Bug Description

/v1/props should be GET /props when targeting llama.cpp. The fix in Hermes would be to call /props relative to the server root, not the OpenAI base path.

Using llama-server with flag
--props

Steps to Reproduce

using llama-server with flag --props

Expected Behavior

srv log_server_r: done request: GET /props 192.168.3.51 200

Actual Behavior

from the log files when using llama.cpp

srv log_server_r: done request: GET /v1/props 192.168.3.51 404

Affected Component

Other

Messaging Platform (if gateway-related)

No response

Debug Report

n/a

Operating System

windows 11

Python Version

No response

Hermes Version

0.10

Additional Logs / Traceback (optional)

Root Cause Analysis (optional)

No response

Proposed Fix (optional)

The fix in Hermes would be to call /props relative to the server root, not the OpenAI base path.

Are you willing to submit a PR for this?

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