mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-04-25 00:51:20 +00:00
c6b1ef4e58
Adds a first-class 'stepfun' API-key provider surfaced as Step Plan: - Support Step Plan setup for both International and China regions - Discover Step Plan models live from /step_plan/v1/models, with a small coding-focused fallback catalog when discovery is unavailable - Thread StepFun through provider metadata, setup persistence, status and doctor output, auxiliary routing, and model normalization - Add tests for provider resolution, model validation, metadata mapping, and StepFun region/model persistence Based on #6005 by @hengm3467. Co-authored-by: hengm3467 <100685635+hengm3467@users.noreply.github.com>
287 lines
10 KiB
Python
287 lines
10 KiB
Python
"""Tests for agent.models_dev — models.dev registry integration."""
|
|
import json
|
|
from unittest.mock import patch, MagicMock
|
|
|
|
import pytest
|
|
from agent.models_dev import (
|
|
PROVIDER_TO_MODELS_DEV,
|
|
_extract_context,
|
|
fetch_models_dev,
|
|
get_model_capabilities,
|
|
lookup_models_dev_context,
|
|
)
|
|
|
|
|
|
SAMPLE_REGISTRY = {
|
|
"anthropic": {
|
|
"id": "anthropic",
|
|
"name": "Anthropic",
|
|
"models": {
|
|
"claude-opus-4-6": {
|
|
"id": "claude-opus-4-6",
|
|
"limit": {"context": 1000000, "output": 128000},
|
|
},
|
|
"claude-sonnet-4-6": {
|
|
"id": "claude-sonnet-4-6",
|
|
"limit": {"context": 1000000, "output": 64000},
|
|
},
|
|
"claude-sonnet-4-0": {
|
|
"id": "claude-sonnet-4-0",
|
|
"limit": {"context": 200000, "output": 64000},
|
|
},
|
|
},
|
|
},
|
|
"github-copilot": {
|
|
"id": "github-copilot",
|
|
"name": "GitHub Copilot",
|
|
"models": {
|
|
"claude-opus-4.6": {
|
|
"id": "claude-opus-4.6",
|
|
"limit": {"context": 128000, "output": 32000},
|
|
},
|
|
},
|
|
},
|
|
"kilo": {
|
|
"id": "kilo",
|
|
"name": "Kilo Gateway",
|
|
"models": {
|
|
"anthropic/claude-sonnet-4.6": {
|
|
"id": "anthropic/claude-sonnet-4.6",
|
|
"limit": {"context": 1000000, "output": 128000},
|
|
},
|
|
},
|
|
},
|
|
"deepseek": {
|
|
"id": "deepseek",
|
|
"name": "DeepSeek",
|
|
"models": {
|
|
"deepseek-chat": {
|
|
"id": "deepseek-chat",
|
|
"limit": {"context": 128000, "output": 8192},
|
|
},
|
|
},
|
|
},
|
|
"audio-only": {
|
|
"id": "audio-only",
|
|
"models": {
|
|
"tts-model": {
|
|
"id": "tts-model",
|
|
"limit": {"context": 0, "output": 0},
|
|
},
|
|
},
|
|
},
|
|
}
|
|
|
|
|
|
class TestProviderMapping:
|
|
def test_all_mapped_providers_are_strings(self):
|
|
for hermes_id, mdev_id in PROVIDER_TO_MODELS_DEV.items():
|
|
assert isinstance(hermes_id, str)
|
|
assert isinstance(mdev_id, str)
|
|
|
|
def test_known_providers_mapped(self):
|
|
assert PROVIDER_TO_MODELS_DEV["anthropic"] == "anthropic"
|
|
assert PROVIDER_TO_MODELS_DEV["copilot"] == "github-copilot"
|
|
assert PROVIDER_TO_MODELS_DEV["stepfun"] == "stepfun"
|
|
assert PROVIDER_TO_MODELS_DEV["kilocode"] == "kilo"
|
|
assert PROVIDER_TO_MODELS_DEV["ai-gateway"] == "vercel"
|
|
|
|
def test_unmapped_provider_not_in_dict(self):
|
|
assert "nous" not in PROVIDER_TO_MODELS_DEV
|
|
|
|
def test_openai_codex_mapped_to_openai(self):
|
|
assert PROVIDER_TO_MODELS_DEV["openai"] == "openai"
|
|
assert PROVIDER_TO_MODELS_DEV["openai-codex"] == "openai"
|
|
|
|
|
|
class TestExtractContext:
|
|
def test_valid_entry(self):
|
|
assert _extract_context({"limit": {"context": 128000}}) == 128000
