feat(langgraph): add set_node_defaults() to StateGraph by longquanzheng · Pull Request #7747 · langchain-ai/langgraph

Quanzheng Long (longquanzheng) · 2026-05-08T19:11:30Z

Add StateGraph.set_node_defaults() — a fluent builder method for setting graph-wide node policies in one place. Per-node values from add_node() always take precedence. Defaults are applied at compile() time.

graph = (
    StateGraph(State)
    .set_node_defaults(
        retry_policy=RetryPolicy(max_attempts=3),
        error_handler=my_fallback_handler,
        timeout=TimeoutPolicy(run_timeout=30),
    )
    .add_node("a", node_a)
    .add_node("b", node_b, retry_policy=custom)  # overrides default
    .add_edge(START, "a")
    .compile()
)

Error handlers are never invoked on error-handler nodes themselves — handler failures fail the run. Not inherited by subgraphs.

Supported defaults

`set_node_defaults()` kwarg	Fallback for `add_node(...)` kwarg	Applies to error-handler nodes?
`retry_policy`	`retry_policy`	Yes
`cache_policy`	`cache_policy`	No — caching handler results is unsafe
`error_handler`	`error_handler`	No — handlers must never catch themselves
`timeout`	`timeout`	Yes

Changes

libs/langgraph/langgraph/graph/state.py — new _NodeDefaults dataclass, set_node_defaults() method on StateGraph; compile() applies builder defaults to node specs with per-branch rules for which defaults apply to error-handler nodes.
libs/langgraph/tests/test_retry.py — 14 new tests covering all four policy types, per-node override precedence, chaining, combined retry+handler, handler exclusion, RunnableConfig injection, and name collision.

Verification

make format, make lint, make test all passing in libs/langgraph.

Sydney Runkle (sydney-runkle)

one other idea -- do we also want to support:

default node retry policy?
default node cache policy?

if we do, do we want a cleaner API (not just 3 new args)

and another note, i've heard requests for graph level timeouts as well... that would be implemented differently though (it's not a node default)

Sydney Runkle (sydney-runkle) · 2026-05-08T19:52:47Z

        debug: bool = False,
        name: str | None = None,
        transformers: Sequence[Callable[[tuple[str, ...]], Any]] | None = None,
+        default_error_handler: StateNode[Any, ContextT] | None = None,


ok actually, i think might be cleaner in StateGraph.__init__

that way we can just manage this in add_node :)

can we TAL at that alternative?

great feedback. change to set_defaults for now.

Sydney Runkle (sydney-runkle) · 2026-05-09T09:54:44Z

        self._add_schema(self.input_schema, allow_managed=False)
        self._add_schema(self.output_schema, allow_managed=False)

+    def set_defaults(


set_node_defaults?

Sydney Runkle (sydney-runkle) · 2026-05-09T09:55:08Z

        self.output_schema = cast(type[OutputT], output_schema or state_schema)
        self.context_schema = context_schema

+        self._default_retry_policy: RetryPolicy | Sequence[RetryPolicy] | None = None


self._node_defaults.retry_policy? and similar

Sydney Runkle (sydney-runkle) · 2026-05-09T09:55:45Z

        debug: bool = False,
        name: str | None = None,
        transformers: Sequence[Callable[[tuple[str, ...]], Any]] | None = None,
+        default_error_handler: StateNode[Any, ContextT] | None = None,


let's remove this arg to compile and just expose the set_defaults method

…r_handler compile arg Consolidate the four `_default_*` builder fields into a single `_NodeDefaults` dataclass and apply defaults via a tight `_apply_node_defaults` loop in `compile()`. Per-spec mutation already fills every node's policy before Pregel sees it, so the redundant graph-level `retry_policy`/`cache_policy` pass-through is dropped.

donezo

Sydney Runkle (sydney-runkle) · 2026-05-09T10:22:59Z

question here is where we want to apply defaults
if we do it in compile, then the order of set_node_defaults and add_node doesn't matter
but it feels cleaner if when you add a node, the policy gets attached (so you could inspect the nodes and see)
but i don't really want to enforce this in 2 places

Sydney Runkle (sydney-runkle) · 2026-05-09T10:25:53Z

if we supported on init as opposed to a method, we could enforce at node addition time

…efaults=...) and apply at add_node time Promote the internal _NodeDefaults dataclass to a public NodeDefaults constructor arg. Defaults are resolved per-spec inside add_node, so compile() no longer needs an apply pass. The synthetic default error-handler node is materialized in __init__ when set, and add_node's existing duplicate-name guard now naturally rejects user nodes that collide with it.

