Spaces:
Running
Running
File size: 13,995 Bytes
5a87378 5c747ec 5a87378 67629a4 6bc04da 5a87378 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 | """Tests for CLI proxy env variable handling and backend validation.
Verifies that:
1. OPENAI_TARGET_API_URL and GEMINI_TARGET_API_URL env vars are read by `headroom proxy`
2. litellm-* backends are accepted by both CLI and argparse paths
"""
import os
from unittest.mock import patch
import pytest
click = pytest.importorskip("click")
pytest.importorskip("fastapi")
from click.testing import CliRunner # noqa: E402
from headroom.cli.main import main # noqa: E402
@pytest.fixture
def runner():
return CliRunner()
class TestCLIProxyEnvVars:
"""Test that the CLI proxy command reads API URL env vars."""
def test_headroom_host_from_env(self, runner):
"""HEADROOM_HOST env var should be passed to ProxyConfig."""
captured_config = {}
def mock_run_server(config):
captured_config["config"] = config
with patch("headroom.proxy.server.run_server", mock_run_server):
result = runner.invoke(
main,
["proxy"],
env={"HEADROOM_HOST": "0.0.0.0"},
catch_exceptions=False,
)
assert result.exit_code == 0, result.output
assert captured_config["config"].host == "0.0.0.0"
def test_headroom_port_from_env(self, runner):
"""HEADROOM_PORT env var should be passed to ProxyConfig."""
captured_config = {}
def mock_run_server(config):
captured_config["config"] = config
with patch("headroom.proxy.server.run_server", mock_run_server):
result = runner.invoke(
main,
["proxy"],
env={"HEADROOM_PORT": "9797"},
catch_exceptions=False,
)
assert result.exit_code == 0, result.output
assert captured_config["config"].port == 9797
def test_headroom_budget_from_env(self, runner):
"""HEADROOM_BUDGET env var should be passed to ProxyConfig."""
captured_config = {}
def mock_run_server(config):
captured_config["config"] = config
with patch("headroom.proxy.server.run_server", mock_run_server):
result = runner.invoke(
main,
["proxy"],
env={"HEADROOM_BUDGET": "100.5"},
catch_exceptions=False,
)
assert result.exit_code == 0, result.output
assert captured_config["config"].budget_limit_usd == 100.5
def test_openai_target_api_url_from_env(self, runner):
"""OPENAI_TARGET_API_URL env var should be passed to ProxyConfig."""
captured_config = {}
def mock_run_server(config):
captured_config["config"] = config
with patch("headroom.proxy.server.run_server", mock_run_server):
result = runner.invoke(
main,
["proxy"],
env={"OPENAI_TARGET_API_URL": "http://my-vllm:4000"},
catch_exceptions=False,
)
assert result.exit_code == 0, result.output
assert captured_config["config"].openai_api_url == "http://my-vllm:4000"
def test_gemini_target_api_url_from_env(self, runner):
"""GEMINI_TARGET_API_URL env var should be passed to ProxyConfig."""
captured_config = {}
def mock_run_server(config):
captured_config["config"] = config
with patch("headroom.proxy.server.run_server", mock_run_server):
result = runner.invoke(
main,
["proxy"],
env={"GEMINI_TARGET_API_URL": "http://my-gemini:5000"},
catch_exceptions=False,
)
assert result.exit_code == 0, result.output
assert captured_config["config"].gemini_api_url == "http://my-gemini:5000"
def test_openai_api_url_cli_flag(self, runner):
"""--openai-api-url CLI flag should take precedence."""
captured_config = {}
def mock_run_server(config):
captured_config["config"] = config
with patch("headroom.proxy.server.run_server", mock_run_server):
result = runner.invoke(
main,
["proxy", "--openai-api-url", "http://from-cli:4000"],
catch_exceptions=False,
)
assert result.exit_code == 0, result.output
assert captured_config["config"].openai_api_url == "http://from-cli:4000"
def test_cli_flag_overrides_env_var(self, runner):
"""CLI flag should take precedence over env var."""
