feat(file-summary): 接入文件汇总工作流触发
This commit is contained in:
16
review_agent/file_summary/events.py
Normal file
16
review_agent/file_summary/events.py
Normal file
@@ -0,0 +1,16 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from review_agent.models import FileSummaryBatch, WorkflowEvent
|
||||
|
||||
|
||||
def record_event(batch: FileSummaryBatch, event_type: str, payload: dict | None = None) -> WorkflowEvent:
|
||||
return WorkflowEvent.objects.create(batch=batch, event_type=event_type, payload=payload or {})
|
||||
|
||||
|
||||
def serialize_event(event: WorkflowEvent) -> dict[str, object]:
|
||||
return {
|
||||
"id": event.pk,
|
||||
"event_type": event.event_type,
|
||||
"payload": event.payload,
|
||||
"created_at": event.created_at.isoformat(),
|
||||
}
|
||||
@@ -3,6 +3,8 @@ from django.http import Http404, JsonResponse
|
||||
from django.views.decorators.http import require_http_methods
|
||||
|
||||
from review_agent.models import Conversation, FileAttachment
|
||||
from review_agent.models import FileSummaryBatch, WorkflowEvent
|
||||
from .events import serialize_event
|
||||
|
||||
from .storage import save_uploaded_attachment, serialize_attachment
|
||||
|
||||
@@ -56,3 +58,50 @@ def attachment_detail(request, conversation_id: int, attachment_id: int):
|
||||
attachment.is_active = False
|
||||
attachment.save(update_fields=["upload_status", "is_active"])
|
||||
return JsonResponse({"ok": True, "attachment": serialize_attachment(attachment)})
|
||||
|
||||
|
||||
@require_http_methods(["GET"])
|
||||
@login_required
|
||||
def batch_status(request, batch_id: int):
|
||||
batch = FileSummaryBatch.objects.filter(pk=batch_id, user=request.user).first()
|
||||
if not batch:
|
||||
raise Http404("批次不存在。")
|
||||
return JsonResponse(
|
||||
{
|
||||
"batch": {
|
||||
"id": batch.pk,
|
||||
"batch_no": batch.batch_no,
|
||||
"status": batch.status,
|
||||
"product_name": batch.product_name,
|
||||
"total_files": batch.total_files,
|
||||
"success_files": batch.success_files,
|
||||
"failed_files": batch.failed_files,
|
||||
"total_pages": batch.total_pages,
|
||||
},
|
||||
"nodes": [
|
||||
{
|
||||
"node_code": node.node_code,
|
||||
"node_name": node.node_name,
|
||||
"status": node.status,
|
||||
"progress": node.progress,
|
||||
"message": node.message,
|
||||
}
|
||||
for node in batch.node_runs.order_by("id")
|
||||
],
|
||||
}
|
||||
)
|
||||
|
||||
|
||||
@require_http_methods(["GET"])
|
||||
@login_required
|
||||
def batch_events(request, batch_id: int):
|
||||
batch = FileSummaryBatch.objects.filter(pk=batch_id, user=request.user).first()
|
||||
if not batch:
|
||||
raise Http404("批次不存在。")
|
||||
after = request.GET.get("after") or "0"
|
||||
try:
|
||||
after_id = int(after)
|
||||
except ValueError:
|
||||
after_id = 0
|
||||
events = WorkflowEvent.objects.filter(batch=batch, pk__gt=after_id).order_by("id")
|
||||
return JsonResponse({"events": [serialize_event(event) for event in events]})
|
||||
|
||||
127
review_agent/file_summary/workflow.py
Normal file
127
review_agent/file_summary/workflow.py
Normal file
@@ -0,0 +1,127 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from threading import Thread
|
||||
from uuid import uuid4
|
||||
|
||||
from django.db import transaction
|
||||
from django.utils import timezone
|
||||
|
||||
from review_agent.models import (
|
||||
Conversation,
|
||||
FileAttachment,
|
||||
FileSummaryBatch,
|
||||
FileSummaryBatchAttachment,
|
||||
Message,
|
||||
WorkflowNodeRun,
|
||||
)
|
||||
|
||||
from .events import record_event
|
||||
|
||||
|
||||
NODE_DEFINITIONS = [
|
||||
("upload", "附件固化"),
|
||||
("extract", "压缩包解压"),
|
||||
("inventory", "文件扫描"),
|
||||
("page_count", "页数统计"),
|
||||
("product_detect", "产品识别"),
|
||||
("report", "报告输出"),
|
||||
("complete", "完成"),
|
||||
]
|
||||
|
||||
|
||||
def build_batch_no() -> str:
|
||||
return f"FS-{timezone.localtime().strftime('%Y%m%d%H%M%S')}-{uuid4().hex[:6]}"
|
||||
|
||||
|
||||
