Spaces:
Build error
Build error
File size: 13,248 Bytes
905c229 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 | """Tests for provider model fallback and configuration."""
import json
import os
import tempfile
from pathlib import Path
from unittest.mock import patch
import pytest
from headroom.providers.anthropic import (
AnthropicProvider,
_infer_model_tier,
)
from headroom.providers.anthropic import (
_load_custom_model_config as anthropic_load_config,
)
from headroom.providers.openai import (
OpenAIProvider,
_infer_model_family,
)
from headroom.providers.openai import (
_load_custom_model_config as openai_load_config,
)
class TestAnthropicModelFallback:
"""Tests for Anthropic provider model fallback."""
def test_known_claude_4_models(self):
"""Test that Claude 4/4.5 models are recognized."""
provider = AnthropicProvider()
# Claude Opus 4.5
assert provider.get_context_limit("claude-opus-4-5-20251101") == 200000
assert provider.supports_model("claude-opus-4-5-20251101")
# Claude Sonnet 4
assert provider.get_context_limit("claude-sonnet-4-20250514") == 200000
assert provider.supports_model("claude-sonnet-4-20250514")
# Claude Haiku 4
assert provider.get_context_limit("claude-haiku-4-5-20251001") == 200000
assert provider.supports_model("claude-haiku-4-5-20251001")
def test_pattern_based_inference_opus(self):
"""Test pattern-based inference for opus models."""
provider = AnthropicProvider()
# Future opus model should infer 200K and opus pricing
limit = provider.get_context_limit("claude-opus-5-20260101")
assert limit == 200000
pricing = provider._get_pricing("claude-opus-5-20260101")
assert pricing["input"] == 15.00
assert pricing["output"] == 75.00
def test_pattern_based_inference_sonnet(self):
"""Test pattern-based inference for sonnet models."""
provider = AnthropicProvider()
limit = provider.get_context_limit("claude-sonnet-5-20260101")
assert limit == 200000
pricing = provider._get_pricing("claude-sonnet-5-20260101")
assert pricing["input"] == 3.00
assert pricing["output"] == 15.00
def test_pattern_based_inference_haiku(self):
"""Test pattern-based inference for haiku models."""
provider = AnthropicProvider()
limit = provider.get_context_limit("claude-haiku-5-20260101")
assert limit == 200000
pricing = provider._get_pricing("claude-haiku-5-20260101")
assert pricing["input"] == 0.80
assert pricing["output"] == 4.00
def test_unknown_claude_model_fallback(self):
"""Test fallback for unknown Claude models."""
provider = AnthropicProvider()
# Unknown Claude model should get 200K default
limit = provider.get_context_limit("claude-unknown-model")
assert limit == 200000
# Should still support it
assert provider.supports_model("claude-unknown-model")
def test_no_exception_for_unknown_model(self):
"""Test that unknown models don't raise exceptions."""
provider = AnthropicProvider()
# Should not raise
limit = provider.get_context_limit("claude-future-model-xyz")
assert limit > 0
def test_infer_model_tier(self):
"""Test model tier inference."""
assert _infer_model_tier("claude-opus-4-5-20251101") == "opus"
assert _infer_model_tier("claude-sonnet-4-20250514") == "sonnet"
assert _infer_model_tier("claude-haiku-4-5-20251001") == "haiku"
assert _infer_model_tier("claude-3-5-sonnet-latest") == "sonnet"
assert _infer_model_tier("CLAUDE-OPUS-FUTURE") == "opus" # Case insensitive
assert _infer_model_tier("some-other-model") is None
def test_explicit_context_limits_override(self):
"""Test that explicit context_limits override defaults."""
provider = AnthropicProvider(context_limits={"custom-model": 500000})
assert provider.get_context_limit("custom-model") == 500000
def test_pricing_for_known_models(self):
"""Test pricing retrieval for known models."""
provider = AnthropicProvider()
# Claude Opus 4.5
pricing = provider._get_pricing("claude-opus-4-5-20251101")
assert pricing["input"] == 15.00
assert pricing["output"] == 75.00
assert pricing["cached_input"] == 1.50
def test_cost_estimation_for_new_models(self):
"""Test cost estimation works for new models."""
