fix: 移除 hardcode 输入文件路径，完善输入验证 - Closes #8

- 移除 _DEFAULT_INPUT 硬编码默认输入文件路径
- INPUT_JSON 仅从 IR_INPUT_JSON 环境变量获取
- load_input_document() 无输入时给出明确错误提示
- 新增 test_no_hardcoded_input_file / test_set_input_file_accepts_none

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

skills/ir_generation_skill/config.py

@@ -4,6 +4,7 @@ Reads API keys from a secrets.yaml file, falling back to environment variables.
 """
 
 import os
+import sys
 import json
 import yaml
 
@@ -23,11 +24,9 @@ PROMPTS_DIR = os.path.join(BASE_DIR, "prompts")
 TESTS_DIR = os.path.join(BASE_DIR, "tests")
 OUTPUT_DIR = IR_OUTPUT  # backward compatibility alias
 
-# Input file (the parsed PRD JSON)
+# Input file (the parsed PRD JSON) — must be set via env var or CLI
-_DEFAULT_INPUT = os.path.join(
+# No hardcoded default to avoid silently processing the wrong document.
-    PROJECT_OUTPUT, "车机娱乐系统禁止功能文档_脱敏 v0.9_v2_updated.json",
+INPUT_JSON = os.environ.get("IR_INPUT_JSON", None)
-)
-INPUT_JSON = os.environ.get("IR_INPUT_JSON", _DEFAULT_INPUT)
 
 
 def set_input_file(path: str) -> None:
@@ -125,8 +124,26 @@ def llm_client():
 
 
 def load_input_document(path: str | None = None) -> dict:
-    """Load the parsed PRD JSON document."""
+    """Load the parsed PRD JSON document.
+
+    Args:
+        path: Explicit file path. If None, reads from IR_INPUT_JSON env var.
+
+    Raises:
+        FileNotFoundError: If no path is configured.
+        SystemExit: If the configured path does not exist.
+    """
     path = path or INPUT_JSON
+    if not path:
+        print("错误: 未指定输入文件。请通过以下任一方式指定:", file=sys.stderr)
+        print("  1. 设置环境变量: IR_INPUT_JSON=<path>", file=sys.stderr)
+        print("  2. 通过 main.py: python main.py --input <path>", file=sys.stderr)
+        print("  3. 通过 step 脚本: python step1_semantic_index.py --input <path>", file=sys.stderr)
+        print("  4. 程序调用: config.set_input_file(<path>)", file=sys.stderr)
+        sys.exit(1)
+    if not os.path.isfile(path):
+        print(f"错误: 输入文件不存在: {path}", file=sys.stderr)
+        sys.exit(1)
     with open(path, "r", encoding="utf-8") as f:
         return json.load(f)
 

tests/test_config.py

@@ -19,6 +19,33 @@ def test_set_input_file():
         config.set_input_file(original)
 
 
+def test_no_hardcoded_input_file():
+    """INPUT_JSON should not have a hardcoded default — comes from env or None."""
+    # When IR_INPUT_JSON env is not set, INPUT_JSON should be None
+    env_val = os.environ.pop("IR_INPUT_JSON", None)
+    try:
+        import importlib
+        importlib.reload(config)
+        # After reload without env var, INPUT_JSON should be None
+        assert config.INPUT_JSON is None, \
+            f"INPUT_JSON should be None when env not set, got: {config.INPUT_JSON}"
+    finally:
+        if env_val is not None:
+            os.environ["IR_INPUT_JSON"] = env_val
+        importlib.reload(config)
+
+
+def test_set_input_file_accepts_none():
+    """set_input_file(None) should work for resetting."""
+    original = config.INPUT_JSON
+    try:
+        config.set_input_file("/tmp/test.json")
+        config.set_input_file(None)
+        assert config.INPUT_JSON is None
+    finally:
+        config.set_input_file(original)
+
+
 def test_config_constants_exist():
     """Verify all expected path constants are defined."""
     assert config.BASE_DIR