langchain-ai/langchain
61.7
Adequate · 14 November 2026
184.6k
lines of production code
Python
primary language
6
measurements over time
What this system is
Features
Add CI and linting scripts for the langchain-openrouter package
This change introduces a set of utility scripts for the new \langchain-openrouter\ partner package to support development and CI workflows. It includes \check\_imports.py\ to validate Python file imports, \check\_version.py\ to ensure version consistency between \pyproject.toml\ and \\_version.py\, and \lint\_imports.sh\ to prevent unauthorized imports from \langchain\ or \langchain\_experimental\ namespaces. These tools help maintain code quality and consistency for the new provider integration.
libs/partners/openrouter/scripts · high confidence
Add Fireworks partner package validation scripts
This change introduces three new scripts for the Fireworks partner integration to enforce code quality and consistency. \check\_imports.py\ validates that Python files load without errors, \check\_version.py\ ensures the package version in \pyproject.toml\ matches the version defined in \\_version.py\, and \lint\_imports.sh\ prevents unauthorized imports from \langchain\ or \langchain\_experimental\ (allowing only specific v1 middleware paths).
libs/partners/fireworks/scripts · high confidence
Add FireworksEmbeddings integration
The langchain-fireworks partner package now includes a FireworksEmbeddings class, allowing users to generate vector embeddings using Fireworks AI models. The integration defaults to the nomic-ai/nomic-embed-text-v1.5 model and automatically retrieves the API key from the FIREWORKS\_API\_KEY environment variable or accepts it directly during initialization.
langchain-fireworks · high confidence
Add OpenAI moderation middleware for agent traffic
Users can now integrate OpenAI's moderation endpoint into their agents via the new \OpenAIModerationMiddleware\. This middleware intercepts agent traffic to check user inputs, model outputs, and optionally tool results for policy violations. It supports configurable moderation models (defaulting to \omni-moderation-latest\) and allows users to define how violations are handled—either by raising an error, ending the run, or replacing the flagged content with a custom message. The implementation is exposed through the \langchain\_openai.middleware\ package. Also in this area: 9 commits (0 fixes) modifying libs/partners.
_libs/partners/openai/langchain\openai/middleware · medium confidence · unverified
Add Perplexity integration with CI validation scripts
This change introduces the Perplexity Chat integration partner library, accompanied by three new scripts in the \libs/partners/perplexity/scripts\ directory to support development and CI workflows. The \check\_imports.py\ script validates that Python files load without errors, \check\_version.py\ ensures version consistency between \pyproject.toml\ and the package's \\_version.py\, and \lint\_imports.sh\ prevents unauthorized imports from \langchain\ or \langchain\_experimental\ modules, thereby enforcing dependency boundaries for the new integration.
libs/partners/perplexity/scripts · high confidence
Add PerplexityEmbeddings class and new search/response types
This update introduces the \PerplexityEmbeddings\ class, allowing users to generate vector embeddings via the Perplexity API for use in LangChain applications. It also adds new Pydantic models (\UserLocation\, \WebSearchOptions\, \MediaResponse\) to \types.py\, providing structured support for advanced web search parameters and media response configurations in the integration.
langchain-perplexity · high confidence
Add import and version validation scripts for the Exa partner library
The Exa partner library now includes three new scripts in the \scripts\ directory to enforce code quality and consistency during development and CI. \check\_imports.py\ validates that specified Python files can be successfully imported, \check\version.py\ ensures the version string in \pyproject.toml\ matches the \\\version\\_\ variable in \langchain\_exa/\_version.py\, and \lint\_imports.sh\ prevents accidental imports from \langchain\ or \langchain\_experimental\ (with specific allowances for \langchain.agents\ and \langchain.tools\).
libs/partners/exa/scripts · high confidence
Add utility functions for checking Hugging Face Optimum and OpenVINO availability
The library now includes a new \import\_utils.py\ module that provides helper functions to detect the presence and versions of \optimum\, \optimum.intel\, and \openvino\ packages. This enables the Hugging Face integration to conditionally support features dependent on these libraries, such as Intel IPEX models, by checking availability at runtime rather than failing on import.
_libs/partners/huggingface/langchain\huggingface/utils · high confidence
Added DeepSeek model profile data
The \langchain\_deepseek\ package now includes a \data\ directory containing auto-generated model profiles for DeepSeek models (including \deepseek-flash\, \deepseek-v4-flash\, \deepseek-v4-flash-vision-exp\, and \deepseek-v4-pro\). This data, sourced from models.dev, provides metadata such as token limits, input/output capabilities, and feature flags. The profiles are augmented via a TOML configuration file to explicitly enable \tool\_call\_streaming\ for the provider.
_libs/partners/deepseek/langchain\deepseek/data · high confidence
Added Groq partner integration scripts
This change introduces a set of utility scripts for the new Groq partner integration located in libs/partners/groq/scripts. The check\version.py script validates that the package version defined in pyproject.toml matches the \\version\\_ variable in the source code to prevent mismatches. The check\_imports.py script ensures that specific Python files can be loaded without import errors. Additionally, lint\_imports.sh enforces coding standards by preventing imports from langchain or langchain\experimental (with specific allowances for langchain.agents and langchain.tools), and an \\init\\_.py file is added to define the scripts module.
libs/partners/groq/scripts · high confidence
Added Hugging Face model profile data and configuration
The Hugging Face partner package now includes a dedicated data module containing auto-generated model profiles sourced from models.dev, covering details such as token limits, input/output modalities, and capabilities like tool calling and structured outputs for models including MiniMax and Qwen series. A configuration file (\profile\_augmentations.toml\) is also introduced to allow provider-specific overrides, such as enabling tool call streaming by default.
_libs/partners/huggingface/langchain\huggingface/data · high confidence
Added import, version, and linting scripts for the Ollama partner package
The Ollama partner package now includes three new scripts in its \scripts\ directory to support development and CI workflows. \check\_imports.py\ allows developers to verify that specific Python files load without errors, while \check\_version.py\ ensures version consistency between \pyproject.toml\ and the package's \\_version.py\ file to prevent release mismatches. Additionally, \lint\_imports.sh\ enforces import hygiene by preventing direct imports from \langchain\ or \langchain\_experimental\ (with specific allowances for \langchain.agents\ and \langchain.tools\), helping to maintain proper package boundaries.
libs/partners/ollama/scripts · high confidence
Added validation scripts for the Hugging Face partner library
This change introduces three new scripts to the Hugging Face partner library to enforce code quality and consistency. \check\_imports.py\ validates that Python files can be loaded without errors, \check\_version.py\ ensures the version string in \pyproject.toml\ matches the one in \\_version.py\ to prevent release mismatches, and \lint\_imports.sh\ prevents accidental imports from \langchain\ or \langchain\_experimental\ packages, allowing only specific legacy paths.
libs/partners/huggingface/scripts · high confidence
Added validation scripts for the Nomic partner integration
The Nomic partner integration now includes three new scripts to enforce code quality and consistency: \check\_imports.py\ validates that Python files load without errors, \check\_version.py\ ensures the version in \pyproject.toml\ matches \langchain\_nomic/\_version.py\ to prevent mismatches, and \lint\_imports.sh\ prevents importing from \langchain\ or \langchain\_experimental\ (except for specific v1 middleware paths).
libs/partners/nomic/scripts · high confidence
Async support added to example selectors
The example selector classes in \langchain\_core.example\_selectors\ now include asynchronous methods (\aadd\_example\ and \aselect\_examples\) alongside their synchronous counterparts. This allows users to integrate example selection logic into async workflows without blocking the event loop, with \BaseExampleSelector\, \SemanticSimilarityExampleSelector\, and related classes updated to support this new capability.
_libs/core/langchain\_core/example\selectors · high confidence
DeepSeek partner library adds CI validation scripts
The DeepSeek partner library now includes three new scripts in its \scripts\ directory to enforce code quality and consistency during development and CI. \check\_imports.py\ validates that Python files can be loaded without errors, \check\version.py\ ensures the version defined in \pyproject.toml\ matches the \\\version\\_\ variable in the package's \\_version.py\, and \lint\_imports.sh\ prevents accidental imports from \langchain\ or \langchain\_experimental\ (except for allowed v1 middleware paths).
libs/partners/deepseek/scripts · high confidence
Initial release of langchain-exa integration
This change introduces the \langchain-exa\ package (version 1.1.0), providing LangChain components for the Exa Search API. It adds \ExaSearchRetriever\ for document retrieval, \ExaSearchResults\ and \ExaFindSimilarResults\ tools for search and similarity queries, and exposes \HighlightsContentsOptions\ and \TextContentsOptions\ from the underlying \exa\_py\ library. The integration supports search types (auto, deep, fast), domain filtering, date ranges, and content options like highlights and summaries.
_libs/partners/exa/langchain\exa · high confidence
Initial release of langchain-huggingface package
The \langchain-huggingface\ partner integration is now available as a standalone package (version 1.2.2). This release introduces the \ChatHuggingFace\ chat model, \HuggingFaceEmbeddings\ and \HuggingFaceEndpointEmbeddings\ for embedding tasks, and \HuggingFaceEndpoint\ and \HuggingFacePipeline\ for LLM inference, providing a unified entry point for Hugging Face models within LangChain.