…h(node_defaults=...) and apply at add_node time" This reverts commit d04b1c4.

Sydney Runkle (sydney-runkle)

a few things that might be odd here -- nodes don't have the correct retry policy / error handler / timeout until compile time :/

@npentrel

## Summary - Add a new `## Graph-wide defaults with set_node_defaults` section to the LangGraph fault tolerance page - Documents the new `set_node_defaults()` method on `StateGraph` introduced in [langchain-ai/langgraph#7747](langchain-ai/langgraph#7747) - Covers: overview with full example, precedence rules, default error handler (with `RunnableConfig`), applicability matrix, and scope note - Updated the intro bullet list to reference the new section - Added a Limitations bullet for subgraph inheritance ## Links - Linear: https://linear.app/langchain/issue/DOC-1112/update-langgraph-fault-tolerance-page-based-on-pr-7747 - Slack: https://langchain.slack.com/archives/C09G1T60QV9/p1779224166104029 - Reference PR: langchain-ai/langgraph#7747 ## Verification Not run; docs-only copy change. ## Reviewers Requested review from: @npentrel, @lnhsingh Co-authored-by: Docs Bot <brace@langchain.dev>

… policy defaults Port of langchain-ai/langgraph#7747. Adds a fluent setNodeDefaults({ retryPolicy?, cachePolicy? }) builder method that sets graph-wide node policy defaults, resolved at compile() time so call order is irrelevant. Per-node addNode values always take precedence. Defaults are not inherited by subgraphs. Scoped to the retryPolicy/cachePolicy node policies that exist in JS today; Python's error_handler/timeout defaults are out of scope because those node features do not yet exist in the JS engine.

