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

"""Unit: the phase-117 tool-calls DISCLOSURE contract (task 01).

The owner's visual-glitch report (2026-09-15): one per-call tool "card"
per ``tool`` frame — 6+ stacked full-width bordered cards on a phone —
swamped a completed answer, and the flex row broke the label
mid-word. The fix (phase 117, owner decisions D1–D6) wraps the
existing ``.tool-calls`` list in a native ``details`` disclosure with a
plain-text "Tool call(s) (N)" summary — created OPEN on the first live
``tool`` frame, folded at rest (delta/done/stop via ``closeToolCalls``),
and rendered CLOSED on the restore path and the shared page (D3). The
line bytes, the four label literals, and the ``<code>`` textContent
arguments stay byte-identical (D6), so the phase-37/70/87/95 pins
stay green.

No ``app/`` logic (frontend-only, D1) — like
``test_frontend_tool_states.py``, this module pins the JS/CSS markers
at source level: the disclosure/summary build (task 01) and the
debox/dechip + disclosure CSS contract (task 02). The E2E story suite
(task 03) completes the phase.
"""
from __future__ import annotations

import re
from pathlib import Path

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

#: The four pinned tool-line label literals (D6) — the emoji guard and
#: the phase-37/70 pins key off these exact bytes.
PINNED_LABELS = (
    'line.textContent = "📄 Reading "',
    'line.textContent = "🔎 Searching for "',
    'line.textContent = "🔎 Listing documents in "',
    'line.textContent = "🔎 Listing documents"',
)


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


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


def _css() -> str:
    return STYLES_CSS.read_text(encoding="utf-8")


def _fn(src: str, name: str) -> str:
    """The flat function body (house extraction: first ``\n}\n`` after
    the definition — the function must stay flat, no nested
    declarations)."""
    fn = src.find(f"function {name}")
    assert fn != -1, f"{name} must exist"
    return src[fn : src.find("\n}\n", fn)]


def test_append_tool_line_builds_an_open_details_disclosure() -> None:
    """appendToolLine (D2/D3/D5): the FIRST frame creates a native
    ``details.tool-calls-disclosure`` — a ``summary.tool-calls-summary``
    (first child) + the existing ``.tool-calls`` list (role=list +
    aria-label "Tool calls", second child) — inserted before the bubble
    where the list used to be. It starts OPEN while the turn is live;
    every append re-renders the plain-text "Tool call(s) (N)" count on
    the summary through textContent (no innerHTML anywhere)."""
    body = _fn(_js(), "appendToolLine")
    assert "document.createElement(\"details\")" in body
    assert "className = \"tool-calls-disclosure\"" in body
    assert "container.open = true", (
        "D3: created OPEN on the first live tool frame — the calls and "
        "the phase-87 .tool-elapsed suffix stay visible during the turn"
    )
    assert "document.createElement(\"summary\")" in body
    assert "className = \"tool-calls-summary\"" in body
    # The list keeps its exact phase-37 shape, nested in the disclosure.
    assert "className = \"tool-calls\"" in body
    assert 'setAttribute("role", "list")' in body
    assert 'setAttribute("aria-label", "Tool calls")' in body
    assert 'insertBefore(container, body.querySelector(".bubble"))' in body, (
        "the disclosure sits ABOVE the answer, below an existing Thinking block"
    )
    # D5: the count rides the summary — the template fragment itself
    # (singular for one call, plural otherwise), textContent-built.
    assert "Tool call${n === 1 ? \"\" : \"s\"} (${n})" in body, (
        "the plain-text count template (D5) on every append"
    )
    assert "innerHTML" not in body, (
        "no HTML injection surface on tool lines — textContent only"
    )


def test_append_tool_line_keeps_the_four_pinned_labels() -> None:
    """D6: the four ``line.textContent`` label literals and the
    ``<code>`` textContent arguments stay byte-identical — the emoji
    guard, the phase-37/70 unit pins, and the E2E text assertions all
    key off these exact bytes."""
    body = _fn(_js(), "appendToolLine")
    for label in PINNED_LABELS:
        assert label in body, f"pinned label literal changed: {label!r}"
    assert "code.textContent = argument" in body, (
        "the path/pattern/scope is data — textContent, never innerHTML"
    )


def test_close_tool_calls_defined_and_called_at_every_rest_site() -> None:
    """closeToolCalls (D3): defined next to closeThinkingBlock,
    idempotent (optional-chaining query → open=false), and called at
    ALL rest sites — the delta handler (the answer began), the done
    handler (the turn ended), the stop/abort settle (the turn was
    stopped), and the restore path — so the definition + ≥4 calls."""
    js = _js()
    body = _fn(js, "closeToolCalls")
    assert 'querySelector?.(".tool-calls-disclosure")' in body, (
        "targets the disclosure of the given wrap only"
    )
    assert "disc.open = false" in body, "fold: open=false (idempotent)"
    assert js.count("closeToolCalls(wrap)") >= 4, (
        "the definition + the delta/done/stop handler sites + the "
        "renderStoredMessage restore fold — the disclosure settles "
        "exactly where the Thinking block settles"
    )


def test_restore_path_folds_the_disclosure() -> None:
    """renderStoredMessage (D3): a restored brain record with `tools`
    re-renders through the SAME appendToolLine (byte-identical), and
    the disclosure is FOLDED right after the loop — a completed turn
    from storage is one compact "Tool calls (N)" line, not N stacked
    cards (the space fix; mirrors the thinking restore rendering
    collapsed)."""
    js = _js()
    fn = js.find("function renderStoredMessage")
    assert fn != -1
    body = js[fn : js.find("function restoreConversation", fn)]
    assert "appendToolLine(wrap, t.name, arg, tOffset, tLimit)" in body
    assert "closeToolCalls(wrap)" in body
    assert (
        body.find("appendToolLine(wrap, t.name, arg, tOffset, tLimit)")
        < body.find("closeToolCalls(wrap)")
    ), "the fold sits AFTER the tool-line restore loop"


