forked from phoenix/litellm-mirror
* fix(ollama.py): fix get model info request Fixes https://github.com/BerriAI/litellm/issues/6703 * feat(anthropic/chat/transformation.py): support passing user id to anthropic via openai 'user' param * docs(anthropic.md): document all supported openai params for anthropic * test: fix tests * fix: fix tests * feat(jina_ai/): add rerank support Closes https://github.com/BerriAI/litellm/issues/6691 * test: handle service unavailable error * fix(handler.py): refactor together ai rerank call * test: update test to handle overloaded error * test: fix test * Litellm router trace (#6742) * feat(router.py): add trace_id to parent functions - allows tracking retry/fallbacks * feat(router.py): log trace id across retry/fallback logic allows grouping llm logs for the same request * test: fix tests * fix: fix test * fix(transformation.py): only set non-none stop_sequences * Litellm router disable fallbacks (#6743) * bump: version 1.52.6 → 1.52.7 * feat(router.py): enable dynamically disabling fallbacks Allows for enabling/disabling fallbacks per key * feat(litellm_pre_call_utils.py): support setting 'disable_fallbacks' on litellm key * test: fix test * fix(exception_mapping_utils.py): map 'model is overloaded' to internal server error * fix(lm_studio/embed): support translating lm studio optional params ' * feat(auth_checks.py): fix auth check inside route - `/team/list` Fixes regression where non-admin w/ user_id=None able to query all teams * docs proxy_budget_rescheduler_min_time * helm run DISABLE_SCHEMA_UPDATE * docs helm pre sync hook * fix migration job.yaml * fix DATABASE_URL * use existing spec for migrations job * fix yaml on migrations job * fix migration job * update doc on pre sync hook * fix migrations-job.yaml * fix migration job * fix prisma migration * test - handle eol model claude-2, use claude-2.1 instead * (docs) add instructions on how to contribute to docker image * Update code blocks huggingface.md (#6737) * Update prefix.md (#6734) * fix test_supports_response_schema * mark Helm PreSyn as BETA * (Feat) Add support for storing virtual keys in AWS SecretManager (#6728) * add SecretManager to httpxSpecialProvider * fix importing AWSSecretsManagerV2 * add unit testing for writing keys to AWS secret manager * use KeyManagementEventHooks for key/generated events * us event hooks for key management endpoints * working AWSSecretsManagerV2 * fix write secret to AWS secret manager on /key/generate * fix KeyManagementSettings * use tasks for key management hooks * add async_delete_secret * add test for async_delete_secret * use _delete_virtual_keys_from_secret_manager * fix test secret manager * test_key_generate_with_secret_manager_call * fix check for key_management_settings * sync_read_secret * test_aws_secret_manager * fix sync_read_secret * use helper to check when _should_read_secret_from_secret_manager * test_get_secret_with_access_mode * test - handle eol model claude-2, use claude-2.1 instead * docs AWS secret manager * fix test_read_nonexistent_secret * fix test_supports_response_schema * ci/cd run again * LiteLLM Minor Fixes & Improvement (11/14/2024) (#6730) * fix(ollama.py): fix get model info request Fixes https://github.com/BerriAI/litellm/issues/6703 * feat(anthropic/chat/transformation.py): support passing user id to anthropic via openai 'user' param * docs(anthropic.md): document all supported openai params for anthropic * test: fix tests * fix: fix tests * feat(jina_ai/): add rerank support Closes https://github.com/BerriAI/litellm/issues/6691 * test: handle service unavailable error * fix(handler.py): refactor together ai rerank call * test: update test to handle overloaded error * test: fix test * Litellm router trace (#6742) * feat(router.py): add trace_id to parent functions - allows tracking retry/fallbacks * feat(router.py): log trace id