_libs/partners/huggingface/langchain\huggingface · high confidence
Introduce HuggingFace LLM components with streaming, provider support, and local pipeline execution
The \langchain\_huggingface.llms\ module now exposes \HuggingFaceEndpoint\ and \HuggingFacePipeline\ classes. \HuggingFaceEndpoint\ enables inference via the Hugging Face Inference API (or third-party providers like Novita) with support for async streaming, configurable generation parameters, and environment-based token configuration. \HuggingFacePipeline\ allows running models locally using the \transformers\ library, supporting tasks such as text generation, summarization, and image-text-to-text, with explicit handling for device mapping and backend selection (including a deprecation notice for the retired IPEX backend in favor of native PyTorch acceleration).
_libs/partners/huggingface/langchain\huggingface/llms · high confidence
Introduce LangChain integration for DeepSeek models
Adds the \langchain-deepseek\ package (version 1.1.1), providing the \ChatDeepSeek\ class to interact with DeepSeek's API. The integration extends the OpenAI-compatible base to handle DeepSeek-specific features, including mapping \prompt\_cache\_hit\_tokens\ to usage metadata, supporting strict beta structured output, and ensuring correct tool choice behavior for Azure deployments.
_libs/partners/deepseek/langchain\deepseek · high confidence
Introduce LangChain integration for Perplexity AI
This release adds the \langchain-perplexity\ partner package (v1.4.1), providing a complete set of components to interact with Perplexity AI. Users can now use \ChatPerplexity\ for chat completions, \PerplexityEmbeddings\ for vector embeddings, and \PerplexitySearchRetriever\ or \PerplexitySearchResults\ for web search capabilities. The integration includes specialized output parsers (\ReasoningJsonOutputParser\, \ReasoningStructuredOutputParser\) to handle reasoning model outputs by stripping think tags, and supports both the standard Chat Completions API and the new Responses (Agent) API via a dedicated flag.
_libs/partners/perplexity/langchain\perplexity · high confidence
Introduce LangChain integration for xAI
Adds the \langchain-xai\ package (version 1.3.0), providing the \ChatXAI\ class to interact with xAI's Chat Completions API. This new integration allows users to instantiate and invoke xAI models (such as Grok) using standard LangChain interfaces, including support for streaming, async operations, and structured output.
_libs/partners/xai/langchain\xai · high confidence
Introduce MistralAIEmbeddings with retry logic and token batching
Adds the \MistralAIEmbeddings\ class to the \langchain\_mistralai\ partner package, enabling users to generate vector embeddings via the Mistral API. The implementation includes automatic retry mechanisms for transient errors (timeouts, 429 rate limits, and 5xx server errors) and handles token batching with a 16k token limit per request to optimize API usage.
langchain-mistralai · high confidence
Introduce NomicEmbeddings partner integration with local inference and vision support
The \langchain\_nomic\ package is now available, providing the \NomicEmbeddings\ class for generating text and image embeddings. Users can configure the model via the \model\ parameter, specify embedding dimensions with \dimensionality\, and choose between remote, local, or dynamic inference modes using \inference\_mode\. Local inference allows execution on specific devices (e.g., CPU/GPU) via the \device\ parameter, while the new \vision\_model\ parameter enables image embedding capabilities through \embed\_image\.
_libs/partners/nomic/langchain\nomic · high confidence
Introduce VectorStore abstraction and InMemoryVectorStore implementation
The \langchain\_core.vectorstores\ package now provides a foundational \VectorStore\ abstract base class and a concrete \InMemoryVectorStore\ implementation for local, in-memory vector storage and search. Users can now import \VectorStore\, \VectorStoreRetriever\, and \InMemoryVectorStore\ directly from \langchain\_core.vectorstores\. The \InMemoryVectorStore\ supports adding, deleting, and searching documents using cosine similarity (via NumPy or simsimd), with optional filtering and maximal marginal relevance (MMR) retrieval. The base \VectorStore\ defines standard interfaces like \add\_texts\, \delete\, \similarity\_search\, and async equivalents, enabling consistent integration across different vector store backends.
_libs/core/langchain\core/vectorstores · high confidence
Introduce \`create\_agent\` factory with middleware support and structured output strategies
LangChain v1 now provides a new \create\_agent\ factory function (exposed in \langchain.agents\) to build agents with a modern middleware architecture. This replaces the previous \create\_react\_agent\ pattern, allowing users to attach middleware hooks for tracing, tool call wrapping, and state management. The factory includes built-in support for structured output via \ProviderStrategy\ and \ToolStrategy\, enabling typed responses from models like GPT-4o and GPT-5. Additionally, nested agents (subagents) invoked by tools are now surfaced as typed handles on \run.subagents\, providing clear causality tracking for nested execution flows.
_libs/langchain\v1/langchain/agents · high confidence
Introduce beta \`langchain.mcp\` namespace for connecting to MCP servers
The \langchain.mcp\ namespace is now available (in beta) to connect LangChain agents to Model Context Protocol (MCP) servers. This release introduces the \MCPAdapter\ class, which adapts MCP targets—such as HTTP URLs, local script paths, or pre-built FastMCP clients—into LangChain tools suitable for \create\_agent\. It also includes \as\_langchain\_tool\ for converting individual MCP tools and \MCPToolArtifact\ for attaching structured content. A key behavioral addition is interrupt-driven elicitation: when an MCP server requests input mid-call, the adapter automatically triggers a LangGraph \interrupt()\, allowing a human to provide answers and resume the run. The namespace raises a \LangChainBetaWarning\ on import to indicate that the API is actively being developed.
_libs/langchain\v1/langchain/mcp · high confidence
Introduce content-block-centric streaming (v3) and model profiles
The \langchain\_core.language\_models\ package now exposes a new streaming protocol via \BaseChatModel.stream\_events(version="v3")\ and \astream\_events(version="v3")\, which emit structured \content-block-delta\ and \content-block-finish\ events instead of raw message chunks. This change is supported by a new \\_compat\_bridge\ module that translates existing \AIMessageChunk\ streams into the new protocol, and a \ChatModelStream\ class that provides typed projections (e.g., \.text\, \.tool\_calls\) for accumulating these events. Additionally, a \ModelProfile\ type and \model.profile\ property have been added to \BaseChatModel\ to expose model capabilities (such as supported input types like images, audio, and PDFs) sourced from \langchain-model-profiles\. The package also includes updated fake models (\FakeListChatModel\, \FakeMessagesListChatModel\) and utility functions for handling OpenAI-style data blocks and message normalization.
_libs/core/langchain\_core/language\models · high confidence
Introduce langchain-mistralai partner package (v1.1.6)
This change introduces the \langchain-mistralai\ package as a standalone partner integration for LangChain, exposing \ChatMistralAI\ and \MistralAIEmbeddings\ classes. The implementation includes a content-block translator (\\_compat.py\) to map Mistral-specific message formats (such as citations, reasoning/thinking blocks, and tool calls) to LangChain's standard v1 message types, ensuring compatibility with downstream consumers. It also establishes a global SSL context for secure HTTP connections and integrates with the LangChain model profile registry for metadata tracking.
_libs/partners/mistralai/langchain\mistralai · high confidence
Introduce langchain-openrouter partner package
Users can now integrate with the OpenRouter unified API through the new \langchain-openrouter\ package. This release adds the \ChatOpenRouter\ class, enabling access to hundreds of models from multiple providers (such as OpenAI, Anthropic, and Google) within LangChain applications. The integration supports standard chat parameters, streaming, tool calling, and includes features for attribution, session tracking, and cost metadata.
_libs/partners/openrouter/langchain\openrouter · high confidence
Introduce langchain-tests as the new standard testing library
The \libs/standard-tests\ package is now published as \langchain-tests\, replacing the previous \langchain\_standard\_tests\ name. This library provides a standardized set of base test classes and integration test suites for LangChain integrations, covering components such as chat models, embeddings, retrievers, vector stores, tools, caches, and base stores. It includes a pytest plugin that automatically forwards LangSmith CI environment variables (tags and metadata) into tracing context when running in GitHub Actions, and uses VCR cassettes with a custom YAML serializer to record and replay API interactions for reliable testing.
libs/standard-tests · high confidence
Introduce lazy imports and new prompt template types in langchain\_core.prompts
The \langchain\core.prompts\ package now uses lazy imports via a custom \\\getattr\\\ in \\\init\\_.py\ to improve startup performance, exposing classes like \ChatPromptTemplate\, \PromptTemplate\, and \MessagesPlaceholder\ on demand. This release also introduces several new prompt template types: \DictPromptTemplate\ for formatting dictionary-based templates, \ImagePromptTemplate\ for multimodal image inputs (with file path loading removed for security), and \FewShotPromptWithTemplates\ which allows prefix/suffix components to be full prompt templates rather than just strings. Additionally, \MessagesPlaceholder\ now supports an \optional\ flag and a \n\_messages\ limit to control how many history messages are included.
_libs/core/langchain\core/prompts · high confidence
Introduce model profile management and refresh tooling
This change introduces the \langchain\_model\_profiles\ package, providing the infrastructure to manage and refresh model profile data. It includes a CLI (\cli.py\) to fetch and update profiles from models.dev, a diffing engine (\\_summary.py\) that generates plain-English Markdown summaries of changes (new, removed, or modified models and fields) for pull requests, and support for profile augmentations via TOML configuration. This enables maintainers to easily review and merge updates to model capabilities and metadata.
_libs/model-profiles/langchain\_model\profiles · high confidence
Introduce provider-specific block translators for standard content parsing
A new \block\_translators\ module has been added to \langchain\_core\ to handle the conversion of provider-specific message content (from Anthropic, Bedrock, Bedrock Converse, Google GenAI, Google VertexAI, Groq, and OpenAI) into the standard v1 \ContentBlock\ format. This change introduces a centralized registry system where each provider can register its own translation logic for both full messages and streaming chunks. For users, this means that accessing \content\_blocks\ on \AIMessage\ or \AIMessageChunk\ instances from these providers will now yield standardized, structured blocks (such as text, images, files, and tool calls) rather than raw provider-specific dictionaries, ensuring consistent behavior across different model integrations.
