"""Unit: the phase-146 (task 02) "the search tool shows WHERE"
frontend + record contract.

The wire half (the ``ChatToolEvent`` additive ``path`` + the frame
builder) is pinned by phase 146 task 01 (``test_sse_events.py`` /
``test_chat_gate.py``). This task's behavior lives in
``frontend/assets/app.js`` (``appendToolLine``'s additive ``scope``
param + the ``.grep-scope`` span, the live ``tool`` branch's
``ev.path`` read + the ``toolRecord.path`` stamp + the status label's
`` in <scope>`` extension, the restore path's ``t.path`` pass-through)
and ``app/schemas.py`` (the saved record's additive ``path`` on
``ToolCall`` — the persistence boundary that carries the scope from
the live record through the ``bor.chat.v1`` JSONB to the restore
path). Like the other frontend-adjacent unit files
(``test_read_range_tool_lines.py`` is the phase-139 precedent,
``test_frontend_tool_states.py`` the phase-37 one), this module pins
the JS markers the story depends on so a silent regression in the
scope wording, the string guard, the persistence shape, or the
byte-identity of bare greps is caught without a browser. A small
node-driven behavioral check (skipped when node is unavailable, the
phase-139 pattern) proves the scoped line's structure (two ``<code>``
spans + the `` in `` text node) and the bare line's byte-identity.
The E2E gate is the phase's story suite
(``tests/e2e/test_search_tool_scope.py``).
"""
from __future__ import annotations

import json
import shutil
import subprocess
from pathlib import Path

import pytest
from pydantic import ValidationError

from app.schemas import ChatMessage, ToolCall

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

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

#: The saved record's scope cap (mirrors ``argument`` — the combined
#: ``source/path`` identity is ≤ 120 + 1 + 1000; 2 000 is the same
#: ×2 headroom).
PATH_CAP = 2000


def _js() -> str:
    return APP_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 ``}`` (the house 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 _live_branch(js: str) -> str:
    """The live ``tool`` SSE branch (up to the ``delta`` branch)."""
    tool_idx = js.find('ev.type === "tool"')
    delta_idx = js.find('ev.type === "delta"')
    assert -1 < tool_idx < delta_idx
    return js[tool_idx:delta_idx]


def _restore_body(js: str) -> str:
    """The phase-14 restore path (``renderStoredMessage``)."""
    fn = js.find("function renderStoredMessage")
    assert fn != -1
    end = js.find("function restoreConversation")
    assert fn < end
    return js[fn:end]


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 — appendToolLine: the .grep-scope span on the Searching line
# --------------------------------------------------------------------------


def test_append_tool_line_signature_takes_optional_scope() -> None:
    """appendToolLine gains the additive ``scope`` param (fifth,
    default ``null`` — a pre-phase 5-arg call renders byte-identical),
    and the grep arm appends the scope span through the pinned
    structure (a ``.grep-scope`` span SIBLING after the pattern
    ``<code>`` — the phase-139 read-range-suffix precedent)."""
    js = _js()
    assert (
        "function appendToolLine(wrap, name, argument, offset = null, "
        "limit = null, scope = null)" in js
    ), "the signature carries the additive scope (default null)"
    body = _extract(js, "appendToolLine")
    assert "if (typeof scope === \"string\" && scope)" in body, (
        "the span is appended ONLY when the scope is a non-empty string"
    )
    assert 'scopeSpan.className = "grep-scope"' in body, (
        "the scope rides a .grep-scope span"
    )
    assert 'document.createTextNode(" in ")' in body, (
        "the ` in ` join is a text node (the scope is data, never markup)"
    )
    assert "scopeCode.textContent = scope" in body, (
        "the scope is data — textContent, never innerHTML"
    )


def test_grep_scope_span_is_a_sibling_after_the_pattern_code() -> None:
    """The .grep-scope span is a SIBLING appended AFTER the pattern
    ``<code>`` child — the pinned ``🔎 Searching for `` + ``<code>``
    bytes are untouched (the phase-70/87/117 label pins + the frontend
    emoji guard stay green; no new emoji)."""
    body = _extract(_js(), "appendToolLine")
    assert 'line.textContent = "🔎 Searching for "' in body, (
        "the pinned grep label literal is untouched"
    )
    # Inside the grep arm: the pattern <code> is appended first, the
    # scope span after it.
    grep_arm = body.find("🔎 Searching for ")
    ls_arm = body.find("🔎 Listing documents in ")
    assert -1 < grep_arm < ls_arm
    arm = body[grep_arm:ls_arm]
    code_append = arm.find("line.appendChild(code)")
    scope_append = arm.find("line.appendChild(scopeSpan)")
    assert -1 < code_append < scope_append, (
        "the scope span lands AFTER the pattern <code> child"
    )
    assert "innerHTML" not in body, (
        "no HTML injection surface on tool lines — textContent only"
    )


