fix(deps): update dependency langgraph to >=0.5.1,<0.6

[renovate]

This PR contains the following updates:

Package	Change	Age	Confidence
langgraph	>=0.2.20,<0.3 -> >=0.5.1,<0.6

---

Release Notes

langchain-ai/langgraph (langgraph)

v0.5.1

Compare Source

Changes since 0.5.0

• langgraph: release v0.5.1 (#​5323)
• langgraph[fix]: remove deprecated pydantic logic + fix schema gen behavior for typed dicts (#​5296)
• fix[deps]: update lockfiles / deps bounds for internal tools (#​5301)
• fix broken link (#​5291)
• prebuilt: release 0.5.2 (#​5280)
• prebuilt[patch]: import recognized tool message content block types from langchain-core (#​5275)
• release[prebuilt]: bump version to v0.5.1 (#​5228)
• chore: sdk bumps (#​5220)

v0.5.0

Compare Source

LangGraph 0.5 – the “Getting-Ready-for-1.0” release 🎉

TL;DR – 0.5 is not a radical rewrite, but a scrub-down and tune-up of the LangGraph core.

APIs are a little stricter, you have more control over streaming, checkpoints are lighter, etc. 99 % of users can upgrade with nothing more than a pip install --upgrade langgraph==0.5.*.

---

Why 0.5?

The team’s next big milestone is a 1.0 release in a few months.

To get there we needed to:

• lock in the few API surfaces that still felt “fuzzy”
• prune internal code paths that made distributed execution harder
• land long-queued performance work

0.5 is that housekeeping release.

---

Headline changes

1. A leaner, stricter StateGraph

1. state_schema is now mandatory.

   “Untyped” graphs were never shown in the docs and produced surprising runtime errors. Requiring an explicit schema fixes that class of bugs and improves static analysis.

2. input/output → input_schema/output_schema

   The old names still work but raise a deprecation warning.

   graph = StateGraph(
       state_schema=MyState,
       input_schema=UserQuery,
       output_schema=AssistantResponse,
   )

4. New NodeBuilder utility

   A simpler, declarative way to create nodes and attach them to channels. The old Channel.subscribe_to helper keeps working but will be removed in 1.0.

2. Smarter streaming modes

• stream_mode="debug" is now an alias for the pair["tasks", "checkpoints"]. You can now turn them on individually:

graph.stream(stream_mode="tasks")        # only task-level updates
graph.stream(stream_mode="checkpoints")  # only checkpoint deltas

This makes it cheaper to subscribe only to the information you need.

3. Checkpointing overhaul

• Smaller blobs & faster restores
  Redundant keys have been dropped and per-task writes are stored directly.
• Seamless migrations
  Legacy “pending _sends” data is auto-migrated the first time it is loaded. Custom checkpointers continue to work unchanged.

4. Better serialization

• JsonPlusSerializer now handles NumPy arrays stored in your state (including Fortran-ordered ones) without falling back to pickle.

---

Minor breaking changes you might notice

1. state_schema required – add it if you were passing only input and output schemas instead (very rare).
2. input / output renaming – rename to input_schema / output_schema.
3. Subclassing internals – if you subclassed PregelNode and Runnable, drop the latter.

Nothing else should require code changes.

---

How to upgrade

pip install -U "langgraph>=0.5"

If you maintain a plugin / custom checkpointer, run your test suite once; the public interfaces are untouched.

---

What’s next?

We’re hard at work on LangGraph 1.0, chime in here with any comments, feedback or questions, we want to hear from everyone.

