From 041ed94e95fbdb70d5252d4e00c18da99015016a Mon Sep 17 00:00:00 2001 From: Yuneng Jiang Date: Fri, 23 Oct 2026 15:34:36 -0700 Subject: [PATCH 1/2] chore(caching)!: remove the disk cache backend Drop the disk cache type and its diskcache dependency, along with the caching install extra that existed only to pull it in. diskcache has not had a release since August 2023 Cache now raises a ValueError listing the supported types when it gets a type it does not know. Before, an unknown type built a Cache with no backend, which only failed on first use BREAKING CHANGE: cache_params type "disk" and the litellm[caching] extra are gone. A proxy configured with type disk now refuses to start. Use local or redis instead --- .github/workflows/test-unit.yml | 8 +- license_cache.json | 1 - litellm/caching/Readme.md | 8 +- litellm/caching/__init__.py | 1 - litellm/caching/caching.py | 16 +-- litellm/caching/caching_handler.py | 2 +- litellm/caching/disk_cache.py | 88 -------------- litellm/router.py | 2 +- litellm/types/caching.py | 1 - osv-scanner.toml | 5 - pyproject.toml | 1 - tests/unit/caching/test_caching.py | 7 ++ tests/unit/caching/test_disk_cache.py | 158 -------------------------- uv.lock | 15 +-- 14 files changed, 23 insertions(+), 290 deletions(-) delete mode 100644 litellm/caching/disk_cache.py delete mode 100644 tests/unit/caching/test_disk_cache.py diff --git a/.github/workflows/test-unit.yml b/.github/workflows/test-unit.yml index 76af64c8ccd..4cb480c48c7 100644 --- a/.github/workflows/test-unit.yml +++ b/.github/workflows/test-unit.yml @@ -996,9 +996,9 @@ jobs: run: | diff -u model_prices_and_context_window.json litellm/model_prices_and_context_window_backup.json if [ -z "$RUST_BRIDGE_ARTIFACT" ]; then - .github/scripts/uv_sync_with_retries.sh --frozen --group ci --group proxy-dev --extra google --extra proxy --extra semantic-router --extra saml --extra caching --extra extra_proxy --extra proxy-runtime --extra utils + .github/scripts/uv_sync_with_retries.sh --frozen --group ci --group proxy-dev --extra google --extra proxy --extra semantic-router --extra saml --extra extra_proxy --extra proxy-runtime --extra utils else - .github/scripts/uv_sync_with_retries.sh --frozen --group ci --group proxy-dev --extra google --extra proxy --extra semantic-router --extra saml --extra caching --extra extra_proxy --extra proxy-runtime --extra utils --no-install-project + .github/scripts/uv_sync_with_retries.sh --frozen --group ci --group proxy-dev --extra google --extra proxy --extra semantic-router --extra saml --extra extra_proxy --extra proxy-runtime --extra utils --no-install-project uv pip install --no-deps --python .venv/bin/python rust-bridge-dist/*.whl cp rust-bridge-dist/litellm/rust_bridge/_native.abi3.so litellm/rust_bridge/_native.abi3.so uv run --no-sync python -c "import importlib.metadata; import litellm.rust_bridge._native; print(importlib.metadata.version('litellm'))" @@ -1434,9 +1434,9 @@ jobs: RUST_BRIDGE_ARTIFACT: ${{ needs.rust-bridge.outputs.artifact }} run: | if [ -z "$RUST_BRIDGE_ARTIFACT" ]; then - .github/scripts/uv_sync_with_retries.sh --frozen --group ci --group proxy-dev --extra google --extra proxy --extra semantic-router --extra saml --extra caching --extra extra_proxy --extra proxy-runtime --extra utils + .github/scripts/uv_sync_with_retries.sh --frozen --group ci --group proxy-dev --extra google --extra proxy --extra semantic-router --extra saml --extra extra_proxy --extra proxy-runtime --extra utils else - .github/scripts/uv_sync_with_retries.sh --frozen --group ci --group proxy-dev --extra google --extra proxy --extra semantic-router --extra saml --extra caching --extra extra_proxy --extra proxy-runtime --extra utils --no-install-project + .github/scripts/uv_sync_with_retries.sh --frozen --group ci --group proxy-dev --extra google --extra proxy --extra semantic-router --extra saml --extra extra_proxy --extra proxy-runtime --extra utils --no-install-project uv pip install --no-deps --python .venv/bin/python rust-bridge-dist/*.whl cp rust-bridge-dist/litellm/rust_bridge/_native.abi3.so litellm/rust_bridge/_native.abi3.so fi diff --git a/license_cache.json b/license_cache.json index dc061b48f4f..cd8a54d72a0 100644 --- a/license_cache.json +++ b/license_cache.json @@ -11,7 +11,6 @@ "azure-keyvault-secrets:4.10.0": "MIT License", "google-cloud-kms:2.24.2": "Apache 2.0", "numpydoc:1.8.0": "Copyright (C) 2008-2023 Stefan van der Walt , Pauli Virtanen Redistribution and use in source and binary forms, with or without modification, are permitted provided that the following conditions are met: 1. Redistributions of source code must retain the above copyright notice, this list of conditions and the following disclaimer. 