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

"""Unit: the phase-139 (task 03) "the Reading line shows which lines"
frontend contract.

No new Python app logic exists for this task — the behavior lives in
``frontend/assets/app.js`` (the ``readRangeSuffix`` helper + the
``appendToolLine`` suffix span + the live ``tool`` branch's
``ev.offset``/``ev.limit`` read + the ``toolAcc`` persistence stamp +
the restore pass-through) and ``frontend/assets/shared.js`` (the shared
page's parity copy of the suffix + ``addToolLines``). Like the other
frontend-adjacent unit files (``test_frontend_tool_states.py`` is the
phase-37 precedent, ``test_read_truncation_frontend.py`` the phase-95
one), this module pins the JS markers the story depends on so a silent
regression in the suffix wording, the well-formedness guard, the
persistence shape, or the shared-page parity is caught without a
browser. A small node-driven behavioral check (skipped when node is
unavailable, like the phase-10 renderer check in
``test_document_viewer.py``) proves the three suffix shapes, the
plain-read line's byte-identity to pre-phase, and the shared-page
parity. The E2E gate is the phase's story suite
(``tests/e2e/test_read_range_tool_lines.py``).
"""
from __future__ import annotations

import json
import shutil
import subprocess
from pathlib import Path

import pytest

FRONTEND = Path(__file__).resolve().parents[2] / "frontend"
APP_JS = FRONTEND / "assets" / "app.js"
SHARED_JS = FRONTEND / "assets" / "shared.js"

HAVE_NODE = shutil.which("node") is not None


def _js() -> str:
    return APP_JS.read_text(encoding="utf-8")


def _shared_js() -> str:
    return SHARED_JS.read_text(encoding="utf-8")


def _extract(js: str, name: str) -> str:
    """One top-level function by name — from its ``function NAME`` to
    its column-0 closing ``}`` (inner braces are indented, so the first
    ``\\n}\\n`` is the function's own end — the
    ``test_frontend_tool_states`` extraction convention)."""
    fn = js.find(f"function {name}")
    assert fn != -1, f"{name} not found"
    end = js.find("\n}\n", fn)
    assert end != -1, f"could not find the end of {name}"
    return js[fn : end + 2]


def _run_node(script: str) -> str:
    proc = subprocess.run(["node", "-e", script], capture_output=True, text=True, timeout=60)
    assert proc.returncode == 0, f"node failed: {proc.stderr}"
    return proc.stdout


# --------------------------------------------------------------------------
# app.js — readRangeSuffix: the single source of truth for the wording
# --------------------------------------------------------------------------


def test_read_range_suffix_exists_with_the_pinned_literals() -> None:
    """readRangeSuffix (app.js): the well-formedness guard mirrors the
    server's ``_whole_line_number`` (``Number.isInteger(x) && x >= 1``
    — bools are not integers in JS), and the three suffix shapes carry
    the EXACT pinned copy — both present → `` (lines {offset}–{offset +
    limit - 1})`` (EN-DASH, ASSUMPTION A1: the REQUESTED extent),
    offset only → `` (from line {offset})``, limit only →
    `` (first {limit} lines)``, otherwise `` ""``."""
    body = _extract(_js(), "readRangeSuffix")
    assert "Number.isInteger(offset) && offset >= 1" in body, (
        "the offset guard mirrors the server's _whole_line_number"
    )
    assert "Number.isInteger(limit) && limit >= 1" in body, (
        "the limit guard mirrors the server's _whole_line_number"
    )
    assert "` (lines ${offset}–${offset + limit - 1})`" in body, (
        "the both-present shape — the REQUESTED extent, en-dash per the"
        " pinned copy (ASSUMPTION A1)"
    )
    assert "` (from line ${offset})`" in body, "the offset-only shape"
    assert "` (first ${limit} lines)`" in body, "the limit-only shape"
    assert 'return ""' in body, "neither field well-formed → no suffix"


def test_read_range_suffix_shape_order() -> None:
    """The both-present shape wins (it is checked first), then
    offset-only, then limit-only, then the empty fallback — so a
    well-formed pair always renders the range, never a one-sided
    shape."""
    body = _extract(_js(), "readRangeSuffix")
    both = body.find("if (offOk && limOk)")
    off_only = body.find("if (offOk)")
    lim_only = body.find("if (limOk)")
    empty = body.find('return ""')
    assert -1 < both < off_only < lim_only < empty, (
        "both → offset-only → limit-only → empty, in order"
    )