Detailed Changelog

• feat: crons sorting sdk (#​5197)
• feat(langgraph): task masquerading with update state
• Add print_mode= arg to invoke/stream (#​5201)
• Fix bug where Command(update=) could be ignored if there was a 2nd interrupt after it
• Reduce extraneous keys in checkpoint.metadata
• If FuturesDict callback has been GCed, don't call it
• Add migration for pending_sends (#​5106)
• Introduce "tasks" and "checkpoints" stream modes
• Add migration for pending_sends
• Restore compatibility with custom checkpointer classes created in prior versions
• Revert "Remove UntrackedValue channel"
• Revert "Remove MessageGraph (#​4875)"
• fix(langgraph): remove deprecated output usage in favor of output_schema (#​5095)
• refactor(langgraph): Remove PregelNode's inheritance from Runnable (#​5093)
• Remove support for node reading a single managed value
• PregelLoop: Simplify tick() method (#​5080)
• serialize/deserialize pandas with pickle fallback (#​5057)
• Remove code paths no longer needed
• Avoid saving checkpoints for subgraphs when checkpoint_during=False (#​5051)
• Remove gitmcp badge (#​5055)
• Avoid saving checkpoints for subgraphs when checkpoint_during=False
• Clean up things for Matt!
• Support numpy array serialization in JsonPlusSerializer (#​5035)
• Update ormsgpack (#​5034)
• deprecate input and output in favor of input_schema and output_schema (#​4983)
• using StateT as default for InputT
• lint: use pep 604 union syntax and pep 585 generic syntax (#​4963)
• docs: remove references to StateGraph(dict) (#​4964)
• rename retry -> retry_policy (#​4957)
• Fix step_timeout causing ParentCommand/GraphInterrupt exception to bubble up
• docs: fix a grammar issue in multiple files (#​4935)
• Make it possible to run test command without docker installed (#​4948)
• Fix async callback manager tag handling (#​4949)
• Pass tags when configuring async callback manager
• Allow same-name channels and nodes in StateGraph (#​4944)
• Make it possible to run test command without docker installed
• docs: fix ensure_config docstring
• Allow same-name channels and nodes in StateGraph
• Improve type checking on graph init and invoke/stream (#​4932)
• docs: fix a grammar issue in multiple files
• Fix makefile command file for dev server - pidfile was always empty
• Fix Command(graph=PARENT) when used together w checkpointer=True
• Remove unused deprecation decorator/warning (#​4917)
• Require state_schema in StateGraph.__init__ (#​4897)
• Remove add_conditional_edge(..., then=) (#​4893)
• Avoid repeated runtime calls to get_type_hints
• Remove MessageGraph (#​4875)
• Remove non-state Graph
• Remove UntrackedValue channel
• Remove UntrackedValue channel (#​4859)
• Flip default for checkpoint_during
• Remove Channel node builder
• Update managed value usage in local_read (#​4854)
• Modify stream mode messages and custom to respect subgraphs=False (#​4843)
• Remove Checkpoint.writes (#​4822)
• Remove Checkpoint.pending_sends (#​4820)
• Pregel: Add NodeBuilder class to replace Channel.subscribe_to (#​4819)
• Remove dict subclasses used for values/updates stream chunks (#​4816)
• Remove old checkpoint test fixtures (#​4814)
• Remove postgres shallow checkpointer (#​4813)
• Remove ChannelsManager, ManagedValues are now static classes and never instantiated (#​4812)
• Remove Context channel / managed value, Remove SharedValue (#​4857)
• Pregel: Add NodeBuilder class to replace Channel.subscribe_to
• Remove old checkpoint test fixtures
• Remove postgres shallow checkpointer
• Remove ChannelsManager, ManagedValues are now static classes and never instantiated
• Remove Context channel / managed value, Remove SharedValue