def test_thinking_anchor_accounts_for_the_disclosure() -> None:
    """ensureThinkingBlock: the anchor is the WHOLE disclosure (a
    `thinking` frame after the first `tool` frame lands the scratchpad
    ABOVE the disclosure, not inside it); the bare .tool-calls and
    .bubble terms stay as fallbacks, and the block still opens while
    active (phase-109 toggle behavior untouched)."""
    body = _fn(_js(), "ensureThinkingBlock")
    assert ".tool-calls-disclosure" in body, "the new anchor term"
    assert 'querySelector(".tool-calls")' in body, "the pre-117 fallback"
    assert 'querySelector(".bubble")' in body
    assert "block.open = true" in body


def test_shared_page_add_tool_lines_builds_a_closed_disclosure() -> None:
    """shared.js addToolLines (D3 parity): the SAME
    ``details.tool-calls-disclosure`` + summary + ``.tool-calls`` list —
    but created CLOSED (a pure render has no live turn to open it),
    with the count set once at the end. The four label literals, the
    three textContent-only argument lines, and the phase-95 marker stay
    byte-identical (no innerHTML anywhere)."""
    body = _fn(_shared_js(), "addToolLines")
    assert "document.createElement(\"details\")" in body
    assert "className = \"tool-calls-disclosure\"" in body
    assert "document.createElement(\"summary\")" in body
    assert "open = false" in body, (
        "D3: the shared page renders the disclosure CLOSED — never an "
        "auto-expanded record"
    )
    assert "className = \"tool-calls\"" in body
    for label in PINNED_LABELS:
        assert label in body, f"pinned label literal changed: {label!r}"
    assert "Tool call${n === 1 ? \"\" : \"s\"} (${n})" in body, (
        "the same plain-text count template (D5), set once at the end"
    )
    assert body.count("code.textContent = argument") == 3, (
        "all three argument-bearing lines (read / grep / ls) stay "
        "textContent-only"
    )
    assert "innerHTML" not in body, (
        "no HTML injection surface on shared tool lines — textContent only"
    )


def test_tool_call_rule_is_deboxed_inline_flow() -> None:
    """D4: the ``.tool-call`` rule is DEBOXED — no ``display: flex``,
    no card (no background / border / radius / padding), and no
    ``var(--accent-line)`` left border. The accent now rides the TEXT
    (``var(--accent-ink)``, ≈10.4:1 on the surface), and the line keeps
    the compact status metrics + ``overflow-wrap: anywhere`` so the
    label + inline ``code`` flow as ONE continuous run — a long path
    wraps to the left edge and the label never breaks mid-word (the
    "Rea/ding" glitch is gone)."""
    m = re.search(r"\.tool-call \{([^}]*)\}", _css())
    assert m, "the .tool-call rule must exist"
    row = m.group(1)
    assert "display: flex" not in row, (
        "deboxed: no flex — the label + code are one inline run"
    )
    assert "var(--accent-line)" not in row, "deboxed: no accent left border"
    assert "border" not in row, "deboxed: no card borders at all"
    assert "background" not in row, "deboxed: no card background"
    assert "padding" not in row, "deboxed: no card padding"
    assert "var(--accent-ink)" in row, (
        "the accent now rides the text color (≈10.4:1 on the surface)"
    )
    assert "font-size: 0.8rem" in row, "the compact status metrics stay"
    assert "overflow-wrap: anywhere" in row, "the path wraps inside the run"


def test_tool_call_code_rule_is_dechipped() -> None:
    """D4: the ``.tool-call code`` rule KEEPS ``var(--mono)`` +
    ``var(--ink)`` (≈11.5:1 on the surface — AA) but LOSES the chip
    (no background, no padding, no radius) — the path is inline text
    in the line's run now."""
    m = re.search(r"\.tool-call code \{([^}]*)\}", _css())
    assert m, "the .tool-call code rule must exist"
    code = m.group(1)
    assert "var(--mono)" in code
    assert "var(--ink)" in code
    assert "background" not in code, "dechipped: no chip background"
    assert "padding" not in code, "dechipped: no chip padding"
    assert "border-radius" not in code, "dechipped: no chip radius"
    assert "overflow-wrap: anywhere" in code


def test_tool_calls_disclosure_and_summary_rules_exist() -> None:
    """Phase 117 (D2/D4): the NEW ``.tool-calls-disclosure`` and
    ``.tool-calls-summary`` rules exist — the summary is a native
    focusable toggle carrying the accent TEXT (``var(--accent-ink)``,
    ≈10.4:1 on the surface; text + color, never color alone, B5),
    modeled on the details.thinking family, with no new color literal
    (the phase-92 zero-literal invariant)."""
    css = _css()
    assert re.search(r"\.tool-calls-disclosure \{", css), (
        "the .tool-calls-disclosure rule must exist"
    )
    m = re.search(r"\.tool-calls-summary \{([^}]*)\}", css)
    assert m, "the .tool-calls-summary rule must exist"
    summary = m.group(1)
    assert "var(--accent-ink)" in summary, (
        "the accent rides the summary text (≈10.4:1 on the surface)"
    )
    assert "cursor: pointer" in summary, "a toggle affordance"