mirror of
https://github.com/langchain-ai/langgraphjs.git
synced 2026-08-24 21:51:39 -04:00
@langchain/angular@1.0.30
540 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 github-actions[bot]
|
9320c37da2 |
chore: version packages (#2674)
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-sdk@1.9.29 ### Patch Changes - [#2668](https://github.com/langchain-ai/langgraphjs/pull/2668) [`f9c0e88`](https://github.com/langchain-ai/langgraphjs/commit/f9c0e885e25149fe614d7d2002c884b80ab54484) Thanks [@edenbuilds](https://github.com/edenbuilds)! - Always attach the underlying Response on HTTPError. - [#2675](https://github.com/langchain-ai/langgraphjs/pull/2675) [`3958305`](https://github.com/langchain-ai/langgraphjs/commit/3958305d3ee89419abc496f28602cf4b38f2a6b3) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(sdk): deliver input channel events on the root-bus fast path `channelProjection` with `replay: false` (the `useChannelEffect` default) compared `event.method` to channel names, so `input.requested` never matched `"input"`. Match via `inferChannel` instead, same as the slow path. - [#2677](https://github.com/langchain-ai/langgraphjs/pull/2677) [`4c0fd78`](https://github.com/langchain-ai/langgraphjs/commit/4c0fd78485e1778234ddb56c7579f8d823946f18) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(sdk): defer stream join until lazy thread create commits Hydrating an externally-minted thread id that 404s still opened `/stream/events` before `POST /commands` created the row. On langgraph_api's in-mem runtime that join is accepted but dead, so the first run delivered nothing until idle reconnect. Treat missing threads like client-minted ones and start the root pump only after dispatch succeeds. - [#2672](https://github.com/langchain-ai/langgraphjs/pull/2672) [`5be518f`](https://github.com/langchain-ai/langgraphjs/commit/5be518fe18f2497a28957dfec85522997e6df4f3) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(sdk): surface nested interrupts on stream.interrupts `input.requested` events from subgraphs/subagents were dropped live by a root-only filter, while hydrate seeded them from `state.tasks`, so HITL UIs saw nested interrupts only after reload. Mirror every namespace onto `rootStore.interrupts` (with `Interrupt.namespace`), and resolve that namespace in `respond({ interruptId })` when callers omit it. - [#2676](https://github.com/langchain-ai/langgraphjs/pull/2676) [`b3c1ceb`](https://github.com/langchain-ai/langgraphjs/commit/b3c1ceb2cc16dcb15e7a9c1178fe6ddb98e5a93f) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(sdk): resolve respond() namespace from interrupt id When callers pass `{ interruptId }` without `namespace`, look the namespace up on `thread.interrupts` instead of defaulting to root. ## @langchain/angular@1.0.30 ### Patch Changes - [#2676](https://github.com/langchain-ai/langgraphjs/pull/2676) [`b3c1ceb`](https://github.com/langchain-ai/langgraphjs/commit/b3c1ceb2cc16dcb15e7a9c1178fe6ddb98e5a93f) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(sdk): resolve respond() namespace from interrupt id When callers pass `{ interruptId }` without `namespace`, look the namespace up on `thread.interrupts` instead of defaulting to root. - Updated dependencies [[`f9c0e88`](https://github.com/langchain-ai/langgraphjs/commit/f9c0e885e25149fe614d7d2002c884b80ab54484), [`3958305`](https://github.com/langchain-ai/langgraphjs/commit/3958305d3ee89419abc496f28602cf4b38f2a6b3), [`4c0fd78`](https://github.com/langchain-ai/langgraphjs/commit/4c0fd78485e1778234ddb56c7579f8d823946f18), [`5be518f`](https://github.com/langchain-ai/langgraphjs/commit/5be518fe18f2497a28957dfec85522997e6df4f3), [`b3c1ceb`](https://github.com/langchain-ai/langgraphjs/commit/b3c1ceb2cc16dcb15e7a9c1178fe6ddb98e5a93f)]: - @langchain/langgraph-sdk@1.9.29 ## @langchain/react@1.0.30 ### Patch Changes - [#2676](https://github.com/langchain-ai/langgraphjs/pull/2676) [`b3c1ceb`](https://github.com/langchain-ai/langgraphjs/commit/b3c1ceb2cc16dcb15e7a9c1178fe6ddb98e5a93f) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(sdk): resolve respond() namespace from interrupt id When callers pass `{ interruptId }` without `namespace`, look the namespace up on `thread.interrupts` instead of defaulting to root. - Updated dependencies [[`f9c0e88`](https://github.com/langchain-ai/langgraphjs/commit/f9c0e885e25149fe614d7d2002c884b80ab54484), [`3958305`](https://github.com/langchain-ai/langgraphjs/commit/3958305d3ee89419abc496f28602cf4b38f2a6b3), [`4c0fd78`](https://github.com/langchain-ai/langgraphjs/commit/4c0fd78485e1778234ddb56c7579f8d823946f18), [`5be518f`](https://github.com/langchain-ai/langgraphjs/commit/5be518fe18f2497a28957dfec85522997e6df4f3), [`b3c1ceb`](https://github.com/langchain-ai/langgraphjs/commit/b3c1ceb2cc16dcb15e7a9c1178fe6ddb98e5a93f)]: - @langchain/langgraph-sdk@1.9.29 ## @langchain/svelte@1.0.30 ### Patch Changes - [#2676](https://github.com/langchain-ai/langgraphjs/pull/2676) [`b3c1ceb`](https://github.com/langchain-ai/langgraphjs/commit/b3c1ceb2cc16dcb15e7a9c1178fe6ddb98e5a93f) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(sdk): resolve respond() namespace from interrupt id When callers pass `{ interruptId }` without `namespace`, look the namespace up on `thread.interrupts` instead of defaulting to root. - Updated dependencies [[`f9c0e88`](https://github.com/langchain-ai/langgraphjs/commit/f9c0e885e25149fe614d7d2002c884b80ab54484), [`3958305`](https://github.com/langchain-ai/langgraphjs/commit/3958305d3ee89419abc496f28602cf4b38f2a6b3), [`4c0fd78`](https://github.com/langchain-ai/langgraphjs/commit/4c0fd78485e1778234ddb56c7579f8d823946f18), [`5be518f`](https://github.com/langchain-ai/langgraphjs/commit/5be518fe18f2497a28957dfec85522997e6df4f3), [`b3c1ceb`](https://github.com/langchain-ai/langgraphjs/commit/b3c1ceb2cc16dcb15e7a9c1178fe6ddb98e5a93f)]: - @langchain/langgraph-sdk@1.9.29 ## @langchain/vue@1.0.30 ### Patch Changes - [#2676](https://github.com/langchain-ai/langgraphjs/pull/2676) [`b3c1ceb`](https://github.com/langchain-ai/langgraphjs/commit/b3c1ceb2cc16dcb15e7a9c1178fe6ddb98e5a93f) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(sdk): resolve respond() namespace from interrupt id When callers pass `{ interruptId }` without `namespace`, look the namespace up on `thread.interrupts` instead of defaulting to root. - Updated dependencies [[`f9c0e88`](https://github.com/langchain-ai/langgraphjs/commit/f9c0e885e25149fe614d7d2002c884b80ab54484), [`3958305`](https://github.com/langchain-ai/langgraphjs/commit/3958305d3ee89419abc496f28602cf4b38f2a6b3), [`4c0fd78`](https://github.com/langchain-ai/langgraphjs/commit/4c0fd78485e1778234ddb56c7579f8d823946f18), [`5be518f`](https://github.com/langchain-ai/langgraphjs/commit/5be518fe18f2497a28957dfec85522997e6df4f3), [`b3c1ceb`](https://github.com/langchain-ai/langgraphjs/commit/b3c1ceb2cc16dcb15e7a9c1178fe6ddb98e5a93f)]: - @langchain/langgraph-sdk@1.9.29 Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> |
||
|
Christian Bromann
|
b3c1ceb2cc |
fix(sdk): resolve respond() namespace from interrupt id (#2676)
`respond(response, { interruptId })` was sending resumes with the root
namespace whenever `namespace` was omitted. For subgraph interrupts that
mis-targets the resume even though the id already uniquely identifies
the pending interrupt on the thread.
Look the namespace up from `thread.interrupts` by id (same as
`respondAll` / the no-arg path). An explicit `namespace` still
overrides; unknown ids still fall back to root.
|
||
|
Christian Bromann
|
4c0fd78485 |
fix(sdk): defer stream join until lazy thread create commits (#2677)
Hydrating an externally-minted thread id that 404s still opened `/stream/events` before `POST /commands` created the row. On langgraph_api's in-mem runtime that join is accepted but dead, so the first run delivered nothing until idle reconnect. Treat missing threads like client-minted ones and start the root pump only after dispatch succeeds. |
||
|
Christian Bromann
|
3958305d3e |
fix(sdk): deliver input channel events on the root-bus fast path (#2675)
`channelProjection` with `replay: false` (the `useChannelEffect`
default) matched root-bus events by comparing `event.method` to channel
names. That works for `values` / `messages` / etc., but input events are
`input.requested`, so subscribers to `["input"]` got nothing and no
error.
The fast path now classifies with `inferChannel`, same as the slow
subscription path.
## Test plan
- [x] `pnpm exec vitest run src/stream/projections/channel.test.ts
src/client/stream/subscription.test.ts
src/stream/projections/channel-effect.test.ts` (from `libs/sdk`)
- [x] Changeset added for affected package(s)
- [ ] `useChannelEffect(stream, ["input"], { onEvent })` on a graph that
`interrupt()`s — callback fires without needing `replay: true`
|
||
|
Christian Bromann
|
5be518fe18 |
fix(sdk): surface nested interrupts on stream.interrupts (#2672)
Nested `interrupt()` calls (subgraphs / createDeepAgent subagents) never
showed up on `useStream().interrupts` while the run was live —
`#recordRootInterrupt` early-returned on non-root namespaces — but
hydrate seeded them from `state.tasks`, so the same interrupt appeared
after a reload. Mirror every `input.requested` onto
`rootStore.interrupts` with `Interrupt.namespace`, and look that
namespace up in `respond({ interruptId })` when it isn't passed
explicitly.
|
||
|
edenbuilds
|
f9c0e885e2 |
fix(sdk): always attach Response on HTTPError (#2668)
## Summary - Always pass `includeResponse: true` when converting failed `Response` objects to `HTTPError`, so `error.response` is available without registering `onFailedResponseHook`. ## Test plan - [x] New unit test `should attach error.response without onFailedResponseHook` passes with the fix - [x] Same test fails with `response: undefined` when the fix is stashed (`git stash` A/B) - [x] Changeset for `@langchain/langgraph-sdk` Fixes #2632 Co-authored-by: edenbuilds <279970382+edenbuilds@users.noreply.github.com> |
||
|
github-actions[bot]
|
5f9915234a |
chore: version packages (#2655)
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-api@1.4.4 ### Patch Changes - [#2645](https://github.com/langchain-ai/langgraphjs/pull/2645) [`059f3b8`](https://github.com/langchain-ai/langgraphjs/commit/059f3b8200d1f2f6bd701eb26bac24675395918a) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(langgraph-api): stop wiping graph recursionLimit with undefined When a run omitted `config.recursion_limit`, the server still passed `recursionLimit: undefined` into `streamEvents`. Pregel spreads that over the graph's `withConfig` default, so agents fell back to langchain-core's 25. Omit undefined keys so bound limits (and deepagents' 10000) stick. - Updated dependencies [[`059f3b8`](https://github.com/langchain-ai/langgraphjs/commit/059f3b8200d1f2f6bd701eb26bac24675395918a)]: - @langchain/langgraph-ui@1.4.4 ## @langchain/langgraph-cli@1.4.4 ### Patch Changes - [#2645](https://github.com/langchain-ai/langgraphjs/pull/2645) [`059f3b8`](https://github.com/langchain-ai/langgraphjs/commit/059f3b8200d1f2f6bd701eb26bac24675395918a) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(langgraph-api): stop wiping graph recursionLimit with undefined When a run omitted `config.recursion_limit`, the server still passed `recursionLimit: undefined` into `streamEvents`. Pregel spreads that over the graph's `withConfig` default, so agents fell back to langchain-core's 25. Omit undefined keys so bound limits (and deepagents' 10000) stick. - Updated dependencies [[`059f3b8`](https://github.com/langchain-ai/langgraphjs/commit/059f3b8200d1f2f6bd701eb26bac24675395918a)]: - @langchain/langgraph-api@1.4.4 ## @langchain/langgraph@1.4.9 ### Patch Changes - [#2653](https://github.com/langchain-ai/langgraphjs/pull/2653) [`7880055`](https://github.com/langchain-ai/langgraphjs/commit/7880055ac7303483e424380cdd52f54cd094e311) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(langgraph): checkpoint Topic as a flat values list Match Python Topic checkpoints so Host JS graphs no longer put `__pregel_tasks: [[], []]` through the Python checkpointer. Keep reading legacy `[seen, values]` checkpoints for restore compatibility. ## @langchain/langgraph-ui@1.4.4 ### Patch Changes - [#2645](https://github.com/langchain-ai/langgraphjs/pull/2645) [`059f3b8`](https://github.com/langchain-ai/langgraphjs/commit/059f3b8200d1f2f6bd701eb26bac24675395918a) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(langgraph-api): stop wiping graph recursionLimit with undefined When a run omitted `config.recursion_limit`, the server still passed `recursionLimit: undefined` into `streamEvents`. Pregel spreads that over the graph's `withConfig` default, so agents fell back to langchain-core's 25. Omit undefined keys so bound limits (and deepagents' 10000) stick. Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> |
||
|
Christian Bromann
|
7880055ac7 |
fix(langgraph): checkpoint Topic as a flat values list (#2653)
Topic checkpoints now emit a flat values list like Python, so Host no longer sees empty `__pregel_tasks` as `[[], []]` and fails checkpointer_put. Legacy `[seen, values]` checkpoints still restore. ## Test plan - [x] `pnpm test src/tests/channels.test.ts` (langgraph-core) - [x] `pnpm exec vitest run src/tests/pregel.test.ts -t 'obtain correct channel values|PregelExecutableTasks'` - [x] Changeset added for affected package(s) |
||
|
Christian Bromann
|
059f3b8200 |
fix(langgraph-api): stop wiping graph recursionLimit with undefined (#2645)
When a run omitted `config.recursion_limit`, we still passed `recursionLimit: undefined` into `streamEvents`. Pregel merges that over the graph's `withConfig` default, so agents (including deepagents with a bound 10000) fell back to langchain-core's 25 and hit `GraphRecursionError` early. Omit undefined keys from stream/assistant config objects so bound limits stick. ## Test plan - [x] `pnpm test tests/stream.test.mts` in `libs/langgraph-api` (8 passed) - [x] Changeset added for affected package(s) |
||
|
github-actions[bot]
|
483e6df5ea |
chore: version packages (#2621)
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-sdk@1.9.28 ### Patch Changes - [#2622](https://github.com/langchain-ai/langgraphjs/pull/2622) [`cf2407a`](https://github.com/langchain-ai/langgraphjs/commit/cf2407a31657a8308312873a13863f496b34f3ca) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(sdk): clear hydrate interrupt allowlist on respond() `submit()` already cleared `#hydratedActiveInterruptIds` so a new run's live `input.requested` events were not dropped as historical. `respond()` / `respondAll()` (via `dispatchResume`) did not, so a follow-on HITL after resume never appeared on `stream.interrupt` and free-text submits could resume with the wrong payload. - [#2613](https://github.com/langchain-ai/langgraphjs/pull/2613) [`82a320f`](https://github.com/langchain-ai/langgraphjs/commit/82a320faf6876238f8bac8aa6a7c593bef2be061) Thanks [@sreeramsama](https://github.com/sreeramsama)! - Fix `useStream` crash (`TypeError: Cannot read properties of null (reading 'fetch')`) when a thread is cleared while hydration is in flight. The stale hydrate now bails immediately after the `getState()` await — it no longer applies the fetched state to the thread that was left, nor opens a reconnect via `threads.stream(null, …)`. ## @langchain/angular@1.0.29 ### Patch Changes - Updated dependencies [[`cf2407a`](https://github.com/langchain-ai/langgraphjs/commit/cf2407a31657a8308312873a13863f496b34f3ca), [`82a320f`](https://github.com/langchain-ai/langgraphjs/commit/82a320faf6876238f8bac8aa6a7c593bef2be061)]: - @langchain/langgraph-sdk@1.9.28 ## @langchain/react@1.0.29 ### Patch Changes - Updated dependencies [[`cf2407a`](https://github.com/langchain-ai/langgraphjs/commit/cf2407a31657a8308312873a13863f496b34f3ca), [`82a320f`](https://github.com/langchain-ai/langgraphjs/commit/82a320faf6876238f8bac8aa6a7c593bef2be061)]: - @langchain/langgraph-sdk@1.9.28 ## @langchain/svelte@1.0.29 ### Patch Changes - Updated dependencies [[`cf2407a`](https://github.com/langchain-ai/langgraphjs/commit/cf2407a31657a8308312873a13863f496b34f3ca), [`82a320f`](https://github.com/langchain-ai/langgraphjs/commit/82a320faf6876238f8bac8aa6a7c593bef2be061)]: - @langchain/langgraph-sdk@1.9.28 ## @langchain/vue@1.0.29 ### Patch Changes - Updated dependencies [[`cf2407a`](https://github.com/langchain-ai/langgraphjs/commit/cf2407a31657a8308312873a13863f496b34f3ca), [`82a320f`](https://github.com/langchain-ai/langgraphjs/commit/82a320faf6876238f8bac8aa6a7c593bef2be061)]: - @langchain/langgraph-sdk@1.9.28 Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> |
||
|
Christian Bromann
|
cf2407a316 |
fix(sdk): clear hydrate interrupt allowlist on respond() (#2622)
## Summary - Clear the hydrate-window interrupt allowlist in `dispatchResume()` (same as `submit()`), so `respond()` / `respondAll()` accept genuinely new live `input.requested` events from the resumed run. - Without this, a second HITL after answering the first never appeared on `stream.interrupt`, and clients could free-text `submit` into an implicit resume with the wrong payload (`KeyError: 'decisions'` on HITL middleware). - Add a regression test covering hydrate → `respond()` → follow-on interrupt id. |
||
|
Sreeram Sama
|
82a320faf6 |
fix(sdk): guard useStream hydrate reconnect against a cleared thread id (#2613)
## Summary
`useStream`'s mount-time **hydrate → reconnect** path can call
`client.threads.stream(null, …)` when the thread id is cleared while
hydration is in flight, throwing an uncaught `TypeError: Cannot read
properties of null (reading 'fetch')`. This adds a post-`await` guard in
the controller (root cause) and makes `ThreadsClient.stream` null-safe
at the boundary (defense-in-depth), plus a regression test.
