litellm/tests/test_litellm/proxy/test_proxy_cli.py

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

1634 lines
60 KiB
Python
Raw Permalink Normal View History

import os
import sys
from pathlib import Path
from types import SimpleNamespace
from unittest.mock import AsyncMock, MagicMock, patch
import click
import fastapi
import pytest
sys.path.insert(
0, os.path.abspath("../../..")
) # Adds the parent directory to the system-path
import builtins
import types
from litellm.proxy.proxy_cli import ProxyInitializationHelpers
[Release Fix] (#22411) * fix(lint): suppress PLR0915 for 3 complex methods that exceed 50-statement limit - streaming_iterator.py: _process_event (84 statements) - transformation.py: translate_messages_to_responses_input (51 statements) - transformation.py: transform_realtime_response (54 statements) Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> * fix(mypy): resolve type errors in public_endpoints, user_api_key_auth, common_utils, transformation - public_endpoints.py: fix _cached_endpoints type annotation - user_api_key_auth.py: accept Optional[str] for end_user_id parameter - common_utils.py: add NewProjectRequest/UpdateProjectRequest to Union type - transformation.py: add ChatCompletionRedactedThinkingBlock and list[Any] to content type Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> * fix(proxy-extras): bump version to 0.4.50 and sync schema - Bump litellm-proxy-extras from 0.4.49 to 0.4.50 - Sync schema.prisma with main proxy schema - Includes new LiteLLM_ClaudeCodePluginTable model - Includes new @@index([startTime, request_id]) on SpendLogs - Update version references in requirements.txt and pyproject.toml Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> * fix(router): use string id in test_add_deployment and add defensive str() in register_model - Change test to use string '100' instead of int 100 for model_info.id - Add str() conversion in register_model to prevent AttributeError on non-string keys Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> * fix(security): update minimatch to 10.2.4 to fix CVE-2026-27903 and CVE-2026-27904 - Run npm audit fix in docs/my-website - Updates minimatch from 10.2.1 to 10.2.4 (fixes HIGH severity ReDoS vulnerabilities) Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> * fix(test): update realtime guardrail test assertions to match actual guardrail behavior - test_text_message_blocked_by_guardrail_no_ai_response: allow guardrail's own block message text in response.done (previously expected empty content) - test_voice_transcript_blocked_by_guardrail: allow guardrail to send response.cancel + block message + response.create flow (previously expected no response.create) Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> * fix: revert proxy-extras version in requirements.txt and pyproject.toml The litellm-proxy-extras 0.4.50 is not published to PyPI yet, so consumer references must stay at 0.4.49. Only the source package pyproject.toml should be bumped to 0.4.50 for the publish_proxy_extras CI job. Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> * fix: make transcript delta check optional in voice guardrail test The guardrail sends an error event (guardrail_violation) when blocking voice transcripts; it does not always produce transcript deltas. Remove the assertion requiring response.audio_transcript.delta since the error event is the primary signal that blocked content was handled. Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> * Add missing env keys to documentation: LITELLM_MAX_STREAMING_DURATION_SECONDS and LITELLM_USE_CHAT_COMPLETIONS_URL_FOR_ANTHROPIC_MESSAGES These two environment variables were used in code but not documented in the environment variables reference section of config_settings.md, causing the test_env_keys.py CI test to fail. Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> * Fix 13 mypy type errors across 6 files - in_flight_requests_middleware.py: Fix type: ignore error codes from [union-attr] to [attr-defined], add [arg-type] for Gauge **kwargs - transformation.py: Add [assignment] ignore for output_format reassignment, add fallback empty string for tool use id to fix arg-type - responses/main.py: Remove redundant type annotation on second secret_fields assignment to fix no-redef - streaming_iterator.py: Add [assignment] ignores for intermediate cache token assignments - handler.py: Add [typeddict-item] ignore for AnthropicMessagesRequest construction from dict - public_endpoints.py: Add [arg-type] ignore for _load_endpoints() return type mismatch with SupportedEndpoint model Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> * fix: add auth overrides to spend tracking tests, fix realtime guardrail assertion, update UI minimatch - Add app.dependency_overrides for user_api_key_auth in 4 spend tracking tests that were returning 401 Unauthorized (error_code, error_message, error_code_and_key_alias, key_hash) - Fix realtime guardrail test to check ANY error event for guardrail_violation instead of just the first (OpenAI may send its own errors first) - Update ui/litellm-dashboard/package-lock.json to fix minimatch vulnerability Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> * Fix failing MCP e2e and create_mcp_server UI tests Test 1 (test_independent_clients_no_shared_session): - Add allow_all_keys: true to MCP servers in test config. With master_key and no DB, get_allowed_mcp_servers returned empty, causing 0 tools and 403 on tool calls. allow_all_keys bypasses per-key restrictions. - Add asyncio.sleep(0.5) between client connections to allow MCP SDK TaskGroup cleanup and avoid ExceptionGroup on connection close (MCP #915). Test 2 (create_mcp_server 'auth value is provided'): - Use userEvent.setup({ delay: null }) for instant keystrokes to avoid timeout from default typing delay on CI. - Increase per-test timeout to 15000ms for CI environments. Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> * fix: stabilize proxy unit tests for parallel execution - test_response_polling_handler: add xdist_group to prevent heavy import OOM - test_db_schema_migration: use temp dir for worker isolation, sync schema.prisma index - test_custom_tokenizer_bug: use lighter tokenizer to prevent OOM in parallel Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> * fix: add auth overrides to more spend tracking and model info tests - Fix test_ui_view_spend_logs_pagination missing auth override (401) - Fix test_view_spend_tags missing auth override (401) - Fix test_view_spend_tags_no_database missing auth override (401) - Fix test_empty_model_list.py to use app.dependency_overrides instead of patch() for FastAPI dependency injection auth Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> * fix(test): use patch.object for aiohttp transport test to work in parallel execution The @patch decorator was not intercepting the static method call in parallel xdist workers. Using patch.object on the directly-imported class is more reliable. Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> * fix(security): update minimatch from 10.2.1 to 10.2.4 in Dockerfile The Docker image was explicitly pinning minimatch@10.2.1 which has HIGH severity ReDoS vulnerabilities (GHSA-7r86-cg39-jmmj, GHSA-23c5-xmqv-rm74). Update to 10.2.4 which includes fixes for both CVEs. Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> * fix(ui): prevent MCP and TeamInfo test timeouts on CI - Add userEvent.setup({ delay: null }) to all tests using userEvent in both files - Add timeout: 15000 to tests with significant user interaction (typing, multiple clicks) - Fixes: create_mcp_server Bearer Token test, TeamInfo cancel button test Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> * fix: stabilize parallel test execution and aiohttp transport test - test_aiohttp_handler: rewrite transport test to not rely on static method mock (consistently fails in parallel xdist workers) - test_proxy_cli: add xdist_group to prevent timeout during heavy imports - test_swagger_chat_completions: add xdist_group to prevent timeout Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> * fix(security): add serialize-javascript override to fix GHSA-5c6j-r48x-rmvq Add npm override for serialize-javascript>=7.0.3 in docs/my-website to fix HIGH severity RCE vulnerability via RegExp.flags. Also bump minimatch override to >=10.2.4. Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> * Fix flaky tests: remove broken Vertex model, add retries for Anthropic - Remove vertex_ai/meta/llama-4-scout-17b-16e-instruct-maas from test_partner_models_httpx_streaming - consistently returns 400 BadRequest - Add @pytest.mark.flaky(retries=6, delay=10) to test_function_call_parsing for transient Anthropic API overload errors - Add @pytest.mark.flaky(retries=6, delay=10) to test_openai_stream_options_call for transient Anthropic InternalServerError Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> * fix(ci): add xdist_group(proxy_heavy) to prevent OOM in parallel proxy tests - Add pytestmark = pytest.mark.xdist_group('proxy_heavy') to test_proxy_utils.py - Change test_db_schema_migration.py from schema_migration to proxy_heavy group - Add @pytest.mark.xdist_group('proxy_heavy') to test_proxy_server.py::test_health Groups heavy proxy tests to run on same worker, avoiding worker OOM crashes. Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> * Fix vertex AI qwen global endpoint test to mock vertexai module import The test_vertex_ai_qwen_global_endpoint_url test was failing because the VertexAIPartnerModels.completion() method tries to 'import vertexai' before any of the mocked code runs. In environments without google-cloud-aiplatform installed, this import fails with a VertexAIError(status_code=400). Fix by: - Adding patch.dict('sys.modules', {'vertexai': MagicMock()}) to mock the vertexai module import - Adding vertex_ai_location parameter to the acompletion call for completeness Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> * fix(ci): add xdist_group to health endpoint and watsonx tests for parallel stability - test_health_liveliness_endpoint: add xdist_group('proxy_health') to prevent timeout - test_watsonx_gpt_oss tests: add xdist_group('watsonx_heavy') to prevent mock interference Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> * fix(test): pre-populate WatsonX IAM token cache to prevent parallel test interference The watsonx prompt transformation test was failing in parallel execution because litellm.module_level_client.post mock was being interfered with by other tests. Pre-populating the IAM token cache avoids the HTTP call entirely. Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> * fix(test): add spend data polling with retries for e2e pass-through tests - test_vertex_with_spend.test.js: Replace 15s fixed wait with polling loop (up to 6 attempts, 10s apart) for spend data to appear in DB - Increase test timeout from 25s to 90s to accommodate polling - base_anthropic_messages_tool_search_test.py: Add flaky(retries=3) for streaming test that depends on live Anthropic API Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> * fix(ci): reduce parallel workers from 8 to 4 for proxy tests to prevent OOM - litellm_proxy_unit_testing_part2: -n 8 -> -n 4 - litellm_mapped_tests_proxy_part2: -n 8 -> -n 4, timeout 60 -> 120 - Worker crashes consistently caused by too many parallel proxy tests each loading the full FastAPI app and heavy dependency tree Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> * fix(db): add migration for SpendLogs composite index (startTime, request_id) The @@index([startTime, request_id]) was added to schema.prisma but had no corresponding migration. This caused test_aaaasschema_migration_check to fail because prisma migrate diff detected the missing index. Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> * fix(db): add migration for MCP available_on_public_internet default change to true The schema.prisma changed the default for available_on_public_internet from false to true, but no migration was created. This caused the schema migration test to detect drift. Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> * fix(test): increase server wait time and add retry to flaky external API tests - test_basic_python_version.py: increase server startup wait from 60s to 90s for slower CI environments (fixes installing_litellm_on_python_3_13) - test_a2a_agent.py: add flaky(retries=3, delay=5) for non-streaming test that depends on live A2A agent endpoint Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> * fix(test): add flaky retries to all intermittent external API tests for 0-fail CI Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> * fix(test): add auth overrides to file endpoint tests that return 500 The test_target_storage tests were getting 500 because the FastAPI auth dependency wasn't overridden. Added app.dependency_overrides for proper auth bypass in test environment. Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> --------- Co-authored-by: Cursor Agent <cursoragent@cursor.com> Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com>
2026-03-01 01:46:35 +08:00
@pytest.mark.xdist_group("proxy_cli")
class TestProxyInitializationHelpers:
@patch("importlib.metadata.version")
@patch("click.echo")
def test_echo_litellm_version(self, mock_echo, mock_version):
# Setup
mock_version.return_value = "1.0.0"
# Execute
ProxyInitializationHelpers._echo_litellm_version()
# Assert
mock_version.assert_called_once_with("litellm")
mock_echo.assert_called_once_with("\nLiteLLM: Current Version = 1.0.0\n")
@patch("httpx.get")
@patch("builtins.print")
@patch("json.dumps")
def test_run_health_check(self, mock_dumps, mock_print, mock_get):
# Setup
mock_response = MagicMock()
mock_response.json.return_value = {"status": "healthy"}
mock_get.return_value = mock_response
mock_dumps.return_value = '{"status": "healthy"}'
# Execute
ProxyInitializationHelpers._run_health_check("localhost", 8000)
# Assert
mock_get.assert_called_once_with(url="http://localhost:8000/health")
mock_response.json.assert_called_once()
mock_dumps.assert_called_once_with({"status": "healthy"}, indent=4)
@patch("openai.OpenAI")
@patch("click.echo")
@patch("builtins.print")
def test_run_test_chat_completion(self, mock_print, mock_echo, mock_openai):
# Setup
mock_client = MagicMock()
mock_openai.return_value = mock_client
mock_response = MagicMock()
mock_client.chat.completions.create.return_value = mock_response
mock_stream_response = MagicMock()
mock_stream_response.__iter__.return_value = [MagicMock(), MagicMock()]
mock_client.chat.completions.create.side_effect = [
mock_response,
mock_stream_response,
]
# Execute
with pytest.raises(ValueError, match="Invalid test value"):
ProxyInitializationHelpers._run_test_chat_completion(
"localhost", 8000, "gpt-3.5-turbo", True
)
# Test with valid string test value
ProxyInitializationHelpers._run_test_chat_completion(
"localhost", 8000, "gpt-3.5-turbo", "http://test-url"
)
# Assert
mock_openai.assert_called_once_with(
api_key="My API Key", base_url="http://test-url"
)
mock_client.chat.completions.create.assert_called()
def test_get_default_unvicorn_init_args(self):
# Test without log_config
args = ProxyInitializationHelpers._get_default_unvicorn_init_args(
"localhost", 8000
)
assert args["app"] == "litellm.proxy.proxy_server:app"
assert args["host"] == "localhost"
assert args["port"] == 8000
# Test with log_config
args = ProxyInitializationHelpers._get_default_unvicorn_init_args(
"localhost", 8000, "log_config.json"
)
assert args["log_config"] == "log_config.json"
# Test with json_logs=True
with patch("litellm.json_logs", True):
args = ProxyInitializationHelpers._get_default_unvicorn_init_args(
"localhost", 8000
)
2026-01-25 04:59:51 +08:00
# When json_logs is True, log_config should be set to the JSON log config dict
assert args["log_config"] is not None
assert isinstance(args["log_config"], dict)
assert "version" in args["log_config"]
assert "formatters" in args["log_config"]
# Test with keepalive_timeout
args = ProxyInitializationHelpers._get_default_unvicorn_init_args(
"localhost", 8000, None, 60
)
assert args["timeout_keep_alive"] == 60
# Test with both log_config and keepalive_timeout
args = ProxyInitializationHelpers._get_default_unvicorn_init_args(
"localhost", 8000, "log_config.json", 120
)
assert args["log_config"] == "log_config.json"
assert args["timeout_keep_alive"] == 120
class _FakeUvicornConfig:
def __init__(self, timeout_worker_healthcheck=None):
pass
with patch("uvicorn.Config", _FakeUvicornConfig):
args = ProxyInitializationHelpers._get_default_unvicorn_init_args(
"localhost", 8000, timeout_worker_healthcheck=15
)
assert args["timeout_worker_healthcheck"] == 15
feat(proxy): hot-reload .env in dev when running with --reload (#29783) * feat(proxy): hot-reload .env in dev when running with --reload The --reload watcher already restarts the worker on *.py and --config YAML edits, but .env was unwatched, so changing a key there did nothing until a manual restart. Add .env to the uvicorn reload_includes (and to the StatReload monkeypatch, which ignores reload_includes) so an edit triggers a worker restart. A reloaded worker is a fresh process that inherits the reloader's environment, so load_dotenv(override=False) would keep serving the stale inherited value for any key already in the environment. The CLI now exports LITELLM_DEV_ENV_HOT_RELOAD when --reload is set, and litellm/__init__.py reads it to load .env with override=True only on that dev path, leaving normal startup precedence untouched. * feat(proxy): warn that --reload makes .env override shell env vars When --reload is active, worker processes re-read .env with override=True, so .env values win over shell-exported environment variables. Surface this dotenv precedence change with a startup warning so a developer who relies on a shell-exported override is not silently surprised. * fix(proxy): type reload helper paths as Optional[str] to satisfy mypy * fix(proxy): watch the cwd .env in both reload backends for parity WatchFiles only watches cwd (and the --config dir) for .env, while the StatReload fallback used find_dotenv(usecwd=True), which walks up to a parent-dir .env that WatchFiles never sees. Point StatReload at the same cwd .env so the two reload backends react to the same file.
