feat: 支持会话内补传资料并保持绑定

2026-06-04 01:51:48 +08:00
parent 1e18fd2be9
commit 96f710ea13
6 changed files with 278 additions and 53 deletions
--- a/apps/chat/forms.py
+++ b/apps/chat/forms.py
@@ -1,4 +1,7 @@
 from django import forms
+from pathlib import Path
+
+from apps.documents.forms import MultipleFileField, SUPPORTED_EXTENSIONS


 class ChatForm(forms.Form):
@@ -38,3 +41,23 @@ class ChatForm(forms.Form):
    def clean_document_ids(self):
        # View 与 Agent Core 都使用整型文档 ID，统一在表单层完成转换。
        return [int(document_id) for document_id in self.cleaned_data.get("document_ids", [])]
+
+
+class ConversationUploadForm(forms.Form):
+    # 会话右侧上传区只负责继续补传资料，不修改会话绑定关系。
+    files = MultipleFileField(label="补充文件或资料包", required=False)
+    file = forms.FileField(label="兼容单文件上传", required=False)
+
+    def clean(self):
+        cleaned_data = super().clean()
+        files = list(cleaned_data.get("files") or [])
+        file = cleaned_data.get("file")
+        if file:
+            files.append(file)
+        if not files:
+            raise forms.ValidationError("请至少上传一个文件或资料包。")
+        for uploaded_file in files:
+            if Path(uploaded_file.name).suffix.lower() not in SUPPORTED_EXTENSIONS:
+                raise forms.ValidationError("仅支持 .txt、.md、.pdf、.docx、.zip 和 .7z 文件")
+        cleaned_data["uploaded_files"] = files
+        return cleaned_data
--- a/apps/chat/urls.py
+++ b/apps/chat/urls.py
@@ -9,4 +9,5 @@ app_name = "chat"
 urlpatterns = [
    path("", views.index, name="index"),
    path("<str:conversation_id>/", views.detail, name="detail"),
+    path("<str:conversation_id>/upload/", views.upload_documents, name="upload-documents"),
 ]
--- a/apps/chat/views.py
+++ b/apps/chat/views.py
@@ -1,14 +1,17 @@
+from django.contrib import messages
 from django.utils import timezone
 from django.shortcuts import get_object_or_404, redirect, render
 from django.urls import reverse
+from django.views.decorators.http import require_POST

 from agent_core.orchestrator import run_agent
 from agent_core.results import AgentResult
 from apps.audit.services import create_audit_log, create_notification_record
 from apps.documents.models import SubmissionBatch, UploadedDocument
+from apps.documents.services import append_documents_to_batch
 from apps.scenarios.services import get_scenario

-from .forms import ChatForm
+from .forms import ChatForm, ConversationUploadForm
 from .models import Conversation


@@ -37,6 +40,7 @@ def detail(request, conversation_id: str):
    batch = SubmissionBatch.objects.filter(batch_id=conversation.batch_id).first()
    documents = UploadedDocument.objects.filter(batch=batch)
    form = ChatForm(request.POST or None, documents=documents)
+    upload_form = ConversationUploadForm()
    result = None
    audit_log = None
    active_node = None
@@ -97,10 +101,35 @@ def detail(request, conversation_id: str):
            "node_results": conversation.node_results,
            "active_node": active_node,
            "workspace_summary": workspace_summary,
+            "upload_form": upload_form,
        },
    )


