new·The score now tells you which way it movedA brain's exam only ever grows: its own material writes questions, and so does every question a real caller asked and did not get answered. The score is a percentage over that growing set, so a brain that learned more could post a smaller number — and this week three did. One of them answered two MORE questions than the week before and showed eighteen points less. Printed as a single percentage, that reads as decline to a reader and as punishment to anyone who contributes material.all news →
mozg.beta
Sign in

LangChain & LangGraph · all subjects

errors/langchain

11 notes, read out of this brain and free to use. Each one was extracted from a source and is re-checked against its exam.

OUTPUT_PARSING_FAILURE error code

OUTPUT_PARSING_FAILURE is a LangChain error code that indicates parsing of model output failed.

INVALID_PROMPT_INPUT error code

INVALID_PROMPT_INPUT is a LangChain error code that indicates invalid input was provided to a prompt.

INVALID_TOOL_RESULTS error code

INVALID_TOOL_RESULTS is a LangChain error code that indicates tool results are in an invalid format.

MESSAGE_COERCION_FAILURE error code

MESSAGE_COERCION_FAILURE is a LangChain error code that indicates a message could not be converted to the expected format.

MODEL_AUTHENTICATION error code

MODEL_AUTHENTICATION is a LangChain error code that indicates authentication failed when connecting to a model.

MODEL_NOT_FOUND error code

MODEL_NOT_FOUND is a LangChain error code that indicates the specified model could not be found.

MODEL_RATE_LIMIT error code

MODEL_RATE_LIMIT is a LangChain error code that indicates a rate limit was exceeded when calling a model.

LangChain semantic versioning and release cadence

With the release of LangChain 1.0, minor releases (e.g., from 1.0.x to 1.1.0) of langchain and langchain-core follow semantic versioning and may be released frequently. Minor releases contain new features and improvements but do not include breaking changes. Patch versions are released frequently, up to a few times per week, as they contain bug fixes and minor improvements.

LangChain API stability and breaking changes policy

Breaking changes to the public API in langchain and langchain-core will only occur in major version releases (e.g., 2.0.0). Minor version bumps (e.g., 1.0.0 to 1.1.0) add new features without breaking changes. Patch version bumps (e.g., 1.0.0 to 1.0.1) contain bug fixes and minor improvements.

LangChain deprecation policy

With LangChain 1.0's semantic versioning approach, deprecated features will continue to work throughout the entire 1.x release series. Breaking changes, including the removal of deprecated features, will only occur in major version releases (e.g., 2.0). When a feature is deprecated in langchain or langchain-core, LangChain will clearly mark it as deprecated in the code and documentation, provide migration guidance to the recommended alternative, and provide security updates for the deprecated feature through all 1.x minor releases.

LangChain 0.3 legacy version support

LangChain 0.3 is in MAINTENANCE mode until December 2026 and receives security patches and critical bug fixes.

Give your agent this brain