# --------------------------------------------------------------------------
# app.js — appendToolLine: the suffix span on the Reading line
# --------------------------------------------------------------------------


def test_append_tool_line_signature_takes_optional_range() -> None:
    """appendToolLine gains the additive ``offset``/``limit`` params
    (default ``null`` — a pre-phase 3-arg call renders byte-identical),
    and the read arm renders the suffix through the SAME helper.
    Phase 146 (task 02) extends the signature one more additive param
    (``scope = null`` — the scoped grep's document) — the 5-arg
    pre-phase-146 call shape renders byte-identically."""
    body = _extract(_js(), "appendToolLine")
    assert (
        "function appendToolLine(wrap, name, argument, offset = null, limit = null, "
        "scope = null)" in _js()
    ), "the signature carries the additive offset/limit/scope (default null)"
    assert "readRangeSuffix(offset, limit)" in body, (
        "the read arm renders the suffix through the SAME helper"
    )
    assert 'range.className = "read-range"' in body, (
        "the suffix rides a .read-range span"
    )
    assert "range.textContent = rangeSuffix" in body, (
        "the range is data — textContent, never innerHTML"
    )
    assert "if (rangeSuffix)" in body, (
        "the span is appended ONLY when the suffix is non-empty — a"
        " plain read's line stays byte-identical"
    )


def test_append_tool_line_suffix_is_a_sibling_after_the_code() -> None:
    """The .read-range span is a SIBLING appended AFTER the ``<code>``
    child (the phase-95 truncation-note precedent — append a span,
    never rewrite the pinned template text), so the line's pinned
    ``📄 Reading `` + ``<code>`` bytes are untouched."""
    body = _extract(_js(), "appendToolLine")
    code_append = body.find("line.appendChild(code)")
    range_append = body.find("line.appendChild(range)")
    assert -1 < code_append < range_append, (
        "the range span lands AFTER the <code> child"
    )
    # The read arm's pinned template text is untouched (phase-87/117).
    assert 'line.textContent = "📄 Reading "' in body
    assert "innerHTML" not in body, (
        "no HTML injection surface on tool lines — textContent only"
    )


# --------------------------------------------------------------------------
# app.js — the live `tool` branch: ev.offset/ev.limit + the toolAcc stamp
# --------------------------------------------------------------------------


def test_live_tool_branch_reads_the_range_with_the_guard() -> None:
    """The live ``tool`` branch reads ``ev.offset`` / ``ev.limit`` with
    the SAME well-formedness guard (``Number.isInteger(x) && x >= 1``
    → ``null`` when absent / malformed), so a non-range frame keeps the
    exact pre-phase ``{name, argument}`` record shape (the additive
    ``bor.chat.v1`` JSONB — old records restore byte-identically, no
    migration)."""
    js = _js()
    tool_idx = js.find('ev.type === "tool"')
    delta_idx = js.find('ev.type === "delta"')
    branch = js[tool_idx:delta_idx]
    assert "Number.isInteger(ev.offset) && ev.offset >= 1 ? ev.offset : null" in branch, (
        "ev.offset reads through the house guard → null when absent"
    )
    assert "Number.isInteger(ev.limit) && ev.limit >= 1 ? ev.limit : null" in branch, (
        "ev.limit reads through the house guard → null when absent"
    )
    # The record carries the fields ONLY when non-null.
    assert "const toolRecord = { name, argument }" in branch, (
        "the base record stays {name, argument}-generic"
    )
    assert "if (frameOffset !== null) toolRecord.offset = frameOffset" in branch, (
        "offset joins the record ONLY when non-null"
    )
    assert "if (frameLimit !== null) toolRecord.limit = frameLimit" in branch, (
        "limit joins the record ONLY when non-null"
    )
    assert "toolAcc.push(toolRecord)" in branch, "every tool frame is recorded"
    # Phase 146 (task 02): the scope joins the SAME two pass-throughs.
    assert (
        "appendToolLine(wrap, name, argument, frameOffset, frameLimit, framePath)"
        in branch
    )


