BUG: Backend: Agent Handlers Cause Stale Context by Not Updating Cache

[DeveloperAmrit]

Is there an existing issue for this?

• I have searched the existing issues

What happened?

📌 Issue Overview

When a user updates their data (weight, symptoms, appointments) using natural language chat (via the Agent), the changes are committed to the database, but the Agent's context cache is not updated. This results in the Agent having "stale" knowledge of the user's state until the cache expires or the server restarts.

🔍 Steps to Reproduce

1. Send a POST request to /agent with the query: "Log my weight as 95kg".
2. Immediately send a follow-up POST request to /agent what is my current weight

🎯 Expected Behavior

The Agent should respond referencing the newly logged weight of 95kg.

🚨 Actual Behavior

The Agent responds using the old weight (from the previous cache state), ignoring the update just made.

📷 Screenshot

💡 Suggested Improvements

Update the handlers in handlers folder to trigger a cache update upon successful database insertion.

Record

• I agree to follow this project's Code of Conduct
• I want to work on this issue

[Sunilvishyt]

Hi @DeveloperAmrit , I’ve analyzed this issue and would like to work on it!

My Plan:

I'll modify the handlers in the handlers/ directory to ensure that after a successful database commit (weight, symptoms, etc.), the Agent's LangChain memory/context is updated or invalidated.

This will ensure that follow-up queries reflect the most recent database state without needing a server restart.

Could you please assign this to me? Thanks!

[DeveloperAmrit]

@Sunilvishyt Sorry bro, but i am already working on it

[RashiS26]

@DeveloperAmrit can you assign me this issue?