"""Tests for find_gaps — coverage map + code-vs-corpus signals."""

from __future__ import annotations

from pathlib import Path
from typing import Any

import pytest

from codex.synthesis import find_gaps
from tests.synthesis.conftest import StubLLM


def test_find_gaps_code_cites_missing_bibkey(
    monkeypatch: pytest.MonkeyPatch,
    mock_paper_titles: None,
    mock_settings: Path,
    fixture_chunks: list[dict[str, object]],
    tmp_path: Path,
) -> None:
    """A bibkey referenced in code but absent from corpus → direct gap lead."""
    # Build a small C++ source tree with an @cite pointing at a missing bibkey
    src_dir = tmp_path / "src"
    src_dir.mkdir()
    (src_dir / "main.cpp").write_text(
        "// @cite UnknownPaper2099\nvoid foo() {}\n",
        encoding="utf-8",
    )

    # All probes return the fixture chunks (so coverage map yields nothing)
    monkeypatch.setattr(
        "codex.synthesis._retrieve_chunks",
        lambda queries, top_k: [dict(c) for c in fixture_chunks],
    )

    leads = find_gaps(lib_path=str(src_dir), llm=StubLLM(""))
    bibkeys_in_gaps = {p.bibkey for lead in leads for p in lead.provenance}
    # The missing bibkey shows up as a gap
    assert any("UnknownPaper2099" in lead.title for lead in leads)
    assert "UnknownPaper2099" in bibkeys_in_gaps


def test_find_gaps_code_known_bibkey_not_reported(
    monkeypatch: pytest.MonkeyPatch,
    mock_paper_titles: None,
    mock_settings: Path,
    fixture_chunks: list[dict[str, object]],
    tmp_path: Path,
) -> None:
    """A bibkey already in the corpus is NOT flagged by the code-vs-corpus path."""
    src_dir = tmp_path / "src"
    src_dir.mkdir()
    (src_dir / "main.cpp").write_text(
        "// @cite Springborn2008\nvoid foo() {}\n",
        encoding="utf-8",
    )
    monkeypatch.setattr(
        "codex.synthesis._retrieve_chunks",
        lambda queries, top_k: [dict(c) for c in fixture_chunks],
    )
    leads = find_gaps(lib_path=str(src_dir), llm=StubLLM(""))
    # Springborn2008 IS in the corpus → not a gap
    assert not any("Springborn2008" in lead.title for lead in leads)


def test_find_gaps_missing_lib_path_ok(
    monkeypatch: pytest.MonkeyPatch,
    mock_paper_titles: None,
    mock_settings: Path,
    fixture_chunks: list[dict[str, object]],
) -> None:
    """Without lib_path the code-vs-corpus path is skipped (no crash)."""
    monkeypatch.setattr(
        "codex.synthesis._retrieve_chunks",
        lambda queries, top_k: [dict(c) for c in fixture_chunks],
    )
    leads = find_gaps(lib_path=None, llm=StubLLM(""))
    # No crash; result list may be empty depending on coverage map.
    assert isinstance(leads, list)


def test_find_gaps_coverage_map_low_coverage_triggers_llm(
    monkeypatch: pytest.MonkeyPatch,
    mock_paper_titles: None,
    mock_settings: Path,
) -> None:
    """A topic covered by only 1 bibkey (< 2) triggers the LLM gap prompt.

    The grounded body must reference Springborn2008 [...] in a content-5-gram
    that exists in the chunk, otherwise the lead is dropped.
    """
    sparse_chunks: list[dict[str, Any]] = [
        {
            "id": 10,
            "paper_id": "springborn-2008",
            "ord": 16,
            "content": (
                "For an ideal tetrahedron with dihedral angles the hyperbolic volume is "
                "V = L(gamma1) + L(gamma2) + L(gamma3). "
                "The volume function V0 is strictly concave on the angle domain."
            ),
            "bibkey": "Springborn2008",
        },
    ]
    monkeypatch.setattr(
        "codex.synthesis._retrieve_chunks",
        lambda queries, top_k: [dict(c) for c in sparse_chunks],
    )
    grounded_body = (
        "Only Springborn2008 covers the volume formula at depth, while comparison "
        "papers are missing.\n"
        "For an ideal tetrahedron with dihedral angles the hyperbolic volume is "
        "V = L(gamma1) + L(gamma2) + L(gamma3). [Springborn2008 #chunk 16]\n"
    )
    # Coverage gaps are opt-in (audit R-8): pass the topic explicitly.
    leads = find_gaps(llm=StubLLM(grounded_body), topics=["hyperbolic volume formula"])
    assert any(lead.kind == "gap" for lead in leads)


def test_find_gaps_no_coverage_gaps_without_explicit_topics(
    monkeypatch: pytest.MonkeyPatch,
    mock_paper_titles: None,
    mock_settings: Path,
) -> None:
    """Without explicit topics, paper titles do NOT auto-generate coverage gaps (R-8)."""
    sparse_chunks: list[dict[str, Any]] = [
        {
            "id": 10,
            "paper_id": "springborn-2008",
            "ord": 16,
            "content": "the hyperbolic volume is V = L(gamma1) + L(gamma2) + L(gamma3)",
            "bibkey": "Springborn2008",
        },
    ]
    monkeypatch.setattr(
        "codex.synthesis._retrieve_chunks",
        lambda queries, top_k: [dict(c) for c in sparse_chunks],
    )
    # No lib_path, no topics → the coverage map must not run despite sparse coverage.
    leads = find_gaps(llm=StubLLM("a gap. [Springborn2008 #chunk 16]"))
    assert leads == []


def test_find_gaps_explicit_topics_override_default(
    monkeypatch: pytest.MonkeyPatch,
    mock_paper_titles: None,
    mock_settings: Path,
) -> None:
    """Passing topics= explicitly overrides the default (paper titles)."""
    captured_queries: list[list[str]] = []

    def fake_retrieve(queries: list[str], top_k: int) -> list[dict[str, Any]]:
        captured_queries.append(queries)
        return []  # forces direct-gap-no-chunks path

    monkeypatch.setattr("codex.synthesis._retrieve_chunks", fake_retrieve)
    find_gaps(llm=StubLLM(""), topics=["custom topic A", "custom topic B"])
    # Both custom topics should have been probed
    flat = [q for qs in captured_queries for q in qs]
    assert "custom topic A" in flat
    assert "custom topic B" in flat