chore: version packages - #2
github-actions[bot] wants to merge 1 commit into
Conversation
e055d6b to
3221e41
Compare
b46ad56 to
b918b43
Compare
|
Kilo Code Review could not run — your account is out of credits. Add credits at app.kilo.ai to enable reviews on this change. |
1265e1f to
08db8db
Compare
08db8db to
936892a
Compare
Code Review SummaryStatus: No Issues Found | Recommendation: Merge Files Reviewed (5 files)
Reviewed by gemma-4-26b-a4b-it · 3,874 tokens |
5a8ac63 to
2296400
Compare
2296400 to
a7b0c9d
Compare
e624be2 to
4b4b041
Compare
c5fab3e to
a6f9738
Compare
ed32d41 to
a583586
Compare
f042f32 to
8cea3a3
Compare
84a7832 to
6bb03e6
Compare
872c5fb to
74f4244
Compare
3a12d71 to
1b36638
Compare
1b36638 to
ced9484
Compare
ced9484 to
2596b5d
Compare
|
Important Review skippedBot user detected. To trigger a single review, invoke the ⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Advanced Run ID: You can disable this status message by setting the Use the checkbox below for a quick retry:
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
This PR was opened by the Changesets release 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@1.11.0
Minor Changes
#2831
3234c69Thanks @ramon-langchain! - Expose connection lifecycle callbacks for built-in streaming transports.onConnectedruns after the initial SSE or WebSocket connection becomes usable and after every successful reconnect. Its payload distinguishes aninitialconnection from areconnectedconnection and includes the reconnect attempt number.onReconnectnow also receives the scheduleddelayMs, allowing applications to display accurate retry state before the next connection attempt. React, Vue, Svelte, and Angular stream hooks forward both callbacks.Patch Changes
#2831
3234c69Thanks @ramon-langchain! - Recover cleanly when a thread's root event stream terminates unexpectedly.If the stream fails or closes while a run is active, the controller now records the transport error and clears
isLoadingrather than leaving the UI in a permanently running state. Once the failed pump settles, a later submission can start a fresh root subscription without recreating the thread stream or replaying the failed command.#2809
11a4535Thanks @hntrl! - fix(sdk): appropriately track persisted seq for stream replaySequences weren't being appropriately attributed when rehydrating the page (e.g. on refresh). This meant we'd lose stream information on
useStreamon reloads. This has been fixed by adding a lookup step to determine what the most appropriate sequence index is to track in the event stream.:x#2762
2fab6fdThanks @JessYanCoding! - Sendcheckpoint_idin theruns.stream()request body, so acheckpointIdpassed toclient.runs.stream()forks from the requested checkpoint instead of being silently dropped. Matchesruns.create()andruns.wait(), which already send it.#2813
4fc118fThanks @eliornl! - fix(sdk): show interrupts raised after a passive thread rejoinAfter a page refresh mid-run,
useStreamfiltered every interrupt it did notalready know from the hydrated thread state as replayed history, and waited
for a
checkpointsevent to lift that filter. Current runtimes never emitthat event and the replay buffer trims it on long runs, so interrupts raised
after the refresh never appeared until the next reload. Unknown interrupts are
now settled against the server's thread state when the run reaches a terminal
lifecycle: the ones the server lists as pending are shown, the rest are
dropped as history.
#2812
db4bdadThanks @eliornl! - fix(sdk): recover from a server-side thread stream drop instead of freezingThe protocol SSE transport now reconnects when the server closes the event
stream cleanly. The thread stream is open-ended, so a clean close only happens
when the server's own upstream consumer died or it is restarting; before, the
client treated it as the end of the thread and the UI froze mid-run with no
error. A connection that delivered events also resets the reconnect budget, so
long-lived pages survive repeated deploys.
maxReconnectAttempts: 0keeps theold end-on-close behavior.
