test(03-01): add ASRInput and ASROutput schemas

- Add ASRInput schema with video_path and content_type fields
- Add ASROutput schema with tool/has_subtitle/output_files/segments/text/duration_seconds/speakers
- Create test_processors directory with conftest fixtures
- Add comprehensive schema tests (8 test cases)

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

kb_pipeline/schemas.py

@@ -6,7 +6,7 @@ StepStatus、StepRecord、WorkflowState 和 StepDefinition。
 """
 
 from pydantic import BaseModel, Field
-from typing import Optional, Dict, Literal, Any
+from typing import Optional, Dict, Literal, Any, List
 from datetime import datetime
 from enum import Enum
 
@@ -185,3 +185,51 @@ class StepDefinition(BaseModel):
     input_schema: type[StepInput] = Field(..., description="输入 Schema 类型")
     output_schema: type[StepOutput] = Field(..., description="输出 Schema 类型")
     dependencies: list[str] = Field(default_factory=list, description="依赖的步骤列表")
+
+
+# =============================================================================
+# ASR Schemas (Phase 3)
+# =============================================================================
+
+class ASRInput(StepInput):
+    """ASR 步骤输入
+
+    继承 StepInput 的基础字段，添加视频路径和内容类型。
+
+    Attributes:
+        video_path: 视频文件路径
+        content_type: 内容类型，默认为 'video'
+    """
+    video_path: str = Field(..., description="视频文件路径")
+    content_type: str = Field(default="video", description="内容类型")
+
+
+class ASROutput(StepOutput):
+    """ASR 步骤输出
+
+    继承 StepOutput 的基础字段，添加 ASR 特定字段。
+
+    Attributes:
+        tool: 使用的工具 (subtitle, whisper, whisper-diarization)
+        has_subtitle: 是否有官方字幕
+        output_files: 输出文件路径字典 {txt, srt, json}
+        segments: 带时间戳的分段列表
+        text: 完整文本
+        duration_seconds: 音频时长
+        speakers: 说话者列表（仅说话者分离时有值）
+    """
+    tool: Literal["subtitle", "whisper", "whisper-diarization"] = Field(
+        ..., description="使用的工具"
+    )
+    has_subtitle: bool = Field(..., description="是否有官方字幕")
+    output_files: Dict[str, str] = Field(
+        default_factory=dict, description="输出文件路径 {txt, srt, json}"
+    )
+    segments: List[Dict[str, Any]] = Field(
+        default_factory=list, description="带时间戳的分段列表"
+    )
+    text: str = Field(default="", description="完整文本")
+    duration_seconds: float = Field(default=0.0, description="音频时长")
+    speakers: Optional[List[str]] = Field(
+        None, description="说话者列表（仅说话者分离时有值）"
+    )