feat(langgraph): add node-level error handlers by longquanzheng · Pull Request #7233 · langchain-ai/langgraph

Quanzheng Long (longquanzheng) · 2026-03-20T20:57:23Z

Why this matters

Today, an unhandled exception in a node aborts the whole graph run, even if the failure is recoverable. The only built-in recovery is RetryPolicy, which can't compensate, fan out to a recovery branch, or surface a structured error to downstream logic.

Wrapping the node body in try/except isn't a real substitute either: most fallible nodes want to retry on retryable errors first (with backoff, jitter, classification) and only then handle the residual failure. Reimplementing RetryPolicy semantics inside every fallible node — and keeping it in sync as the policy evolves — is exactly the boilerplate RetryPolicy was meant to remove. A handler that runs after the configured retry policy is exhausted is the missing piece.

This PR adds first-class node-level error handlers so failure handling is colocated with the failing node configuration:

graph.add_node("name", func, error_handler=handler_func, retry_policy=...)
handler runs only after retry_policy is exhausted, so retry and handling stay decoupled
handler receives the failed node's name and exception via a typed error: NodeError parameter
handler can update state and route via Command(goto=...) for Saga / compensation flows

What changed

Added node-level handler binding on StateGraph.add_node(..., error_handler=...).
Introduced langgraph.errors.NodeError(node, error), a frozen dataclass injected into handler signatures by type annotation (error: NodeError). Keeps per-task failure context out of the long-lived Runtime object.
Plumbed failure context through a dedicated CONFIG_KEY_NODE_ERROR configurable key.
Added task-scoped reserved write key ERROR_SOURCE_NODE for checkpointed failure provenance, so handlers see the same context after resume.
Added per-node node_error_handler_map wiring through Pregel compile/runtime.
Added sync/async tests covering retry exhaustion, Command routing, handler-side failures, subgraph failures, checkpoint resume, and concurrent-with-interrupt() safety.

Intended usage

from typing_extensions import TypedDict
from langgraph.errors import NodeError
from langgraph.graph import START, StateGraph
from langgraph.types import Command, RetryPolicy


class State(TypedDict):
    status: str


def reserve_inventory(state: State) -> State:
    return {"status": "reserved"}


def charge_payment(state: State) -> State:
    raise RuntimeError("payment timeout")


def payment_error_handler(state: State, error: NodeError) -> Command:
    # per-task failure context, injected by type annotation;
    # only invoked after `retry_policy` is exhausted
    return Command(
        update={"status": f"compensated_after_{error.node}: {error.error}"},
        goto="finalize",
    )


def finalize(state: State) -> State:
    return state


graph = (
    StateGraph(State)
    .add_node("reserve_inventory", reserve_inventory)
    .add_node(
        "charge_payment",
        charge_payment,
        retry_policy=RetryPolicy(max_attempts=3, retry_on=ConnectionError),
        error_handler=payment_error_handler,
    )
    .add_node("finalize", finalize)
    .add_edge(START, "reserve_inventory")
    .add_edge("reserve_inventory", "charge_payment")
    .compile()
)

The error: NodeError parameter is opt-in: handlers that don't need failure context can keep the simpler (state) or (state, runtime) signatures.

Validation

Executed in libs/langgraph:

make format
make lint
make test

All passing.

Quanzheng Long (longquanzheng) · 2026-04-29T16:36:36Z

Copilot please resolve the conflict

Copilot · 2026-04-29T16:37:39Z

Copilot please resolve the conflict

The merge conflict has been resolved — commit 06774fc merges origin/main into this branch. The latest CI run is also passing.

…current execution The error handler routing in the sync/async concurrent runners was catching GraphBubbleUp exceptions (including GraphInterrupt from interrupt()), silently routing them to the error handler instead of letting them bubble up to pause execution. Add isinstance check to exclude GraphBubbleUp from error handler routing. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Replace graph-level error handler wiring with per-node `error_handler` on `add_node`, route failures to handlers with singular runtime context fields, and remove GRAPH_ERROR_INFO channel usage while preserving retry, subgraph, checkpoint-resume, and interrupt behavior. Made-with: Cursor

Avoid concurrent writes to the same state key in interrupt coverage tests so they validate GraphBubbleUp handling instead of failing with InvalidUpdateError. Made-with: Cursor

Skip async interrupt concurrency coverage on Python runtimes that do not support contextvars-based get_config in async contexts. Made-with: Cursor