_libs/core/langchain\_core/messages/block\translators · high confidence
Introduce standalone langchain-text-splitters package
The text splitting utilities are now available as a standalone \langchain-text-splitters\ package, decoupled from the main \langchain\ library. This new package includes the full suite of splitters (such as \CharacterTextSplitter\, \HTMLHeaderTextSplitter\, \MarkdownHeaderTextSplitter\, and \JSFrameworkTextSplitter\) with lazy loading for heavy optional dependencies like \nltk\ and \spacy\ to keep the initial import lightweight. It also provides a dedicated development environment with a \Makefile\ for linting, formatting, and testing, along with standard project files like \LICENSE\ and \README.md\.
libs/text-splitters · high confidence
Introduce the \`langchain-openai\` package with ChatGPT OAuth support and OpenAI SDK 3.0 compatibility
This change introduces the new \langchain\_openai\ package (version 1.6.6), which consolidates OpenAI integrations including \ChatOpenAI\, \OpenAI\, \AzureChatOpenAI\, \OpenAIEmbeddings\, and a new \custom\_tool\ utility. The package adds support for the OpenAI Python SDK 3.0 by dynamically resolving the underlying HTTP client (\httpx\ vs \httpx2\) to ensure compatibility. It also introduces \ChatOpenAICodex\, a chat model that authenticates via ChatGPT OAuth (Authorization Code Flow with PKCE) for subscription-based access, storing tokens in \\~/.langchain/chatgpt-auth.json\. Additionally, the package exports \StreamChunkTimeoutError\ to help users handle streaming hangs.
_libs/partners/openai/langchain\openai · high confidence
Introduce v1 chat model factory with expanded provider support
The \langchain\_v1\ package now includes a new \init\_chat\_model\ factory function that simplifies instantiating chat models by automatically inferring the provider from the model name and handling optional dependency installation. This entry point exposes \BaseChatModel\ and \init\_chat\_model\, registering a comprehensive set of built-in providers including Anthropic, AWS Bedrock (standard, converse, and Mantle variants), Azure AI Foundry, OpenAI, Google Vertex/GenAI, Hugging Face, Meta, Upstage, and LangSmith (via gateway). Users can now create models across these providers with a single call, with the system automatically resolving the correct integration package and class.
_libs/langchain\_v1/langchain/chat\models · high confidence
Introduces internal API management for beta and deprecation warnings
The \langchain\_core.\api\ module now provides the infrastructure for marking LangChain components as beta or deprecated. This includes the \@beta\ and \@deprecated\ decorators, which emit specific warnings (\LangChainBetaWarning\ and \LangChainDeprecationWarning\) to users while suppressing them for internal library calls. The module also supports lazy loading of these utilities via a custom \\\getattr\\_\ to reduce import overhead, and provides helper functions for path manipulation used in warning messages.
_libs/core/langchain\_core/\api · high confidence
Introduces new agent middleware package with comprehensive plugin system
The \langchain.agents.middleware\ package is now available, providing a structured way to extend agent behavior through middleware plugins. This release introduces several key middleware components: \HumanInTheLoopMiddleware\ for human review and approval workflows, \PIIMiddleware\ for detecting and redacting personally identifiable information in real-time, \SummarizationMiddleware\ for managing context window usage, and \ModelRetryMiddleware\ for handling transient model failures with exponential backoff. Additional utilities include \ToolRetryMiddleware\, \ModelCallLimitMiddleware\ for tracking usage, \FilesystemFileSearchMiddleware\ for file operations, and \ContextEditingMiddleware\ for state manipulation. The package also includes shared utilities for retry logic, trace policy configuration, and internal call filtering, all exposed through a unified \\_\init\\_.py\ interface.
_libs/langchain\v1/langchain/agents/middleware · high confidence
Introduction of langchain-core as the foundational library for LangChain abstractions
The \langchain-core\ package is introduced to define the base abstractions for the LangChain ecosystem, including interfaces for chat models, LLMs, vector stores, retrievers, and the universal invocation protocol (Runnables). This new location establishes the core schema definitions for agents, caching mechanisms, chat message history, and key-value stores, while also providing standard exception types and rate-limiting utilities. By centralizing these foundational components, the library ensures a lightweight dependency footprint and provides a stable API layer for third-party integrations and higher-level LangChain features.
_libs/core/langchain\core · high confidence
Introduction of structured output parsers in langchain\_core
The \langchain\_core.output\parsers\ module has been introduced to provide a centralized set of parsers for converting LLM outputs into structured data. This includes \JsonOutputParser\ and \PydanticOutputParser\ for JSON and Pydantic model validation, \XMLOutputParser\ with secure \defusedxml\ support, and list parsers (\CommaSeparatedListOutputParser\, \ListOutputParser\, etc.). The module also exports OpenAI tools parsers (\JsonOutputToolsParser\, \PydanticToolsParser\) and base classes like \BaseOutputParser\ and \BaseTransformOutputParser\ to support streaming and cumulative parsing. All parsers are lazily imported via \\\getattr\\_\ to optimize startup time.
_libs/core/langchain\_core/output\parsers · high confidence
Introduction of the LangChain Expression Language (LCEL) Runnable primitives
This change introduces the core \Runnable\ objects and the LangChain Expression Language (LCEL) to \langchain\_core\. It provides a declarative API for building production-grade programs that inherently support synchronous, asynchronous, batch, and streaming operations. The module exposes key composition primitives such as \RunnableSequence\ (for chaining steps with the \\|\ operator) and \RunnableParallel\ (for concurrent execution), along with utility classes like \RunnableLambda\, \RunnableBranch\, \RunnableWithFallbacks\, and \RunnableWithMessageHistory\. It also includes configuration management via \RunnableConfig\ and graph visualization capabilities using Mermaid and ASCII diagrams.
_libs/core/langchain\core/runnables · high confidence
Introduction of the langchain-openai LLM module
The \langchain\_openai.llms\ package has been introduced, providing the \OpenAI\ and \AzureOpenAI\ classes for large language model completions. This new module separates text-completion models from chat models (which reside in \chat\_models/\) and implements the \BaseOpenAI\ foundation class. It supports configuration via environment variables, handles Azure-specific endpoints and deployments, and includes validation logic to ensure compatibility with the OpenAI Python SDK v1.x.
_libs/partners/openai/langchain\openai/llms · high confidence
LangChain Classic package scaffolding and development environment setup
The \libs/langchain\ directory is now structured as the standalone \langchain-classic\ package, providing the legacy chains, community re-exports, and deprecated functionality. This change introduces a complete development environment for the package, including a \Makefile\ with targets for linting, formatting, and testing via \uv\, a \dev.Dockerfile\ based on Python 3.14, and a \uv.lock\ file for dependency management. It also adds a \.dockerignore\ file, an MIT \LICENSE\, and an updated \README.md\ directing users to the main \langchain\ package for new development.
libs/langchain · high confidence
Move document loader interfaces to core and add LangSmith loader
The document loader base classes (BaseLoader, BaseBlobParser) and blob schema (Blob, BlobLoader) have been moved from the community package into langchain\_core, providing a stable, core-level interface for loading and parsing documents. This location also introduces the LangSmithLoader, which allows users to load LangSmith dataset examples as Document objects for few-shot retrieval, supporting features like nested content keys, dataset splits, and versioning.
_libs/core/langchain\_core/document\loaders · high confidence
New Anthropic middleware package for tools, caching, and search
The \langchain\_anthropic\ package now includes a dedicated \middleware\ module that provides several new capabilities for agents using Anthropic models. Users can now leverage \AnthropicPromptCachingMiddleware\ to optimize API usage by caching system messages and tool definitions. The package also introduces \ClaudeBashToolMiddleware\ to expose the native bash tool, \StateFileSearchMiddleware\ for glob and grep searches over virtual files, and \FilesystemClaudeMemoryMiddleware\ and \StateClaudeTextEditorMiddleware\ for managing text editing and memory tools via state or filesystem backends.