@transaction.atomic
|
||||
def create_file_summary_batch(
|
||||
*,
|
||||
conversation: Conversation,
|
||||
user,
|
||||
trigger_message: Message | None = None,
|
||||
) -> FileSummaryBatch:
|
||||
active_attachments = list(
|
||||
FileAttachment.objects.select_for_update()
|
||||
.filter(conversation=conversation, is_active=True)
|
||||
.exclude(upload_status=FileAttachment.UploadStatus.DELETED)
|
||||
.order_by("original_name", "-created_at")
|
||||
)
|
||||
if not active_attachments:
|
||||
raise ValueError("当前对话没有可用附件。")
|
||||
|
||||
batch = FileSummaryBatch.objects.create(
|
||||
conversation=conversation,
|
||||
user=user,
|
||||
trigger_message=trigger_message,
|
||||
batch_no=build_batch_no(),
|
||||
)
|
||||
|
||||
for attachment in active_attachments:
|
||||
FileSummaryBatchAttachment.objects.create(batch=batch, attachment=attachment)
|
||||
attachment.upload_status = FileAttachment.UploadStatus.BOUND
|
||||
attachment.save(update_fields=["upload_status"])
|
||||
|
||||
for code, name in NODE_DEFINITIONS:
|
||||
WorkflowNodeRun.objects.create(batch=batch, node_code=code, node_name=name)
|
||||
|
||||
record_event(batch, "workflow_created", {"batch_id": batch.pk, "batch_no": batch.batch_no})
|
||||
return batch
|
||||
|
||||
|
||||
class WorkflowExecutor:
|
||||
def __init__(self, batch: FileSummaryBatch):
|
||||
self.batch = batch
|
||||
|
||||
def run(self) -> None:
|
||||
self.batch.status = FileSummaryBatch.Status.RUNNING
|
||||
self.batch.started_at = timezone.now()
|
||||
self.batch.save(update_fields=["status", "started_at"])
|
||||
record_event(self.batch, "workflow_started", {"batch_id": self.batch.pk})
|
||||
|
||||
try:
|
||||
for node in self.batch.node_runs.order_by("id"):
|
||||
self._run_node(node)
|
||||
except Exception as exc:
|
||||
self.batch.status = FileSummaryBatch.Status.FAILED
|
||||
self.batch.error_message = str(exc)
|
||||
self.batch.finished_at = timezone.now()
|
||||
self.batch.save(update_fields=["status", "error_message", "finished_at"])
|
||||
record_event(self.batch, "workflow_failed", {"message": str(exc)})
|
||||
return
|
||||
|
||||
self.batch.status = FileSummaryBatch.Status.SUCCESS
|
||||
self.batch.finished_at = timezone.now()
|
||||
self.batch.save(update_fields=["status", "finished_at"])
|
||||
record_event(self.batch, "workflow_completed", {"batch_id": self.batch.pk})
|
||||
|
||||
def _run_node(self, node: WorkflowNodeRun) -> None:
|
||||
now = timezone.now()
|
||||
node.status = WorkflowNodeRun.Status.RUNNING
|
||||
node.progress = 10
|
||||
node.started_at = now
|
||||
node.message = f"{node.node_name}处理中"
|
||||
node.save(update_fields=["status", "progress", "started_at", "message"])
|
||||
record_event(
|
||||
self.batch,
|
||||
"node_progress",
|
||||
{"node_code": node.node_code, "status": node.status, "progress": node.progress},
|
||||
)
|
||||
|
||||
node.status = WorkflowNodeRun.Status.SUCCESS
|
||||
node.progress = 100
|
||||
node.finished_at = timezone.now()
|
||||
node.message = f"{node.node_name}完成"
|
||||
node.save(update_fields=["status", "progress", "finished_at", "message"])
|
||||
record_event(
|
||||
self.batch,
|
||||
"node_progress",
|
||||
{"node_code": node.node_code, "status": node.status, "progress": node.progress},
|
||||
)
|
||||
|
||||
|
||||
def start_file_summary_workflow(batch: FileSummaryBatch, *, async_run: bool = True) -> None:
|
||||
executor = WorkflowExecutor(batch)
|
||||
if not async_run:
|
||||
executor.run()
|
||||
return
|
||||
Thread(target=executor.run, daemon=True).start()
|
||||
30
review_agent/file_summary/workflow_trigger.py
Normal file
30
review_agent/file_summary/workflow_trigger.py
Normal file
@@ -0,0 +1,30 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass
|
||||
|
||||
from review_agent.models import Conversation, FileAttachment
|
||||
|
||||
|
||||
TRIGGER_KEYWORDS = ("自动汇总", "文件目录", "页数", "目录与页数", "文件清单")
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class TriggerResult:
|
||||
should_start: bool