across retry/fallback logic allows grouping llm logs for the same request * test: fix tests * fix: fix test * fix(transformation.py): only set non-none stop_sequences * Litellm router disable fallbacks (#6743) * bump: version 1.52.6 → 1.52.7 * feat(router.py): enable dynamically disabling fallbacks Allows for enabling/disabling fallbacks per key * feat(litellm_pre_call_utils.py): support setting 'disable_fallbacks' on litellm key * test: fix test * fix(exception_mapping_utils.py): map 'model is overloaded' to internal server error * test: handle gemini error * test: fix test * fix: new run * bump: version 1.52.7 → 1.52.8 * docs: add docs on jina ai rerank support * docs(reliability.md): add tutorial on disabling fallbacks per key * docs(logging.md): add 'trace_id' param to standard logging payload * (feat) add bedrock/stability.stable-image-ultra-v1:0 (#6723) * add stability.stable-image-ultra-v1:0 * add pricing for stability.stable-image-ultra-v1:0 * fix test_supports_response_schema * ci/cd run again * [Feature]: Stop swallowing up AzureOpenAi exception responses in litellm's implementation for a BadRequestError (#6745) * fix azure exceptions * test_bad_request_error_contains_httpx_response * test_bad_request_error_contains_httpx_response * use safe access to get exception response * fix get attr * [Feature]: json_schema in response support for Anthropic (#6748) * _convert_tool_response_to_message * fix ModelResponseIterator * fix test_json_response_format * test_json_response_format_stream * fix _convert_tool_response_to_message * use helper _handle_json_mode_chunk * fix _process_response * unit testing for test_convert_tool_response_to_message_no_arguments * update doc for JSON mode * fix: import audio check (#6740) * fix imagegeneration output_cost_per_image on model cost map (#6752) * (feat) Vertex AI - add support for fine tuned embedding models (#6749) * fix use fine tuned vertex embedding models * test_vertex_embedding_url * add _transform_openai_request_to_fine_tuned_embedding_request * add _transform_openai_request_to_fine_tuned_embedding_request * add transform_openai_request_to_vertex_embedding_request * add _transform_vertex_response_to_openai_for_fine_tuned_models * test_vertexai_embedding for ft models * fix test_vertexai_embedding_finetuned * doc fine tuned / custom embedding models * fix test test_partner_models_httpx * bump: version 1.52.8 → 1.52.9 * LiteLLM Minor Fixes & Improvements (11/13/2024) (#6729) * fix(utils.py): add logprobs support for together ai Fixes https://github.com/BerriAI/litellm/issues/6724 * feat(pass_through_endpoints/): add anthropic/ pass-through endpoint adds new `anthropic/` pass-through endpoint + refactors docs * feat(spend_management_endpoints.py): allow /global/spend/report to query team + customer id enables seeing spend for a customer in a team * Add integration with MLflow Tracing (#6147) * Add MLflow logger Signed-off-by: B-Step62 <yuki.watanabe@databricks.com> * Streaming handling Signed-off-by: B-Step62 <yuki.watanabe@databricks.com> * lint Signed-off-by: B-Step62 <yuki.watanabe@databricks.com> * address comments and fix issues Signed-off-by: B-Step62 <yuki.watanabe@databricks.com> * address comments and fix issues Signed-off-by: B-Step62 <yuki.watanabe@databricks.com> * Move logger construction code Signed-off-by: B-Step62 <yuki.watanabe@databricks.com> * Add docs Signed-off-by: B-Step62 <yuki.watanabe@databricks.com> * async handlers Signed-off-by: B-Step62 <yuki.watanabe@databricks.com> * new picture Signed-off-by: B-Step62 <yuki.watanabe@databricks.com> --------- Signed-off-by: B-Step62 <yuki.watanabe@databricks.com> * fix(mlflow.py): fix ruff linting errors * ci(config.yml): add mlflow to ci testing * fix: fix test * test: fix test * Litellm key update fix (#6710) * fix(caching): convert arg to equivalent kwargs in llm caching handler