_libs/partners/anthropic/langchain\anthropic/middleware · high confidence
New OllamaEmbeddings integration with model validation and async support
The langchain-ollama package now includes a dedicated OllamaEmbeddings class, allowing users to generate vector embeddings using local Ollama models. This integration supports specifying the model name, configuring a custom base URL, and passing additional HTTP client arguments for both synchronous and asynchronous operations. It also introduces a \dimensions\ parameter to control output vector size and a \validate\_model\_on\_init\ flag to verify model availability at startup.
langchain-ollama · high confidence
New agent middleware framework with shell, planning, and context management capabilities
LangChain introduces a new middleware system for agents in the \langchain\_v1\ package, replacing the legacy chain-based architecture. This update adds a \ShellToolMiddleware\ that provides agents with a persistent, secure shell session, featuring configurable execution policies (host, Docker, or Codex sandbox) and built-in PII redaction for sensitive data. A \TodoListMiddleware\ is included to help agents manage complex, multi-step tasks through a structured to-do list. Additionally, a \ContextEditingMiddleware\ automatically prunes older tool results to manage context window size, and a new \structured\_output\ module enables agents to return strongly-typed responses using Pydantic models or TypedDicts. The legacy \langchain\ package (v0.0.1) and its basic chains (LLMChain, LLMMathChain, etc.) have been removed.
langchain · high confidence
New chat model integration test suite in langchain-tests
The \langchain-tests\ package now includes a comprehensive \ChatModelIntegrationTests\ class in \langchain\_tests/integration\_tests/chat\_models.py\. This new test suite validates chat model behaviors, including structured output parsing (Pydantic, TypedDict, JSON Schema), tool calling (with and without arguments), streaming event validation, and Unicode handling. It also introduces specific assertions for content-block-centric streaming and tool call chunks, ensuring models conform to the standard interface for both synchronous and asynchronous interactions.
langchain-tests · high confidence
New core abstractions and hardened SSRF protection
langchain-core introduces several foundational classes and interfaces: a new \SSRFPolicy\ module that blocks private IPs, localhost, cloud metadata endpoints, and Kubernetes internal addresses to prevent Server-Side Request Forgery; base classes for document compression (\BaseDocumentCompressor\) and structured queries (\StructuredQuery\, \Comparison\, \Operation\); and new output containers (\ChatResult\, \LLMResult\, \RunInfo\) alongside a \Serializable\ base class for JSON serialization. It also adds \BaseChatMessageHistory\ for managing chat history, \LengthBasedExampleSelector\ for prompt example selection, and \FakeEmbeddings\/\DeterministicFakeEmbedding\ for testing. The \BaseTool\ implementation is updated to support custom \extras\, handle injected arguments correctly, and preserve field descriptions in the \@tool\ decorator.
langchain-core · high confidence
New document abstractions and lazy-loading module structure
The \langchain\core.documents\ module has been restructured to support lazy imports via a custom \\\getattr\\\ in \\\init\\_.py\, improving startup performance. This change introduces new core abstractions for data retrieval workflows: \BaseMedia\ (providing optional \id\ and \metadata\ fields), \Blob\ (for raw data loading with MIME type and encoding support), and \BaseDocumentCompressor\ (for post-processing retrieved documents). These classes are distinct from LLM chat message content blocks and are intended for use in RAG pipelines, vector stores, and document processing.
_libs/core/langchain\core/documents · high confidence
New experimental model routing and ChatGPT OAuth capabilities
The \langchain-openai\ package introduces two new capabilities. First, it adds support for the OpenAI Decisions API, providing \OpenAIDecisions\ and types like \Predicate\, \Choice\, and \Score\ to evaluate conditions or select from options, which is utilized by the new experimental \OpenAIModelRouterMiddleware\ to dynamically select agent models based on task criteria. Second, it adds \ChatGPT OAuth\ helpers and the \\_ChatOpenAICodex\ chat model, enabling authentication via the ChatGPT subscription flow (OAuth 2.0 with PKCE) for accessing Codex features, distinct from the standard API key flow.
langchain-openai · high confidence
New indexing API with DocumentIndex abstraction and in-memory implementation
The \langchain\_core.indexing\ package introduces a new high-level API for indexing documents into vector stores, designed to handle deduplication and avoid re-indexing unchanged content. This change adds the \DocumentIndex\ abstraction and an \InMemoryDocumentIndex\ implementation for testing or lightweight use, alongside the \RecordManager\ interface for tracking document state. The \index\ and \aindex\ functions now support configurable hashing algorithms (SHA-1, SHA-256, SHA-512, blake2b) with a warning for the default SHA-1, and include logic to validate batch sizes to prevent infinite loops. The API also exposes \UpsertResponse\ and \DeleteResponse\ types to clarify upsert and deletion semantics.
_libs/core/langchain\core/indexing · high confidence
New internal SSRF protection utilities for URL validation and HTTP transport
The \langchain\_core.\_security\ module has been introduced to provide internal Server-Side Request Forgery (SSRF) protection. This includes \SSRFPolicy\ for defining allowed schemes and blocked IP ranges (such as private, localhost, and cloud metadata IPs), validation functions like \validate\_safe\_url\ and \is\_safe\_url\ to check URLs before use, and \SSRFSafeTransport\ classes for both synchronous and asynchronous HTTP clients that enforce these policies by resolving DNS and pinning to validated IPs. These utilities are internal and not part of the public API, designed to be used by other LangChain components to secure outgoing requests.
_libs/core/langchain\_core/\security · high confidence
New langchain-openai embeddings module with Azure AD and dimension support
The embeddings logic has been reorganized into a new \langchain\_openai.embeddings\ package, exposing \OpenAIEmbeddings\ and \AzureOpenAIEmbeddings\. For Azure users, the integration now explicitly supports embedding dimensions via the \dimensions\ parameter and adds flexible Azure Active Directory authentication through \azure\_ad\_token\ and \azure\_ad\_token\_provider\ fields. The \AzureOpenAIEmbeddings\ class also enforces stricter validation for \openai\_api\_base\ versus \azure\_endpoint\ to align with the OpenAI Python SDK v1+ requirements.
_libs/partners/openai/langchain\openai/embeddings · high confidence
New messages module exposes core message types and utilities
A new \langchain.messages\ module has been added to the v1 library, re-exporting a comprehensive set of message types, content blocks, and utility functions from \langchain\_core\. This includes role-based messages (HumanMessage, AIMessage, SystemMessage, ToolMessage), content block types for text, images, audio, video, and data, as well as tool call representations, usage metadata, and the \trim\_messages\ utility. Users can now import these standard message components directly from \langchain.messages\ instead of \langchain\_core.messages\.
_libs/langchain\v1/langchain/messages · high confidence
New scripts for linting, version checking, and recording Codex cassettes
The \libs/partners/openai/scripts\ directory now includes several new utility scripts: \check\_imports.py\ and \lint\_imports.sh\ to validate import correctness and prevent unauthorized dependencies; \check\_version.py\ to ensure version consistency between \pyproject.toml\ and \\_version.py\; and \record\_codex\_cassettes.sh\ (along with \RECORD\_CODEX\_CASSETTES.md\) to facilitate recording and scrubbing VCR cassettes for the experimental \ChatOpenAICodex\ integration tests, ensuring no OAuth secrets leak into CI artifacts.
libs/partners/openai/scripts · high confidence
New sparse embeddings provider interface for Qdrant
The Qdrant integration now includes a new \SparseEmbeddings\ abstract base class and \SparseVector\ data model, enabling users to integrate sparse embedding models with Qdrant. This interface defines methods for embedding documents and queries (both synchronous and asynchronous), allowing for hybrid search capabilities that combine dense and sparse vector representations.
langchain-qdrant · high confidence
New tools module with lazy imports and enhanced tool creation
The \langchain\core.tools\ package has been restructured to support lazy imports via a custom \\\getattr\\\ in \\\init\\_.py\, improving startup performance by deferring the loading of heavy dependencies like Pydantic and specific tool implementations until they are actually accessed. This module now exposes a comprehensive \tool\ decorator in \convert.py\ that allows converting Python functions and Runnables into LangChain tools, featuring automatic schema inference, docstring parsing, and support for provider-specific extras. Additionally, the package introduces \StructuredTool\ for complex multi-argument inputs with JSON-serializable schemas, a simplified \Tool\ class for single-function wrappers, and utility functions in \render.py\ to generate text descriptions of tools for agent prompts.
_libs/core/langchain\core/tools · high confidence
New unified \`init\_embeddings\` factory in LangChain v1
LangChain v1 introduces a new \init\_embeddings\ function in \libs/langchain\v1/langchain/embeddings/base.py\ that provides a unified way to instantiate embedding models across multiple providers (such as OpenAI, Azure AI, Bedrock, Cohere, and Google Genai) using a single API. This factory parses provider-specific model strings (e.g., \openai:text-embedding-3-small\) or accepts explicit provider arguments, handling the underlying imports and instantiation logic. The \\\init\\_.py\ module exposes this factory and the core \Embeddings\ interface, while also warning users that community and cache-backed embeddings have moved to \langchain-classic\.
_libs/langchain\v1/langchain/embeddings · high confidence
New validation scripts for the Chroma partner package
Added three new scripts to the Chroma partner location to improve build integrity: \check\_imports.py\ verifies that Python files can be imported without error, \check\_version.py\ ensures version consistency between \pyproject.toml\ and \\_version.py\, and \lint\_imports.sh\ prevents accidental imports from \langchain\ or \langchain\_experimental\ namespaces.
libs/partners/chroma/scripts · high confidence
Plain-English summaries for model profile refresh PRs
The \langchain-model-profiles\ library now includes a module that generates skimmable Markdown summaries for automated pull requests that update model profile data. Instead of reviewers having to manually inspect large diffs of generated data, this new feature deterministically produces a plain-English overview of added, removed, and changed models, along with specific field-level updates, directly in the PR body.
langchain-model-profiles · high confidence
Public utility module with lazy loading and gateway configuration helpers
The \langchain\_core.utils\ package is now a public, lazily-imported module that exposes a comprehensive set of utilities—including environment variable resolution (\get\_from\_env\, \get\_from\_dict\_or\_env\), string formatting (\StrictFormatter\), iterator helpers (\batch\_iterate\, \abatch\_iterate\), JSON parsing (\parse\_partial\_json\), and HTML link extraction—without eagerly importing their dependencies. This location also introduces private helpers for resolving LangSmith gateway configuration (\\_gateway.py\), which centralizes the precedence rules for base URLs and API keys so that provider integrations can route requests through the LangSmith proxy consistently.
