mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-04-25 00:51:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: auto-promote free Moonshot models to top of ai-gateway picker

Browse source 
When the live Vercel AI Gateway catalog exposes a Moonshot model with
zero input AND output pricing, it's promoted to position #1 as the
recommended default — even if the exact ID isn't in the curated
AI_GATEWAY_MODELS list. This enables dynamic discovery of new free
Moonshot variants without requiring a PR to update curation.

Paid Moonshot models are unaffected; falls back to the normal curated
recommended tag when no free Moonshot is live.
This commit is contained in:
jerilynzheng 2026-04-20 00:18:51 -07:00 • committed by Teknium
parent ac26a460f9
commit 5bb2d11b07
2 changed files with 50 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

20
hermes_cli/models.py
View file

@ -812,8 +812,24 @@ def fetch_ai_gateway_models(
if not curated:
return list(_ai_gateway_catalog_cache or fallback)
first_id, _ = curated[0]
curated[0] = (first_id, "recommended")
# If the live catalog offers a free Moonshot model, auto-promote it to
# position #1 as "recommended" — dynamic discovery without a PR.
free_moonshot = next(
(
mid
for mid, item in live_by_id.items()
if mid.startswith("moonshotai/")
and _ai_gateway_model_is_free(item.get("pricing"))
),
None,
)
if free_moonshot:
curated = [(mid, desc) for mid, desc in curated if mid != free_moonshot]
curated.insert(0, (free_moonshot, "recommended"))
else:
first_id, _ = curated[0]
curated[0] = (first_id, "recommended")
_ai_gateway_catalog_cache = curated
return list(curated)

32
tests/hermes_cli/test_ai_gateway_models.py
View file

@ -122,6 +122,38 @@ def test_fetch_ai_gateway_models_tags_free_models():
assert by_id[second_id] == "free"
def test_free_moonshot_model_auto_promoted_to_top_even_if_not_curated():
_reset_caches()
first_curated = AI_GATEWAY_MODELS[0][0]
unlisted_free_moonshot = "moonshotai/kimi-coder-free-preview"
payload = {
"data": [
{"id": first_curated, "pricing": {"input": "0.001", "output": "0.002"}},
{"id": unlisted_free_moonshot, "pricing": {"input": "0", "output": "0"}},
]
}
with patch("urllib.request.urlopen", return_value=_mock_urlopen(payload)):
result = fetch_ai_gateway_models(force_refresh=True)
assert result[0] == (unlisted_free_moonshot, "recommended")
assert any(mid == first_curated for mid, _ in result)
def test_paid_moonshot_does_not_get_auto_promoted():
_reset_caches()
first_curated = AI_GATEWAY_MODELS[0][0]
payload = {
"data": [
{"id": first_curated, "pricing": {"input": "0.001", "output": "0.002"}},
{"id": "moonshotai/some-paid-variant", "pricing": {"input": "0.001", "output": "0.002"}},
]
}
with patch("urllib.request.urlopen", return_value=_mock_urlopen(payload)):
result = fetch_ai_gateway_models(force_refresh=True)
assert result[0][0] == first_curated
def test_fetch_ai_gateway_models_falls_back_on_error():
_reset_caches()
with patch("urllib.request.urlopen", side_effect=OSError("network")):