def test_live_read_status_carries_the_range_suffix() -> None:
    """ASSUMPTION A2: the read status label carries the SAME
    requested-range suffix as the line (``readRangeSuffix`` — the single
    source of truth); a non-range read renders byte-identical (the
    helper returns ``""``). The ls labels are untouched; the grep label
    gains the phase-146 additive scope (`` in <path>`` ONLY when the
    frame carried one — a bare grep renders the exact pre-phase label).
    """
    js = _js()
    tool_idx = js.find('ev.type === "tool"')
    delta_idx = js.find('ev.type === "delta"')
    branch = js[tool_idx:delta_idx]
    assert (
        "`${brand()} is reading ${argument}${readRangeSuffix(frameOffset, frameLimit)}`"
        in branch
    ), "the read status carries the suffix (A2)"
    # The other labels: the grep scope extension (phase 146) + the
    # ls labels untouched.
    assert (
        "`${brand()} is searching for ${argument}"
        "${framePath ? ` in ${framePath}` : \"\"}`" in branch
    )
    assert "`${brand()} is listing documents in ${argument}`" in branch
    assert "`${brand()} is listing documents`" in branch


# --------------------------------------------------------------------------
# app.js — the restore path: the stored range re-renders the suffix
# --------------------------------------------------------------------------


def test_restore_path_passes_the_stored_range_through() -> None:
    """The phase-14 restore path (renderStoredMessage): a stored tool
    record with ``offset``/``limit`` (the live ``toolAcc`` stamp —
    additive on ``bor.chat.v1``) re-renders the SAME suffix through the
    SAME helper; a record saved before the phase (no fields) renders
    byte-identically (the guard → null → no span)."""
    js = _js()
    fn = js.find("function renderStoredMessage")
    assert fn != -1
    end = js.find("function restoreConversation")
    body = js[fn:end]
    assert "Number.isInteger(t.offset) && t.offset >= 1 ? t.offset : null" in body, (
        "the stored offset reads through the house guard"
    )
    assert "Number.isInteger(t.limit) && t.limit >= 1 ? t.limit : null" in body, (
        "the stored limit reads through the house guard"
    )
    assert "appendToolLine(wrap, t.name, arg, tOffset, tLimit, tPath)" in body, (
        "the stored range + the phase-146 stored scope ride the SAME helper"
    )


# --------------------------------------------------------------------------
# shared.js — the parity copy: identical literals + the addToolLines span
# --------------------------------------------------------------------------


def test_shared_page_suffix_is_byte_identical_to_app_js() -> None:
    """shared.js's ``readRangeSuffix`` is the parity copy — IDENTICAL
    literals and IDENTICAL guard (the phase-50 restore contract: the
    shared page re-renders saved records pixel-identically to the chat
    page). The three suffix shapes + the guard must match app.js
    EXACTLY."""
    shared = _extract(_shared_js(), "readRangeSuffix")
    app = _extract(_js(), "readRangeSuffix")
    for literal in (
        "Number.isInteger(offset) && offset >= 1",
        "Number.isInteger(limit) && limit >= 1",
        "` (lines ${offset}–${offset + limit - 1})`",
        "` (from line ${offset})`",
        "` (first ${limit} lines)`",
        'return ""',
    ):
        assert literal in shared, f"shared.js lost the parity literal {literal!r}"
        assert literal in app, f"app.js lost the parity literal {literal!r}"


def test_shared_page_add_tool_lines_renders_the_range_span() -> None:
    """shared.js's ``addToolLines``: the SAME .read-range span as the
    chat page's ``appendToolLine`` — a sibling after the ``<code>``
    child, textContent only, appended ONLY when the suffix is non-empty
    (a record without the fields renders exactly as today)."""
    body = _extract(_shared_js(), "addToolLines")
    assert "readRangeSuffix(t.offset, t.limit)" in body, (
        "the shared page renders the suffix from the stored record"
    )
    assert 'range.className = "read-range"' in body
    assert "range.textContent = rangeSuffix" in body
    assert "if (rangeSuffix)" in body
    code_append = body.find("line.appendChild(code)")
    range_append = body.find("line.appendChild(range)")
    assert -1 < code_append < range_append, (
        "the shared range span lands AFTER the <code> child (parity)"
    )
    assert "innerHTML" not in body, (
        "no HTML injection surface on shared tool lines — textContent only"
    )


def test_no_cdn_added() -> None:
    """AGENTS.md rule 6: the range suffix adds no external
    script/link."""
    index = (FRONTEND / "index.html").read_text(encoding="utf-8")
    assert 'src="http' not in index and 'href="http' not in index


# --------------------------------------------------------------------------
# behavior (node): the three suffix shapes, the plain line's
# byte-identity, and the shared-page parity
# --------------------------------------------------------------------------