_libs/core/langchain\core/utils · high confidence
Qdrant integration v1.1.0 introduces sparse embeddings and hybrid search
The \langchain-qdrant\ package has been updated to version 1.1.0, introducing native support for sparse embeddings and hybrid retrieval modes. Users can now utilize the \FastEmbedSparse\ class for sparse text embeddings and configure the \QdrantVectorStore\ with a \RetrievalMode\ enum (DENSE, SPARSE, or HYBRID) to combine dense and sparse vectors in a single query. The integration also exposes a new \QdrantVectorStore\ class alongside the legacy \Qdrant\ class, which is now deprecated, and includes built-in support for Maximal Marginal Relevance (MMR) search.
_libs/partners/qdrant/langchain\qdrant · high confidence
langchain-anthropic 1.7.4 release with Anthropic SDK 1.x support and new model capabilities
The \langchain-anthropic\ partner package has been updated to version 1.7.4, introducing support for the Anthropic Python SDK 1.x alongside the existing 0.x compatibility layer. This update ensures that sampling parameters like \temperature\, \top\_p\, and \top\_k\ are correctly routed to \extra\_body\ when using SDK 1.x, which no longer accepts them as direct arguments. The release also adds support for new model features including Claude Opus 5, Claude Fable 5.1, and the \claude-sonnet-4-5\ default model, while introducing built-in tool support for features like web fetch, code execution, MCP toolsets, and computer use. Additionally, the package now includes a \ChatAnthropicBedrockWrapper\ for AWS Bedrock integration, improved streaming usage metadata, and standardized model profiles for better token limit handling.
_libs/partners/anthropic/langchain\anthropic · high confidence
Removals
Removal of legacy example notebooks
The \examples\ directory has removed three Jupyter notebooks (\llm\_math.ipynb\, \self\_ask\_with\_search.ipynb\, and \simple\_prompts.ipynb\) that demonstrated older LangChain patterns, such as \LLMMathChain\, \SelfAskWithSearchChain\, and the legacy \Prompt\ class. Users relying on these specific examples for reference or copy-pasting will no longer find them in this location.
examples · high confidence
Security
Harden serialization against injection attacks
The \langchain\_core.load\ module now implements escape-based protection against injection attacks during deserialization. Plain user data dicts containing an 'lc' key are automatically escaped during serialization and unwrapped during loading, ensuring they are returned as plain dicts rather than being instantiated as LangChain objects. This prevents crafted payloads from tricking the deserializer into instantiating arbitrary classes. Additionally, the \load\ function now enforces a strict allowlist of classes (controlled by \allowed\_objects\) and validates import paths against trusted namespaces before any module is imported, significantly reducing the risk of SSRF and other side effects when deserializing untrusted manifests.
_libs/core/langchain\core/load · high confidence
Security patch for Pygments dependency
The Pygments library has been updated to version 2.20.0 or higher across all packages to address the [CVE redacted] vulnerability.
(dependencies) · high confidence
Architecture
Tracing module restructured with lazy imports and Pydantic v1/v2 compatibility
The \langchain\core.tracers\ package has been reorganized to use lazy imports via a custom \\\getattr\\\ in \\\init\\_.py\, improving startup performance by deferring the loading of heavy tracer modules. Additionally, a new \\_compat.py\ module was introduced to provide Pydantic v1 and v2 compatibility helpers for \Run\ objects, ensuring that tracer operations like serialization and copying work correctly regardless of the installed Pydantic version. This structural change also includes new internal streaming support classes and context management utilities for the v2 tracing API.
_libs/core/langchain\core/tracers · high confidence
Behavioural changes
1 commit (0 fixes) modifying libs/core/langchain\_core/decisions
A change to existing behaviour in libs/core/langchain\_core/decisions — 1 commit, 2 files: “feat(core): add decision models (\#41765)” (refs \#41765).
_libs/core/langchain\core/decisions · medium confidence · unverified
16 commits (2 fixes) modifying libs/partners/typesafe
A change to existing behaviour in libs/partners/typesafe — 16 commits (2 fixs), 37 files: “release(typesafe): 0.0.1 (\#41650)”; “feat(typesafe): make classifier questions invocation-scoped (\#40659)”; “feat(typesafe): experimental \ModelRouterMiddleware\ (\#40543)”; and 13 more (refs \#41650, \#40659, \#40543, \#40545, \#41266, …).
libs/partners/typesafe · medium confidence · unverified
3 commits (0 fixes) modifying libs/langchain\_v1/examples
A change to existing behaviour in libs/langchain\_v1/examples — 3 commits, 17 files: “chore(deps): bump the minor-and-patch group across 3 directories with 32 updates (\#41465)”; “docs(langchain): runnable \langchain.mcp\ examples (\#39976)”; “feat(langchain): Remove EOL'd Python 3.10 from langchain\_v1 (\#41301)” (refs \#41465, \#39976, \#41301).
_libs/langchain\v1/examples · medium confidence · unverified
3 commits (0 fixes) modifying libs/partners/openai/langchain\_openai/decisions
A change to existing behaviour in libs/partners/openai/langchain\_openai/decisions — 3 commits, 5 files: “feat(partners): Remove EOL'd Python 3.10 from partner packages (\#41268)”; “feat(openai): add OpenAIClassifier for the GA Decisions API (\#41787)”; “feat(openai): support decisions api (\#41125)” (refs \#41268, \#41787, \#41125).
_libs/partners/openai/langchain\openai/decisions · medium confidence · unverified
9 commits (0 fixes) modifying libs/partners
A change to existing behaviour in libs/partners — 9 commits, 64 files: “chore(deps): bump filelock from 4.2.5 to 4.2.10 in /libs/partners/qdrant (\#41835)”; “feat(groq): route \ChatGroq\ through LangSmith gateway (\#41837)”; “chore(model-profiles): refresh model profile data (\#41828)”; and 6 more (refs \#41835, \#41837, \#41828, \#41840, \#41839, …). Also in this area: Added tests for OpenAI Decisions API and Agent Middleware.
_libs/partners/openai/tests/integration\_tests/decisions, libs/partners/openai/tests/unit\_tests/decisions, libs/partners/openai/tests/integration\tests/middleware · medium confidence · unverified
Added CI scripts for import validation and version consistency
New scripts have been added to the Anthropic partner library to enforce code quality and release integrity during CI. The \check\_imports.py\ script validates that specified Python files load without errors, while \lint\_imports.sh\ prevents accidental imports from \langchain\ or \langchain\_experimental\ (except for allowed v1 middleware paths). Additionally, \check\version.py\ ensures that the package version defined in \pyproject.toml\ matches the \\\version\\_\ variable in \\_version.py\, preventing version mismatches.
libs/partners/anthropic/scripts · high confidence
Added CI scripts for import validation and version consistency in xAI partner library
The xAI partner library now includes three new scripts to enforce code quality and release integrity during CI. \check\_imports.py\ validates that Python files can be imported without errors, \check\_version.py\ ensures the version in \pyproject.toml\ matches \langchain\_xai/\_version.py\ to prevent mismatches, and \lint\_imports.sh\ prevents accidental imports from \langchain\ or \langchain\_experimental\ (except for allowed v1 middleware paths).
libs/partners/xai/scripts · high confidence
Added import and version validation scripts for the Mistral AI partner package
The Mistral AI partner package now includes three new scripts in its \scripts\ directory to enforce code quality and consistency. \check\_imports.py\ validates that Python files load without errors, \check\version.py\ ensures the version defined in \pyproject.toml\ matches the \\\version\\_\ variable in \\_version.py\ to prevent mismatches, and \lint\_imports.sh\ prevents accidental imports from \langchain\ or \langchain\_experimental\ (except for allowed v1 middleware paths).
libs/partners/mistralai/scripts · high confidence
Added pre-commit scripts to validate import integrity and version consistency
Two new utility scripts have been added to the langchain v1 scaffolding to improve release safety and development hygiene. The \check\_imports.py\ script allows developers to quickly verify that a list of Python files can be loaded by the interpreter without errors, helping catch syntax or dependency issues before running expensive tests. The \check\version.py\ script ensures that the version string defined in \pyproject.toml\ matches the \\\version\\\ variable in \langchain/\\init\\_.py\, preventing version mismatches during commits.
_libs/langchain\v1/scripts · high confidence
Added validation scripts for import hygiene and version consistency
New scripts have been introduced to the Qdrant partner package to enforce code quality and release integrity. \check\_imports.py\ validates that Python files load without errors, \check\_version.py\ ensures the version string in \pyproject.toml\ matches the one in \\_version.py\ to prevent mismatches, and \lint\_imports.sh\ prevents accidental imports from \langchain\ or \langchain\_experimental\ namespaces.
libs/partners/qdrant/scripts · high confidence
Embeddings module restructured with lazy imports and async support
The embeddings namespace has been reorganized to support lazy loading via a custom \\_\getattr\\_\ mechanism, improving import performance by deferring the loading of \Embeddings\, \FakeEmbeddings\, and \DeterministicFakeEmbedding\ until they are actually accessed. The core \Embeddings\ abstract base class now explicitly defines asynchronous methods (\aembed\_documents\ and \aembed\_query\) that default to running their synchronous counterparts in an executor, providing a built-in async interface for embedding models without requiring individual implementations to handle concurrency.
_libs/core/langchain\core/embeddings · high confidence
Expose rate limiters from langchain\_core
The \langchain\_v1\ package now exposes \BaseRateLimiter\ and \InMemoryRateLimiter\ from \langchain\_core\ at \langchain.rate\_limiters\. Users can import these classes directly from this new location to limit the rate of requests to APIs when using \BaseChatModel\.
