fix(deps): update dependency langgraph to >=0.4.3,<0.5

[renovate]

This PR contains the following updates:

Package	Change	Age	Adoption	Passing	Confidence
langgraph	>=0.2.20,<0.3 -> >=0.4.3,<0.5

---

Release Notes

langchain-ai/langgraph (langgraph)

v0.4.3

Compare Source

Changes since 0.4.2

• release: 0.4.3 (#​4592)
• langgraph: use tuples for streamed message events in RemoteGraph (#​4589)
• Fix remote streaming of subgraphs (#​4590)
• Add a limit to Pregel.draw (#​4575)

v0.4.2

Compare Source

Changes since 0.4.1

• 0.4.2 (#​4570)
• update
• langgraph: decouple name from assistant ID in RemoteGraph
• prebuilt: switch to executing parallel tool calls via Send by default (#​4438)
• fix for langgraph
• docstring fixes for libs/langgraph
• docs: update add_messages API ref (#​4495)
• update other tests

v0.4.1

Compare Source

langgraph 0.4.1

Summary of Changes

• Fixed an issue handling END in StateGraph edges to properly terminate graph execution #​4458
• Migrated codebase to exclusively use Pydantic V2, removing support for Pydantic V1 #​4448
• Added ability to merge UI message props using a new merge parameter #​4473
• Changed TAG_NOSTREAM from "langsmith:nostream" to "nostream", maintaining backwards compatibility #​4473
• Improved docstrings and documentation throughout the codebase #​4463
• Fixed UI message metadata handling in push_ui_message #​4467

Detailed Changes

langgraph.graph.state.StateGraph

• Fixed handling of the END constant in get_writes and _control_static functions, ensuring proper graph termination when returning to END #​4458

langgraph.graph.ui

• Added a new merge parameter to push_ui_message function, allowing incremental updates to UI messages #​4473
• Enhanced ui_message_reducer to support merging props from existing messages when the merge flag is set #​4473
• Fixed metadata handling in push_ui_message by removing old metadata merging which could cause unexpected behavior #​4467

langgraph.constants

• Changed TAG_NOSTREAM from "langsmith:nostream" to "nostream" #​4473
• Added TAG_NOSTREAM_ALT with the old value ("langsmith:nostream") for backward compatibility #​4473

langgraph.graph.schema_utils

• Removed support for Pydantic V1 models in SchemaCoercionMapper #​4448
• Simplified type adapters to work exclusively with Pydantic V2 #​4448

langgraph.utils.pydantic

• Completely rewritten to use only Pydantic V2 APIs #​4448
• Added proper caching for model creation with lru_cache for better performance #​4448
• Fixed handling of reserved names and field remapping to avoid collisions with Pydantic internals #​4448

langgraph.channels.base.BaseChannel

• Added docstring to clarify the purpose of this base class #​4463

v0.4.0

Compare Source

langgraph 0.4.0

Summary of Changes

• Added improved support for interrupt handling in streaming modes, with interrupts now properly propagated in "values" stream mode #​4374
• Enhanced interrupt resumption with namespace-specific resume values, allowing targeted resumption of specific interrupts #​4406
• Fixed branch handling to properly process END nodes in graph visualization and execution #​4409
• Fixed issue where empty Commands with resume maps would raise an error #​4444
• Updated Python compatibility to allow future Python versions while maintaining 3.9+ support #​4416

Detailed Changes

langgraph.types.Interrupt

• Added interrupt_id property that generates a unique ID for the interrupt based on its namespace #​4406
• Updated ID generation to use | as a separator between namespace elements for better uniqueness #​4406

langgraph.types.StreamMode

• Updated docstring to clarify that "values" mode emits all values including interrupts after each step #​4374

langgraph.types.StateSnapshot

• Added interrupts field to track interrupts that occurred in a step and are pending resolution #​4406
• Improved documentation for all fields in the class #​4406

langgraph.types.Command

• Enhanced resume parameter to support mapping interrupt IDs to resume values #​4406
• Improved documentation for the resume parameter #​4406

langgraph.pregel.Pregel

• Improved invoke and ainvoke methods to properly collect and handle interrupts in streamed output #​4374
• Enhanced interrupt emission to work in both "values" and "updates" stream modes #​4374
• Modified state snapshot preparation to collect interrupts from tasks #​4406

