test(15-00): add test infrastructure placeholders for Phase 15

创建了测试基础设施，为后续计划提供测试框架。

## 创建的文件

1. **tests/test_processors/test_srt.py** - SRTProcessor 配置集成测试占位符
   - TestConfigIntegration 测试类
   - 5 个测试占位符（pytest.skip）

2. **tests/test_backward_compat.py** - 向后兼容性测试
   - TestBackwardCompatibility 测试类
   - 部分测试已实现（来自计划 15-01）
   - 部分测试占位符（pytest.skip）

3. **tests/conftest.py** - 添加共享 fixtures
   - temp_env_vars fixture：临时环境变量管理
   - mock_kbsettings fixture：Mock KBSettings 实例
   - 添加 os 模块导入

## 偏离说明

计划要求所有测试都是占位符（pytest.skip），但实际上：
- test_config.py 已由计划 15-01 实现完整测试
- test_backward_compat.py 有部分实现

原因：计划 15-01 在 15-00 之前执行，导致测试不是占位符。

## 验证

- pytest 发现所有新增测试类和测试函数
- 测试文件结构符合项目规范

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

tests/conftest.py

@@ -1,5 +1,6 @@
 """共享测试 fixtures 和配置"""
 
+import os
 from typing import Optional
 from unittest.mock import Mock
 from pathlib import Path
@@ -182,3 +183,54 @@ def long_subtitle_segments():
             text=f"这是第 {i + 1} 句字幕内容。" * 5
         ))
     return segments
+
+
+# ============================================================================
+# Phase 15 Fixtures: 配置集成测试
+# ============================================================================
+
+@pytest.fixture
+def temp_env_vars(monkeypatch):
+    """临时环境变量 fixture，测试后自动清理"""
+    original_env = {}
+    saved_vars = {}
+
+    def _set_env(env_dict):
+        nonlocal original_env, saved_vars
+        # 保存原始值
+        for key in env_dict.keys():
+            original_env[key] = os.environ.get(key)
+        # 设置新值
+        for key, value in env_dict.items():
+            if value is None:
+                os.environ.pop(key, None)
+            else:
+                os.environ[key] = value
+            saved_vars[key] = value
+
+    yield _set_env
+
+    # 清理：恢复原始环境变量
+    for key, original_value in original_env.items():
+        if original_value is None:
+            os.environ.pop(key, None)
+        else:
+            os.environ[key] = original_value
+
+
+@pytest.fixture
+def mock_kbsettings():
+    """Mock KBSettings fixture，用于隔离测试环境"""
+    from kb_workflow.pipeline.config import KBSettings
+    from kb_workflow.pipeline.config import get_settings
+
+    mock_settings = MagicMock(spec=KBSettings)
+    mock_settings.enable_semantic_segmentation = True
+    mock_settings.base_path = "/tmp/kb"
+    mock_settings.archive_path = "/tmp/archive"
+    mock_settings.hf_token = MagicMock()
+    mock_settings.hf_token.get_secret_value.return_value = ""
+    mock_settings.zhihu_cookie = MagicMock()
+    mock_settings.zhihu_cookie.get_secret_value.return_value = ""
+
+    return mock_settings