+@require_POST
+def upload_documents(request, conversation_id: str):
+    conversation = get_object_or_404(Conversation, conversation_id=conversation_id)
+    batch = get_object_or_404(SubmissionBatch, batch_id=conversation.batch_id)
+    upload_form = ConversationUploadForm(request.POST, request.FILES)
+    if upload_form.is_valid():
+        result = append_documents_to_batch(
+            "document_review",
+            batch,
+            upload_form.cleaned_data["uploaded_files"],
+        )
+        warning_count = len(result["registration_overview_report"]["warnings"])
+        message = "资料已补充到当前资料包。"
+        if warning_count:
+            message += f" 当前有 {warning_count} 条待复核提示。"
+        messages.success(request, message)
+    else:
+        messages.error(
+            request,
+            "补充资料失败：" + " ".join(upload_form.non_field_errors()) if upload_form.non_field_errors() else "补充资料失败。",
+        )
+    return redirect("chat:detail", conversation_id=conversation.conversation_id)
+
+
 def _persist_notification_records(result: AgentResult, *, web_detail_url: str = "") -> None:
    payload = result.notification_payload or {}
    owners = payload.get("owners") or []
--- a/apps/documents/services.py
+++ b/apps/documents/services.py
@@ -53,51 +53,14 @@ def import_submission_batch(scenario_id: str, uploaded_files: list) -> dict:
        workflow_type="registration",
        import_status=SubmissionBatch.STATUS_PROCESSING,
    )
-    documents = []
-    candidates = []
-    chapter_summary = {}
-    total_pages = 0
-    warnings = []
-
-    expanded_result = _expand_uploaded_files(uploaded_files)
-    expanded_files = expanded_result["files"]
-    warnings.extend(expanded_result["warnings"])
-    for uploaded_item in expanded_files:
-        uploaded_file = uploaded_item["uploaded_file"]
-        relative_path = uploaded_item["relative_path"]
-        document = create_uploaded_document(
-            scenario_id,
-            uploaded_file,
-            batch=batch,
-            relative_path=relative_path,
-        )
-        text = extract_text(document)
-        page_count = _estimate_page_count(text)
-        document.page_count = page_count
-        document.page_count_confidence = "estimated"
-        document.document_role = _detect_document_role(document.relative_path)
-        document.chapter_code = _detect_chapter_code(document.relative_path, text)
-        document.chapter_match_status = "matched" if document.chapter_code else "unknown"
-        document.needs_manual_review = not bool(document.chapter_code)
-        document.save(
-            update_fields=[
-                "page_count",
-                "page_count_confidence",
-                "document_role",
-                "chapter_code",
-                "chapter_match_status",
-                "needs_manual_review",
-                "updated_at",
-            ]
-        )
-        documents.append(document)
-        total_pages += page_count
-        chapter_key = document.chapter_code or "UNCLASSIFIED"
-        chapter_summary[chapter_key] = chapter_summary.get(chapter_key, 0) + 1
-        candidates.extend(_extract_product_candidates(document.relative_path, text))
-
-    product_name, product_warnings = _select_product_name(candidates)
-    warnings.extend(product_warnings)
+    ingest_result = _ingest_files_into_batch(
+        batch=batch,
+        scenario_id=scenario_id,
+        uploaded_files=uploaded_files,
+    )
+    documents = ingest_result["documents"]
+    warnings = ingest_result["warnings"]
+    product_name = ingest_result["product_name"]
    conversation = create_conversation_for_batch(batch.batch_id, product_name)

    if not documents:
@@ -106,11 +69,8 @@ def import_submission_batch(scenario_id: str, uploaded_files: list) -> dict:
    batch.product_name = product_name
    batch.conversation_id = conversation.conversation_id
    batch.file_count = len(documents)
-    batch.page_count = total_pages
-    batch.chapter_summary = [
-        {"chapter_code": chapter_code, "document_count": count}
-        for chapter_code, count in sorted(chapter_summary.items())
-    ]
+    batch.page_count = ingest_result["page_count"]
+    batch.chapter_summary = ingest_result["chapter_summary"]
    batch.exception_count = len(warnings)
    if not documents:
        batch.import_status = SubmissionBatch.STATUS_FAILED
@@ -155,6 +115,89 @@ def import_submission_batch(scenario_id: str, uploaded_files: list) -> dict:
    }


