ss-tools/backend/tests/agent/test_title_cleaning.py

# backend/tests/agent/test_title_cleaning.py
# #region Test.Agent.Persistence.CleanTitle [C:2] [TYPE Module] [SEMANTICS test,agent,persistence,title]
# @BRIEF Unit tests for rule-based conversation title cleaning — all edge cases.
# @RELATION BINDS_TO -> [AgentChat.Persistence.CleanTitle]
# @TEST_EDGE: empty_input -> "Новый диалог"
# @TEST_EDGE: whitespace_only -> "Новый диалог"
# @TEST_EDGE: file_markers -> stripped before first marker
# @TEST_EDGE: prefetch_markers -> stripped before first marker
# @TEST_EDGE: hitl_title -> preserved as-is
# @TEST_EDGE: json_input -> "Данные: {...}"
# @TEST_EDGE: url_input -> domain extracted
# @TEST_EDGE: long_text -> truncated at 80 with word boundary
# @TEST_EDGE: code_input -> first line preserved
import pytest
from src.agent._persistence import clean_title


class TestCleanTitle:
    """Rule-based title cleaning — all edge cases from the spec matrix."""

    # ── Empty / whitespace ──
    def test_empty_string(self):
        assert clean_title("") == "Новый диалог"

    def test_whitespace_only(self):
        assert clean_title("   \n  \t  ") == "Новый диалог"

    def test_none_input(self):
        assert clean_title(None) == "Новый диалог"

    # ── Short / normal ──
    def test_short_greeting(self):
        assert clean_title("Привет") == "Привет"

    def test_emoji_only(self):
        assert clean_title("🔥") == "🔥"

    def test_normal_russian(self):
        assert clean_title("Покажи доступные дашборды") == "Покажи доступные дашборды"

    def test_normal_english(self):
        assert clean_title("Show me all dashboards in prod") == "Show me all dashboards in prod"

    # ── File markers ──
    def test_file_marker_stripped(self):
        result = clean_title("Покажи дашборды\n--- Uploaded file content ---\nid,name\n1,A")
        assert result == "Покажи дашборды"

    def test_only_file_marker(self):
        result = clean_title("--- Uploaded file content ---\nid,name\n1,A")
        assert result == "Новый диалог"

    # ── Pre-fetch markers ──
    def test_prefetch_marker_stripped(self):
        result = clean_title("Мигрируй 42\n[PRE-FETCHED DATA]\nAvailable dashboards...")
        assert result == "Мигрируй 42"

    def test_prefetch_end_marker_stripped(self):
        result = clean_title("Поиск\n[/PRE-FETCHED DATA]\nextra")
        assert result == "Поиск"

    # ── HITL titles (preserved) ──
    def test_hitl_confirm_preserved(self):
        assert clean_title("✅ get_health_summary") == "✅ get_health_summary"

    def test_hitl_deny_preserved(self):
        assert clean_title("⏹️ show_capabilities") == "⏹️ show_capabilities"

    # ── JSON / CSV / URL detection ──
    def test_json_input(self):
        result = clean_title('{"id": 1, "name": "Dashboard A"}')
        assert result.startswith("Данные: ")

    def test_csv_input(self):
        result = clean_title("id,name,status\n1,Dashboard A,active")
        # CSV under 80 chars, first line kept as-is
        assert result == "id,name,status"

    def test_url_input(self):
        result = clean_title("https://superset.example.com/dashboard/42")
        # Should extract domain
        assert "superset.example.com" in result

    # ── Sentence cut ──
    def test_cut_at_first_sentence(self):
        result = clean_title(
            "Чтобы проанализировать систему, мне нужно проверить health. "
            "Для начала покажи список дашбордов."
        )
        assert "Чтобы проанализировать систему, мне нужно проверить health." in result
        assert "Для начала" not in result

    def test_cut_at_exclamation(self):
        result = clean_title("Срочно! Проверь статус системы.")
        assert result == "Срочно!"

    def test_cut_at_question(self):
        result = clean_title("Как работает миграция? Нужно подробное описание.")
        assert result == "Как работает миграция?"

    # ── Long text truncation ──
    def test_long_text_truncated(self):
        long_text = "Это очень длинное сообщение про миграцию дашбордов из окружения dev в prod с заменой конфигов и фиксом кросс-фильтров"
        result = clean_title(long_text)
        assert len(result) <= 80
        assert result.endswith("…")

    def test_long_text_no_spaces(self):
        result = clean_title("A" * 200)
        assert len(result) <= 80

    # ── Code detection ──
    def test_code_def(self):
        result = clean_title("def migrate(): pass\n\nMore text here")
        assert result == "def migrate(): pass"

    def test_code_import(self):
        result = clean_title("import os\nimport sys\n\nShow dashboards")
        assert result == "import os"

    # ── Already clean ──
    def test_already_clean_title(self):
        assert clean_title("CSV-файл: Анализ дашбордов") == "CSV-файл: Анализ дашбордов"

    # ── Edge: no dot at end ──
    def test_single_sentence_no_punctuation(self):
        result = clean_title("Проверь статус системы ss-dev")
        assert result == "Проверь статус системы ss-dev"
# #endregion Test.Agent.Persistence.CleanTitle