@christian-bromann

This PR was opened by the [Changesets release](https://github.com/changesets/action) GitHub action. When you're ready to do a release, you can merge this and the packages will be published to npm automatically. If you're not ready to do a release yet, that's fine, whenever you add more changesets to main, this PR will be updated. # Releases ## @langchain/langgraph-checkpoint@1.1.0 ### Minor Changes - [#2452](#2452) [`a8e7659`](a8e7659) Thanks [@christian-bromann](https://github.com/christian-bromann)! - Add `DeltaChannel` and the writes-history saver API (beta). `DeltaChannel` is a reducer channel that stores only a sentinel in checkpoint blobs instead of the full accumulated value, reconstructing state on read by replaying ancestor writes through a batch reducer. This avoids re-serializing the entire accumulated value at every step (e.g. long message histories). - `DeltaChannel(reducer, { snapshotFrequency })` in `@langchain/langgraph` — count-based snapshot cadence (default `snapshotFrequency=1000`) plus a system bound `DELTA_MAX_SUPERSTEPS_SINCE_SNAPSHOT` (default 5000, env `LANGGRAPH_DELTA_MAX_SUPERSTEPS_SINCE_SNAPSHOT`). - `messagesDeltaReducer` — a batching-invariant messages reducer that coerces raw object/string writes, for use with `DeltaChannel`. - `BaseCheckpointSaver.getDeltaChannelHistory({ config, channels })` (beta) — walks the parent chain returning per-channel `{ writes, seed? }`, with a direct-storage override in `MemorySaver`. - `counters_since_delta_snapshot` added to `CheckpointMetadata`; `DeltaSnapshot` serialization support in the JSON+ serializer. Reconstruction is wired through the Pregel read/execution paths (initialization, `getState`, `updateState`, local reads) and `exit` durability accumulates and anchors delta writes so threads remain reconstructible without forcing snapshots. ### Patch Changes - [#2450](#2450) [`2f6d873`](2f6d873) Thanks [@christian-bromann](https://github.com/christian-bromann)! - Add node-level timeouts. A `timeout` option is now supported on `StateGraph.addNode`, the functional API (`task`/`entrypoint`), and the `Send` constructor. Pass a number of milliseconds for a hard wall-clock cap, or a `TimeoutPolicy` for finer control: ```ts import { TimeoutPolicy } from "@langchain/langgraph"; // hard wall-clock cap on each attempt builder.addNode("agent", agentFn, { timeout: 60_000 }); // full control builder.addNode("agent", agentFn, { timeout: { runTimeout: 60_000, // hard wall-clock cap, never refreshed idleTimeout: 10_000, // cap on time without observable progress refreshOn: "auto", // "auto" | "heartbeat" }, }); // per-task override new Send("agent", state, { timeout: { idleTimeout: 5_000 } }); ``` When a timeout fires, a `NodeTimeoutError` (carrying `node`, `kind` (`"run"`/`"idle"`), `timeout`, `elapsed`, `runTimeout`, `idleTimeout`) is raised, the attempt's buffered writes are dropped, and the node's `AbortSignal` is aborted. `idleTimeout` is refreshed by observable progress (writes, custom stream-writer calls, child-task scheduling, callback events) or an explicit `runtime.heartbeat()` call. The timer resets per retry attempt, and `NodeTimeoutError` is retryable under the default retry policy. Ports langchain-ai/langgraph#7599, [#7646](https://github.com/langchain-ai/langgraphjs/issues/7646), and [#7659](https://github.com/langchain-ai/langgraphjs/issues/7659). ## @langchain/langgraph@1.4.0 ### Minor Changes - [#2449](#2449) [`d12d269`](d12d269) Thanks [@christian-bromann](https://github.com/christian-bromann)! - Add cooperative, between-superstep graph draining via `RunControl`. A new `RunControl` (exported from `@langchain/langgraph`) exposes `requestDrain(reason)` plus read-only `drainRequested` / `drainReason`. Pass it through the new `control` option on `invoke` / `stream` / `streamEvents` (and the functional API). It is surfaced on `runtime.control`, so nodes can read it or call `requestDrain()` themselves, and it is propagated into subgraphs. When a drain is requested, the