")).to_be_hidden()
    expect(page.locator(".msg.user .bubble")).to_contain_text(QUESTION)
    bubble = page.locator(".msg.brain .bubble")
    expect(bubble).to_have_count(1)
    expect(bubble.first).to_contain_text(MOCK_ANSWER_MARKER)
    expect(page.locator(".msg.brain .source-chip")).to_have_count(0)
    _no_error_banner(page)

    # Storage is byte-identical to the pre-navigation payload — the
    # completed turn persisted exactly as before (one brain message, done
    # metadata intact; no duplicate from the pagehide path).
    assert _stored_parsed(page) == before


# ---------------------------------------------------------------------------
# 6. The DELIBERATE clear is untouched: New chat (chat-page only since
#    the owner rework 2026-08-28) still clears the conversation
#    (phase 14 contract)
# ---------------------------------------------------------------------------


def test_new_chat_still_clears_conversation(
    page: Page, app_url: str, seeded_kb: None
) -> None:
    page.set_default_timeout(30_000)
    login(page, app_url, next="/")  # phase 79: chat is require_user-gated
    _ask(page, QUESTION)
    assert _stored(page) is not None

    # The New chat button is chat-page only (it left the shared bar at
    # owner request, 2026-08-28) — the deliberate clear runs right here.
    new_chat = page.locator("#new-chat-btn")
    expect(new_chat).to_be_visible()
    new_chat.click()

    # The chat lands on its empty state and the conversation key is
    # GONE — the deliberate clear is unaffected by the phase-20 pagehide
    # save point.
    expect(page.locator("#empty-state")).to_be_visible()
    expect(page.locator(".msg")).to_have_count(0)
    assert _stored(page) is None, "New Chat must clear the localStorage key"
    _no_error_banner(page)