langgraph.graph.branch.Writer

• Updated signature to accept a boolean parameter indicating whether the operation is for static writes #​4409
• Fixed branch handling to properly process END nodes #​4409

langgraph.pregel.loop.PregelLoop

• Fixed Command handling to support empty Commands with resume maps #​4444
• Added support for namespace-based resumption through CONFIG_KEY_RESUME_MAP #​4406

langgraph.pregel.draw

• Improved graph visualization to correctly handle END nodes #​4409
• Added add_edge utility function to prevent duplicate edges in graph visualization #​4409

v0.3.34

langgraph 0.3.34

Summary of Changes

• Fixed handling of interrupts in nested graph execution by properly marking tasks with execution context information #​4389
• Improved sanitization of configuration values in remote graphs #​4389
• Fixed issues with cached properties when copying PregelNode objects #​4389

Detailed Changes

langgraph.pregel.algo.prepare_single_task

• Enhanced task path handling by appending a boolean flag (True/False) to indicate whether a call is being made #​4389
• When True, interrupts should not be returned from the task (responsibility lies with the parent)
• When False, interrupts should be returned from the task
• Updated all related code to use the full task path instead of truncated version

langgraph.pregel.loop.PregelLoop

• Added logic in _output_writes to check task path context before emitting interrupts #​4389
• For tasks with path[0] == PUSH and path[-1] is True (indicating a call context), interrupts are not emitted as they'll be handled by the parent

langgraph.pregel.read.PregelNode

• Fixed copy method to properly drop cached properties when copying nodes #​4389
• Specifically clears flat_writers, node, and input_cache_key cached properties to ensure proper initialization of the copied node

langgraph.pregel.remote.sanitize_config_value

• Added new utility function to recursively sanitize configuration values #​4389
• Ensures configuration values contain only primitive types (string, int, float, bool) or collections thereof
• Properly handles nested dictionaries, lists, and tuples

langgraph.pregel.remote.RemoteGraph

• Improved _sanitize_config method to use the new sanitize_config_value function #​4389
• Now properly sanitizes nested metadata and configurable values
• Maintains only valid configuration values that can be safely serialized

v0.3.32

Compare Source

langgraph 0.3.32

Summary of Changes

• Fixed SchemaCoercionMapper to properly handle Pydantic models with validators (#​4363)
• Improved branch handling with better entry processing and passthrough logic (#​4354)
• Refactored graph visualization with dedicated draw_graph functionality (#​4354)
• Added static analysis support for channel writes to improve conditional edges (#​4354)
• Improved message processing in StreamMessagesHandler for better efficiency (#​4379)
• Updated type annotations throughout the codebase for better compatibility with Python typing (#​4368)

Detailed Changes

langgraph.graph.schema_utils.SchemaCoercionMapper

• Fixed an issue with Pydantic models that have validators by detecting validator presence and using the appropriate coercion strategy (#​4363)
• For Pydantic v1 models with validators, now directly calls the model constructor
• For Pydantic v2 models with validators, now uses model_validate instead of model_construct

langgraph.graph.branch.Branch

• Improved write handling in branches with better passthrough logic (#​4354)
• Changed the writer interface to simplify integration with ChannelWrite
• Added functionality to detect when a PASSTHROUGH value is needed to maintain the input

langgraph.pregel.write.ChannelWrite

• Added get_static_writes method to support static analysis of what a writer might write (#​4354)
• Extended register_writer to accept static declarations for writers
• Added a static field to ChannelWriteTupleEntry to declare writes for static analysis
• Refactored write assembly into a separate _assemble_writes function for better code organization

langgraph.pregel.draw

• Added new dedicated module for graph visualization (#​4354)
• Implemented draw_graph function that simulates execution to discover edges
• Graph visualization now correctly handles subgraphs and conditional edges

langgraph.pregel.messages.StreamMessagesHandler

• Refactored message handling to use a new helper method _find_and_emit_messages (#​4379)
• Improved Command handling to properly process messages from Command updates

langgraph.channels.dynamic_barrier_value.DynamicBarrierValue

• Updated type annotations to use collections.abc.Set instead of set (#​4354)
• Improved type consistency throughout the class

v0.3.31

Compare Source

langgraph 0.3.31

Summary of Changes

• Improved thread ID handling in checkpointing and state management for more reliable concurrent execution (#​4281)

