portfolio-optimiser/tests/test_read_file_directory_refusal_loadbearing.py

"""``read_file`` on a DIRECTORY is refused by name and pointed at ``read_dir``.

Finding (c) of the live K2 session (``docs/2026-09-06-major2-levende-k2.md`` § 3/§ 4): a live model
walking the ladder ``list_bundles -> read_bundle -> read_dir -> read_file`` reached a level holding
subdirectories (``30-1``, ``30-7``, ``521-001`` ...) and then called ``read_file`` on one of them.
Three such calls in one run.

**What was CHECKED FIRST, and what it found.** The order allows for two causes and asks which one
holds. It is the second. A listing DOES already separate the two kinds structurally: every
``directory_listing`` payload answers with ``directories`` (entries keyed ``path``, carrying a
subtree ``documents`` count) and ``documents`` (entries keyed ``name``, carrying ``type``, ``title``
and ``chars``) as two distinct keys, and no directory ever appears among the documents. Arm (4)
pins that, because it is a property this file now depends on rather than one it introduces. So no
trailing-``/`` marker is added: the shape already says which is which, and changing the payload
would move a listing three older gates measure byte for byte.

What was missing is the OTHER half. MEASURED before this work, on the shipped nested example base:

    read_file(id, "a")      -> builtins.IsADirectoryError: [Errno 21] Is a directory: '<abs path>'

An ``OSError``, so it lands on the crash channel rather than the CLI's refusal tuple and hosting's
400 arm, and it says nothing about which rung the caller should have used. The refusal now names
both -- that the path is a directory, and ``read_dir`` -- following ``VerdictLayerRefused`` and
``DimensionScopeRefused``: the rule lives in the TOOL, so it holds for both callers (the
exploration and, since S2c, the debate), and it is a ``ValueError`` because the caller is a model
choosing a path, not a program that is broken.

**MEASURED, REPORTED, NOT FIXED (outside this order).** The live call was
``read_file(".../30-7.md")`` -- the model appended ``.md`` to a directory NAME, which resolves to a
path that does not exist at all, not to the directory. Measured on the same base:

    read_file(id, "a.md")   -> builtins.FileNotFoundError: [Errno 2] No such file or directory

That is a second, adjacent defect with the same shape (an OSError on the crash channel where a
named refusal belongs), and the fix ordered here does not cover it. Arm (5) pins the measurement so
the gap is a fact in the suite rather than a sentence in a report.

Detach point: remove the directory branch from ``read_file`` -> RED on (1), (2) and (3).
"""

from __future__ import annotations

from pathlib import Path
from typing import Any

import pytest

from portfolio_optimiser.explore import DirectoryPathRefused, navigator_tools

_EXAMPLES = Path(__file__).resolve().parents[1] / "shared" / "examples"
#: The only NESTED base shipped -- the one that HAS a directory to ask for.
_NESTED = _EXAMPLES / "nav-golden-hierarchy" / "bundle"


def _tools(bundle_dir: Path) -> dict[str, Any]:
    return {t.name: t for t in navigator_tools((str(bundle_dir),))}


async def _invoke(tool: Any, **arguments: Any) -> str:
    """A tool's answer as text (S2c's helper: ``invoke`` returns ``[Content]``, and a test that
    stringified the list would compare object reprs and pass against anything)."""
    return "".join(getattr(c, "text", "") or "" for c in await tool.invoke(arguments=arguments))


def _a_directory(bundle_dir: Path) -> str:
    """A directory path taken out of the listing itself -- the same way a model gets one."""
    listing = _tools(bundle_dir)["read_bundle"].func(bundle_id=bundle_dir.name)
    assert listing["directories"], "fixture has no subdirectory to ask for"
    return str(listing["directories"][0]["path"])


def test_a_directory_path_is_refused_and_the_other_rung_is_named() -> None:
    """(1) the refusal says WHAT the path is and WHICH tool reads it."""
    path = _a_directory(_NESTED)
    message = _tools(_NESTED)["read_file"].func(bundle_id=_NESTED.name, path=path)
    assert message.startswith(f"REFUSED ({DirectoryPathRefused.__name__})"), (
        "the refusal is not distinguishable from a document's body"
    )
    assert path in message
    assert "directory" in message
    assert "read_dir" in message, "a refusal that does not name the other rung strands the caller"


def test_the_refusal_is_a_value_error_not_an_os_error() -> None:
    """(2) the channel, which is the half a message alone cannot carry.

