Bug Description

/model is no longer a functioning command in the Telegram gateway, even though it shows in Telegram as an available command, and setting the model in the cli does not change the model used by the telegram session.

The result is that, in 0.6.0, there is no way to reliably switch models in the Telegram gateway.

This also means that you cannot switch models unless you can access the cli, so hitting a rate limit on the selected LLM in Telegram will kill the gateway until you can log back in to the cli. That's a genuine issue.

Steps to Reproduce

1. Run hermes in telegram
2. Run /model + your desired model
3. It doesn't switch
4. Switch models in hermes cli
5. Restart gateway
6. Gateway still doesnt update models

Expected Behavior

Leave /model as a functioning command in the Telegram gateway.

Actual Behavior

No model switch happens in Telegram.

Affected Component

Gateway (Telegram/Discord/Slack/WhatsApp)

Messaging Platform (if gateway-related)

Telegram

Operating System

Ubuntu 24.04

Python Version

3.11.9

Hermes Version

0.6.0

Relevant Logs / Traceback

Root Cause Analysis (optional)

No response

Proposed Fix (optional)

No response

Are you willing to submit a PR for this?

• I'd like to fix this myself and submit a PR