"""Tests for scripts/vram_detect.py."""

from pathlib import Path

import pytest

import scripts.vram_detect as vram


def test_lookup_model_context() -> None:
    assert vram._lookup_model_context("gpt-4o") == 128_000
    assert vram._lookup_model_context("claude-3-5-sonnet") == 200_000
    assert vram._lookup_model_context("unknown-model") == 0


def test_parse_token_value() -> None:
    assert vram._parse_token_value("128k") == 128_000
    assert vram._parse_token_value("128K") == 128_000
    assert vram._parse_token_value("128000") == 128_000
    assert vram._parse_token_value("nonsense") is None


def test_extract_value() -> None:
    assert vram._extract_value("- **Model**: gpt-4o") == "gpt-4o"
    assert vram._extract_value("model = gpt-4o  # comment") == "gpt-4o"
    assert vram._extract_value("- **Model**: auto") == "auto"


def test_parse_config_model(tmp_path: Path) -> None:
    config = tmp_path / "config.md"
    config.write_text(
        "## VRAM Configuration\n"
        "- **Auto-detect**: Yes\n"
        "- **Target context**: 16k tokens\n"
        "- **Headroom**: 25%\n"
        "\n"
        "## Model Configuration\n"
        "- **Model**: gpt-4o\n"
        "- **Override context window**: 128k\n"
    )
    model, override = vram._parse_config_model(config)
    assert model == "gpt-4o"
    assert override == 128_000


def test_parse_config_model_skips_code_blocks(tmp_path: Path) -> None:
    """Example code blocks should not be parsed as live config."""
    config = tmp_path / "config.md"
    config.write_text(
        "## VRAM Configuration\n"
        "- **Headroom**: 25%\n"
        "```\n"
        "- **Headroom**: 99%\n"
        "```\n"
    )
    parsed = vram.parse_vram_config(config)
    assert parsed["headroom_pct"] == 25


def test_parse_vram_config_manual(tmp_path: Path) -> None:
    config = tmp_path / "config.md"
    config.write_text(
        "## VRAM Configuration\n"
        "- **Auto-detect**: No\n"
        "- **Target context**: 8k\n"
        "- **Headroom**: 30%\n"
        "- **Max peak context per sub-task**: 5.6k\n"
    )
    parsed = vram.parse_vram_config(config)
    assert parsed["auto_detect"] is False
    assert parsed["target_context_kb"] == 8000
    assert parsed["headroom_pct"] == 30
    assert parsed["max_peak_kb"] == 5600


def test_recommend_context_api_model() -> None:
    config = {"auto_detect": True, "headroom_pct": 25, "target_context_kb": 0, "max_peak_kb": 0}
    _, recommended_kb, max_peak_kb = vram.recommend_context(
        gpu_vram_gb=0,
        ram_gb=16,
        model_context_kb=128_000,
        overhead_tokens=4000,
        config=config,
    )
    assert recommended_kb > 0
    assert max_peak_kb > 0
    assert recommended_kb <= 128_000 * 0.75  # after headroom


def test_recommend_context_manual_mode() -> None:
    config = {"auto_detect": False, "headroom_pct": 30, "target_context_kb": 8000, "max_peak_kb": 0}
    headroom, recommended_kb, max_peak_kb = vram.recommend_context(
        gpu_vram_gb=0,
        ram_gb=16,
        model_context_kb=0,
        overhead_tokens=0,
        config=config,
    )
    assert headroom == 30
    assert recommended_kb == 8000
    assert max_peak_kb == 5600


def test_extract_model_from_file_respects_10kb_limit(tmp_path: Path) -> None:
    """Only the first 10KB of an API config file is scanned."""
    env_file = tmp_path / ".env"
    # Put the model name far beyond 10KB.
    env_file.write_text("x" * 11_000 + "\nMODEL=far-away-model\n")
    model = vram._extract_model_from_file(env_file)
    assert model is None