+def append_documents_to_batch(
+    scenario_id: str,
+    batch: SubmissionBatch,
+    uploaded_files: list,
+) -> dict:
+    """
+    在既有资料包下继续补传文件，并保持会话绑定不变。
+
+    该服务只负责 Documents 侧的数据更新：
+    - 新文件继续归属原 batch
+    - conversation_id 不变
+    - 如原产品名为空，可用新增文件补齐
+    - 如新增文件产品名与原产品名冲突，则转为待复核
+    """
+    ingest_result = _ingest_files_into_batch(
+        batch=batch,
+        scenario_id=scenario_id,
+        uploaded_files=uploaded_files,
+        keep_existing_product_name=True,
+    )
+    warnings = list(ingest_result["warnings"])
+    all_documents = list(batch.documents.order_by("id"))
+
+    if not all_documents:
+        warnings.append("未发现可导入的支持文件，请检查资料包格式或补充 PDF/DOCX/MD/TXT 文件。")
+        batch.import_status = SubmissionBatch.STATUS_FAILED
+    elif warnings:
+        batch.import_status = SubmissionBatch.STATUS_REVIEW_REQUIRED
+    else:
+        batch.import_status = SubmissionBatch.STATUS_COMPLETED
+
+    batch.product_name = ingest_result["product_name"]
+    batch.file_count = len(all_documents)
+    batch.page_count = ingest_result["page_count"]
+    batch.chapter_summary = ingest_result["chapter_summary"]
+    batch.exception_count = len(warnings)
+    batch.save(
+        update_fields=[
+            "product_name",
+            "file_count",
+            "page_count",
+            "chapter_summary",
+            "exception_count",
+            "import_status",
+            "updated_at",
+        ]
+    )
+
+    if batch.conversation_id:
+        from apps.chat.models import Conversation
+
+        conversation = Conversation.objects.filter(conversation_id=batch.conversation_id).first()
+        if conversation:
+            conversation.product_name = batch.product_name
+            if batch.product_name:
+                conversation.title = batch.product_name
+            conversation.save(update_fields=["product_name", "title", "updated_at"])
+
+    return {
+        "batch_id": batch.batch_id,
+        "conversation_id": batch.conversation_id,
+        "product_name": batch.product_name,
+        "registration_overview_report": {
+            "batch_id": batch.batch_id,
+            "product_name": batch.product_name,
+            "file_count": batch.file_count,
+            "total_page_count": batch.page_count,
+            "chapter_summary": batch.chapter_summary,
+            "documents": [
+                {
+                    "document_id": document.id,
+                    "original_name": document.original_name,
+                    "chapter_code": document.chapter_code,
+                    "page_count": document.page_count,
+                    "document_role": document.document_role,
+                }
+                for document in all_documents
+            ],
+            "warnings": warnings,
+        },
+    }
+
+
 def extract_text(document: UploadedDocument) -> str:
    """
    根据文档类型选择合适的文本抽取策略。
@@ -248,6 +291,87 @@ def _expand_uploaded_files(uploaded_files: list) -> list[dict]:
    return {"files": expanded_files, "warnings": warnings}


