Timmy_Foundation/hermes-agent
15
0
Fork 0
Code Issues 233 Pull Requests 11 Actions 4 Packages Projects Releases Wiki Activity

Merge pull request #2403 from NousResearch/hermes/hermes-31d7db3b

Browse Source 
fix(model_metadata): use /v1/props endpoint for llama.cpp context detection
This commit is contained in:
Teknium
2026-03-21 18:07:41 -07:00
committed by GitHub
parent a0f411c87d 29d0541ac9
commit ec22635b47
1 changed files with 9 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
agent/model_metadata.py
View File

@@ -260,9 +260,11 @@ def detect_local_server_type(base_url: str) -> Optional[str]:
pass
except Exception:
pass
# llama.cpp exposes /props
# llama.cpp exposes /v1/props (older builds used /props without the /v1 prefix)
try:
r = client.get(f"{server_url}/props")
r = client.get(f"{server_url}/v1/props")
if r.status_code != 200:
r = client.get(f"{server_url}/props") # fallback for older builds
if r.status_code == 200 and "default_generation_settings" in r.text:
return "llamacpp"
except Exception:
@@ -455,8 +457,11 @@ def fetch_endpoint_model_metadata(
)
if is_llamacpp:
try:
props_url = candidate.rstrip("/").replace("/v1", "") + "/props"
props_resp = requests.get(props_url, headers=headers, timeout=5)
# Try /v1/props first (current llama.cpp); fall back to /props for older builds
base = candidate.rstrip("/").replace("/v1", "")
props_resp = requests.get(base + "/v1/props", headers=headers, timeout=5)
if not props_resp.ok:
props_resp = requests.get(base + "/props", headers=headers, timeout=5)
if props_resp.ok:
props = props_resp.json()
gen_settings = props.get("default_generation_settings", {})