实现Agent对话，合格自动提交，不合格补充材料的能力

2026-06-14 12:56:33 +08:00
parent ef9e1d771b
commit 01d4686ceb
68 changed files with 8914 additions and 1908 deletions
@@ -5,6 +5,18 @@

 对外接口:
    extract_invoices(directory) -> tuple[list[dict], list[dict], dict]
+
+错误传播规则:
+    - 单个文件提取失败: 记录日志 + SSE error 事件，继续处理下一个文件
+    - 全部文件提取失败:  raise ExtractionError，携带失败文件列表和原始错误
+    - 缓存读取失败: 静默降级，尝试重新提取
+
+SSE 文件进度事件:
+    在 source_dir 下写入 file_events.log，每行一个 JSON 对象：
+    - {"type": "file_progress", "file": "...", "status": "processing"}
+    - {"type": "file_progress", "file": "...", "status": "done", "summary": {...}}
+    - {"type": "file_progress", "file": "...", "status": "cached"}
+    - {"type": "file_progress", "file": "...", "status": "error", "error": "..."}
 """

 import json
@@ -12,35 +24,37 @@ from pathlib import Path
 from typing import Any

 from .. import get_logger
+from ..exceptions import ExtractionError
+from .invoice import CACHE_DIR_NAME, classify_invoice_batch
 from .llm_extractor import extract_document
 from .matcher import match_invoices_to_cards

 log = get_logger("extractor")

+# SSE 文件进度事件日志文件名
+FILE_EVENTS_LOG = "file_events.log"

-def _classify_invoice_batch(
-    invoices: list[dict[str, str]],
-) -> dict[str, list[dict[str, str]]]:
-    """按发票类型分组"""
-    travel: list[dict[str, str]] = []
-    general: list[dict[str, str]] = []
-    application: list[dict[str, str]] = []
-    for inv in invoices:
-        inv_type = inv.get("invoice_type", "general")
-        if inv_type == "application":
-            application.append(inv)
-        elif inv_type in ("train", "hotel"):
-            travel.append(inv)
-        else:
-            general.append(inv)
-    return {"travel": travel, "general": general, "application": application}
+# 支持的文件扩展名
+SUPPORTED_EXTENSIONS = {".pdf", ".png", ".jpg", ".jpeg", ".bmp", ".webp"}


-# JSON 缓存目录（相对于源文件目录）
-CACHE_DIR_NAME = ".invoice_cache"
+def _emit_file_event(source_dir: Path, file_name: str, status: str, **kwargs: Any) -> None:
+    """向 file_events.log 追加一行 JSON 事件（线程安全，失败时静默忽略）"""
+    event = {
+        "type": "file_progress",
+        "file": file_name,
+        "status": status,
+        **kwargs,
+    }
+    try:
+        event_path = source_dir / FILE_EVENTS_LOG
+        with open(event_path, "a", encoding="utf-8") as f:
+            f.write(json.dumps(event, ensure_ascii=False) + "\n")
+    except Exception:
+        pass
+

 # 支持的文件扩展名
-SUPPORTED_EXTENSIONS = {".pdf", ".jpg", ".jpeg", ".png", ".webp", ".bmp"}


 def _get_cache_dir(source_dir: Path) -> Path:
@@ -87,7 +101,59 @@ def _load_from_cache(json_path: Path, expected_extension: str | None = None) ->
        return None


-def _extract_document(file_path: Path, cache_dir: Path) -> dict[str, str] | None:
+def _build_summary(data: dict[str, Any]) -> dict[str, str]:
+    """从提取结果构建前端展示摘要（人类可读格式）。
+
+    返回所有非内部字段（排除 _source_file 等下划线前缀字段），
+    并将 invoice_type 转换为中文标签。列表/字典类型的值会展开为可读文本。
+    """
+    invoice_type_map = {
+        "train": "高铁票",
+        "hotel": "酒店住宿",
+        "general": "普通发票",
+        "payment": "支付记录",
+        "application": "出差申请单",
+    }
+
+    summary = {}
+    for key, value in data.items():
+        # 跳过内部字段
+        if key.startswith("_"):
+            continue
+        # 跳过空值
+        if value is None or value == "":
+            continue
+        # invoice_type 转为中文标签
+        if key == "invoice_type":
+            summary["invoice_type_label"] = invoice_type_map.get(str(value), str(value))
+        elif isinstance(value, list):
+            # 列表展开为多行可读文本
+            if len(value) == 0:
+                continue
+            parts = []
+            for item in value:
+                if isinstance(item, dict):
+                    # 字典项用 "key: value" 格式拼接
+                    pair_parts = [f"{k}: {v}" for k, v in item.items()]
+                    parts.append(" | ".join(pair_parts))
+                else:
+                    parts.append(str(item))
+            summary[key] = "\n".join(parts)
+        elif isinstance(value, dict):
+            # 字典展开为 "key: value" 格式
+            pair_parts = [f"{k}: {v}" for k, v in value.items()]
+            summary[key] = " | ".join(pair_parts)
+        else:
+            summary[key] = str(value)
+
+    return summary
+
+
+def _extract_document(
+    file_path: Path,
+    cache_dir: Path,
+    source_dir: Path,
+) -> tuple[dict[str, str] | None, str | None]:
    """提取单个文件的结构化信息，优先使用缓存。

