chore(deps): bump uuid, @langchain/openai, @langchain/qdrant and langchain

[dependabot]

Removes uuid. It's no longer used after updating ancestor dependencies uuid, @langchain/openai, @langchain/qdrant and langchain. These dependencies need to be updated together.

Removes uuid

Updates @langchain/openai from 0.5.18 to 1.5.3

Release notes

Sourced from @​langchain/openai's releases.

@​langchain/openai@​1.5.3

Patch Changes

• #11100 3205b35 Thanks @​colifran! - fix(langchain, openai): decouple strict tools from strict structured output response

@​langchain/openai@​1.5.2

Patch Changes

• #11045 05936ab Thanks @​jackjin1997! - fix(openai): omit empty id and content on reasoning items in Responses API input

  Reasoning blocks reassembled from streaming chunks (e.g. via streamEvents) never carry an id, since OpenAI's streaming protocol only includes it in non-streaming responses. When such a message was replayed as Responses API input on the next turn, the reasoning item was emitted with id: "", which OpenAI rejects with 400 Invalid 'input[n].id': ''. The id field is now omitted when absent.

  A second error surfaced immediately after that fix: the same converter set a populated content array on the reasoning input item, which the Responses API also rejects (400 Invalid 'input[n].content': array too long. Expected an array with maximum length 0). Reasoning input items only carry summary, so content is no longer forwarded. Thanks to @​csrujanreddy for catching the second issue and verifying both fixes against the live API.

• #11065 798cb70 Thanks @​rxits! - fix(openai): route standard url file blocks to native input_file in Responses API

• #11090 80c790b Thanks @​nikhilpakhloo! - fix(openai): stream built-in tool progress events

@​langchain/openai@​1.5.1

Patch Changes

• #11001 80b43ec Thanks @​Herrtian! - Wrap Responses API stream iteration errors with existing OpenAI client error handling.

@​langchain/openai@​1.5.0

Minor Changes

• #10924 2e28115 Thanks @​christian-bromann! - feat(openai): add native streamEvents event converters

@​langchain/openai@​1.4.7

Patch Changes

• #10918 3999fab Thanks @​christian-bromann! - fix(openai): stream custom tool calls through Responses API chunks

• #10791 fce9ab4 Thanks @​Genmin! - fix(openai): preserve top-level Responses API ids on AI messages

@​langchain/openai@​1.4.6

Patch Changes

• #10902 229a7ad Thanks @​christian-bromann! - fix(openai): preserve v1 assistant tool calls

• #10895 36fb0ef Thanks @​BertBR! - fix(openai): guard bare JSON.parse in Responses API converter against trailing non-whitespace characters

  convertResponsesDeltaToChatGenerationChunk previously called JSON.parse(msg.text) directly when response.text.format.type === "json_schema". Some models (observed with gpt-5-mini on service_tier: "auto") intermittently emit trailing non-whitespace characters (extra tokens, control characters) after a valid JSON object, causing a SyntaxError that propagates as an unhandled exception and kills the entire streaming response mid-flight. The parse is now wrapped in a try/catch: on failure, additional_kwargs.parsed is left undefined, the stream completes normally, and the existing withStructuredOutput pipeline handles the typed failure — includeRaw: true returns { raw, parsed: null } via its withFallbacks wrapper, includeRaw: false throws a typed OutputParserException that the caller can catch and retry. Closes #10894.

Commits

• f1d64ff chore: version packages (#11101)
• 72ffc4b fix(aws): add Bedrock stream idle timeout (#11098)
• 3205b35 fix(langchain, openai): decouple strict tools from strict structured output r...
• 1ee0df0 chore: version packages (#11097)
• f017708 fix(core): better 429 error handling (#10674)
• 05936ab fix(openai): omit empty reasoning item id in Responses API input (#11045)
• 798cb70 fix(openai): route standard url file blocks to native input_file in Responses...
• 80c790b fix(openai): stream built-in tool progress events (#11090)
• d2e6afc fix(groq): require @​langchain/core >= 1.1.30 in peer dependency (#11072)
• c66870e feat(weaviate): add X-Weaviate-Client-Integration telemetry header (#11088)
• Additional commits viewable in compare view

Maintainer changes

This version was pushed to npm by GitHub Actions, a new releaser for @​langchain/openai since your current version.