def test_only_the_grep_arm_reads_the_scope() -> None:
    """The scope param feeds ONLY the grep arm: the read / ls / listing
    arms never consult it (a scope on a non-grep call renders exactly
    the pre-phase line — no .grep-scope span outside the grep arm)."""
    body = _extract(_js(), "appendToolLine")
    grep_arm = body.find("🔎 Searching for ")
    ls_arm = body.find("🔎 Listing documents in ")
    guard = body.find("typeof scope === \"string\" && scope")
    # The scope guard appears exactly once in the function — inside the
    # grep arm (after the Searching label, before the ls arm).
    assert body.count("typeof scope === \"string\" && scope") == 1
    assert -1 < grep_arm < guard < ls_arm, (
        "the scope guard sits inside the grep arm only"
    )
    # The read arm renders the range suffix only — never the scope.
    read_arm_end = body.find("🔎 Searching for ")
    read_arm = body[:read_arm_end]
    assert "scopeSpan" not in read_arm


# --------------------------------------------------------------------------
# app.js — the live `tool` branch: ev.path + the toolAcc stamp + label
# --------------------------------------------------------------------------


def test_live_tool_branch_reads_the_scope_with_the_guard() -> None:
    """The live ``tool`` branch reads ``ev.path`` with the SAME string
    guard as ``argument`` (``typeof ev.path === "string" && ev.path``
    → ``null`` when absent / empty / malformed), and the record gains
    ``path`` ONLY when non-null — a bare grep keeps the exact
    pre-phase ``{name, argument}`` shape (the additive ``bor.chat.v1``
    JSONB — old records restore byte-identically, no migration)."""
    branch = _live_branch(_js())
    assert (
        "typeof ev.path === \"string\" && ev.path ? ev.path : null" in branch
    ), "ev.path reads through the house string guard → null when absent"
    assert "const toolRecord = { name, argument }" in branch, (
        "the base record stays {name, argument}-generic"
    )
    assert "if (framePath !== null) toolRecord.path = framePath" in branch, (
        "path joins the record ONLY when non-null (additive key)"
    )
    assert "toolAcc.push(toolRecord)" in branch, "every tool frame is recorded"
    # The scope rides the SAME helper (the line's fifth argument).
    assert (
        "appendToolLine(wrap, name, argument, frameOffset, frameLimit, "
        "framePath)" in branch
    )


def test_live_grep_status_carries_the_scope() -> None:
    """The grep status label shows WHERE the search runs:
    ``… is searching for <pattern> in <source/path>`` — the scope rides
    the template's additive `` in <scope>`` extension (empty-string
    fallback when the frame carried none, so a bare grep renders the
    EXACT pre-phase label). The read / ls labels are untouched."""
    branch = _live_branch(_js())
    assert (
        "`${brand()} is searching for ${argument}"
        "${framePath ? ` in ${framePath}` : \"\"}`" in branch
    ), "the grep status carries the scope (the in-scope extension)"
    # The read / ls labels are byte-identical to pre-phase.
    assert (
        "`${brand()} is reading ${argument}${readRangeSuffix(frameOffset, frameLimit)}`"
        in branch
    )
    assert "`${brand()} is listing documents in ${argument}`" in branch
    assert "`${brand()} is listing documents`" in branch
    # The OLD bare-grep label literal is gone (superseded by the
    # additive template) — the byte-identity lives in the template's
    # empty-string fallback (pinned behaviorally under node below).
    assert "`${brand()} is searching for ${argument}`" not in branch


# --------------------------------------------------------------------------
# app.js — the restore path: the stored scope re-renders the line
# --------------------------------------------------------------------------


def test_restore_path_passes_the_stored_scope_through() -> None:
    """The phase-14 restore path (renderStoredMessage): a stored tool
    record with ``path`` (the live ``toolAcc`` stamp — additive on
    ``bor.chat.v1``) re-renders the SAME scope through the SAME helper;
    a record saved before the phase (no ``path`` key) renders
    byte-identically (the guard → null → no span)."""
    body = _restore_body(_js())
    assert (
        "typeof t.path === \"string\" && t.path ? t.path : null" in body
    ), "the stored scope reads through the house string guard"
    assert (
        "appendToolLine(wrap, t.name, arg, tOffset, tLimit, tPath)" in body
    ), "the stored scope rides the SAME helper"