    ``ValueError`` is the ``BundlePathNotFound``/``DimensionScopeRefused`` precedent -- the CLI's
    refusal tuple and hosting's 400 arm. The ``OSError`` assert is what tells a REPLACEMENT from a
    wrapper: re-raising ``IsADirectoryError`` with a better message would pass arm (1).
    """
    path = _a_directory(_NESTED)
    answer = _tools(_NESTED)["read_file"].func(bundle_id=_NESTED.name, path=path)
    # F99-D3: the refusal is RETURNED now, so the branch is identified by the kind it names. The
    # channel assertion moves onto the class itself and keeps both halves: it is on the CLI's
    # refusal tuple, and it is NOT a re-raised ``IsADirectoryError`` wearing a better message --
    # an ``OSError`` is outside ``_RETURNABLE_REFUSALS`` and would propagate rather than answer.
    assert answer.startswith(f"REFUSED ({DirectoryPathRefused.__name__})")
    assert issubclass(DirectoryPathRefused, ValueError)
    assert not issubclass(DirectoryPathRefused, OSError)


async def test_the_refusal_holds_through_the_real_tool_surface() -> None:
    """(3) reached through ``invoke``, not only through ``.func``.

    The seam a model actually calls is the tool, and a check that only ran on the plain function
    would be absent from the one caller it was written for.
    """
    path = _a_directory(_NESTED)
    answer = await _invoke(_tools(_NESTED)["read_file"], bundle_id=_NESTED.name, path=path)
    assert answer.startswith(f"REFUSED ({DirectoryPathRefused.__name__})")
    assert "read_dir" in answer


def test_a_listing_already_separates_directories_from_documents() -> None:
    """(4) the "check first" arm: the payload's shape is what distinguishes the two kinds.

    Also the anti-vacuity control for this file -- it proves the fixture really does hold both
    kinds, so arm (1) is asking for a directory rather than for nothing.
    """
    listing = _tools(_NESTED)["read_bundle"].func(bundle_id=_NESTED.name)
    directories = {d["path"] for d in listing["directories"]}
    documents = {d["name"] for d in listing["documents"]}
    assert directories and documents, "fixture must hold both kinds for this to mean anything"
    assert directories.isdisjoint(documents)
    assert all(set(d) == {"path", "documents"} for d in listing["directories"])
    assert all(set(d) == {"name", "type", "title", "chars"} for d in listing["documents"])


def test_a_document_is_still_returned_whole() -> None:
    """CONTROL: the branch is a gate, not a wall -- the rung it guards still works."""
    listing = _tools(_NESTED)["read_bundle"].func(bundle_id=_NESTED.name)
    name = listing["documents"][0]["name"]
    body = _tools(_NESTED)["read_file"].func(bundle_id=_NESTED.name, path=name)
    assert body.strip(), "reading a real document must be untouched by the directory branch"


def test_a_nonexistent_sibling_is_still_an_os_error() -> None:
    """(5) MEASURED, REPORTED, NOT FIXED: the live call's ACTUAL shape.

    The model appended ``.md`` to a directory name, which is not a directory -- it is a path that
    does not exist. This order fixes the directory case; this arm records that the adjacent case is
    unchanged, so the gap cannot be mistaken for covered. Written as an assertion on the CURRENT
    behaviour: when it goes red, someone has closed it, and that is a decision to be recorded.
    """
    path = _a_directory(_NESTED) + ".md"
    with pytest.raises(FileNotFoundError):
        _tools(_NESTED)["read_file"].func(bundle_id=_NESTED.name, path=path)