Updates @langchain/qdrant from 0.1.3 to 1.0.3

Release notes

Sourced from @​langchain/qdrant's releases.

@​langchain/qdrant@​1.0.3

Patch Changes

• #10872 a640079 Thanks @​hntrl! - chore(deps): remove redundant @​types/uuid declarations

  Remove @types/uuid from package manifests that rely on @langchain/core/utils/uuid or do not require uuid type stubs directly, and refresh the lockfile entries accordingly.

Commits

• 1b19e4f chore: version packages (#10899)
• 426e3ab chore: fix uuid changeset (#10916)
• 245c982 chore(deps): bump fast-xml-builder from 1.1.5 to 1.2.0 (#10914)
• 126dac5 chore(deps): bump brace-expansion from 5.0.5 to 5.0.6 (#10912)
• 1abe24b chore(deps): bump fast-uri from 3.1.0 to 3.1.2 (#10913)
• 229a7ad fix(openai): preserve v1 assistant tool calls (#10902)
• f26fc4a fix(core): share fakeModel invocation state across bindTools instances (#10901)
• a0cd747 chore(deps): bump fast-xml-builder from 1.1.5 to 1.1.9 (#10910)
• b208e62 chore(deps): bump ip-address from 10.1.0 to 10.2.0 (#10909)
• f7e50fb feat(google): Service tier and custom headers (#10704)
• Additional commits viewable in compare view

Maintainer changes

This version was pushed to npm by GitHub Actions, a new releaser for @​langchain/qdrant since your current version.

Updates langchain from 0.3.37 to 1.5.2

Release notes

Sourced from langchain's releases.

langchain@1.5.2

Patch Changes

• #11100 3205b35 Thanks @​colifran! - fix(langchain, openai): decouple strict tools from strict structured output response

langchain@1.5.1

Patch Changes

• #11087 534b43a Thanks @​christian-bromann! - fix(langchain): keep tool call streams pending across any tool interrupt

  A raw interrupt() raised from inside a tool surfaced as a tool-error and rejected the call's un-awaited output promise, producing an unhandled rejection that crashed HITL runs. The tool-call stream transformer now treats any serialized graph interrupt as control flow (the call stays pending and resumes), not just humanInTheLoopMiddleware interrupts.

langchain@1.5.0

Minor Changes

• #11062 3ebd10a Thanks @​christian-bromann! - feat(langchain): surface tool-dispatched subagents on run.subagents

  Add a native subagent stream transformer to createAgent so v3 runs expose named nested agents (createAgent({ name }) invoked from tools) as typed SubagentRunStream handles with name, cause, scoped messages / toolCalls, and output. Refactors agent stream transformers into agents/transformers/ and exports only the public stream types from the package entry.

langchain@1.4.6

Patch Changes

• #11012 4aeaa76 Thanks @​christian-bromann! - feat(langchain): add when predicate to human-in-the-loop middleware

  Add an optional when callback on InterruptOnConfig so callers can dynamically skip interrupts for specific tool calls. The predicate receives a ToolCallRequest (batch afterModel context) and returns whether to interrupt or auto-approve, matching Python HumanInTheLoopMiddleware.

• #11080 e51478a Thanks @​aolsenjazz! - feat(aws): bedrock prompt caching middleware

  Adds bedrockPromptCachingMiddleware. The interface largely matches what was previous implemented with anthropicPromptCachingMiddleware, making a best-effort attempt at utilizing prompt caching features for supported models.

langchain@1.4.2

Patch Changes

• #10900 6bbddca Thanks @​christian-bromann! - fix(langchain): unwrap tool message outputs in agent streams

• #10706 4ecb660 Thanks @​JadenKim-dev! - fix(langchain): set name on todoListMiddleware ToolMessages

langchain@1.4.1

... (truncated)

Commits

• See full diff in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

---

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

• @dependabot rebase will rebase this PR
• @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
• @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
• @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)
  You can disable automated security fix PRs for this repo from the Security Alerts page.

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Actions	Updated (UTC)
jargons-dev	Error		Jun 29, 2026 9:38pm