## Root cause
`StreamController.hydrate()` null-guards `#currentThreadId` **before**
the `await`, then re-reads it **after** to open the reconnect, with no
re-check in between:
```ts
// controller.ts
if (this.#currentThreadId == null) { …; return; } // guard BEFORE await (L538)
…
const state = await this.#fetchHydrationState(); // getState() — async gap (L564)
…
const thread = this.#ensureThread(this.#currentThreadId, !threadActive); // L731, no re-check
```
`#ensureThread` forwards the id to `client.threads.stream(threadId, {
fetch, … })`. If `#currentThreadId` becomes `null` **during the await**
(the host clears the id, `hydrate(null)` runs, or the component unmounts
during navigation), `hydrate` resumes and calls `threads.stream(null,
{…})`. In `ThreadsClient.stream`, a non-string first arg is treated as
the **options** object, so `null` becomes `options` and `options.fetch`
throws:
```ts
// client/threads/index.ts
const { threadId, options } = typeof threadIdOrOptions === "string"
? { threadId: threadIdOrOptions, options: maybeOptions }
: { threadId: uuidv7(), options: threadIdOrOptions }; // null ⇒ options = null
const userFetch = options.fetch; // null.fetch → throw
```
## Why it's intermittent
The null has to land inside the narrow `await #fetchHydrationState()`
window, and only for an **active** thread (idle/finished threads take
the deferred path and skip `#ensureThread`). It needs a concurrent
thread-id clear (navigation/unmount) racing an in-flight hydrate — so
it's flaky, not deterministic.
## Changes
- **`stream/controller.ts` (root fix):** re-check `this.#disposed` /
`this.#currentThreadId != null` after the `await`, before
`#ensureThread(...)`. Hydration is already settled by then, so an early
return is safe. Mirrors the existing post-await guard idiom (e.g.
`controller.ts` discovery-seed path).
- **`client/threads/index.ts` (defense-in-depth):** treat a nullish
first arg as the generate-thread-id form (use the second arg as options)
instead of binding `null` to `options`.
- **`stream/controller.test.ts`:** regression test — `getState()`
resolves *after* the thread id is cleared mid-hydrate; asserts the
reconnect is never opened with a null id.
## Risk
Low. The controller guard only early-returns when there's no thread to
reconnect. The `stream` overload change preserves behavior for the
string- and object-first calls; it only fixes the nullish-first-arg
case.
## How it was found
Surfaced as a flaky teardown `pageerror` in a downstream app's
Playwright E2E (agent editor: create → chat → delete). Confirmed against
`@langchain/langgraph-sdk@1.9.27` and reproduced on `main` (this
branch).
## Notes for reviewers
- Opened as **draft**: the regression test was authored to match
existing `controller.test.ts` conventions but **not run** in my
environment (SDK deps weren't installed) — please verify it in CI /
locally.
- Either change fixes the reported crash on its own; the
`threads.stream` hardening is optional but cheap.
|
||
|
github-actions[bot]
|
afb42cd7fe |
chore: version packages (#2607)
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-sdk@1.9.27 ### Patch Changes - [#2606](https://github.com/langchain-ai/langgraphjs/pull/2606) [`fa4658c`](https://github.com/langchain-ai/langgraphjs/commit/fa4658c79489eb5fb3e38744c34a6f5bf2373831) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(sdk): omit carried `since` on SSE reconnect Protocol `seq` is connection-scoped: a new `POST /stream/events` re-numbers Redis replay from 1, so advancing `since` from observed seqs and sending it after a successful open filtered out the full history (heartbeats only). An explicit caller `since` is still sent until the stream connects (including pre-ready retries); post-connect reconnects omit `since` and rely on durable `event_id` dedup. ## @langchain/angular@1.0.28 ### Patch Changes - Updated dependencies [[`fa4658c`](https://github.com/langchain-ai/langgraphjs/commit/fa4658c79489eb5fb3e38744c34a6f5bf2373831)]: - @langchain/langgraph-sdk@1.9.27 ## @langchain/react@1.0.28 ### Patch Changes - Updated dependencies [[`fa4658c`](https://github.com/langchain-ai/langgraphjs/commit/fa4658c79489eb5fb3e38744c34a6f5bf2373831)]: - @langchain/langgraph-sdk@1.9.27 ## @langchain/svelte@1.0.28 ### Patch Changes - Updated dependencies [[`fa4658c`](https://github.com/langchain-ai/langgraphjs/commit/fa4658c79489eb5fb3e38744c34a6f5bf2373831)]: - @langchain/langgraph-sdk@1.9.27 ## @langchain/vue@1.0.28 ### Patch Changes - Updated dependencies [[`fa4658c`](https://github.com/langchain-ai/langgraphjs/commit/fa4658c79489eb5fb3e38744c34a6f5bf2373831)]: - @langchain/langgraph-sdk@1.9.27 Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> |
||
|
Christian Bromann
|
fa4658c794 |
fix(sdk): omit since on SSE reconnect (#2606)
## Summary - Stop sending body `since` on SSE (re)connect in `ProtocolSseTransportAdapter`. - Protocol `seq` is connection-scoped; a new POST re-numbers Redis history from 1, so a prior session's `since` (e.g. `146`) dropped the entire replay and left only heartbeats after QUIC/idle drops. - Clients continue to deduplicate via durable `event_id`. A durable cursor can replace this later. |
||
|
github-actions[bot]
|
3dccad1391 |
chore: version packages (#2603)
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-api@1.4.3 ### Patch Changes - Updated dependencies []: - @langchain/langgraph-ui@1.4.3 ## @langchain/langgraph-cli@1.4.3 ### Patch Changes - [#2595](https://github.com/langchain-ai/langgraphjs/pull/2595) [`dac8c2f`](https://github.com/langchain-ai/langgraphjs/commit/dac8c2fa7edfd643aa393a1d6407759b6cd8acf4) Thanks [@christian-bromann](https://github.com/christian-bromann)! - chore: bump langsmith to ^0.8.0 - Updated dependencies []: - @langchain/langgraph-api@1.4.3 ## @langchain/langgraph@1.4.8 ### Patch Changes - [#2604](https://github.com/langchain-ai/langgraphjs/pull/2604) [`42ec394`](https://github.com/langchain-ai/langgraphjs/commit/42ec39460bfe0c3be017fb043c668c3204c8a175) Thanks [@hntrl](https://github.com/hntrl)! - fix(pregel): wait for completed-superstep persistence with sync durability - Updated dependencies [[`f326b89`](https://github.com/langchain-ai/langgraphjs/commit/f326b89365043bfa846e0b428564bcafafab4aaa), [`c201256`](https://github.com/langchain-ai/langgraphjs/commit/c201256b27d55c9aa333d3d15f6ec16c2fd7de9b)]: - @langchain/langgraph-sdk@1.9.26 ## @langchain/langgraph-sdk@1.9.26 ### Patch Changes - [#2605](https://github.com/langchain-ai/langgraphjs/pull/2605) [`f326b89`](https://github.com/langchain-ai/langgraphjs/commit/f326b89365043bfa846e0b428564bcafafab4aaa) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(sdk): keep SSE reconnect enabled with custom fetch Auth/proxy fetch shims previously forced `maxReconnectAttempts: 0`, so HITL waits that lost `/stream/events` (e.g. `ERR_QUIC_PROTOCOL_ERROR`) never recovered and left `respond()`/`submit()` spinning. Fail-fast test mocks should pass `maxReconnectAttempts: 0` explicitly. Also plumbs reconnect options through framework `useStream` bindings. - [#2602](https://github.com/langchain-ai/langgraphjs/pull/2602) [`c201256`](https://github.com/langchain-ai/langgraphjs/commit/c201256b27d55c9aa333d3d15f6ec16c2fd7de9b) Thanks [@HugoDurand](https://github.com/HugoDurand)! - fix(sdk): support clearing a cron's end time via `crons.update(cronId, { endTime: null })` `CronsClient.update` now accepts `endTime: null` to clear a previously set cron end time; omitting `endTime` still leaves it unchanged. The field was typed `string`, so callers could not express "clear" even though the request already forwards an explicit `null`. ## @langchain/angular@1.0.27 ### Patch Changes - [#2605](https://github.com/langchain-ai/langgraphjs/pull/2605) [`f326b89`](https://github.com/langchain-ai/langgraphjs/commit/f326b89365043bfa846e0b428564bcafafab4aaa) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(sdk): keep SSE reconnect enabled with custom fetch Auth/proxy fetch shims previously forced `maxReconnectAttempts: 0`, so HITL waits that lost `/stream/events` (e.g. `ERR_QUIC_PROTOCOL_ERROR`) never recovered and left `respond()`/`submit()` spinning. Fail-fast test mocks should pass `maxReconnectAttempts: 0` explicitly. Also plumbs reconnect options through framework `useStream` bindings. - Updated dependencies [[`f326b89`](https://github.com/langchain-ai/langgraphjs/commit/f326b89365043bfa846e0b428564bcafafab4aaa), [`c201256`](https://github.com/langchain-ai/langgraphjs/commit/c201256b27d55c9aa333d3d15f6ec16c2fd7de9b)]: - @langchain/langgraph-sdk@1.9.26 ## @langchain/react@1.0.27 ### Patch Changes - [#2605](https://github.com/langchain-ai/langgraphjs/pull/2605) [`f326b89`](https://github.com/langchain-ai/langgraphjs/commit/f326b89365043bfa846e0b428564bcafafab4aaa) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(sdk): keep SSE reconnect enabled with custom fetch Auth/proxy fetch shims previously forced `maxReconnectAttempts: 0`, so HITL waits that lost `/stream/events` (e.g. `ERR_QUIC_PROTOCOL_ERROR`) never recovered and left `respond()`/`submit()` spinning. Fail-fast test mocks should pass `maxReconnectAttempts: 0` explicitly. Also plumbs reconnect options through framework `useStream` bindings. - Updated dependencies [[`f326b89`](https://github.com/langchain-ai/langgraphjs/commit/f326b89365043bfa846e0b428564bcafafab4aaa), [`c201256`](https://github.com/langchain-ai/langgraphjs/commit/c201256b27d55c9aa333d3d15f6ec16c2fd7de9b)]: - @langchain/langgraph-sdk@1.9.26 ## @langchain/svelte@1.0.27 ### Patch Changes - [#2605](https://github.com/langchain-ai/langgraphjs/pull/2605) [`f326b89`](https://github.com/langchain-ai/langgraphjs/commit/f326b89365043bfa846e0b428564bcafafab4aaa) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(sdk): keep SSE reconnect enabled with custom fetch Auth/proxy fetch shims previously forced `maxReconnectAttempts: 0`, so HITL waits that lost `/stream/events` (e.g. `ERR_QUIC_PROTOCOL_ERROR`) never recovered and left `respond()`/`submit()` spinning. Fail-fast test mocks should pass `maxReconnectAttempts: 0` explicitly. Also plumbs reconnect options through framework `useStream` bindings. - Updated dependencies [[`f326b89`](https://github.com/langchain-ai/langgraphjs/commit/f326b89365043bfa846e0b428564bcafafab4aaa), [`c201256`](https://github.com/langchain-ai/langgraphjs/commit/c201256b27d55c9aa333d3d15f6ec16c2fd7de9b)]: - @langchain/langgraph-sdk@1.9.26 ## @langchain/vue@1.0.27 ### Patch Changes - [#2605](https://github.com/langchain-ai/langgraphjs/pull/2605) [`f326b89`](https://github.com/langchain-ai/langgraphjs/commit/f326b89365043bfa846e0b428564bcafafab4aaa) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(sdk): keep SSE reconnect enabled with custom fetch Auth/proxy fetch shims previously forced `maxReconnectAttempts: 0`, so HITL waits that lost `/stream/events` (e.g. `ERR_QUIC_PROTOCOL_ERROR`) never recovered and left `respond()`/`submit()` spinning. Fail-fast test mocks should pass `maxReconnectAttempts: 0` explicitly. Also plumbs reconnect options through framework `useStream` bindings. - Updated dependencies [[`f326b89`](https://github.com/langchain-ai/langgraphjs/commit/f326b89365043bfa846e0b428564bcafafab4aaa), [`c201256`](https://github.com/langchain-ai/langgraphjs/commit/c201256b27d55c9aa333d3d15f6ec16c2fd7de9b)]: - @langchain/langgraph-sdk@1.9.26 ## @langchain/langgraph-ui@1.4.3 Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> |
||
|
Christian Bromann
|
f326b89365 |
fix(sdk): keep SSE reconnect enabled with custom fetch (#2605)
## Summary - Keep SSE auto-reconnect and idle-reconnect enabled when a custom `fetch` is supplied (auth/proxy shims), instead of silently forcing `maxReconnectAttempts: 0`. - Plumb `maxReconnectAttempts`, `streamIdleReconnect`, `reconnectDelayMs`, and `onReconnect` through `StreamController` and React/Vue/Svelte/Angular `useStream`. - Add transport unit coverage plus browser interrupt tests that drop `/stream/events` mid-HITL and assert `respond()` still completes. |
||
|
Hunter Lovell
|
42ec39460b |
fix(core): enforce sync durability barriers (#2604)
## Summary Makes `durability: "sync"` enforce its superstep boundary: persistence produced by a completed superstep must settle before the scheduler prepares and dispatches the next one. Previously, persistence was tracked and awaited at final cleanup but could overlap later supersteps. ## Changes - Snapshot and await the current run's tracked `putWrites()` and ordered checkpoint `put()` promises after each completed superstep when durability is `sync`. - Preserve asynchronous and exit-only durability behavior, including the existing final persistence settlement path. - Add gated `StateGraph` regression coverage for `invoke`, `stream`, and `streamEvents`, plus coverage that async mode may progress while persistence is pending. - Add a patch changeset for `@langchain/langgraph`. |
||
|
Christian Bromann
|
dac8c2fa7e |
chore: bump langsmith to ^0.8.0 (#2595)
## Description The langsmith SDK published v0.8.0. This updates the `langsmith` dependency in the workspaces that pin it via a caret range (`langgraph-cli`) to `^0.8.0` and refreshes `pnpm-lock.yaml` so the workspace packages resolve to `0.8.0`. The broad peer/dependency range in `langgraph-api` (`>=0.5.19 <1.0.0`) already permits `0.8.0` and is left unchanged, matching prior langsmith bump PRs. Transitive `langsmith` versions pulled in by published `@langchain/*` packages are left untouched. ## Test Plan - [ ] `pnpm install --frozen-lockfile` resolves without changes Made by [Open SWE](https://openswe.vercel.app/agents/019f436f-3343-7169-a06a-5f64fe70e3af) --------- Signed-off-by: Christian Bromann <git@bromann.dev> Co-authored-by: Christian Bromann <731337+christian-bromann@users.noreply.github.com> Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> |
||
|
Hugo DURAND
|
c201256b27 |
fix(sdk): support clearing cron end_time via update({ endTime: null }) (#2602)