+def _ingest_files_into_batch(
+    *,
+    batch: SubmissionBatch,
+    scenario_id: str,
+    uploaded_files: list,
+    keep_existing_product_name: bool = False,
+) -> dict:
+    expanded_result = _expand_uploaded_files(uploaded_files)
+    expanded_files = expanded_result["files"]
+    warnings = list(expanded_result["warnings"])
+    new_documents = []
+    new_candidates = []
+
+    for uploaded_item in expanded_files:
+        uploaded_file = uploaded_item["uploaded_file"]
+        relative_path = uploaded_item["relative_path"]
+        document = create_uploaded_document(
+            scenario_id,
+            uploaded_file,
+            batch=batch,
+            relative_path=relative_path,
+        )
+        text = extract_text(document)
+        page_count = _estimate_page_count(text)
+        document.page_count = page_count
+        document.page_count_confidence = "estimated"
+        document.document_role = _detect_document_role(document.relative_path)
+        document.chapter_code = _detect_chapter_code(document.relative_path, text)
+        document.chapter_match_status = "matched" if document.chapter_code else "unknown"
+        document.needs_manual_review = not bool(document.chapter_code)
+        document.save(
+            update_fields=[
+                "page_count",
+                "page_count_confidence",
+                "document_role",
+                "chapter_code",
+                "chapter_match_status",
+                "needs_manual_review",
+                "updated_at",
+            ]
+        )
+        new_documents.append(document)
+        new_candidates.extend(_extract_product_candidates(document.relative_path, text))
+
+    all_documents = list(batch.documents.order_by("id"))
+    chapter_summary = {}
+    total_pages = 0
+    for document in all_documents:
+        total_pages += document.page_count
+        chapter_key = document.chapter_code or "UNCLASSIFIED"
+        chapter_summary[chapter_key] = chapter_summary.get(chapter_key, 0) + 1
+
+    product_name = batch.product_name
+    if keep_existing_product_name and batch.product_name:
+        conflict_names = {
+            item["product_name"] for item in new_candidates if item["product_name"] != batch.product_name
+        }
+        if conflict_names:
+            warnings.append(
+                "新增文件与当前资料包产品名称不一致："
+                + " / ".join([batch.product_name, *sorted(conflict_names)])
+            )
+    else:
+        product_name, product_warnings = _select_product_name(new_candidates)
+        warnings.extend(product_warnings)
+        if keep_existing_product_name and not product_name:
+            product_name = batch.product_name
+
+    return {
+        "documents": all_documents if keep_existing_product_name else new_documents,
+        "new_documents": new_documents,
+        "warnings": warnings,
+        "product_name": product_name,
+        "page_count": total_pages if keep_existing_product_name else total_pages,
+        "chapter_summary": [
+            {"chapter_code": chapter_code, "document_count": count}
+            for chapter_code, count in sorted(chapter_summary.items())
+        ],
+    }
+
+
 def _extract_zip_entries(uploaded_file) -> dict:
    archive_bytes = uploaded_file.read()
    uploaded_file.seek(0)
--- a/templates/chat/index.html
+++ b/templates/chat/index.html
@@ -119,9 +119,19 @@
              <div>导入状态：{{ batch.get_import_status_display_text }}</div>
            </li>
          </ul>
+          <form method="post" action="{% url 'chat:upload-documents' conversation.conversation_id %}" enctype="multipart/form-data" class="stack" style="margin-top: 16px;">
+            {% csrf_token %}
+            <div>
+              {{ upload_form.files.label_tag }}
+              {{ upload_form.files }}
+            </div>
+            <div class="button-row">
+              <button type="submit">继续上传资料</button>
+              <a class="button" href="{% url 'documents:list' %}">返回资料包</a>
+            </div>
+          </form>
          <div class="button-row" style="margin-top: 16px;">
-            <a class="button button-primary" href="{% url 'documents:upload' %}">继续上传资料</a>
-            <a class="button" href="{% url 'documents:list' %}">返回资料包</a>
+            <a class="button" href="{% url 'documents:upload' %}">导入新资料包</a>
          </div>
        {% else %}
          <div class="notice">暂无绑定资料包。</div>
--- a/tests/test_chat.py
+++ b/tests/test_chat.py
@@ -1,4 +1,5 @@
 from django.urls import reverse
+from django.core.files.uploadedfile import SimpleUploadedFile

 from agent_core.results import AgentResult
 from apps.audit.models import AgentAuditLog
@@ -325,3 +326,40 @@ def test_chat_page_shows_upload_entry_and_dynamic_context_cards(client, db):
    assert "是否允许正式导出" in content
    assert "通知状态" in content
    assert "飞书通知 / 待处理" in content
+
+
+def test_chat_upload_keeps_existing_conversation_binding_and_adds_documents(client, db):
+    batch, conversation = _create_conversation_with_batch()
+    existing_document = UploadedDocument.objects.create(
+        batch=batch,
+        scenario_id="document_review",
+        original_name="原说明书.md",
+        file_type="md",
+        size=1,
+        status=UploadedDocument.STATUS_INDEXED,
+    )
+    existing_count = UploadedDocument.objects.filter(batch=batch).count()
+    upload_file = SimpleUploadedFile(
+        "新增补充资料.txt",
+        "产品名称：新型冠状病毒 2019-nCoV 核酸检测试剂盒".encode("utf-8"),
+        content_type="text/plain",
+    )
+
+    response = client.post(
+        reverse("chat:upload-documents", args=[conversation.conversation_id]),
+        {"files": [upload_file]},
+        follow=True,
+    )
+
+    content = response.content.decode("utf-8")
+    batch.refresh_from_db()
+    conversation.refresh_from_db()
+    assert response.status_code == 200
+    assert SubmissionBatch.objects.count() == 1
+    assert Conversation.objects.count() == 1
+    assert conversation.conversation_id == "conv-001"
+    assert batch.conversation_id == conversation.conversation_id
+    assert UploadedDocument.objects.filter(batch=batch).count() == existing_count + 1
+    assert UploadedDocument.objects.filter(batch=batch, original_name="新增补充资料.txt").exists()
+    assert "新增补充资料.txt" in content
+    assert "已补充到当前资料包" in content