langgenius/dify · error · ConversationCompletedError

conversation_completed

conversation_completed

Error message

The conversation has ended. Please start a new conversation.

What it means

Returned (HTTP 400, error_code `conversation_completed`, 'The conversation has ended. Please start a new conversation.') by POST .../draft/iteration/nodes/<node_id>/run when the service raises `services.errors.conversation.ConversationCompletedError`. A conversation that has reached its terminal state cannot accept further node runs; the controller maps this to the typed ConversationCompletedError HTTP exception.

Source

Thrown at api/controllers/console/datasets/rag_pipeline/rag_pipeline_workflow.py:294

    @edit_permission_required
    @rbac_permission_required(RBACResourceScope.DATASET, RBACPermission.DATASET_EDIT)
    @model_validate(NodeRunPayload)
    def post(self, req_data: NodeRunPayload, current_user: Account, pipeline: Pipeline, node_id: str):
        """
        Run draft workflow iteration node
        """
        args = req_data.model_dump(exclude_none=True)

        try:
            response = PipelineGenerateService.generate_single_iteration(
                pipeline=pipeline, user=current_user, node_id=node_id, args=args, session=db.session(), streaming=True
            )

            return helper.compact_generate_response(response)
        except services.errors.conversation.ConversationNotExistsError:
            raise NotFound("Conversation Not Exists.")
        except services.errors.conversation.ConversationCompletedError:
            raise ConversationCompletedError()
        except ValueError as e:
            raise e
        except Exception:
            logging.exception("internal server error.")
            raise InternalServerError()


@console_ns.route("/rag/pipelines/<uuid:pipeline_id>/workflows/draft/loop/nodes/<string:node_id>/run")
class RagPipelineDraftRunLoopNodeApi(Resource):
    @console_ns.expect(console_ns.models[NodeRunPayload.__name__])
    @console_ns.response(200, "Success", console_ns.models[RagPipelineOpaqueResponse.__name__])
    @setup_required
    @login_required
    @account_initialization_required
    @edit_permission_required
    @rbac_permission_required(RBACResourceScope.DATASET, RBACPermission.DATASET_EDIT)
    @with_current_user
    @get_rag_pipeline

View on GitHub (pinned to ef8544b173)

Solutions

1. Start a new conversation before issuing the next iteration run.
2. Detect the conversation completed event in the client and disable further iteration controls.
3. Clear conversation state when the end event arrives.
4. Design the workflow to keep the conversation open if continued iteration is intended.

Example fix

// before
if (conversationEnded) await runIteration(nodeId)
// after
if (conversationEnded) {
  conversation = await createConversation()
}
await runIteration(nodeId, conversation.id)

// client-side: stop issuing iteration runs after the conversation end event
if (conversation.status === 'completed') {
  conversation = await createConversation()
}
await post(`${base}/draft/iteration/nodes/${nodeId}/run`, { conversation_id: conversation.id })

try {
  await post(`${base}/draft/iteration/nodes/${nodeId}/run`, payload)
} catch (e) {
  if (e.code === 'conversation_completed') {
    // start a new conversation and retry once, or stop the workflow
  } else throw e
}

When it happens

Trigger: Issuing an iteration run against a conversation that has already produced its final output; chaining runs after the conversation was marked complete; replaying a request after end-of-conversation.

Common situations: Workflow that emits a 'stop' or 'end' event then receives further iteration requests. UI allowing continued iteration after the conversation summary is shown. Backend that auto-completes conversations on a timer.

Related errors

• Conversation Not Exists.
• Internal Server Error
• expected dict for file, got {type(raw_value)}
• expected list for files, got {type(raw_value)}
• expected dict for files[0], got {type(raw_value)}

AI-assisted analysis of langgenius/dify@ef8544b173 (2026-08-12). Data as JSON: /api/errors/a9e078ff74e7a9b7. Report an issue: GitHub.