## What & why `CronsClient.update` could not clear a cron's `end_time`. The field was typed `endTime?: string`, so a type-checked caller had no way to express "remove the end time" — even though, unlike the Python SDK, the JS request builder was already correct at runtime: it uses per-field `if (payload?.endTime !== undefined)` guards (not a `None`-strip), and `null !== undefined`, so a `null` would already be forwarded and `JSON.stringify` preserves it. So the defect was purely a **type imprecision**, and the fix is at the source — the model — rather than a workaround in the request logic: - `CronsUpdatePayload.endTime`: `string` → `string | null`. PATCH semantics are now the standard tri-state: - **omit `endTime`** → keep the existing value - **`endTime: null`** → clear it - **`endTime: "<iso>"`** → set it - `CronsCreatePayload.endTime` is intentionally left `string` — create never needs to clear. This mirrors the Python SDK change in langchain-ai/langgraph#8334 (`update(end_time=None)`), and requires an Agent Server that supports clearing `end_time` via `PATCH /runs/crons/{id}` (`end_time: null`). Against an older server, `update(id, { endTime: null })` is a harmless no-op for clearing (the server coalesces `null` back to the stored value), and a clear-only patch may 400. ## Also in this PR (unify `update()`) While here, `update()`'s payload construction is unified with the existing `create()` / `createForThread()` style: the 16 repetitive `if (payload?.X !== undefined) json.Y = payload.X` guards become a single declarative object literal. `JSON.stringify` drops `undefined` keys and keeps `null`, so the wire output is **identical** — this is a behaviour-preserving refactor, pinned by the pre-existing "only sends defined fields" / "sends all updatable fields" tests. Net −44 lines in the method. ## Test plan - [x] `vitest run` on `libs/sdk/src/client/crons/index.test.ts` — **9 passed** (8 existing + 1 new: `update(id, { endTime: null })` sends body `{ end_time: null }`), no type errors. - [x] `pnpm build` (tsc compile + `attw` + `publint`) — clean. - [x] `oxlint` — 0 warnings / 0 errors; `oxfmt --check` — clean. - [x] Changeset added (`@langchain/langgraph-sdk`: patch). |
||
|
github-actions[bot]
|
96876a4bf0 |
chore: version packages (#2583)
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-api@1.4.2 ### Patch Changes - [#2590](https://github.com/langchain-ai/langgraphjs/pull/2590) [`f71e00c`](https://github.com/langchain-ai/langgraphjs/commit/f71e00c52600a6dafacccdde1363e83c17c8d97b) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(api): inject langgraph_auth_user on protocol-v2 run.start Stamp authenticated user fields onto run config in createOrResumeRun so v2 streaming matches the REST runs API. Shared helpers also dedupe REST run config auth/header enrichment. - [#2575](https://github.com/langchain-ai/langgraphjs/pull/2575) [`e1b40c2`](https://github.com/langchain-ai/langgraphjs/commit/e1b40c29e14f8e9fb2696acc62d611e14a813f43) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(cli): support node_version 24 in langgraph.json Allow Node 24 in the CLI config schema and Docker base image resolution. The langgraphjs-api:24 image is already published from langgraph-api. - Updated dependencies [[`f71e00c`](https://github.com/langchain-ai/langgraphjs/commit/f71e00c52600a6dafacccdde1363e83c17c8d97b), [`e1b40c2`](https://github.com/langchain-ai/langgraphjs/commit/e1b40c29e14f8e9fb2696acc62d611e14a813f43)]: - @langchain/langgraph-ui@1.4.2 ## @langchain/langgraph-cli@1.4.2 ### Patch Changes - [#2590](https://github.com/langchain-ai/langgraphjs/pull/2590) [`f71e00c`](https://github.com/langchain-ai/langgraphjs/commit/f71e00c52600a6dafacccdde1363e83c17c8d97b) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(api): inject langgraph_auth_user on protocol-v2 run.start Stamp authenticated user fields onto run config in createOrResumeRun so v2 streaming matches the REST runs API. Shared helpers also dedupe REST run config auth/header enrichment. - [#2575](https://github.com/langchain-ai/langgraphjs/pull/2575) [`e1b40c2`](https://github.com/langchain-ai/langgraphjs/commit/e1b40c29e14f8e9fb2696acc62d611e14a813f43) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(cli): support node_version 24 in langgraph.json Allow Node 24 in the CLI config schema and Docker base image resolution. The langgraphjs-api:24 image is already published from langgraph-api. - Updated dependencies [[`f71e00c`](https://github.com/langchain-ai/langgraphjs/commit/f71e00c52600a6dafacccdde1363e83c17c8d97b), [`e1b40c2`](https://github.com/langchain-ai/langgraphjs/commit/e1b40c29e14f8e9fb2696acc62d611e14a813f43)]: - @langchain/langgraph-api@1.4.2 ## @langchain/langgraph-ui@1.4.2 ### Patch Changes - [#2590](https://github.com/langchain-ai/langgraphjs/pull/2590) [`f71e00c`](https://github.com/langchain-ai/langgraphjs/commit/f71e00c52600a6dafacccdde1363e83c17c8d97b) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(api): inject langgraph_auth_user on protocol-v2 run.start Stamp authenticated user fields onto run config in createOrResumeRun so v2 streaming matches the REST runs API. Shared helpers also dedupe REST run config auth/header enrichment. - [#2575](https://github.com/langchain-ai/langgraphjs/pull/2575) [`e1b40c2`](https://github.com/langchain-ai/langgraphjs/commit/e1b40c29e14f8e9fb2696acc62d611e14a813f43) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(cli): support node_version 24 in langgraph.json Allow Node 24 in the CLI config schema and Docker base image resolution. The langgraphjs-api:24 image is already published from langgraph-api. Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> |
||
|
Christian Bromann
|
f71e00c526 |
fix(api): inject langgraph_auth_user on protocol-v2 run.start (#2590)
## Summary - Inject `langgraph_auth_user`, `langgraph_auth_user_id`, and `langgraph_auth_permissions` into run config in protocol v2 `createOrResumeRun`, matching the REST `createValidRun` behavior. - Extract shared `applyAuthToRunConfig` / `applyRequestHeadersToRunConfig` helpers and use them from both REST and protocol paths. - Pass `userId` into `runs.put()` from the protocol path for parity with REST. |
||
|
Christian Bromann
|
e1b40c29e1 |
fix(cli): support node_version 24 in langgraph.json (#2575)
## Summary
- Add `"24"` to `NodeVersionSchema` in `@langchain/langgraph-cli` so
`node_version: "24"` is accepted in `langgraph.json`.
- Add config, `getBaseImage`, and `configToDocker` tests for Node 24 tag
resolution (`langchain/langgraphjs-api:24` and `{api_version}-node24`).
- Update CLI README to document supported Node versions (`"20"`, `"22"`,
`"24"`).
|
||
|
Christian Bromann
|
ad7f9beb1e | fix(ci): ignore example packages globbing the changelog | ||
|
github-actions[bot]
|
2174637623 |
chore: version packages (#2572)
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@1.4.7 ### Patch Changes - [#2571](https://github.com/langchain-ai/langgraphjs/pull/2571) [`85ba859`](https://github.com/langchain-ai/langgraphjs/commit/85ba859b6f60f4bf193d3313fa24149efe05491b) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(langgraph): drop unused zod-to-json-schema peer dependency Remove the vestigial `zod-to-json-schema` (and its `peerDependenciesMeta`/dev) declarations. JSON Schema generation now flows through `@langchain/core`'s Zod v3/v4 interop (`toJsonSchema`), so the old `zod-to-json-schema@^3.x` peer (which pins `zod@^3.24.1`) is no longer needed and was the last source of install-time peer conflicts with Zod v4. Closes [#1706](https://github.com/langchain-ai/langgraphjs/issues/1706). ## @example/ai-elements@0.1.43 ### Patch Changes - Updated dependencies \[[`85ba859`](https://github.com/langchain-ai/langgraphjs/commit/85ba859b6f60f4bf193d3313fa24149efe05491b)]: - @langchain/langgraph@1.4.7 ## @examples/assistant-ui-claude@0.1.43 ### Patch Changes - Updated dependencies \[[`85ba859`](https://github.com/langchain-ai/langgraphjs/commit/85ba859b6f60f4bf193d3313fa24149efe05491b)]: - @langchain/langgraph@1.4.7 ## @examples/ui-angular@0.0.53 ### Patch Changes - Updated dependencies \[[`85ba859`](https://github.com/langchain-ai/langgraphjs/commit/85ba859b6f60f4bf193d3313fa24149efe05491b)]: - @langchain/langgraph@1.4.7 ## @examples/ui-multimodal@0.0.29 ### Patch Changes - Updated dependencies \[[`85ba859`](https://github.com/langchain-ai/langgraphjs/commit/85ba859b6f60f4bf193d3313fa24149efe05491b)]: - @langchain/langgraph@1.4.7 ## @examples/ui-react@0.0.29 ### Patch Changes - Updated dependencies \[[`85ba859`](https://github.com/langchain-ai/langgraphjs/commit/85ba859b6f60f4bf193d3313fa24149efe05491b)]: - @langchain/langgraph@1.4.7 ## langgraph@1.0.47 ### Patch Changes - Updated dependencies \[[`85ba859`](https://github.com/langchain-ai/langgraphjs/commit/85ba859b6f60f4bf193d3313fa24149efe05491b)]: - @langchain/langgraph@1.4.7 Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> |
||
|
Christian Bromann
|
85ba859b6f |
fix(langgraph): drop unused zod-to-json-schema dependency (#2571)
## Summary - Remove the vestigial `zod-to-json-schema` peer/dev dependency from `@langchain/langgraph` (`libs/langgraph-core`) and the `langgraph` umbrella package. Nothing in source imports it anymore — graph JSON Schema generation flows through `@langchain/core/utils/json_schema`'s `toJsonSchema`, which uses Zod v4's native `toJSONSchema` with a v3 fallback. - This was the last remaining `zod@^3.24.1` peer constraint, which is what produced the install-time conflict with Zod v4 reported in #1706. - Prune the unused `zod-to-json-schema` declaration from 6 example projects (`multi_agent`, `chatbot-simulation-evaluation`, `reflection`, `rewoo`, `plan-and-execute`, `quickstart`) that declared but never used it. Kept it in `rag`, `how-tos`, and `chatbots`, whose notebooks genuinely call `zodToJsonSchema`. - Regenerate `pnpm-lock.yaml`. Fixes #1706 |
||
|
github-actions[bot]
|
86389fa3a6 |
chore: version packages (#2567)
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@1.1.3 ### Patch Changes - [#2566](https://github.com/langchain-ai/langgraphjs/pull/2566) [`091a46f`](https://github.com/langchain-ai/langgraphjs/commit/091a46f32ddd3a85ee89e35fb9ea953dfc4cf8b4) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(langgraph-checkpoint-postgres): prevent createAgent failures with PostgresSaver Add BaseCheckpointSaver.toJSON() so ConfigurableModel can stringify runnable config without traversing pg Pool timers, and default missing checkpoint maps on load/copy so resume no longer crashes on undefined versions_seen. Closes [#1808](https://github.com/langchain-ai/langgraphjs/issues/1808). ## @langchain/langgraph-checkpoint-postgres@1.0.4 ### Patch Changes - [#2566](https://github.com/langchain-ai/langgraphjs/pull/2566) [`091a46f`](https://github.com/langchain-ai/langgraphjs/commit/091a46f32ddd3a85ee89e35fb9ea953dfc4cf8b4) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(langgraph-checkpoint-postgres): prevent createAgent failures with PostgresSaver Add BaseCheckpointSaver.toJSON() so ConfigurableModel can stringify runnable config without traversing pg Pool timers, and default missing checkpoint maps on load/copy so resume no longer crashes on undefined versions_seen. Closes [#1808](https://github.com/langchain-ai/langgraphjs/issues/1808). ## @langchain/langgraph-api@1.4.1 ### Patch Changes - [#2568](https://github.com/langchain-ai/langgraphjs/pull/2568) [`38d15e2`](https://github.com/langchain-ai/langgraphjs/commit/38d15e2f1f9dded34665a602cd9311cbcf5fbefc) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(langgraph-api): support configurable TypeScript loaders in dev server Add `node_loader` to `langgraph.json` (and `LANGGRAPH_NODE_LOADER` env override) so projects using reflect-metadata can use `ts-node` (`--loader ts-node/esm`) instead of the default tsx CLI. Other loaders default to `--import`; only registered shorthands like `ts-node` use `--loader`. `--no-reload` now also disables tsx's internal watch mode. Closes [#1834](https://github.com/langchain-ai/langgraphjs/issues/1834). - Updated dependencies \[]: - @langchain/langgraph-ui@1.4.1 ## @langchain/langgraph-cli@1.4.1 ### Patch Changes - [#2568](https://github.com/langchain-ai/langgraphjs/pull/2568) [`38d15e2`](https://github.com/langchain-ai/langgraphjs/commit/38d15e2f1f9dded34665a602cd9311cbcf5fbefc) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(langgraph-api): support configurable TypeScript loaders in dev server Add `node_loader` to `langgraph.json` (and `LANGGRAPH_NODE_LOADER` env override) so projects using reflect-metadata can use `ts-node` (`--loader ts-node/esm`) instead of the default tsx CLI. Other loaders default to `--import`; only registered shorthands like `ts-node` use `--loader`. `--no-reload` now also disables tsx's internal watch mode. Closes [#1834](https://github.com/langchain-ai/langgraphjs/issues/1834). - Updated dependencies \[[`38d15e2`](https://github.com/langchain-ai/langgraphjs/commit/38d15e2f1f9dded34665a602cd9311cbcf5fbefc)]: - @langchain/langgraph-api@1.4.1 ## @langchain/langgraph@1.4.6 ### Patch Changes - [`03a0d8b`](https://github.com/langchain-ai/langgraphjs/commit/03a0d8b8632082e6dbf4a96fcf37f8f67151b74f) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(langgraph): emit valid UUIDs for exit-mode delta task_ids Exit-mode DeltaChannel writes used a step-prefixed synthetic task id that produced a 6-segment string Postgres rejects for `checkpoint_writes.task_id uuid` in LangGraph API. Embed the superstep in the first UUID group instead, matching langchain-ai/langgraph#8165. - Updated dependencies \[[`0558e47`](https://github.com/langchain-ai/langgraphjs/commit/0558e472b7697304c62cb6fe69cc3005e8e1a457), [`091a46f`](https://github.com/langchain-ai/langgraphjs/commit/091a46f32ddd3a85ee89e35fb9ea953dfc4cf8b4)]: - @langchain/langgraph-sdk@1.9.25 - @langchain/langgraph-checkpoint@1.1.3 ## @langchain/langgraph-sdk@1.9.25 ### Patch Changes - [#2565](https://github.com/langchain-ai/langgraphjs/pull/2565) [`0558e47`](https://github.com/langchain-ai/langgraphjs/commit/0558e472b7697304c62cb6fe69cc3005e8e1a457) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(sdk): bundle pure-ESM deps into CJS build to fix ERR_REQUIRE_ESM Bundle the pure-ESM dependencies `p-retry` and `p-queue` (and their transitive ESM-only deps) into the build output so the CJS artifact no longer does a top-level `require()` of an ESM module. This fixes `ERR_REQUIRE_ESM` for CommonJS consumers on Node versions where `require(ESM)` is not enabled by default (< 20.19 / < 22.12). Closes [#2562](https://github.com/langchain-ai/langgraphjs/issues/2562). ## @langchain/angular@1.0.26 ### Patch Changes - Updated dependencies \[[`0558e47`](https://github.com/langchain-ai/langgraphjs/commit/0558e472b7697304c62cb6fe69cc3005e8e1a457)]: - @langchain/langgraph-sdk@1.9.25 ## @langchain/react@1.0.26 ### Patch Changes - Updated dependencies \[[`0558e47`](https://github.com/langchain-ai/langgraphjs/commit/0558e472b7697304c62cb6fe69cc3005e8e1a457)]: - @langchain/langgraph-sdk@1.9.25 ## @langchain/svelte@1.0.26 ### Patch Changes - Updated dependencies \[[`0558e47`](https://github.com/langchain-ai/langgraphjs/commit/0558e472b7697304c62cb6fe69cc3005e8e1a457)]: - @langchain/langgraph-sdk@1.9.25 ## @langchain/vue@1.0.26 ### Patch Changes - Updated dependencies \[[`0558e47`](https://github.com/langchain-ai/langgraphjs/commit/0558e472b7697304c62cb6fe69cc3005e8e1a457)]: - @langchain/langgraph-sdk@1.9.25 ## @langchain/langgraph-ui@1.4.1 ## @example/ai-elements@0.1.42 ### Patch Changes - Updated dependencies \[[`03a0d8b`](https://github.com/langchain-ai/langgraphjs/commit/03a0d8b8632082e6dbf4a96fcf37f8f67151b74f)]: - @langchain/langgraph@1.4.6 - @langchain/react@1.0.26 ## @examples/assistant-ui-claude@0.1.42 ### Patch Changes - Updated dependencies \[[`03a0d8b`](https://github.com/langchain-ai/langgraphjs/commit/03a0d8b8632082e6dbf4a96fcf37f8f67151b74f)]: - @langchain/langgraph@1.4.6 - @langchain/react@1.0.26 ## @examples/ui-angular@0.0.52 ### Patch Changes - Updated dependencies \[[`0558e47`](https://github.com/langchain-ai/langgraphjs/commit/0558e472b7697304c62cb6fe69cc3005e8e1a457), [`03a0d8b`](https://github.com/langchain-ai/langgraphjs/commit/03a0d8b8632082e6dbf4a96fcf37f8f67151b74f)]: - @langchain/langgraph-sdk@1.9.25 - @langchain/langgraph@1.4.6 - @langchain/angular@1.0.26 ## @examples/ui-multimodal@0.0.28 ### Patch Changes - Updated dependencies \[[`03a0d8b`](https://github.com/langchain-ai/langgraphjs/commit/03a0d8b8632082e6dbf4a96fcf37f8f67151b74f)]: - @langchain/langgraph@1.4.6 - @langchain/react@1.0.26 ## @examples/ui-react@0.0.28 ### Patch Changes - Updated dependencies \[[`0558e47`](https://github.com/langchain-ai/langgraphjs/commit/0558e472b7697304c62cb6fe69cc3005e8e1a457), [`03a0d8b`](https://github.com/langchain-ai/langgraphjs/commit/03a0d8b8632082e6dbf4a96fcf37f8f67151b74f)]: - @langchain/langgraph-sdk@1.9.25 - @langchain/langgraph@1.4.6 - @langchain/react@1.0.26 ## langgraph@1.0.46 ### Patch Changes - Updated dependencies \[[`03a0d8b`](https://github.com/langchain-ai/langgraphjs/commit/03a0d8b8632082e6dbf4a96fcf37f8f67151b74f)]: - @langchain/langgraph@1.4.6 Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> |