prevent unexpected errors * fix(caching_handler.py): don't pass args to caching * fix(caching): remove all *args from caching.py * fix(caching): consistent function signatures + abc method * test(caching_unit_tests.py): add unit tests for llm caching ensures coverage for common caching scenarios across different implementations * refactor(litellm_logging.py): move to using cache key from hidden params instead of regenerating one * fix(router.py): drop redis password requirement * fix(proxy_server.py): fix faulty slack alerting check * fix(langfuse.py): avoid copying functions/thread lock objects in metadata fixes metadata copy error when parent otel span in metadata * test: update test * fix(key_management_endpoints.py): fix /key/update with metadata update * fix(key_management_endpoints.py): fix key_prepare_update helper * fix(key_management_endpoints.py): reset value to none if set in key update * fix: update test ' * Litellm dev 11 11 2024 (#6693) * fix(__init__.py): add 'watsonx_text' as mapped llm api route Fixes https://github.com/BerriAI/litellm/issues/6663 * fix(opentelemetry.py): fix passing parallel tool calls to otel Fixes https://github.com/BerriAI/litellm/issues/6677 * refactor(test_opentelemetry_unit_tests.py): create a base set of unit tests for all logging integrations - test for parallel tool call handling reduces bugs in repo * fix(__init__.py): update provider-model mapping to include all known provider-model mappings Fixes https://github.com/BerriAI/litellm/issues/6669 * feat(anthropic): support passing document in llm api call * docs(anthropic.md): add pdf anthropic call to docs + expose new 'supports_pdf_input' function * fix(factory.py): fix linting error * add clear doc string for GCS bucket logging * Add docs to export logs to Laminar (#6674) * Add docs to export logs to Laminar * minor fix: newline at end of file * place laminar after http and grpc * (Feat) Add langsmith key based logging (#6682) * add langsmith_api_key to StandardCallbackDynamicParams * create a file for langsmith types * langsmith add key / team based logging * add key based logging for langsmith * fix langsmith key based logging * fix linting langsmith * remove NOQA violation * add unit test coverage for all helpers in test langsmith * test_langsmith_key_based_logging * docs langsmith key based logging * run langsmith tests in logging callback tests * fix logging testing * test_langsmith_key_based_logging * test_add_callback_via_key_litellm_pre_call_utils_langsmith * add debug statement langsmith key based logging * test_langsmith_key_based_logging * (fix) OpenAI's optional messages[].name does not work with Mistral API (#6701) * use helper for _transform_messages mistral * add test_message_with_name to base LLMChat test * fix linting * add xAI on Admin UI (#6680) * (docs) add benchmarks on 1K RPS (#6704) * docs litellm proxy benchmarks * docs GCS bucket * doc fix - reduce clutter on logging doc title * (feat) add cost tracking stable diffusion 3 on Bedrock (#6676) * add cost tracking for sd3 * test_image_generation_bedrock * fix get model info for image cost * add cost_calculator for stability 1 models * add unit testing for bedrock image cost calc * test_cost_calculator_with_no_optional_params * add test_cost_calculator_basic * correctly allow size Optional * fix cost_calculator * sd3 unit tests cost calc * fix raise correct error 404 when /key/info is called on non-existent key (#6653) * fix raise correct error on /key/info * add not_found_error error * fix key not found in DB error * use 1 helper for checking token hash * fix error code on key info * fix test key gen prisma * test_generate_and_call_key_info * test fix test_call_with_valid_model_using_all_models * fix key info tests * bump: version 1.52.4 → 1.52.5 * add defaults used for GCS logging * LiteLLM Minor Fixes & Improvements (11/12/2024) (#6705) * fix(caching): convert arg to equivalent kwargs in llm caching handler prevent unexpected errors * fix(caching_handler.py): don't pass args to caching * fix(caching): remove all *args from caching.py * fix(caching): consistent function signatures + abc method * test(caching_unit_tests.py): add unit tests for llm caching ensures coverage for common caching scenarios across different implementations * refactor(litellm_logging.py): move to using cache key from hidden params instead of regenerating one * fix(router.py): drop redis password requirement * fix(proxy_server.py): fix faulty slack alerting check * fix(langfuse.py): avoid copying functions/thread lock objects in metadata fixes metadata copy error when parent otel span in metadata * test: update test * bump: version 1.52.5 → 1.52.6 * (feat) helm hook to sync db schema (#6715) * v0 migration job * fix job * fix migrations job.yml * handle standalone DB on helm hook * fix argo cd annotations * fix db migration helm hook * fix migration job * doc fix Using Http/2 with Hypercorn * (fix proxy redis) Add redis sentinel support (#6154) * add sentinel_password support * add doc for setting redis sentinel password * fix redis sentinel - use sentinel password * Fix: Update gpt-4o costs to that of gpt-4o-2024-08-06 (#6714) Fixes #6713 * (fix) using Anthropic `response_format={"type": "json_object"}` (#6721) * add support for response_format=json anthropic * add test_json_response_format to baseLLM ChatTest * fix test_litellm_anthropic_prompt_caching_tools * fix test_anthropic_function_call_with_no_schema * test test_create_json_tool_call_for_response_format * (feat) Add cost tracking for Azure Dall-e-3 Image Generation + use base class to ensure basic image generation tests pass (#6716) * add BaseImageGenTest * use 1 class for unit testing * add debugging to BaseImageGenTest * TestAzureOpenAIDalle3 * fix response_cost_calculator * test_basic_image_generation * fix img gen basic test * fix _select_model_name_for_cost_calc * fix test_aimage_generation_bedrock_with_optional_params * fix undo changes cost tracking * fix response_cost_calculator * fix test_cost_azure_gpt_35 * fix remove dup test (#6718) * (build) update db helm hook * (build) helm db pre sync hook * (build) helm db sync hook * test: run test_team_logging firdst --------- Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com> Co-authored-by: Dinmukhamed Mailibay <47117969+dinmukhamedm@users.noreply.github.com> Co-authored-by: Kilian Lieret <kilian.lieret@posteo.de> * test: update test * test: skip anthropic overloaded error * test: cleanup test * test: update tests * test: fix test * test: handle gemini overloaded model error * test: handle internal server error * test: handle anthropic overloaded error * test: handle claude instability --------- Signed-off-by: B-Step62 <yuki.watanabe@databricks.com> Co-authored-by: Yuki Watanabe <31463517+B-Step62@users.noreply.github.com> Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com> Co-authored-by: Dinmukhamed Mailibay <47117969+dinmukhamedm@users.noreply.github.com> Co-authored-by: Kilian Lieret <kilian.lieret@posteo.de> --------- Signed-off-by: B-Step62 <yuki.watanabe@databricks.com> Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com> Co-authored-by: Jongseob Jeon <aiden.jongseob@gmail.com> Co-authored-by: Camden Clark <camdenaws@gmail.com> Co-authored-by: Rasswanth <61219215+IamRash-7@users.noreply.github.com> Co-authored-by: Yuki Watanabe <31463517+B-Step62@users.noreply.github.com> Co-authored-by: Dinmukhamed Mailibay <47117969+dinmukhamedm@users.noreply.github.com> Co-authored-by: Kilian Lieret <kilian.lieret@posteo.de>
417 lines
13 KiB
Python
417 lines
13 KiB
Python
# What is this?
|
|
## Unit tests for user_api_key_auth helper functions
|
|
|
|
import os
|
|
import sys
|
|
|
|
sys.path.insert(
|
|
0, os.path.abspath("../..")