|
|
|
|
def test_zero_context_returns_none(self):
|
|
assert _extract_context({"limit": {"context": 0}}) is None
|
|
|
|
def test_missing_limit_returns_none(self):
|
|
assert _extract_context({"id": "test"}) is None
|
|
|
|
def test_missing_context_returns_none(self):
|
|
assert _extract_context({"limit": {"output": 8192}}) is None
|
|
|
|
def test_non_dict_returns_none(self):
|
|
assert _extract_context("not a dict") is None
|
|
|
|
def test_float_context_coerced_to_int(self):
|
|
assert _extract_context({"limit": {"context": 131072.0}}) == 131072
|
|
|
|
|
|
class TestLookupModelsDevContext:
|
|
@patch("agent.models_dev.fetch_models_dev")
|
|
def test_exact_match(self, mock_fetch):
|
|
mock_fetch.return_value = SAMPLE_REGISTRY
|
|
assert lookup_models_dev_context("anthropic", "claude-opus-4-6") == 1000000
|
|
|
|
@patch("agent.models_dev.fetch_models_dev")
|
|
def test_case_insensitive_match(self, mock_fetch):
|
|
mock_fetch.return_value = SAMPLE_REGISTRY
|
|
assert lookup_models_dev_context("anthropic", "Claude-Opus-4-6") == 1000000
|
|
|
|
@patch("agent.models_dev.fetch_models_dev")
|
|
def test_provider_not_mapped(self, mock_fetch):
|
|
mock_fetch.return_value = SAMPLE_REGISTRY
|
|
assert lookup_models_dev_context("nous", "some-model") is None
|
|
|
|
@patch("agent.models_dev.fetch_models_dev")
|
|
def test_model_not_found(self, mock_fetch):
|
|
mock_fetch.return_value = SAMPLE_REGISTRY
|
|
assert lookup_models_dev_context("anthropic", "nonexistent-model") is None
|
|
|
|
@patch("agent.models_dev.fetch_models_dev")
|
|
def test_provider_aware_context(self, mock_fetch):
|
|
"""Same model, different context per provider."""
|
|
mock_fetch.return_value = SAMPLE_REGISTRY
|
|
# Anthropic direct: 1M
|
|
assert lookup_models_dev_context("anthropic", "claude-opus-4-6") == 1000000
|
|
# GitHub Copilot: only 128K for same model
|
|
assert lookup_models_dev_context("copilot", "claude-opus-4.6") == 128000
|
|
|
|
@patch("agent.models_dev.fetch_models_dev")
|
|
def test_zero_context_filtered(self, mock_fetch):
|
|
mock_fetch.return_value = SAMPLE_REGISTRY
|
|
# audio-only is not a mapped provider, but test the filtering directly
|
|
data = SAMPLE_REGISTRY["audio-only"]["models"]["tts-model"]
|
|
assert _extract_context(data) is None
|
|
|
|
@patch("agent.models_dev.fetch_models_dev")
|
|
def test_empty_registry(self, mock_fetch):
|
|
mock_fetch.return_value = {}
|
|
assert lookup_models_dev_context("anthropic", "claude-opus-4-6") is None
|
|
|
|
|
|
class TestFetchModelsDev:
|
|
@patch("agent.models_dev.requests.get")
|
|
def test_fetch_success(self, mock_get):
|
|
mock_resp = MagicMock()
|
|
mock_resp.status_code = 200
|
|
mock_resp.json.return_value = SAMPLE_REGISTRY
|
|
mock_resp.raise_for_status = MagicMock()
|
|
mock_get.return_value = mock_resp
|
|
|
|
# Clear caches
|
|
import agent.models_dev as md
|
|
md._models_dev_cache = {}
|
|
md._models_dev_cache_time = 0
|
|
|
|
with patch.object(md, "_save_disk_cache"):
|
|
result = fetch_models_dev(force_refresh=True)
|
|
|
|
assert "anthropic" in result
|
|
assert len(result) == len(SAMPLE_REGISTRY)
|
|
|
|
@patch("agent.models_dev.requests.get")
|
|
def test_fetch_failure_returns_stale_cache(self, mock_get):
|
|
mock_get.side_effect = Exception("network error")
|
|
|
|
import agent.models_dev as md
|
|
md._models_dev_cache = SAMPLE_REGISTRY
|
|