Pregel loop checks the flag at the top of each superstep (after the previous step's writes are applied and checkpointed): if more tasks remain it saves the checkpoint and throws the new `GraphDrained` error (also under `durability: "exit"`), so the run can be resumed later from the same config. If the graph naturally finishes on that tick it returns normally and the caller can inspect `control.drainRequested`. A drain requested inside a subgraph bubbles up and stops the parent at its next boundary. Draining never cancels work that is already running — pair it with an `AbortSignal` if you need a hard upper bound. - [#2452](#2452) [`a8e7659`](a8e7659) Thanks [@christian-bromann](https://github.com/christian-bromann)! - Add `DeltaChannel` and the writes-history saver API (beta). `DeltaChannel` is a reducer channel that stores only a sentinel in checkpoint blobs instead of the full accumulated value, reconstructing state on read by replaying ancestor writes through a batch reducer. This avoids re-serializing the entire accumulated value at every step (e.g. long message histories). - `DeltaChannel(reducer, { snapshotFrequency })` in `@langchain/langgraph` — count-based snapshot cadence (default `snapshotFrequency=1000`) plus a system bound `DELTA_MAX_SUPERSTEPS_SINCE_SNAPSHOT` (default 5000, env `LANGGRAPH_DELTA_MAX_SUPERSTEPS_SINCE_SNAPSHOT`). - `messagesDeltaReducer` — a batching-invariant messages reducer that coerces raw object/string writes, for use with `DeltaChannel`. - `BaseCheckpointSaver.getDeltaChannelHistory({ config, channels })` (beta) — walks the parent chain returning per-channel `{ writes, seed? }`, with a direct-storage override in `MemorySaver`. - `counters_since_delta_snapshot` added to `CheckpointMetadata`; `DeltaSnapshot` serialization support in the JSON+ serializer. Reconstruction is wired through the Pregel read/execution paths (initialization, `getState`, `updateState`, local reads) and `exit` durability accumulates and anchors delta writes so threads remain reconstructible without forcing snapshots. - [#2451](#2451) [`d65a920`](d65a920) Thanks [@christian-bromann](https://github.com/christian-bromann)! - feat(langgraph): add node-level error handlers `StateGraph.addNode(name, fn, { errorHandler })` now accepts a first-class node-level error handler. The handler runs ONLY after the failing node's `retryPolicy` is exhausted, so retry and handling stay decoupled. It receives a typed `NodeError { node, error }` and the typed node input state, can return a state update, and can route to a recovery branch via `new Command({ goto })` (saga / compensation flows). Failure provenance is checkpointed (via a reserved `ERROR_SOURCE_NODE` write) so handlers observe the same context after a checkpoint resume. Uncaught node errors without a handler still abort the run as before, and `GraphBubbleUp` errors (such as `interrupt()`) are never swallowed by a handler. `StateGraph.setNodeDefaults({ errorHandler })` now also accepts a graph-wide default handler. It is materialized at `compile()` as a single shared handler and invoked for every regular node that does not set its own `errorHandler`. A per-node handler always takes precedence, the default never catches a failure raised by an error-handler node itself (handler failures fail the run), and the default is not inherited by subgraphs. Ports the Python feature from langchain-ai/langgraph#7233. - [#2450](#2450) [`2f6d873`](2f6d873) Thanks [@christian-bromann](https://github.com/christian-bromann)! - Add node-level timeouts. A `timeout` option is now supported on `StateGraph.addNode`, the functional API (`task`/`entrypoint`), and the `Send` constructor. Pass a number of milliseconds for a hard wall-clock cap, or a `TimeoutPolicy` for finer control: ```ts import { TimeoutPolicy } from "@langchain/langgraph"; // hard wall-clock cap on each attempt builder.addNode("agent", agentFn, { timeout: 60_000 }); // full control builder.addNode("agent", agentFn, { timeout: { runTimeout: 60_000, // hard wall-clock