Detailed Changes

langgraph.constants.CONFIG_KEY_THREAD_ID

• Added new constant to track thread IDs for current invocations (#​4281)

langgraph.pregel.Pregel

• Enhanced thread ID handling to ensure consistent string representation in configurations (#​4281)
• Improved state retrieval methods (get_state, aget_state) to properly handle thread IDs
• Updated state history methods to consistently use string thread IDs in checkpoint configurations
• Fixed superstep execution to maintain consistent thread ID format across multiple steps

langgraph.pregel.loop.PregelLoop

• Added thread ID validation in checkpoint configurations to ensure consistent string format (#​4281)
• Fixed checkpoint configuration handling to properly maintain thread ID consistency between runs

v0.3.30

Compare Source

langgraph 0.3.30

Summary of Changes

• Improved streaming support for Command objects by properly handling unwrapping in responses #​4250
• Refactored Pydantic model update handling to improve code maintainability and reduce duplication #​4255

Detailed Changes

langgraph.pregel.messages.StreamMessagesHandler

• Added support for properly handling Command objects in streaming responses by extracting the .update value #​4250
• This allows Command objects to be used more seamlessly in streaming contexts, both as individual responses and when contained in sequences

langgraph.utils.fields.get_update_as_tuples

• Added new utility function to extract update fields from Pydantic models as tuples #​4255
• Consistently handles both Pydantic v1 and v2 models
• Preserves behavior of only updating values that differ from defaults or are explicitly set

langgraph.graph.state.StateGraph

• Refactored internal _get_updates function to use the new get_update_as_tuples utility, reducing code duplication #​4255

langgraph.types.Command

• Updated internal _update_as_tuples method to use the new centralized utility function #​4255

v0.3.29

Compare Source

langgraph 0.3.29

Summary of Changes

• Performance optimizations for StateGraph and Pregel execution (#​4242)
• Streamlined branch handling with simpler command processing (#​4247, #​4248)
• Improved trace and context handling with better performance (#​4256)

Detailed Changes

langgraph.graph.state.CompiledStateGraph

• Added schema caching via a new schema_to_mapper dictionary to avoid recreating schema mappers repeatedly (#​4242)
• Simplified branch handling by removing SELF branch mechanism (#​4247)
• Refactored command processing to directly output tuples of channel/value pairs instead of sending commands through branches (#​4248)

langgraph.pregel.read.PregelNode

• Added an input_cache_key property for efficient input caching (#​4242)
• Disabled tracing by default for better performance (#​4256)

langgraph.pregel.algo

• Added input caching to avoid recomputing the same inputs for nodes (#​4242)
• Improved channel reading efficiency by checking availability before reading (#​4242)
• Changed _proc_input to return a value directly instead of being an iterator (#​4242)

langgraph.pregel.write.ChannelWrite

• Removed tagging mechanism and simplified tracing (#​4256)
• Disabled tracing by default for improved performance (#​4256)

langgraph.utils.runnable.RunnableCallable

• Improved context handling for better performance and tracing (#​4256)
• Added explicit run detection from trace handlers (#​4256)
• Better handling of nested runnable invocations (#​4256)

langgraph.utils.runnable.RunnableSeq

• Enhanced context propagation for nested sequential operations (#​4256)
• Improved streaming with explicit iterator handling (#​4256)
• Added helper functions for consuming iterators and async iterators (#​4256)

v0.3.28

Compare Source

langgraph 0.3.28

Summary of Changes

• Added support for multiple retry policies, where the first matching policy will be applied when an exception occurs #​4240
• Improved performance and reliability of schema coercion between dictionaries and Pydantic models #​4200
• Optimized default retry logic with better ordering of HTTP error checks for improved exception handling performance