|
|
) # Adds the parent directory to the system path
|
|
from typing import Dict, List, Optional
|
|
from unittest.mock import MagicMock, patch, AsyncMock
|
|
|
|
import pytest
|
|
from starlette.datastructures import URL
|
|
|
|
import litellm
|
|
from litellm.proxy.auth.user_api_key_auth import user_api_key_auth
|
|
|
|
|
|
class Request:
|
|
def __init__(self, client_ip: Optional[str] = None, headers: Optional[dict] = None):
|
|
self.client = MagicMock()
|
|
self.client.host = client_ip
|
|
self.headers: Dict[str, str] = {}
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"allowed_ips, client_ip, expected_result",
|
|
[
|
|
(None, "127.0.0.1", True), # No IP restrictions, should be allowed
|
|
(["127.0.0.1"], "127.0.0.1", True), # IP in allowed list
|
|
(["192.168.1.1"], "127.0.0.1", False), # IP not in allowed list
|
|
([], "127.0.0.1", False), # Empty allowed list, no IP should be allowed
|
|
(["192.168.1.1", "10.0.0.1"], "10.0.0.1", True), # IP in allowed list
|
|
(
|
|
["192.168.1.1"],
|
|
None,
|
|
False,
|
|
), # Request with no client IP should not be allowed
|
|
],
|
|
)
|
|
def test_check_valid_ip(
|
|
allowed_ips: Optional[List[str]], client_ip: Optional[str], expected_result: bool
|
|
):
|
|
from litellm.proxy.auth.auth_utils import _check_valid_ip
|
|
|
|
request = Request(client_ip)
|
|
|
|
assert _check_valid_ip(allowed_ips, request)[0] == expected_result # type: ignore
|
|
|
|
|
|
# test x-forwarder for is used when user has opted in
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"allowed_ips, client_ip, expected_result",
|
|
[
|
|
(None, "127.0.0.1", True), # No IP restrictions, should be allowed
|
|
(["127.0.0.1"], "127.0.0.1", True), # IP in allowed list
|
|
(["192.168.1.1"], "127.0.0.1", False), # IP not in allowed list
|
|
([], "127.0.0.1", False), # Empty allowed list, no IP should be allowed
|
|
(["192.168.1.1", "10.0.0.1"], "10.0.0.1", True), # IP in allowed list
|
|
(
|
|
["192.168.1.1"],
|
|
None,
|
|
False,
|
|
), # Request with no client IP should not be allowed
|
|
],
|
|
)
|
|
def test_check_valid_ip_sent_with_x_forwarded_for(
|
|
allowed_ips: Optional[List[str]], client_ip: Optional[str], expected_result: bool
|
|
):
|
|
from litellm.proxy.auth.auth_utils import _check_valid_ip
|
|
|
|
request = Request(client_ip, headers={"X-Forwarded-For": client_ip})
|
|
|
|
assert _check_valid_ip(allowed_ips, request, use_x_forwarded_for=True)[0] == expected_result # type: ignore
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_check_blocked_team():
|
|
"""
|
|
cached valid_token obj has team_blocked = true
|
|
|
|
cached team obj has team_blocked = false
|
|
|
|
assert team is not blocked
|
|
"""
|
|
import asyncio
|
|
import time
|
|
|
|
from fastapi import Request
|
|
from starlette.datastructures import URL
|
|
|
|
from litellm.proxy._types import (
|
|
LiteLLM_TeamTable,
|
|
LiteLLM_TeamTableCachedObj,
|
|
UserAPIKeyAuth,
|
|
)
|
|
from litellm.proxy.auth.user_api_key_auth import user_api_key_auth
|
|
from litellm.proxy.proxy_server import hash_token, user_api_key_cache
|
|
|
|
_team_id = "1234"
|
|
user_key = "sk-12345678"
|
|
|
|
valid_token = UserAPIKeyAuth(
|
|
team_id=_team_id,
|
|
team_blocked=True,
|
|
token=hash_token(user_key),
|
|
last_refreshed_at=time.time(),
|
|
)
|
|
await asyncio.sleep(1)
|
|
team_obj = LiteLLM_TeamTableCachedObj(
|
|
team_id=_team_id, blocked=False, last_refreshed_at=time.time()
|
|
)
|
|
hashed_token = hash_token(user_key)
|
|
print(f"STORING TOKEN UNDER KEY={hashed_token}")
|
|