2026-06-07 00:39:21 +08:00
def test_get_reload_options_no_config_still_watches_env(self):
proxy: hot-reload config YAML when --reload is set (#27274) * proxy: hot-reload config YAML when --reload is set Uvicorn's --reload only watches *.py by default, so editing the --config YAML did not restart the proxy. _get_reload_options() now extends reload_dirs/reload_includes with the config file's directory and basename when --config is provided. * proxy: qualify reload_includes with absolute config path Address Greptile review on PR #27274. When the --config file lives outside cwd, reload_includes previously stored only the basename, which meant uvicorn/watchfiles would also reload on edits to any same-named file inside cwd. Use the absolute config path as the include pattern in that case so only the actual proxy config triggers a restart. Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com> * fix(proxy): use basename for reload_includes config pattern Uvicorn's resolve_reload_patterns() calls pathlib.Path.glob(), which raises NotImplementedError on absolute patterns (uvicorn discussion 2156). Passing config_abs (an absolute path) when the config file lived outside cwd crashed startup under --reload. The config_dir is already added to reload_dirs, so using just the basename as the include pattern is sufficient to match the specific config file. * fix: make it reload app when yaml changes * style: remove unneeded comments --------- Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Cursor Agent <cursoragent@cursor.com> Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com>
2026-05-07 00:06:58 +08:00
opts = ProxyInitializationHelpers._get_reload_options(None)
feat(proxy): hot-reload .env in dev when running with --reload (#29783) * feat(proxy): hot-reload .env in dev when running with --reload The --reload watcher already restarts the worker on *.py and --config YAML edits, but .env was unwatched, so changing a key there did nothing until a manual restart. Add .env to the uvicorn reload_includes (and to the StatReload monkeypatch, which ignores reload_includes) so an edit triggers a worker restart. A reloaded worker is a fresh process that inherits the reloader's environment, so load_dotenv(override=False) would keep serving the stale inherited value for any key already in the environment. The CLI now exports LITELLM_DEV_ENV_HOT_RELOAD when --reload is set, and litellm/__init__.py reads it to load .env with override=True only on that dev path, leaving normal startup precedence untouched. * feat(proxy): warn that --reload makes .env override shell env vars When --reload is active, worker processes re-read .env with override=True, so .env values win over shell-exported environment variables. Surface this dotenv precedence change with a startup warning so a developer who relies on a shell-exported override is not silently surprised. * fix(proxy): type reload helper paths as Optional[str] to satisfy mypy * fix(proxy): watch the cwd .env in both reload backends for parity WatchFiles only watches cwd (and the --config dir) for .env, while the StatReload fallback used find_dotenv(usecwd=True), which walks up to a parent-dir .env that WatchFiles never sees. Point StatReload at the same cwd .env so the two reload backends react to the same file.
2026-06-07 00:39:21 +08:00
assert opts["reload"] is True
assert opts["reload_dirs"] == [os.path.abspath(os.getcwd())]
assert opts["reload_includes"] == ["*.py", ".env"]
proxy: hot-reload config YAML when --reload is set (#27274) * proxy: hot-reload config YAML when --reload is set Uvicorn's --reload only watches *.py by default, so editing the --config YAML did not restart the proxy. _get_reload_options() now extends reload_dirs/reload_includes with the config file's directory and basename when --config is provided. * proxy: qualify reload_includes with absolute config path Address Greptile review on PR #27274. When the --config file lives outside cwd, reload_includes previously stored only the basename, which meant uvicorn/watchfiles would also reload on edits to any same-named file inside cwd. Use the absolute config path as the include pattern in that case so only the actual proxy config triggers a restart. Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com> * fix(proxy): use basename for reload_includes config pattern Uvicorn's resolve_reload_patterns() calls pathlib.Path.glob(), which raises NotImplementedError on absolute patterns (uvicorn discussion 2156). Passing config_abs (an absolute path) when the config file lived outside cwd crashed startup under --reload. The config_dir is already added to reload_dirs, so using just the basename as the include pattern is sufficient to match the specific config file. * fix: make it reload app when yaml changes * style: remove unneeded comments --------- Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Cursor Agent <cursoragent@cursor.com> Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com>
2026-05-07 00:06:58 +08:00
def test_get_reload_options_with_config_in_cwd(self, tmp_path, monkeypatch):
config_file = tmp_path / "config.yaml"
config_file.write_text("model_list: []\n")
monkeypatch.chdir(tmp_path)
opts = ProxyInitializationHelpers._get_reload_options("config.yaml")
assert opts["reload"] is True
assert opts["reload_dirs"] == [str(tmp_path)]
feat(proxy): hot-reload .env in dev when running with --reload (#29783) * feat(proxy): hot-reload .env in dev when running with --reload The --reload watcher already restarts the worker on *.py and --config YAML edits, but .env was unwatched, so changing a key there did nothing until a manual restart. Add .env to the uvicorn reload_includes (and to the StatReload monkeypatch, which ignores reload_includes) so an edit triggers a worker restart. A reloaded worker is a fresh process that inherits the reloader's environment, so load_dotenv(override=False) would keep serving the stale inherited value for any key already in the environment. The CLI now exports LITELLM_DEV_ENV_HOT_RELOAD when --reload is set, and litellm/__init__.py reads it to load .env with override=True only on that dev path, leaving normal startup precedence untouched. * feat(proxy): warn that --reload makes .env override shell env vars When --reload is active, worker processes re-read .env with override=True, so .env values win over shell-exported environment variables. Surface this dotenv precedence change with a startup warning so a developer who relies on a shell-exported override is not silently surprised. * fix(proxy): type reload helper paths as Optional[str] to satisfy mypy * fix(proxy): watch the cwd .env in both reload backends for parity WatchFiles only watches cwd (and the --config dir) for .env, while the StatReload fallback used find_dotenv(usecwd=True), which walks up to a parent-dir .env that WatchFiles never sees. Point StatReload at the same cwd .env so the two reload backends react to the same file.
2026-06-07 00:39:21 +08:00
assert opts["reload_includes"] == ["*.py", ".env", "config.yaml"]
proxy: hot-reload config YAML when --reload is set (#27274) * proxy: hot-reload config YAML when --reload is set Uvicorn's --reload only watches *.py by default, so editing the --config YAML did not restart the proxy. _get_reload_options() now extends reload_dirs/reload_includes with the config file's directory and basename when --config is provided. * proxy: qualify reload_includes with absolute config path Address Greptile review on PR #27274. When the --config file lives outside cwd, reload_includes previously stored only the basename, which meant uvicorn/watchfiles would also reload on edits to any same-named file inside cwd. Use the absolute config path as the include pattern in that case so only the actual proxy config triggers a restart. Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com> * fix(proxy): use basename for reload_includes config pattern Uvicorn's resolve_reload_patterns() calls pathlib.Path.glob(), which raises NotImplementedError on absolute patterns (uvicorn discussion 2156). Passing config_abs (an absolute path) when the config file lived outside cwd crashed startup under --reload. The config_dir is already added to reload_dirs, so using just the basename as the include pattern is sufficient to match the specific config file. * fix: make it reload app when yaml changes * style: remove unneeded comments --------- Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Cursor Agent <cursoragent@cursor.com> Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com>
2026-05-07 00:06:58 +08:00
def test_get_reload_options_with_config_outside_cwd(self, tmp_path, monkeypatch):
cwd_dir = tmp_path / "work"
cwd_dir.mkdir()
elsewhere = tmp_path / "configs"
elsewhere.mkdir()
config_file = elsewhere / "proxy.yaml"
config_file.write_text("model_list: []\n")
monkeypatch.chdir(cwd_dir)
opts = ProxyInitializationHelpers._get_reload_options(str(config_file))
assert opts["reload"] is True
assert opts["reload_dirs"] == [str(cwd_dir), str(elsewhere)]
feat(proxy): hot-reload .env in dev when running with --reload (#29783) * feat(proxy): hot-reload .env in dev when running with --reload The --reload watcher already restarts the worker on *.py and --config YAML edits, but .env was unwatched, so changing a key there did nothing until a manual restart. Add .env to the uvicorn reload_includes (and to the StatReload monkeypatch, which ignores reload_includes) so an edit triggers a worker restart. A reloaded worker is a fresh process that inherits the reloader's environment, so load_dotenv(override=False) would keep serving the stale inherited value for any key already in the environment. The CLI now exports LITELLM_DEV_ENV_HOT_RELOAD when --reload is set, and litellm/__init__.py reads it to load .env with override=True only on that dev path, leaving normal startup precedence untouched. * feat(proxy): warn that --reload makes .env override shell env vars When --reload is active, worker processes re-read .env with override=True, so .env values win over shell-exported environment variables. Surface this dotenv precedence change with a startup warning so a developer who relies on a shell-exported override is not silently surprised. * fix(proxy): type reload helper paths as Optional[str] to satisfy mypy * fix(proxy): watch the cwd .env in both reload backends for parity WatchFiles only watches cwd (and the --config dir) for .env, while the StatReload fallback used find_dotenv(usecwd=True), which walks up to a parent-dir .env that WatchFiles never sees. Point StatReload at the same cwd .env so the two reload backends react to the same file.