cap, never refreshed idleTimeout: 10_000, // cap on time without observable progress refreshOn: "auto", // "auto" | "heartbeat" }, }); // per-task override new Send("agent", state, { timeout: { idleTimeout: 5_000 } }); ``` When a timeout fires, a `NodeTimeoutError` (carrying `node`, `kind` (`"run"`/`"idle"`), `timeout`, `elapsed`, `runTimeout`, `idleTimeout`) is raised, the attempt's buffered writes are dropped, and the node's `AbortSignal` is aborted. `idleTimeout` is refreshed by observable progress (writes, custom stream-writer calls, child-task scheduling, callback events) or an explicit `runtime.heartbeat()` call. The timer resets per retry attempt, and `NodeTimeoutError` is retryable under the default retry policy. Ports langchain-ai/langgraph#7599, [#7646](https://github.com/langchain-ai/langgraphjs/issues/7646), and [#7659](https://github.com/langchain-ai/langgraphjs/issues/7659). - [#2461](#2461) [`801d955`](801d955) Thanks [@christian-bromann](https://github.com/christian-bromann)! - Add `StateGraph.setNodeDefaults()` for setting graph-wide node policy defaults (`retryPolicy`, `cachePolicy`). Per-node values passed to `addNode` always take precedence, and defaults are resolved at `compile()` time so call order does not matter. Defaults are not inherited by subgraphs. Ports Python's `set_node_defaults()` (langchain-ai/langgraph#7747). ### Patch Changes - [#2179](#2179) [`01c67df`](01c67df) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(core): time travel replay/fork for graphs with interrupts and subgraphs Ports Python fixes for stale RESUME writes during replay, wrong subgraph checkpoint loading during time travel, missing fork checkpoints on replay, and direct-to-subgraph time travel. - [#2514](#2514) [`9e0201d`](9e0201d) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(schema): expose StateSchema JSON schemas for Studio introspection Route StateSchema runtime definitions through getJsonSchema() and getInputJsonSchema() so LangGraph Studio receives state, input, and context schemas when graphs use the StateSchema primitive. Fixes [#2466](#2466) - [#2471](#2471) [`9b96f60`](9b96f60) Thanks [@christian-bromann](https://github.com/christian-bromann)! - perf(core): skip debug checkpoint snapshots when not streaming them Avoid building full-state `mapDebugCheckpoint` payloads on every tick when no consumer subscribed to `checkpoints` or `debug` stream modes. v3 companion checkpoint envelopes are unchanged (they come from values metadata). - [#2472](#2472) [`8e06ace`](8e06ace) Thanks [@christian-bromann](https://github.com/christian-bromann)! - perf(core): index pending writes for O(1) task-prep lookups Build a PendingWritesIndex once per \_prepareNextTasks call so resume and skip-done-task checks avoid repeated linear scans over checkpointPendingWrites. - [#2473](#2473) [`a8b0036`](a8b0036) Thanks [@christian-bromann](https://github.com/christian-bromann)! - perf(core): optimize applyWrites, interrupt seen, and channel errors Reduce allocations in \_applyWrites, fix O(N²) interrupt versions_seen updates, skip stack traces on EmptyChannelError control flow, and cache task lists in the pregel loop and runner. - [#2444](#2444) [`4096933`](4096933) Thanks [@christian-bromann](https://github.com/christian-bromann)! - feat(remote): add RemoteGraph v3 streaming support Expose the v3 `streamEvents` surface for `RemoteGraph` by adapting remote SDK thread streams to the local `GraphRunStream` shape. - Updated dependencies \[[`a8e7659`](a8e7659), [`2f6d873`](2f6d873)]: - @langchain/langgraph-checkpoint@1.1.0 ## @langchain/langgraph-checkpoint-mongodb@1.3.4 ### Patch Changes - [#2517](#2517) [`67a4f8d`](67a4f8d) Thanks [@jackjin1997](https://github.com/jackjin1997)! - fix: `MongoDBSaver.putWrites` now honors `WRITES_IDX_MAP`, pinning special channels (`__error__`, `__scheduled__`, `__interrupt__`, `__resume__`) to fixed negative indices instead of the call-local ordinal. Previously a mixed `putWrites([[...regular...], [INTERRUPT, …]], taskId)` placed