user_api_key_cache.set_cache(key=hashed_token, value=valid_token)
|
|
user_api_key_cache.set_cache(key="team_id:{}".format(_team_id), value=team_obj)
|
|
|
|
setattr(litellm.proxy.proxy_server, "user_api_key_cache", user_api_key_cache)
|
|
setattr(litellm.proxy.proxy_server, "master_key", "sk-1234")
|
|
setattr(litellm.proxy.proxy_server, "prisma_client", "hello-world")
|
|
|
|
request = Request(scope={"type": "http"})
|
|
request._url = URL(url="/chat/completions")
|
|
|
|
await user_api_key_auth(request=request, api_key="Bearer " + user_key)
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"user_role, expected_role",
|
|
[
|
|
("app_user", "internal_user"),
|
|
("internal_user", "internal_user"),
|
|
("proxy_admin_viewer", "proxy_admin_viewer"),
|
|
],
|
|
)
|
|
def test_returned_user_api_key_auth(user_role, expected_role):
|
|
from litellm.proxy._types import LiteLLM_UserTable, LitellmUserRoles
|
|
from litellm.proxy.auth.user_api_key_auth import _return_user_api_key_auth_obj
|
|
from datetime import datetime
|
|
|
|
new_obj = _return_user_api_key_auth_obj(
|
|
user_obj=LiteLLM_UserTable(
|
|
user_role=user_role, user_id="", max_budget=None, user_email=""
|
|
),
|
|
api_key="hello-world",
|
|
parent_otel_span=None,
|
|
valid_token_dict={},
|
|
route="/chat/completion",
|
|
start_time=datetime.now(),
|
|
)
|
|
|
|
assert new_obj.user_role == expected_role
|
|
|
|
|
|
@pytest.mark.parametrize("key_ownership", ["user_key", "team_key"])
|
|
@pytest.mark.asyncio
|
|
async def test_aaauser_personal_budgets(key_ownership):
|
|
"""
|
|
Set a personal budget on a user
|
|
|
|
- have it only apply when key belongs to user -> raises BudgetExceededError
|
|
- if key belongs to team, have key respect team budget -> allows call to go through
|
|
"""
|
|
import asyncio
|
|
import time
|
|
|
|
from fastapi import Request
|
|
from starlette.datastructures import URL
|
|
import litellm
|
|
|
|
from litellm.proxy._types import LiteLLM_UserTable, UserAPIKeyAuth
|
|
from litellm.proxy.auth.user_api_key_auth import user_api_key_auth
|
|
from litellm.proxy.proxy_server import hash_token, user_api_key_cache
|
|
|
|
_user_id = "1234"
|
|
user_key = "sk-12345678"
|
|
|
|
if key_ownership == "user_key":
|
|
valid_token = UserAPIKeyAuth(
|
|
token=hash_token(user_key),
|
|
last_refreshed_at=time.time(),
|
|
user_id=_user_id,
|
|
spend=20,
|
|
)
|
|
elif key_ownership == "team_key":
|
|
valid_token = UserAPIKeyAuth(
|
|
token=hash_token(user_key),
|
|
last_refreshed_at=time.time(),
|
|
user_id=_user_id,
|
|
team_id="my-special-team",
|
|
team_max_budget=100,
|
|
spend=20,
|
|
)
|
|
|
|
user_obj = LiteLLM_UserTable(
|
|
user_id=_user_id, spend=11, max_budget=10, user_email=""
|
|
)
|
|
user_api_key_cache.set_cache(key=hash_token(user_key), value=valid_token)
|
|
user_api_key_cache.set_cache(key="{}".format(_user_id), value=user_obj)
|
|
|
|
setattr(litellm.proxy.proxy_server, "user_api_key_cache", user_api_key_cache)
|
|
setattr(litellm.proxy.proxy_server, "master_key", "sk-1234")
|
|
setattr(litellm.proxy.proxy_server, "prisma_client", "hello-world")
|
|
|
|
request = Request(scope={"type": "http"})
|
|
request._url = URL(url="/chat/completions")
|
|
|
|
test_user_cache = getattr(litellm.proxy.proxy_server, "user_api_key_cache")
|
|
|
|
assert test_user_cache.get_cache(key=hash_token(user_key)) == valid_token
|
|
|
|
try:
|
|
await user_api_key_auth(request=request, api_key="Bearer " + user_key)
|
|
|
|
if key_ownership == "user_key":
|
|
pytest.fail("Expected this call to fail. User is over limit.")