Replace `runtime.execution_info.from_node_name`/`from_node_error` with a `NodeError(node, error)` dataclass injected into handler signatures by type annotation (`error: NodeError`). Plumbs failure context through a dedicated `CONFIG_KEY_NODE_ERROR` configurable key instead of overloading `ExecutionInfo`, keeping per-task failure context out of the long-lived Runtime object. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

Port Python parity for node-level error handlers (langchain-ai/langgraph#7233). addNode(name, fn, { errorHandler }) registers a first-class handler that runs only after the node's retryPolicy is exhausted. The handler receives a typed NodeError { node, error }, can return a state update, and can route via Command({ goto }) for saga / compensation flows. Failure provenance is checkpointed via a reserved ERROR_SOURCE_NODE write so handlers see the same context after resume. GraphBubbleUp errors (e.g. interrupt()) are never routed to a handler, and nodes without a handler still abort the run.

`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 }`, 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. Ports the Python feature from langchain-ai/langgraph#7233.

@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>

Quanzheng Long (longquanzheng) marked this pull request as ready for review March 20, 2026 21:05

langchain-automated-triage Bot added the internal label Mar 24, 2026

Mason Daugherty (mdrxy) added the bypass-issue-check Maintainer override: skip issue-link enforcement label Mar 24, 2026

Quanzheng Long (longquanzheng) changed the title ~~feat: add graph level error handling~~ feat(langgraph): migrate graph-level to node-level error handlers Apr 9, 2026

Quanzheng Long (longquanzheng) changed the title ~~feat(langgraph): migrate graph-level to node-level error handlers~~ feat(langgraph): add node-level error handlers Apr 9, 2026

Copilot started work on behalf of Quanzheng Long (longquanzheng) April 29, 2026 16:36 View session

Copilot finished work on behalf of Quanzheng Long (longquanzheng) April 29, 2026 16:38

Quanzheng Long (longquanzheng) and others added 7 commits April 29, 2026 13:37

done

c0de9aa

done

1ea1f5c

test(langgraph): fix concurrent interrupt handler tests

cff884b

Avoid concurrent writes to the same state key in interrupt coverage tests so they validate GraphBubbleUp handling instead of failing with InvalidUpdateError. Made-with: Cursor

test(langgraph): guard async interrupt test on contextvars support

184beb8

Skip async interrupt concurrency coverage on Python runtimes that do not support contextvars-based get_config in async contexts. Made-with: Cursor

Quanzheng Long (longquanzheng) force-pushed the long/0320-graph-err-handler branch from 9fc5d58 to 3cbc07b Compare April 29, 2026 20:47

Quanzheng Long (longquanzheng) merged commit 63d8611 into main Apr 30, 2026
72 checks passed

Quanzheng Long (longquanzheng) deleted the long/0320-graph-err-handler branch April 30, 2026 04:27

This was referenced May 10, 2026

More robust error handling for nodes #6170

Open

feat(langgraph): add graph-wide default error handler fallback #7757

Closed

feat(langgraph): add graph-wide default error handler fallback gouveags/langgraph#1

Closed

Sydney Runkle (sydney-runkle) mentioned this pull request May 11, 2026

refactor(langgraph): error_handler as a policy field, not a hidden node #7770

Closed

Christian Bromann (christian-bromann) mentioned this pull request May 28, 2026

feat(langgraph): add node-level error handlers langchain-ai/langgraphjs#2451

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

Antonio Lopez (Lopez-Antonio) mentioned this pull request Jun 11, 2026

fix: enhance fault tolerance with reties, timeouts and error handlers eve-esa/agents#1

Open

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

feat(langgraph): add node-level error handlers#7233

feat(langgraph): add node-level error handlers#7233
Quanzheng Long (longquanzheng) merged 7 commits into
mainfrom
long/0320-graph-err-handler

Quanzheng Long (longquanzheng) commented Mar 20, 2026 •

edited

Loading

Uh oh!

Quanzheng Long (longquanzheng) commented Apr 29, 2026

Uh oh!

Copilot AI commented Apr 29, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

5 participants

Conversation

Quanzheng Long (longquanzheng) commented Mar 20, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Why this matters

What changed

Intended usage

Validation

Uh oh!

Quanzheng Long (longquanzheng) commented Apr 29, 2026

Uh oh!

Copilot AI commented Apr 29, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

5 participants

Quanzheng Long (longquanzheng) commented Mar 20, 2026 •

edited

Loading