langgenius/dify · warning · NotFound

Conversation Not Exists.

Error message

Conversation Not Exists.

What it means

Raised as NotFound('Conversation Not Exists.') in AdvancedChatDraftWorkflowRunApi.post when AppGenerateService.generate raises services.errors.conversation.ConversationNotExistsError (api/controllers/console/app/workflow.py:725-726). The supplied conversation_id does not correspond to an existing conversation for the app, so the advanced-chat draft run cannot continue.

Source

Thrown at api/controllers/console/app/workflow.py:726

        args = args_model.model_dump(exclude_none=True)

        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(

View on GitHub (pinned to ef8544b173)

Solutions

1. Omit conversation_id (or send null) to start a new conversation for the draft run.
2. If continuing an existing thread, obtain a fresh conversation_id from the conversation list for the app.
3. Clear the front-end conversation state when a conversation is deleted or completed.

Example fix

// before: sending a stale conversation id
{query:'hi', conversation_id: oldId}
// after: start fresh when in doubt
{query:'hi', conversation_id: null}

// Validate conversation_id before the draft run
async function conversationExists(appId, convId) {
  if (!convId) return true // new conversation
  const res = await fetch(`/apps/${appId}/conversations`)
  const list = await res.json()
  return list.data.some(c => c.id === convId)
}
if (!(await conversationExists(appId, payload.conversation_id))) payload.conversation_id = null

try {
  return await runDraft(appId, payload)
} catch (e) {
  if (e.status === 404 && /Conversation Not Exists/.test(e.message)) {
    payload.conversation_id = null; return runDraft(appId, payload)
  }
  throw e
}

When it happens

Trigger: POSTing /apps/{app_id}/advanced-chat/workflows/draft/run with a conversation_id that does not exist or does not belong to the app. The generate path loads the conversation and fails.

Common situations: Stale conversation_id from a deleted/ended conversation; conversation_id from a different app; UUID typo; conversation purged by retention; front-end not clearing conversation_id after the thread was removed.

Related errors

• conversation_completed
• Webhook trigger not found for this node
• Trigger not found
• Conversation Not Exists.
• usage_invalid_flag

AI-assisted analysis of langgenius/dify@ef8544b173 (2026-08-12). Data as JSON: /api/errors/87e88d77f0858108. Report an issue: GitHub.