||
|
Christian Bromann
|
03a0d8b863 |
fix(langgraph): emit valid UUIDs for exit-mode delta task_ids
Exit-mode DeltaChannel writes used a step-prefixed synthetic task id that Postgres rejects for checkpoint_writes.task_id uuid in LangGraph API. Embed the superstep in the first UUID group instead, matching langgraph#8165. |
||
|
Christian Bromann
|
38d15e2f1f |
fix(langgraph-api): support configurable TypeScript loaders in dev server (#2568)
## Summary - Add configurable TypeScript loader support for the in-memory dev server to fix reflect-metadata / `emitDecoratorMetadata` incompatibility with tsx (esbuild). - Introduce `node_loader` on Node `langgraph.json` configs and `LANGGRAPH_NODE_LOADER` env override; default remains `tsx` CLI watch mode. - Generalize non-tsx loaders to `node [--watch] --import <loader> --import preload entrypoint`, with shorthand mapping for `ts-node` → `ts-node/esm`. - Add `spawn-args` helper + unit tests; add `ts-node` as optional peer dependency of `@langchain/langgraph-api`. Fixes #1834 |
||
|
Christian Bromann
|
091a46f32d |
fix(langgraph-checkpoint-postgres): prevent createAgent failures with PostgresSaver (#2566)
## Summary
- Add `BaseCheckpointSaver.toJSON()` so runnable
`configurable.__pregel_checkpointer` can be JSON-stringified without
traversing backend clients (fixes the circular `Timeout` error when
using `createAgent` with `PostgresSaver`).
- Harden `copyCheckpoint()` and `PostgresSaver._loadCheckpoint()` to
default missing `channel_versions` and `versions_seen` to `{}`, fixing
resume crashes on `__input__` after a failed first run.
- Add unit and integration tests covering stringify safety and missing
`versions_seen` recovery.
Fixes #1808
|
||
|
Christian Bromann
|
0558e472b7 |
fix(sdk): bundle pure-ESM deps into CJS build to fix ERR_REQUIRE_ESM (#2565)
## Summary - Fix `ERR_REQUIRE_ESM` in `@langchain/langgraph-sdk` for CommonJS consumers on Node < 20.19 / < 22.12: the CJS build no longer does a top-level `require()` of the pure-ESM `p-retry`/`p-queue`. They (and their transitive ESM-only deps) are now bundled and transpiled into relative CJS chunks. - Add per-package build overrides via an optional `tsdown.config.ts`, mirroring the langchainjs convention. `internal/build` discovers and merges it (`config: false` disables tsdown's own discovery so the config's imports resolve from the package dir), and re-exports `defineConfig` from `@langchain/build` so packages get type-safe configs without depending on `tsdown` directly. - Remove the leftover `libs/checkpoint-redis/langchain.config.js` (from the old `@langchain/scripts` build) — it was the only package still carrying one and the current tsdown build ignores it. Fixes #2562 |
||
|
github-actions[bot]
|
31261c3be5 |
chore: version packages (#2558)
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-mongodb@1.4.0 ### Minor Changes - [#1928](https://github.com/langchain-ai/langgraphjs/pull/1928) [`3d7fcea`](https://github.com/langchain-ai/langgraphjs/commit/3d7fcea7d7ea7f1203d24be9df607d5a8e8717bc) Thanks [@Mihailoff](https://github.com/Mihailoff)! - Add TTL support for automatic checkpoint expiration - Add optional `ttl` parameter to MongoDBSaver (value in seconds) - Add `setup()` method to create TTL indexes on collections - Add `upserted_at` timestamp to documents when TTL is enabled - Each write refreshes TTL (expires after inactivity, not creation) ### Patch Changes - [#2556](https://github.com/langchain-ai/langgraphjs/pull/2556) [`bee3c91`](https://github.com/langchain-ai/langgraphjs/commit/bee3c91d0adc315ebde0622d8c4b1fff041c1bfd) Thanks [@mohamedkhaled4053](https://github.com/mohamedkhaled4053)! - Fix `MongoDBSaver.putWrites` throwing `MongoServerError: Invalid BulkOperation, Batch cannot be empty` when called with an empty `writes` array. This is reached by human-in-the-loop / `interrupt()` flows, where a task can complete producing zero channel writes and LangGraph calls `putWrites(config, [], taskId)`. `putWrites` now no-ops on empty writes, matching the behavior of the postgres and sqlite savers (which iterate and naturally skip empty batches). - [#2550](https://github.com/langchain-ai/langgraphjs/pull/2550) [`2b8cc2f`](https://github.com/langchain-ai/langgraphjs/commit/2b8cc2f3fd5c9d3c33b56e013292daf5d936428e) Thanks [@lazydiv](https://github.com/lazydiv)! - feat(checkpoint-mongodb): add setup() to create required indexes ## @langchain/langgraph-api@1.4.0 ### Minor Changes - [#2559](https://github.com/langchain-ai/langgraphjs/pull/2559) [`48cbdd2`](https://github.com/langchain-ai/langgraphjs/commit/48cbdd23fdf29277530f6aa05c397c9902e81206) Thanks [@christian-bromann](https://github.com/christian-bromann)! - feat(langgraph-cli): add `deploy` command for LangSmith Deployment Port the Python CLI's `langgraph deploy` workflow to `@langchain/langgraph-cli`, including local and remote build paths, deployment lifecycle subcommands (`list`, `revisions list`, `delete`, `logs`), and host-backend client utilities with tests. ### Patch Changes - [#2557](https://github.com/langchain-ai/langgraphjs/pull/2557) [`b1e856d`](https://github.com/langchain-ai/langgraphjs/commit/b1e856d987ac16148dc0872d1fecf70e659ef28e) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(langgraph-api): preserve non-empty response_metadata on protocol-v2 state messages The protocol-v2 state normalizer stripped `response_metadata` from messages, dropping data that HITL flows rely on — an interrupt's card is carried on `AIMessage.response_metadata` (e.g. `{ cards: ... }`). Non-empty `response_metadata` is now retained so the card reaches the client. - [#2557](https://github.com/langchain-ai/langgraphjs/pull/2557) [`b1e856d`](https://github.com/langchain-ai/langgraphjs/commit/b1e856d987ac16148dc0872d1fecf70e659ef28e) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(sdk): apply state update and goto alongside interrupt resume `respond(decision, { update, goto })` now maps to LangGraph's `Command(resume, update, goto)`, so a human-in-the-loop UI can commit a state update (e.g. push the interrupt card into state) in the **same superstep** as the resume — one checkpoint, no separate `updateState` write, no flicker. `@langchain/langgraph-api` forwards `update`/`goto` through `input.respond`, and `@langchain/core` message instances in `update` are serialized to dicts before transport, exactly like `submit()`. Bumps `@langchain/protocol` to `^0.0.18` for the `Goto` type. `respond`/`respondAll` also apply `update` **optimistically** (mirroring `submit()`): the pushed messages paint immediately, with stable ids minted so the resumed run's echo reconciles them in place. Without this the interrupt is cleared the instant `respond()` dispatches while the pushed card only reappears a server round-trip later — so the card would flicker in that gap. The optimistic state settles on the resumed run's terminal (pending → sent, or rolled back on a failure before any echo). User-initiated optimistic writes (`submit()` / `respond()` / `respondAll()`) now commit to the store **synchronously**, in the same tick as the triggering event, instead of being coalesced onto the next macrotask. This lets a framework render the pushed message in the **same commit** as any local UI state the caller flips alongside it (e.g. a HITL form swapping its inputs for the resolved card), so the card no longer blinks out for the one-macrotask window before the flush lands. High-frequency streaming writes keep their macrotask coalescing. - Updated dependencies \[[`48cbdd2`](https://github.com/langchain-ai/langgraphjs/commit/48cbdd23fdf29277530f6aa05c397c9902e81206)]: - @langchain/langgraph-ui@1.4.0 ## @langchain/langgraph-cli@1.4.0 ### Minor Changes - [#2559](https://github.com/langchain-ai/langgraphjs/pull/2559) [`48cbdd2`](https://github.com/langchain-ai/langgraphjs/commit/48cbdd23fdf29277530f6aa05c397c9902e81206) Thanks [@christian-bromann](https://github.com/christian-bromann)! - feat(langgraph-cli): add `deploy` command for LangSmith Deployment Port the Python CLI's `langgraph deploy` workflow to `@langchain/langgraph-cli`, including local and remote build paths, deployment lifecycle subcommands (`list`, `revisions list`, `delete`, `logs`), and host-backend client utilities with tests. ### Patch Changes - Updated dependencies \[[`48cbdd2`](https://github.com/langchain-ai/langgraphjs/commit/48cbdd23fdf29277530f6aa05c397c9902e81206), [`b1e856d`](https://github.com/langchain-ai/langgraphjs/commit/b1e856d987ac16148dc0872d1fecf70e659ef28e), [`b1e856d`](https://github.com/langchain-ai/langgraphjs/commit/b1e856d987ac16148dc0872d1fecf70e659ef28e)]: - @langchain/langgraph-api@1.4.0 ## @langchain/langgraph-ui@1.4.0 ### Minor Changes - [#2559](https://github.com/langchain-ai/langgraphjs/pull/2559) [`48cbdd2`](https://github.com/langchain-ai/langgraphjs/commit/48cbdd23fdf29277530f6aa05c397c9902e81206) Thanks [@christian-bromann](https://github.com/christian-bromann)! - feat(langgraph-cli): add `deploy` command for LangSmith Deployment Port the Python CLI's `langgraph deploy` workflow to `@langchain/langgraph-cli`, including local and remote build paths, deployment lifecycle subcommands (`list`, `revisions list`, `delete`, `logs`), and host-backend client utilities with tests. ## @langchain/langgraph@1.4.5 ### Patch Changes - [#2557](https://github.com/langchain-ai/langgraphjs/pull/2557) [`b1e856d`](https://github.com/langchain-ai/langgraphjs/commit/b1e856d987ac16148dc0872d1fecf70e659ef28e) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(sdk): apply state update and goto alongside interrupt resume `respond(decision, { update, goto })` now maps to LangGraph's `Command(resume, update, goto)`, so a human-in-the-loop UI can commit a state update (e.g. push the interrupt card into state) in the **same superstep** as the resume — one checkpoint, no separate `updateState` write, no flicker. `@langchain/langgraph-api` forwards `update`/`goto` through `input.respond`, and `@langchain/core` message instances in `update` are serialized to dicts before transport, exactly like `submit()`. Bumps `@langchain/protocol` to `^0.0.18` for the `Goto` type. `respond`/`respondAll` also apply `update` **optimistically** (mirroring `submit()`): the pushed messages paint immediately, with stable ids minted so the resumed run's echo reconciles them in place. Without this the interrupt is cleared the instant `respond()` dispatches while the pushed card only reappears a server round-trip later — so the card would flicker in that gap. The optimistic state settles on the resumed run's terminal (pending → sent, or rolled back on a failure before any echo). User-initiated optimistic writes (`submit()` / `respond()` / `respondAll()`) now commit to the store **synchronously**, in the same tick as the triggering event, instead of being coalesced onto the next macrotask. This lets a framework render the pushed message in the **same commit** as any local UI state the caller flips alongside it (e.g. a HITL form swapping its inputs for the resolved card), so the card no longer blinks out for the one-macrotask window before the flush lands. High-frequency streaming writes keep their macrotask coalescing. - Updated dependencies \[[`b1e856d`](https://github.com/langchain-ai/langgraphjs/commit/b1e856d987ac16148dc0872d1fecf70e659ef28e)]: - @langchain/langgraph-sdk@1.9.24 ## @langchain/langgraph-sdk@1.9.24 ### Patch Changes - [#2557](https://github.com/langchain-ai/langgraphjs/pull/2557) [`b1e856d`](https://github.com/langchain-ai/langgraphjs/commit/b1e856d987ac16148dc0872d1fecf70e659ef28e) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(sdk): apply state update and goto alongside interrupt resume `respond(decision, { update, goto })` now maps to LangGraph's `Command(resume, update, goto)`, so a human-in-the-loop UI can commit a state update (e.g. push the interrupt card into state) in the **same superstep** as the resume — one checkpoint, no separate `updateState` write, no flicker. `@langchain/langgraph-api` forwards `update`/`goto` through `input.respond`, and `@langchain/core` message instances in `update` are serialized to dicts before transport, exactly like `submit()`. Bumps `@langchain/protocol` to `^0.0.18` for the `Goto` type. `respond`/`respondAll` also apply `update` **optimistically** (mirroring `submit()`): the pushed messages paint immediately, with stable ids minted so the resumed run's echo reconciles them in place. Without this the interrupt is cleared the instant `respond()` dispatches while the pushed card only reappears a server round-trip later — so the card would flicker in that gap. The optimistic state settles on the resumed run's terminal (pending → sent, or rolled back on a failure before any echo). User-initiated optimistic writes (`submit()` / `respond()` / `respondAll()`) now commit to the store **synchronously**, in the same tick as the triggering event, instead of being coalesced onto the next macrotask. This lets a framework render the pushed message in the **same commit** as any local UI state the caller flips alongside it (e.g. a HITL form swapping its inputs for the resolved card), so the card no longer blinks out for the one-macrotask window before the flush lands. High-frequency streaming writes keep their macrotask coalescing. ## @langchain/angular@1.0.25 ### Patch Changes - [#2557](https://github.com/langchain-ai/langgraphjs/pull/2557) [`b1e856d`](https://github.com/langchain-ai/langgraphjs/commit/b1e856d987ac16148dc0872d1fecf70e659ef28e) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(sdk): apply state update and goto alongside interrupt resume `respond(decision, { update, goto })` now maps to LangGraph's `Command(resume, update, goto)`, so a human-in-the-loop UI can commit a state update (e.g. push the interrupt card into state) in the **same superstep** as the resume — one