Working perfect with window buffer memory but not with postgre chat memory

[Brijesh_Mahawar]

@ria @jan @sirdavidoff This workflow is working perfect with window buffer memory storing context of end to end conversation but we want to store the data permanently, currently we are using session id as user WhatsApp no. and Postgres memory to store conversation , all the conversations are storing properly and reflecting in same manner like window buffer memory but the main issue we are facing in postgres workflow is , it is not able to hold the past conversation.

thanks !! in advance , please advice.

Information on your n8n setup

• **n8n version: 1.78.1
• **Database (default: SQLite): Postgres
• **n8n EXECUTIONS_PROCESS setting (default: own, main): Default
• **Running n8n via (Docker, npm, n8n cloud, desktop app): Docker
• **Operating system: Ubuntu Preformatted text

[Jim_Le]

Hey @Brijesh_Mahawar

The chat memory only deletes messages once you reach the defined context length or if you delete manually (also maybe your PG is a temp table/database?).

What value do you currently have the context length? If you want to store messages permanently, perhaps you can increase this setting to a very high number.

[Brijesh_Mahawar]

Hi @Jim_Le Thanks !! for the response. Its working fine i am also having issue that the workflow stopped responding after some time even though it is toggled to active mode.