2026-06-07 00:39:21 +08:00
assert opts["reload_includes"] == ["*.py", ".env", "proxy.yaml"]
proxy: hot-reload config YAML when --reload is set (#27274) * proxy: hot-reload config YAML when --reload is set Uvicorn's --reload only watches *.py by default, so editing the --config YAML did not restart the proxy. _get_reload_options() now extends reload_dirs/reload_includes with the config file's directory and basename when --config is provided. * proxy: qualify reload_includes with absolute config path Address Greptile review on PR #27274. When the --config file lives outside cwd, reload_includes previously stored only the basename, which meant uvicorn/watchfiles would also reload on edits to any same-named file inside cwd. Use the absolute config path as the include pattern in that case so only the actual proxy config triggers a restart. Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com> * fix(proxy): use basename for reload_includes config pattern Uvicorn's resolve_reload_patterns() calls pathlib.Path.glob(), which raises NotImplementedError on absolute patterns (uvicorn discussion 2156). Passing config_abs (an absolute path) when the config file lived outside cwd crashed startup under --reload. The config_dir is already added to reload_dirs, so using just the basename as the include pattern is sufficient to match the specific config file. * fix: make it reload app when yaml changes * style: remove unneeded comments --------- Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Cursor Agent <cursoragent@cursor.com> Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com>
2026-05-07 00:06:58 +08:00
feat(proxy): hot-reload .env in dev when running with --reload (#29783) * feat(proxy): hot-reload .env in dev when running with --reload The --reload watcher already restarts the worker on *.py and --config YAML edits, but .env was unwatched, so changing a key there did nothing until a manual restart. Add .env to the uvicorn reload_includes (and to the StatReload monkeypatch, which ignores reload_includes) so an edit triggers a worker restart. A reloaded worker is a fresh process that inherits the reloader's environment, so load_dotenv(override=False) would keep serving the stale inherited value for any key already in the environment. The CLI now exports LITELLM_DEV_ENV_HOT_RELOAD when --reload is set, and litellm/__init__.py reads it to load .env with override=True only on that dev path, leaving normal startup precedence untouched. * feat(proxy): warn that --reload makes .env override shell env vars When --reload is active, worker processes re-read .env with override=True, so .env values win over shell-exported environment variables. Surface this dotenv precedence change with a startup warning so a developer who relies on a shell-exported override is not silently surprised. * fix(proxy): type reload helper paths as Optional[str] to satisfy mypy * fix(proxy): watch the cwd .env in both reload backends for parity WatchFiles only watches cwd (and the --config dir) for .env, while the StatReload fallback used find_dotenv(usecwd=True), which walks up to a parent-dir .env that WatchFiles never sees. Point StatReload at the same cwd .env so the two reload backends react to the same file.
2026-06-07 00:39:21 +08:00
def test_patch_statreload_extra_paths_yields_config_and_py(self, tmp_path):
proxy: hot-reload config YAML when --reload is set (#27274) * proxy: hot-reload config YAML when --reload is set Uvicorn's --reload only watches *.py by default, so editing the --config YAML did not restart the proxy. _get_reload_options() now extends reload_dirs/reload_includes with the config file's directory and basename when --config is provided. * proxy: qualify reload_includes with absolute config path Address Greptile review on PR #27274. When the --config file lives outside cwd, reload_includes previously stored only the basename, which meant uvicorn/watchfiles would also reload on edits to any same-named file inside cwd. Use the absolute config path as the include pattern in that case so only the actual proxy config triggers a restart. Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com> * fix(proxy): use basename for reload_includes config pattern Uvicorn's resolve_reload_patterns() calls pathlib.Path.glob(), which raises NotImplementedError on absolute patterns (uvicorn discussion 2156). Passing config_abs (an absolute path) when the config file lived outside cwd crashed startup under --reload. The config_dir is already added to reload_dirs, so using just the basename as the include pattern is sufficient to match the specific config file. * fix: make it reload app when yaml changes * style: remove unneeded comments --------- Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Cursor Agent <cursoragent@cursor.com> Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com>
2026-05-07 00:06:58 +08:00
from pathlib import Path
from uvicorn.supervisors.statreload import StatReload
if hasattr(StatReload, "_litellm_patched_config_paths"):
StatReload._litellm_patched_config_paths.clear()
config_file = tmp_path / "config.yaml"
config_file.write_text("model_list: []\n")
py_file = tmp_path / "module.py"
py_file.write_text("x = 1\n")
feat(proxy): hot-reload .env in dev when running with --reload (#29783) * feat(proxy): hot-reload .env in dev when running with --reload The --reload watcher already restarts the worker on *.py and --config YAML edits, but .env was unwatched, so changing a key there did nothing until a manual restart. Add .env to the uvicorn reload_includes (and to the StatReload monkeypatch, which ignores reload_includes) so an edit triggers a worker restart. A reloaded worker is a fresh process that inherits the reloader's environment, so load_dotenv(override=False) would keep serving the stale inherited value for any key already in the environment. The CLI now exports LITELLM_DEV_ENV_HOT_RELOAD when --reload is set, and litellm/__init__.py reads it to load .env with override=True only on that dev path, leaving normal startup precedence untouched. * feat(proxy): warn that --reload makes .env override shell env vars When --reload is active, worker processes re-read .env with override=True, so .env values win over shell-exported environment variables. Surface this dotenv precedence change with a startup warning so a developer who relies on a shell-exported override is not silently surprised. * fix(proxy): type reload helper paths as Optional[str] to satisfy mypy * fix(proxy): watch the cwd .env in both reload backends for parity WatchFiles only watches cwd (and the --config dir) for .env, while the StatReload fallback used find_dotenv(usecwd=True), which walks up to a parent-dir .env that WatchFiles never sees. Point StatReload at the same cwd .env so the two reload backends react to the same file.
2026-06-07 00:39:21 +08:00
applied = ProxyInitializationHelpers._patch_statreload_extra_paths(
[str(config_file)]
proxy: hot-reload config YAML when --reload is set (#27274) * proxy: hot-reload config YAML when --reload is set Uvicorn's --reload only watches *.py by default, so editing the --config YAML did not restart the proxy. _get_reload_options() now extends reload_dirs/reload_includes with the config file's directory and basename when --config is provided. * proxy: qualify reload_includes with absolute config path Address Greptile review on PR #27274. When the --config file lives outside cwd, reload_includes previously stored only the basename, which meant uvicorn/watchfiles would also reload on edits to any same-named file inside cwd. Use the absolute config path as the include pattern in that case so only the actual proxy config triggers a restart. Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com> * fix(proxy): use basename for reload_includes config pattern Uvicorn's resolve_reload_patterns() calls pathlib.Path.glob(), which raises NotImplementedError on absolute patterns (uvicorn discussion 2156). Passing config_abs (an absolute path) when the config file lived outside cwd crashed startup under --reload. The config_dir is already added to reload_dirs, so using just the basename as the include pattern is sufficient to match the specific config file. * fix: make it reload app when yaml changes * style: remove unneeded comments --------- Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Cursor Agent <cursoragent@cursor.com> Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com>
2026-05-07 00:06:58 +08:00
)
assert applied is True
fake_self = types.SimpleNamespace(
config=types.SimpleNamespace(reload_dirs=[tmp_path])
)
yielded_paths = {Path(p).resolve() for p in StatReload.iter_py_files(fake_self)}
assert config_file.resolve() in yielded_paths
assert py_file.resolve() in yielded_paths
feat(proxy): hot-reload .env in dev when running with --reload (#29783) * feat(proxy): hot-reload .env in dev when running with --reload The --reload watcher already restarts the worker on *.py and --config YAML edits, but .env was unwatched, so changing a key there did nothing until a manual restart. Add .env to the uvicorn reload_includes (and to the StatReload monkeypatch, which ignores reload_includes) so an edit triggers a worker restart. A reloaded worker is a fresh process that inherits the reloader's environment, so load_dotenv(override=False) would keep serving the stale inherited value for any key already in the environment. The CLI now exports LITELLM_DEV_ENV_HOT_RELOAD when --reload is set, and litellm/__init__.py reads it to load .env with override=True only on that dev path, leaving normal startup precedence untouched. * feat(proxy): warn that --reload makes .env override shell env vars When --reload is active, worker processes re-read .env with override=True, so .env values win over shell-exported environment variables. Surface this dotenv precedence change with a startup warning so a developer who relies on a shell-exported override is not silently surprised. * fix(proxy): type reload helper paths as Optional[str] to satisfy mypy * fix(proxy): watch the cwd .env in both reload backends for parity WatchFiles only watches cwd (and the --config dir) for .env, while the StatReload fallback used find_dotenv(usecwd=True), which walks up to a parent-dir .env that WatchFiles never sees. Point StatReload at the same cwd .env so the two reload backends react to the same file.
2026-06-07 00:39:21 +08:00
def test_patch_statreload_extra_paths_yields_env(self, tmp_path):
from pathlib import Path
from uvicorn.supervisors.statreload import StatReload
if hasattr(StatReload, "_litellm_patched_config_paths"):
StatReload._litellm_patched_config_paths.clear()
env_file = tmp_path / ".env"
env_file.write_text("FOO=bar\n")
applied = ProxyInitializationHelpers._patch_statreload_extra_paths(
[str(env_file)]
)
assert applied is True
fake_self = types.SimpleNamespace(
config=types.SimpleNamespace(reload_dirs=[tmp_path])
)
yielded_paths = {Path(p).resolve() for p in StatReload.iter_py_files(fake_self)}
assert env_file.resolve() in yielded_paths
def test_patch_statreload_extra_paths_skips_falsy(self, tmp_path):
from uvicorn.supervisors.statreload import StatReload
if hasattr(StatReload, "_litellm_patched_config_paths"):
StatReload._litellm_patched_config_paths.clear()
assert ProxyInitializationHelpers._patch_statreload_extra_paths([]) is False
assert (
ProxyInitializationHelpers._patch_statreload_extra_paths([None, ""])
is False
)
def test_patch_statreload_extra_paths_is_idempotent(self, tmp_path):
proxy: hot-reload config YAML when --reload is set (#27274) * proxy: hot-reload config YAML when --reload is set Uvicorn's --reload only watches *.py by default, so editing the --config YAML did not restart the proxy. _get_reload_options() now extends reload_dirs/reload_includes with the config file's directory and basename when --config is provided. * proxy: qualify reload_includes with absolute config path Address Greptile review on PR #27274. When the --config file lives outside cwd, reload_includes previously stored only the basename, which meant uvicorn/watchfiles would also reload on edits to any same-named file inside cwd. Use the absolute config path as the include pattern in that case so only the actual proxy config triggers a restart. Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com> * fix(proxy): use basename for reload_includes config pattern Uvicorn's resolve_reload_patterns() calls pathlib.Path.glob(), which raises NotImplementedError on absolute patterns (uvicorn discussion 2156). Passing config_abs (an absolute path) when the config file lived outside cwd crashed startup under --reload. The config_dir is already added to reload_dirs, so using just the basename as the include pattern is sufficient to match the specific config file. * fix: make it reload app when yaml changes * style: remove unneeded comments --------- Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Cursor Agent <cursoragent@cursor.com> Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com>
2026-05-07 00:06:58 +08:00
from pathlib import Path
from uvicorn.supervisors.statreload import StatReload
if hasattr(StatReload, "_litellm_patched_config_paths"):
StatReload._litellm_patched_config_paths.clear()
config_file = tmp_path / "config.yaml"
config_file.write_text("model_list: []\n")
py_file = tmp_path / "only.py"
py_file.write_text("x = 1\n")
for _ in range(3):
feat(proxy): hot-reload .env in dev when running with --reload (#29783) * feat(proxy): hot-reload .env in dev when running with --reload The --reload watcher already restarts the worker on *.py and --config YAML edits, but .env was unwatched, so changing a key there did nothing until a manual restart. Add .env to the uvicorn reload_includes (and to the StatReload monkeypatch, which ignores reload_includes) so an edit triggers a worker restart. A reloaded worker is a fresh process that inherits the reloader's environment, so load_dotenv(override=False) would keep serving the stale inherited value for any key already in the environment. The CLI now exports LITELLM_DEV_ENV_HOT_RELOAD when --reload is set, and litellm/__init__.py reads it to load .env with override=True only on that dev path, leaving normal startup precedence untouched. * feat(proxy): warn that --reload makes .env override shell env vars When --reload is active, worker processes re-read .env with override=True, so .env values win over shell-exported environment variables. Surface this dotenv precedence change with a startup warning so a developer who relies on a shell-exported override is not silently surprised. * fix(proxy): type reload helper paths as Optional[str] to satisfy mypy * fix(proxy): watch the cwd .env in both reload backends for parity WatchFiles only watches cwd (and the --config dir) for .env, while the StatReload fallback used find_dotenv(usecwd=True), which walks up to a parent-dir .env that WatchFiles never sees. Point StatReload at the same cwd .env so the two reload backends react to the same file.