checkpoint, no separate `updateState` write, no flicker. `@langchain/langgraph-api` forwards `update`/`goto` through `input.respond`, and `@langchain/core` message instances in `update` are serialized to dicts before transport, exactly like `submit()`. Bumps `@langchain/protocol` to `^0.0.18` for the `Goto` type. `respond`/`respondAll` also apply `update` **optimistically** (mirroring `submit()`): the pushed messages paint immediately, with stable ids minted so the resumed run's echo reconciles them in place. Without this the interrupt is cleared the instant `respond()` dispatches while the pushed card only reappears a server round-trip later — so the card would flicker in that gap. The optimistic state settles on the resumed run's terminal (pending → sent, or rolled back on a failure before any echo). User-initiated optimistic writes (`submit()` / `respond()` / `respondAll()`) now commit to the store **synchronously**, in the same tick as the triggering event, instead of being coalesced onto the next macrotask. This lets a framework render the pushed message in the **same commit** as any local UI state the caller flips alongside it (e.g. a HITL form swapping its inputs for the resolved card), so the card no longer blinks out for the one-macrotask window before the flush lands. High-frequency streaming writes keep their macrotask coalescing. - Updated dependencies \[[`b1e856d`](https://github.com/langchain-ai/langgraphjs/commit/b1e856d987ac16148dc0872d1fecf70e659ef28e)]: - @langchain/langgraph-sdk@1.9.24 ## @langchain/react@1.0.25 ### Patch Changes - [#2557](https://github.com/langchain-ai/langgraphjs/pull/2557) [`b1e856d`](https://github.com/langchain-ai/langgraphjs/commit/b1e856d987ac16148dc0872d1fecf70e659ef28e) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(sdk): apply state update and goto alongside interrupt resume `respond(decision, { update, goto })` now maps to LangGraph's `Command(resume, update, goto)`, so a human-in-the-loop UI can commit a state update (e.g. push the interrupt card into state) in the **same superstep** as the resume — one checkpoint, no separate `updateState` write, no flicker. `@langchain/langgraph-api` forwards `update`/`goto` through `input.respond`, and `@langchain/core` message instances in `update` are serialized to dicts before transport, exactly like `submit()`. Bumps `@langchain/protocol` to `^0.0.18` for the `Goto` type. `respond`/`respondAll` also apply `update` **optimistically** (mirroring `submit()`): the pushed messages paint immediately, with stable ids minted so the resumed run's echo reconciles them in place. Without this the interrupt is cleared the instant `respond()` dispatches while the pushed card only reappears a server round-trip later — so the card would flicker in that gap. The optimistic state settles on the resumed run's terminal (pending → sent, or rolled back on a failure before any echo). User-initiated optimistic writes (`submit()` / `respond()` / `respondAll()`) now commit to the store **synchronously**, in the same tick as the triggering event, instead of being coalesced onto the next macrotask. This lets a framework render the pushed message in the **same commit** as any local UI state the caller flips alongside it (e.g. a HITL form swapping its inputs for the resolved card), so the card no longer blinks out for the one-macrotask window before the flush lands. High-frequency streaming writes keep their macrotask coalescing. - Updated dependencies \[[`b1e856d`](https://github.com/langchain-ai/langgraphjs/commit/b1e856d987ac16148dc0872d1fecf70e659ef28e)]: - @langchain/langgraph-sdk@1.9.24 ## @langchain/svelte@1.0.25 ### Patch Changes - [#2557](https://github.com/langchain-ai/langgraphjs/pull/2557) [`b1e856d`](https://github.com/langchain-ai/langgraphjs/commit/b1e856d987ac16148dc0872d1fecf70e659ef28e) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(sdk): apply state update and goto alongside interrupt resume `respond(decision, { update, goto })` now maps to LangGraph's `Command(resume, update, goto)`, so a human-in-the-loop UI can commit a state update (e.g. push the interrupt card into state) in the **same superstep** as the resume — one checkpoint, no separate `updateState` write, no flicker. `@langchain/langgraph-api` forwards `update`/`goto` through `input.respond`, and `@langchain/core` message instances in `update` are serialized to dicts before transport, exactly like `submit()`. Bumps `@langchain/protocol` to `^0.0.18` for the `Goto` type. `respond`/`respondAll` also apply `update` **optimistically** (mirroring `submit()`): the pushed messages paint immediately, with stable ids minted so the resumed run's echo reconciles them in place. Without this the interrupt is cleared the instant `respond()` dispatches while the pushed card only reappears a server round-trip later — so the card would flicker in that gap. The optimistic state settles on the resumed run's terminal (pending → sent, or rolled back on a failure before any echo). User-initiated optimistic writes (`submit()` / `respond()` / `respondAll()`) now commit to the store **synchronously**, in the same tick as the triggering event, instead of being coalesced onto the next macrotask. This lets a framework render the pushed message in the **same commit** as any local UI state the caller flips alongside it (e.g. a HITL form swapping its inputs for the resolved card), so the card no longer blinks out for the one-macrotask window before the flush lands. High-frequency streaming writes keep their macrotask coalescing. - Updated dependencies \[[`b1e856d`](https://github.com/langchain-ai/langgraphjs/commit/b1e856d987ac16148dc0872d1fecf70e659ef28e)]: - @langchain/langgraph-sdk@1.9.24 ## @langchain/vue@1.0.25 ### Patch Changes - [#2557](https://github.com/langchain-ai/langgraphjs/pull/2557) [`b1e856d`](https://github.com/langchain-ai/langgraphjs/commit/b1e856d987ac16148dc0872d1fecf70e659ef28e) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(sdk): apply state update and goto alongside interrupt resume `respond(decision, { update, goto })` now maps to LangGraph's `Command(resume, update, goto)`, so a human-in-the-loop UI can commit a state update (e.g. push the interrupt card into state) in the **same superstep** as the resume — one checkpoint, no separate `updateState` write, no flicker. `@langchain/langgraph-api` forwards `update`/`goto` through `input.respond`, and `@langchain/core` message instances in `update` are serialized to dicts before transport, exactly like `submit()`. Bumps `@langchain/protocol` to `^0.0.18` for the `Goto` type. `respond`/`respondAll` also apply `update` **optimistically** (mirroring `submit()`): the pushed messages paint immediately, with stable ids minted so the resumed run's echo reconciles them in place. Without this the interrupt is cleared the instant `respond()` dispatches while the pushed card only reappears a server round-trip later — so the card would flicker in that gap. The optimistic state settles on the resumed run's terminal (pending → sent, or rolled back on a failure before any echo). User-initiated optimistic writes (`submit()` / `respond()` / `respondAll()`) now commit to the store **synchronously**, in the same tick as the triggering event, instead of being coalesced onto the next macrotask. This lets a framework render the pushed message in the **same commit** as any local UI state the caller flips alongside it (e.g. a HITL form swapping its inputs for the resolved card), so the card no longer blinks out for the one-macrotask window before the flush lands. High-frequency streaming writes keep their macrotask coalescing. - Updated dependencies \[[`b1e856d`](https://github.com/langchain-ai/langgraphjs/commit/b1e856d987ac16148dc0872d1fecf70e659ef28e)]: - @langchain/langgraph-sdk@1.9.24 ## @example/ai-elements@0.1.41 ### Patch Changes - Updated dependencies \[[`b1e856d`](https://github.com/langchain-ai/langgraphjs/commit/b1e856d987ac16148dc0872d1fecf70e659ef28e)]: - @langchain/react@1.0.25 - @langchain/langgraph@1.4.5 ## @examples/assistant-ui-claude@0.1.41 ### Patch Changes - Updated dependencies \[[`b1e856d`](https://github.com/langchain-ai/langgraphjs/commit/b1e856d987ac16148dc0872d1fecf70e659ef28e)]: - @langchain/react@1.0.25 - @langchain/langgraph@1.4.5 ## @examples/ui-angular@0.0.51 ### Patch Changes - Updated dependencies \[[`b1e856d`](https://github.com/langchain-ai/langgraphjs/commit/b1e856d987ac16148dc0872d1fecf70e659ef28e)]: - @langchain/langgraph-sdk@1.9.24 - @langchain/angular@1.0.25 - @langchain/langgraph@1.4.5 ## @examples/ui-multimodal@0.0.27 ### Patch Changes - Updated dependencies \[[`b1e856d`](https://github.com/langchain-ai/langgraphjs/commit/b1e856d987ac16148dc0872d1fecf70e659ef28e)]: - @langchain/react@1.0.25 - @langchain/langgraph@1.4.5 ## @examples/ui-react@0.0.27 ### Patch Changes - Updated dependencies \[[`b1e856d`](https://github.com/langchain-ai/langgraphjs/commit/b1e856d987ac16148dc0872d1fecf70e659ef28e)]: - @langchain/langgraph-sdk@1.9.24 - @langchain/react@1.0.25 - @langchain/langgraph@1.4.5 ## langgraph@1.0.45 ### Patch Changes - Updated dependencies \[[`b1e856d`](https://github.com/langchain-ai/langgraphjs/commit/b1e856d987ac16148dc0872d1fecf70e659ef28e)]: - @langchain/langgraph@1.4.5 Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> |
||
|
Christian Bromann
|
48cbdd23fd |
feat(langgraph-cli): add deploy command for LangSmith Deployment (#2559)
## Summary - Add `langgraphjs deploy` to `@langchain/langgraph-cli`, porting the Python CLI's LangSmith Deployment workflow for JS projects. - Support local Docker build/push and remote source-archive upload paths, plus `deploy list`, `deploy revisions list`, `deploy delete`, and `deploy logs`. - Introduce host-backend client, archive/ignore/output helpers, and unit tests; wire the command into the CLI entrypoint and add the `ignore` dependency. Test on our deployment cookbook: ``` pnpm run deploy > js-langsmith@0.1.0 deploy /Users/christian.bromann/Sites/LangChain/deployment-cookbook/js-langsmith > langgraphjs deploy Note: 'langgraphjs deploy' is in beta. Expect frequent updates and improvements. Skipping reserved env var: LANGSMITH_API_KEY Skipping reserved env var: LANGSMITH_TENANT_ID Docker is installed but not running. Start Docker and try again. Using remote build instead. 1. Looking up deployment 'deployment-cookbook-agent' No deployment found. Will create. 2. Creating deployment 'deployment-cookbook-agent' Deployment ID: fc41ac21-0251-4caf-9f6b-e8e381520e59 3. Creating source archive Archive created (0.1 MB) 4. Requesting upload URL 5. Uploading source Uploading (0.1 MB)... 100% 6. Triggering remote build View status: https://smith.langchain.com/o/d7ca4f49-e65f-4c96-8d03-e1d713acb728/host/deployments/fc41ac21-0251-4caf-9f6b-e8e381520e59 QUEUED... (9s) AWAITING_BUILD... (18s) BUILDING... (3m 13s) AWAITING_DEPLOY... (3m 32s) DEPLOYING... (4m 50s) Deployment successful! URL: https://deployment-cookbook-agent-3569d4ef8d405f40850d56230f67258b.us.langgraph.app View status: https://smith.langchain.com/o/d7ca4f49-e65f-4c96-8d03-e1d713acb728/host/deployments/fc41ac21-0251-4caf-9f6b-e8e381520e59 ``` |
||
|
lazyDev
|
2b8cc2f3fd |
feat(checkpoint): add setup() to create required MongoDB indexes (#2550)
## Summary Fixes #2551 `MongoDBSaver` queries `checkpoints` and `checkpoint_writes` collections by `thread_id`, `checkpoint_ns`, and `checkpoint_id`, but never creates indexes on these fields. As the collections grow, every `getTuple()`, `list()`, and `putWrites()` call triggers a **full collection scan**. In production with ~450K checkpoints and ~570K checkpoint_writes, this caused: - `getState` taking **5-10 seconds** per request (scanning all 450K docs each time) - Total API response times of **30-40 seconds** instead of **3 seconds** ### Changes - Adds a `setup()` method to `MongoDBSaver` that creates a compound index `{ thread_id: 1, checkpoint_ns: 1, checkpoint_id: -1 }` on both collections - The method is idempotent (`createIndex` is a no-op when the index already exists), safe to call on every app start - Follows the same pattern as `MongoDBStore.start()` which already creates indexes ### Before / After (production, 450K checkpoints) | Metric | Before | After | |---|---|---| | Docs examined per query | 445,801 | 1 | | `checkpoints` query | 5,173ms | <10ms | | `checkpoint_writes` query | 925ms | <10ms | ### Test plan - [x] Unit test added verifying `setup()` creates indexes on both collections with correct key spec - [x] Existing integration tests pass --------- Signed-off-by: Christian Bromann <git@bromann.dev> Co-authored-by: Christian Bromann <git@bromann.dev> |
||
|
Christian Bromann
|
b1e856d987 |
feat(sdk): apply state update and goto alongside interrupt resume (#2557)
## Summary
- Add `update` and `goto` options to `respond()` across the SDK so
resolving an interrupt can apply a state update and/or directed jump in
the **same superstep** — mapped to LangGraph's `Command(resume, update,
goto)`. The canonical use case is a HITL flow that pushes the interrupt
card into state at the moment it answers, committed in one checkpoint
with no flicker.
- `@langchain/langgraph-sdk`: new `update`/`goto` fields on
`StreamRespondAllOptions`, forwarded by
`StreamController.respond`/`respondAll`; `@langchain/core` `BaseMessage`
instances under the `messagesKey` are serialized to dicts before
transport, exactly like `submit()`.
- `@langchain/langgraph-api`: forward `update`/`goto` from
`input.respond` into the run `Command` in both the protocol service and
the embedded server.
- `@langchain/react`, `@langchain/vue`, `@langchain/svelte`,
`@langchain/angular`: document the new `respond({ update, goto })`
capability (incl. `BaseMessage` examples).
- Fix: the protocol-v2 state normalizer stripped `response_metadata`,
which HITL cards ride on (`AIMessage.response_metadata`); non-empty
`response_metadata` is now preserved.
- Add React browser tests (`interrupt_card_graph` fixture via
`createAgent`) covering the approve and reject paths: the FE-pushed card
lands in committed state exactly once and persists through a slow tool
execution.
|
||
|
George Mihailov
|
3d7fcea7d7 |
feat(langgraph-checkpoint-mongodb): add TTL support for automatic checkpoint data expiration (#1928)
Add optional TTL parameter to MongoDBSaver that enables automatic
expiration of checkpoints using MongoDB's TTL indexes.
- Add `ttl` option to MongoDBSaverParams (value in seconds)
- Add `setup()` method to create TTL indexes, returns Error[] for caller
to handle failures
- Add `upserted_at` timestamp to documents when TTL is enabled
- Each write refreshes TTL (expires after inactivity, not creation)
```js
// Create checkpointer with 1-hour TTL (in seconds)
const checkpointer = new MongoDBSaver({
client,
ttl: 3600,
});
// Create TTL indexes (call on startup/deployment)
const errors = await checkpointer.setup();
if (errors.length) {
console.warn("Failed to create TTL indexes:", errors);
}
```
Fixes # (issue)
Ever growing records in database.
