#!/usr/bin/env python3
"""Tests for session_pair_harvester."""

import json
import sys
import os
import tempfile

sys.path.insert(0, os.path.dirname(__file__))
from session_pair_harvester import extract_pairs_from_session, deduplicate_pairs, compute_hash


def test_basic_extraction():
    session = {
        "id": "test_001",
        "model": "test-model",
        "conversations": [
            {"from": "system", "value": "You are helpful."},
            {"from": "human", "value": "What is Python?"},
            {"from": "gpt", "value": "Python is a high-level programming language known for its readability and versatility. It supports multiple paradigms including procedural, object-oriented, and functional programming. Python is widely used in web development, data science, machine learning, and automation."},
        ]
    }
    pairs = extract_pairs_from_session(session, min_ratio=1.5, min_response_words=10)
    assert len(pairs) == 1
    assert pairs[0]["terse"] == "What is Python?"
    assert "programming language" in pairs[0]["rich"]
    assert pairs[0]["source"] == "test_001"
    print("PASS: test_basic_extraction")


def test_filters_short_responses():
    session = {
        "id": "test_002",
        "model": "test",
        "conversations": [
            {"from": "human", "value": "Hi"},
            {"from": "gpt", "value": "Hello!"},
        ]
    }
    pairs = extract_pairs_from_session(session, min_ratio=1.5, min_response_words=20)
    assert len(pairs) == 0
    print("PASS: test_filters_short_responses")


def test_skips_tool_results():
    session = {
        "id": "test_003",
        "model": "test",
        "conversations": [
            {"from": "human", "value": '{"output": "file content", "exit_code": 0}'},
            {"from": "gpt", "value": "The file was read successfully. Now let me analyze the content and provide a detailed summary of what was found in the file system."},
        ]
    }
    pairs = extract_pairs_from_session(session, min_ratio=1.5, min_response_words=10)
    assert len(pairs) == 0
    print("PASS: test_skips_tool_results")


def test_deduplication():
    pairs = [
        {"terse": "What is X?", "rich": "X is Y.", "source": "s1", "model": "m"},
        {"terse": "What is X?", "rich": "X is Y.", "source": "s2", "model": "m"},
        {"terse": "What is Z?", "rich": "Z is W.", "source": "s1", "model": "m"},
    ]
    unique = deduplicate_pairs(pairs)
    assert len(unique) == 2
    print("PASS: test_deduplication")


def test_ratio_filter():
    session = {
        "id": "test_005",
        "model": "test",
        "conversations": [
            {"from": "human", "value": "Explain quantum computing in detail with examples and applications"},
            {"from": "gpt", "value": "OK."},
        ]
    }
    pairs = extract_pairs_from_session(session, min_ratio=1.5, min_response_words=10)
    assert len(pairs) == 0  # response too short relative to prompt
    print("PASS: test_ratio_filter")


if __name__ == "__main__":
    test_basic_extraction()
    test_filters_short_responses()
    test_skips_tool_results()
    test_deduplication()
    test_ratio_filter()
    print("\nAll tests passed.")