md._models_dev_cache_time = 0 # expired
|
|
|
|
with patch.object(md, "_load_disk_cache", return_value=SAMPLE_REGISTRY):
|
|
result = fetch_models_dev(force_refresh=True)
|
|
|
|
assert "anthropic" in result
|
|
|
|
@patch("agent.models_dev.requests.get")
|
|
def test_in_memory_cache_used(self, mock_get):
|
|
import agent.models_dev as md
|
|
import time
|
|
md._models_dev_cache = SAMPLE_REGISTRY
|
|
md._models_dev_cache_time = time.time() # fresh
|
|
|
|
result = fetch_models_dev()
|
|
mock_get.assert_not_called()
|
|
assert result == SAMPLE_REGISTRY
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# get_model_capabilities — vision via modalities.input
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
CAPS_REGISTRY = {
|
|
"google": {
|
|
"id": "google",
|
|
"models": {
|
|
"gemma-4-31b-it": {
|
|
"id": "gemma-4-31b-it",
|
|
"attachment": False,
|
|
"tool_call": True,
|
|
"modalities": {"input": ["text", "image"]},
|
|
"limit": {"context": 128000, "output": 8192},
|
|
},
|
|
"gemma-3-1b": {
|
|
"id": "gemma-3-1b",
|
|
"tool_call": True,
|
|
"limit": {"context": 32000, "output": 8192},
|
|
},
|
|
},
|
|
},
|
|
"anthropic": {
|
|
"id": "anthropic",
|
|
"models": {
|
|
"claude-sonnet-4": {
|
|
"id": "claude-sonnet-4",
|
|
"attachment": True,
|
|
"tool_call": True,
|
|
"limit": {"context": 200000, "output": 64000},
|
|
},
|
|
},
|
|
},
|
|
}
|
|
|
|
|
|
class TestGetModelCapabilities:
|
|
"""Tests for get_model_capabilities vision detection."""
|
|
|
|
def test_vision_from_attachment_flag(self):
|
|
"""Models with attachment=True should report supports_vision=True."""
|
|
with patch("agent.models_dev.fetch_models_dev", return_value=CAPS_REGISTRY):
|
|
caps = get_model_capabilities("anthropic", "claude-sonnet-4")
|
|
assert caps is not None
|
|
assert caps.supports_vision is True
|
|
|
|
def test_vision_from_modalities_input_image(self):
|
|
"""Models with 'image' in modalities.input but attachment=False should
|
|
still report supports_vision=True (the core fix in this PR)."""
|
|
with patch("agent.models_dev.fetch_models_dev", return_value=CAPS_REGISTRY):
|
|
caps = get_model_capabilities("google", "gemma-4-31b-it")
|
|
assert caps is not None
|
|
assert caps.supports_vision is True
|
|
|
|
def test_no_vision_without_attachment_or_modalities(self):
|
|
"""Models with neither attachment nor image modality should be non-vision."""
|
|
with patch("agent.models_dev.fetch_models_dev", return_value=CAPS_REGISTRY):
|
|
caps = get_model_capabilities("google", "gemma-3-1b")
|
|
assert caps is not None
|
|
assert caps.supports_vision is False
|
|
|
|
def test_modalities_non_dict_handled(self):
|
|
"""Non-dict modalities field should not crash."""
|
|
registry = {
|
|
"google": {"id": "google", "models": {
|
|
"weird-model": {
|
|
"id": "weird-model",
|
|
"modalities": "text", # not a dict
|
|
"limit": {"context": 200000, "output": 8192},
|
|
},
|
|
}},
|
|
}
|
|
with patch("agent.models_dev.fetch_models_dev", return_value=registry):
|
|
caps = get_model_capabilities("gemini", "weird-model")
|
|
assert caps is not None
|
|
assert caps.supports_vision is False
|
|
|
|
def test_model_not_found_returns_none(self):
|
|
"""Unknown model should return None."""
|
|
with patch("agent.models_dev.fetch_models_dev", return_value=CAPS_REGISTRY):
|
|
caps = get_model_capabilities("anthropic", "nonexistent-model")
|
|
assert caps is None
|