LLeMbas/tests/test_agent_patch.py

"""Applying a unified diff.

Pure unit tests, no server and no database: this is where the behaviour that
makes `file_edit` usable by a real model lives, and every case here is one that
a real model produces.
"""

from __future__ import annotations

import pytest

from lembas.services.agent import patch


def _apply(text: str, diff: str) -> str:
    return patch.apply(text, patch.parse(diff))


FILE = "\n".join(f"line {n}" for n in range(1, 21)) + "\n"


# --- The ordinary case ----------------------------------------------------------
def test_a_hunk_at_the_line_it_says_applies():
    result = _apply(
        FILE,
        "@@ -4,3 +4,3 @@\n line 3\n-line 4\n+LINE FOUR\n line 5\n",
    )
    assert "LINE FOUR" in result
    assert "line 4\n" not in result
    assert result.count("\n") == FILE.count("\n"), "no lines gained or lost"


def test_headers_are_tolerated():
    """Models emit them by habit. Refusing costs a round trip to say so."""
    result = _apply(
        FILE,
        "diff --git a/x.py b/x.py\nindex 1234567..89abcde 100644\n"
        "--- a/x.py\n+++ b/x.py\n@@ -4,3 +4,3 @@\n line 3\n-line 4\n+LINE FOUR\n line 5\n",
    )
    assert "LINE FOUR" in result


def test_several_hunks_apply_in_order():
    result = _apply(
        FILE,
        "@@ -2,3 +2,3 @@\n line 1\n-line 2\n+TWO\n line 3\n"
        "@@ -15,3 +15,3 @@\n line 14\n-line 15\n+FIFTEEN\n line 16\n",
    )
    assert "TWO" in result and "FIFTEEN" in result


def test_a_pure_insertion_needs_no_context():
    """And names the line it goes *after*, so it is not off by one the way
    every other hunk is."""
    result = _apply("a\nb\n", "@@ -1,0 +2,1 @@\n+inserted\n")
    assert result == "a\ninserted\nb\n"


# --- Line numbers drift, context does not ---------------------------------------
def test_a_hunk_whose_line_numbers_are_wrong_still_applies():
    """The single highest-value behaviour here. Models count from a truncated
    read or from the file as it was three edits ago and get the numbers wrong;
    they get the context right."""
    result = _apply(
        FILE,
        "@@ -1,3 +1,3 @@\n line 11\n-line 12\n+TWELVE\n line 13\n",
    )
    assert "TWELVE" in result
    assert "line 12\n" not in result


def test_a_hunk_that_matches_nowhere_is_refused_and_names_what_is_there():
    with pytest.raises(patch.PatchError) as caught:
        _apply(FILE, "@@ -4,3 +4,3 @@\n nothing\n-like this\n+new\n at all\n")

    message = caught.value.message
    assert "Hunk 1 did not apply" in message
    assert "Nothing was written" in message
    assert "Send a patch whose context matches" in message


def test_the_refusal_prints_the_file_around_where_the_hunk_expected_to_land():
    """One line of "but the file has …" was not enough to retry from. A model
    whose numbers are two out cannot see where it actually is, sends the same
    patch again, and that is most of the retry loop this tool produces. The
    window is numbered, because the numbers are what was wrong, and the hinted
    line is marked."""
    with pytest.raises(patch.PatchError) as caught:
        _apply(FILE, "@@ -4,3 +4,3 @@\n nothing\n-like this\n+new\n at all\n")

    message = caught.value.message
    assert "->     4  line 4" in message, message
    assert "     3  line 3" in message, "and what is on either side of it"
    assert "     5  line 5" in message


def test_a_hunk_past_the_end_is_told_where_the_end_is():
    """"(past the end of the file)" said the position was wrong without saying
    what would have been right, which is the same dead end one line further on."""
    with pytest.raises(patch.PatchError) as caught:
        _apply("one\ntwo\n", "@@ -40,3 +40,3 @@\n nothing\n-like this\n+new\n at all\n")

    assert "the file ends at line 2" in caught.value.message


def test_an_empty_file_says_that_rather_than_printing_nothing():
    with pytest.raises(patch.PatchError) as caught:
        _apply("", "@@ -1,3 +1,3 @@\n nothing\n-like this\n+new\n at all\n")

    assert "the file is empty" in caught.value.message


def test_ambiguous_context_is_refused_rather_than_guessed_at():
    """The one failure that silently corrupts a file. Two identical blocks and a
    hint pointing at neither: there is no way to tell which was meant."""
    text = "start\nsame\nsame\nsame\nmiddle\nsame\nsame\nsame\nend\n"
    with pytest.raises(patch.PatchError) as caught:
        _apply(text, "@@ -50,3 +50,3 @@\n same\n-same\n+CHANGED\n same\n")

