mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-01 12:02:05 +00:00
fix(models): live-first merge + update opencode-zen catalog + uncap aggregator picker
This commit is contained in:
Afnath Ahamed
Teknium
parent
2e7e600eaa
commit
f98ffbc246
5 changed files with 110 additions and 26 deletions
|
|
@ -44,6 +44,11 @@ from agent.models_dev import (
|
|||
list_provider_models,
|
||||
)
|
||||
|
||||
# Providers whose picker model list should NOT be capped by max_models.
|
||||
# OpenCode Zen is an aggregator whose full catalog must be visible so
|
||||
# users can pick any model they have access to.
|
||||
_UNCAPPED_PICKER_PROVIDERS: frozenset[str] = frozenset({"opencode-zen"})
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
|
|
@ -1650,7 +1655,10 @@ def list_authenticated_providers(
|
|||
if hermes_id in _MODELS_DEV_PREFERRED:
|
||||
model_ids = _merge_with_models_dev(hermes_id, model_ids)
|
||||
total = len(model_ids)
|
||||
top = model_ids[:max_models] if max_models is not None else model_ids
|
||||
if hermes_id in _UNCAPPED_PICKER_PROVIDERS:
|
||||
top = model_ids # Aggregator: show full catalog regardless of max_models
|
||||
else:
|
||||
top = model_ids[:max_models] if max_models is not None else model_ids
|
||||
|
||||
slug = hermes_id
|
||||
pinfo = _mdev_pinfo(mdev_id)
|
||||
|
|
@ -1813,7 +1821,10 @@ def list_authenticated_providers(
|
|||
if hermes_slug in _MODELS_DEV_PREFERRED:
|
||||
model_ids = _merge_with_models_dev(hermes_slug, model_ids)
|
||||
total = len(model_ids)
|
||||
top = model_ids[:max_models] if max_models is not None else model_ids
|
||||
if hermes_slug in _UNCAPPED_PICKER_PROVIDERS:
|
||||
top = model_ids # Aggregator: show full catalog regardless of max_models
|
||||
else:
|
||||
top = model_ids[:max_models] if max_models is not None else model_ids
|
||||
|
||||
results.append({
|
||||
"slug": hermes_slug,
|
||||
|
|
|
|||
|
|
@ -381,9 +381,15 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
|
|||
],
|
||||
"opencode-zen": [
|
||||
"kimi-k2.5",
|
||||
"kimi-k2.6",
|
||||
"gpt-5.5",
|
||||
"gpt-5.5-pro",
|
||||
"gpt-5.4-pro",
|
||||
"gpt-5.4",
|
||||
"gpt-5.4-mini",
|
||||
"gpt-5.4-nano",
|
||||
"gpt-5.3-codex",
|
||||
"gpt-5.3-codex-spark",
|
||||
"gpt-5.2",
|
||||
"gpt-5.2-codex",
|
||||
"gpt-5.1",
|
||||
|
|
@ -393,6 +399,9 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
|
|||
"gpt-5",
|
||||
"gpt-5-codex",
|
||||
"gpt-5-nano",
|
||||
"claude-fable-5",
|
||||
"claude-opus-4-8",
|
||||
"claude-opus-4-7",
|
||||
"claude-opus-4-6",
|
||||
"claude-opus-4-5",
|
||||
"claude-opus-4-1",
|
||||
|
|
@ -400,21 +409,25 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
|
|||
"claude-sonnet-4-5",
|
||||
"claude-sonnet-4",
|
||||
"claude-haiku-4-5",
|
||||
"claude-3-5-haiku",
|
||||
"gemini-3.5-flash",
|
||||
"gemini-3.1-pro",
|
||||
"gemini-3-pro",
|
||||
"gemini-3-flash",
|
||||
"minimax-m2.7",
|
||||
"minimax-m2.5",
|
||||
"minimax-m2.5-free",
|
||||
"minimax-m2.1",
|
||||
"minimax-m3-free",
|
||||
"glm-5.1",
|
||||
"glm-5",
|
||||
"glm-4.7",
|
||||
"glm-4.6",
|
||||
"kimi-k2-thinking",
|
||||
"kimi-k2",
|
||||
"qwen3-coder",
|
||||
"deepseek-v4-pro",
|
||||
"deepseek-v4-flash",
|
||||
"deepseek-v4-flash-free",
|
||||
"qwen3.6-plus",
|
||||
"qwen3.6-plus-free",
|
||||
"qwen3.5-plus",
|
||||
"grok-build-0.1",
|
||||
"big-pickle",
|
||||
"mimo-v2.5-free",
|
||||
"north-mini-code-free",
|
||||
"nemotron-3-ultra-free",
|
||||
],
|
||||
"opencode-go": [
|
||||
"kimi-k2.6",
|
||||
|
|
@ -2420,15 +2433,24 @@ def provider_model_ids(provider: Optional[str], *, force_refresh: bool = False)