tests/test_backward_compat.py

@@ -0,0 +1,179 @@
+"""Backward Compatibility Tests
+
+Tests to ensure that configuration changes don't break existing functionality:
+- Rule-based segmentation (SemanticSegmenter) works unchanged (CONFIG-02)
+- AnalyzeProcessor is not affected by SRTProcessor config changes (CONFIG-03)
+- Existing API calls remain compatible
+"""
+
+import pytest
+from unittest.mock import Mock, patch, MagicMock
+from pathlib import Path
+from kb_workflow.srt.parser import Segment
+from kb_workflow.srt.segmenter import SemanticSegmenter
+
+
+# =============================================================================
+# Test Fixtures
+# =============================================================================
+
+@pytest.fixture
+def sample_segments():
+    """Sample subtitle segments for testing"""
+    return [
+        Segment(1, 0.0, 5.0, "第一句内容"),
+        Segment(2, 5.0, 10.0, "第二句内容"),
+        Segment(3, 10.0, 15.0, "第三句内容"),
+    ]
+
+
+@pytest.fixture
+def long_text_segments():
+    """Segments with long text that triggers length-based splitting"""
+    text = "这是一段很长的文本内容" * 50  # ~500 characters
+    return [
+        Segment(1, 0.0, 5.0, text[:250]),
+        Segment(2, 5.0, 10.0, text[:250]),
+        Segment(3, 10.0, 15.0, text[:250]),
+    ]
+
+
+@pytest.fixture
+def gap_segments():
+    """Segments with time gaps > 3 seconds"""
+    return [
+        Segment(1, 0.0, 5.0, "第一段落内容"),
+        Segment(2, 10.0, 15.0, "第二段落内容"),  # 5 second gap
+        Segment(3, 15.0, 20.0, "继续第二段落"),
+    ]
+
+
+# =============================================================================
+# Task 1: Rule-based Segmentation Backward Compatibility (CONFIG-02)
+# =============================================================================
+
+class TestBackwardCompatibility:
+    """Test backward compatibility for rule-based segmentation (CONFIG-02)"""
+
+    def test_rule_based_segmentation_unchanged(self, sample_segments):
+        """Test 1: enable_semantic_segmentation=False 使用规则分段器"""
+        from kb_workflow.pipeline.processors.srt import SRTProcessor
+        from kb_workflow.srt.semantic_engine import SemanticSegmentationEngine
+
+        # Create SRTProcessor with semantic segmentation disabled
+        processor = SRTProcessor(
+            state_manager=None,
+            enable_semantic_segmentation=False
+        )
+
+        # Verify it uses SemanticSegmenter (rule-based)
+        assert isinstance(processor.segmenter, SemanticSegmenter), \
+            "Should use SemanticSegmenter when enable_semantic_segmentation=False"
+
+        # Verify it does NOT use SemanticSegmentationEngine
+        assert not isinstance(processor.segmenter, SemanticSegmentationEngine), \
+            "Should NOT use SemanticSegmentationEngine when enable_semantic_segmentation=False"
+
+        # Verify segment() returns plain text list (not VideoSegment objects)
+        result = processor.segmenter.segment(sample_segments)
+        assert isinstance(result, list), "segment() should return a list"
+        assert len(result) > 0, "Should have at least one paragraph"
+        assert all(isinstance(para, str) for para in result), \
+            "Rule-based segmenter should return plain text strings, not VideoSegment objects"
+
+    def test_rule_based_no_llm_calls(self, sample_segments):
+        """Test 2: 规则分段不调用 LLM，无网络开销"""
+        from kb_workflow.pipeline.processors.srt import SRTProcessor
+
+        # Mock SimpleAIClient to detect any LLM calls
+        with patch('kb_workflow.deep_analyzer.SimpleAIClient') as mock_client:
+            # Create processor with rule-based segmentation
+            processor = SRTProcessor(
+                state_manager=None,
+                enable_semantic_segmentation=False
+            )
+
+            # Call segment method
+            result = processor.segmenter.segment(sample_segments)
+
+            # Verify SimpleAIClient was NOT called
+            # (rule-based segmentation should not initialize AI client)
+            assert not mock_client.called, \
+                "Rule-based segmentation should NOT call SimpleAIClient"
+
+        # Verify we still get results without LLM
+        assert len(result) > 0, "Should have results without LLM"
+
+    def test_rule_based_thresholds_unchanged(self, gap_segments, long_text_segments):
+        """Test 3: 规则分段的分段逻辑（时间/长度阈值）未改变"""
+        segmenter = SemanticSegmenter(
+            gap_threshold=3.0,  # Phase 12 default
+            max_paragraph_chars=500  # Phase 12 default
+        )
+
+        # Test 1: Time gap threshold (3 seconds)
+        result = segmenter.segment(gap_segments)
+        # Should split into 2 paragraphs due to 5-second gap
+        assert len(result) == 2, \
+            f"Should split into 2 paragraphs due to time gap, got {len(result)}"
+        assert "第一段落内容" in result[0]
+        assert "第二段落内容" in result[1]
+
+        # Test 2: Character length threshold (500 chars)
+        result = segmenter.segment(long_text_segments)
+        # Each segment is ~250 chars, so with 3 segments we should get splits
+        # First segment: 250 chars (no split)
+        # Second segment: 250 + 250 = 500 chars (might split depending on exact count)
+        assert len(result) >= 1, "Should have at least one paragraph"
+        assert all(isinstance(para, str) for para in result), \
+            "All results should be plain text strings"
+
+    @pytest.mark.skipif(True, reason="Not implemented yet - will implement in Task 3")
+    def test_existing_api_compatibility(self):
+        """Test 4: 不传 enable_semantic_segmentation 参数时使用配置默认值"""
+        # This test will be implemented in Task 3
+        pass
+
+    @pytest.mark.skipif(True, reason="Not implemented yet - will implement in Task 3")
+    def test_explicit_false_overrides_config(self):
+        """Test 5: 显式传 False 时覆盖配置，使用规则分段"""
+        # This test will be implemented in Task 3
+        pass
+
+    @pytest.mark.skipif(True, reason="Not implemented yet - will implement in Task 3")
+    def test_migration_path(self):
+        """Test 6: 验证用户可以通过两种方式启用语义分段"""
+        # This test will be implemented in Task 3
+        pass
+
+    @pytest.mark.skipif(True, reason="Not implemented yet - will implement in Task 2")
+    def test_analyze_processor_unaffected(self):
+        """Test 7: AnalyzeProcessor 不受 KBSettings.enable_semantic_segmentation 影响"""
+        # This test will be implemented in Task 2
+        pass
+
+
+# =============================================================================
+# Task 2: AnalyzeProcessor Independence (CONFIG-03)
+# =============================================================================
+
+class TestAnalyzeProcessorIndependence:
+    """Test that AnalyzeProcessor is independent of SRTProcessor configuration"""
+
+    @pytest.mark.skipif(True, reason="Not implemented yet - will implement in Task 2")
+    def test_analyze_processor_unaffected_by_config(self):
+        """Test: AnalyzeProcessor 不受 KBSettings.enable_semantic_segmentation 影响"""
+        # This test will be implemented in Task 2
+        pass
+
+    @pytest.mark.skipif(True, reason="Not implemented yet - will implement in Task 2")
+    def test_analyze_processor_normal_initialization(self):
+        """Test: AnalyzeProcessor 正常初始化和处理"""
+        # This test will be implemented in Task 2
+        pass
+
+    @pytest.mark.skipif(True, reason="Not implemented yet - will implement in Task 2")
+    def test_analyze_processor_output_unchanged(self):
+        """Test: AnalyzeProcessor 输出格式未改变"""
+        # This test will be implemented in Task 2
+        pass