2026-06-07 00:39:21 +08:00
ProxyInitializationHelpers._patch_statreload_extra_paths([str(config_file)])
proxy: hot-reload config YAML when --reload is set (#27274) * proxy: hot-reload config YAML when --reload is set Uvicorn's --reload only watches *.py by default, so editing the --config YAML did not restart the proxy. _get_reload_options() now extends reload_dirs/reload_includes with the config file's directory and basename when --config is provided. * proxy: qualify reload_includes with absolute config path Address Greptile review on PR #27274. When the --config file lives outside cwd, reload_includes previously stored only the basename, which meant uvicorn/watchfiles would also reload on edits to any same-named file inside cwd. Use the absolute config path as the include pattern in that case so only the actual proxy config triggers a restart. Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com> * fix(proxy): use basename for reload_includes config pattern Uvicorn's resolve_reload_patterns() calls pathlib.Path.glob(), which raises NotImplementedError on absolute patterns (uvicorn discussion 2156). Passing config_abs (an absolute path) when the config file lived outside cwd crashed startup under --reload. The config_dir is already added to reload_dirs, so using just the basename as the include pattern is sufficient to match the specific config file. * fix: make it reload app when yaml changes * style: remove unneeded comments --------- Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Cursor Agent <cursoragent@cursor.com> Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com>
2026-05-07 00:06:58 +08:00
fake_self = types.SimpleNamespace(
config=types.SimpleNamespace(reload_dirs=[tmp_path])
)
yielded = list(StatReload.iter_py_files(fake_self))
assert len(yielded) == len(set(map(str, yielded)))
yielded_paths = {Path(p).resolve() for p in yielded}
assert config_file.resolve() in yielded_paths
assert py_file.resolve() in yielded_paths
feat(proxy): hot-reload .env in dev when running with --reload (#29783) * feat(proxy): hot-reload .env in dev when running with --reload The --reload watcher already restarts the worker on *.py and --config YAML edits, but .env was unwatched, so changing a key there did nothing until a manual restart. Add .env to the uvicorn reload_includes (and to the StatReload monkeypatch, which ignores reload_includes) so an edit triggers a worker restart. A reloaded worker is a fresh process that inherits the reloader's environment, so load_dotenv(override=False) would keep serving the stale inherited value for any key already in the environment. The CLI now exports LITELLM_DEV_ENV_HOT_RELOAD when --reload is set, and litellm/__init__.py reads it to load .env with override=True only on that dev path, leaving normal startup precedence untouched. * feat(proxy): warn that --reload makes .env override shell env vars When --reload is active, worker processes re-read .env with override=True, so .env values win over shell-exported environment variables. Surface this dotenv precedence change with a startup warning so a developer who relies on a shell-exported override is not silently surprised. * fix(proxy): type reload helper paths as Optional[str] to satisfy mypy * fix(proxy): watch the cwd .env in both reload backends for parity WatchFiles only watches cwd (and the --config dir) for .env, while the StatReload fallback used find_dotenv(usecwd=True), which walks up to a parent-dir .env that WatchFiles never sees. Point StatReload at the same cwd .env so the two reload backends react to the same file.
2026-06-07 00:39:21 +08:00
def test_configure_dev_reload_watches_env_and_sets_override_flag(
self, tmp_path, monkeypatch
):
from pathlib import Path
from uvicorn.supervisors.statreload import StatReload
if hasattr(StatReload, "_litellm_patched_config_paths"):
StatReload._litellm_patched_config_paths.clear()
monkeypatch.delenv("LITELLM_DEV_ENV_HOT_RELOAD", raising=False)
config_file = tmp_path / "config.yaml"
config_file.write_text("model_list: []\n")
env_file = tmp_path / ".env"
env_file.write_text("FOO=bar\n")
monkeypatch.chdir(tmp_path)
uvicorn_args: dict = {}
with patch("litellm._logging.verbose_proxy_logger.warning") as mock_warning:
ProxyInitializationHelpers._configure_dev_reload(
uvicorn_args, str(config_file)
)
assert os.environ["LITELLM_DEV_ENV_HOT_RELOAD"] == "True"
assert uvicorn_args["reload"] is True
assert ".env" in uvicorn_args["reload_includes"]
mock_warning.assert_called_once()
warning_text = mock_warning.call_args.args[0].lower()
assert "override" in warning_text
assert ".env" in warning_text
fake_self = types.SimpleNamespace(
config=types.SimpleNamespace(reload_dirs=[tmp_path])
)
yielded_paths = {Path(p).resolve() for p in StatReload.iter_py_files(fake_self)}
assert env_file.resolve() in yielded_paths
assert config_file.resolve() in yielded_paths
def test_dev_env_hot_reload_enabled_reads_flag(self, monkeypatch):
import litellm
monkeypatch.setenv("LITELLM_DEV_ENV_HOT_RELOAD", "True")
assert litellm._dev_env_hot_reload_enabled() is True
monkeypatch.setenv("LITELLM_DEV_ENV_HOT_RELOAD", "false")
assert litellm._dev_env_hot_reload_enabled() is False
monkeypatch.delenv("LITELLM_DEV_ENV_HOT_RELOAD", raising=False)
assert litellm._dev_env_hot_reload_enabled() is False
@patch("asyncio.run")
@patch("builtins.print")
def test_init_hypercorn_server(self, mock_print, mock_asyncio_run):
# Setup
mock_app = MagicMock()
# Execute
ProxyInitializationHelpers._init_hypercorn_server(
mock_app, "localhost", 8000, None, None, None
)
# Assert
mock_asyncio_run.assert_called_once()
# Test with SSL
ProxyInitializationHelpers._init_hypercorn_server(
mock_app, "localhost", 8000, "cert.pem", "key.pem", "ECDHE"
)
@patch("granian.Granian")
@patch("builtins.print")
def test_init_granian_server(self, mock_print, mock_granian_cls):
pytest.importorskip("granian")
mock_server = MagicMock()
mock_granian_cls.return_value = mock_server
fake_interfaces = SimpleNamespace(ASGI="asgi")
with patch("granian.constants.Interfaces", fake_interfaces):
ProxyInitializationHelpers._init_granian_server(
host="0.0.0.0",
port=4000,
num_workers=2,
ssl_certfile_path=None,
ssl_keyfile_path=None,
max_requests_before_restart=None,
ciphers=None,
granian_runtime_threads=None,
)
mock_granian_cls.assert_called_once()
call_kwargs = mock_granian_cls.call_args.kwargs
assert call_kwargs["target"] == "litellm.proxy.proxy_server:app"
assert call_kwargs["address"] == "0.0.0.0"
assert call_kwargs["port"] == 4000
assert call_kwargs["workers"] == 2
assert call_kwargs["interface"] == "asgi"
assert call_kwargs["websockets"] is True
assert "runtime_threads" not in call_kwargs
mock_server.serve.assert_called_once()
@patch("granian.Granian")
@patch("builtins.print")
def test_init_granian_server_runtime_threads(self, mock_print, mock_granian_cls):
pytest.importorskip("granian")
mock_server = MagicMock()
mock_granian_cls.return_value = mock_server
fake_interfaces = SimpleNamespace(ASGI="asgi")
with patch("granian.constants.Interfaces", fake_interfaces):
ProxyInitializationHelpers._init_granian_server(
host="0.0.0.0",
port=4000,
num_workers=1,
ssl_certfile_path=None,
ssl_keyfile_path=None,
max_requests_before_restart=None,
ciphers=None,
granian_runtime_threads=4,
)
assert mock_granian_cls.call_args.kwargs["runtime_threads"] == 4
@patch("granian.Granian")
@patch("builtins.print")
def test_init_granian_server_ssl(self, mock_print, mock_granian_cls):
pytest.importorskip("granian")
mock_server = MagicMock()
mock_granian_cls.return_value = mock_server
fake_interfaces = SimpleNamespace(ASGI="asgi")
with patch("granian.constants.Interfaces", fake_interfaces):
ProxyInitializationHelpers._init_granian_server(
host="0.0.0.0",
port=4000,
num_workers=1,
ssl_certfile_path="/path/to/cert.pem",
ssl_keyfile_path="/path/to/key.pem",
max_requests_before_restart=None,
ciphers=None,
granian_runtime_threads=None,
)
call_kwargs = mock_granian_cls.call_args.kwargs
assert call_kwargs["ssl_cert"] == Path("/path/to/cert.pem")
assert call_kwargs["ssl_key"] == Path("/path/to/key.pem")
mock_server.serve.assert_called_once()
@patch("granian.Granian")
def test_init_granian_server_ssl_requires_cert_and_key(self, mock_granian_cls):
pytest.importorskip("granian")
fake_interfaces = SimpleNamespace(ASGI="asgi")
with patch("granian.constants.Interfaces", fake_interfaces):
with pytest.raises(click.ClickException, match="Both --ssl_certfile_path"):
ProxyInitializationHelpers._init_granian_server(
host="0.0.0.0",
port=4000,
num_workers=1,
ssl_certfile_path="/path/to/cert.pem",
ssl_keyfile_path=None,
max_requests_before_restart=None,
ciphers=None,
granian_runtime_threads=None,
)
mock_granian_cls.assert_not_called()
@patch("subprocess.Popen")
def test_run_ollama_serve(self, mock_popen):
# Execute
ProxyInitializationHelpers._run_ollama_serve()
# Assert
mock_popen.assert_called_once()
# Test exception handling
mock_popen.side_effect = Exception("Test exception")
ProxyInitializationHelpers._run_ollama_serve() # Should not raise
@patch("socket.socket")
def test_is_port_in_use(self, mock_socket):
# Setup for port in use
mock_socket_instance = MagicMock()
mock_socket_instance.connect_ex.return_value = 0
mock_socket.return_value.__enter__.return_value = mock_socket_instance
# Execute and Assert
assert ProxyInitializationHelpers._is_port_in_use(8000) is True
# Setup for port not in use
mock_socket_instance.connect_ex.return_value = 1
# Execute and Assert
assert ProxyInitializationHelpers._is_port_in_use(8000) is False
def test_get_loop_type(self):
# Test on Windows
with patch("sys.platform", "win32"):
assert ProxyInitializationHelpers._get_loop_type() is None
# Test on Linux
with patch("sys.platform", "linux"):
assert ProxyInitializationHelpers._get_loop_type() == "uvloop"
@patch.dict(os.environ, {}, clear=True)
def test_database_url_construction_with_special_characters(self):
# Setup environment variables with special characters that need escaping
test_env = {
"DATABASE_HOST": "localhost:5432",
"DATABASE_USERNAME": "user@with+special",
"DATABASE_PASSWORD": "test-password-special-chars",
"DATABASE_NAME": "db_name/test",
}
with patch.dict(os.environ, test_env):
# Call the relevant function - we'll need to extract the database URL construction logic
# This is simulating what happens in the run_server function when database_url is None
import urllib.parse
from litellm.proxy.proxy_cli import append_query_params
database_host = os.environ["DATABASE_HOST"]
database_username = os.environ["DATABASE_USERNAME"]
database_password = os.environ["DATABASE_PASSWORD"]
database_name = os.environ["DATABASE_NAME"]
# Test the URL encoding part
database_username_enc = urllib.parse.quote_plus(database_username)
database_password_enc = urllib.parse.quote_plus(database_password)
database_name_enc = urllib.parse.quote_plus(database_name)
# Construct DATABASE_URL from the provided variables
database_url = f"postgresql://{database_username_enc}:{database_password_enc}@{database_host}/{database_name_enc}"
# Assert the correct URL was constructed with properly escaped characters
expected_url = "postgresql://user%40with%2Bspecial:test-password-special-chars@localhost:5432/db_name%2Ftest"
assert database_url == expected_url
# Test appending query parameters
params = {"connection_limit": 10, "pool_timeout": 60}
modified_url = append_query_params(database_url, params)
assert "connection_limit=10" in modified_url
assert "pool_timeout=60" in modified_url
def test_append_query_params_handles_missing_url(self):
from litellm.proxy.proxy_cli import append_query_params
modified_url = append_query_params(None, {"connection_limit": 10})
assert modified_url == ""
@patch("uvicorn.run")
@patch("atexit.register") # critical
@patch("litellm.proxy.db.prisma_client.PrismaManager.setup_database")
@patch(
"litellm.proxy.db.prisma_client.should_update_prisma_schema", return_value=False
)
def test_skip_server_startup(
self, mock_should_update, mock_setup_db, mock_atexit_register, mock_uvicorn_run
):
from click.testing import CliRunner
2026-01-25 04:59:51 +08:00
from litellm.proxy.proxy_cli import run_server
runner = CliRunner()
mock_proxy_module = MagicMock(
app=MagicMock(),
ProxyConfig=MagicMock(),
KeyManagementSettings=MagicMock(),
save_worker_config=MagicMock(),
)