Detailed Changes

langgraph.func.task

• Enhanced to accept a sequence of retry policies in addition to a single policy, providing more flexible error handling #​4240

langgraph.graph.schema_utils.SchemaCoercionMapper

• Significantly refactored for better performance with dictionary to Pydantic model coercion #​4200
• Added efficient caching with functools.lru_cache to avoid redundant processing
• Improved handling of tuple, set, and other collection types
• Added fast paths for basic types with identity conversions
• Better compatibility with both Pydantic v1 and v2
• Fixed order of checking Pydantic versions for more reliable detection

langgraph.graph.state.StateGraph

• Updated add_node to support sequences of retry policies, with documentation for how multiple policies are applied #​4240
• Fixed a bug in _get_updates to correctly detect Pydantic model field sets based on their version #​4200

langgraph.pregel.Pregel

• Now accepts and properly handles a sequence of retry policies instead of just a single policy #​4240
• Improved type hints and initialization to better handle both single policy and sequence cases

langgraph.pregel.retry

• Enhanced retry mechanism to select the first matching policy from a sequence of policies #​4240
• Added _should_retry_on helper function to determine if a policy applies to a specific exception
• Improved backoff calculation logic to apply the correct policy's backoff rate
• Better logging with clearer retry attempt messages

langgraph.types

• Updated default_retry_on function with optimized ordering of HTTP error checks for better performance
• Changed PregelExecutableTask.retry_policy type to support sequences of policies #​4240

v0.3.27

Compare Source

langgraph 0.3.27

Summary of Changes

• Added a new checkpoint_during parameter to control when checkpoints are created, allowing users to optimize graph execution performance by only checkpointing at the end of a run (PR #​4169)
• Improved robustness with better handling of missing optional dependencies (PR #​4203)
• Enhanced RemoteGraph with simpler and more strict config serialization to avoid serialization errors (PR #​4205)

Detailed Changes

langgraph.pregel.Pregel

• Added new checkpoint_during parameter to stream(), astream(), invoke() and ainvoke() methods. When set to False, the graph only creates a checkpoint at the end of execution rather than after each step, which can improve performance for large graphs (PR #​4169)
• Added graceful handling for when _StreamingCallbackHandler is not available, making the library more robust (PR #​4203)

langgraph.pregel.loop.PregelLoop

• Renamed checkpoint_every_step to checkpoint_during for clearer semantics (PR #​4169)
• Added new method _put_pending_writes() to handle persisting writes when checkpointing is deferred (PR #​4169)
• Improved handling of checkpoints by avoiding redundant saves and tracking saved checkpoint IDs (PR #​4169)
• Enhanced write handling to properly track task-specific writes and ensure critical writes are always checkpointed (PR #​4169)

langgraph.pregel.remote.RemoteGraph

• Simplified config sanitization by removing dependency on orjson in favor of strict type checking (PR #​4205)
• Added a CONF_DROPLIST to exclude internal configuration keys from being serialized (PR #​4205)
• Improved the sanitization logic to only include primitive types (string, int, float, bool) in serialized configs (PR #​4205)

langgraph.utils.runnable.RunnableSeq

• Added null checks for _StreamingCallbackHandler to improve robustness when the class is not available (PR #​4203)

v0.3.26

Compare Source

langgraph 0.3.26

Summary of Changes

• Fixed an issue where GraphInterrupt exceptions were raised unnecessarily in remote graph streaming when no caller namespace was present (#​4202)

Detailed Changes

langgraph.pregel.remote.RemoteGraph

• Added a check to only raise GraphInterrupt exceptions in the stream and astream methods when a caller namespace is present, preventing unnecessary interrupts in certain streaming contexts (#​4202)

v0.3.25

Compare Source

langgraph 0.3.25

Summary of Changes

• Added new UI messaging system for LangGraph, enabling developers to send and manage UI component updates during graph execution (#​4157)

Detailed Changes

langgraph.graph.ui

• Added new UIMessage TypedDict to represent UI component updates with properties and metadata (#​4157)
• Added RemoveUIMessage TypedDict for removing UI components from the current state (#​4157)
• Added AnyUIMessage Union type combining both message types (#​4157)
• Added push_ui_message() function to create and send UI messages for rendering components (#​4157)
• Added delete_ui_message() function to remove UI components by ID (#​4157)
• Added ui_message_reducer() function to merge UI message lists, handling both additions and removals (#​4157)

v0.3.24

Compare Source

langgraph 0.3.24

Summary of Changes

• Added checkpoint migration mechanism to ensure backward compatibility with older checkpoint formats (#​4125)
• Updated checkpoint version from 2 to 3 with consistent naming convention for channel keys (#​4125)

