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)
 

tests/test_invoice.py

@@ -6,9 +6,7 @@
 from src.doc.invoice import (
     INVOICE_LEVEL_COLUMNS,
     PAYMENT_RECORD_COLUMNS,
-)
-from src.doc.invoice import (
-    _classify_invoice_batch as classify_invoice_batch,
+    classify_invoice_batch,
 )
 
 # 字段键名与发票类型（与源码中的字符串字面量保持一致）

tests/test_llm_extractor.py

@@ -1,7 +1,7 @@
 """LLM 信息提取模块单元测试
 
 覆盖范围：
-- _parse_json_response：纯 JSON、Markdown 包裹、带前缀、解析失败
+- `parse_json_response`：纯 JSON、Markdown 包裹、带前缀、解析失败
 - _image_to_base64：图片转 base64
 - extract_document：成功提取、LLM 失败
 """
@@ -16,8 +16,8 @@ import pytest
 
 from src.doc.llm_extractor import (
     _image_to_base64,
-    _parse_json_response,
     extract_document,
+    parse_json_response,
 )
 
 # 字段键名（与源码中的字符串字面量保持一致）
@@ -28,7 +28,7 @@ K_CARD_NO = "card_no"
 K_CARD_AMOUNT = "card_amount"
 
 # ------------------------------------------------------------------
-# _parse_json_response
+# parse_json_response
 # ------------------------------------------------------------------
 
 
@@ -37,47 +37,47 @@ class TestParseJsonResponse:
 
     def test_pure_json(self):
         raw = json.dumps({K_INVOICE_NUMBER: "123456", K_TOTAL_AMOUNT: "100.00"})
-        result = _parse_json_response(raw)
+        result = parse_json_response(raw)
         assert result[K_INVOICE_NUMBER] == "123456"
         assert result[K_TOTAL_AMOUNT] == "100.00"
 
     def test_markdown_json_block(self):
         raw = f'```json\n{{"{K_INVOICE_NUMBER}": "789"}}\n```'
-        result = _parse_json_response(raw)
+        result = parse_json_response(raw)
         assert result[K_INVOICE_NUMBER] == "789"
 
     def test_markdown_block_without_lang(self):
         raw = '```\n{"key": "value"}\n```'
-        result = _parse_json_response(raw)
+        result = parse_json_response(raw)
         assert result["key"] == "value"
 
     def test_json_prefix(self):
         raw = f'json\n{{"{K_INVOICE_NUMBER}": "001"}}'
-        result = _parse_json_response(raw)
+        result = parse_json_response(raw)
         assert result[K_INVOICE_NUMBER] == "001"
 
     def test_json_prefix_with_whitespace(self):
         raw = '  json  \n{"a": 1}'
-        result = _parse_json_response(raw)
+        result = parse_json_response(raw)
         assert result["a"] == 1
 
     def test_nested_json(self):
         raw = json.dumps({"outer": {"inner": [1, 2, 3]}})
-        result = _parse_json_response(raw)
+        result = parse_json_response(raw)
         assert result["outer"]["inner"] == [1, 2, 3]
 
     def test_whitespace_around_json(self):
         raw = '  \n  {"x": 42}  \n  '
-        result = _parse_json_response(raw)
+        result = parse_json_response(raw)
         assert result["x"] == 42
 
     def test_invalid_json_raises(self):
         with pytest.raises(ValueError):
-            _parse_json_response("not json at all")
+            parse_json_response("not json at all")
 
     def test_empty_string_raises(self):
         with pytest.raises(ValueError):
-            _parse_json_response("")
+            parse_json_response("")
 
 
 # ------------------------------------------------------------------