# Remove DATABASE_URL/DIRECT_URL so the CLI doesn't attempt
# real prisma operations when these are set in CI.
clean_env = {
k: v
for k, v in os.environ.items()
if k not in ("DATABASE_URL", "DIRECT_URL")
}
with (
patch.dict(
os.environ,
clean_env,
clear=True,
),
patch.dict(
"sys.modules",
{
"proxy_server": mock_proxy_module,
# Prevent real import of proxy_server inside Click's
# isolation context (heavy side effects cause stream
# lifecycle issues with Click 8.2+)
"litellm.proxy.proxy_server": mock_proxy_module,
},
),
patch(
"litellm.proxy.proxy_cli.ProxyInitializationHelpers._get_default_unvicorn_init_args"
) as mock_get_args,
):
mock_get_args.return_value = {
"app": "litellm.proxy.proxy_server:app",
"host": "localhost",
"port": 8000,
}
2026-01-24 04:10:08 +08:00
# --- skip startup ---
result = runner.invoke(run_server, ["--local", "--skip_server_startup"])
assert (
result.exit_code == 0
), f"exit_code={result.exit_code}, output={result.output}"
2026-01-24 04:10:08 +08:00
assert "Skipping server startup" in result.output
mock_uvicorn_run.assert_not_called()
2026-01-24 04:10:08 +08:00
# --- normal startup ---
mock_uvicorn_run.reset_mock()
result = runner.invoke(run_server, ["--local"])
assert (
result.exit_code == 0
), f"exit_code={result.exit_code}, output={result.output}"
mock_uvicorn_run.assert_called_once()
@pytest.mark.parametrize(
"timeout_config,expected_timeout",
[
({"database_connection_timeout": 30}, 30),
({"database_connection_pool_timeout": 45}, 45),
(
{
"database_connection_timeout": 30,
"database_connection_pool_timeout": 45,
},
30,
),
],
)
@patch("subprocess.run")
@patch("atexit.register")
@patch("litellm.proxy.db.prisma_client.PrismaManager.setup_database")
@patch(
"litellm.proxy.db.prisma_client.should_update_prisma_schema", return_value=False
)
def test_db_timeout_settings_are_forwarded_to_pool_timeout(
self,
mock_should_update,
mock_setup_db,
mock_atexit_register,
mock_subprocess_run,
timeout_config,
expected_timeout,
):
from click.testing import CliRunner
from litellm.proxy.proxy_cli import run_server
runner = CliRunner()
mock_subprocess_run.return_value = MagicMock(returncode=0)
mock_proxy_module = MagicMock(
app=MagicMock(),
ProxyConfig=MagicMock(),
KeyManagementSettings=MagicMock(),
save_worker_config=MagicMock(),
)
mock_proxy_module.ProxyConfig.return_value.get_config = AsyncMock(
return_value={
"general_settings": {
"database_url": "postgresql://test:test@localhost:5432/test",
"database_connection_pool_limit": 5,
**timeout_config,
}
}
)
clean_env = {
k: v
for k, v in os.environ.items()
if k not in ("DATABASE_URL", "DIRECT_URL")
}
with (
patch.dict(os.environ, clean_env, clear=True),
patch.dict(
"sys.modules",
{
"proxy_server": mock_proxy_module,
"litellm.proxy.proxy_server": mock_proxy_module,
},
),
patch(
"litellm.proxy.proxy_cli.ProxyInitializationHelpers._get_default_unvicorn_init_args"
) as mock_get_args,
patch(
"litellm.proxy.proxy_cli.append_query_params",
side_effect=lambda url, params: (
f"{url}?connection_limit={params['connection_limit']}&pool_timeout={params['pool_timeout']}"
),
) as mock_append_query_params,
):
mock_get_args.return_value = {
"app": "litellm.proxy.proxy_server:app",
"host": "localhost",
"port": 8000,
}
result = runner.invoke(
run_server,
["--local", "--config", "test-config.yaml", "--skip_server_startup"],
)
assert (
result.exit_code == 0
), f"exit_code={result.exit_code}, output={result.output}"
mock_append_query_params.assert_called()
appended_params = mock_append_query_params.call_args.args[1]
assert appended_params["connection_limit"] == 5
assert appended_params["pool_timeout"] == expected_timeout
def test_build_db_connection_url_params_defaults(self):
from litellm.proxy.proxy_cli import _build_db_connection_url_params
params = _build_db_connection_url_params(connection_limit=10, pool_timeout=60)
assert params == {"connection_limit": 10, "pool_timeout": 60}
def test_build_db_connection_url_params_omits_none_timeouts(self):
from litellm.proxy.proxy_cli import _build_db_connection_url_params
params = _build_db_connection_url_params(
connection_limit=10,
pool_timeout=60,
connect_timeout=None,
socket_timeout=None,
)
assert "connect_timeout" not in params
assert "socket_timeout" not in params
def test_build_db_connection_url_params_includes_optional_timeouts(self):
from litellm.proxy.proxy_cli import _build_db_connection_url_params
params = _build_db_connection_url_params(
connection_limit=10,
pool_timeout=60,
connect_timeout=15,
socket_timeout=120,
)
assert params["connect_timeout"] == 15
assert params["socket_timeout"] == 120
def test_build_db_connection_url_params_extras_override_defaults(self):
from litellm.proxy.proxy_cli import _build_db_connection_url_params
params = _build_db_connection_url_params(
connection_limit=10,
pool_timeout=60,
extra_params={
"pgbouncer": "true",
"statement_cache_size": 0,
"pool_timeout": 5,
},
)
assert params["pgbouncer"] == "true"
assert params["statement_cache_size"] == 0
assert params["pool_timeout"] == 5
@patch("subprocess.run")
@patch("atexit.register")
@patch("litellm.proxy.db.prisma_client.PrismaManager.setup_database")
@patch(
"litellm.proxy.db.prisma_client.should_update_prisma_schema", return_value=False
)
def test_db_connection_extra_params_forwarded_to_url(
self,
mock_should_update,
mock_setup_db,
mock_atexit_register,
mock_subprocess_run,
):
from click.testing import CliRunner
from litellm.proxy.proxy_cli import run_server
runner = CliRunner()
mock_subprocess_run.return_value = MagicMock(returncode=0)
mock_proxy_module = MagicMock(
app=MagicMock(),
ProxyConfig=MagicMock(),
KeyManagementSettings=MagicMock(),
save_worker_config=MagicMock(),
)
mock_proxy_module.ProxyConfig.return_value.get_config = AsyncMock(
return_value={
"general_settings": {
"database_url": "postgresql://test:test@localhost:5432/test",
"database_connect_timeout": 15,
"database_socket_timeout": 120,
"database_extra_connection_params": {
"pgbouncer": "true",
"statement_cache_size": 0,
},
}
}
)
clean_env = {
k: v
for k, v in os.environ.items()
if k not in ("DATABASE_URL", "DIRECT_URL")
}
with (
patch.dict(os.environ, clean_env, clear=True),
patch.dict(
"sys.modules",
{
"proxy_server": mock_proxy_module,
"litellm.proxy.proxy_server": mock_proxy_module,
},
),
patch(
"litellm.proxy.proxy_cli.ProxyInitializationHelpers._get_default_unvicorn_init_args"
) as mock_get_args,
patch(
"litellm.proxy.proxy_cli.append_query_params",
side_effect=lambda url, params: str(url),
) as mock_append_query_params,
):
mock_get_args.return_value = {
"app": "litellm.proxy.proxy_server:app",
"host": "localhost",
"port": 8000,
}
result = runner.invoke(
run_server,
["--local", "--config", "test-config.yaml", "--skip_server_startup"],
)
assert (
result.exit_code == 0
), f"exit_code={result.exit_code}, output={result.output}"
mock_append_query_params.assert_called()
appended_params = mock_append_query_params.call_args.args[1]
assert appended_params["connect_timeout"] == 15
assert appended_params["socket_timeout"] == 120
assert appended_params["pgbouncer"] == "true"
assert appended_params["statement_cache_size"] == 0
def test_build_db_connection_url_params_disable_prepared_statements(self):
from litellm.proxy.proxy_cli import _build_db_connection_url_params
params = _build_db_connection_url_params(
connection_limit=10,
pool_timeout=60,
disable_prepared_statements=True,
)
assert params["pgbouncer"] == "true"
def test_build_db_connection_url_params_no_pgbouncer_by_default(self):
from litellm.proxy.proxy_cli import _build_db_connection_url_params
params = _build_db_connection_url_params(
connection_limit=10,
pool_timeout=60,
)
assert "pgbouncer" not in params
def test_build_db_connection_url_params_extra_pgbouncer_overrides_flag(self):
from litellm.proxy.proxy_cli import _build_db_connection_url_params
params = _build_db_connection_url_params(
connection_limit=10,
pool_timeout=60,
disable_prepared_statements=True,
extra_params={"pgbouncer": "false"},
)
assert params["pgbouncer"] == "false"
@pytest.mark.parametrize(
"config_value, expect_pgbouncer",
[
(True, True),
(False, False),
("true", True),
("false", False),
("not-a-bool", False),
],
)
@patch("subprocess.run")
@patch("atexit.register")
@patch("litellm.proxy.db.prisma_client.PrismaManager.setup_database")
@patch(
"litellm.proxy.db.prisma_client.should_update_prisma_schema", return_value=False
)
def test_disable_prepared_statements_forwarded_to_url(
self,
mock_should_update,
mock_setup_db,
mock_atexit_register,
mock_subprocess_run,
config_value,
expect_pgbouncer,
):
from click.testing import CliRunner
from litellm.proxy.proxy_cli import run_server
runner = CliRunner()
mock_subprocess_run.return_value = MagicMock(returncode=0)
mock_proxy_module = MagicMock(
app=MagicMock(),
ProxyConfig=MagicMock(),
KeyManagementSettings=MagicMock(),
save_worker_config=MagicMock(),
)
mock_proxy_module.ProxyConfig.return_value.get_config = AsyncMock(
return_value={
"general_settings": {
"database_url": "postgresql://test:test@localhost:5432/test",
"database_disable_prepared_statements": config_value,
}
}
)
clean_env = {
k: v
for k, v in os.environ.items()
if k not in ("DATABASE_URL", "DIRECT_URL")
}
with (
patch.dict(os.environ, clean_env, clear=True),
patch.dict(
"sys.modules",
{
"proxy_server": mock_proxy_module,
"litellm.proxy.proxy_server": mock_proxy_module,
},
),
patch(
"litellm.proxy.proxy_cli.ProxyInitializationHelpers._get_default_unvicorn_init_args"
) as mock_get_args,
patch(
"litellm.proxy.proxy_cli.append_query_params",
side_effect=lambda url, params: str(url),
) as mock_append_query_params,
):
mock_get_args.return_value = {
"app": "litellm.proxy.proxy_server:app",
"host": "localhost",
"port": 8000,
}
result = runner.invoke(
run_server,
["--local", "--config", "test-config.yaml", "--skip_server_startup"],
)
assert (
result.exit_code == 0
), f"exit_code={result.exit_code}, output={result.output}"
mock_append_query_params.assert_called()
appended_params = mock_append_query_params.call_args.args[1]
if expect_pgbouncer:
assert appended_params["pgbouncer"] == "true"
else:
assert "pgbouncer" not in appended_params
@patch("uvicorn.run")
@patch("atexit.register")
@patch("litellm.proxy.db.prisma_client.PrismaManager.setup_database")
@patch(
"litellm.proxy.db.prisma_client.should_update_prisma_schema", return_value=False
)
def test_proxy_default_api_version_uses_azure_default(
self, mock_should_update, mock_setup_db, mock_atexit_register, mock_uvicorn_run
):
"""Proxy default api_version should match litellm.AZURE_DEFAULT_API_VERSION for consistency."""