|
|
except Exception:
|
|
if key_ownership == "team_key":
|
|
pytest.fail("Expected this call to work. Key is below team budget.")
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
@pytest.mark.parametrize("prohibited_param", ["api_base", "base_url"])
|
|
async def test_user_api_key_auth_fails_with_prohibited_params(prohibited_param):
|
|
"""
|
|
Relevant issue: https://huntr.com/bounties/4001e1a2-7b7a-4776-a3ae-e6692ec3d997
|
|
"""
|
|
import json
|
|
|
|
from fastapi import Request
|
|
|
|
# Setup
|
|
user_key = "sk-1234"
|
|
|
|
setattr(litellm.proxy.proxy_server, "master_key", "sk-1234")
|
|
|
|
# Create request with prohibited parameter in body
|
|
request = Request(scope={"type": "http"})
|
|
request._url = URL(url="/chat/completions")
|
|
|
|
async def return_body():
|
|
body = {prohibited_param: "https://custom-api.com"}
|
|
return bytes(json.dumps(body), "utf-8")
|
|
|
|
request.body = return_body
|
|
try:
|
|
response = await user_api_key_auth(
|
|
request=request, api_key="Bearer " + user_key
|
|
)
|
|
except Exception as e:
|
|
print("error str=", str(e))
|
|
error_message = str(e.message)
|
|
print("error message=", error_message)
|
|
assert "is not allowed in request body" in error_message
|
|
|
|
|
|
@pytest.mark.asyncio()
|
|
@pytest.mark.parametrize(
|
|
"route, should_raise_error",
|
|
[
|
|
("/embeddings", False),
|
|
("/chat/completions", True),
|
|
("/completions", True),
|
|
("/models", True),
|
|
("/v1/embeddings", True),
|
|
],
|
|
)
|
|
async def test_auth_with_allowed_routes(route, should_raise_error):
|
|
# Setup
|
|
user_key = "sk-1234"
|
|
|
|
general_settings = {"allowed_routes": ["/embeddings"]}
|
|
from fastapi import Request
|
|
|
|
from litellm.proxy import proxy_server
|
|
|
|
initial_general_settings = getattr(proxy_server, "general_settings")
|
|
|
|
setattr(proxy_server, "master_key", "sk-1234")
|
|
setattr(proxy_server, "general_settings", general_settings)
|
|
|
|
request = Request(scope={"type": "http"})
|
|
request._url = URL(url=route)
|
|
|
|
if should_raise_error:
|
|
try:
|
|
await user_api_key_auth(request=request, api_key="Bearer " + user_key)
|
|
pytest.fail("Expected this call to fail. User is over limit.")
