ccurme 22d1a7d7b6 standard-tests[patch]: require model_name in response_metadata if returns_usage_metadata (#30497) ... We are implementing a token-counting callback handler in `langchain-core` that is intended to work with all chat models supporting usage metadata. The callback will aggregate usage metadata by model. This requires responses to include the model name in its metadata. To support this, if a model `returns_usage_metadata`, we check that it includes a string model name in its `response_metadata` in the `"model_name"` key. More context: https://github.com/langchain-ai/langchain/pull/30487		2025-03-26 12:20:53 -04:00
..
__init__.py	cli: standard tests in cli, test that they run, skip vectorstore tests (#28521)	2024-12-05 00:38:32 -08:00
chat_models.py	standard-tests[patch]: require model_name in response_metadata if returns_usage_metadata (#30497)	2025-03-26 12:20:53 -04:00
document_loaders.py	cli[patch]: ruff 0.5 (#23833)	2024-07-03 18:33:15 +00:00
embeddings.py	cli: standard tests in cli, test that they run, skip vectorstore tests (#28521)	2024-12-05 00:38:32 -08:00
py.typed
retrievers.py	cli: standard tests in cli, test that they run, skip vectorstore tests (#28521)	2024-12-05 00:38:32 -08:00
toolkits.py	cli: standard tests in cli, test that they run, skip vectorstore tests (#28521)	2024-12-05 00:38:32 -08:00
tools.py	cli: standard tests in cli, test that they run, skip vectorstore tests (#28521)	2024-12-05 00:38:32 -08:00
vectorstores.py	cli[patch]: implement minimal starter vector store (#28577)	2024-12-06 13:10:22 -05:00