Detailed Changes

langgraph.graph.state.StateGraph

• Added _migrate_checkpoint method to handle migrating between different checkpoint formats (#​4125)
• Implemented migration logic to convert older channel key formats (start:node, branch:source:condition:node, or just node) to the new unified format branch:to:node (#​4125)

langgraph.pregel.Pregel

• Added _migrate_checkpoint method to support checkpoint migration (#​4125)
• Added checkpoint migration calls throughout the execution flow to ensure checkpoints are properly upgraded when loaded (#​4125)
• Passed migration function to loop constructors to enable checkpoint migration at key points in execution (#​4125)

v0.3.23

Compare Source

langgraph 0.3.23

Summary of Changes

• Added a special REMOVE_ALL_MESSAGES identifier to allow clearing all messages in a MessageGraph conversation in one operation #​4117
• Moved empty_checkpoint function from being imported from a base module to being defined in the pregel checkpoint module #​4126

Detailed Changes

langgraph.graph.message.add_messages

• Added a special REMOVE_ALL_MESSAGES constant identifier ("__remove_all__")
• Enhanced the message merging logic to detect when a RemoveMessage with this special ID is included
• When this special removal message is detected, all previous messages are discarded and only messages after this special message are returned
• This provides a convenient way to clear an entire conversation history in one operation #​4117

langgraph.pregel.checkpoint.empty_checkpoint

• Moved the function definition from being imported from langgraph.checkpoint.base to being directly defined in langgraph.pregel.checkpoint
• Redefined LATEST_VERSION = 2 in the same module
• Updated imports in relevant files to reference the new location
• No change in functionality, purely a code organization improvement #​4126

v0.3.22

Compare Source

langgraph 0.3.22

Summary of Changes

• Improved error display by removing internal frames from tracebacks, making it easier to identify the actual source of errors (#​4054)
• Added a copy() method to all channel classes for more efficient state copying, improving performance (#​4106)
• Improved thread safety with new LazyAtomicCounter implementation (#​4101)
• Enhanced support for Python 3.12 with optional eager task execution (#​4055)
• Fixed type annotation for destinations parameter in StateGraph.add_node() (#​4053)
• Refactored checkpoint handling for better consistency and performance (#​4103, #​4105)
• Improved handling of resume values in PregelScratchpad (#​4098)
• Refactored StateGraph edge handling for better consistency (#​4064)

Detailed Changes

langgraph.pregel.runner.PregelRunner

• Improved error tracebacks by removing internal frames from stack traces, making it easier to identify the actual source of errors (#​4054)
• The library now filters out internal frames from langgraph, making error messages cleaner and more useful

langgraph.channels.base.BaseChannel and all channel implementations

• Added a new copy() method to all channel classes for more efficient state copying (#​4106)
• Improved handling of checkpoints with consistent usage of MISSING constant instead of None (#​4103)
• Updated method signatures to remove Optional types where appropriate
• Enhanced checkpoint methods for better consistency across channel types (#​4105)

langgraph.pregel.algo.LazyAtomicCounter

• Added a new thread-safe counter implementation that lazily initializes only when needed (#​4101)
• Used for various counters in PregelScratchpad to improve thread safety

langgraph.pregel.algo.local_read

• Refactored to use the new channel copy() method instead of creating checkpoints, significantly improving performance (#​4106)
• Simplified interface by removing unnecessary parameters

langgraph.utils.future.run_coroutine_threadsafe

• Added support for "lazy" task execution control (#​4055)
• Added support for eager tasks when running on Python 3.12
• Improved detection of when the current thread is already using the target event loop

langgraph.graph.state.StateGraph

• Fixed type annotation for destinations parameter in add_node() to correctly support tuples with multiple strings (#​4053)
• Refactored edge handling for more consistent behavior (#​4064)
• Changed some list types to tuples for immutability
• Added a constant for branch channel formatting

langgraph.types.PregelScratchpad

• Made the dataclass immutable for better safety (#​4098)
• Improved handling of resume values with better null value management

langgraph.pregel.checkpoint.create_checkpoint

• Moved checkpoint creation to its own module for better organization (#​4105)
• Improved handling of MISSING values in checkpoint creation

v0.3.21

Compare Source

langgraph 0.3.21

Summary of Changes

• Added a warning and early return when attempting to add an edge between non-existent nodes in Graph (#​4021)
• Fixed interrupt handling in remote graphs to properly construct Interrupt objects from the received data (#​4040)
• Changed the return type of the update method in Topic channel from None to bool (#​4029)