|
|
except Exception as e:
|
|
print("error str=", str(e.message))
|
|
error_str = str(e.message)
|
|
assert "Route" in error_str and "not allowed" in error_str
|
|
pass
|
|
else:
|
|
await user_api_key_auth(request=request, api_key="Bearer " + user_key)
|
|
|
|
setattr(proxy_server, "general_settings", initial_general_settings)
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"route, user_role, expected_result",
|
|
[
|
|
# Proxy Admin checks
|
|
("/global/spend/logs", "proxy_admin", True),
|
|
("/key/delete", "proxy_admin", False),
|
|
("/key/generate", "proxy_admin", False),
|
|
("/key/regenerate", "proxy_admin", False),
|
|
# Internal User checks - allowed routes
|
|
("/global/spend/logs", "internal_user", True),
|
|
("/key/delete", "internal_user", False),
|
|
("/key/generate", "internal_user", False),
|
|
("/key/82akk800000000jjsk/regenerate", "internal_user", False),
|
|
# Internal User Viewer
|
|
("/key/generate", "internal_user_viewer", False),
|
|
# Internal User checks - disallowed routes
|
|
("/organization/member_add", "internal_user", False),
|
|
],
|
|
)
|
|
def test_is_ui_route_allowed(route, user_role, expected_result):
|
|
from litellm.proxy.auth.user_api_key_auth import _is_ui_route
|
|
from litellm.proxy._types import LiteLLM_UserTable
|
|
|
|
user_obj = LiteLLM_UserTable(
|
|
user_id="3b803c0e-666e-4e99-bd5c-6e534c07e297",
|
|
max_budget=None,
|
|
spend=0.0,
|
|
model_max_budget={},
|
|
model_spend={},
|
|
user_email="my-test-email@1234.com",
|
|
models=[],
|
|
tpm_limit=None,
|
|
rpm_limit=None,
|
|
user_role=user_role,
|
|
organization_memberships=[],
|
|
)
|
|
|
|
received_args: dict = {
|
|
"route": route,
|
|
"user_obj": user_obj,
|
|
}
|
|
try:
|
|
assert _is_ui_route(**received_args) == expected_result
|
|
except Exception as e:
|
|
# If expected result is False, we expect an error
|
|
if expected_result is False:
|
|
pass
|
|
else:
|
|
raise e
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"route, user_role, expected_result",
|
|
[
|
|
("/key/generate", "internal_user_viewer", False),
|
|
],
|
|
)
|
|
def test_is_api_route_allowed(route, user_role, expected_result):
|
|
from litellm.proxy.auth.user_api_key_auth import _is_api_route_allowed
|
|
from litellm.proxy._types import LiteLLM_UserTable
|
|
|
|
user_obj = LiteLLM_UserTable(
|
|
user_id="3b803c0e-666e-4e99-bd5c-6e534c07e297",
|
|
max_budget=None,
|
|
spend=0.0,
|
|
model_max_budget={},
|
|
model_spend={},
|
|
user_email="my-test-email@1234.com",
|
|
models=[],
|
|
tpm_limit=None,
|
|
rpm_limit=None,
|
|
user_role=user_role,
|
|
organization_memberships=[],
|
|
)
|
|
|
|
received_args: dict = {
|
|
"route": route,
|
|
"user_obj": user_obj,
|
|
}
|
|
try:
|
|
assert _is_api_route_allowed(**received_args) == expected_result
|
|
except Exception as e:
|
|
# If expected result is False, we expect an error
|
|
if expected_result is False:
|
|
pass
|
|
else:
|
|
raise e
|
|
|
|
|
|
from litellm.proxy._types import LitellmUserRoles
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"user_role, auth_user_id, requested_user_id, expected_result",
|
|
[
|
|
(LitellmUserRoles.PROXY_ADMIN, "1234", None, True),
|
|
(LitellmUserRoles.PROXY_ADMIN_VIEW_ONLY, None, "1234", True),
|
|
(LitellmUserRoles.TEAM, "1234", None, False),
|
|
(LitellmUserRoles.TEAM, None, None, False),
|
|
(LitellmUserRoles.TEAM, "1234", "1234", True),
|
|
],
|
|
)
|
|
def test_allowed_route_inside_route(
|
|
user_role, auth_user_id, requested_user_id, expected_result
|
|
):
|
|
from litellm.proxy.auth.auth_checks import allowed_route_check_inside_route
|
|
from litellm.proxy._types import UserAPIKeyAuth, LitellmUserRoles
|
|
|
|
assert (
|
|
allowed_route_check_inside_route(
|
|
user_api_key_dict=UserAPIKeyAuth(user_role=user_role, user_id=auth_user_id),
|
|
requested_user_id=requested_user_id,
|
|
)
|
|
== expected_result
|
|
)
|