provider = AnthropicProvider()
cost = provider.estimate_cost(
input_tokens=1000000,
output_tokens=100000,
model="claude-opus-4-5-20251101",
cached_tokens=0,
)
# $15/1M input + $75/1M * 0.1M output = $15 + $7.5 = $22.5
assert cost == pytest.approx(22.5, rel=0.01)
class TestAnthropicConfigLoading:
"""Tests for Anthropic config file/env var loading."""
def test_load_from_env_var_json(self):
"""Test loading config from JSON env var."""
config = {"context_limits": {"test-model": 300000}}
with patch.dict(os.environ, {"HEADROOM_MODEL_LIMITS": json.dumps(config)}):
loaded = anthropic_load_config()
assert loaded["context_limits"]["test-model"] == 300000
def test_load_from_env_var_file(self):
"""Test loading config from file path in env var."""
config = {"context_limits": {"file-model": 400000}}
with tempfile.NamedTemporaryFile(mode="w", suffix=".json", delete=False) as f:
json.dump(config, f)
f.flush()
with patch.dict(os.environ, {"HEADROOM_MODEL_LIMITS": f.name}):
loaded = anthropic_load_config()
assert loaded["context_limits"]["file-model"] == 400000
os.unlink(f.name)
def test_load_from_config_file(self):
"""Test loading from ~/.headroom/models.json."""
config = {
"anthropic": {
"context_limits": {"config-model": 250000},
"pricing": {"config-model": {"input": 5.0, "output": 25.0}},
}
}
with tempfile.TemporaryDirectory() as tmpdir:
config_dir = Path(tmpdir) / ".headroom"
config_dir.mkdir()
config_file = config_dir / "models.json"
config_file.write_text(json.dumps(config))
with patch.object(Path, "home", return_value=Path(tmpdir)):
loaded = anthropic_load_config()
assert loaded["context_limits"]["config-model"] == 250000
def test_env_var_overrides_config_file(self):
"""Test that env var takes precedence over config file."""
env_config = {"context_limits": {"test-model": 100000}}
file_config = {"anthropic": {"context_limits": {"test-model": 200000}}}
with tempfile.TemporaryDirectory() as tmpdir:
config_dir = Path(tmpdir) / ".headroom"
config_dir.mkdir()
config_file = config_dir / "models.json"
config_file.write_text(json.dumps(file_config))
with patch.object(Path, "home", return_value=Path(tmpdir)):
with patch.dict(os.environ, {"HEADROOM_MODEL_LIMITS": json.dumps(env_config)}):
loaded = anthropic_load_config()
# Env var should win
assert loaded["context_limits"]["test-model"] == 100000
class TestOpenAIModelFallback:
"""Tests for OpenAI provider model fallback."""
def test_known_models(self):
"""Test that known models work."""
provider = OpenAIProvider()
assert provider.get_context_limit("gpt-4o") == 128000
assert provider.get_context_limit("gpt-4o-mini") == 128000
assert provider.get_context_limit("o1") == 200000
assert provider.get_context_limit("o3-mini") == 200000
def test_pattern_based_inference_gpt4o(self):
"""Test pattern-based inference for gpt-4o models."""
provider = OpenAIProvider()
# Future gpt-4o model
limit = provider.get_context_limit("gpt-4o-2025-01-01")
assert limit == 128000
def test_pattern_based_inference_o1(self):
"""Test pattern-based inference for o1 models."""
provider = OpenAIProvider()
limit = provider.get_context_limit("o1-super-2025")
assert limit == 200000
def test_pattern_based_inference_o3(self):
"""Test pattern-based inference for o3 models."""
provider = OpenAIProvider()
limit = provider.get_context_limit("o3-large-2025")
assert limit == 200000
def test_unknown_model_fallback(self):
"""Test fallback for unknown models."""