|
||||
workflow_type: str = ""
|
||||
reason: str = ""
|
||||
|
||||
|
||||
def evaluate_file_summary_trigger(conversation: Conversation, content: str) -> TriggerResult:
|
||||
text = (content or "").strip()
|
||||
if not any(keyword in text for keyword in TRIGGER_KEYWORDS):
|
||||
return TriggerResult(should_start=False, reason="not_matched")
|
||||
|
||||
has_attachment = FileAttachment.objects.filter(
|
||||
conversation=conversation,
|
||||
is_active=True,
|
||||
).exclude(upload_status=FileAttachment.UploadStatus.DELETED).exists()
|
||||
if not has_attachment:
|
||||
return TriggerResult(should_start=False, reason="missing_attachment")
|
||||
|
||||
return TriggerResult(should_start=True, workflow_type="file_summary")
|
||||
@@ -3,8 +3,11 @@ from __future__ import annotations
|
||||
import json
|
||||
|
||||
from django.db.models import Q, QuerySet
|
||||
from django.conf import settings
|
||||
from django.utils import timezone
|
||||
|
||||
from .file_summary.workflow import create_file_summary_batch, start_file_summary_workflow
|
||||
from .file_summary.workflow_trigger import evaluate_file_summary_trigger
|
||||
from .llm import LLMConfigurationError, LLMRequestError, generate_reply, stream_reply
|
||||
from .models import Conversation, Message
|
||||
|
||||
@@ -88,6 +91,7 @@ def stream_message(conversation: Conversation, content: str):
|
||||
|
||||
user_message = append_user_message(conversation, content)
|
||||
assistant_parts: list[str] = []
|
||||
trigger = evaluate_file_summary_trigger(conversation, content)
|
||||
|
||||
yield sse_event(
|
||||
"meta",
|
||||
@@ -99,6 +103,51 @@ def stream_message(conversation: Conversation, content: str):
|
||||
},
|
||||
)
|
||||
|
||||
if trigger.reason == "missing_attachment":
|
||||
reply_content = "请先在当前对话右侧上传需要汇总的文件或压缩包,然后再发送自动汇总指令。"
|
||||
assistant_message = append_assistant_message(conversation, reply_content)
|
||||
yield sse_event("chunk", {"delta": reply_content})
|
||||
yield sse_event(
|
||||
"done",
|
||||
{
|
||||
"assistant_message_id": assistant_message.pk,
|
||||
"conversation_id": conversation.pk,
|
||||
"title": conversation.title,
|
||||
},
|
||||
)
|
||||
return
|
||||
|
||||
if trigger.should_start:
|
||||
batch = create_file_summary_batch(
|
||||
conversation=conversation,
|
||||
user=conversation.user,
|
||||
trigger_message=user_message,
|
||||
)
|
||||
start_file_summary_workflow(
|
||||
batch,
|
||||
async_run=getattr(settings, "FILE_SUMMARY_ASYNC", True),
|
||||
)
|
||||
reply_content = f"已启动文件目录与页数自动汇总工作流,批次号:{batch.batch_no}。"
|
||||
assistant_message = append_assistant_message(conversation, reply_content)
|
||||
yield sse_event(
|
||||
"workflow_started",
|
||||
{
|
||||
"workflow_type": "file_summary",
|
||||
"batch_id": batch.pk,
|
||||
"batch_no": batch.batch_no,
|
||||
},
|
||||
)
|
||||
yield sse_event("chunk", {"delta": reply_content})
|
||||
yield sse_event(
|
||||
"done",
|
||||
{
|
||||
"assistant_message_id": assistant_message.pk,
|
||||
"conversation_id": conversation.pk,
|
||||
"title": conversation.title,
|
||||
},
|
||||
)
|
||||
return
|
||||
|
||||
try:
|
||||
for chunk in stream_reply(conversation, content):
|
||||
assistant_parts.append(chunk)
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
from django.urls import path
|
||||
|
||||
from .file_summary.views import attachment_detail, attachments
|
||||
from .file_summary.views import attachment_detail, attachments, batch_events, batch_status
|
||||
|
||||
|
||||
urlpatterns = [
|
||||
@@ -19,4 +19,14 @@ urlpatterns = [
|
||||
attachment_detail,
|
||||
name="file_summary_attachment_detail",
|
||||
),
|
||||
path(
|
||||
"api/review-agent/file-summary/<int:batch_id>/status/",
|
||||
batch_status,
|
||||
name="file_summary_batch_status",
|
||||
),
|
||||
path(
|
||||
"api/review-agent/file-summary/<int:batch_id>/events/",
|
||||
batch_events,
|
||||
name="file_summary_batch_events",
|
||||
),
|
||||
]
|
||||
|
||||
Reference in New Issue
Block a user