the INTERRUPT at a positive idx that could collide with a regular write at the same `(task_id, idx)`, and the unconditional `$set` upsert silently overwrote whichever row landed there first. The conflict-resolution clause now matches the Postgres / SQLite (TS and Python) checkpointers: `$set` only when every channel is a special one, `$setOnInsert` otherwise. ## @langchain/langgraph-checkpoint-postgres@1.0.3 ### Patch Changes - [#2512](#2512) [`375c73f`](375c73f) Thanks [@jackjin1997](https://github.com/jackjin1997)! - fix: reject SQL `LIKE` wildcards (`%`, `_`) and the backslash escape character in `PostgresStore` namespace labels. `BaseStore.search()` matches namespaces via `namespace_path LIKE ${prefix}%`, and these characters in caller-supplied namespace labels are interpreted as wildcards by Postgres even through a bound parameter — letting a namespace prefix of `["%"]` match every namespace in the store across tenants. `validateNamespace` now throws for these characters at all `search` / `get` / `put` entrypoints, keeping store-wide consistency. CWE-1336. ## @langchain/langgraph-checkpoint-redis@1.0.8 ### Patch Changes - [#2518](#2518) [`9182ea3`](9182ea3) Thanks [@jackjin1997](https://github.com/jackjin1997)! - fix: `RedisSaver.putWrites` now honors `WRITES_IDX_MAP`, pinning special channels (`__error__`, `__scheduled__`, `__interrupt__`, `__resume__`) to fixed negative indices in their Redis key (`checkpoint_write:…:<idx>`) instead of the call-local ordinal. Previously a mixed `putWrites([[…regular…], [INTERRUPT, …]], taskId)` placed the INTERRUPT key at the positive idx of its position in the batch, where a peer task's regular write at the same idx would overwrite it via the unconditional `JSON.SET`. The conflict-resolution clause now matches Postgres / SQLite / MongoDB: unguarded `JSON.SET` when every write is a special channel, `JSON.SET … NX` (insert-or-ignore) otherwise. ## @langchain/langgraph-checkpoint-sqlite@1.0.3 ### Patch Changes - [#2516](#2516) [`f6a6d26`](f6a6d26) Thanks [@jackjin1997](https://github.com/jackjin1997)! - fix: `SqliteSaver.putWrites` now honors `WRITES_IDX_MAP`, pinning special channels (`__error__`, `__scheduled__`, `__interrupt__`, `__resume__`) to fixed negative indices instead of the call-local ordinal. Previously a follow-up `putWrites([[INTERRUPT, …]], taskId)` for the same checkpoint silently `REPLACE`d the regular write previously stored at `idx=0` for that task, losing data. The conflict-resolution clause also now matches the Python checkpointer contract: `OR REPLACE` only when every channel is a special one (so e.g. INTERRUPT→RESUME state transitions overwrite), `OR IGNORE` otherwise. ## @langchain/angular@1.0.21 ### Patch Changes - [#2515](#2515) [`49b8c1a`](49b8c1a) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix: make AnyStream a true supertype so selector hooks need no cast A concrete `useStream<typeof agent>()` handle was not assignable to `AnyStream` because generic-computed covariant members (`toolCalls`, `values`) don't widen under `any` — `InferToolCalls<any>[]` resolves to `AssembledToolCall<…, never>[]`, narrower than a concrete handle. Override those members with their widest forms (preserving each framework's reactivity wrapper — plain arrays for React/Svelte, `ShallowRef` for Vue, `Signal` for Angular) so the message/tool/value selector hooks accept a fully-typed stream without an `as AnyStream` cast. ## @langchain/react@1.0.21 ### Patch Changes - [#2515](#2515) [`49b8c1a`](49b8c1a) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix: make AnyStream a true supertype so selector hooks need no cast A concrete `useStream<typeof agent>()` handle was not assignable to `AnyStream` because generic-computed covariant members (`toolCalls`, `values`) don't widen under `any` — `InferToolCalls<any>[]` resolves to `AssembledToolCall<…, never>[]`, narrower than a concrete handle. Override those members with their widest forms (preserving each framework's reactivity wrapper — plain arrays for