langgenius/dify · warning · ConversationCompletedError

conversation_completed

conversation_completed

Error message

The conversation has ended. Please start a new conversation.

What it means

Raised as ConversationCompletedError in AdvancedChatDraftWorkflowRunApi.post when AppGenerateService.generate raises services.errors.conversation.ConversationCompletedError (api/controllers/console/app/workflow.py:727-728). The referenced conversation has reached a terminal/completed state and no further messages can be appended to it; a new conversation must be started.

Source

Thrown at api/controllers/console/app/workflow.py:728

        external_trace_id = get_external_trace_id(request)
        if external_trace_id:
            args["external_trace_id"] = external_trace_id

        try:
            response = AppGenerateService.generate(
                session=session,
                app_model=app_model,
                user=current_user,
                args=args,
                invoke_from=InvokeFrom.DEBUGGER,
                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 InvokeRateLimitError as ex:
            raise InvokeRateLimitHttpError(ex.description)
        except ValueError as e:
            raise e
        except Exception:
            logger.exception("internal server error.")
            raise InternalServerError()


@console_ns.route("/apps/<uuid:app_id>/advanced-chat/workflows/draft/iteration/nodes/<string:node_id>/run")
class AdvancedChatDraftRunIterationNodeApi(Resource):
    @console_ns.doc("run_advanced_chat_draft_iteration_node")
    @console_ns.doc(description="Run draft workflow iteration node for advanced chat")
    @console_ns.doc(params={"app_id": "Application ID", "node_id": "Node ID"})
    @console_ns.expect(console_ns.models[IterationNodeRunPayload.__name__])
    @console_ns.response(
        200,
        "Iteration node run started successfully",

View on GitHub (pinned to ef8544b173)

Solutions

1. Start a new conversation (send conversation_id: null) to continue the session.
2. If the completion was unintended, review the workflow terminator/end conditions that marked the conversation completed.
3. Clear the front-end conversation_id once the conversation is completed so subsequent runs start a new thread.

Example fix

// before: reusing a completed conversation
{query:'hi', conversation_id: completedId}
// after: begin a new conversation
{query:'hi', conversation_id: null}

// Check conversation status before running; start new if completed
const conv = await getConversation(appId, payload.conversation_id)
if (conv?.status === 'completed') payload.conversation_id = null
await runDraft(appId, payload)

try {
  return await runDraft(appId, payload)
} catch (e) {
  if (e.code === 'conversation_completed') {
    payload.conversation_id = null; return runDraft(appId, payload)
  }
  throw e
}

When it happens

Trigger: POSTing a draft run against a conversation_id that is marked completed/ended. The service refuses to add turns to a finished conversation.

Common situations: End-of-conversation triggered by a workflow terminator node; explicit 'end conversation' action; conversation auto-completed by a max-turns rule; client reusing a conversation the user already finished.

Related errors

• Conversation Not Exists.
• patched environment variables require an id
• patched environment variable ids must be unique
• deleted environment variable ids must not be empty
• deleted environment variable ids must be unique

AI-assisted analysis of langgenius/dify@ef8544b173 (2026-08-12). Data as JSON: /api/errors/05f6127a3b8505b0. Report an issue: GitHub.