2. Redistributions in binary form must reproduce the above copyright notice, this list of conditions and the following disclaimer in the documentation and/or other materials provided with the distribution. THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. ", - "diskcache:5.6.3": "Apache 2.0", "mlflow:3.9.0": "Copyright 2018 Databricks, Inc. All rights reserved.\n \n \t\t\t\tApache License\n Version 2.0, January 2004\n http://www.apache.org/licenses/\n \n TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION\n \n 1. Definitions.\n \n \"License\" shall mean the terms and conditions for use, reproduction,\n and distribution as defined by Sections 1 through 9 of this document.\n \n \"Licensor\" shall mean the copyright owner or entity authorized by\n the copyright owner that is granting the License.\n \n \"Legal Entity\" shall mean the union of the acting entity and all\n other entities that control, are controlled by, or are under common\n control with that entity. For the purposes of this definition,\n \"control\" means (i) the power, direct or indirect, to cause the\n direction or management of such entity, whether by contract or\n otherwise, or (ii) ownership of fifty percent (50%) or more of the\n outstanding shares, or (iii) beneficial ownership of such entity.\n \n \"You\" (or \"Your\") shall mean an individual or Legal Entity\n exercising permissions granted by this License.\n \n \"Source\" form shall mean the preferred form for making modifications,\n including but not limited to software source code, documentation\n source, and configuration files.\n \n \"Object\" form shall mean any form resulting from mechanical\n transformation or translation of a Source form, including but\n not limited to compiled object code, generated documentation,\n and conversions to other media types.\n \n \"Work\" shall mean the work of authorship, whether in Source or\n Object form, made available under the License, as indicated by a\n copyright notice that is included in or attached to the work\n (an example is provided in the Appendix below).\n \n \"Derivative Works\" shall mean any work, whether in Source or Object\n form, that is based on (or derived from) the Work and for which the\n editorial revisions, annotations, elaborations, or other modifications\n represent, as a whole, an original work of authorship. For the purposes\n of this License, Derivative Works shall not include works that remain\n separable from, or merely link (or bind by name) to the interfaces of,\n the Work and Derivative Works thereof.\n \n \"Contribution\" shall mean any work of authorship, including\n the original version of the Work and any modifications or additions\n to that Work or Derivative Works thereof, that is intentionally\n submitted to Licensor for inclusion in the Work by the copyright owner\n or by an individual or Legal Entity authorized to submit on behalf of\n the copyright owner. For the purposes of this definition, \"submitted\"\n means any form of electronic, verbal, or written communication sent\n to the Licensor or its representatives, including but not limited to\n communication on electronic mailing lists, source code control systems,\n and issue tracking systems that are managed by, or on behalf of, the\n Licensor for the purpose of discussing and improving the Work, but\n excluding communication that is conspicuously marked or otherwise\n designated in writing by the copyright owner as \"Not a Contribution.\"\n \n \"Contributor\" shall mean Licensor and any individual or Legal Entity\n on behalf of whom a Contribution has been received by Licensor and\n subsequently incorporated within the Work.\n \n 2. Grant of Copyright License. Subject to the terms and conditions of\n this License, each Contributor hereby grants to You a perpetual,\n worldwide, non-exclusive, no-charge, royalty-free, irrevocable\n copyright license to reproduce, prepare Derivative Works of,\n publicly display, publicly perform, sublicense, and distribute the\n Work and such Derivative Works in Source or Object form.