captured_config = {}
def mock_run_server(config):
captured_config["config"] = config
with patch("headroom.proxy.server.run_server", mock_run_server):
result = runner.invoke(
main,
["proxy", "--openai-api-url", "http://from-cli:4000"],
env={"OPENAI_TARGET_API_URL": "http://from-env:4000"},
catch_exceptions=False,
)
assert result.exit_code == 0, result.output
assert captured_config["config"].openai_api_url == "http://from-cli:4000"
def test_no_env_var_defaults_to_none(self, runner):
"""Without env var or flag, openai_api_url should be None."""
captured_config = {}
def mock_run_server(config):
captured_config["config"] = config
# Ensure the env var is not set
env = {k: v for k, v in os.environ.items() if k != "OPENAI_TARGET_API_URL"}
with (
patch("headroom.proxy.server.run_server", mock_run_server),
patch.dict(os.environ, env, clear=True),
):
result = runner.invoke(
main,
["proxy"],
catch_exceptions=False,
)
assert result.exit_code == 0, result.output
assert captured_config["config"].openai_api_url is None
def test_both_api_urls_from_env(self, runner):
"""Both OPENAI and GEMINI target URLs can be set via env."""
captured_config = {}
def mock_run_server(config):
captured_config["config"] = config
with patch("headroom.proxy.server.run_server", mock_run_server):
result = runner.invoke(
main,
["proxy"],
env={
"OPENAI_TARGET_API_URL": "http://my-vllm:4000",
"GEMINI_TARGET_API_URL": "http://my-gemini:5000",
},
catch_exceptions=False,
)
assert result.exit_code == 0, result.output
assert captured_config["config"].openai_api_url == "http://my-vllm:4000"
assert captured_config["config"].gemini_api_url == "http://my-gemini:5000"
def test_retry_and_connect_timeout_cli_flags(self, runner):
"""Fast-fail CLI flags should map into ProxyConfig."""
captured_config = {}
def mock_run_server(config):
captured_config["config"] = config
with patch("headroom.proxy.server.run_server", mock_run_server):
result = runner.invoke(
main,
[
"proxy",
"--retry-max-attempts",
"1",
"--connect-timeout-seconds",
"3",
],
catch_exceptions=False,
)
assert result.exit_code == 0, result.output
assert captured_config["config"].retry_max_attempts == 1
assert captured_config["config"].connect_timeout_seconds == 3
def test_production_scaling_env_vars(self, runner):
captured = {}
def mock_run_server(config, **kwargs):
captured["config"] = config
captured["kwargs"] = kwargs
with patch("headroom.proxy.server.run_server", mock_run_server):
result = runner.invoke(
main,
["proxy"],
env={
"HEADROOM_WORKERS": "4",
"HEADROOM_LIMIT_CONCURRENCY": "250",
"HEADROOM_MAX_CONNECTIONS": "200",
"HEADROOM_MAX_KEEPALIVE": "50",
},
catch_exceptions=False,
)
assert result.exit_code == 0, result.output
assert captured["config"].max_connections == 200
assert captured["config"].max_keepalive_connections == 50
assert captured["kwargs"] == {"workers": 4, "limit_concurrency": 250}
def test_production_scaling_cli_flags_override_env_vars(self, runner):
captured = {}
def mock_run_server(config, **kwargs):
captured["config"] = config
captured["kwargs"] = kwargs
with patch("headroom.proxy.server.run_server", mock_run_server):
result = runner.invoke(
main,
[
"proxy",
"--workers",
"3",
"--limit-concurrency",
"125",
"--max-connections",
"150",
"--max-keepalive",
"25",
],
env={
"HEADROOM_WORKERS": "4",
"HEADROOM_LIMIT_CONCURRENCY": "250",
"HEADROOM_MAX_CONNECTIONS": "200",
"HEADROOM_MAX_KEEPALIVE": "50",
},
catch_exceptions=False,
)
assert result.exit_code == 0, result.output
assert captured["config"].max_connections == 150
assert captured["config"].max_keepalive_connections == 25
assert captured["kwargs"] == {"workers": 3, "limit_concurrency": 125}
class TestCLIProxyBackend:
"""Test that litellm-* backends are accepted by the CLI."""