# --------------------------------------------------------------------------
# app/schemas.py — ToolCall.path: the persistence boundary
# --------------------------------------------------------------------------


def test_tool_call_path_absent_by_default_and_omitted() -> None:
    """A tool record without ``path`` (every pre-phase record, every
    bare grep) validates UNCHANGED and serializes WITHOUT the key —
    ABSENT, never null: the saved shape stays byte-identical to
    pre-phase (the phase-50 backward-compat rule, no migration)."""
    call = ToolCall.model_validate({"name": "grep", "argument": "p"})
    assert call.path is None
    dumped = call.model_dump()
    assert "path" not in dumped, dumped
    # The full pre-phase key set is exactly what round-trips.
    assert set(dumped) == {
        "name",
        "argument",
        "truncated",
        "chars_shown",
        "chars_total",
        "offset",
        "limit",
    }, dumped


def test_tool_call_path_round_trips_when_set() -> None:
    """A SCOPED grep's record carries ``path`` (the re-searched
    document's combined ``source/path``) through validate → dump —
    the save → restore round-trip keeps it, so the restore path and
    the shared page can re-render the scope."""
    call = ToolCall.model_validate(
        {"name": "grep", "argument": "p", "path": "search_docs/reese-notes.md"}
    )
    assert call.path == "search_docs/reese-notes.md"
    assert call.model_dump()["path"] == "search_docs/reese-notes.md"


def test_tool_call_path_at_cap_validates() -> None:
    call = ToolCall.model_validate({"name": "grep", "argument": "p", "path": "a" * PATH_CAP})
    assert len(call.path or "") == PATH_CAP


def test_tool_call_path_one_over_cap_rejects() -> None:
    with pytest.raises(ValidationError) as exc:
        ToolCall.model_validate(
            {"name": "grep", "argument": "p", "path": "a" * (PATH_CAP + 1)}
        )
    assert any(e["loc"] == ("path",) for e in exc.value.errors()), exc.value.errors()


def test_chat_message_scoped_tool_record_crosses_the_boundary() -> None:
    """The full message boundary (``extra="forbid"`` on
    ``ChatMessage``): ``path`` is an ACCEPTED key on the nested tool
    record — a scoped grep's brain record does not 422 at the
    anonymous write surface (the phase-113 lesson: a missing key
    silently unsaves the record), and the dump keeps it."""
    msg = ChatMessage.model_validate(
        {
            "who": "brain",
            "text": "ok",
            "tools": [
                {"name": "grep", "argument": "p", "path": "search_docs/reese-notes.md"},
                {"name": "grep", "argument": "p"},
            ],
        }
    )
    dumped = msg.model_dump()
    assert dumped["tools"][0]["path"] == "search_docs/reese-notes.md"
    assert "path" not in dumped["tools"][1], dumped["tools"][1]


# --------------------------------------------------------------------------
# behavior (node): the scoped line's structure + the bare line's
# byte-identity
# --------------------------------------------------------------------------

#: A minimal DOM stub — the phase-139 stub plus ``createTextNode``
#: (the .grep-scope span holds a text node + a <code> child). Every
#: node is snapshotted as a JSON row (the test-document-viewer
#: pattern).
_DOM_STUB = """
class TextNode {
  constructor(text) { this._text = String(text); }
  get textContent() { return this._text; }
}
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),
  createTextNode: (t) => new TextNode(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) =>
        c.tag
          ? {
              tag: c.tag,
              cls: c.className,
              text: c.textContent,
              children: describe(c).children,
            }
          : { text: c.textContent }
    ),
  };
}
"""


@pytest.mark.skipif(not HAVE_NODE, reason="node not available")
def test_scoped_grep_line_and_bare_byte_identity_under_node() -> None:
    """The REAL app.js ``appendToolLine`` under node (against the DOM
    stub): a BARE grep (no scope — including an empty string and a
    non-string scope, the guard's fallbacks) renders the pre-phase line
    byte-identically — ``🔎 Searching for <code>pattern</code>``, a
    single ``code`` child, NO ``.grep-scope`` span; a SCOPED grep
    appends the ``.grep-scope`` span AFTER the pattern ``<code>``
    holding the `` in `` text node + the second ``<code>`` (the scope,
    data, never markup). The legacy name (``search_documents``) keeps
    the same byte-identity for a bare call."""
    append = _extract(_js(), "appendToolLine")
    driver = (
        _DOM_STUB
        + "\n"
        + append
        + '\nconst PATTERN = "reese-sentinel-42";\n'
        + 'const SCOPE = "search_docs/reese-notes.md";\n'
        # bare grep (no scope)
        + "const w0 = makeWrap();\n"
        + 'appendToolLine(w0, "grep", PATTERN);\n'
        + 'const bare = describe(w0.querySelector(".tool-call"));\n'
        # bare grep, legacy name (no scope)
        + "const w1 = makeWrap();\n"
        + 'appendToolLine(w1, "search_documents", PATTERN);\n'
        + 'const legacy = describe(w1.querySelector(".tool-call"));\n'
        # guarded fallbacks: empty string + non-string scope
        + "const w2 = makeWrap();\n"
        + 'appendToolLine(w2, "grep", PATTERN, null, null, "");\n'
        + 'const emptyScope = describe(w2.querySelector(".tool-call"));\n'
        + "const w3 = makeWrap();\n"
        + 'appendToolLine(w3, "grep", PATTERN, null, null, 42);\n'
        + 'const badScope = describe(w3.querySelector(".tool-call"));\n'
        # the scoped grep
        + "const w4 = makeWrap();\n"
        + 'appendToolLine(w4, "grep", PATTERN, null, null, SCOPE);\n'
        + 'const scoped = describe(w4.querySelector(".tool-call"));\n'
        "console.log(JSON.stringify("
        "{ bare, legacy, emptyScope, badScope, scoped }));"
    )
    out = json.loads(_run_node(driver))
    bare, legacy, empty_scope, bad_scope, scoped = (
        out["bare"],
        out["legacy"],
        out["emptyScope"],
        out["badScope"],
        out["scoped"],
    )

