build(deps): bump langchain from 0.3.37 to 1.2.24

[dependabot]

Bumps langchain from 0.3.37 to 1.2.24.

Release notes

Sourced from langchain's releases.

langchain@1.2.24

Patch Changes

• #10034 8eea9d4 Thanks @​christian-bromann! - fix(langchain): fix streaming types

langchain@1.2.23

Patch Changes

• #10010 bf6eac4 Thanks @​christian-bromann! - fix(langchain): fix structured output on opus

• Updated dependencies [70a4400]:

  • @​langchain/core@​1.1.24

langchain@1.2.21

Patch Changes

• #9996 5113204 Thanks @​christian-bromann! - fix(langchain): propagate subagent name in metadata

• Updated dependencies [8f166b1]:

  • @​langchain/core@​1.1.22

langchain@1.2.20

Patch Changes

• #9983 ea7e791 Thanks @​encodedz! - Support concurrent agentNode dynamic prompts properly.

• #9986 8a52dad Thanks @​brettshollenberger! - Don't re-emit input state from middleware hooks that return void

• #9982 4558fa6 Thanks @​hntrl! - feat(langchain): add optional tools parameter to countTokensApproximately for more accurate token estimates when tools are bound to a model

• #9981 5f28338 Thanks @​hntrl! - feat(agents): support returning Command from wrapModelCall middleware

  Allow wrapModelCall middleware hooks to return Command objects for advanced control flow (routing, state updates), matching the existing wrapToolCall pattern. The framework tracks the effective AIMessage through the middleware chain so outer middleware always receive an AIMessage from handler(), even when an inner middleware returns a Command.

• Updated dependencies [d5e3db0]:

  • @​langchain/core@​1.1.21

langchain@1.2.18

Patch Changes

• #9763 8f0757f Thanks @​AdamParker19! - fix(langchain): resolve className collision in MODEL_PROVIDER_CONFIG

  Refactored getChatModelByClassName to accept an optional modelProvider parameter for direct lookup, avoiding the className collision issue where multiple providers share the same className (e.g., google-vertexai and google-vertexai-web both use "ChatVertexAI"). When modelProvider is provided, the function uses direct config lookup instead of searching by className. Backward compatibility is maintained for existing callers that only pass className. This eliminates the duplicated import logic that was previously in _initChatModelHelper.

langchain@1.2.17

Patch Changes

... (truncated)

Commits

• See full diff in compare view

You can trigger a rebase of this PR 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)

Note
Automatic rebases have been disabled on this pull request as it has been open for over 30 days.

[vercel]

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

Project	Deployment	Actions	Updated (UTC)
leafra	Error		Feb 17, 2026 10:34pm
leafra-9rgi	Error		Feb 17, 2026 10:34pm