Detailed Changes

langgraph.graph.graph.Graph

• Added a validation check and warning when trying to add an edge between nodes that don't exist, preventing silent failures (#​4021)

langgraph.pregel.remote.RemoteGraph

• Improved interrupt handling in both synchronous and asynchronous stream methods by properly constructing Interrupt objects from the received data, ensuring proper serialization/deserialization of interrupts (#​4040)

langgraph.channels.topic.Topic

• Changed the return type of the update method from None to bool to align with the interface of other channel types (#​4029)

v0.3.20

Compare Source

langgraph 0.3.20

Summary of Changes

• Replaced msgpack dependency with ormsgpack for improved serialization performance #​3953
• Changed behavior when extending subgraphs with missing entrypoints to log a warning instead of raising an exception #​3997
• Improved hash function used in UUID generation from 64-bit to 128-bit for better collision resistance #​4005

Detailed Changes

langgraph.graph.graph.Graph

• Modified add_edge method to log a warning and continue execution instead of raising a ValueError when a subgraph has a missing entrypoint #​3997

langgraph.pregel.algo

• Upgraded the hash function used in _xxhash_str from xxh3_64_hexdigest to xxh3_128_hexdigest for better collision resistance when generating UUIDs #​4005

Dependencies

• Replaced msgpack with ormsgpack (version 1.8.0+) dependency for faster and more efficient MessagePack serialization #​3953

v0.3.19

Compare Source

langgraph 0.3.19

Summary of Changes

• Added significant performance optimization for node execution by only triggering nodes dependent on updated channels (#​3916, #​3931)
• Improved task ID generation performance using XXH3 hash algorithm instead of SHA-1 (#​3954)
• Fixed issues with node writers in StateGraph to properly handle channel writes (#​3949)
• Fixed checkpoint configuration reference in PregelLoop (#​3960)
• Added explicit function configuration support to improve handling of callable arguments (#​3949)
• Added direct subgraph specification support for PregelNode (#​3949)

Detailed Changes

langgraph.pregel.algo.apply_writes

• Now returns a tuple containing both managed value writes and a set of updated channels (#​3916)
• Fixed channel update logic to check if channels are available before updating them (#​3949)

langgraph.pregel.algo.prepare_next_tasks

• Added optimization to only consider nodes that depend on channels that were updated in the previous step (#​3916)
• Added parameters trigger_to_nodes and updated_channels to support the optimization (#​3916)
• Added special case handling for empty channel versions to skip unnecessary processing (#​3931)

langgraph.pregel.Pregel

• Added trigger_to_nodes property to store mapping from triggers to dependent nodes (#​3931)
• Updated validate method to compute trigger_to_nodes mapping (#​3931)
• Fixed type annotations across multiple methods for better consistency (#​3931)

langgraph.pregel.PregelLoop

• Fixed reference to checkpoint configuration in loop initialization (#​3960)
• Updated tick and _first methods to track and pass updated channels information (#​3916)

langgraph.pregel.read.PregelNode

• Added subgraphs parameter to directly specify subgraphs instead of extracting them from bound runnable (#​3949)
• Fixed copy method to properly handle subgraphs (#​3949)

langgraph.graph.state.StateGraph

• Fixed how channel writers are attached to nodes using writers.append() instead of |= operator (#​3949)
• Improved branch handling by moving code to avoid redundant computations (#​3949)

langgraph.utils.runnable.RunnableCallable

• Added func_accepts_config parameter to explicitly control whether a function accepts config parameter (#​3949)
• Improved parameter inspection logic to handle explicit configuration (#​3949)

langgraph.pregel.algo._xxhash_str

• Added new function for task ID generation using XXH3 hash algorithm, which is faster than the previous SHA-1 implementation (#​3954)
• Updated task ID generation to use xxhash for newer checkpoint versions (#​3954)

v0.3.18

Compare Source

langgraph 0.3.18

Summary of Changes

• Improved memory usage in task execution by using weak references for task objects (#​3924)
• Enhanced tracing context handling with proper cleanup to avoid memory leaks and improve LangSmith integration (#​3922)