\n \n 3. Grant of Patent License. Subject to the terms and conditions of\n this License, each Contributor hereby grants to You a perpetual,\n worldwide, non-exclusive, no-charge, royalty-free, irrevocable\n (except as stated in this section) patent license to make, have made,\n use, offer to sell, sell, import, and otherwise transfer the Work,\n where such license applies only to those patent claims licensable\n by such Contributor that are necessarily infringed by their\n Contribution(s) alone or by combination of their Contribution(s)\n with the Work to which such Contribution(s) was submitted. If You\n institute patent litigation against any entity (including a\n cross-claim or counterclaim in a lawsuit) alleging that the Work\n or a Contribution incorporated within the Work constitutes direct\n or contributory patent infringement, then any patent licenses\n granted to You under this License for that Work shall terminate\n as of the date such litigation is filed.\n \n 4. Redistribution. You may reproduce and distribute copies of the\n Work or Derivative Works thereof in any medium, with or without\n modifications, and in Source or Object form, provided that You\n meet the following conditions:\n \n (a) You must give any other recipients of the Work or\n Derivative Works a copy of this License; and\n \n (b) You must cause any modified files to carry prominent notices\n stating that You changed the files; and\n \n (c) You must retain, in the Source form of any Derivative Works\n that You distribute, all copyright, patent, trademark, and\n attribution notices from the Source form of the Work,\n excluding those notices that do not pertain to any part of\n the Derivative Works; and\n \n (d) If the Work includes a \"NOTICE\" text file as part of its\n distribution, then any Derivative Works that You distribute must\n include a readable copy of the attribution notices contained\n within such NOTICE file, excluding those notices that do not\n pertain to any part of the Derivative Works, in at least one\n of the following places: within a NOTICE text file distributed\n as part of the Derivative Works; within the Source form or\n documentation, if provided along with the Derivative Works; or,\n within a display generated by the Derivative Works, if and\n wherever such third-party notices normally appear. The contents\n of the NOTICE file are for informational purposes only and\n do not modify the License. You may add Your own attribution\n notices within Derivative Works that You distribute, alongside\n or as an addendum to the NOTICE text from the Work, provided\n that such additional attribution notices cannot be construed\n as modifying the License.\n \n You may add Your own copyright statement to Your modifications and\n may provide additional or different license terms and conditions\n for use, reproduction, or distribution of Your modifications, or\n for any such Derivative Works as a whole, provided Your use,\n reproduction, and distribution of the Work otherwise complies with\n the conditions stated in this License.\n \n 5. Submission of Contributions. Unless You explicitly state otherwise,\n any Contribution intentionally submitted for inclusion in the Work\n by You to the Licensor shall be under the terms and conditions of\n this License, without any additional terms or conditions.\n Notwithstanding the above, nothing herein shall supersede or modify\n the terms of any separate license agreement you may have executed\n with Licensor regarding such Contributions.\n \n 6. Trademarks. This License does not grant permission to use the trade\n names, trademarks, service marks, or product names of the Licensor,\n except as required for reasonable and customary use in describing the\n origin of the Work and reproducing the content of the NOTICE file.\n \n 7. Disclaimer of Warranty. Unless required by applicable law or\n agreed to in writing, Licensor provides the Work (and each\n Contributor provides its Contributions) on an \"AS IS\" BASIS,\n WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or\n implied, including, without limitation, any warranties or conditions\n of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A\n PARTICULAR PURPOSE. You are solely responsible for determining the\n appropriateness of using or redistributing the Work and assume any\n risks associated with Your exercise of permissions under this License.\n \n 8. Limitation of Liability. In no event and under no legal theory,\n whether in tort (including negligence), contract, or otherwise,\n unless required by applicable law (such as deliberate and grossly\n negligent acts) or agreed to in writing, shall any Contributor be\n liable to You for damages, including any direct, indirect, special,\n incidental, or consequential damages of any character arising as a\n result of this License or out of the use or inability to use the\n Work (including but not limited to damages for loss of goodwill,\n work stoppage, computer failure or malfunction, or any and all\n other commercial damages or losses), even if such Contributor\n has been advised of the possibility of such damages.