    # The bare line: byte-identical to pre-phase — ONE <code> child,
    # no .grep-scope span, the exact pinned text.
    assert bare["text"] == "🔎 Searching for reese-sentinel-42", bare
    assert bare["children"] == [
        {
            "tag": "code",
            "cls": "",
            "text": "reese-sentinel-42",
            "children": [],
        }
    ], bare
    # The legacy-name bare call renders the SAME bytes (no migration).
    assert legacy == bare, (legacy, bare)
    # The guard's fallbacks (empty string / non-string) → the bare line.
    assert empty_scope == bare, (empty_scope, bare)
    assert bad_scope == bare, (bad_scope, bare)

    # The scoped line: the pinned prefix + pattern, then the scope span.
    assert (
        scoped["text"]
        == "🔎 Searching for reese-sentinel-42 in search_docs/reese-notes.md"
    ), scoped
    assert scoped["children"][0] == {
        "tag": "code",
        "cls": "",
        "text": "reese-sentinel-42",
        "children": [],
    }, scoped
    span = scoped["children"][1]
    assert span["tag"] == "span" and span["cls"] == "grep-scope", scoped
    assert span["text"] == " in search_docs/reese-notes.md", scoped
    # TWO <code> spans (pattern, then scope) with the " in " text node
    # between them — the textContent structure, not a regex over the
    # whole line (the phase-139 range-suffix pin style).
    assert span["children"][0] == {"text": " in "}, scoped
    assert span["children"][1] == {
        "tag": "code",
        "cls": "",
        "text": "search_docs/reese-notes.md",
        "children": [],
    }, scoped
    # Document order of the line's <code> elements: the pattern first
    # (the direct child), then the scope (inside the span).
    codes = [scoped["children"][0]["text"]] + [
        c["text"] for c in span["children"] if c.get("tag") == "code"
    ]
    assert codes == ["reese-sentinel-42", "search_docs/reese-notes.md"], scoped


@pytest.mark.skipif(not HAVE_NODE, reason="node not available")
def test_non_grep_arms_ignoring_the_scope_stay_byte_identical() -> None:
    """A non-grep call that somehow carried a scope (a read / an ls /
    the plain listing) renders EXACTLY the pre-phase line — the scope
    param feeds only the grep arm, so no .grep-scope span can leak
    into the other three lines."""
    append = _extract(_js(), "appendToolLine")
    range_suffix = _extract(_js(), "readRangeSuffix")
    driver = (
        _DOM_STUB
        + "\n"
        + range_suffix
        + "\n"
        + append
        + "const w0 = makeWrap();\n"
        + 'appendToolLine(w0, "read", "s/d.md", null, null, "x");\n'
        + 'const readLine = describe(w0.querySelector(".tool-call"));\n'
        + "const w1 = makeWrap();\n"
        + 'appendToolLine(w1, "ls", "s", null, null, "x");\n'
        + 'const lsLine = describe(w1.querySelector(".tool-call"));\n'
        + "const w2 = makeWrap();\n"
        + 'appendToolLine(w2, "ls", null, null, null, "x");\n'
        + 'const plainLine = describe(w2.querySelector(".tool-call"));\n'
        "console.log(JSON.stringify({ readLine, lsLine, plainLine }));"
    )
    out = json.loads(_run_node(driver))
    for line in (out["readLine"], out["lsLine"], out["plainLine"]):
        assert all(c.get("cls") != "grep-scope" for c in line["children"]), line
    assert out["readLine"]["text"] == "📄 Reading s/d.md", out["readLine"]
    assert out["lsLine"]["text"] == "🔎 Listing documents in s", out["lsLine"]
    assert out["plainLine"]["text"] == "🔎 Listing documents", out["plainLine"]