_libs/langchain\_v1/langchain/rate\limiters · high confidence
HuggingFace integration restructured with new chat and embedding classes
The langchain-huggingface package has been restructured to provide updated integration classes. The new \ChatHuggingFace\ class implements full chat model support, including message conversion, tool call handling, and streaming capabilities. The \HuggingFaceEmbeddings\ class now supports separate keyword arguments for query and document encoding, and explicitly warns users that the IPEX backend is no longer supported. Additionally, \HuggingFaceEndpointEmbeddings\ has been updated to support inference providers and includes stricter validation to reject URLs in the \repo\_id\ field.
langchain-huggingface · high confidence
Introduce \`langchain\_openai\` chat model package with Responses API support and streaming reliability fixes
The \langchain\_openai\ package is restructured into a dedicated \chat\_models\ module, introducing \ChatOpenAI\ and \AzureChatOpenAI\ classes that now support the OpenAI Responses API (including structured output, built-in tools, and reasoning summaries) alongside the legacy Chat Completions API. A new \\_client\_utils\ module enhances streaming reliability by adding per-chunk timeout wrappers and platform-aware TCP keepalive socket tuning, while a \\_compat\ module manages backward-compatible conversion between v0.3 and new Responses API message formats. Additionally, an experimental \\_ChatOpenAICodex\ class is added to support ChatGPT OAuth-backed Codex access, and a \custom\_tool\ decorator is provided for defining OpenAI custom tools with freeform string inputs.
_libs/partners/openai/langchain\_openai/chat\models · high confidence
Introduce base TextSplitter with input validation
The \langchain-text-splitters\ library now exposes a \TextSplitter\ base class that validates \chunk\_size\ and \chunk\_overlap\ parameters at initialization, raising \ValueError\ for invalid configurations (e.g., non-positive chunk size or overlap exceeding chunk size). This ensures that downstream splitting operations fail fast with clear errors rather than potentially causing infinite loops or unexpected behavior.
langchain-text-splitters · high confidence
Introduce langchain-groq v1.1.3 with GroqContextOverflowError and v1 content compatibility
The langchain-groq integration is updated to version 1.1.3, introducing a specific GroqContextOverflowError that maps Groq's context-length errors to LangChain's standard exception for better error handling. The package also adds a compatibility layer (\_convert\_from\_v1\_to\_groq) to handle conversion of LangChain v1 content blocks (such as reasoning and server tool calls) into the format expected by the Groq API, ensuring smoother interoperability during migration or mixed-version usage.
_libs/partners/groq/langchain\groq · high confidence
Introduce lazy-loaded callback module exports and context-manager-based file handling
The \langchain\core.callbacks\ package now uses dynamic, lazy imports via \\\getattr\\_\ to reduce startup overhead, exposing all standard handlers and managers (including \UsageMetadataCallbackHandler\, \StdOutCallbackHandler\, \FileCallbackHandler\, and custom event dispatchers) without forcing immediate module loads. Additionally, \FileCallbackHandler\ now requires context-manager usage (\with FileCallbackHandler(...) as handler:\) for proper file lifecycle management, issuing a deprecation warning for direct instantiation to prevent resource leaks.
_libs/core/langchain\core/callbacks · high confidence
Introduce lazy-loaded output classes with chunk concatenation support
The \langchain\core.outputs\ module now uses lazy loading via a custom \\\getattr\\_\ to improve import performance, exposing \ChatGeneration\, \ChatGenerationChunk\, \ChatResult\, \Generation\, \GenerationChunk\, \LLMResult\, and \RunInfo\. \ChatGeneration\ automatically derives its \text\ attribute from the underlying message content, handling legacy content blocks. \ChatGenerationChunk\ and \GenerationChunk\ now support concatenation via the \+\ operator and a \merge\_chat\_generation\_chunks\ utility, enabling efficient streaming aggregation.
_libs/core/langchain\core/outputs · high confidence
Introduce v1 tools namespace with backward-compatible re-exports
The \langchain.tools\ module is now available in the v1 package, providing a dedicated namespace for tool-related components. This location acts as a compatibility layer that re-exports core tool classes (such as \BaseTool\, \tool\, and \ToolException\) from \langchain\_core\ and runtime/state injection utilities (\ToolRuntime\, \InjectedState\, \InjectedStore\) from \langgraph.prebuilt\. This allows existing code to import from \langchain.tools\ without immediate refactoring, while establishing the new v1 structure for tool management.
_libs/langchain\v1/langchain/tools · high confidence
LangChain Classic package introduces deprecation warnings for legacy imports
The \langchain\_classic\ package now surfaces deprecation warnings when users import legacy classes and functions (such as \MRKLChain\, \ReActChain\, \LLMChain\, and various agent toolkits) from the root module or submodules. Instead of silently working, these imports now trigger warnings directing users to migrate to the new import paths in \langchain\_classic\ (e.g., \langchain\_classic.agents.MRKLChain\) or \langchain\_community\. Some older agents (like \create\_csv\_agent\) have been moved to \langchain\_experimental\ and will raise an \ImportError\ with instructions to install that package. This change helps users identify and update deprecated code paths before they are removed in a future major version.
_libs/langchain/langchain\classic · high confidence
LangChain Classic package restructured with deprecated legacy components
The \langchain-classic\ package has been reorganized to include legacy agent, chain, memory, and output parser implementations that are now marked as deprecated. Key components such as \BaseSingleActionAgent\, \VectorStoreToolkit\, \ConversationalRetrievalChain\, and various memory stores (e.g., \ConversationSummaryMemory\, \InMemoryEntityStore\) are now explicitly deprecated with removal scheduled for version 2.0.0, directing users toward newer APIs like \create\_agent\ and the \Store\ API. This change consolidates older patterns into a single package location while signaling their end-of-life status.
langchain-classic · high confidence
Lint script to restrict LangChain imports
A new linting script (lint\_imports.sh) has been added to the model-profiles library to enforce import policies. It prevents code from importing directly from langchain or langchain\_experimental, with specific allowances for langchain.agents and langchain.tools (v1 middleware). This change ensures that dependencies are managed consistently and prevents accidental usage of experimental or base LangChain modules in this library.
libs/model-profiles/scripts · high confidence
Messages module restructured with lazy imports and new content block types
The \langchain\core.messages\ package has been reorganized to use lazy imports via a custom \\\getattr\\\ in \\\init\\_.py\, improving startup performance by deferring the loading of heavy message classes until they are accessed. This change introduces a new standardized \content.py\ module defining multimodal content blocks (such as \TextContentBlock\, \ImageContentBlock\, and \ReasoningContentBlock\) and updates message classes like \AIMessage\ and \ToolMessage\ to support these typed content blocks alongside legacy string content. Additionally, \BaseMessage\ now includes an \id\ field for unique identification and a \response\_metadata\ field for provider-specific data, while \ToolMessage\ gains an \artifact\ field to store full tool outputs separate from the content sent to the model.
_libs/core/langchain\core/messages · high confidence
New import and version consistency checks for core library
Added scripts to enforce import and version consistency within the core library. The \check\_imports.py\ script validates that Python modules can be successfully imported, while \check\_version.py\ ensures the version defined in \pyproject.toml\ matches the \VERSION\ variable in \langchain\_core/version.py\. Additionally, \lint\_imports.sh\ prevents accidental imports from \langchain\ or \langchain\_experimental\ packages, allowing only specific legacy paths like \langchain.agents\ and \langchain.tools\.
libs/core/scripts · high confidence
New import validation and linting scripts for LangChain
Added \check\_imports.py\ and \lint\_imports.sh\ to the LangChain scripts directory to enforce import hygiene and verify module loadability. The Python script allows developers to quickly verify that a list of Python files can be loaded by the interpreter without errors, printing tracebacks for any failures. The shell script enforces specific import rules within the \langchain\_classic\ directory, ensuring that internal modules do not import from disallowed sub-packages and preventing imports from \langchain\_experimental\ or the global namespace of \langchain\_community\.
libs/langchain/scripts · high confidence
Perplexity model profile data distribution
The Perplexity integration now includes a dedicated data package containing auto-generated model profiles for Sonar, Sonar Deep Research, Sonar Pro, and Sonar Reasoning Pro. These profiles define specific capabilities such as input/output modalities (text, image, audio, video), token limits, and features like tool calling and reasoning outputs, allowing the integration to accurately reflect the current specifications of Perplexity's models.
_libs/partners/perplexity/langchain\perplexity/data · high confidence
Repository infrastructure overhaul and v0.2 documentation refresh
The repository has been restructured for its v0.2 release, replacing the legacy \setup.py\ and root \Makefile\ with a \uv\-based monorepo architecture where each package in \libs/\ manages its own dependencies and build tasks. Development tooling is standardized via a new \.pre-commit-config.yaml\ (enforcing \ruff\ and \mypy\), \.editorconfig\, and \.markdownlint.json\. The \README.md\ has been completely rewritten to reflect the new 'agent engineering platform' positioning, featuring updated installation instructions (\uv add langchain\), new code examples using \init\_chat\_model\, and links to the new documentation site and ecosystem products like LangGraph and Deep Agents.
(repo-wide) · high confidence
Updated Fireworks model profiles with new capabilities and reasoning effort support
The Fireworks partner package now includes refreshed model profile data for models such as DeepSeek V4 Flash, DeepSeek V4 Pro, Ember-1, and GLM-5p1/5p2. This update adds support for the \reasoning\_effort\ parameter (with levels like low, medium, high, etc.) on specific models like DeepSeek V4 Pro and GLM-5p1/5p2, and explicitly declares that native PDF inputs are unsupported for these models.