---------
Co-authored-by: Christian Bromann <git@bromann.dev>
Co-authored-by: Cursor <cursoragent@cursor.com>
|
||
|
Mohamed Khaled
|
bee3c91d0a |
fix(langgraph-checkpoint-mongodb): no-op putWrites on empty writes (#2556)
## Summary `MongoDBSaver.putWrites` builds a `bulkWrite` operations array from `writes` and calls `collection.bulkWrite(operations)`. When `writes` is empty, `operations` is empty and the MongoDB driver throws: ``` MongoServerError: Invalid BulkOperation, Batch cannot be empty ``` This is reached in normal operation by **human-in-the-loop / `interrupt()`** flows: when a graph interrupts to wait for input, a task can complete producing **zero channel writes**, so LangGraph calls `putWrites(config, [], taskId)` and the saver throws. The other first-party savers don't hit this — `checkpoint-postgres` and `checkpoint-sqlite` iterate over `writes`, so an empty array is a natural no-op. The sibling `store.ts` in this same package already guards its bulk write with `if (bulkOps.length > 0)`. `putWrites` was simply missing the equivalent guard. ## Fix Skip the `bulkWrite` call when there are no operations, mirroring the existing guard in `store.ts`. The guard is at the call site (not an early return), so the existing `configurable` validation is preserved. This aligns the MongoDB saver's empty-writes behavior with the postgres and sqlite savers. ## Tests - **Unit** (`checkpoints.test.ts`): asserts `putWrites(config, [], taskId)` resolves and that `bulkWrite` is **not** called. Verified to fail before the fix (`bulkWrite` was called with `[]`). - **Integration** (`checkpoints.int.test.ts`): asserts `putWrites` with empty writes resolves and persists nothing — the truest repro against the real driver. `pnpm build`, `pnpm lint`, `pnpm format:check`, and the unit suite all pass locally. A changeset is included (`@langchain/langgraph-checkpoint-mongodb` patch). ## Related Same class of HITL / `interrupt()` + `putWrites` bug previously fixed for the Redis saver: #1996 / #2026. Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |
||
|
github-actions[bot]
|
e6082e0575 |
chore: version packages (#2554)
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@1.4.4 ### Patch Changes - [#2552](https://github.com/langchain-ai/langgraphjs/pull/2552) [`d662cbb`](https://github.com/langchain-ai/langgraphjs/commit/d662cbbc63eebdf1312e57d41908da1b9018e783) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(langgraph): isolate concurrent singleton-agent invocations by thread `ensureLangGraphConfig` ignores the ambient `AsyncLocalStorage` `configurable` on root-level invokes that supply an invoke-time `thread_id` and have no nesting keys (ignoring graph-bound `.withConfig()` defaults). On a fresh top-level run the ambient `configurable` can belong to another concurrent invocation, so its keys — internal scratchpad/task-input as well as user keys like `tenant_id`/`user_id` — must not leak in; values the caller wants arrive through the explicit (bound + invoke-time) configs. Ambient nesting (`__pregel_read__`) and bound child graphs invoked from parent tasks are unaffected. This prevents cross-invocation leakage between concurrent `invoke()` calls on a shared compiled graph (e.g. BullMQ workers with `concurrency > 1`). Complements the config-merge fix that stopped shared graph-bound `metadata`/`configurable` objects from being mutated across invocations ([#2040](https://github.com/langchain-ai/langgraphjs/issues/2040)). - [#2553](https://github.com/langchain-ai/langgraphjs/pull/2553) [`1c2aa5b`](https://github.com/langchain-ai/langgraphjs/commit/1c2aa5bfeacd8b7463e3d5b6010daee26e9217e0) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(langgraph): recognize JSON-erased `Overwrite` values across runtimes `Overwrite` already survives JSON serialization in JS because `Overwrite.toJSON()` emits the canonical `{ "__overwrite__": value }` sentinel. `_getOverwriteValue` now additionally recognizes the discriminator form `{ "type": "__overwrite__", value }` produced when a typed `Overwrite` from another runtime (e.g. a Python dataclass routed through the LangGraph API server) is serialized and its type is erased. This keeps `Overwrite` (and `DeltaChannel`) semantics intact across cross-runtime JSON boundaries. These delta-channel APIs remain Beta. ## @example/ai-elements@0.1.40 ### Patch Changes - Updated dependencies \[[`d662cbb`](https://github.com/langchain-ai/langgraphjs/commit/d662cbbc63eebdf1312e57d41908da1b9018e783), [`1c2aa5b`](https://github.com/langchain-ai/langgraphjs/commit/1c2aa5bfeacd8b7463e3d5b6010daee26e9217e0)]: - @langchain/langgraph@1.4.4 ## @examples/assistant-ui-claude@0.1.40 ### Patch Changes - Updated dependencies \[[`d662cbb`](https://github.com/langchain-ai/langgraphjs/commit/d662cbbc63eebdf1312e57d41908da1b9018e783), [`1c2aa5b`](https://github.com/langchain-ai/langgraphjs/commit/1c2aa5bfeacd8b7463e3d5b6010daee26e9217e0)]: - @langchain/langgraph@1.4.4 ## @examples/ui-angular@0.0.50 ### Patch Changes - Updated dependencies \[[`d662cbb`](https://github.com/langchain-ai/langgraphjs/commit/d662cbbc63eebdf1312e57d41908da1b9018e783), [`1c2aa5b`](https://github.com/langchain-ai/langgraphjs/commit/1c2aa5bfeacd8b7463e3d5b6010daee26e9217e0)]: - @langchain/langgraph@1.4.4 ## @examples/ui-multimodal@0.0.26 ### Patch Changes - Updated dependencies \[[`d662cbb`](https://github.com/langchain-ai/langgraphjs/commit/d662cbbc63eebdf1312e57d41908da1b9018e783), [`1c2aa5b`](https://github.com/langchain-ai/langgraphjs/commit/1c2aa5bfeacd8b7463e3d5b6010daee26e9217e0)]: - @langchain/langgraph@1.4.4 ## @examples/ui-react@0.0.26 ### Patch Changes - Updated dependencies \[[`d662cbb`](https://github.com/langchain-ai/langgraphjs/commit/d662cbbc63eebdf1312e57d41908da1b9018e783), [`1c2aa5b`](https://github.com/langchain-ai/langgraphjs/commit/1c2aa5bfeacd8b7463e3d5b6010daee26e9217e0)]: - @langchain/langgraph@1.4.4 ## langgraph@1.0.44 ### Patch Changes - Updated dependencies \[[`d662cbb`](https://github.com/langchain-ai/langgraphjs/commit/d662cbbc63eebdf1312e57d41908da1b9018e783), [`1c2aa5b`](https://github.com/langchain-ai/langgraphjs/commit/1c2aa5bfeacd8b7463e3d5b6010daee26e9217e0)]: - @langchain/langgraph@1.4.4 Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> |
||
|
Christian Bromann
|
d662cbbc63 |
fix(langgraph): isolate concurrent singleton-agent invocations by thread (#2552)
## Summary - Hardens `ensureLangGraphConfig` so root-level invokes with an explicit `thread_id` (and no nesting keys) no longer inherit langgraph-internal `configurable` entries from `AsyncLocalStorage`, preventing scratchpad/`currentTaskInput` leakage between concurrent `invoke()` calls on a singleton agent. - Adds unit tests for the new ALS-skipping behavior and an end-to-end regression test that verifies checkpoint and tool state stay isolated across concurrent invocations on a shared graph with `.withConfig()`. - Complements #2531 (config merge / shared bound-config mutation fix), which was the primary cause of cross-thread contamination reported in #2040. fixes #2040 |
||
|
Christian Bromann
|
1c2aa5bfea |
fix(langgraph): recognize JSON-erased Overwrite values across runtimes (#2553)
## Summary
- JS `Overwrite` already survives JSON serialization because
`Overwrite.toJSON()` emits the canonical `{ "__overwrite__": value }`
sentinel, which `_getOverwriteValue` recognizes.
- This adds recognition of the discriminator form `{ "type":
"__overwrite__", value }` that results when a typed `Overwrite` from
another runtime (notably a Python dataclass, post
langchain-ai/langgraph#8127) is serialized through a JSON boundary and
its type is erased.
- Brings JS to full parity with Python's three-form `_get_overwrite`
(instance, sentinel dict, discriminator dict), so `Overwrite`
round-trips both directions across the JS↔Python API boundary.
Delta-channel APIs remain Beta.
|
||
|
github-actions[bot]
|
73ecaa0fb5 |
chore: version packages (#2536)
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@1.1.2 ### Patch Changes - [#2544](https://github.com/langchain-ai/langgraphjs/pull/2544) [`4487214`](https://github.com/langchain-ai/langgraphjs/commit/448721449f0801009ba76b03dd2e9c16f900bbba) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(langgraph): make concurrent DeltaChannel writes deterministic on replay Concurrent same-superstep writes to a `DeltaChannel` could reconstruct from a checkpoint differently than they were applied live, because live execution ordered them by task path while savers replayed them by task id. This fixes that divergence in two complementary ways: - Plain concurrent writes are now applied in the canonical `(task_id, idx)` order on both paths: `_applyWrites` orders them that way live, and the `getDeltaChannelHistory` walk enforces the same order so reconstruction matches live for every saver (Postgres, SQLite, MongoDB, Redis, and custom). - An `Overwrite` now wins its entire super-step: every sibling write in the same step — before AND after the `Overwrite` — is discarded, matching `BinaryOperatorAggregate`. This makes the result independent of the (unstable) ordering of concurrent fan-in writes; previously a plain write that landed after an `Overwrite` in the same step was still folded in. To keep reconstruction in sync with this `Overwrite` rule, any `DeltaChannel` that sees an `Overwrite` in a super-step is now force-snapshotted at the next checkpoint (and, under `"exit"` durability, in the final checkpoint). The post-overwrite value is materialized into `channel_values`, so a cold read seeds from that snapshot and never has to replay across the reset — making live and reconstructed state identical without changing the sparse-replay history shape. These delta-channel APIs remain Beta. - [#2531](https://github.com/langchain-ai/langgraphjs/pull/2531) [`38cfe01`](https://github.com/langchain-ai/langgraphjs/commit/38cfe01ff02490ff6bcc86c66708ef671f2e0d4b) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(langgraph): forward task metadata and name subagents via lc_agent_name `mapDebugTasks` now forwards filtered user-meaningful task config metadata (including `lc_agent_name`) onto `tasks` stream payloads. The lifecycle transformer uses that metadata to set subagent `graph_name` from `lc_agent_name` and recover `cause: { type: "toolCall", tool_call_id }` from parent tool-dispatch tasks. Adds the shared `EXCLUDED_METADATA_KEYS` constant to `@langchain/langgraph-checkpoint`. Ports langgraph#7928. ## @langchain/langgraph-checkpoint-redis@1.0.10 ### Patch Changes - [#2336](https://github.com/langchain-ai/langgraphjs/pull/2336) [`25907eb`](https://github.com/langchain-ai/langgraphjs/commit/25907eb0be25258c26327c6c68c72bc828ee1cff) Thanks [@MohMaherId](https://github.com/MohMaherId)! - fix(langgraph-checkpoint-redis): persist and reconstruct full `channel_values` across multi-node graphs. `RedisSaver.put()` delta-filters `channel_values` to only the channels written by the current node, but `getTuple()` had no reconstruction logic — unlike `PostgresSaver` — so any multi-node graph whose last node wrote a subset of channels silently lost the others. Each changed channel is now persisted as a version-keyed `checkpoint_blob:*` entry in `put()` and missing channels are reconstructed from those blobs on read. `deleteThread()` now also deletes the `checkpoint_blob:*` keys. Without this the blobs introduced above would orphan forever (memory growth) and thread deletion would be incomplete, matching `PostgresSaver.deleteThread()` parity. When `ttlConfig.refreshOnRead` is enabled, reads now refresh the TTL of the reconstructed `checkpoint_blob:*` keys alongside the checkpoint key. Otherwise a read would keep the checkpoint alive while the blobs it depends on expired, silently dropping reconstructed channels. On write, `put()` now refreshes the TTL of every blob the checkpoint references (the full `channel_versions` set), not just the channels changed by the current node, so carried-over blobs from earlier nodes expire in lockstep with the checkpoint doc. This write-side refresh is independent of `refreshOnRead`. The per-channel blob writes also now run in parallel. Known limitation: with TTL enabled, a carried-over blob can still be lost if it expires during an idle gap longer than `defaultTTL` (no read or write refreshed it in time). When that happens the channel is left cleanly absent on read rather than erroring. Fully closing this gap (re-persisting expired blobs) is tracked as a follow-up. ## @langchain/langgraph@1.4.3 ### Patch Changes - [#2544](https://github.com/langchain-ai/langgraphjs/pull/2544) [`4487214`](https://github.com/langchain-ai/langgraphjs/commit/448721449f0801009ba76b03dd2e9c16f900bbba) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(langgraph): make concurrent DeltaChannel writes deterministic on replay Concurrent same-superstep writes to a `DeltaChannel` could reconstruct from a checkpoint differently than they were applied live, because live execution ordered them by task path while savers replayed them by task id. This fixes that divergence in two complementary ways: - Plain concurrent writes are now applied in the canonical `(task_id, idx)` order on both paths: `_applyWrites` orders them that way live, and the `getDeltaChannelHistory` walk enforces the same order so reconstruction matches live for every saver (Postgres, SQLite, MongoDB, Redis, and custom). - An `Overwrite` now wins its entire super-step: every sibling write in the same step — before AND after the `Overwrite` — is discarded, matching `BinaryOperatorAggregate`. This makes the result independent of the (unstable) ordering of concurrent fan-in writes; previously a plain write that landed after an `Overwrite` in the same step was still folded in. To keep reconstruction in sync with this `Overwrite` rule, any `DeltaChannel` that sees an `Overwrite` in a super-step is now force-snapshotted at the next checkpoint (and, under `"exit"` durability, in the final checkpoint). The post-overwrite value is materialized into `channel_values`, so a cold read seeds from that snapshot and never has to replay across the reset — making live and reconstructed state identical without changing the sparse-replay history shape. These delta-channel APIs remain Beta. - [#2531](https://github.com/langchain-ai/langgraphjs/pull/2531) [`38cfe01`](https://github.com/langchain-ai/langgraphjs/commit/38cfe01ff02490ff6bcc86c66708ef671f2e0d4b) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(langgraph): merge instead of overwrite in `ensureLangGraphConfig` `ensureLangGraphConfig` now per-key merges `callbacks`, `tags`, `metadata`, and `configurable` across configs instead of last-write-wins, so values bound via `.withConfig({...