Unsolicited server error frames (no command id) and a shared stream that gives
up reconnecting now reach
stream.error:ThreadStream.onErrorexposes them,useStreamsetserror, clearsisLoading, and settles the in-flightsubmit()as failed.#2808
55fa26bThanks @hntrl! - fix(sdk): coalesce locally resolved interruptswhen resolving interrupts using
useStream, there was a case where we prioritized the remote state values (which we lookup in React Strict mode on every page transition) over the local interrupt responses we know we've responded with.This has since been fixed to first prioritize the local cache of interrupts, resolved against the remote state values when a run hits a terminal event
@langchain/angular@1.1.0
Minor Changes
#2831
3234c69Thanks @ramon-langchain! - Expose connection lifecycle callbacks for built-in streaming transports.onConnectedruns after the initial SSE or WebSocket connection becomes usable and after every successful reconnect. Its payload distinguishes aninitialconnection from areconnectedconnection and includes the reconnect attempt number.onReconnectnow also receives the scheduleddelayMs, allowing applications to display accurate retry state before the next connection attempt. React, Vue, Svelte, and Angular stream hooks forward both callbacks.Patch Changes
3234c69,3234c69,11a4535,2fab6fd,4fc118f,db4bdad,55fa26b]:@langchain/react@1.1.0
Minor Changes
#2831
3234c69Thanks @ramon-langchain! - Expose connection lifecycle callbacks for built-in streaming transports.onConnectedruns after the initial SSE or WebSocket connection becomes usable and after every successful reconnect. Its payload distinguishes aninitialconnection from areconnectedconnection and includes the reconnect attempt number.onReconnectnow also receives the scheduleddelayMs, allowing applications to display accurate retry state before the next connection attempt. React, Vue, Svelte, and Angular stream hooks forward both callbacks.Patch Changes
3234c69,3234c69,11a4535,2fab6fd,4fc118f,db4bdad,55fa26b]:@langchain/svelte@1.1.0
Minor Changes
#2831
3234c69Thanks @ramon-langchain! - Expose connection lifecycle callbacks for built-in streaming transports.onConnectedruns after the initial SSE or WebSocket connection becomes usable and after every successful reconnect. Its payload distinguishes aninitialconnection from areconnectedconnection and includes the reconnect attempt number.onReconnectnow also receives the scheduleddelayMs, allowing applications to display accurate retry state before the next connection attempt. React, Vue, Svelte, and Angular stream hooks forward both callbacks.Patch Changes
3234c69,3234c69,11a4535,2fab6fd,4fc118f,db4bdad,55fa26b]:@langchain/vue@1.1.0
Minor Changes
#2831
3234c69Thanks @ramon-langchain! - Expose connection lifecycle callbacks for built-in streaming transports.onConnectedruns after the initial SSE or WebSocket connection becomes usable and after every successful reconnect. Its payload distinguishes aninitialconnection from areconnectedconnection and includes the reconnect attempt number.onReconnectnow also receives the scheduleddelayMs, allowing applications to display accurate retry state before the next connection attempt. React, Vue, Svelte, and Angular stream hooks forward both callbacks.Patch Changes
3234c69,3234c69,11a4535,2fab6fd,4fc118f,db4bdad,55fa26b]:@langchain/langgraph-api@1.4.6
Patch Changes
0a9611aThanks @t3s7r! - fix(api):run.startwith input on a cancelled thread no longer folds the input intoCommand(resume). A cancelled run shares the "interrupted" status with a genuineinterrupt()pause, but has no pending interrupt to consume the resume value, so the submitted message was silently dropped. The input-vs-resume decision now keys on whether the thread actually has pending interrupts (both in the protocol service and the embed protocol).@langchain/langgraph-cli@1.4.6
Patch Changes
0a9611a]:@langchain/langgraph@1.4.15
Patch Changes
#2794
83a4b62Thanks @hntrl! - feat(langgraph): add per-nodetracePolicyinput/output processors andomitPayloadTransform the payloads recorded on a node's own trace run while retaining its span and timing. Processors receive raw values and fall back to the original payload if they throw. Graph state, root runs, and child runs remain unchanged when processors do not mutate their arguments.
Matches Python's callback-level behavior: transforms also affect chain events and message streaming, so omitting outputs can suppress messages returned directly by nodes and omitting inputs can affect message deduplication.
Updated dependencies [
3234c69,3234c69,11a4535,2fab6fd,4fc118f,db4bdad,55fa26b]:@langchain/langgraph-cua@1.0.3
No changes in this release.
@langchain/langgraph-supervisor@1.1.2
No changes in this release.
@langchain/langgraph-swarm@1.0.3
No changes in this release.
@langchain/langgraph-ui@1.4.6
No changes in this release.