seb/hermes-agent
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(models): keep curated-first ordering in live+curated merge; use pure-catalog helper in validation

Browse Source 
The generic live+curated merge (commit 630b438) seeded the merged list
from live results, demoting curated-only models below live ones. That
regressed #46309, which deliberately surfaces the newest curated model
(kimi-k2.7-code) FIRST in the native picker even when the live /models
listing lags. Restore curated-first ordering: curated entries lead (in
catalog order), live-only entries are appended for discovery. This keeps
the #46850 fix (zai glm-5.2 now appears) without the kimi regression.

Also switch the validate_requested_model curated fallback (commit
ee7b8a4) from provider_model_ids() — which triggers a second, uncached
live /models fetch with its own 8s timeout and may resolve different
credentials than the api_key/base_url just probed — to the pure-catalog
helper _model_in_provider_catalog(). Membership is checked against the
shipped catalog only, with no extra network call.

Tests: restore the curated-first assertion in
test_kimi_coding_live_catalog_does_not_hide_curated_k2_7_code; update
the new merge tests to curated-first semantics; de-circularize the
validation fallback tests to patch _PROVIDER_MODELS (the real source)
instead of mocking the function under test.
This commit is contained in:
kshitijk4poor
2026-06-16 23:25:07 +05:30
parent ee7b8a4672
commit 658ac1d866
3 changed files with 71 additions and 39 deletions
Download Patch File Download Diff File Expand all files Collapse all files
hermes_cli/models.py
+22 -24
View File
@@ -2370,16 +2370,18 @@ def provider_model_ids(provider: Optional[str], *, force_refresh: bool = False)
if api_key:
live = _p.fetch_models(api_key=api_key)
if live:
# Merge live API results with static curated list so
# Merge static curated list with live API results so
# models that the live endpoint omits (stale cache,
# partial rollout) still appear in the picker.
# Live entries come first (provider's preferred order),
# then curated-only entries are appended. (#46850)
# Curated entries come first so deliberately-surfaced
# newest models (e.g. kimi-k2.7-code, #46309) stay at
# the top of the picker; live-only entries are appended
# afterwards for discovery. (#46850)
curated = list(_PROVIDER_MODELS.get(normalized, []))
if curated:
merged = list(live)
merged_lower = {m.lower() for m in live}
for m in curated:
merged = list(curated)
merged_lower = {m.lower() for m in curated}
for m in live:
if m.lower() not in merged_lower:
merged.append(m)
merged_lower.add(m.lower())
@@ -3942,24 +3944,20 @@ def validate_requested_model(
# Model not in live /v1/models — check the curated catalog
# before rejecting. Providers may omit models from their live
# listing that are still valid (stale cache, partial rollout,
# gated previews). If the curated list has it, accept with a
# note. (#46850)
try:
curated = provider_model_ids(normalized)
except Exception:
curated = []
if curated:
curated_lower = {m.lower(): m for m in curated}
if requested_for_lookup.lower() in curated_lower:
return {
"accepted": True,
"persist": True,
"recognized": True,
"message": (
f"Note: `{requested}` was not found in the live /v1/models listing "
f"but exists in the curated catalog — accepted."
),
}
# gated previews). Use the pure-catalog helper (no extra live
# fetch) so we only accept models Hermes actually ships. (#46850)
if _model_in_provider_catalog(
requested_for_lookup.lower(), _provider_keys(normalized)
):
return {
"accepted": True,
"persist": True,
"recognized": True,
"message": (
f"Note: `{requested}` was not found in the live /v1/models listing "
f"but exists in the curated catalog — accepted."
),
}
return {
"accepted": False,