实现Agent对话，合格自动提交，不合格补充材料的能力

tests/test_extractor.py

@@ -9,6 +9,9 @@ from __future__ import annotations
 from pathlib import Path
 from typing import Any
 
+import pytest
+
+from src import exceptions
 from src.doc.extractor import extract_invoices
 
 # 字段键名（与源码中的字符串字面量保持一致）
@@ -87,12 +90,13 @@ class TestExtractInvoices:
         pdf.touch()
 
         monkeypatch.setattr("src.doc.extractor._find_all_files", lambda d: [pdf])
-        monkeypatch.setattr("src.doc.extractor._extract_document", lambda p, c: None)
+        monkeypatch.setattr("src.doc.extractor._extract_document", lambda p, c, s: (None, "parse error"))
 
-        records, apps, groups = extract_invoices(str(tmp_path))
-        assert records == []
-        assert apps == []
-        assert groups == {"travel": [], "general": [], "application": []}
+        with pytest.raises(exceptions.ExtractionError) as exc_info:
+            extract_invoices(str(tmp_path))
+
+        assert "broken.pdf" in exc_info.value.failed_files
+        assert exc_info.value.details["broken.pdf"] == "parse error"
 
     def test_normal_flow_general_invoices(self, tmp_path: Path, monkeypatch):
         pdf1 = tmp_path / "inv1.pdf"
@@ -107,10 +111,10 @@ class TestExtractInvoices:
 
         call_index = [0]
 
-        def fake_extract(path, cache_dir):
+        def fake_extract(path, cache_dir, source_dir):
             idx = call_index[0]
             call_index[0] += 1
-            return inv1 if idx == 0 else inv2
+            return (inv1, None) if idx == 0 else (inv2, None)
 
         monkeypatch.setattr("src.doc.extractor._extract_document", fake_extract)
 
@@ -156,10 +160,10 @@ class TestExtractInvoices:
         invoices_list = [inv_train, inv_hotel, inv_general]
         call_index = [0]
 
-        def fake_extract(path, cache_dir):
+        def fake_extract(path, cache_dir, source_dir):
             idx = call_index[0]
             call_index[0] += 1
-            return invoices_list[idx]
+            return (invoices_list[idx], None)
 
         monkeypatch.setattr("src.doc.extractor._extract_document", fake_extract)
 
@@ -224,10 +228,10 @@ class TestExtractInvoices:
         results = [inv, app]
         call_index = [0]
 
-        def fake_extract(path, cache_dir):
+        def fake_extract(path, cache_dir, source_dir):
             idx = call_index[0]
             call_index[0] += 1
-            return results[idx]
+            return (results[idx], None)
 
         monkeypatch.setattr("src.doc.extractor._extract_document", fake_extract)
 
@@ -269,10 +273,10 @@ class TestExtractInvoices:
         results = [inv, card]
         call_index = [0]
 
-        def fake_extract(path, cache_dir):
+        def fake_extract(path, cache_dir, source_dir):
             idx = call_index[0]
             call_index[0] += 1
-            return results[idx]
+            return (results[idx], None)
 
         monkeypatch.setattr("src.doc.extractor._extract_document", fake_extract)
 
@@ -312,10 +316,10 @@ class TestExtractInvoices:
         results = [inv, None]
         call_index = [0]
 
-        def fake_extract(path, cache_dir):
+        def fake_extract(path, cache_dir, source_dir):
             idx = call_index[0]
             call_index[0] += 1
-            return results[idx]
+            return (results[idx], "parse error") if results[idx] is None else (results[idx], None)
 
         monkeypatch.setattr("src.doc.extractor._extract_document", fake_extract)