NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
PyPI, #436 most downloaded on PyPI
SDK for interacting with LangGraph API
Latest stable
0.4.14
Last release 16 days ago
06 Nov 2026
Release timing varies
gaps range from 8 days to 3 months
Some releases are documented
notes for 15 of the last 60 stable releases
2 versions withdrawn
withdrawn after publishing
3 years old
112 releases · first in 2024
Drag across the ruler to compare, or tap a release to open it.
feat(sdk-py): add strict_resume to runs.create, stream and wait
feat(sdk-py): add cancel_reason to Run
Your coding agent can read these notes before it upgrades. Set up the MCP server →
feat(sdk-py): remove fairness_weight from PrioritySettings
PrioritySettings.fairness_weight — removed. The server stores only
priority and fairness_group on the thread; it ignores a
fairness_weight and logs a warning. Remove it from your callback.PrioritySettings.priority — now says -5 runs first and 5 runs last,
matching how the server orders runs. 0.4.9 to 0.4.11 said the reverse, and
their example gave premium users 3, which runs them after everyone at the
default 0. Check any callback written from those docs.test(sdk-py): check that a reconnect loop resumes after the newest event
Changes since sdk==0.4.10
Thread-centric streaming (v3) — client.threads.stream() returns an
AsyncThreadStream (or SyncThreadStream) context manager that owns one
SSE or WebSocket connection for the lifetime of a thread session.
Typed projections — thread.messages, thread.tool_calls,
thread.values, and thread.extensions[name] all share the same underlying
transport connection. Iterating multiple projections concurrently expands the
server-side filter union without opening additional connections.
Scoped subgraph handles — thread.subgraphs (alias thread.subagents)
yields one ScopedStreamHandle per direct child invocation, each exposing
.messages, .tool_calls, and .subgraphs scoped to that namespace.
WebSocket transport — pass transport="websocket" to
client.threads.stream() to use a WebSocket connection instead of SSE
(async client only).
Automatic reconnect — the shared SSE fan-out and the lifecycle watcher
both reconnect on transport drops, replaying missed events via a since
cursor and deduplicating by event_id.
thread.agent.get_tree() — fetches the assistant graph definition for
the current session's assistant_id with optional xray depth control.
thread.run.respond() — resumes a run after a server-side interrupt,
resolving the outstanding InterruptPayload by interrupt_id.
thread.output — awaitable that resolves to the terminal thread state
values dict after the run lifecycle completes.
Priority (beta) — register an async function with @priority.assign
and name the object in the priority section of langgraph.json. The
server calls the function with a PriorityContext at the first run on a
thread with no settings and stores the PrioritySettings it returns
(priority, fairness_group) on the thread. Requires
langgraph-api 0.18.0 or later and a langgraph-cli that supports the
section; older versions of either ignore it.
client.threads.stream() now accepts transport="sse" (default) or
transport="websocket" in place of the previous transport-agnostic default.actions= and reject empty or
invalid action lists. Because unmatched custom-auth paths remain allowed,
deployments using action-scoped handlers should configure a global
default-deny handler; langgraph-api 0.10+ warns about uncovered paths at
startup. Resource-specific decorators retain matching resources= selectors
for backward compatibility; use @auth.on(resources=...) for other resources.AsyncThreadStream, SyncThreadStream, and all
projection classes) is new in this release. The existing
client.runs.stream() (v2) surface is unchanged and remains fully supported.thread_id is minted client-side (UUIDv4) when not provided; the server
creates the thread row lazily on the first run.start.fix(sdk-py): retry runs.wait with a bodyless GET and raise run errors in sync wait
Changes since sdk==0.4.9
feat(sdk-py): add Priority for thread priority settings
Changes since sdk==0.4.8
fix(sdk-py): surface thread stream errors and stop retrying a rejected stream
fix(sdk-py): end a thread stream's run only on a root lifecycle event
fix(sdk-py): percent-encode thread_id and assistant_id in thread stream requests
Changes since sdk==0.4.5
chore(deps): bump anyio from 4.14.2 to 4.15.1 in /libs/sdk-py
Changes since sdk==0.4.4
feat: route LangSmith traces from thread streams
feat(sdk-py): add decrypt replacement result
Changes since sdk==0.4.2
README.md structure (#8064)lc_versions config metadata (#8052)langgraph: decouple name from assistant ID in RemoteGraph
Changes since 0.4.1
Fixed an issue handling END in StateGraph edges to properly terminate graph execution #4458
END in StateGraph edges to properly terminate graph execution #4458merge parameter #4473TAG_NOSTREAM from "langsmith:nostream" to "nostream", maintaining backwards compatibility #4473push_ui_message #4467END constant in get_writes and _control_static functions, ensuring proper graph termination when returning to END #4458merge parameter to push_ui_message function, allowing incremental updates to UI messages #4473ui_message_reducer to support merging props from existing messages when the merge flag is set #4473push_ui_message by removing old metadata merging which could cause unexpected behavior #4467TAG_NOSTREAM from "langsmith:nostream" to "nostream" #4473TAG_NOSTREAM_ALT with the old value ("langsmith:nostream") for backward compatibility #4473SchemaCoercionMapper #4448lru_cache for better performance #4448Added improved support for interrupt handling in streaming modes, with interrupts now properly propagated in "values" stream mode #4374
"values" stream mode #4374interrupt_id property that generates a unique ID for the interrupt based on its namespace #4406| as a separator between namespace elements for better uniqueness #4406"values" mode emits all values including interrupts after each step #4374interrupts field to track interrupts that occurred in a step and are pending resolution #4406resume parameter to support mapping interrupt IDs to resume values #4406resume parameter #4406invoke and ainvoke methods to properly collect and handle interrupts in streamed output #4374"values" and "updates" stream modes #4374Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
One column per month.