|
|||
# Merge static curated list with live API results so
|
||||
# models that the live endpoint omits (stale cache,
|
||||
# partial rollout) still appear in the picker.
|
||||
# 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)
|
||||
# Live API entries come first (the provider's authoritative
|
||||
# catalog), then curated-only entries are appended for
|
||||
# discovery — models that the live endpoint hasn't caught up
|
||||
# on still surface, but models the provider no longer serves
|
||||
# (stale curated entries) don't pollute the top of the picker.
|
||||
#
|
||||
# Design note: Single providers (kimi, zai) use curated-first
|
||||
# (commit 658ac1d86) to surface newest models even when live
|
||||
# API lags (#46309). However, aggregators like OpenCode Zen
|
||||
# have a live API as their authoritative catalog — the curated
|
||||
# list is just a fallback for models the live endpoint hasn't
|
||||
# caught up on. For aggregators, live-first prevents stale
|
||||
# curated entries from polluting the picker. (#46850)
|
||||
curated = list(_PROVIDER_MODELS.get(normalized, []))
|
||||
if curated:
|
||||
merged = list(curated)
|
||||
merged_lower = {m.lower() for m in curated}
|
||||
for m in live:
|
||||
merged = list(live)
|
||||
merged_lower = {m.lower() for m in live}
|
||||
for m in curated:
|
||||
if m.lower() not in merged_lower:
|
||||
merged.append(m)
|
||||
merged_lower.add(m.lower())
|
||||
|
|
|
|||
|
|
@ -114,8 +114,8 @@ class TestProviderModelIdsPreferred:
|
|||
patch("providers.base.ProviderProfile.fetch_models", return_value=["kimi-k2.6"]),
|
||||
):
|
||||
out = provider_model_ids("kimi-coding")
|
||||
# Curated-first order; curated newest (k2.7-code) stays ahead of live.
|
||||
assert out[:2] == ["kimi-k2.7-code", "kimi-k2.6"]
|
||||
# Live-first order; live entry (k2.6) comes before curated-only (k2.7-code).
|
||||
assert out[:2] == ["kimi-k2.6", "kimi-k2.7-code"]
|
||||
|
||||
def test_kimi_setup_flow_uses_same_coding_plan_catalog(self):
|
||||
"""The setup wizard must not carry a stale duplicate Kimi model list."""
|
||||
|
|
|
|||
51
tests/hermes_cli/test_opencode_zen_model_limit.py
Normal file
51
tests/hermes_cli/test_opencode_zen_model_limit.py
Normal file
|
|
@ -0,0 +1,51 @@
|
|||
"""Regression tests for OpenCode Zen model picker limits."""
|
||||
|
||||
import os
|
||||
from unittest.mock import patch
|
||||
|
||||
import hermes_cli.providers as providers_mod
|
||||
from hermes_cli.model_switch import list_authenticated_providers
|
||||
|
||||
|
||||
def test_opencode_zen_lists_all_models_while_other_providers_remain_capped(monkeypatch):
|
||||
"""OpenCode Zen is an aggregator product, so the picker must expose its full catalog."""