def test_litellm_hosted_vllm_backend_accepted(self, runner):
"""--backend litellm-hosted_vllm should be accepted (not rejected)."""
captured_config = {}
def mock_run_server(config):
captured_config["config"] = config
with patch("headroom.proxy.server.run_server", mock_run_server):
result = runner.invoke(
main,
["proxy", "--backend", "litellm-hosted_vllm"],
catch_exceptions=False,
)
assert result.exit_code == 0, result.output
assert captured_config["config"].backend == "litellm-hosted_vllm"
def test_litellm_vertex_backend_accepted(self, runner):
"""--backend litellm-vertex should be accepted."""
captured_config = {}
def mock_run_server(config):
captured_config["config"] = config
with patch("headroom.proxy.server.run_server", mock_run_server):
result = runner.invoke(
main,
["proxy", "--backend", "litellm-vertex"],
catch_exceptions=False,
)
assert result.exit_code == 0, result.output
assert captured_config["config"].backend == "litellm-vertex"
def test_litellm_backend_with_openai_url(self, runner):
"""Full vLLM setup: litellm backend + OPENAI_TARGET_API_URL."""
captured_config = {}
def mock_run_server(config):
captured_config["config"] = config
with patch("headroom.proxy.server.run_server", mock_run_server):
result = runner.invoke(
main,
[
"proxy",
"--backend",
"litellm-hosted_vllm",
"--openai-api-url",
"http://my-vllm:4000",
],
catch_exceptions=False,
)
assert result.exit_code == 0, result.output
assert captured_config["config"].backend == "litellm-hosted_vllm"
assert captured_config["config"].openai_api_url == "http://my-vllm:4000"
class TestCLIAnyllmProviderEnv:
"""Test that HEADROOM_ANYLLM_PROVIDER env var is read by the CLI."""
def test_anyllm_provider_from_env(self, runner):
"""HEADROOM_ANYLLM_PROVIDER env var should override the default."""
captured_config = {}
def mock_run_server(config):
captured_config["config"] = config
with patch("headroom.proxy.server.run_server", mock_run_server):
result = runner.invoke(
main,
["proxy", "--backend", "anyllm"],
env={"HEADROOM_ANYLLM_PROVIDER": "llamacpp"},
catch_exceptions=False,
)
assert result.exit_code == 0, result.output
assert captured_config["config"].anyllm_provider == "llamacpp"
def test_anyllm_provider_cli_flag_works(self, runner):
"""--anyllm-provider flag should still work."""
captured_config = {}
def mock_run_server(config):
captured_config["config"] = config
with patch("headroom.proxy.server.run_server", mock_run_server):
result = runner.invoke(
main,
["proxy", "--backend", "anyllm", "--anyllm-provider", "groq"],
catch_exceptions=False,
)
assert result.exit_code == 0, result.output
assert captured_config["config"].anyllm_provider == "groq"
class TestArgparseBackendValidation:
"""Test that the argparse path (python -m headroom.proxy.server) accepts litellm-* backends."""
def test_argparse_accepts_litellm_backend(self):
"""The argparse --backend should accept litellm-hosted_vllm (no choices restriction)."""
import argparse
# Recreate the parser matching server.py's main() argparse setup
# We just need to verify argparse doesn't reject litellm-* values
parser = argparse.ArgumentParser()
parser.add_argument("--backend", default="anthropic")
args = parser.parse_args(["--backend", "litellm-hosted_vllm"])
assert args.backend == "litellm-hosted_vllm"
|