_libs/partners/fireworks/langchain\fireworks/data · high confidence
Updated Groq model profile data
The model profile data for the Groq integration has been refreshed to include new models such as Canopy Labs Orpheus variants and the Groq Compound models, along with updated metadata for existing models like Llama 3.1 and Llama 3.3. This ensures the library accurately reflects the latest capabilities, token limits, and input/output modalities available through the Groq API.
_libs/partners/groq/langchain\groq/data · high confidence
Updated Mistral model profile data with new fields and refreshed entries
The model profile data for the Mistral AI partner package has been refreshed to include new model variants (such as Devstral and Magistral series) and updated metadata. The data structure now explicitly includes \text\_inputs\ and \text\_outputs\ boolean fields for each model, providing clearer information about supported input and output modalities. This change ensures that applications relying on this data have accurate, up-to-date information about model capabilities and constraints. Also in this area: 9 commits (0 fixes) modifying libs/partners; Update partner library versions and refresh model profiles; Support for Claude Sonnet 5.5 in LangChain Anthropic.
_libs/partners/mistralai/langchain\mistralai/data · medium confidence · unverified
Updated OpenAI model profiles with GPT-5/6 support and reasoning effort levels
The OpenAI partner package now includes refreshed model profile data for the \langchain\_openai\ library, adding support for newer models such as GPT-5, GPT-5.1, GPT-5.2, GPT-5.3, GPT-5.4, GPT-5.5, GPT-5.6, and GPT-6 variants (including Astra, Sol, Luna, and Terra). These profiles define capabilities like structured output, tool calling, and input types, and explicitly configure \reasoning\_effort\_levels\ (e.g., none, low, medium, high, xhigh, max) and \max\_input\_tokens\ (272,000) for the GPT-5/6 series. The data is managed via \profile\_augmentations.toml\ to allow overrides for specific models, ensuring accurate parameter handling for these latest releases.
_libs/partners/openai/langchain\openai/data · high confidence
Updated OpenRouter model profile data and streaming configuration
The OpenRouter partner package's internal model profile data has been refreshed to reflect the latest model capabilities and metadata from the models.dev source. Additionally, the configuration for the OpenRouter provider has been updated to explicitly enable tool call streaming by default via the profile augmentations file.
_libs/partners/openrouter/langchain\openrouter/data · high confidence
Updated model profiles for new Claude versions and reasoning capabilities
The Anthropic partner package now includes updated model profile data for Claude Fable 5, Fable 5.1, Opus 5, Opus 5.5, Sonnet 5, and Sonnet 4.6/4.7/4.8. These profiles enable structured output and fine-grained reasoning effort levels (low, medium, high, xhigh, max) for the specified models, ensuring the library correctly exposes these capabilities to users.
_libs/partners/anthropic/langchain\anthropic/data · high confidence
Updated model profiles for xAI with new Grok versions and reasoning effort support
The xAI partner package now includes refreshed model profile data for several new Grok models (4.20, 4.3, 4.5, 4.6, 4.7, and Build 0.1), detailing their input/output capabilities such as text, image, and PDF support. Notably, the Grok 4.3 profile has been updated to include \reasoning\_effort\_levels\ (none, low, medium, high) with a default of 'low', aligning with the core framework's new standard parameter for controlling reasoning depth.
_libs/partners/xai/langchain\xai/data · high confidence
langchain-fireworks v1.6.3 release with document reranking and SDK migration
The langchain-fireworks package has been updated to version 1.6.3, introducing a new FireworksRerank component for document reranking alongside the existing ChatFireworks, Fireworks, and FireworksEmbeddings integrations. This release migrates the underlying client to the fireworks-ai 1.x SDK and includes behavioral fixes such as dropping reasoning history blocks from responses, translating multimodal content blocks for chat completions, and ensuring proper handling of tool choices with multiple tools.
_libs/partners/fireworks/langchain\fireworks · high confidence
langchain-ollama v1.1.0 release with v1 content block compatibility
The \langchain-ollama\ package has been updated to version 1.1.0, introducing a new compatibility layer (\\_compat.py\) that converts LangChain v1 content blocks to the Ollama SDK format, ensuring support for text, image, and non-standard content types. This release also includes a dedicated model validation utility (\\_utils.py\) that verifies model existence and handles connection errors, and adds support for parsing URLs with embedded basic authentication credentials in the \base\_url\ parameter for both sync and async clients.
_libs/partners/ollama/langchain\ollama · high confidence
Test coverage
1 commit adding/updating tests in libs/core/tests/unit\tests/decisions; Add unit tests for MistralAI partner package; Added OpenAI test infrastructure with OAuth secret scrubbing; Added benchmark tests for agent instantiation; Added benchmark tests for import times, async callbacks, and tool schema conversion; Added empty \\init\\_.py files to test directories; Added empty test structure for dependencies; Added fake callback handler for testing; Added fake callback handlers for unit testing; Added import tests for utilities module; Added import validation tests for docstore and smith modules; Added import validation tests for langchain\_classic schema modules; Added import validation tests for the prompts module; Added integration test package for agents; Added integration test scaffolding and fixtures; Added integration test suite for LangChain core components; Added integration tests for Azure OpenAI LLM wrapper; Added integration tests for ChatAnthropic and AnthropicLLM; Added integration tests for ChatGroq; Added integration tests for Elasticsearch chat message history; Added integration tests for Exa search and retrieval tools; Added integration tests for FastEmbedSparse with Qdrant; Added integration tests for Fireworks chat, LLM, and embedding models; Added integration tests for HuggingFace chat, embeddings, and LLMs; Added integration tests for HuggingFace partners; Added integration tests for MCPAdapter protocol era handling; Added integration tests for MistralAI chat and embedding models; Added integration tests for Ollama embeddings and LLMs; Added integration tests for OpenAI and Azure OpenAI LLMs; Added integration tests for OpenAI functions and moderation chains; Added integration tests for Perplexity chat, embeddings, and search; Added integration tests for QdrantVectorStore; Added integration tests for document compressor rerankers; Added integration tests for embedding distance evaluation chains; Added integration tests for embeddings initialization; Added integration tests for the DeepSeek chat model; Added integration tests for the Qdrant vector store; Added integration tests for the generic configurable chat model initialization; Added integration tests for the langchain-openrouter provider; Added integration tests for the v1 chat model initialization; Added integration tests for xAI chat model features; Added regression tests for the vector stores public API; Added sample data files for integration tests; Added serialization/deserialization snapshot tests for ChatAnthropic; Added serialization/deserialization test for ChatFireworks; Added serialization/deserialization test for ChatMistralAI; Added serialization/deserialization tests for ChatGroq; Added serialization/deserialization tests for OpenAI chat models; Added snapshot tests for ChatXAI serialization; Added snapshot tests for agent graph diagrams; Added snapshot tests for chat and prompt input schemas; Added snapshot tests for runnable serialization and graph visualization; Added snapshot tests for serialization output; Added test data module for PDF integration tests; Added test fixtures for non-UTF-8 encoding and OpenAPI specifications; Added test fixtures for prompt serialization and security validation; Added test infrastructure for Groq partner integration; Added test infrastructure for agent middleware; Added test infrastructure for cache integration tests; Added test package structure for HuggingFace integration; Added test runner documentation for Ollama integration tests; Added test utilities for cache integration tests; Added tests for document parser public API stability; Added tests for the dynamic import and deprecation handling API; Added unit and integration tests for model profiles CLI and summary generation; Added unit test suite for agents in langchain\_v1; Added unit test suite for langchain v1 scaffolding; Added unit tests for ChatGeneration.text and outputs module imports; Added unit tests for Document class initialization, string representation, and public API exports; Added unit tests for ExactMatch and RegexMatch string evaluators; Added unit tests for HubRunnable and OpenAIFunctionsRouter; Added unit tests for HuggingFace integration components; Added unit tests for InMemoryCache; Added unit tests for InMemoryStore; Added unit tests for InMemoryVectorStore and VectorStore utilities; Added unit tests for JSON parsing evaluators; Added unit tests for LLM base functionality, caching, and tracing; Added unit tests for LLM module imports and fake model utilities; Added unit tests for LangSmith evaluation runner utilities and string run evaluators; Added unit tests for OpenAI LLM integration; Added unit tests for SelfQueryRetriever base functionality; Added unit tests for agent middleware core functionality; Added unit tests for agent middleware type safety and backwards compatibility; Added unit tests for agent output parsers; Added unit tests for agent scratchpad formatting utilities; Added unit tests for agent trajectory evaluation chain; Added unit tests for chat history deprecation and async interfaces; Added unit tests for chat model caching, rate limiting, and tracing; Added unit tests for chat model initialization and module exports; Added unit tests for core callback system behaviors; Added unit tests for core indexing components; Added unit tests for core message utilities and serialization; Added unit tests for core tracer functionality; Added unit tests for core utility functions; Added unit tests for document compressor components; Added unit tests for document loader base classes and LangSmith loader; Added unit tests for document loader imports and base schema; Added unit tests for embeddings module initialization and model parsing; Added unit tests for fake LLM and callback utilities; Added unit tests for langchain-openai; Added unit tests for langchain\_classic chains; Added unit tests for memory module imports and CombinedMemory functionality; Added unit tests for message block translators; Added unit tests for pairwise evaluation chains; Added unit tests for prompt templates and loading; Added unit tests for runnable module public API exports; Added unit tests for runnables and rate limiters; Added unit tests for serialization and deserialization in the load module; Added unit tests for string distance evaluation chains; Added unit tests for the DeepSeek chat model integration; Added unit tests for the Groq integration; Added unit tests for the LangChain Anthropic integration; Added unit tests for the LoggingCallbackHandler tracer; Added unit tests for the Ollama partner integration; Added unit tests for the Qdrant partner package; Added unit tests for the agents module; Added unit tests for the core API deprecation and beta warning utilities; Added unit tests for the criteria evaluation chain; Added unit tests for the indexing API; Added unit tests for the load module's serialization and security behaviors; Added unit tests for the new MCP adapter integration; Added unit tests for the query constructor parser; Added unit tests for the v1 chat model initialization and provider inference; Added unit tests for the xAI chat integration; Added unit tests for tools module imports and rendering; Added unit tests for tools module public API; Added unit tests for v3 streaming, projections, and model profiles; Initial unit test suite for langchain-openrouter; New integration test suite for OpenAI chat models; New unit test suite for LangChain Core; New unit test suite for langchain-classic; Removed integration and unit tests for chains, LLMs, and prompts; Unit test coverage for Perplexity integration; Unit tests added for OpenAI agent middleware components; Unit tests for OpenAI chat models; Updated test infrastructure with VCR cassette improvements.