v0.4.10

Compare Source

Changes since 0.4.9

• Revert change to default value of checkpoint_during arg (#​5177)
• Revert change to default value of checkpoint_during arg
• Fix bug where Command(update=) could be ignored if there was a 2nd interrupt after it
• Reduce extraneous keys in checkpoint.metadata
• If FuturesDict callback has been GCed, don't call it
• langgraph 0.5.0rc1
• langgraph 0.5.0rc0
• Preparation for 0.5 release: langgraph-checkpoint (#​5124)
• Preparation for 0.5 release
• Add migration for pending_sends (#​5106)
• Lint
• Introduce "tasks" and "checkpoints" stream modes
• Add migration for pending_sends
• Restore compatibility with custom checkpointer classes created in prior versions
• Revert "Remove UntrackedValue channel"
• Revert "Remove MessageGraph (#​4875)"
• fix(langgraph): remove deprecated output usage in favor of output_schema (#​5095)
• refactor(langgraph): Remove PregelNode's inheritance from Runnable (#​5093)
• Remove support for node reading a single managed value
• PregelLoop: Simplify tick() method (#​5080)
• serialize/deserialize pandas with pickle fallback (#​5057)
• Remove code paths no longer needed
• Avoid saving checkpoints for subgraphs when checkpoint_during=False (#​5051)
• Remove gitmcp badge (#​5055)
• Update existing
• Add tests
• Avoid saving checkpoints for subgraphs when checkpoint_during=False
• Clean up things for Matt!
• Support numpy array serialization in JsonPlusSerializer (#​5035)
• Update ormsgpack (#​5034)
• deprecate input and output in favor of input_schema and output_schema (#​4983)
• using StateT as default for InputT
• lint: use pep 604 union syntax and pep 585 generic syntax (#​4963)
• docs: remove references to StateGraph(dict) (#​4964)
• rename retry -> retry_policy (#​4957)
• Fix step_timeout causing ParentCommand/GraphInterrupt exception to bubble up
• docs: fix a grammar issue in multiple files (#​4935)
• Make it possible to run test command without docker installed (#​4948)
• Fix async callback manager tag handling (#​4949)
• Pass tags when configuring async callback manager
• Allow same-name channels and nodes in StateGraph (#​4944)
• Make it possible to run test command without docker installed
• docs: fix ensure_config docstring
• Allow same-name channels and nodes in StateGraph
• Improve type checking on graph init and invoke/stream (#​4932)
• docs: fix a grammar issue in multiple files
• Fix makefile command file for dev server - pidfile was always empty
• Fix Command(graph=PARENT) when used together w checkpointer=True
• Remove unused deprecation decorator/warning (#​4917)
• Require state_schema in StateGraph.__init__ (#​4897)
• Remove add_conditional_edge(..., then=) (#​4893)
• Avoid repeated runtime calls to get_type_hints
• Remove MessageGraph (#​4875)
• Remove non-state Graph
• Remove UntrackedValue channel
• Remove UntrackedValue channel (#​4859)
• Flip default for checkpoint_during
• Remove Channel node builder
• Update managed value usage in local_read (#​4854)
• Modify stream mode messages and custom to respect subgraphs=False (#​4843)
• Remove Checkpoint.writes (#​4822)
• Remove Checkpoint.pending_sends (#​4820)
• Pregel: Add NodeBuilder class to replace Channel.subscribe_to (#​4819)
• Remove dict subclasses used for values/updates stream chunks (#​4816)
• Remove old checkpoint test fixtures (#​4814)
• Remove postgres shallow checkpointer (#​4813)
• Remove ChannelsManager, ManagedValues are now static classes and never instantiated (#​4812)
• Remove Context channel / managed value, Remove SharedValue (#​4857)
• Update managed value usage in local_read
• Format
• Remove Checkpoint.writes
• Remove Checkpoint.pending_sends
• Pregel: Add NodeBuilder class to replace Channel.subscribe_to
• Lint
• Remove old checkpoint test fixtures
• Remove postgres shallow checkpointer
• Remove ChannelsManager, ManagedValues are now static classes and never instantiated
• Remove Context channel / managed value, Remove SharedValue

v0.4.9

Compare Source

Changes since 0.5.0rc1

• Revert change to default value of checkpoint_during arg (#​5177)
• Revert change to default value of checkpoint_during arg
• Fix bug where Command(update=) could be ignored if there was a 2nd interrupt after it
• Reduce extraneous keys in checkpoint.metadata
• If FuturesDict callback has been GCed, don't call it

v0.4.8

Compare Source

Changes since 0.4.7

• Remove unused deprecation decorator/warning (#​4917)
• Require state_schema in StateGraph.__init__ (#​4897)
• Remove add_conditional_edge(..., then=) (#​4893)
• Avoid repeated runtime calls to get_type_hints
• Remove MessageGraph (#​4875)
• Remove non-state Graph
• Remove UntrackedValue channel
• Remove UntrackedValue channel (#​4859)
• Flip default for checkpoint_during
• Remove Channel node builder
• Update managed value usage in local_read (#​4854)
• Modify stream mode messages and custom to respect subgraphs=False (#​4843)
• Remove Checkpoint.writes (#​4822)
• Remove Checkpoint.pending_sends (#​4820)
• Pregel: Add NodeBuilder class to replace Channel.subscribe_to (#​4819)
• Remove dict subclasses used for values/updates stream chunks (#​4816)
• Remove old checkpoint test fixtures (#​4814)
• Remove postgres shallow checkpointer (#​4813)
• Remove ChannelsManager, ManagedValues are now static classes and never instantiated (#​4812)
• Remove Context channel / managed value, Remove SharedValue (#​4857)
• Remove SchemaCoercionMapper
• Update managed value usage in local_read
• prebuilt: release 0.2.2 (#​4851)
• Format
• Remove Checkpoint.writes
• Remove Checkpoint.pending_sends
• Pregel: Add NodeBuilder class to replace Channel.subscribe_to
• Lint
• Remove old checkpoint test fixtures
• Remove postgres shallow checkpointer
• Remove ChannelsManager, ManagedValues are now static classes and never instantiated
• Remove Context channel / managed value, Remove SharedValue
• Merge branch 'main' into fix-examples-link-readme
• Update libs/langgraph/README.md
• Update libs/langgraph/README.md
• Merge branch 'main' into fix-examples-link-readme
• Merge branch 'main' into fix-examples-link-readme
• Merge branch 'main' into fix-examples-link-readme
• Merge branch 'langchain-ai:main' into fix-examples-link-readme
• fix link to examples page in readme.md