    assert "appear" in caught.value.message
    assert "more unchanged lines" in caught.value.message.lower()


def test_drift_beyond_the_ceiling_is_not_searched():
    long = "\n".join(f"line {n}" for n in range(1, 1000)) + "\n"
    with pytest.raises(patch.PatchError):
        _apply(long, "@@ -1,3 +1,3 @@\n line 900\n-line 901\n+NINE\n line 902\n")


def test_nothing_is_written_when_a_later_hunk_fails():
    """Atomic. A half-applied file is worse than a refused one, and the model
    cannot tell the difference without reading it again."""
    with pytest.raises(patch.PatchError) as caught:
        _apply(
            FILE,
            "@@ -2,3 +2,3 @@\n line 1\n-line 2\n+TWO\n line 3\n"
            "@@ -15,3 +15,3 @@\n bogus\n-nope\n+x\n also bogus\n",
        )
    assert caught.value.hunk == 2


def test_hunks_out_of_order_are_refused():
    """Otherwise a duplicated hunk applies the same change twice."""
    with pytest.raises(patch.PatchError):
        _apply(
            FILE,
            "@@ -15,3 +15,3 @@\n line 14\n-line 15\n+FIFTEEN\n line 16\n"
            "@@ -2,3 +2,3 @@\n line 1\n-line 2\n+TWO\n line 3\n",
        )


# --- The things that break on real files ------------------------------------------
def test_a_crlf_file_round_trips_as_crlf():
    """Without normalising in and restoring out, every hunk on a Windows file
    fails on context that looks identical in the error message."""
    text = "alpha\r\nbeta\r\ngamma\r\n"
    result = _apply(text, "@@ -1,3 +1,3 @@\n alpha\n-beta\n+BETA\n gamma\n")

    assert result == "alpha\r\nBETA\r\ngamma\r\n"
    assert "\n\n" not in result.replace("\r\n", "\n\n").replace("\n\n", "\r\n")


def test_a_blank_context_line_with_no_leading_space_applies():
    """Trailing whitespace is stripped by half the things a model's output
    passes through, so this is the normal case rather than a malformed one."""
    text = "alpha\n\ngamma\n"
    result = _apply(text, "@@ -1,3 +1,3 @@\n alpha\n\n-gamma\n+GAMMA\n")
    assert result == "alpha\n\nGAMMA\n"


def test_a_file_with_no_trailing_newline_keeps_none():
    result = _apply("alpha\nbeta", "@@ -1,2 +1,2 @@\n alpha\n-beta\n+BETA\n")
    assert result == "alpha\nBETA"


def test_the_no_newline_marker_on_the_new_side_removes_the_trailing_newline():
    result = _apply(
        "alpha\nbeta\n",
        "@@ -1,2 +1,2 @@\n alpha\n-beta\n+BETA\n\\ No newline at end of file\n",
    )
    assert result == "alpha\nBETA"


def test_the_no_newline_marker_on_the_old_side_is_not_an_instruction():
    """git emits it for the old side too. Reading that as an instruction would
    strip a newline the patch never touched."""
    result = _apply(
        "alpha\nbeta\n",
        "@@ -1,2 +1,2 @@\n alpha\n-beta\n\\ No newline at end of file\n+BETA\n",
    )
    assert result == "alpha\nBETA\n"


# --- Refusing the unusable ---------------------------------------------------------
def test_a_patch_with_no_hunks_says_what_one_looks_like():
    with pytest.raises(patch.PatchError) as caught:
        patch.parse("just change line four please")
    assert "@@" in caught.value.message


def test_too_many_hunks_is_refused_and_points_at_file_write():
    diff = "".join(
        f"@@ -{n},1 +{n},1 @@\n-line {n}\n+LINE {n}\n" for n in range(1, patch.MAX_HUNKS + 5)
    )
    with pytest.raises(patch.PatchError) as caught:
        patch.parse(diff)
    assert "file_write" in caught.value.message


# --- Rendering -----------------------------------------------------------------------
def test_render_produces_a_diff_of_the_change():
    diff = patch.render("alpha\nbeta\n", "alpha\nBETA\n", "x.py")
    assert "-beta" in diff
    assert "+BETA" in diff
    assert "a/x.py" in diff


def test_render_is_bounded():
    """It goes on the message row forever and is re-parsed on every page load,
    and a generated file's diff can be larger than the file."""
    before = "\n".join(str(n) for n in range(500))
    after = "\n".join(f"x{n}" for n in range(500))
    diff = patch.render(before, after, "big.txt", max_lines=20)

    assert len(diff.split("\n")) <= 21
    assert "more lines" in diff