})` survive when a later (e.g. invoke-time) config supplies other keys. The merged dicts are fresh objects, fixing a by-reference mutation of shared base configs. Also drops the now-redundant `combineCallbacks` workaround in `streamEvents`, which double-registered and double-fired graph-bound callbacks. - [#2531](https://github.com/langchain-ai/langgraphjs/pull/2531) [`38cfe01`](https://github.com/langchain-ai/langgraphjs/commit/38cfe01ff02490ff6bcc86c66708ef671f2e0d4b) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(langgraph): preserve namespace nesting for imperative graph invokes When a compiled graph is invoked from inside another graph's running task (e.g. a tool body calling `subAgent.invoke(...)`), the surrounding task context — including the langgraph-internal nesting keys (`__pregel_read`, `__pregel_stream`, `checkpoint_ns`, the checkpoint map) — is propagated implicitly via `AsyncLocalStorage`. The base `Runnable.stream` calls langchain-core's `ensureConfig`, which replaces the ambient `configurable` wholesale whenever the caller passes its own. Because `createAgent` always supplies a `configurable`, every tool-invoked sub-agent lost those keys, ran as a fresh root run, and had its streamed events flattened to the root namespace instead of nesting under the triggering task. `Pregel.stream` now merges the ambient `configurable` underneath the caller's (caller keys win per-key) when the ambient marks an active task (`__pregel_read` present) but the explicit `configurable` is missing it. Declared subgraph nodes (which already carry their own `__pregel_read`) and top-level runs are unaffected. - [#2537](https://github.com/langchain-ai/langgraphjs/pull/2537) [`be09666`](https://github.com/langchain-ai/langgraphjs/commit/be096663f42fe7ea9355d6c0def4854e657866d8) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(langgraph): dispatch stream messages handler inline The v3 `messages` handler (`StreamProtocolMessagesHandler`, which powers `run.messages`) only performs a synchronous `push()` onto the run's stream, but its callbacks were dispatched on LangChain's background callback queue (the default `awaitHandlers === false`). A model or tool call inside a nested or parallel task could therefore flush its `messages` chunk _after_ the Pregel loop returned and sealed the stream, where `IterableReadableWritableStream.push` silently drops chunks once closed. This surfaced as empty per-message streams (`sub.messages`) for subagents dispatched in parallel from a single tools step. The handler now sets `awaitHandlers = true` so its callbacks run inline — every push happens during the originating model/chain call while the stream is still open. This avoids the global over-wait, fake-timer deadlock, and error-path unhandled rejections that a blanket `awaitAllCallbacks()` drain before close would have introduced. - [#2531](https://github.com/langchain-ai/langgraphjs/pull/2531) [`38cfe01`](https://github.com/langchain-ai/langgraphjs/commit/38cfe01ff02490ff6bcc86c66708ef671f2e0d4b) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(langgraph): forward task metadata and name subagents via lc_agent_name `mapDebugTasks` now forwards filtered user-meaningful task config metadata (including `lc_agent_name`) onto `tasks` stream payloads. The lifecycle transformer uses that metadata to set subagent `graph_name` from `lc_agent_name` and recover `cause: { type: "toolCall", tool_call_id }` from parent tool-dispatch tasks. Adds the shared `EXCLUDED_METADATA_KEYS` constant to `@langchain/langgraph-checkpoint`. Ports langgraph#7928. - [#2549](https://github.com/langchain-ai/langgraphjs/pull/2549) [`bc667a9`](https://github.com/langchain-ai/langgraphjs/commit/bc667a998ae9909d15795387dad45048e8947219) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(langgraph): support DeltaChannel fields in StateSchema Add a `DeltaValue` state field (and a `MessagesDeltaValue` prebuilt) so a `DeltaChannel` can be declared via `StateSchema`, not just `Annotation.Root` or a raw channel map. `StateSchema` now maps `DeltaValue` to a `DeltaChannel` (forwarding `snapshotFrequency` and the value-schema default) and validates its inputs/`Overwrite` updates like `ReducedValue`. - Updated dependencies \[[`4487214`](https://github.com/langchain-ai/langgraphjs/commit/448721449f0801009ba76b03dd2e9c16f900bbba), [`2134c8a`](https://github.com/langchain-ai/langgraphjs/commit/2134c8a2c0bc8dd2ebea33e1191c8dd0c4b83236), [`38cfe01`](https://github.com/langchain-ai/langgraphjs/commit/38cfe01ff02490ff6bcc86c66708ef671f2e0d4b)]: - @langchain/langgraph-checkpoint@1.1.2 - @langchain/langgraph-sdk@1.9.23 ## @langchain/langgraph-sdk@1.9.23 ### Patch Changes - [#2545](https://github.com/langchain-ai/langgraphjs/pull/2545) [`2134c8a`](https://github.com/langchain-ai/langgraphjs/commit/2134c8a2c0bc8dd2ebea33e1191c8dd0c4b83236) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(sdk): avoid scoped stream resubscribe churn Defer final projection disposal by one microtask so framework bindings that release and immediately reacquire the same scoped projection during reactive updates keep the existing stream subscription instead of rotating through root-only and scoped SSE filters. ## @langchain/angular@1.0.24 ### Patch Changes - Updated dependencies \[[`2134c8a`](https://github.com/langchain-ai/langgraphjs/commit/2134c8a2c0bc8dd2ebea33e1191c8dd0c4b83236)]: - @langchain/langgraph-sdk@1.9.23 ## @langchain/react@1.0.24 ### Patch Changes - Updated dependencies \[[`2134c8a`](https://github.com/langchain-ai/langgraphjs/commit/2134c8a2c0bc8dd2ebea33e1191c8dd0c4b83236)]: - @langchain/langgraph-sdk@1.9.23 ## @langchain/svelte@1.0.24 ### Patch Changes - Updated dependencies \[[`2134c8a`](https://github.com/langchain-ai/langgraphjs/commit/2134c8a2c0bc8dd2ebea33e1191c8dd0c4b83236)]: - @langchain/langgraph-sdk@1.9.23 ## @langchain/vue@1.0.24 ### Patch Changes - Updated dependencies \[[`2134c8a`](https://github.com/langchain-ai/langgraphjs/commit/2134c8a2c0bc8dd2ebea33e1191c8dd0c4b83236)]: - @langchain/langgraph-sdk@1.9.23 ## @example/ai-elements@0.1.39 ### Patch Changes - Updated dependencies \[[`4487214`](https://github.com/langchain-ai/langgraphjs/commit/448721449f0801009ba76b03dd2e9c16f900bbba), [`38cfe01`](https://github.com/langchain-ai/langgraphjs/commit/38cfe01ff02490ff6bcc86c66708ef671f2e0d4b), [`38cfe01`](https://github.com/langchain-ai/langgraphjs/commit/38cfe01ff02490ff6bcc86c66708ef671f2e0d4b), [`be09666`](https://github.com/langchain-ai/langgraphjs/commit/be096663f42fe7ea9355d6c0def4854e657866d8), [`38cfe01`](https://github.com/langchain-ai/langgraphjs/commit/38cfe01ff02490ff6bcc86c66708ef671f2e0d4b), [`bc667a9`](https://github.com/langchain-ai/langgraphjs/commit/bc667a998ae9909d15795387dad45048e8947219)]: - @langchain/langgraph@1.4.3 - @langchain/react@1.0.24 ## @examples/assistant-ui-claude@0.1.39 ### Patch Changes - Updated dependencies \[[`4487214`](https://github.com/langchain-ai/langgraphjs/commit/448721449f0801009ba76b03dd2e9c16f900bbba), [`38cfe01`](https://github.com/langchain-ai/langgraphjs/commit/38cfe01ff02490ff6bcc86c66708ef671f2e0d4b), [`38cfe01`](https://github.com/langchain-ai/langgraphjs/commit/38cfe01ff02490ff6bcc86c66708ef671f2e0d4b), [`be09666`](https://github.com/langchain-ai/langgraphjs/commit/be096663f42fe7ea9355d6c0def4854e657866d8), [`38cfe01`](https://github.com/langchain-ai/langgraphjs/commit/38cfe01ff02490ff6bcc86c66708ef671f2e0d4b), [`bc667a9`](https://github.com/langchain-ai/langgraphjs/commit/bc667a998ae9909d15795387dad45048e8947219)]: - @langchain/langgraph@1.4.3 - @langchain/react@1.0.24 ## @examples/ui-angular@0.0.49 ### Patch Changes - Updated dependencies \[[`4487214`](https://github.com/langchain-ai/langgraphjs/commit/448721449f0801009ba76b03dd2e9c16f900bbba), [`38cfe01`](https://github.com/langchain-ai/langgraphjs/commit/38cfe01ff02490ff6bcc86c66708ef671f2e0d4b), [`38cfe01`](https://github.com/langchain-ai/langgraphjs/commit/38cfe01ff02490ff6bcc86c66708ef671f2e0d4b), [`2134c8a`](https://github.com/langchain-ai/langgraphjs/commit/2134c8a2c0bc8dd2ebea33e1191c8dd0c4b83236), [`be09666`](https://github.com/langchain-ai/langgraphjs/commit/be096663f42fe7ea9355d6c0def4854e657866d8), [`38cfe01`](https://github.com/langchain-ai/langgraphjs/commit/38cfe01ff02490ff6bcc86c66708ef671f2e0d4b), [`bc667a9`](https://github.com/langchain-ai/langgraphjs/commit/bc667a998ae9909d15795387dad45048e8947219)]: - @langchain/langgraph@1.4.3 - @langchain/langgraph-sdk@1.9.23 - @langchain/angular@1.0.24 ## @examples/ui-multimodal@0.0.25 ### Patch Changes - Updated dependencies \[[`4487214`](https://github.com/langchain-ai/langgraphjs/commit/448721449f0801009ba76b03dd2e9c16f900bbba), [`38cfe01`](https://github.com/langchain-ai/langgraphjs/commit/38cfe01ff02490ff6bcc86c66708ef671f2e0d4b), [`38cfe01`](https://github.com/langchain-ai/langgraphjs/commit/38cfe01ff02490ff6bcc86c66708ef671f2e0d4b), [`be09666`](https://github.com/langchain-ai/langgraphjs/commit/be096663f42fe7ea9355d6c0def4854e657866d8), [`38cfe01`](https://github.com/langchain-ai/langgraphjs/commit/38cfe01ff02490ff6bcc86c66708ef671f2e0d4b), [`bc667a9`](https://github.com/langchain-ai/langgraphjs/commit/bc667a998ae9909d15795387dad45048e8947219)]: - @langchain/langgraph@1.4.3 - @langchain/react@1.0.24 ## @examples/ui-react@0.0.25 ### Patch Changes - Updated dependencies \[[`4487214`](https://github.com/langchain-ai/langgraphjs/commit/448721449f0801009ba76b03dd2e9c16f900bbba), [`38cfe01`](https://github.com/langchain-ai/langgraphjs/commit/38cfe01ff02490ff6bcc86c66708ef671f2e0d4b), [`38cfe01`](https://github.com/langchain-ai/langgraphjs/commit/38cfe01ff02490ff6bcc86c66708ef671f2e0d4b), [`2134c8a`](https://github.com/langchain-ai/langgraphjs/commit/2134c8a2c0bc8dd2ebea33e1191c8dd0c4b83236), [`be09666`](https://github.com/langchain-ai/langgraphjs/commit/be096663f42fe7ea9355d6c0def4854e657866d8), [`38cfe01`](https://github.com/langchain-ai/langgraphjs/commit/38cfe01ff02490ff6bcc86c66708ef671f2e0d4b), [`bc667a9`](https://github.com/langchain-ai/langgraphjs/commit/bc667a998ae9909d15795387dad45048e8947219)]: - @langchain/langgraph@1.4.3 - @langchain/langgraph-sdk@1.9.23 - @langchain/react@1.0.24 ## langgraph@1.0.43 ### Patch Changes - Updated dependencies \[[`4487214`](https://github.com/langchain-ai/langgraphjs/commit/448721449f0801009ba76b03dd2e9c16f900bbba), [`38cfe01`](https://github.com/langchain-ai/langgraphjs/commit/38cfe01ff02490ff6bcc86c66708ef671f2e0d4b), [`38cfe01`](https://github.com/langchain-ai/langgraphjs/commit/38cfe01ff02490ff6bcc86c66708ef671f2e0d4b), [`be09666`](https://github.com/langchain-ai/langgraphjs/commit/be096663f42fe7ea9355d6c0def4854e657866d8), [`38cfe01`](https://github.com/langchain-ai/langgraphjs/commit/38cfe01ff02490ff6bcc86c66708ef671f2e0d4b), [`bc667a9`](https://github.com/langchain-ai/langgraphjs/commit/bc667a998ae9909d15795387dad45048e8947219)]: - @langchain/langgraph@1.4.3 Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> |
||
|
Christian Bromann
|
448721449f |
fix(langgraph): replay concurrent DeltaChannel writes in live order (#2544)
## Summary - Fix a non-deterministic divergence where a `DeltaChannel`'s reconstructed state did not match its live state when concurrent writes (notably a plain write + an `Overwrite`) were applied in the same super-step. Live execution applied concurrent writes in task-**path** order, while every checkpointer replays persisted writes in task-**id** order, so an `Overwrite` hard reset could land at a different point on reload. - `_applyWrites` (`@langchain/langgraph`) now applies concurrent `DeltaChannel` writes in the canonical `(task_id, idx)` order — the same order checkpointers replay them in. - The base `getDeltaChannelHistory` (`@langchain/langgraph-checkpoint`) now stable-sorts each ancestor checkpoint's writes by `task_id`, making reconstruction order independent of how a saver returns `pendingWrites`. This fixes Postgres, SQLite, MongoDB, Redis, and any custom saver in one place; MemorySaver was already correct via its override. |
||
|
Christian Bromann
|
bc667a998a |
fix(langgraph): support DeltaChannel fields in StateSchema (#2549)
## Summary - Add `DeltaValue<Value, Input>` (`state/values/delta.ts`), a `StateSchema` field backed by a `DeltaChannel`'s batch reducer + `snapshotFrequency` — distinct from `ReducedValue`'s single-value reducer. - Wire `DeltaValue` into `StateSchema`: `getChannels()` maps it to a `DeltaChannel` (forwarding `snapshotFrequency` and seeding the initial value from the value-schema default); `getJsonSchema()`/`getInputJsonSchema()`/`validateInput()` handle it (incl. `Overwrite`) like `ReducedValue`; and the type helpers infer `State`/`Update` correctly. - Add the `MessagesDeltaValue` prebuilt (a `DeltaChannel`-backed drop-in for `MessagesValue`); export `DeltaValue` and `MessagesDeltaValue` from `@langchain/langgraph`. - Previously `DeltaChannel` was only usable via `Annotation.Root` / raw channel maps; the `StateSchema` class and Zod paths threw. This closes the `StateSchema` gap (Zod remains a separate follow-up). |
||
|
Christian Bromann
|
2134c8a2c0 |
fix(sdk): avoid scoped stream resubscribe churn (#2545)
## Summary - Defer final `ChannelRegistry` projection disposal by one microtask so same-turn reacquires keep the existing projection runtime alive. - Preserve `registry.size` as an active-consumer diagnostic while allowing pending disposals to be cancelled. - Add regression coverage for release-then-reacquire behavior. |
||
|
Christian Bromann
|
be096663f4 |
fix(langgraph): dispatch stream messages handler inline (#2537)
## Summary - The v3 `messages` handler (`StreamProtocolMessagesHandler`) defaulted to background callback dispatch (`awaitHandlers === false`), so its synchronous `push()` onto the run stream could land after the Pregel loop sealed the stream — where `IterableReadableWritableStream.push` silently drops chunks. - This caused empty per-message streams (`sub.messages`) for subagents dispatched in parallel from a single tools step. - Fix: set `awaitHandlers = true` so the handler dispatches inline and every push happens during the originating model/chain call while the stream is still open. This avoids the global over-wait, fake-timer deadlock, and error-path unhandled rejections that a blanket `awaitAllCallbacks()` drain before `stream.close()` would have introduced. --------- Signed-off-by: Christian Bromann <git@bromann.dev> |
||
|
Christian Bromann
|
38cfe01ff0 |
fix(langgraph): merge instead of overwrite in ensureLangGraphConfig (#2531)
## Summary
- Port of langgraph#7926: `ensureLangGraphConfig` now per-key merges
`callbacks`, `tags`, `metadata`, and `configurable` across configs
instead of overwriting, so values bound via `.withConfig({...})` are
preserved when a later config (e.g. invoke-time `thread_id`) only
supplies a subset of keys. Later configs still win per key on collision.
- Merged dicts are fresh objects, fixing a by-reference mutation where
`propagateConfigurableToMetadata` could mutate a shared bound config's
`metadata` across invocations.
- Removed the now-redundant `combineCallbacks` pre-combine in
`Pregel.streamEvents` (v1/v2). Because the config merge now folds in
`this.config` callbacks, pre-combining re-registered graph-bound
handlers and double-fired them; only call-time callbacks are forwarded
now.