\n \n 9. Accepting Warranty or Additional Liability. While redistributing\n the Work or Derivative Works thereof, You may choose to offer,\n and charge a fee for, acceptance of support, warranty, indemnity,\n or other liability obligations and/or rights consistent with this\n License. However, in accepting such obligations, You may act only\n on Your own behalf and on Your sole responsibility, not on behalf\n of any other Contributor, and only if You agree to indemnify,\n defend, and hold each Contributor harmless for any liability\n incurred by, or claims asserted against, such Contributor by reason\n of your accepting any such warranty or additional liability.\n \n END OF TERMS AND CONDITIONS\n APPENDIX: How to apply the Apache License to your work.\n \n To apply the Apache License to your work, attach the following\n boilerplate notice, with the fields enclosed by brackets \"[]\"\n replaced with your own identifying information. (Don't include\n the brackets!) The text should be enclosed in the appropriate\n comment syntax for the file format. We also recommend that a\n file or class name and description of purpose be included on the\n same \"printed page\" as the copyright notice for easier\n identification within third-party archives.\n \n Copyright [yyyy] [name of copyright owner]\n \n Licensed under the Apache License, Version 2.0 (the \"License\");\n you may not use this file except in compliance with the License.\n You may obtain a copy of the License at\n \n http://www.apache.org/licenses/LICENSE-2.0\n \n Unless required by applicable law or agreed to in writing, software\n distributed under the License is distributed on an \"AS IS\" BASIS,\n WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n See the License for the specific language governing permissions and\n limitations under the License.\n ", "diff-cover:9.7.2": "Apache-2.0", "flake8:7.3.0": "MIT", diff --git a/litellm/caching/Readme.md b/litellm/caching/Readme.md index 1d920219830..e91a5fec888 100644 --- a/litellm/caching/Readme.md +++ b/litellm/caching/Readme.md @@ -8,10 +8,9 @@ The following caching mechanisms are supported: 2. **RedisSemanticCache** 3. **QdrantSemanticCache** 4. **InMemoryCache** -5. **DiskCache** -6. **S3Cache** -7. **AzureBlobCache** -8. **DualCache** (updates both Redis and an in-memory cache simultaneously) +5. **S3Cache** +6. **AzureBlobCache** +7. **DualCache** (updates both Redis and an in-memory cache simultaneously) ## Folder Structure @@ -20,7 +19,6 @@ litellm/caching/ ├── base_cache.py ├── caching.py ├── caching_handler.py -├── disk_cache.py ├── dual_cache.py ├── in_memory_cache.py ├── qdrant_semantic_cache.py diff --git a/litellm/caching/__init__.py b/litellm/caching/__init__.py index 87f4f7a7c63..db79a9cafee 100644 --- a/litellm/caching/__init__.py +++ b/litellm/caching/__init__.py @@ -1,6 +1,5 @@ from .azure_blob_cache import AzureBlobCache from .caching import Cache, LiteLLMCacheType -from .disk_cache import DiskCache from .dual_cache import DualCache from .gcs_cache import GCSCache from .in_memory_cache import InMemoryCache diff --git a/litellm/caching/caching.py b/litellm/caching/caching.py index 5f5b8210096..eb054099ea6 100644 --- a/litellm/caching/caching.py +++ b/litellm/caching/caching.py @@ -31,7 +31,6 @@ from litellm.types.utils import EmbeddingResponse, is_litellm_owned_kwarg from .azure_blob_cache import AzureBlobCache from .base_cache import BaseCache -from .disk_cache import DiskCache from .dual_cache import DualCache # noqa: F401 # re-exported, callers import DualCache from litellm.caching.caching from .gcs_cache import GCSCache from .in_memory_cache import InMemoryCache @@ -132,7 +131,6 @@ class Cache: valkey_semantic_cache_index_name: str | None = None, redis_flush_size: int | None = None, redis_startup_nodes: list | None = None, - disk_cache_dir: str | None = None, qdrant_api_base: str | None = None, qdrant_api_key: str | None = None, qdrant_collection_name: str | None = None, @@ -153,7 +151,7 @@ class Cache: Initializes the cache based on the given type. Args: - type (str, optional): The type of cache to initialize. Can be "local", "redis", "redis-semantic", "qdrant-semantic", "s3" or "disk". Defaults to "local". + type (str, optional): The type of cache to initialize. Can be "local", "redis", "redis-semantic", "qdrant-semantic" or "s3". Defaults to "local". # Redis Cache Args host (str, optional): The host address for the Redis cache. Required if type is "redis". @@ -174,9 +172,6 @@ class Cache: semantic_cache_scope (str, optional): "key" isolates semantic-cache buckets per key/team/org. "end_user" additionally isolates per end user (falls back to the key scope when the request carries no end-user id). Defaults to "key". max_messages (int, optional): Requests with more `messages` (or Responses API `input` items) than this are neither looked up nor stored, so long agent conversations never serve or create a cache entry. None disables the limit. Defaults to 4. - # Disk Cache Args - disk_cache_dir (str, optional): The directory for the disk cache. Defaults to None. - # S3 Cache Args s3_bucket_name (str, optional): The bucket name for the s3 cache. Defaults to None. s3_region_name (str, optional): The region name for the s3 cache. Defaults to None. @@ -306,8 +301,9 @@ class Cache: account_url=azure_account_url, container=azure_blob_container, ) - elif type == LiteLLMCacheType.DISK: - self.cache = DiskCache(disk_cache_dir=disk_cache_dir) + else: + supported_types: Final = ", ".join(member.value for member in LiteLLMCacheType) + raise ValueError(f"Unsupported cache type {type!r}. Supported types: {supported_types}") if "cache" not in litellm.input_callback: litellm.input_callback.append("cache") if "cache" not in litellm.success_callback: @@ -1028,7 +1024,7 @@ def enable_cache( Enable cache with the specified configuration. Args: - type (Optional[Literal["local", "redis", "s3", "disk"]]): The type of cache to enable. Defaults to "local". + type (Optional[Literal["local", "redis", "s3"]]): The type of cache to enable. Defaults to "local". host (Optional[str]): The host address of the cache server. Defaults to None. port (Optional[str]): The port number of the cache server. Defaults to None. password (Optional[str]): The password for the cache server. Defaults to None. @@ -1075,7 +1071,7 @@ def update_cache( Update the cache for LiteLLM. Args: - type (Optional[Literal["local", "redis", "s3", "disk"]]): The type of cache. Defaults to "local". + type (Optional[Literal["local", "redis", "s3"]]): The type of cache. Defaults to "local". host (Optional[str]): The host of the cache. Defaults to None. port (Optional[str]): The port of the cache. Defaults to None. password (Optional[str]): The password for the cache. Defaults to None. diff --git a/litellm/caching/caching_handler.py b/litellm/caching/caching_handler.py index 7089ff78835..db51214dfdc 100644 --- a/litellm/caching/caching_handler.py +++ b/litellm/caching/caching_handler.py @@ -9,7 +9,7 @@ This file is a wrapper around caching.py This class is used to handle caching logic specific for LLM API requests (completion / embedding / text_completion / transcription etc) -It utilizes the (RedisCache, s3Cache, RedisSemanticCache, QdrantSemanticCache, InMemoryCache, DiskCache) based on what the user has setup +It utilizes the (RedisCache, s3Cache, RedisSemanticCache, QdrantSemanticCache, InMemoryCache) based on what the user has setup In each method it will call the appropriate method from caching.py """ diff --git a/litellm/caching/disk_cache.py b/litellm/caching/disk_cache.py deleted file mode 100644 index 50939ad51ca..00000000000 --- a/litellm/caching/disk_cache.py +++ /dev/null @@ -1,88 +0,0 @@ -import json -from typing import TYPE_CHECKING, Any, Final - -from .base_cache import BaseCache - -if TYPE_CHECKING: - from opentelemetry.trace import Span as _Span - - Span = _Span | Any -else: - Span = Any - - -class DiskCache(BaseCache): - def __init__(self, disk_cache_dir: str | None = None): - try: - import diskcache as dc - except ModuleNotFoundError as e: - raise ModuleNotFoundError("Please install litellm with `litellm[caching]` to use disk caching.") from e - - # if users don't provider one, use the default litellm cache - if disk_cache_dir is None: - self.disk_cache = dc.Cache(".litellm_cache") - else: - self.disk_cache = dc.Cache(disk_cache_dir) - - def set_cache(self, key, value, **kwargs): - if "ttl" in kwargs: - self.disk_cache.set(key, value, expire=kwargs["ttl"]) - else: - self.disk_cache.set(key, value) - - async def async_set_cache(self, key, value, **kwargs): - self.set_cache(key=key, value=value, **kwargs) - - async def async_set_cache_pipeline(self, cache_list, **kwargs): - for cache_key, cache_value in cache_list: - if "ttl" in kwargs: - self.set_cache(key=cache_key, value=cache_value, ttl=kwargs["ttl"]) - else: - self.set_cache(key=cache_key, value=cache_value) - - def get_cache(self, key, **kwargs): - original_cached_response: Final = self.disk_cache.get(key) - if original_cached_response: - try: - cached_response = json.loads(original_cached_response) - except Exception: - cached_response = original_cached_response - return cached_response - return None - - def batch_get_cache(self, keys: list, **kwargs): - return_val: Final = [] - for k in keys: - val = self.get_cache(key=k, **kwargs) - return_val.append(val) - return return_val - - def increment_cache(self, key, value: int, **kwargs) -> int: - with self.disk_cache.transact(): - cached_value: Final = self.get_cache(key=key) - init_value: Final = cached_value if isinstance(cached_value, int) else 0 - new_value: Final = init_value + value - self.set_cache(key, new_value, **kwargs) - return new_value - - async def async_get_cache(self, key, **kwargs): - return self.get_cache(key=key, **kwargs) - - async def async_batch_get_cache(self, keys: list, **kwargs): - return_val: Final = [] - for k in keys: - val = self.get_cache(key=k, **kwargs) - return_val.append(val) - return return_val - - async def async_increment(self, key, value: int, **kwargs) -> int: - return self.increment_cache(key=key, value=value, **kwargs) - - def flush_cache(self): - self.disk_cache.clear() - - async def disconnect(self): - pass - - def delete_cache(self, key): - self.disk_cache.pop(key) diff --git a/litellm/router.py b/litellm/router.py index da04e59f18a..902e0f2e70e 100644 --- a/litellm/router.py +++ b/litellm/router.py @@ -1343,7 +1343,7 @@ class Router: self.deployment_names: list = [] # names of models under litellm_params. ex. azure/chatgpt-v-2 self.deployment_latency_map = {} ### CACHING ### - cache_type: Literal["local", "redis", "redis-semantic", "s3", "disk"] = "local" # default to an in-memory cache + cache_type: Literal["local", "redis", "redis-semantic", "s3"] = "local" # default to an in-memory cache redis_cache = None cache_config: Final[dict[str, Any]] = {} diff --git a/litellm/types/caching.py b/litellm/types/caching.py index ced2065a674..fb5ab3b4cea 100644 --- a/litellm/types/caching.py +++ b/litellm/types/caching.py @@ -13,7 +13,6 @@ class LiteLLMCacheType(str, Enum): REDIS_SEMANTIC = "redis-semantic" VALKEY_SEMANTIC = "valkey-semantic" S3 = "s3" - DISK = "disk" QDRANT_SEMANTIC = "qdrant-semantic" AZURE_BLOB = "azure-blob" GCS = "gcs" diff --git a/osv-scanner.toml b/osv-scanner.toml index bb802137f6e..6378281d509 100644 --- a/osv-scanner.toml +++ b/osv-scanner.toml @@ -1,8 +1,3 @@ -[[IgnoredVulns]] -id = "GHSA-w8v5-vhqr-4h9v" -ignoreUntil = 2026-11-01 -reason = "diskcache has no fixed release published; remove this entry once one exists" - [[IgnoredVulns]] id = "GHSA-vfj7-8cjw-p6xm" ignoreUntil = 2026-11-03 diff --git a/pyproject.toml b/pyproject.toml index 0dabba4e450..3112c731bbd 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -125,7 +125,6 @@ utils = [ # Not in Docker or PyPI proxy extra. "numpydoc>=1.8.0,<2.0", ] -caching = ["diskcache>=5.6.3,<6.0"] mcp = ["mcp>=2.3.0,<3", "httpx2>=2.10.0,<3", "pydantic>=2.12.0,<3"] # Driver for the MongoDB Atlas vector store; Atlas Vector Search has no HTTP query API. # The floor is 4.9 because that is the release AsyncMongoClient landed in. diff --git a/tests/unit/caching/test_caching.py b/tests/unit/caching/test_caching.py index 91083921130..5ab57d7842a 100644 --- a/tests/unit/caching/test_caching.py +++ b/tests/unit/caching/test_caching.py @@ -250,6 +250,13 @@ def test_semantic_cache_key_reads_tenant_identity_from_litellm_metadata(): assert key_a == key_a_in_litellm_params +@pytest.mark.parametrize("cache_type", ["disk", "not-a-cache"]) +def test_cache_rejects_unsupported_type(cache_type: str) -> None: + cache_params: Final = {"type": cache_type} + with pytest.raises(ValueError, match=f"Unsupported cache type '{cache_type}'. Supported types: local, redis,"): + Cache(**cache_params) + + def test_semantic_cache_scope_rejects_unknown_value(): with pytest.raises(ValueError, match="'team' is not a valid SemanticCacheScope"): _semantic_cache(semantic_cache_scope="team") diff --git a/tests/unit/caching/test_disk_cache.py b/tests/unit/caching/test_disk_cache.py deleted file mode 100644 index 243f194cc7a..00000000000 --- a/tests/unit/caching/test_disk_cache.py +++ /dev/null @@ -1,158 +0,0 @@ -import threading -import time -from concurrent.futures import ThreadPoolExecutor - -import pytest - -pytest.importorskip("diskcache") - -from litellm.caching.disk_cache import DiskCache -from tests._wait_helpers import await_until - - -class _SlowInt(int): - def __add__(self, value: int) -> "_SlowInt": - time.sleep(0.05) - return _SlowInt(int(self) + value) - - -@pytest.fixture -def cache(tmp_path): - return DiskCache(disk_cache_dir=str(tmp_path)) - - -def test_increment_cache_starts_from_zero_when_key_missing(cache): - assert cache.increment_cache("counter", 3) == 3 - assert cache.get_cache("counter") == 3 - - -def test_increment_cache_adds_to_existing_int(cache): - cache.set_cache("counter", 7) - assert cache.increment_cache("counter", 5) == 12 - assert cache.get_cache("counter") == 12 - - -def test_increment_cache_treats_non_int_cached_value_as_zero(cache): - cache.set_cache("counter", "not-a-number") - assert cache.increment_cache("counter", 4) == 4 - assert cache.get_cache("counter") == 4 - - -def test_increment_cache_is_atomic_under_thread_concurrency(cache): - seed = 1000 - cache.set_cache("counter", _SlowInt(seed)) - thread_count = 8 - barrier = threading.Barrier(thread_count) - - def increment(_: int) -> int: - barrier.wait() - return cache.increment_cache("counter", 1) - - with ThreadPoolExecutor(max_workers=thread_count) as executor: - tuple(executor.map(increment, range(thread_count))) - - assert cache.get_cache("counter") == seed + thread_count - - -async def test_async_increment_starts_from_zero_when_key_missing(cache): - assert await cache.async_increment("counter", 2) == 2 - - -async def test_async_increment_adds_to_existing_int(cache): - await cache.async_set_cache("counter", 10) - assert await cache.async_increment("counter", 5) == 15 - - -async def test_async_increment_treats_non_int_cached_value_as_zero(cache): - await cache.async_set_cache("counter", "corrupt") - assert await cache.async_increment("counter", 9) == 9 - - -@pytest.fixture -def disk_cache(tmp_path): - import litellm - from litellm.caching import Cache - - litellm.cache = Cache(type="disk", disk_cache_dir=str(tmp_path)) - yield litellm.cache - litellm.cache = None - - -COMPLETION_MESSAGES = [{"role": "user", "content": "write a one sentence poem about: disk-cache-unit-key"}] - - -def test_completion_is_served_from_disk_cache_until_params_change(disk_cache): - import litellm - - first = litellm.completion( - "gpt-3.5-turbo", messages=COMPLETION_MESSAGES, caching=True, max_tokens=20, mock_response="first" - ) - repeat = litellm.completion( - "gpt-3.5-turbo", messages=COMPLETION_MESSAGES, caching=True, max_tokens=20, mock_response="second" - ) - changed = litellm.completion( - "gpt-3.5-turbo", messages=COMPLETION_MESSAGES, caching=True, temperature=0.5, mock_response="third" - ) - - assert (repeat.choices[0].message.content, repeat.id, repeat.created) == ( - first.choices[0].message.content, - first.id, - first.created, - ) - assert changed.choices[0].message.content == "third" - - -async def test_async_completion_is_served_from_disk_cache_until_params_change(disk_cache): - import litellm - - first = await litellm.acompletion( - "gpt-3.5-turbo", messages=COMPLETION_MESSAGES, caching=True, max_tokens=20, mock_response="first" - ) - await await_until(lambda: len(disk_cache.cache.disk_cache) == 1, message="the first completion is cached") - repeat = await litellm.acompletion( - "gpt-3.5-turbo", messages=COMPLETION_MESSAGES, caching=True, max_tokens=20, mock_response="second" - ) - changed = await litellm.acompletion( - "gpt-3.5-turbo", messages=COMPLETION_MESSAGES, caching=True, temperature=0.5, mock_response="third" - ) - - assert (repeat.choices[0].message.content, repeat.id, repeat.created) == ( - first.choices[0].message.content, - first.id, - first.created, - ) - assert changed.choices[0].message.content == "third" - - -async def test_embedding_is_served_from_disk_cache_until_params_change(disk_cache, respx_mock, monkeypatch): - import httpx - - import litellm - - monkeypatch.setattr(litellm, "disable_aiohttp_transport", True) - input_text = ["hello disk-embedding-unit-key"] - embeddings_route = respx_mock.post("https://api.openai.com/v1/embeddings").mock( - return_value=httpx.Response( - 200, - json={ - "object": "list", - "data": [{"object": "embedding", "index": 0, "embedding": [0.1, 0.2, 0.3]}], - "model": "text-embedding-ada-002", - "usage": {"prompt_tokens": 2, "total_tokens": 2}, - }, - ) - ) - - await litellm.aembedding("openai/text-embedding-ada-002", input=input_text, caching=True, api_key="sk-unit") - await await_until(lambda: len(disk_cache.cache.disk_cache) == 1, message="the first embedding is cached") - cached = await litellm.aembedding( - "openai/text-embedding-ada-002", input=input_text, caching=True, api_key="sk-unit" - ) - assert cached._hidden_params["cache_hit"] is True - assert cached.data[0]["embedding"] == [0.1, 0.2, 0.3] - assert embeddings_route.call_count == 1 - - await litellm.aembedding( - "openai/text-embedding-ada-002", input=input_text, caching=True, user="charlie", api_key="sk-unit" - ) - assert embeddings_route.call_count == 2 diff --git a/uv.lock b/uv.lock index 9b0ada96a43..9cf3a666af7 100644 --- a/uv.lock +++ b/uv.lock @@ -1858,15 +1858,6 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/1e/77/dc8c558f7593132cf8fefec57c4f60c83b16941c574ac5f619abb3ae7933/dill-0.4.1-py3-none-any.whl", hash = "sha256:1e1ce33e978ae97fcfcff5638477032b801c46c7c65cf717f95fbc2248f79a9d", size = 120019, upload-time = "2026-01-19T02:36:55.663Z" }, ] -[[package]] -name = "diskcache" -version = "5.6.3" -source = { registry = "https://pypi.org/simple" } -sdist = { url = "https://files.pythonhosted.org/packages/3f/21/1c1ffc1a039ddcc459db43cc108658f32c57d271d7289a2794e401d0fdb6/diskcache-5.6.3.tar.gz", hash = "sha256:2c3a3fa2743d8535d832ec61c2054a1641f41775aa7c556758a109941e33e4fc", size = 67916, upload-time = "2023-08-31T06:12:00.316Z" } -wheels = [ - { url = "https://files.pythonhosted.org/packages/3f/27/4570e78fc0bf5ea0ca45eb1de3818a23787af9b390c0b0a0033a1b8236f9/diskcache-5.6.3-py3-none-any.whl", hash = "sha256:5e31b2d5fbad117cc363ebaf6b689474db18a1f6438bc82358b024abd4c2ca19", size = 45550, upload-time = "2023-08-31T06:11:58.822Z" }, -] - [[package]] name = "distro" version = "1.9.0" @@ -4667,9 +4658,6 @@ dependencies = [ bedrock-realtime = [ { name = "aws-sdk-bedrock-runtime", extra = ["awscrt"], marker = "python_full_version >= '3.12'" }, ] -caching = [ - { name = "diskcache" }, -] cli = [ { name = "inquirerpy" }, { name = "keyring" }, @@ -4919,7 +4907,6 @@ requires-dist = [ { name = "cryptography", marker = "extra == 'proxy'", specifier = ">=49.0.0,<51.0" }, { name = "ddtrace", marker = "extra == 'proxy-runtime'", specifier = ">=4.8.2,<5.0" }, { name = "detect-secrets", marker = "extra == 'proxy-runtime'", specifier = ">=1.5.0,<2.0" }, - { name = "diskcache", marker = "extra == 'caching'", specifier = ">=5.6.3,<6.0" }, { name = "expression", marker = "extra == 'proxy'", specifier = ">=5.6.0,<6.0" }, { name = "fastapi", marker = "extra == 'proxy'", specifier = ">=0.136.3,<1.0" }, { name = "fastapi-sso", marker = "extra == 'proxy'", specifier = ">=0.19.0,<1.0" }, @@ -5007,7 +4994,7 @@ requires-dist = [ { name = "uvloop", marker = "sys_platform != 'win32' and extra == 'proxy'", specifier = ">=0.22.1,<1.0" }, { name = "websockets", marker = "extra == 'proxy'", specifier = ">=15.0.1,<16.0" }, ] -provides-extras = ["proxy", "cli", "extra-proxy", "utils", "caching", "mcp", "saml", "semantic-router", "mlflow", "grpc", "stt-vertex-chirp", "stt-nvidia-riva", "google", "bedrock-realtime", "proxy-runtime"] +provides-extras = ["proxy", "cli", "extra-proxy", "utils", "mcp", "saml", "semantic-router", "mlflow", "grpc", "stt-vertex-chirp", "stt-nvidia-riva", "google", "bedrock-realtime", "proxy-runtime"] [package.metadata.requires-dev] admin-mcp = [{ name = "litellm-admin-mcp", marker = "python_full_version >= '3.12'", url = "https://github.com/BerriAI/liteadmin-mcp/archive/d35ec9c19c117d4c50cc1eccf6ce1296aac25a1a.tar.gz" }] From 118081ba66361a0d2040e261c2e27c32b514faf5 Mon Sep 17 00:00:00 2001 From: Yuneng Jiang Date: Fri, 23 Oct 2026 16:01:22 -0700 Subject: [PATCH 2/2] test(proxy): expect the unsupported cache type error from _init_cache The test pinned the old fallthrough, where an unknown type left the cache without a backend and the proxy hit an AttributeError reading it --- tests/unit/proxy/proxy_server/test_proxy_config.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tests/unit/proxy/proxy_server/test_proxy_config.py b/tests/unit/proxy/proxy_server/test_proxy_config.py index e59dd19271c..8336601f603 100644 --- a/tests/unit/proxy/proxy_server/test_proxy_config.py +++ b/tests/unit/proxy/proxy_server/test_proxy_config.py @@ -1656,7 +1656,7 @@ def test_ProxyConfig__init_cache_sets_litellm_cache(monkeypatch): def test_ProxyConfig__init_cache_invalid_params_raises(): pc = ProxyConfig() - with pytest.raises(AttributeError): + with pytest.raises(ValueError, match="Unsupported cache type 'this-cache-type-does-not-exist'"): pc._init_cache(cache_params={"type": "this-cache-type-does-not-exist"})