from click.testing import CliRunner
import litellm
from litellm.proxy.proxy_cli import run_server
runner = CliRunner()
mock_proxy_module = MagicMock(
app=MagicMock(),
ProxyConfig=MagicMock(),
KeyManagementSettings=MagicMock(),
save_worker_config=MagicMock(),
)
clean_env = {
k: v
for k, v in os.environ.items()
if k not in ("DATABASE_URL", "DIRECT_URL")
}
with (
patch.dict(os.environ, clean_env, clear=True),
patch.dict(
"sys.modules",
{
"proxy_server": mock_proxy_module,
"litellm.proxy.proxy_server": mock_proxy_module,
},
),
patch(
"litellm.proxy.proxy_cli.ProxyInitializationHelpers._get_default_unvicorn_init_args"
) as mock_get_args,
):
mock_get_args.return_value = {
"app": "litellm.proxy.proxy_server:app",
"host": "localhost",
"port": 8000,
}
result = runner.invoke(run_server, ["--local", "--skip_server_startup"])
assert (
result.exit_code == 0
), f"exit_code={result.exit_code}, output={result.output}"
mock_proxy_module.save_worker_config.assert_called_once()
call_kwargs = mock_proxy_module.save_worker_config.call_args[1]
assert call_kwargs["api_version"] == litellm.AZURE_DEFAULT_API_VERSION
@patch("uvicorn.run")
@patch("builtins.print")
@patch("litellm.proxy.db.prisma_client.PrismaManager.setup_database")
@patch(
"litellm.proxy.db.prisma_client.should_update_prisma_schema", return_value=False
)
def test_keepalive_timeout_flag(
self, mock_should_update, mock_setup_db, mock_print, mock_uvicorn_run
):
"""Test that the keepalive_timeout flag is properly passed to uvicorn"""
from click.testing import CliRunner
from litellm.proxy.proxy_cli import run_server
runner = CliRunner()
mock_app = MagicMock()
mock_proxy_config = MagicMock()
mock_key_mgmt = MagicMock()
mock_save_worker_config = MagicMock()
# Strip DATABASE_URL/DIRECT_URL so run_server doesn't enter the prisma
# DB-setup block (un-timeout'd `subprocess.run(["prisma"])` +
# migrate-deploy retry loop) — same isolation every other run_server
# test in this file uses.
clean_env = {
k: v
for k, v in os.environ.items()
if k not in ("DATABASE_URL", "DIRECT_URL")
}
with (
patch.dict(os.environ, clean_env, clear=True),
patch.dict(
"sys.modules",
{
"proxy_server": MagicMock(
app=mock_app,
ProxyConfig=mock_proxy_config,
KeyManagementSettings=mock_key_mgmt,
save_worker_config=mock_save_worker_config,
)
},
),
patch(
"litellm.proxy.proxy_cli.ProxyInitializationHelpers._get_default_unvicorn_init_args"
) as mock_get_args,
patch(
"litellm.proxy.proxy_cli.ProxyInitializationHelpers._is_port_in_use",
return_value=False,
),
build: migrate packaging, CI, and Docker from Poetry to uv (#25007) * build: migrate packaging metadata to uv * ci: move automation and local tooling to uv * docker: migrate image builds and runtime setup to uv * docs: update install and deployment guidance for uv * chore: align auxiliary scripts and tests with uv * test: harden test_litellm isolation * fix: keep release and health check images self-contained * build: pin uv tooling and health check deps * test: isolate bedrock image request formatting from suite state * test: cover sandbox executor requirements flow * ci: fix circleci no-op command steps * ci: fix circleci publish workflow parsing * fix: stabilize remaining uv migration CI checks * ci: increase matrix test timeout headroom * fix: restore published docker and license coverage * fix: restore proxy runtime build parity * fix: restore proxy extras parity and venv migrations * ci: persist uv path across circleci steps * fix: keep psycopg binary in default test env * docker: preserve prisma cache across stages * test: run local proxy checks through uv python * build: restore runtime deps moved into ci * build: refresh uv lock after upstream merge * fix: restore module import in test_check_migration after merge The conflict resolution imported only the function but the test body references check_migration as a module throughout. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix: revert dependency promotions, remove nodejs-wheel-binaries, fix Docker layer caching - Move google-generativeai, Pillow, tenacity back to ci group (they are lazily imported and bloat the base SDK install needlessly) - Remove nodejs-wheel-binaries from extra_proxy and proxy-dev (redundant in Docker where system Node.js is already installed via apk) - Remove all nodejs-wheel node replacement and venv npm patching blocks from Dockerfiles since the wheel is no longer installed - Add --no-default-groups to CodSpeed benchmark workflow so the benchmark environment matches the old minimal pip install footprint - Apply standard uv two-phase Docker pattern: copy metadata first, install deps (cached layer), then copy source and install project - Replace CircleCI enterprise no-op with proper uv sync command Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * chore: regenerate uv.lock after removing nodejs-wheel-binaries Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix(ci): use cache/restore instead of cache to prevent cache poisoning The old workflow used actions/cache/restore (read-only). The uv migration changed it to actions/cache (read-write), which zizmor flags as a cache poisoning risk. Restore the safer read-only variant. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix(ci): disable setup-uv built-in cache to silence cache-poisoning alert The setup-uv action enables caching by default, which zizmor flags as a cache poisoning risk. Disable it since we already use a read-only cache/restore step. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix(ci): disable setup-uv cache in publish workflow Silences zizmor cache-poisoning alert. Publishing workflow runs infrequently on protected branches so caching adds no real benefit. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix(test): remove duplicate verbose_logger mock in test_check_migration The logger was patched twice — first via mocker.patch() then via mocker.patch.object(autospec=True). The second call fails because autospec cannot inspect an already-mocked attribute. Remove the redundant first patch. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix(ci): free disk space before Docker build in test-server-root-path The Dockerfile.non_root build ran out of disk on the CI runner. Remove Android SDK, .NET, Boost, and GHC toolchains (~12GB) to free space. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-10 02:46:23 +08:00
):
mock_get_args.return_value = {
"app": "litellm.proxy.proxy_server:app",
"host": "localhost",
"port": 8000,
"timeout_keep_alive": 30,
}
result = runner.invoke(run_server, ["--local", "--keepalive_timeout", "30"])
assert result.exit_code == 0
mock_get_args.assert_called_once_with(
host="0.0.0.0",
port=4000,
log_config=None,
keepalive_timeout=30,
timeout_worker_healthcheck=None,
)
mock_uvicorn_run.assert_called_once()
# Check that the uvicorn.run was called with the timeout_keep_alive parameter
call_args = mock_uvicorn_run.call_args
assert call_args[1]["timeout_keep_alive"] == 30
@patch("uvicorn.run")
@patch("builtins.print")
@patch("litellm.proxy.db.prisma_client.PrismaManager.setup_database")
@patch(
"litellm.proxy.db.prisma_client.should_update_prisma_schema", return_value=False
)
def test_timeout_worker_healthcheck_flag(
self, mock_should_update, mock_setup_db, mock_print, mock_uvicorn_run
):
"""Test that the --timeout_worker_healthcheck flag is threaded through to the uvicorn init helper."""
from click.testing import CliRunner
from litellm.proxy.proxy_cli import run_server
runner = CliRunner()
mock_app = MagicMock()
mock_proxy_config = MagicMock()
mock_key_mgmt = MagicMock()
mock_save_worker_config = MagicMock()
# Strip DATABASE_URL/DIRECT_URL so run_server doesn't enter the prisma
# DB-setup block (un-timeout'd `subprocess.run(["prisma"])` +
# migrate-deploy retry loop) — same isolation every other run_server
# test in this file uses.
clean_env = {
k: v
for k, v in os.environ.items()
if k not in ("DATABASE_URL", "DIRECT_URL")
}
with (
patch.dict(os.environ, clean_env, clear=True),
patch.dict(
"sys.modules",
{
"proxy_server": MagicMock(
app=mock_app,
ProxyConfig=mock_proxy_config,
KeyManagementSettings=mock_key_mgmt,
save_worker_config=mock_save_worker_config,
)
},
),
patch(
"litellm.proxy.proxy_cli.ProxyInitializationHelpers._get_default_unvicorn_init_args"
) as mock_get_args,
patch(
"litellm.proxy.proxy_cli.ProxyInitializationHelpers._is_port_in_use",
return_value=False,
),
):
mock_get_args.return_value = {
"app": "litellm.proxy.proxy_server:app",
"host": "localhost",
"port": 8000,
}
result = runner.invoke(
run_server, ["--local", "--timeout_worker_healthcheck", "15"]
)
assert result.exit_code == 0
mock_get_args.assert_called_once_with(
host="0.0.0.0",
port=4000,
log_config=None,
keepalive_timeout=None,
timeout_worker_healthcheck=15,
)
2025-09-29 00:13:40 +08:00
@patch("uvicorn.run")
@patch("builtins.print")
2026-02-26 15:12:27 +08:00
@patch("litellm.proxy.db.prisma_client.PrismaManager.setup_database")
def test_max_requests_before_restart_flag(
self, mock_setup_db, mock_print, mock_uvicorn_run
):
2025-09-29 00:13:40 +08:00
"""Test that the max_requests_before_restart flag is passed to uvicorn as limit_max_requests"""
from click.testing import CliRunner
from litellm.proxy.proxy_cli import run_server
runner = CliRunner()
mock_app = MagicMock()
mock_proxy_config = MagicMock()
mock_key_mgmt = MagicMock()
mock_save_worker_config = MagicMock()
clean_env = {
k: v
for k, v in os.environ.items()
if k not in ("DATABASE_URL", "DIRECT_URL")
}
with (
patch.dict(
os.environ,
clean_env,
clear=True,
),
patch.dict(
"sys.modules",
{
"proxy_server": MagicMock(
app=mock_app,
ProxyConfig=mock_proxy_config,
KeyManagementSettings=mock_key_mgmt,
save_worker_config=mock_save_worker_config,
)
},
),
patch(
"litellm.proxy.proxy_cli.ProxyInitializationHelpers._get_default_unvicorn_init_args"
) as mock_get_args,
):
2025-09-29 00:13:40 +08:00
mock_get_args.return_value = {
"app": "litellm.proxy.proxy_server:app",
"host": "localhost",
"port": 8000,
}
result = runner.invoke(
run_server, ["--local", "--max_requests_before_restart", "123"]
)
assert (
result.exit_code == 0
), f"exit_code={result.exit_code}, output={result.output}"
2025-09-29 00:13:40 +08:00
mock_uvicorn_run.assert_called_once()
# Check that uvicorn.run was called with limit_max_requests parameter
call_args = mock_uvicorn_run.call_args
assert call_args[1]["limit_max_requests"] == 123
@patch.dict(os.environ, {}, clear=True)
def test_construct_database_url_from_env_vars(self):
"""Test the construct_database_url_from_env_vars function with various scenarios"""
from litellm.proxy.utils import construct_database_url_from_env_vars
# Test with all required variables present
test_env = {
"DATABASE_HOST": "localhost:5432",
"DATABASE_USERNAME": "testuser",
"DATABASE_PASSWORD": "testpass",
"DATABASE_NAME": "testdb",
}
with patch.dict(os.environ, test_env):
result = construct_database_url_from_env_vars()
expected_url = "postgresql://testuser:testpass@localhost:5432/testdb"
assert result == expected_url
# Test with special characters that need URL encoding
test_env_special = {
"DATABASE_HOST": "localhost:5432",
"DATABASE_USERNAME": "user@with+special",
"DATABASE_PASSWORD": "test-password-special-chars",
"DATABASE_NAME": "db_name/test",
}
with patch.dict(os.environ, test_env_special):
result = construct_database_url_from_env_vars()
expected_url = "postgresql://user%40with%2Bspecial:test-password-special-chars@localhost:5432/db_name%2Ftest"
assert result == expected_url
# Test without password (should still work)
test_env_no_password = {
"DATABASE_HOST": "localhost:5432",
"DATABASE_USERNAME": "testuser",
"DATABASE_NAME": "testdb",
}
with patch.dict(os.environ, test_env_no_password):
result = construct_database_url_from_env_vars()
expected_url = "postgresql://testuser@localhost:5432/testdb"
assert result == expected_url
# Test with missing required variables (should return None)
test_env_missing = {
"DATABASE_HOST": "localhost:5432",
"DATABASE_USERNAME": "testuser",
# Missing DATABASE_NAME
}
with patch.dict(os.environ, test_env_missing):
result = construct_database_url_from_env_vars()
assert result is None
# Test with empty environment (should return None)
with patch.dict(os.environ, {}, clear=True):
result = construct_database_url_from_env_vars()
assert result is None
@patch("uvicorn.run")
@patch("builtins.print")
def test_run_server_no_config_passed(self, mock_print, mock_uvicorn_run):
"""Test that run_server properly handles the case when no config is passed"""
import asyncio
from click.testing import CliRunner
from litellm.proxy.proxy_cli import run_server
runner = CliRunner()
mock_app = MagicMock()
mock_proxy_config = MagicMock()
mock_key_mgmt = MagicMock()
mock_save_worker_config = MagicMock()
# Mock the ProxyConfig.get_config method to return a proper async config
async def mock_get_config(config_file_path=None):
return {"general_settings": {}, "litellm_settings": {}}
mock_proxy_config_instance = MagicMock()
mock_proxy_config_instance.get_config = mock_get_config
mock_proxy_config.return_value = mock_proxy_config_instance
2026-02-17 06:45:05 +08:00
mock_proxy_server_module = MagicMock(app=mock_app)
# Only remove DATABASE_URL and DIRECT_URL to prevent the database setup
# code path from running. Do NOT use clear=True as it removes PATH, HOME,
# etc., which causes imports inside run_server to break in CI (the real
# litellm.proxy.proxy_server import at line 820 of proxy_cli.py has heavy
# side effects that fail without a proper environment).
env_overrides = {
"DATABASE_URL": "",
"DIRECT_URL": "",
"IAM_TOKEN_DB_AUTH": "",
"USE_AWS_KMS": "",
}
with patch.dict(os.environ, env_overrides):
# Remove DATABASE_URL entirely so the DB setup block is skipped
os.environ.pop("DATABASE_URL", None)
os.environ.pop("DIRECT_URL", None)