tests/test_processors/test_srt.py

@@ -0,0 +1,35 @@
+"""Tests for SRTProcessor and configuration integration.
+
+Test coverage:
+- Configuration integration (CONFIG-01)
+- Backward compatibility (CONFIG-02)
+- Output format verification (OUTPUT-01, OUTPUT-02, OUTPUT-03)
+"""
+
+import pytest
+from unittest.mock import MagicMock, patch
+from pathlib import Path
+
+
+class TestConfigIntegration:
+    """Tests for SRTProcessor configuration integration (CONFIG-01, CONFIG-02)"""
+
+    def test_srt_processor_reads_from_kbsettings(self):
+        """Test SRTProcessor reads enable_semantic_segmentation from KBSettings"""
+        pytest.skip("等待实现: 验证从 KBSettings 读取配置")
+
+    def test_srt_processor_constructor_overrides_config(self):
+        """Test constructor parameter overrides KBSettings"""
+        pytest.skip("等待实现: 验证构造函数参数优先级")
+
+    def test_config_disabled_uses_rule_based(self):
+        """Test disabled config uses rule-based segmentation (CONFIG-02)"""
+        pytest.skip("等待实现: 验证禁用时使用规则分段")
+
+    def test_output_format_with_semantic_enabled(self):
+        """Test output format with semantic segmentation enabled (OUTPUT-01)"""
+        pytest.skip("等待实现: 验证启用时输出 H2 标题")
+
+    def test_output_format_with_semantic_disabled(self):
+        """Test output format with semantic segmentation disabled (OUTPUT-03)"""
+        pytest.skip("等待实现: 验证禁用时输出\"## 内容\"")