feat: 向量记忆 RAG、工具市场、SSE 流式响应、前端集成与测试覆盖

- 新增 embedding_service（语义检索）、knowledge_service（RAG）、text_chunker、document_parser
- 新增 tool_registry（自定义工具注册表）并完善工具市场 API（CRUD + code/http 执行）
- 新增 agent_vector_memory / knowledge_base 模型及对应数据库表
- 实现 SSE 流式响应与 Agent 预算控制
- AgentChat.vue 集成 MainLayout 导航布局
- 完善测试体系：7 个新测试文件共 110 个测试覆盖
- 修复 conftest.py SQLite 内存数据库连接隔离问题

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

backend/tests/test_document_parser.py

@@ -0,0 +1,137 @@
+"""
+文档解析器单元测试
+"""
+from __future__ import annotations
+
+import os
+import tempfile
+import pytest
+
+from app.services.document_parser import parse_document
+
+
+class TestDocumentParser:
+    """文档解析器测试"""
+
+    @pytest.mark.unit
+    def test_parse_txt(self):
+        with tempfile.NamedTemporaryFile(mode="w", suffix=".txt", encoding="utf-8", delete=False) as f:
+            f.write("Hello world\nThis is a test.")
+            tmp_path = f.name
+        try:
+            result = parse_document(tmp_path, "txt")
+            assert "Hello world" in result
+            assert "This is a test" in result
+        finally:
+            os.unlink(tmp_path)
+
+    @pytest.mark.unit
+    def test_parse_txt_utf8_bom(self):
+        """带 BOM 的 UTF-8 文件"""
+        content = "\ufeff你好世界\n测试内容"
+        with tempfile.NamedTemporaryFile(mode="wb", suffix=".txt", delete=False) as f:
+            f.write(content.encode("utf-8-sig"))
+            tmp_path = f.name
+        try:
+            result = parse_document(tmp_path, "txt")
+            assert "你好" in result
+            assert "测试" in result
+        finally:
+            os.unlink(tmp_path)
+
+    @pytest.mark.unit
+    def test_parse_md(self):
+        with tempfile.NamedTemporaryFile(mode="w", suffix=".md", encoding="utf-8", delete=False) as f:
+            f.write("# Title\n\nThis is **bold** text.")
+            tmp_path = f.name
+        try:
+            result = parse_document(tmp_path, "md")
+            assert "Title" in result
+            assert "bold" in result
+        finally:
+            os.unlink(tmp_path)
+
+    @pytest.mark.unit
+    def test_parse_csv(self):
+        with tempfile.NamedTemporaryFile(mode="w", suffix=".csv", encoding="utf-8", delete=False) as f:
+            f.write("name,age,city\nAlice,30,Beijing\nBob,25,Shanghai")
+            tmp_path = f.name
+        try:
+            result = parse_document(tmp_path, "csv")
+            assert "Alice" in result
+            assert "Beijing" in result
+            assert "Bob" in result
+        finally:
+            os.unlink(tmp_path)
+
+    @pytest.mark.unit
+    def test_parse_csv_with_different_delimiter(self):
+        with tempfile.NamedTemporaryFile(mode="w", suffix=".csv", encoding="utf-8", delete=False) as f:
+            f.write("a|b|c\n1|2|3\n4|5|6")
+            tmp_path = f.name
+        try:
+            result = parse_document(tmp_path, "csv")
+            assert "1" in result or "a" in result
+        finally:
+            os.unlink(tmp_path)
+
+    @pytest.mark.unit
+    def test_unsupported_format(self):
+        with tempfile.NamedTemporaryFile(suffix=".xyz", delete=False) as f:
+            tmp_path = f.name
+        try:
+            result = parse_document(tmp_path, "xyz")
+            assert result is None  # 不支持的格式返回 None
+        finally:
+            os.unlink(tmp_path)
+
+    @pytest.mark.unit
+    def test_file_not_found(self):
+        result = parse_document("/nonexistent/file.txt", "txt")
+        assert result is None  # 文件不存在返回 None
+
+    @pytest.mark.unit
+    def test_empty_file(self):
+        with tempfile.NamedTemporaryFile(mode="w", suffix=".txt", encoding="utf-8", delete=False) as f:
+            tmp_path = f.name
+        try:
+            result = parse_document(tmp_path, "txt")
+            assert result is not None
+        finally:
+            os.unlink(tmp_path)
+
+    @pytest.mark.integration
+    def test_parse_docx(self):
+        """需要 python-docx 包"""
+        pytest.importorskip("docx")
+        from docx import Document
+
+        doc = Document()
+        doc.add_paragraph("Hello from docx")
+        doc.add_paragraph("第二段落")
+        with tempfile.NamedTemporaryFile(suffix=".docx", delete=False) as f:
+            doc.save(f.name)
+            tmp_path = f.name
+        try:
+            result = parse_document(tmp_path, "docx")
+            assert "Hello from docx" in result
+            assert "第二段落" in result
+        finally:
+            os.unlink(tmp_path)
+
+    @pytest.mark.integration
+    def test_parse_pdf(self):
+        """需要 PyPDF2 包"""
+        pytest.importorskip("PyPDF2")
+        from PyPDF2 import PdfWriter
+
+        writer = PdfWriter()
+        writer.add_blank_page(72, 72)  # 1 inch page
+        with tempfile.NamedTemporaryFile(suffix=".pdf", delete=False) as f:
+            writer.write(f)
+            tmp_path = f.name
+        try:
+            result = parse_document(tmp_path, "pdf")
+            assert result is not None
+        finally:
+            os.unlink(tmp_path)