React/Svelte, `ShallowRef` for Vue, `Signal` for Angular) so the message/tool/value selector hooks accept a fully-typed stream without an `as AnyStream` cast. ## @langchain/svelte@1.0.21 ### Patch Changes - [#2515](#2515) [`49b8c1a`](49b8c1a) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix: make AnyStream a true supertype so selector hooks need no cast A concrete `useStream<typeof agent>()` handle was not assignable to `AnyStream` because generic-computed covariant members (`toolCalls`, `values`) don't widen under `any` — `InferToolCalls<any>[]` resolves to `AssembledToolCall<…, never>[]`, narrower than a concrete handle. Override those members with their widest forms (preserving each framework's reactivity wrapper — plain arrays for React/Svelte, `ShallowRef` for Vue, `Signal` for Angular) so the message/tool/value selector hooks accept a fully-typed stream without an `as AnyStream` cast. ## @langchain/vue@1.0.21 ### Patch Changes - [#2515](#2515) [`49b8c1a`](49b8c1a) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix: make AnyStream a true supertype so selector hooks need no cast A concrete `useStream<typeof agent>()` handle was not assignable to `AnyStream` because generic-computed covariant members (`toolCalls`, `values`) don't widen under `any` — `InferToolCalls<any>[]` resolves to `AssembledToolCall<…, never>[]`, narrower than a concrete handle. Override those members with their widest forms (preserving each framework's reactivity wrapper — plain arrays for React/Svelte, `ShallowRef` for Vue, `Signal` for Angular) so the message/tool/value selector hooks accept a fully-typed stream without an `as AnyStream` cast. ## @example/ai-elements@0.1.36 ### Patch Changes - Updated dependencies \[[`01c67df`](01c67df), [`d12d269`](d12d269), [`a8e7659`](a8e7659), [`49b8c1a`](49b8c1a), [`9e0201d`](9e0201d), [`9b96f60`](9b96f60), [`8e06ace`](8e06ace), [`d65a920`](d65a920), [`2f6d873`](2f6d873), [`a8b0036`](a8b0036), [`4096933`](4096933), [`801d955`](801d955)]: - @langchain/langgraph@1.4.0 - @langchain/react@1.0.21 ## @examples/assistant-ui-claude@0.1.36 ### Patch Changes - Updated dependencies \[[`01c67df`](01c67df), [`d12d269`](d12d269), [`a8e7659`](a8e7659), [`49b8c1a`](49b8c1a), [`9e0201d`](9e0201d), [`9b96f60`](9b96f60), [`8e06ace`](8e06ace), [`d65a920`](d65a920), [`2f6d873`](2f6d873), [`a8b0036`](a8b0036), [`4096933`](4096933), [`801d955`](801d955)]: - @langchain/langgraph@1.4.0 - @langchain/react@1.0.21 ## @examples/ui-angular@0.0.46 ### Patch Changes - Updated dependencies \[[`01c67df`](01c67df), [`d12d269`](d12d269), [`a8e7659`](a8e7659), [`49b8c1a`](49b8c1a), [`9e0201d`](9e0201d), [`9b96f60`](9b96f60), [`8e06ace`](8e06ace), [`d65a920`](d65a920), [`2f6d873`](2f6d873), [`a8b0036`](a8b0036), [`4096933`](4096933), [`801d955`](801d955)]: - @langchain/langgraph@1.4.0 - @langchain/angular@1.0.21 ## @examples/ui-multimodal@0.0.22 ### Patch Changes - Updated dependencies \[[`01c67df`](01c67df), [`d12d269`](d12d269), [`a8e7659`](a8e7659), [`49b8c1a`](49b8c1a), [`9e0201d`](9e0201d), [`9b96f60`](9b96f60), [`8e06ace`](8e06ace), [`d65a920`](d65a920), [`2f6d873`](2f6d873), [`a8b0036`](a8b0036), [`4096933`](4096933), [`801d955`](801d955)]: - @langchain/langgraph@1.4.0 - @langchain/react@1.0.21 ## @examples/ui-react@0.0.22 ### Patch Changes - Updated dependencies \[[`01c67df`](01c67df), [`d12d269`](d12d269), [`a8e7659`](a8e7659), [`49b8c1a`](49b8c1a), [`9e0201d`](9e0201d), [`9b96f60`](9b96f60), [`8e06ace`](8e06ace), [`d65a920`](d65a920), [`2f6d873`](2f6d873), [`a8b0036`](a8b0036), [`4096933`](4096933), [`801d955`](801d955)]: - @langchain/langgraph@1.4.0 - @langchain/react@1.0.21 ## langgraph@1.0.40 ### Patch Changes - Updated dependencies \[[`01c67df`](01c67df), [`d12d269`](d12d269), [`a8e7659`](a8e7659), [`9e0201d`](9e0201d), [`9b96f60`](9b96f60), [`8e06ace`](8e06ace), [`d65a920`](d65a920), [`2f6d873`](2f6d873), [`a8b0036`](a8b0036), [`4096933`](4096933), [`801d955`](801d955)]: - @langchain/langgraph@1.4.0 Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

done

50979e8

github-actions Bot added the internal label May 8, 2026

Quanzheng Long (longquanzheng) changed the title ~~done~~ feat(langgraph): add default_error_handler to StateGraph.compile() May 8, 2026

Sydney Runkle (sydney-runkle) reviewed May 8, 2026

View reviewed changes

done

082c94d

Quanzheng Long (longquanzheng) changed the title ~~feat(langgraph): add default_error_handler to StateGraph.compile()~~ feat(langgraph): add set_defaults() and default_error_handler to StateGraph May 8, 2026

Sydney Runkle (sydney-runkle) previously requested changes May 9, 2026

View reviewed changes

Sydney Runkle (sydney-runkle) and others added 3 commits May 9, 2026 06:25

refactor: inline _apply_node_defaults into compile()

6212f1c

Revert "refactor(langgraph): replace set_node_defaults with StateGrap…

ceb6514

…h(node_defaults=...) and apply at add_node time" This reverts commit d04b1c4.

Quanzheng Long (longquanzheng) changed the title ~~feat(langgraph): add set_defaults() and default_error_handler to StateGraph~~ feat(langgraph): add set_node_defaults() to StateGraph May 11, 2026

Sydney Runkle (sydney-runkle) approved these changes May 11, 2026

View reviewed changes

Quanzheng Long (longquanzheng) added 3 commits May 11, 2026 14:34

apply retry/timieout to error handler

fbea83c

done

48c5baf

done

baf1945

Sydney Runkle (sydney-runkle) merged commit 3db82d5 into main May 11, 2026
67 checks passed

Sydney Runkle (sydney-runkle) deleted the long/default-err-handler branch May 11, 2026 23:37

This was referenced May 12, 2026

docs(langgraph): document StateGraph.set_node_defaults langchain-ai/docs#3955

Draft

docs(langgraph): document StateGraph.set_node_defaults() on fault-tolerance langchain-ai/docs#3974

Draft

langsmith-fleet Bot mentioned this pull request May 19, 2026

Add set_node_defaults section to LangGraph fault tolerance page langchain-ai/docs#4081

Merged

This was referenced Jun 10, 2026

chore: version packages langchain-ai/langgraphjs#2513

Merged

chore: version packages mexicanamerican/langgraphjs#17

Open

github-actions Bot mentioned this pull request Jun 10, 2026

chore: version packages praxstack/langchain-ai-langgraphjs#2

Open

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

feat(langgraph): add set_node_defaults() to StateGraph#7747

feat(langgraph): add set_node_defaults() to StateGraph#7747
Sydney Runkle (sydney-runkle) merged 9 commits into
mainfrom
long/default-err-handler

Quanzheng Long (longquanzheng) commented May 8, 2026 •

edited

Loading

Uh oh!

Sydney Runkle (sydney-runkle) left a comment

Uh oh!

Sydney Runkle (sydney-runkle) May 8, 2026

Uh oh!

Quanzheng Long (longquanzheng) May 8, 2026

Uh oh!

Sydney Runkle (sydney-runkle) May 9, 2026

Uh oh!

Sydney Runkle (sydney-runkle) May 9, 2026

Uh oh!

Sydney Runkle (sydney-runkle) May 9, 2026

Uh oh!

Sydney Runkle (sydney-runkle) commented May 9, 2026

Uh oh!

Sydney Runkle (sydney-runkle) commented May 9, 2026

Uh oh!

Sydney Runkle (sydney-runkle) left a comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Conversation

Quanzheng Long (longquanzheng) commented May 8, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Supported defaults

Changes

Verification

Uh oh!

Sydney Runkle (sydney-runkle) left a comment

Choose a reason for hiding this comment

Uh oh!

Sydney Runkle (sydney-runkle) May 8, 2026

Choose a reason for hiding this comment

Uh oh!

Quanzheng Long (longquanzheng) May 8, 2026

Choose a reason for hiding this comment

Uh oh!

Sydney Runkle (sydney-runkle) May 9, 2026

Choose a reason for hiding this comment

Uh oh!

Sydney Runkle (sydney-runkle) May 9, 2026

Choose a reason for hiding this comment

Uh oh!

Sydney Runkle (sydney-runkle) May 9, 2026

Choose a reason for hiding this comment

Uh oh!

Sydney Runkle (sydney-runkle) commented May 9, 2026

Uh oh!

Sydney Runkle (sydney-runkle) commented May 9, 2026

Uh oh!

Sydney Runkle (sydney-runkle) left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Quanzheng Long (longquanzheng) commented May 8, 2026 •

edited

Loading