with (
patch.dict(
"sys.modules",
{
"proxy_server": MagicMock(
app=mock_app,
ProxyConfig=mock_proxy_config,
KeyManagementSettings=mock_key_mgmt,
save_worker_config=mock_save_worker_config,
),
# Also mock litellm.proxy.proxy_server to prevent the real
# import at line 820 of proxy_cli.py which has heavy side
# effects (FastAPI app init, logging setup, etc.)
"litellm.proxy.proxy_server": mock_proxy_server_module,
},
),
patch(
"litellm.proxy.proxy_cli.ProxyInitializationHelpers._get_default_unvicorn_init_args"
) as mock_get_args,
):
mock_get_args.return_value = {
"app": "litellm.proxy.proxy_server:app",
"host": "localhost",
"port": 8000,
}
# Test with no config parameter (config=None)
result = runner.invoke(run_server, ["--local"])
2026-02-17 06:45:05 +08:00
assert result.exit_code == 0, (
f"run_server failed with exit_code={result.exit_code}, "
f"output={result.output}, exception={result.exception}"
)
# Verify that uvicorn.run was called
mock_uvicorn_run.assert_called_once()
# Reset mocks for second test
mock_uvicorn_run.reset_mock()
# Test with explicit --config None (should behave the same)
result = runner.invoke(run_server, ["--local", "--config", "None"])
2026-02-17 06:45:05 +08:00
assert result.exit_code == 0, (
f"run_server failed with exit_code={result.exit_code}, "
f"output={result.output}, exception={result.exception}"
)
# Verify that uvicorn.run was called again
mock_uvicorn_run.assert_called_once()
2026-05-08 07:04:56 +08:00
class TestRunServerDbSetup:
"""Tests for run_server's prisma setup_database behavior."""
@patch("subprocess.run")
@patch("atexit.register")
@patch("litellm.proxy.db.prisma_client.PrismaManager.setup_database")
@patch("litellm.proxy.db.check_migration.check_prisma_schema_diff")
@patch("litellm.proxy.db.prisma_client.should_update_prisma_schema")
def test_use_prisma_db_push_flag_behavior(
self,
mock_should_update_schema,
mock_check_schema_diff,
mock_setup_database,
mock_atexit_register,
mock_subprocess_run,
):
"""Test that use_prisma_db_push flag correctly controls PrismaManager.setup_database use_migrate parameter"""
from litellm.proxy.proxy_cli import run_server
# Mock subprocess.run to simulate prisma being available
mock_subprocess_run.return_value = MagicMock(returncode=0)
# Mock should_update_prisma_schema to return True (so setup_database gets called)
mock_should_update_schema.return_value = True
mock_proxy_module = MagicMock(
app=MagicMock(),
ProxyConfig=MagicMock(),
KeyManagementSettings=MagicMock(),
save_worker_config=MagicMock(),
)
clean_env = {
k: v
for k, v in os.environ.items()
if k not in ("DATABASE_URL", "DIRECT_URL")
}
clean_env["DATABASE_URL"] = "postgresql://test:test@localhost:5432/test"
with (
patch.dict(os.environ, clean_env, clear=True),
patch.dict(
"sys.modules",
{
"proxy_server": mock_proxy_module,
"litellm.proxy.proxy_server": mock_proxy_module,
},
),
patch(
"litellm.proxy.proxy_cli.ProxyInitializationHelpers._get_default_unvicorn_init_args"
) as mock_get_args,
):
mock_get_args.return_value = {
"app": "litellm.proxy.proxy_server:app",
"host": "localhost",
"port": 8000,
}
# Use standalone_mode=False to bypass Click's CliRunner stream
# isolation which causes flaky "I/O operation on closed file"
# errors in CI environments (Click 8.3.x stream lifecycle issue).
# Test 1: Without --use_prisma_db_push flag (default behavior)
# use_prisma_db_push should be False (default), so use_migrate should be True
run_server.main(["--local", "--skip_server_startup"], standalone_mode=False)
mock_setup_database.assert_called_with(
use_migrate=True, use_v2_resolver=False
)
# Reset mocks
mock_setup_database.reset_mock()
mock_should_update_schema.reset_mock()
mock_should_update_schema.return_value = True
# Test 2: With --use_prisma_db_push flag set
# use_prisma_db_push should be True, so use_migrate should be False
run_server.main(
["--local", "--skip_server_startup", "--use_prisma_db_push"],
standalone_mode=False,
)
mock_setup_database.assert_called_with(
use_migrate=False, use_v2_resolver=False
)
Gflags worker parameters (#22931) * feat: add LITELLM_WORKER_STARTUP_HOOKS for per-worker initialization (gflags support) Add support for running user-defined startup hooks in each worker process during proxy_startup_event. This enables re-initialization of in-process state (like gflags.FLAGS) that doesn't survive uvicorn worker spawning. Usage: export LITELLM_WORKER_STARTUP_HOOKS=mymodule:init_fn,other:setup_fn Hooks run early in proxy_startup_event (before config/DB loading). Supports both sync and async callables. Errors propagate to prevent broken workers from serving traffic. No-op when env var is unset. Includes 5 tests covering sync/async hooks, multiple hooks, error propagation, and no-hooks-set scenarios. Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> * docs: add Worker Startup Hooks page with gflags usage example - New docs page: docs/proxy/worker_startup_hooks.md - Explains the problem (per-process state lost in multi-worker deployments) - Full gflags example with wrapper module and startup script - Covers multiple hooks, async hooks, error behavior - Architecture diagram showing master→worker flow - Added LITELLM_WORKER_STARTUP_HOOKS to config_settings.md env var table - Added to sidebar under Setup & Deployment Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> * Update litellm/proxy/proxy_server.py Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com> * Apply suggestion from @greptile-apps[bot] Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com> --------- Co-authored-by: Cursor Agent <cursoragent@cursor.com> Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
2026-03-07 10:09:57 +08:00
@patch("subprocess.run")
@patch("atexit.register")
@patch("litellm.proxy.db.prisma_client.PrismaManager.setup_database")
@patch("litellm.proxy.db.check_migration.check_prisma_schema_diff")
@patch("litellm.proxy.db.prisma_client.should_update_prisma_schema")
def test_startup_fails_when_db_setup_fails(
self,
mock_should_update_schema,
mock_check_schema_diff,
mock_setup_database,
mock_atexit_register,
mock_subprocess_run,
):
[Infra] Merging RC Branch with Main (#23786) * fix(test): add missing mocks for test_streamable_http_mcp_handler_mock The test was missing mocks for extract_mcp_auth_context and set_auth_context, causing the handler to fail silently in the except block instead of reaching session_manager.handle_request. This mirrors the fix already applied to the sibling test_sse_mcp_handler_mock. Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> * fix(ci): route OpenAI models through chat completions in pass-through tests The test_anthropic_messages_openai_model_streaming_cost_injection test fails because the OpenAI Responses API returns 400 for requests routed through the Anthropic Messages endpoint. Setting LITELLM_USE_CHAT_COMPLETIONS_URL_FOR_ANTHROPIC_MESSAGES=true routes OpenAI models through the stable chat completions path instead. Cost injection still works since it happens at the proxy level. Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> * fix(ci): fix assemblyai custom auth and router wildcard test flakiness 1. custom_auth_basic.py: Add user_role='proxy_admin' so the custom auth user can access management endpoints like /key/generate. The test test_assemblyai_transcribe_with_non_admin_key was hidden behind an earlier -x failure and was never reached before. 2. test_router_utils.py: Add flaky(retries=3) and increase sleep from 1s to 2s for test_router_get_model_group_usage_wildcard_routes. The async callback needs time to write usage to cache, and 1s is insufficient on slower CI hardware. Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> * ci: retrigger CI pipeline Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> * fix(mypy): use LitellmUserRoles enum instead of raw string in custom_auth_basic Fixes mypy error: Argument 'user_role' has incompatible type 'str'; expected 'LitellmUserRoles | None' Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> * fix: don't close HTTP/SDK clients on LLMClientCache eviction (#22926) * fix: don't close HTTP/SDK clients on LLMClientCache eviction Removing the _remove_key override that eagerly called aclose()/close() on evicted clients. Evicted clients may still be held by in-flight streaming requests; closing them causes: RuntimeError: Cannot send a request, as the client has been closed. This is a regression from commit fb72979432. Clients that are no longer referenced will be garbage-collected naturally. Explicit shutdown cleanup happens via close_litellm_async_clients(). Fixes production crashes after the 1-hour cache TTL expires. * test: update LLMClientCache unit tests for no-close-on-eviction behavior Flip the assertions: evicted clients must NOT be closed. Replace test_remove_key_closes_async_client → test_remove_key_does_not_close_async_client and equivalents for sync/eviction paths. Add test_remove_key_removes_plain_values for non-client cache entries. Remove test_background_tasks_cleaned_up_after_completion (no more _background_tasks). Remove test_remove_key_no_event_loop variant that depended on old behavior. * test: add e2e tests for OpenAI SDK client surviving cache eviction Add two new e2e tests using real AsyncOpenAI clients: - test_evicted_openai_sdk_client_stays_usable: verifies size-based eviction doesn't close the client - test_ttl_expired_openai_sdk_client_stays_usable: verifies TTL expiry eviction doesn't close the client Both tests sleep after eviction so any create_task()-based close would have time to run, making the regression detectable. Also expand the module docstring to explain why the sleep is required. * docs(AGENTS.md): add rule — never close HTTP/SDK clients on cache eviction * docs(CLAUDE.md): add HTTP client cache safety guideline * [Fix] Install bsdmainutils for column command in security scans The security_scans.sh script uses `column` to format vulnerability output, but the package wasn't installed in the CI environment. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: handle string callback values in prometheus multiproc setup When callbacks are configured as a plain string (e.g., `callbacks: "my_callback"`) instead of a list, the proxy crashes on startup with: TypeError: can only concatenate str (not "list") to str Normalize each callback setting to a list before concatenating. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * bump: version 1.82.2 → 1.82.3 * fix(test): update test_startup_fails_when_db_setup_fails for opt-in enforcement The --enforce_prisma_migration_check flag is now required to trigger sys.exit(1) on DB migration failure, after #23675 flipped the default behavior to warn-and-continue. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(cost_calculator): use model name for per-request custom pricing when router_model_id has no pricing When custom pricing is passed as per-request kwargs (input_cost_per_token/output_cost_per_token), completion() registers pricing under the model name, but _select_model_name_for_cost_calc was selecting the router deployment hash (which has no pricing data), causing response_cost to be 0.0. Now checks whether the router_model_id entry actually has pricing before preferring it. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> --------- Co-authored-by: Cursor Agent <cursoragent@cursor.com> Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com> Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-17 06:32:20 +08:00
"""Test that proxy exits with code 1 when PrismaManager.setup_database returns False and --enforce_prisma_migration_check is set"""
from litellm.proxy.proxy_cli import run_server
mock_subprocess_run.return_value = MagicMock(returncode=0)
mock_should_update_schema.return_value = True
mock_setup_database.return_value = False
mock_proxy_module = MagicMock(
app=MagicMock(),
ProxyConfig=MagicMock(),
KeyManagementSettings=MagicMock(),
save_worker_config=MagicMock(),
)
clean_env = {
k: v
for k, v in os.environ.items()
if k not in ("DATABASE_URL", "DIRECT_URL")
}
clean_env["DATABASE_URL"] = "postgresql://test:test@localhost:5432/test"
with (
patch.dict(os.environ, clean_env, clear=True),
patch.dict(
"sys.modules",
{
"proxy_server": mock_proxy_module,
"litellm.proxy.proxy_server": mock_proxy_module,
},
),
patch(
"litellm.proxy.proxy_cli.ProxyInitializationHelpers._get_default_unvicorn_init_args"
) as mock_get_args,
):
mock_get_args.return_value = {
"app": "litellm.proxy.proxy_server:app",
"host": "localhost",
"port": 8000,
}
with pytest.raises(SystemExit) as exc_info:
run_server.main(
[
"--local",
"--skip_server_startup",
"--enforce_prisma_migration_check",
],
standalone_mode=False,
)
assert exc_info.value.code == 1
mock_setup_database.assert_called_once_with(
use_migrate=True, use_v2_resolver=False
)
Gflags worker parameters (#22931) * feat: add LITELLM_WORKER_STARTUP_HOOKS for per-worker initialization (gflags support) Add support for running user-defined startup hooks in each worker process during proxy_startup_event. This enables re-initialization of in-process state (like gflags.FLAGS) that doesn't survive uvicorn worker spawning. Usage: export LITELLM_WORKER_STARTUP_HOOKS=mymodule:init_fn,other:setup_fn Hooks run early in proxy_startup_event (before config/DB loading). Supports both sync and async callables. Errors propagate to prevent broken workers from serving traffic. No-op when env var is unset. Includes 5 tests covering sync/async hooks, multiple hooks, error propagation, and no-hooks-set scenarios. Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> * docs: add Worker Startup Hooks page with gflags usage example - New docs page: docs/proxy/worker_startup_hooks.md - Explains the problem (per-process state lost in multi-worker deployments) - Full gflags example with wrapper module and startup script - Covers multiple hooks, async hooks, error behavior - Architecture diagram showing master→worker flow - Added LITELLM_WORKER_STARTUP_HOOKS to config_settings.md env var table - Added to sidebar under Setup & Deployment Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> * Update litellm/proxy/proxy_server.py Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com> * Apply suggestion from @greptile-apps[bot] Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com> --------- Co-authored-by: Cursor Agent <cursoragent@cursor.com> Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
2026-03-07 10:09:57 +08:00
# --- Module-level helpers for worker startup hook tests ---
_dummy_hook_called = False
def _dummy_hook():
"""A simple sync hook used by test_should_run_worker_startup_hooks."""