|
||||
zen_models = [f"zen-model-{i}" for i in range(57)]
|
||||
deepseek_models = [f"deepseek-model-{i}" for i in range(57)]
|
||||
|
||||
monkeypatch.setattr(
|
||||
"agent.models_dev.PROVIDER_TO_MODELS_DEV",
|
||||
{
|
||||
"opencode-zen": "opencode",
|
||||
"deepseek": "deepseek",
|
||||
},
|
||||
)
|
||||
monkeypatch.setattr(
|
||||
"agent.models_dev.fetch_models_dev",
|
||||
lambda: {"opencode": {}, "deepseek": {}},
|
||||
)
|
||||
monkeypatch.setattr(providers_mod, "HERMES_OVERLAYS", {})
|
||||
monkeypatch.setattr(
|
||||
"hermes_cli.models.cached_provider_model_ids",
|
||||
lambda provider: {
|
||||
"opencode-zen": zen_models,
|
||||
"deepseek": deepseek_models,
|
||||
}.get(provider, []),
|
||||
)
|
||||
|
||||
with patch.dict(
|
||||
os.environ,
|
||||
{
|
||||
"OPENCODE_ZEN_API_KEY": "test-zen-key",
|
||||
"DEEPSEEK_API_KEY": "test-deepseek-key",
|
||||
},
|
||||
clear=False,
|
||||
):
|
||||
providers = list_authenticated_providers(max_models=50)
|
||||
|
||||
opencode_zen = next(p for p in providers if p["slug"] == "opencode-zen")
|
||||
deepseek = next(p for p in providers if p["slug"] == "deepseek")
|
||||
|
||||
assert opencode_zen["models"] == zen_models
|
||||
assert opencode_zen["total_models"] == len(zen_models)
|
||||
assert deepseek["models"] == deepseek_models[:50]
|
||||
assert deepseek["total_models"] == len(deepseek_models)
|
||||
|
|
@ -23,7 +23,7 @@ class TestGenericProviderLiveCuratedMerge:
|
|||
return p
|
||||
|
||||
def test_live_models_merged_with_curated(self):
|
||||
"""Curated models come first; live-only models are appended."""
|
||||
"""Live models come first; curated-only models are appended."""
|
||||
live = ["glm-5.2", "glm-5.1", "glm-5"]
|
||||
curated = _PROVIDER_MODELS["zai"] # includes glm-5.1, glm-5, glm-4.5, etc.
|
||||
profile = self._make_profile(live)
|
||||
|
|
@ -34,9 +34,9 @@ class TestGenericProviderLiveCuratedMerge:
|
|||
):
|
||||
result = provider_model_ids("zai")
|
||||
|
||||
# Curated entries first, in catalog order (keeps newest curated models
|
||||
# like glm-5.2 at the top of the picker — see #46309).
|
||||
assert result[: len(curated)] == list(curated)
|
||||
# Live entries first (provider's authoritative catalog),
|
||||
# curated-only entries appended afterwards.
|
||||
assert result[: len(live)] == list(live)
|
||||
assert result[0] == "glm-5.2"
|
||||
# Models present in both live and curated are not duplicated.
|
||||
assert result.count("glm-5.2") == 1
|
||||
|
|
@ -76,8 +76,8 @@ class TestGenericProviderLiveCuratedMerge:
|
|||
):
|
||||
result = provider_model_ids("zai")
|
||||
|
||||
# Curated-first: curated casing wins for models present in both.
|
||||
assert result == ["glm-5.1", "GLM-5", "glm-4.5"]
|
||||
# Live-first: live casing wins for models present in both.
|
||||
assert result == ["GLM-5.1", "glm-5", "glm-4.5"]
|
||||
|
||||
def test_empty_curated_returns_live_only(self):
|
||||
"""When no curated list exists, live is returned as-is."""
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue