test: 修复端到端管道运行器和 Layer B IndexError - Closes #14

- run_pipeline.py: 修复 subprocess env 传递、parsed_path 检测、Unicode 编码
- test_main_health.py: 修复 _is_functional_section 空章节名 IndexError
- 端到端测试管道: doc_parser → ir_generation(4 steps) → acceptance tests
- 测试发现问题汇总至 dev issue #15

scripts/run_pipeline.py

@@ -42,11 +42,14 @@ def run_doc_parser(docx_path: str, output_dir: str) -> str | None:
 
     print(f"[1/3] Parsing document: {docx_path}")
     result = parse_document(docx_path, output_dir, dry_run=False)
-    parsed_path = result.get("output")
-    if parsed_path and os.path.isfile(parsed_path):
+    # parse_document returns {source, sections, image_sources, image_analysis}
+    # Output is saved as <basename>_parsed.json in output_dir
+    basename = os.path.splitext(os.path.basename(docx_path))[0]
+    parsed_path = os.path.join(output_dir, f"{basename}_parsed.json")
+    if os.path.isfile(parsed_path):
         print(f"  → {parsed_path}")
         return parsed_path
-    print("  ✗ doc_parser failed to produce output", file=sys.stderr)
+    print(f"  [FAIL] doc_parser output not found: {parsed_path}", file=sys.stderr)
     return None
 
 
@@ -55,10 +58,11 @@ def run_doc_parser(docx_path: str, output_dir: str) -> str | None:
 
 def run_ir_pipeline(parsed_path: str) -> str | None:
     """Run the ir_generation steps. Returns path to ir_final.json or None."""
-    config.set_input_file(parsed_path)
     os.makedirs(config.PROJECT_OUTPUT, exist_ok=True)
     os.makedirs(config.IR_OUTPUT, exist_ok=True)
     os.makedirs(config.FINAL_OUTPUT, exist_ok=True)
+    env = os.environ.copy()
+    env["IR_INPUT_JSON"] = parsed_path
 
     steps = [
         ("step1_semantic_index.py", "Semantic Index"),
@@ -72,7 +76,7 @@ def run_ir_pipeline(parsed_path: str) -> str | None:
     for script, label in steps:
         script_path = PROJECT_ROOT / "skills" / "ir_generation_skill" / script
         if not script_path.exists():
-            print(f"  ✗ Missing: {script}", file=sys.stderr)
+            print(f"  [FAIL] Missing: {script}", file=sys.stderr)
             continue
 
         print(f"  Running {script} ({label})...")
@@ -80,28 +84,29 @@ def run_ir_pipeline(parsed_path: str) -> str | None:
             [sys.executable, str(script_path)],
             cwd=str(PROJECT_ROOT),
             capture_output=True, text=True,
+            env=env,
         )
         if result.returncode != 0:
-            print(f"  ✗ {script} failed (exit {result.returncode})", file=sys.stderr)
+            print(f"  [FAIL] {script} failed (exit {result.returncode})", file=sys.stderr)
             print(result.stderr[-500:], file=sys.stderr)
         else:
             # Print last line of stdout for brief progress
             lines = result.stdout.strip().split("\n")
             last = lines[-1] if lines else "done"
-            print(f"  ✓ {label}: {last[:120]}")
+            print(f"  [OK] {label}: {last[:120]}")
 
     if os.path.isfile(config.IR_FINAL_JSON):
         print(f"  → {config.IR_FINAL_JSON}")
         return config.IR_FINAL_JSON
 
-    print("  ✗ IR generation did not produce ir_final.json", file=sys.stderr)
+    print("  [FAIL] IR generation did not produce ir_final.json", file=sys.stderr)
     return None
 
 
 # ── Stage 3: Acceptance Tests ────────────────────────────────────────────────
 
 
-def run_acceptance_tests() -> int:
+def run_acceptance_tests(parsed_json_path: str) -> int:
     """Run QE acceptance tests. Returns pytest exit code."""
     print("[3/3] Running QE acceptance tests...")
 
@@ -111,7 +116,7 @@ def run_acceptance_tests() -> int:
             sys.executable, "-m", "pytest", str(test_dir),
             "-v", "--run-acceptance",
             "--ir-path", config.IR_FINAL_JSON,
-            "--parsed-path", config.INPUT_JSON,
+            "--parsed-path", parsed_json_path,
             "--tb=short",
         ],
         cwd=str(PROJECT_ROOT),
@@ -141,7 +146,7 @@ def main():
         out_dir = args.output_dir or str(PROJECT_ROOT / "output")
         parsed_path = run_doc_parser(docx, out_dir)
         if not parsed_path:
-            print("\n✗ Pipeline blocked at Stage 1 (doc_parser)", file=sys.stderr)
+            print("\n[FAIL] Pipeline blocked at Stage 1 (doc_parser)", file=sys.stderr)
             # Create tracking issue for dev-agent
             _maybe_create_blocking_issue("doc_parser", f"Input: {docx}")
             sys.exit(1)
@@ -157,15 +162,15 @@ def main():
     # Stage 2: IR generation
     ir_path = run_ir_pipeline(parsed_path)
     if not ir_path:
-        print("\n✗ Pipeline blocked at Stage 2 (ir_generation)", file=sys.stderr)
+        print("\n[FAIL] Pipeline blocked at Stage 2 (ir_generation)", file=sys.stderr)
         _maybe_create_blocking_issue("ir_generation", f"Parsed: {parsed_path}")
         sys.exit(1)
 
-    print(f"\n✓ Pipeline complete: {ir_path}")
+    print(f"\n[OK] Pipeline complete: {ir_path}")
 
     # Stage 3: Acceptance tests
     if args.test:
-        exit_code = run_acceptance_tests()
+        exit_code = run_acceptance_tests(parsed_path)
         sys.exit(exit_code)
 
 

tests/acceptance/test_main_health.py

@@ -95,6 +95,8 @@ def _is_functional_section(section_name: str) -> bool:
             return False
     # Documents with only a title (no section number) — check for functional keywords
     sec_num = _section_number(section_name)
+    if not sec_num:
+        return False
     if "." not in sec_num and not sec_num[0].isdigit():
         func_keywords = ["策略", "规则", "功能", "限制", "流程", "配置", "场景",
                          "约束", "条件", "方案", "逻辑", "处理", "机制", "禁止"]