global _dummy_hook_called
_dummy_hook_called = True
_dummy_async_hook_called = False
async def _dummy_async_hook():
"""A simple async hook used by test_should_run_async_worker_startup_hook."""
global _dummy_async_hook_called
_dummy_async_hook_called = True
def _failing_hook():
"""A hook that always raises, used by test_should_raise_on_failing_hook."""
raise RuntimeError("Hook failed on purpose")
class TestWorkerStartupHooks:
"""Tests for the LITELLM_WORKER_STARTUP_HOOKS mechanism in proxy_startup_event."""
@pytest.mark.asyncio
async def test_should_run_worker_startup_hooks(self):
"""Sync worker startup hook is called during proxy_startup_event."""
global _dummy_hook_called
_dummy_hook_called = False
from litellm.proxy.proxy_server import proxy_startup_event
env_overrides = {
"LITELLM_WORKER_STARTUP_HOOKS": "tests.test_litellm.proxy.test_proxy_cli:_dummy_hook",
}
# Remove DATABASE_URL to avoid real DB setup
clean_env = {
k: v
for k, v in os.environ.items()
if k not in ("DATABASE_URL", "DIRECT_URL")
Gflags worker parameters (#22931) * feat: add LITELLM_WORKER_STARTUP_HOOKS for per-worker initialization (gflags support) Add support for running user-defined startup hooks in each worker process during proxy_startup_event. This enables re-initialization of in-process state (like gflags.FLAGS) that doesn't survive uvicorn worker spawning. Usage: export LITELLM_WORKER_STARTUP_HOOKS=mymodule:init_fn,other:setup_fn Hooks run early in proxy_startup_event (before config/DB loading). Supports both sync and async callables. Errors propagate to prevent broken workers from serving traffic. No-op when env var is unset. Includes 5 tests covering sync/async hooks, multiple hooks, error propagation, and no-hooks-set scenarios. Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> * docs: add Worker Startup Hooks page with gflags usage example - New docs page: docs/proxy/worker_startup_hooks.md - Explains the problem (per-process state lost in multi-worker deployments) - Full gflags example with wrapper module and startup script - Covers multiple hooks, async hooks, error behavior - Architecture diagram showing master→worker flow - Added LITELLM_WORKER_STARTUP_HOOKS to config_settings.md env var table - Added to sidebar under Setup & Deployment Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> * Update litellm/proxy/proxy_server.py Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com> * Apply suggestion from @greptile-apps[bot] Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com> --------- Co-authored-by: Cursor Agent <cursoragent@cursor.com> Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
2026-03-07 10:09:57 +08:00
}
clean_env.update(env_overrides)
with patch.dict(os.environ, clean_env, clear=True):
try:
async with proxy_startup_event(app=None) as _:
pass
except Exception:
pass # We expect errors after the hook (no DB, etc.)
assert _dummy_hook_called is True, "Sync startup hook was not called"
@pytest.mark.asyncio
async def test_should_run_async_worker_startup_hook(self):
"""Async worker startup hook is awaited during proxy_startup_event."""
global _dummy_async_hook_called
_dummy_async_hook_called = False
from litellm.proxy.proxy_server import proxy_startup_event
env_overrides = {
"LITELLM_WORKER_STARTUP_HOOKS": "tests.test_litellm.proxy.test_proxy_cli:_dummy_async_hook",
}
clean_env = {
k: v
for k, v in os.environ.items()
if k not in ("DATABASE_URL", "DIRECT_URL")
Gflags worker parameters (#22931) * feat: add LITELLM_WORKER_STARTUP_HOOKS for per-worker initialization (gflags support) Add support for running user-defined startup hooks in each worker process during proxy_startup_event. This enables re-initialization of in-process state (like gflags.FLAGS) that doesn't survive uvicorn worker spawning. Usage: export LITELLM_WORKER_STARTUP_HOOKS=mymodule:init_fn,other:setup_fn Hooks run early in proxy_startup_event (before config/DB loading). Supports both sync and async callables. Errors propagate to prevent broken workers from serving traffic. No-op when env var is unset. Includes 5 tests covering sync/async hooks, multiple hooks, error propagation, and no-hooks-set scenarios. Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> * docs: add Worker Startup Hooks page with gflags usage example - New docs page: docs/proxy/worker_startup_hooks.md - Explains the problem (per-process state lost in multi-worker deployments) - Full gflags example with wrapper module and startup script - Covers multiple hooks, async hooks, error behavior - Architecture diagram showing master→worker flow - Added LITELLM_WORKER_STARTUP_HOOKS to config_settings.md env var table - Added to sidebar under Setup & Deployment Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> * Update litellm/proxy/proxy_server.py Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com> * Apply suggestion from @greptile-apps[bot] Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com> --------- Co-authored-by: Cursor Agent <cursoragent@cursor.com> Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
2026-03-07 10:09:57 +08:00
}
clean_env.update(env_overrides)
with patch.dict(os.environ, clean_env, clear=True):
try:
async with proxy_startup_event(app=None) as _:
pass
except Exception:
pass
assert _dummy_async_hook_called is True, "Async startup hook was not called"
@pytest.mark.asyncio
async def test_should_raise_on_failing_worker_startup_hook(self):
"""A failing worker startup hook propagates the error."""
from litellm.proxy.proxy_server import proxy_startup_event
env_overrides = {
"LITELLM_WORKER_STARTUP_HOOKS": "tests.test_litellm.proxy.test_proxy_cli:_failing_hook",
}
clean_env = {
k: v
for k, v in os.environ.items()
if k not in ("DATABASE_URL", "DIRECT_URL")
Gflags worker parameters (#22931) * feat: add LITELLM_WORKER_STARTUP_HOOKS for per-worker initialization (gflags support) Add support for running user-defined startup hooks in each worker process during proxy_startup_event. This enables re-initialization of in-process state (like gflags.FLAGS) that doesn't survive uvicorn worker spawning. Usage: export LITELLM_WORKER_STARTUP_HOOKS=mymodule:init_fn,other:setup_fn Hooks run early in proxy_startup_event (before config/DB loading). Supports both sync and async callables. Errors propagate to prevent broken workers from serving traffic. No-op when env var is unset. Includes 5 tests covering sync/async hooks, multiple hooks, error propagation, and no-hooks-set scenarios. Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> * docs: add Worker Startup Hooks page with gflags usage example - New docs page: docs/proxy/worker_startup_hooks.md - Explains the problem (per-process state lost in multi-worker deployments) - Full gflags example with wrapper module and startup script - Covers multiple hooks, async hooks, error behavior - Architecture diagram showing master→worker flow - Added LITELLM_WORKER_STARTUP_HOOKS to config_settings.md env var table - Added to sidebar under Setup & Deployment Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> * Update litellm/proxy/proxy_server.py Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com> * Apply suggestion from @greptile-apps[bot] Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com> --------- Co-authored-by: Cursor Agent <cursoragent@cursor.com> Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
2026-03-07 10:09:57 +08:00
}
clean_env.update(env_overrides)
with patch.dict(os.environ, clean_env, clear=True):
with pytest.raises(RuntimeError, match="Hook failed on purpose"):
async with proxy_startup_event(app=None) as _:
pass
def test_should_skip_when_no_hooks_set(self):
"""When LITELLM_WORKER_STARTUP_HOOKS is not set, no hooks are executed."""
global _dummy_hook_called
_dummy_hook_called = False
with patch.dict(os.environ, {}, clear=False):
os.environ.pop("LITELLM_WORKER_STARTUP_HOOKS", None)
# The hook block should be skipped entirely when env var is absent
assert "LITELLM_WORKER_STARTUP_HOOKS" not in os.environ
# Verify that an empty env var value also results in no hook execution
assert os.environ.get("LITELLM_WORKER_STARTUP_HOOKS", "") == ""
@pytest.mark.asyncio
async def test_should_run_multiple_hooks(self):
"""Multiple comma-separated hooks are all called."""
global _dummy_hook_called, _dummy_async_hook_called
_dummy_hook_called = False
_dummy_async_hook_called = False
from litellm.proxy.proxy_server import proxy_startup_event
hooks = (
"tests.test_litellm.proxy.test_proxy_cli:_dummy_hook,"
"tests.test_litellm.proxy.test_proxy_cli:_dummy_async_hook"
)
env_overrides = {
"LITELLM_WORKER_STARTUP_HOOKS": hooks,
}
clean_env = {
k: v
for k, v in os.environ.items()
if k not in ("DATABASE_URL", "DIRECT_URL")
Gflags worker parameters (#22931) * feat: add LITELLM_WORKER_STARTUP_HOOKS for per-worker initialization (gflags support) Add support for running user-defined startup hooks in each worker process during proxy_startup_event. This enables re-initialization of in-process state (like gflags.FLAGS) that doesn't survive uvicorn worker spawning. Usage: export LITELLM_WORKER_STARTUP_HOOKS=mymodule:init_fn,other:setup_fn Hooks run early in proxy_startup_event (before config/DB loading). Supports both sync and async callables. Errors propagate to prevent broken workers from serving traffic. No-op when env var is unset. Includes 5 tests covering sync/async hooks, multiple hooks, error propagation, and no-hooks-set scenarios. Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> * docs: add Worker Startup Hooks page with gflags usage example - New docs page: docs/proxy/worker_startup_hooks.md - Explains the problem (per-process state lost in multi-worker deployments) - Full gflags example with wrapper module and startup script - Covers multiple hooks, async hooks, error behavior - Architecture diagram showing master→worker flow - Added LITELLM_WORKER_STARTUP_HOOKS to config_settings.md env var table - Added to sidebar under Setup & Deployment Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> * Update litellm/proxy/proxy_server.py Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com> * Apply suggestion from @greptile-apps[bot] Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com> --------- Co-authored-by: Cursor Agent <cursoragent@cursor.com> Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com> Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
2026-03-07 10:09:57 +08:00
}
clean_env.update(env_overrides)
with patch.dict(os.environ, clean_env, clear=True):
try:
async with proxy_startup_event(app=None) as _:
pass
except Exception:
pass
assert _dummy_hook_called is True, "First hook was not called"
assert _dummy_async_hook_called is True, "Second hook was not called"