Detailed Changes

langgraph.types.PregelExecutableTask

• Changed from NamedTuple to dataclass to support weak references (#​3924)
• Added memory optimization with weakref_slot=True for Python 3.11+ to reduce memory footprint during execution

langgraph.pregel.runner.PregelRunner

• Modified task handling to use weak references instead of direct references to reduce memory usage and potential memory leaks (#​3924)
• Updated internal _call and _acall methods to properly handle weak references to tasks

langgraph.pregel.loop.PregelLoop

• Updated task update logic to use dataclasses.replace() instead of _replace() to be compatible with the new task implementation (#​3924)

langgraph.utils.runnable.set_config_context

• Implemented as a proper context manager that correctly sets up and cleans up tracing context (#​3922)
• Ensures proper handling of LangChain tracers and LangSmith integration for better monitoring and debugging

langgraph.utils.runnable.RunnableCallable

• Updated to use the new set_config_context context manager for better context handling (#​3922)
• Improved tracing and context cleanup to prevent potential memory leaks

v0.3.17

Compare Source

langgraph 0.3.17

Summary of Changes

• Added new bulk state update functionality for more efficient sequential state updates (#​3737)
• Performance improvements for state management and task processing (#​3912)

Detailed Changes

langgraph.pregel.Pregel

• Added new bulk_update_state and abulk_update_state methods to allow applying multiple updates to a graph state in sequence (#​3737)
• Refactored existing update_state and aupdate_state methods to use the new bulk update functionality (#​3737)
• Improved error handling for multiple update scenarios with clear error messages (#​3737)

langgraph.types.StateUpdate

• Added new StateUpdate type as a NamedTuple with fields values and as_node to represent individual state updates (#​3737)

langgraph.pregel.algo

• Optimized how triggers are handled by sorting process triggers for more consistent behavior (#​3912)
• Improved memory usage by accessing scratchpad directly from parameters instead of through config (#​3912)
• Enhanced performance by using immutable data structures in task preparation (#​3912)

v0.3.16

Compare Source

langgraph 0.3.16

Summary of Changes

• Improved schema coercion with better error handling and type compatibility, increasing default max depth and adding support for set types (#​3871)
• Reduced memory usage by implementing weak references in the pregel execution engine, preventing reference cycles (#​3907)
• Added internal implementation of get_function_nonlocals to reduce external dependencies (#​3894)

Detailed Changes

langgraph.graph.schema_utils.SchemaCoercionMapper

• Increased default max_depth from 5 to 12, allowing deeper nested schema structures
• Added support for set types in schema coercion
• Improved type compatibility by handling errors more gracefully
• Enhanced Pydantic model support for both v1 and v2 with better type hint handling
• Now returns original values instead of raising exceptions in most type coercion failures
• Made the mapper cache a module-level variable rather than a class variable
• Added proper handling of type hints for more accurate schema coercion

langgraph.pregel.Pregel

• Implemented weak references to prevent reference cycles and reduce memory leaks
• Improved memory management by using weakref.WeakMethod for runner callbacks
• Enhanced formatting of conditional assignments for better code readability

langgraph.pregel.runner.PregelRunner

• Refactored to use weak references for futures, task scheduling and execution
• Moved callback implementations from nested functions to module-level functions for better organization
• Separated sync and async call implementations into distinct functions (_call and _acall)
• Improved error handling during task execution

langgraph.pregel.utils.get_function_nonlocals

• Added internal implementation of get_function_nonlocals function
• Implemented AST analysis to determine nonlocal variables accessed by functions
• Added support for proper handling of attributes and nested function definitions

v0.3.15

Compare Source

langgraph 0.3.15

Summary of Changes

• Added more efficient channel availability checks through new is_available() method on all channel types #​3890
• Simplified branch mechanism in StateGraph with unified channel naming #​3891
• Improved performance in Pregel task creation and execution #​3893

Detailed Changes

langgraph.channels.base.BaseChannel

• Added new is_available() method to check if a channel has values without having to catch exceptions #​3890