Dependencies
LangChain v1.4.2 release
The LangChain library has been updated to version 1.4.2. This release includes the standard package initialization and type-stub marker files for the v1 branch.
_libs/langchain\v1/langchain · high confidence
Release of langchain-chroma version 1.1.0
The langchain-chroma partner package has been updated to version 1.1.0. This release includes the core vector store implementation, versioning infrastructure, and type stubs for the Chroma integration, ensuring compatibility with the latest ChromaDB client features and LangChain core standards.
_libs/partners/chroma/langchain\chroma · high confidence
Written by cca.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.
How this codebase got here
Score
- CAI 64 → 62 (-1.8)
- Rubric changed (rubric-2026.10.5 → rubric-2026.11.4) — scores are not directly comparable.
Lenses
- Code Health 75 → 71 (-4.2)
- Architecture 96 → 97 (+0.7)
- Maturity 75 → 75 (+0.2)
- Readiness 54 → 53 (-1.3)
- Security 63 → 61 (-2.6)
- Performance 94 → 94 (+0.0)
Resolved (61)
- Critical CVE: [GHSA redacted] (libs/partners/nomic/uv.lock)
- Duplicated block (10 lines × 2) (libs/core/langchain_core/messages/utils.py)
- Duplicated block (10 lines × 2) (libs/core/langchain_core/messages/utils.py)
- Duplicated block (10 lines × 2) (libs/standard-tests/langchain_tests/integration_tests/sandboxes.py)
- Duplicated block (11 lines × 2) (libs/langchain_v1/langchain/agents/factory.py)
- Duplicated block (12 lines × 2) (libs/langchain/langchain_classic/chains/loading.py)
- Duplicated block (12 lines × 2) (libs/langchain/langchain_classic/chains/loading.py)
- Duplicated block (13 lines × 2) (libs/langchain/langchain_classic/retrievers/time_weighted_retriever.py)
- Duplicated block (14 lines × 2) (libs/core/langchain_core/messages/utils.py)
- Duplicated block (14 lines × 2) (libs/core/langchain_core/prompts/base.py)
- Duplicated block (14 lines × 2) (libs/langchain/langchain_classic/chains/loading.py)
- Duplicated block (15–16 lines × 2) (libs/partners/anthropic/langchain_anthropic/chat_models.py)
- Duplicated block (17 lines × 2) (libs/langchain_v1/langchain/agents/factory.py)
- Duplicated block (17–18 lines × 2) (libs/langchain/langchain_classic/smith/evaluation/runner_utils.py)
- Duplicated block (18 lines × 2) (libs/partners/fireworks/langchain_fireworks/_compat.py)
- Duplicated block (18 lines × 2) (libs/partners/openai/langchain_openai/decisions/base.py)
- Duplicated block (19–20 lines × 2) (libs/core/langchain_core/runnables/base.py)
- Duplicated block (22 lines × 4) (libs/langchain/langchain_classic/chains/loading.py)
- Duplicated block (24–25 lines × 2) (libs/partners/fireworks/langchain_fireworks/chat_models.py)
- Duplicated block (59–71 lines × 2) (libs/core/langchain_core/language_models/_compat_bridge.py)
- …and 41 more
New (351)
- ChatFireworks._astream (cyclomatic 22) (libs/partners/fireworks/langchain_fireworks/chat_models.py)
- ChatFireworks._stream (cyclomatic 22) (libs/partners/fireworks/langchain_fireworks/chat_models.py)
- Duplicated block (10 lines × 2) (libs/partners/fireworks/langchain_fireworks/_compat.py)
- Duplicated block (12 lines × 2) (libs/partners/openai/langchain_openai/decisions/base.py)
- Duplicated block (13 lines × 2) (libs/langchain/langchain_classic/retrievers/time_weighted_retriever.py)
- Duplicated block (14–15 lines × 2) (libs/core/langchain_core/runnables/base.py)
- Duplicated block (19 lines × 2) (libs/partners/openai/langchain_openai/decisions/base.py)
- Duplicated block (22 lines × 4) (libs/langchain/langchain_classic/chains/loading.py)
- Duplicated block (37–38 lines × 2) (libs/partners/fireworks/langchain_fireworks/chat_models.py)
- Duplicated block (6 lines × 2) (libs/partners/openai/langchain_openai/decisions/base.py)
- Duplicated block (62–74 lines × 2) (libs/core/langchain_core/language_models/_compat_bridge.py)
- Duplicated block (7 lines × 2) (libs/partners/openai/langchain_openai/decisions/_classifier_input.py)
- Duplicated block (9 lines × 2) (libs/partners/fireworks/langchain_fireworks/_compat.py)
- Edited copies of one member (3 members, 10+ corresponding lines) (libs/core/langchain_core/callbacks/base.py)
- Edited copies of one member (3 members, 10+ corresponding lines) (libs/langchain/langchain_classic/memory/summary_buffer.py)
- Edited copies of one member (3 members, 10+ corresponding lines) (libs/standard-tests/langchain_tests/integration_tests/sandboxes.py)
- Edited copies of one member (3 members, 11+ corresponding lines) (libs/langchain/langchain_classic/chains/conversational_retrieval/base.py)
- Edited copies of one member (3 members, 12+ corresponding lines) (libs/core/langchain_core/output_parsers/json.py)
- Edited copies of one member (3 members, 14+ corresponding lines) (libs/standard-tests/langchain_tests/unit_tests/chat_models.py)
- Edited copies of one member (3 members, 17+ corresponding lines) (libs/core/langchain_core/tracers/core.py)
- …and 331 more
Changes since last survey
- 134 commits — 109 feature/other, 25 fixes
By area
- libs/partners — 64 commits
- libs/core — 26 commits
- libs/langchain_v1 — 16 commits
- openwiki/.claims — 8 commits
- libs/langchain — 6 commits
- .github/workflows — 4 commits
- libs/model-profiles — 2 commits
- libs/standard-tests — 2 commits
- openwiki/.last-update.json — 2 commits
- .github/ISSUE_TEMPLATE — 1 commit
- .github/actions — 1 commit
- .github/scripts — 1 commit
- libs/text-splitters — 1 commit
Notable commits
- fix: chore(infra): ask how bug reports were discovered (#41563)
- fix: ci(infra): run matrix regression tests before generating jobs (#41487)
- fix: fix(anthropic): handle null cache-creation token counts (#41553)
- fix: fix(anthropic): preserve nested caller on server calls and results (#41678)
- fix: fix(anthropic): raise ModelRefusalError for refusals when tool calls are not forced (#41715)
- fix: fix(anthropic): report streamed content-block tokens to callbacks (#41643)
- fix: fix(anthropic): strip index from compaction blocks (#41637)
- fix: fix(anthropic): trace resolved reasoning effort (#41536)
- fix: fix(core): avoid mutating message content in Anthropic translator (#40213)
- fix: fix(core): cap nesting depth in load() (#41742)
- fix: fix(core): end tool run on cancellation (#41660)
- fix: fix(core): escape node metadata in Mermaid labels (#41512)
- fix: fix(core): load RemoveMessage serialized by LangChain.js (#41642)
- fix: fix(core): preserve gateway tracing metadata in v3 streams (#41504)
- fix: fix(core): stop merge_content from changing the first message's content (#41502)
- fix: fix(fireworks): default max_tokens from model profiles (#41772)
- fix: fix(fireworks): promote reranking out of beta (#41551)
- fix: fix(fireworks): report streamed token usage once (#41693)
- fix: fix(fireworks): report the served model in response metadata (#41686)
- fix: fix(infra): pin optional deps in min-version release checks (#41661)
- …and 114 more
Architecture
- Containers 0 added · 0 removed · contexts 0 added · 1 removed · edges 0 added · 0 removed
Removed bounded contexts (1)
- langchain-typesafe
Written by cca.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.
Survey your own repository
langchain-ai/langchain was measured the same way every project in this corpus was: the same rubric, at a pinned commit, with the result published in full. Point a surveyor at a repository you know and see whether you agree with it.
About this page
- The score is its most recent published measurement, taken on 14 November 2026 at a pinned commit. It is not a live figure and does not change until the project is measured again.
- Measured at commit ea17e48f0a4336c920394fd029de99f1568b4c38 — the exact code this score is about.
- Scored under rubric-2026.11.4 — the same rubric and the same method as every other entry in this index.
- Measured by Canine Code Analyzer (cca.canine.dev) using cca measure-2026.11.65+preprod-36d4cd83012f.