    根据 LLM 返回的「invoice_type」字段自动分类：
@@ -99,28 +165,43 @@ def _extract_document(file_path: Path, cache_dir: Path) -> dict[str, str] | None
    Args:
        file_path: 文件路径（PDF 或图片）。
        cache_dir: JSON 缓存目录。
+        source_dir: 源目录（用于写入 SSE 进度事件）。

    Returns:
-        提取结果字典，失败时返回 None。
+        (提取结果字典或 None, 错误信息或 None)。
    """
+    file_name = file_path.name
+
    json_path = _get_json_path(file_path, cache_dir)
    cached = _load_from_cache(json_path, expected_extension=file_path.suffix.lower())
    if cached:
-        cached["_source_file"] = file_path.name
-        log.info(f"使用缓存: {file_path.name}")
-        return cached
+        cached["_source_file"] = file_name
+        log.info(f"使用缓存: {file_name}")
+        _emit_file_event(source_dir, file_name, "cached")
+        return cached, None

-    log.info(f"使用多模态提取: {file_path.name}")
+    # 发送处理中事件
+    _emit_file_event(source_dir, file_name, "processing")
+
+    log.info(f"使用多模态提取: {file_name}")
    try:
        result = extract_document(file_path)
        if result:
-            result["_source_file"] = file_path.name
+            result["_source_file"] = file_name
            _save_to_cache(file_path, result, cache_dir)
-            return result
-    except Exception as e:
-        log.warning(f"多模态提取失败: {file_path.name} ({e})")

-    return None
+            # 发送完成事件（含摘要）
+            summary = _build_summary(result)
+            _emit_file_event(source_dir, file_name, "done", summary=summary)
+
+            return result, None
+    except Exception as e:
+        err_msg = str(e)
+        log.warning(f"多模态提取失败: {file_name} ({err_msg})")
+        _emit_file_event(source_dir, file_name, "error", error=err_msg)
+        return None, err_msg
+
+    return None, None


 def _find_all_files(directory: str) -> list[Path]:
@@ -181,10 +262,19 @@ def extract_invoices(
            - applications: 出差事前申请单列表（单独存储，不参与支付匹配）
            - groups: 按文档类型分组的字典
                {'travel': [差旅发票], 'general': [普通发票], 'application': [出差事前申请单]}
+
+    Raises:
+        ExtractionError: 当所有文件提取均失败时抛出，携带失败文件列表和原始错误。
    """
    source_dir = Path(directory)
    cache_dir = _get_cache_dir(source_dir)

+    # 清空上次的文件进度事件
+    try:
+        (source_dir / FILE_EVENTS_LOG).unlink(missing_ok=True)
+    except Exception:
+        pass
+
    all_files = _find_all_files(directory)
    if not all_files:
        log.warning("未找到支持的文件")
@@ -195,11 +285,15 @@ def extract_invoices(
    all_invoices = []
    all_cards = []
    applications = []
+    # 记录失败文件及其错误信息
+    failed_files: list[tuple[str, str]] = []

    for file_path in all_files:
-        result = _extract_document(file_path, cache_dir)
+        result, err = _extract_document(file_path, cache_dir, source_dir)

        if not result:
+            if err:
+                failed_files.append((file_path.name, err))
            log.warning(f"未能解析: {file_path.name}")
            continue

@@ -217,6 +311,16 @@ def extract_invoices(
        else:
            log.warning(f"无法分类: {file_path.name} (invoice_type={inv_type})")

+    # 全部文件提取失败时抛出异常，携带原始错误信息
+    if failed_files and not all_invoices and not all_cards and not applications:
+        failed_names = [name for name, _ in failed_files]
+        error_details = {name: err for name, err in failed_files}
+        raise ExtractionError(
+            f"所有 {len(all_files)} 个文件提取均失败",
+            failed_files=failed_names,
+            details=error_details,
+        )
+
    log.info(f"分类结果: 发票 {len(all_invoices)} 张, 支付记录 {len(all_cards)} 条, 申请单 {len(applications)} 份")

    if not all_invoices:
@@ -231,7 +335,7 @@ def extract_invoices(
        all_documents.extend(record.get("_matched_invoices", []))
    all_documents.extend(applications)

-    groups = _classify_invoice_batch(all_documents)
+    groups = classify_invoice_batch(all_documents)
    log.info(
        f"文档分类: 差旅发票 {len(groups['travel'])} 张, "
        f"普通发票 {len(groups['general'])} 张, "