#: A minimal DOM stub — just enough surface for appendToolLine /
#: addToolLines (createElement / querySelector / appendChild /
#: insertBefore / textContent / className / setAttribute). Plain strings
#: only; every node is snapshotted as a JSON row (the
#: test-document-viewer / test-chat-image-questions pattern).
_DOM_STUB = """
class El {
  constructor(tag) {
    this.tag = tag;
    this.children = [];
    this.attrs = {};
    this.className = "";
    this._text = "";
    this.open = false;
  }
  setAttribute(k, v) { this.attrs[k] = String(v); }
  getAttribute(k) { return k in this.attrs ? this.attrs[k] : null; }
  appendChild(c) { this.children.push(c); return c; }
  insertBefore(c, ref) {
    if (!ref) { this.children.push(c); return c; }
    const i = this.children.indexOf(ref);
    if (i === -1) this.children.push(c); else this.children.splice(i, 0, c);
    return c;
  }
  _match(el, sel) {
    if (sel.charAt(0) === ".")
      return (el.className || "").split(/\\s+/).indexOf(sel.slice(1)) !== -1;
    if (sel.charAt(0) === "#") return el.id === sel.slice(1);
    return el.tag === sel;
  }
  querySelector(sel) {
    for (const c of this.children) {
      if (this._match(c, sel)) return c;
      const r = c.querySelector(sel);
      if (r) return r;
    }
    return null;
  }
  querySelectorAll(sel) {
    const out = [];
    for (const c of this.children) {
      if (this._match(c, sel)) out.push(c);
      out.push(...c.querySelectorAll(sel));
    }
    return out;
  }
  get textContent() {
    let t = this._text;
    for (const c of this.children) t += c.textContent;
    return t;
  }
  set textContent(v) { this._text = String(v); this.children = []; }
}
const document = { createElement: (t) => new El(t) };
function makeWrap() {
  const wrap = document.createElement("div");
  const body = document.createElement("div");
  body.className = "msg-body";
  const bubble = document.createElement("div");
  bubble.className = "bubble";
  body.appendChild(bubble);
  wrap.appendChild(body);
  return wrap;
}
function describe(el) {
  return {
    text: el.textContent,
    children: el.children.map(
      (c) => ({ tag: c.tag, cls: c.className, text: c.textContent })
    ),
  };
}
"""


@pytest.mark.skipif(not HAVE_NODE, reason="node not available")
def test_suffix_shapes_under_node() -> None:
    """The REAL app.js ``readRangeSuffix`` under node — the three suffix
    shapes + the malformed fallbacks (the guard: bools / strings / 0 are
    not whole line numbers ≥ 1; a one-sided well-formed pair renders its
    one-sided shape; a well-formed pair renders the range)."""
    fn = _extract(_js(), "readRangeSuffix")
    cases = [
        [42, 30, " (lines 42–71)"],
        [42, None, " (from line 42)"],
        [None, 5, " (first 5 lines)"],
        [None, None, ""],
        ["x", 5, " (first 5 lines)"],  # malformed offset, valid limit
        [42, "y", " (from line 42)"],  # valid offset, malformed limit
        [0, 5, " (first 5 lines)"],  # offset 0 is not ≥ 1
        [42, 0, " (from line 42)"],  # limit 0 is not ≥ 1
        [True, 5, " (first 5 lines)"],  # a bool is not an integer
        [1, 1, " (lines 1–1)"],  # the smallest well-formed range
    ]
    driver = (
        fn
        + "\nconst cases = "
        + json.dumps([[c[0], c[1]] for c in cases])
        + ";\nconsole.log(JSON.stringify(cases.map((c) => readRangeSuffix(c[0], c[1]))));"
    )
    out = json.loads(_run_node(driver))
    assert out == [c[2] for c in cases], out


