Commit graph

4 commits

Author SHA1 Message Date
Hermes Bot
0750da5b37 fix(models): structural OpenRouter free-tier visibility — live fetch + augment fallback (#1426)
Augments @bergeouss's PR #1548 v2 with the structural fix the issue
actually requested. The original PR added 5 hardcoded entries to
_FALLBACK_MODELS which would rot fast as OpenRouter's free-tier roster
turns over monthly.

Adds proper live-fetch logic to the OpenRouter group population so the
free-tier list stays fresh without requiring a code release every time
a new free model lands.

api/config.py:2120 — replaces the static _FALLBACK_MODELS slice with:

  1. Live curated catalog via hermes_cli.models.fetch_openrouter_models()
     — applies the tool-support filter (Kilo-Org/kilocode#9068).
  2. Free-tier live fetch — direct call to https://openrouter.ai/api/v1/models,
     filtered to free-tier-only (pricing.prompt == 0 AND pricing.completion
     == 0, OR :free suffix), bypasses the tool-support filter so newly-added
     free variants appear even before OpenRouter annotates them with tools.
     Capped at 30 entries to keep the picker usable.
  3. Defense-in-depth fallback to _FALLBACK_MODELS (which retains
     @bergeouss's hardcoded list for offline / test envs).
  4. Deduplication via seen_ids — model in both surfaces appears once.

5 new tests + 1 fixed test in tests/test_minimax_provider.py (scoped the
provider='MiniMax' assertion to direct-MiniMax routes by filtering for
'minimax/' prefix and excluding ':free' since the OpenRouter free-tier
variant minimax/minimax-m2.5:free correctly carries provider='OpenRouter').

Co-authored-by: bergeouss <[email protected]>
2026-05-03 19:18:44 +00:00
Frank Song
b277e195fe Fix MiniMax China provider visibility 2026-04-29 15:50:32 +08:00
nesquena-hermes
2d8bccdd96
fix(tests): add autouse cache-isolation fixture to get_available_models test files
Fixes the CI failure introduced by #817: test_model_resolver::test_custom_endpoint_uses_model_config_api_key_for_model_discovery was failing with KeyError: 'auth' due to the 60s TTL cache in get_available_models() being populated by test_byok_model_dropdown.py tests that ran earlier. Added autouse _isolate_models_cache fixture to 5 test files. Full suite 1747/1747, QA harness green.
2026-04-21 17:41:05 -07:00
nesquena-hermes
75e6595e06
feat: add MiniMax M2.7 to fallback model list and fix env var detection — PR #650 by @octo-patch
MiniMax M2.7/highspeed added to _FALLBACK_MODELS. MINIMAX_API_KEY and MINIMAX_CN_API_KEY added to env scan tuple so os.environ is checked. 11 tests. Independent review by @nesquena confirmed correct, needed rebase only.
2026-04-18 07:18:20 +00:00