Skip to content

[Bug]: innitial "hermes setup" inference provider applies to .env not config #3415

@Salt-555

Description

@Salt-555

Bug Description

The model and provider selection chosen at setup doesnt change it in the config.yaml

apologies is this is a repeat.

Steps to Reproduce

new hermes install/ setup
select custom open AI type provider with my local model
restart shell
start hermes
still defaulted to openrouter/claude (config still has this set)
run hermes model and set the custom provider
start hermes and it works fine

seems like the "hemes model" sets it in the config and the "hermes setup" just sets it in the .env unsure if this is intended.

Expected Behavior

It would be awesome if the hermes setup set your prefered model in both the .env and the config.yaml

Actual Behavior

had to set my model in hermes setup and in hermes model

Affected Component

CLI (interactive chat)

Messaging Platform (if gateway-related)

N/A (CLI only)

Operating System

Arch btw

Python Version

3.11.2

Hermes Version

0.4.0

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

Metadata

Metadata

Assignees

No one assigned

    Labels

    type/bugSomething isn't working

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions