mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-05-23 05:31:23 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 7

test(novita): cache pricing, add provider test coverage, AUTHOR_MAP entry

Browse source 
Follow-up to Alex-wuhu's NovitaAI provider commit. Adds:

- _pricing_cache hit/write in _fetch_novita_pricing (was missing — every
  pricing fetch was re-hitting the network), mirroring the
  fetch_ai_gateway_pricing pattern. force_refresh now also propagates
  from get_pricing_for_provider.
- TestNovitaProvider in tests/hermes_cli/test_api_key_providers.py
  covering profile load, alias resolution, registry auto-registration,
  model list parity between main.py and models.py, _URL_TO_PROVIDER,
  _PROVIDER_PREFIXES, context_size in _CONTEXT_LENGTH_KEYS, pricing
  unit conversion, and pricing cache behavior.
- AUTHOR_MAP entry for yanglongwei06@gmail.com → @Alex-yang00.
This commit is contained in:
kshitijk4poor 2026-05-14 12:05:52 +05:30 • committed by kshitij
parent 1551ce46a4
commit 0f0e20ef81
3 changed files with 172 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

21
hermes_cli/models.py
View file

@ -1516,7 +1516,7 @@ def get_pricing_for_provider(provider: str, *, force_refresh: bool = False) -> d
if normalized == "ai-gateway":
return fetch_ai_gateway_pricing(force_refresh=force_refresh)
if normalized == "novita":
return _fetch_novita_pricing()
return _fetch_novita_pricing(force_refresh=force_refresh)
if normalized == "nous":
api_key, base_url = _resolve_nous_pricing_credentials()
if base_url:
@ -1533,19 +1533,31 @@ def get_pricing_for_provider(provider: str, *, force_refresh: bool = False) -> d
return {}
def _fetch_novita_pricing(timeout: float = 8.0) -> dict[str, dict[str, str]]:
def _fetch_novita_pricing(
timeout: float = 8.0,
*,
force_refresh: bool = False,
) -> dict[str, dict[str, str]]:
"""Fetch pricing from NovitaAI /v1/models.
NovitaAI returns input/output prices per million tokens in units of
0.0001 USD. Convert them to the per-token strings used by the shared
pricing formatter.
Results are cached in ``_pricing_cache`` keyed on the resolved base URL,
matching the pattern used by ``fetch_ai_gateway_pricing`` — without this,
every menu render or pricing lookup re-hits the network.
"""
api_key = os.getenv("NOVITA_API_KEY", "").strip()
if not api_key:
return {}
base_url = os.getenv("NOVITA_BASE_URL", "").strip() or "https://api.novita.ai/openai/v1"
url = base_url.rstrip("/") + "/models"
cache_key = base_url.rstrip("/")
if not force_refresh and cache_key in _pricing_cache:
return _pricing_cache[cache_key]
url = cache_key + "/models"
headers = {
"Authorization": f"Bearer {api_key}",
"Accept": "application/json",
@ -1557,6 +1569,7 @@ def _fetch_novita_pricing(timeout: float = 8.0) -> dict[str, dict[str, str]]:
with urllib.request.urlopen(req, timeout=timeout) as resp:
payload = json.loads(resp.read().decode())
except Exception:
_pricing_cache[cache_key] = {}
return {}
result: dict[str, dict[str, str]] = {}
@ -1574,6 +1587,8 @@ def _fetch_novita_pricing(timeout: float = 8.0) -> dict[str, dict[str, str]]:
"prompt": str(float(inp or 0) / 10_000 / 1_000_000),
"completion": str(float(out or 0) / 10_000 / 1_000_000),
}
_pricing_cache[cache_key] = result
return result