All Channel Types

• Refactored all channel implementations to use a MISSING sentinel value instead of attribute errors for tracking empty state #​3890
• Added efficient is_available() implementations to:
  • AnyValue
  • BinaryOperatorAggregate
  • DynamicBarrierValue
  • EphemeralValue
  • LastValue
  • NamedBarrierValue
  • Topic
  • UntrackedValue

langgraph.graph.state.StateGraph

• Simplified branch mechanism by using a single universal channel pattern branch:to:{node} instead of complex channel names #​3891
• Improved efficiency by creating a single branch channel for each node rather than one for each potential branch destination #​3891

langgraph.pregel.algo

• Improved performance by adding dedicated checkpoint_null_version() and _triggers() helper functions #​3893
• Enhanced task creation efficiency by using binascii.unhexlify instead of UUID parsing #​3893
• Optimized memory usage with single tuple constant for push triggers instead of creating new lists #​3893
• Updated to use the new channel is_available() method instead of exception handling #​3890

langgraph.pregel.io

• Removed return_exception parameter from read_channel() as it's no longer needed with the new availability checking #​3890
• Updated branch channel name handling to use the simplified naming convention #​3891

langgraph.types

• Changed PregelExecutableTask.triggers type from list[str] to more flexible Sequence[str] for better performance #​3893

v0.3.14

Compare Source

langgraph 0.3.14

Summary of Changes

• Fixed handling of resume values in nested graph structures, improving reliability when interrupting and resuming tasks across nested graphs (#​3888, #​3889)
• Improved cascading of resume values from parent to child scratchpads, making interrupt/resume more robust in hierarchical contexts (#​3889)
• Enhanced the representation of the Interrupt class by hiding the when field from display outputs (#​3889)

Detailed Changes

langgraph.types.PregelScratchpad

• Redesigned how resume values are handled by replacing direct null_resume storage with a get_null_resume function that takes a consume parameter (#​3888)
• Removed null_resume, _consume_null_resume properties, and the consume_null_resume() method, replacing them with a cleaner and more versatile get_null_resume(bool) callable (#​3888)

langgraph.pregel.algo.prepare_single_task

• Added support for accessing and cascading resume values from parent scratchpads to child scratchpads, improving the handling of resumable interruptions in nested contexts (#​3889)
• Modified _scratchpad function to take a config parameter, allowing it to access the parent scratchpad's resume values (#​3889)

langgraph.types.Interrupt

• Improved the display representation of the Interrupt class by hiding the when field when printing instances (#​3889)

langgraph.pregel.loop.PregelLoop

• Removed redundant code that manually propagated resume values from parent scratchpads, as this is now handled more elegantly through the cascading get_null_resume functionality (#​3889)

v0.3.13

Compare Source

langgraph 0.3.13

Summary of Changes

• Improved graph visualization with parallel traversal of subgraphs and support for RemoteGraph instances ([#​3879](https://redirect.github.com/langchain-ai/langgraph/pull/

---

Configuration

📅 Schedule: Branch creation - At any time (no schedule defined), Automerge - At any time (no schedule defined).

🚦 Automerge: Disabled by config. Please merge this manually once you are satisfied.

♻ Rebasing: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox.

🔕 Ignore: Close this PR and you won't be reminded about this update again.

---

• If you want to rebase/retry this PR, check this box

---

This PR was generated by Mend Renovate. View the repository job log.

[coderabbitai]

Important

Review skipped

Bot user detected.

To trigger a single review, invoke the @coderabbitai review command.

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

---

🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

• Review comments: Directly reply to a review comment made by CodeRabbit. Example:
  • I pushed a fix in commit <commit_id>, please review it.
  • Generate unit testing code for this file.
  • Open a follow-up GitHub issue for this discussion.
• Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
  • @coderabbitai generate unit testing code for this file.
  • @coderabbitai modularize this function.
• PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
  • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
  • @coderabbitai read src/utils.ts and generate unit testing code.
  • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
  • @coderabbitai help me debug CodeRabbit configuration file.

Support

Need help? Join our Discord community for assistance with any issues or questions.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

• @coderabbitai pause to pause the reviews on a PR.
• @coderabbitai resume to resume the paused reviews.
• @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
• @coderabbitai full review to do a full review from scratch and review all the files again.
• @coderabbitai summary to regenerate the summary of the PR.
• @coderabbitai generate sequence diagram to generate a sequence diagram of the changes in this PR.
• @coderabbitai resolve resolve all the CodeRabbit review comments.
• @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
• @coderabbitai help to get help.

Other keywords and placeholders

• Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
• Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
• Add @coderabbitai anywhere in the PR title to generate the title automatically.

CodeRabbit Configuration File (.coderabbit.yaml)

• You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
• Please see the configuration documentation for more information.
• If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

• Visit our Documentation for detailed information on how to use CodeRabbit.
• Join our Discord Community to get help, request features, and share feedback.
• Follow us on X/Twitter for updates and announcements.