provider = OpenAIProvider()
# Unknown model should get 128K default
limit = provider.get_context_limit("gpt-5-future")
assert limit == 128000
def test_no_exception_for_unknown_model(self):
"""Test that unknown models don't raise exceptions."""
provider = OpenAIProvider()
# Should not raise
limit = provider.get_context_limit("gpt-future-xyz")
assert limit > 0
def test_infer_model_family(self):
"""Test model family inference."""
assert _infer_model_family("gpt-4o-2024-11-20") == "gpt-4o"
assert _infer_model_family("gpt-4-turbo-preview") == "gpt-4-turbo"
assert _infer_model_family("gpt-4") == "gpt-4"
assert _infer_model_family("gpt-3.5-turbo") == "gpt-3.5"
assert _infer_model_family("o1-preview") == "o1"
assert _infer_model_family("o3-mini") == "o3"
assert _infer_model_family("unknown") is None
def test_explicit_context_limits_override(self):
"""Test that explicit context_limits override defaults."""
provider = OpenAIProvider(context_limits={"custom-model": 500000})
assert provider.get_context_limit("custom-model") == 500000
def test_supports_model_expanded(self):
"""Test that supports_model works for new patterns."""
provider = OpenAIProvider()
# Should support any gpt-* or o1/o3
assert provider.supports_model("gpt-4o")
assert provider.supports_model("gpt-4o-future")
assert provider.supports_model("gpt-5-future")
assert provider.supports_model("o1-mega")
assert provider.supports_model("o3-ultra")
class TestOpenAIConfigLoading:
"""Tests for OpenAI config file/env var loading."""
def test_load_from_env_var_json(self):
"""Test loading config from JSON env var."""
config = {"openai": {"context_limits": {"test-model": 300000}}}
with patch.dict(os.environ, {"HEADROOM_MODEL_LIMITS": json.dumps(config)}):
loaded = openai_load_config()
assert loaded["context_limits"]["test-model"] == 300000
def test_load_pricing_from_config(self):
"""Test loading pricing from config."""
config = {"openai": {"pricing": {"test-model": [5.0, 15.0]}}}
with tempfile.NamedTemporaryFile(mode="w", suffix=".json", delete=False) as f:
json.dump(config, f)
f.flush()
with patch.dict(os.environ, {"HEADROOM_MODEL_LIMITS": f.name}):
loaded = openai_load_config()
assert loaded["pricing"]["test-model"] == [5.0, 15.0]
os.unlink(f.name)
class TestCrossProviderConsistency:
"""Tests for consistency across providers."""
def test_both_providers_use_same_env_var(self):
"""Test that both providers use HEADROOM_MODEL_LIMITS."""
config = {
"anthropic": {"context_limits": {"anthropic-model": 100000}},
"openai": {"context_limits": {"openai-model": 200000}},
}
with patch.dict(os.environ, {"HEADROOM_MODEL_LIMITS": json.dumps(config)}):
anthropic = anthropic_load_config()
openai = openai_load_config()
assert anthropic["context_limits"]["anthropic-model"] == 100000
assert openai["context_limits"]["openai-model"] == 200000
def test_both_providers_never_raise_for_unknown_models(self):
"""Test that neither provider raises for unknown models."""
anthropic = AnthropicProvider()
openai = OpenAIProvider()
# Neither should raise
anthropic.get_context_limit("claude-future-model-xyz")
openai.get_context_limit("gpt-future-model-xyz")
def test_both_providers_warn_for_unknown_models(self, caplog):
"""Test that both providers warn for unknown models."""
import logging
# Clear warning caches
from headroom.providers import anthropic as anthropic_module
from headroom.providers import openai as openai_module
anthropic_module._UNKNOWN_MODEL_WARNINGS.clear()
openai_module._UNKNOWN_MODEL_WARNINGS.clear()
with caplog.at_level(logging.WARNING):
anthropic = AnthropicProvider()
anthropic.get_context_limit("claude-test-unknown-model")
openai = OpenAIProvider()
openai.get_context_limit("gpt-test-unknown-model")
assert "claude-test-unknown-model" in caplog.text
assert "gpt-test-unknown-model" in caplog.text
|