---------
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
|
||
|
MohMaherId
|
25907eb0be |
fix(langgraph-checkpoint-redis): add blob reconstruction for channel_values in multi-node graphs (#2336)
## Summary Fixes #2334 `RedisSaver.put()` delta-filters `channel_values` based on `newVersions`, storing only channels written by the current node. Unlike `PostgresSaver` (which stores channel blobs separately and reconstructs in `getTuple()`), `RedisSaver` had no reconstruction logic — channels not written by the last node were silently lost. This PR completes the blob storage layer: - **`put()`**: writes each changed channel as a version-keyed Redis JSON key (`checkpoint_blob:{thread_id}:{ns}:{channel}:{version}`) - **`loadCheckpointWithWrites()`**: for each channel in `channel_versions` missing from `channel_values`, looks up the blob at the recorded version and reconstructs full state The `checkpoint_blobs` RediSearch index already existed with the correct schema (`thread_id`, `checkpoint_ns`, `channel`, `version`, `type`) — it just wasn't wired up. ### Reproduction ```json { "name": "redis-checkpoint-bug", "private": true, "type": "module", "scripts": { "dev": "tsx redis-bug.ts", "dev:redis": "REDIS_URL=redis://localhost:6379 tsx redis-bug.ts" }, "dependencies": { "@langchain/core": "^1.1.40", "@langchain/langgraph": "^1.2.9", "@langchain/langgraph-checkpoint": "^1.0.1", "@langchain/langgraph-checkpoint-redis": "1.0.4" }, "devDependencies": { "tsx": "^4.19.0" } } ``` Save the reproduction code from #2334 as `redis-bug.ts`, then: ```bash docker run -d --name redis-test -p 6379:6379 redis:7-alpine pnpm install && pnpm dev:redis ``` ### Test plan - [x] Added integration test: multi-channel state where node B writes only `{status, category}` (not `messages`), verifying `messages` survives in `getTuple()` result - [x] Passes `oxfmt --check` and `oxlint` - [x] Includes changeset - [x] CI: unit tests - [x] CI: lint + format - [x] CI: build |
||
|
github-actions[bot]
|
957cac4ea4 |
chore: version packages (#2526)
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@1.1.1 ### Patch Changes - [#2527](https://github.com/langchain-ai/langgraphjs/pull/2527) [`9e114e5`](https://github.com/langchain-ai/langgraphjs/commit/9e114e55d362a874878a817740de42fd62ae9db7) Thanks [@christian-bromann](https://github.com/christian-bromann)! - chore(deps): remove uuid dependency in favor of embedded uuid in core Replace direct `uuid` package imports with `@langchain/core/utils/uuid` across langgraph packages to deduplicate dependencies and align with @langchain/core's embedded UUID utilities. ## @langchain/langgraph-checkpoint-redis@1.0.9 ### Patch Changes - [#2525](https://github.com/langchain-ai/langgraphjs/pull/2525) [`829a32a`](https://github.com/langchain-ai/langgraphjs/commit/829a32a30cc22103b1cb0aba6a027b7ccdb68447) Thanks [@lhlyu](https://github.com/lhlyu)! - Fix Redis checkpoint pending write deserialization when a write document has no `value` field. RedisJSON omits `undefined` values, so `loadPendingWrites` now restores a missing `value` as `undefined` instead of passing it through JSON parsing. - [#2527](https://github.com/langchain-ai/langgraphjs/pull/2527) [`9e114e5`](https://github.com/langchain-ai/langgraphjs/commit/9e114e55d362a874878a817740de42fd62ae9db7) Thanks [@christian-bromann](https://github.com/christian-bromann)! - chore(deps): remove uuid dependency in favor of embedded uuid in core Replace direct `uuid` package imports with `@langchain/core/utils/uuid` across langgraph packages to deduplicate dependencies and align with @langchain/core's embedded UUID utilities. ## @langchain/langgraph-api@1.3.1 ### Patch Changes - [#2527](https://github.com/langchain-ai/langgraphjs/pull/2527) [`9e114e5`](https://github.com/langchain-ai/langgraphjs/commit/9e114e55d362a874878a817740de42fd62ae9db7) Thanks [@christian-bromann](https://github.com/christian-bromann)! - chore(deps): remove uuid dependency in favor of embedded uuid in core Replace direct `uuid` package imports with `@langchain/core/utils/uuid` across langgraph packages to deduplicate dependencies and align with @langchain/core's embedded UUID utilities. - Updated dependencies \[[`9e114e5`](https://github.com/langchain-ai/langgraphjs/commit/9e114e55d362a874878a817740de42fd62ae9db7)]: - @langchain/langgraph-ui@1.3.1 ## @langchain/langgraph-cli@1.3.1 ### Patch Changes - [#2527](https://github.com/langchain-ai/langgraphjs/pull/2527) [`9e114e5`](https://github.com/langchain-ai/langgraphjs/commit/9e114e55d362a874878a817740de42fd62ae9db7) Thanks [@christian-bromann](https://github.com/christian-bromann)! - chore(deps): remove uuid dependency in favor of embedded uuid in core Replace direct `uuid` package imports with `@langchain/core/utils/uuid` across langgraph packages to deduplicate dependencies and align with @langchain/core's embedded UUID utilities. - Updated dependencies \[[`9e114e5`](https://github.com/langchain-ai/langgraphjs/commit/9e114e55d362a874878a817740de42fd62ae9db7)]: - @langchain/langgraph-api@1.3.1 ## @langchain/langgraph@1.4.2 ### Patch Changes - [#2527](https://github.com/langchain-ai/langgraphjs/pull/2527) [`9e114e5`](https://github.com/langchain-ai/langgraphjs/commit/9e114e55d362a874878a817740de42fd62ae9db7) Thanks [@christian-bromann](https://github.com/christian-bromann)! - chore(deps): remove uuid dependency in favor of embedded uuid in core Replace direct `uuid` package imports with `@langchain/core/utils/uuid` across langgraph packages to deduplicate dependencies and align with @langchain/core's embedded UUID utilities. - Updated dependencies \[[`ba31f04`](https://github.com/langchain-ai/langgraphjs/commit/ba31f045d1d458a456c6f6441e8ee81d32c5c700), [`e7e8035`](https://github.com/langchain-ai/langgraphjs/commit/e7e8035fadca5f0d4cbc55bbbb77e65878ab2952), [`9e114e5`](https://github.com/langchain-ai/langgraphjs/commit/9e114e55d362a874878a817740de42fd62ae9db7)]: - @langchain/langgraph-sdk@1.9.22 - @langchain/langgraph-checkpoint@1.1.1 ## @langchain/langgraph-supervisor@1.1.1 ### Patch Changes - [#2527](https://github.com/langchain-ai/langgraphjs/pull/2527) [`9e114e5`](https://github.com/langchain-ai/langgraphjs/commit/9e114e55d362a874878a817740de42fd62ae9db7) Thanks [@christian-bromann](https://github.com/christian-bromann)! - chore(deps): remove uuid dependency in favor of embedded uuid in core Replace direct `uuid` package imports with `@langchain/core/utils/uuid` across langgraph packages to deduplicate dependencies and align with @langchain/core's embedded UUID utilities. ## @langchain/langgraph-ui@1.3.1 ### Patch Changes - [#2527](https://github.com/langchain-ai/langgraphjs/pull/2527) [`9e114e5`](https://github.com/langchain-ai/langgraphjs/commit/9e114e55d362a874878a817740de42fd62ae9db7) Thanks [@christian-bromann](https://github.com/christian-bromann)! - chore(deps): remove uuid dependency in favor of embedded uuid in core Replace direct `uuid` package imports with `@langchain/core/utils/uuid` across langgraph packages to deduplicate dependencies and align with @langchain/core's embedded UUID utilities. ## @langchain/langgraph-sdk@1.9.22 ### Patch Changes - [#2529](https://github.com/langchain-ai/langgraphjs/pull/2529) [`ba31f04`](https://github.com/langchain-ai/langgraphjs/commit/ba31f045d1d458a456c6f6441e8ee81d32c5c700) Thanks [@christian-bromann](https://github.com/christian-bromann)! - fix(sdk): reconnect SSE streams when heartbeat idle is detected Detect half-open SSE connections by watching for server keep-alive heartbeats (`: heartbeat`) and reconnecting with Last-Event-ID or `since` when they stop. `"auto"` mode arms only after heartbeats are observed, so long tool calls and HITL pauses do not false-fire on heartbeat-emitting servers. - [#2528](https://github.com/langchain-ai/langgraphjs/pull/2528) [`e7e8035`](https://github.com/langchain-ai/langgraphjs/commit/e7e8035fadca5f0d4cbc55bbbb77e65878ab2952) Thanks [@christian-bromann](https://github.com/christian-bromann)! - Allow custom `AgentServerAdapter`s to be late-bound and re-bound to a thread. Adapters can now implement an optional `setThreadId(threadId)`, which `client.threads.stream(threadId, { transport })` calls when binding the active thread — including the lazily-minted id from the first `submit()` on a `threadId: null` controller. The built-in `ProtocolSseTransportAdapter`, `ProtocolWebSocketTransportAdapter`, and `HttpAgentServerAdapter` implement it: `threadId` is now optional at construction, request URLs derive from the currently-bound thread, and `paths` entries may be functions of the thread id (`(threadId) => string`). This lets a single custom transport back a lazy thread-creation flow instead of being pinned to one thread at construction. - [#2527](https://github.com/langchain-ai/langgraphjs/pull/2527) [`9e114e5`](https://github.com/langchain-ai/langgraphjs/commit/9e114e55d362a874878a817740de42fd62ae9db7) Thanks [@christian-bromann](https://github.com/christian-bromann)! - chore(deps): remove uuid dependency in favor of embedded uuid in core Replace direct `uuid` package imports with `@langchain/core/utils/uuid` across langgraph packages to deduplicate dependencies and align with @langchain/core's embedded UUID utilities. ## @langchain/angular@1.0.23 ### Patch Changes - Updated dependencies \[[`ba31f04`](https://github.com/langchain-ai/langgraphjs/commit/ba31f045d1d458a456c6f6441e8ee81d32c5c700), [`e7e8035`](https://github.com/langchain-ai/langgraphjs/commit/e7e8035fadca5f0d4cbc55bbbb77e65878ab2952), [`9e114e5`](https://github.com/langchain-ai/langgraphjs/commit/9e114e55d362a874878a817740de42fd62ae9db7)]: - @langchain/langgraph-sdk@1.9.22 ## @langchain/react@1.0.23 ### Patch Changes - Updated dependencies \[[`ba31f04`](https://github.com/langchain-ai/langgraphjs/commit/ba31f045d1d458a456c6f6441e8ee81d32c5c700), [`e7e8035`](https://github.com/langchain-ai/langgraphjs/commit/e7e8035fadca5f0d4cbc55bbbb77e65878ab2952), [`9e114e5`](https://github.com/langchain-ai/langgraphjs/commit/9e114e55d362a874878a817740de42fd62ae9db7)]: - @langchain/langgraph-sdk@1.9.22 ## @langchain/svelte@1.0.23 ### Patch Changes - Updated dependencies \[[`ba31f04`](https://github.com/langchain-ai/langgraphjs/commit/ba31f045d1d458a456c6f6441e8ee81d32c5c700), [`e7e8035`](https://github.com/langchain-ai/langgraphjs/commit/e7e8035fadca5f0d4cbc55bbbb77e65878ab2952), [`9e114e5`](https://github.com/langchain-ai/langgraphjs/commit/9e114e55d362a874878a817740de42fd62ae9db7)]: - @langchain/langgraph-sdk@1.9.22 ## @langchain/vue@1.0.23 ### Patch Changes - Updated dependencies \[[`ba31f04`](https://github.com/langchain-ai/langgraphjs/commit/ba31f045d1d458a456c6f6441e8ee81d32c5c700), [`e7e8035`](https://github.com/langchain-ai/langgraphjs/commit/e7e8035fadca5f0d4cbc55bbbb77e65878ab2952), [`9e114e5`](https://github.com/langchain-ai/langgraphjs/commit/9e114e55d362a874878a817740de42fd62ae9db7)]: - @langchain/langgraph-sdk@1.9.22 ## @example/ai-elements@0.1.38 ### Patch Changes - Updated dependencies \[[`9e114e5`](https://github.com/langchain-ai/langgraphjs/commit/9e114e55d362a874878a817740de42fd62ae9db7)]: - @langchain/langgraph@1.4.2 - @langchain/react@1.0.23 ## @examples/assistant-ui-claude@0.1.38 ### Patch Changes - Updated dependencies \[[`9e114e5`](https://github.com/langchain-ai/langgraphjs/commit/9e114e55d362a874878a817740de42fd62ae9db7)]: - @langchain/langgraph@1.4.2 - @langchain/react@1.0.23 ## @examples/ui-angular@0.0.48 ### Patch Changes - Updated dependencies \[[`ba31f04`](https://github.com/langchain-ai/langgraphjs/commit/ba31f045d1d458a456c6f6441e8ee81d32c5c700), [`e7e8035`](https://github.com/langchain-ai/langgraphjs/commit/e7e8035fadca5f0d4cbc55bbbb77e65878ab2952), [`9e114e5`](https://github.com/langchain-ai/langgraphjs/commit/9e114e55d362a874878a817740de42fd62ae9db7)]: - @langchain/langgraph-sdk@1.9.22 - @langchain/langgraph@1.4.2 - @langchain/angular@1.0.23 ## @examples/ui-multimodal@0.0.24 ### Patch Changes - Updated dependencies \[[`9e114e5`](https://github.com/langchain-ai/langgraphjs/commit/9e114e55d362a874878a817740de42fd62ae9db7)]: - @langchain/langgraph@1.4.2 - @langchain/react@1.0.23 ## @examples/ui-react@0.0.24 ### Patch Changes - Updated dependencies \[[`ba31f04`](https://github.com/langchain-ai/langgraphjs/commit/ba31f045d1d458a456c6f6441e8ee81d32c5c700), [`e7e8035`](https://github.com/langchain-ai/langgraphjs/commit/e7e8035fadca5f0d4cbc55bbbb77e65878ab2952), [`9e114e5`](https://github.com/langchain-ai/langgraphjs/commit/9e114e55d362a874878a817740de42fd62ae9db7)]: - @langchain/langgraph-sdk@1.9.22 - @langchain/langgraph@1.4.2 - @langchain/react@1.0.23 ## langgraph@1.0.42 ### Patch Changes - Updated dependencies \[[`9e114e5`](https://github.com/langchain-ai/langgraphjs/commit/9e114e55d362a874878a817740de42fd62ae9db7)]: - @langchain/langgraph@1.4.2 Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> |
||
|
Christian Bromann
|
e7e8035fad |
fix(sdk): late-bind threadId on custom AgentServerAdapter transports (#2528)
## Summary - Add optional `setThreadId(threadId)` to `TransportAdapter` and call it from `client.threads.stream` when binding a custom adapter to the active thread (including the id minted on the first `submit()` of a `threadId: null` stream). - Make `threadId` optional at construction on `ProtocolSseTransportAdapter`, `ProtocolWebSocketTransportAdapter`, and `HttpAgentServerAdapter`; derive command/stream/state URLs from the currently-bound thread and allow `paths` entries to be `(threadId) => string`. - Add unit tests for lazy binding, re-binding, function paths, and `client.threads.stream` wiring. - Document lazy thread binding for custom backends in core SDK and framework docs (React, Vue, Svelte, Angular). |
||
|
Christian Bromann
|
ba31f045d1 |
fix(sdk): reconnect SSE streams when heartbeat idle is detected (#2529)
## Summary - Add heartbeat-adaptive idle reconnect for SSE streams (`idleReconnectStream`) so half-open connections (e.g. platform revision rollover) are detected when `: heartbeat` comments stop arriving and the existing reconnect path resumes with `Last-Event-ID` or `since`. - `"auto"` mode (default on built-in SSE transports) stays dormant until heartbeats are observed, sizes the idle window from their cadence (~15s on the platform's 5s heartbeat), and does not false-fire during long tool calls or HITL pauses. - Expose `streamIdleReconnect?: IdleReconnectMode` on `runs.stream`, `runs.joinStream`, and `threads.stream`; reuse `IdleReconnectMode` across public option types. |
||
|
Christian Bromann
|
9e114e55d3 |
chore(deps): remove uuid dependency in favor of embedded uuid in core (#2527)
## Summary - Remove the direct `uuid` npm dependency from `@langchain/langgraph`, `@langchain/langgraph-checkpoint`, `@langchain/langgraph-checkpoint-redis`, `@langchain/langgraph-api`, `@langchain/langgraph-supervisor`, and `@langchain/langgraph-sdk`. - Switch all UUID generation and validation to `@langchain/core/utils/uuid` (v4, v5, v6, v7, and `validate`). - Drop unused `@types/uuid` devDependencies from checkpoint backend packages that no longer reference `uuid` directly. fixes #2481 |