v0.4.7

Compare Source

Changes since 0.4.6

• 0.4.7
• Fix stream mode not respected in subgraphs
• Try to make test less flaky
• Add tests for stream_events when using imperative api

v0.4.6

Compare Source

Changes since 0.4.5

• 0.4.6
• Fix
• Lint
• Add sync test
• Fix
• Fix exception handling for imperative tasks
• prebuilt: release 0.2.1 (#​4801)
• prebuilt: release 0.2.0 (#​4793)
• Code review
• feat(langgraph): push_messages should directly write to the state
• feat(graph): add push_message method to push manually to messages / message-tuple stream (#​4722)
• Add message state test
• Apply same condition for stream_mode=values in suppress interrupt
• Remove redundant cast
• feat(graph): add push_message method to push manually to messages / message-tuple stream
• Last uv.lock?
• Only emit stream values chunks when the output channels have changed (#​4774)
• docs: fix example pregel reducer (#​4740)
• prebuilts hitl: fix branching logic + add structural snapshot tests (#​4767)
• docs: deferred nodes (#​4759)
• Remove local_write utility (#​4751)
• Print output for cached @​task functions (#​4750)
• Print output for cached @​task functions
• sqlite: Add test for search with list filters (#​4747)
• sqlite: update list_namespaces with max_depth (#​4746)
• Update lockfile
• docs: Clean up adjective use in readme (#​4734)
• SqliteStore (#​3608)
• ci: fix benchmark command (#​4729)
• docs: document tuples in streaming guides (#​4690)
• ci: migrate to uv! (#​4698)

v0.4.5

Compare Source

Changes since 0.4.4

• langgraph: release 0.4.5 (#​4709)
• Improve how we match cached writes for async imperative tasks (#​4691)
• Lint
• Improve how we match cached writes for async imperative tasks

v0.4.4

Compare Source

Changes since 0.4.3

• langgraph: release 0.4.4 (#​4704)
• update for consistency
• lint again
• use list
• lint + update
• update
• update
• update
• langgraph: fix drawing graph with root channel
• langgraph: fix graph drawing for self-loops
• Merge branch 'main' into clean
• [Proposal] add gitmcp badge for simple LLM-accessible documentation (#​4502)
• Change LG Cloud > Platform
• Fix invalid channels error message (#​4357)
• docs: remove unused annotation comments in readmes (#​4656)
• docs: General language cleanup (#​4649)
• [docs] LangGraph / LangGraph Platform docs updates (#​4479)
• Port checkpointer/store fixtures in langgraph-prebuilt to idiomatic pattern (#​4629)
• Extend all tests using InMemorySaver to use all available checkpointers (#​4627)
• Implement update_state for functional api (#​4626)
• More idiomatic sync/async checkpointer fixtures in pytest (#​4624)
• More idiomatic sync/async store fixtures in pytest (#​4617)
• Overload clear method to delete all when called without args
• Limit depth
• Extend all tests using InMemorySaver to use all available checkpointers
• Implement update_state for functional api
• Fix
• More idiomatic sync/async checkpointer fixtures in pytest
• Move to sep file
• More idiomatic sync/async store fixtures in pytest
• Lint
• Lint
• Move FileCache to sqlite package, add InMemoryCache
• Add clear cache methods
• Remove refresh
• Add namespace to cache keys
• Lint
• Lint
• Lint
• Lint
• Lint
• Lint
• Lint
• Finish implementation, add tests
• Lint
• Lint
• Accept default cache_policy for graph/entrypoint/pregel
• Fix
• Fix
• Output cached writes
• Lint
• Rename
• Fix type annotation
• Fixes
• Re-do with separate cache interface
• WIP
• Deferred Node (#​4269)
• Start dev server externally (#​4604)

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 t

---

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.
  • Explain this complex logic.
  • 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 explain this code block.
  • @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 explain its main purpose.
  • @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.