@pytest.mark.skipif(not HAVE_NODE, reason="node not available")
def test_plain_line_byte_identical_and_range_line_carries_the_suffix() -> None:
    """The REAL app.js ``appendToolLine`` under node (against the DOM
    stub): a PLAIN read (no offset/limit) renders the pre-phase line
    byte-identical — ``📄 Reading <code>path</code>``, a single ``code``
    child, NO ``.read-range`` span — while a RANGE read appends the
    ``.read-range`` sibling after the ``code`` with the exact suffix."""
    suffix = _extract(_js(), "readRangeSuffix")
    append = _extract(_js(), "appendToolLine")
    driver = (
        _DOM_STUB
        + "\n"
        + suffix
        + "\n"
        + append
        + '\nconst ARG = "samedoc/twice.md";\n'
        + "const w1 = makeWrap();\n"
        + 'appendToolLine(w1, "read", ARG);\n'
        + 'const plain = describe(w1.querySelector(".tool-call"));\n'
        + "const w2 = makeWrap();\n"
        + 'appendToolLine(w2, "read", ARG, 10, 20);\n'
        + 'const range = describe(w2.querySelector(".tool-call"));\n'
        + "console.log(JSON.stringify({ plain, range }));"
    )
    out = json.loads(_run_node(driver))
    plain, range = out["plain"], out["range"]
    # The plain line: byte-identical to pre-phase — ONE <code> child, no
    # .read-range span, the exact pinned text.
    assert plain["text"] == "📄 Reading samedoc/twice.md", plain
    assert len(plain["children"]) == 1, plain
    assert plain["children"][0] == {"tag": "code", "cls": "", "text": "samedoc/twice.md"}, plain
    assert all(c["cls"] != "read-range" for c in plain["children"]), (
        "a plain read must carry NO .read-range span"
    )
    # The range line: the <code> child PLUS the .read-range sibling with
    # the exact suffix (10 + 20 - 1 = 29, en-dash).
    assert range["text"] == "📄 Reading samedoc/twice.md (lines 10–29)", range
    assert range["children"][0] == {"tag": "code", "cls": "", "text": "samedoc/twice.md"}, range
    assert range["children"][1] == {
        "tag": "span",
        "cls": "read-range",
        "text": " (lines 10–29)",
    }, range


@pytest.mark.skipif(not HAVE_NODE, reason="node not available")
def test_shared_page_line_parity_under_node() -> None:
    """The REAL shared.js ``addToolLines`` under node renders the SAME
    line as app.js's ``appendToolLine`` for the same record (the
    parity contract — the shared page re-renders saved records
    pixel-identically to the chat page): identical text and identical
    children (the ``code`` + the ``.read-range`` span with the same
    suffix). A record WITHOUT the fields renders the plain line on both
    pages."""
    shared_suffix = _extract(_shared_js(), "readRangeSuffix")
    add_lines = _extract(_shared_js(), "addToolLines")
    app_suffix = _extract(_js(), "readRangeSuffix")
    append = _extract(_js(), "appendToolLine")
    driver = (
        _DOM_STUB
        + "\n"
        + app_suffix
        + "\n"
        + append
        + '\nconst ARG = "samedoc/twice.md";\n'
        # app.js: a range read + a plain read
        + "const wa = makeWrap();\n"
        + 'appendToolLine(wa, "read", ARG, 10, 20);\n'
        + 'const appRange = describe(wa.querySelector(".tool-call"));\n'
        + "const wp = makeWrap();\n"
        + 'appendToolLine(wp, "read", ARG);\n'
        + 'const appPlain = describe(wp.querySelector(".tool-call"));\n'
        # shared.js: the SAME record (range + no-fields) through addToolLines
        + shared_suffix.replace("function readRangeSuffix", "function sharedSuffix")
        + "\n"
        + add_lines.replace(
            "readRangeSuffix(t.offset, t.limit)", "sharedSuffix(t.offset, t.limit)"
        )
        + "const ws = makeWrap();\n"
        + 'addToolLines(ws, [{ name: "read", argument: ARG, offset: 10, limit: 20 }]);\n'
        + 'const sharedRange = describe(ws.querySelector(".tool-call"));\n'
        + "const wn = makeWrap();\n"
        + 'addToolLines(wn, [{ name: "read", argument: ARG }]);\n'
        + 'const sharedPlain = describe(wn.querySelector(".tool-call"));\n'
        + "console.log(JSON.stringify({ appRange, appPlain, sharedRange, sharedPlain }));"
    )
    out = json.loads(_run_node(driver))
    # The range line is pixel-identical across the two pages.
    assert out["sharedRange"] == out["appRange"], (
        f"parity broken (range): {out['sharedRange']} vs {out['appRange']}"
    )
    # A record without the fields renders the plain line on both pages.
    assert out["sharedPlain"] == out["appPlain"], (
        f"parity broken (plain): {out['sharedPlain']} vs {out['appPlain']}"
    )
    # And the plain line carries no .read-range span (byte-identical).
    assert all(c["cls"] != "read-range" for c in out["sharedPlain"]["children"])