chore(deps): bump the production-dependencies group across 1 directory with 4 updates

[dependabot]

Bumps the production-dependencies group with 2 updates in the / directory: @langchain/classic and langchain.

Updates @langchain/classic from 1.0.40 to 1.0.46

Release notes

Sourced from @​langchain/classic's releases.

@​langchain/classic@​1.0.46

Patch Changes

• Updated dependencies [53dbfc2]:
  • @​langchain/openai@​1.5.11

@​langchain/classic@​1.0.45

Patch Changes

• Updated dependencies [c26c87e]:
  • @​langchain/openai@​1.5.10

@​langchain/classic@​1.0.44

Patch Changes

• #11412 7df258c Thanks @​hntrl! - chore(langgraph): update langgraph deps to track serialization fix

• Updated dependencies [5c9fdf2, fe8eec1, 5c9fdf2]:

  • @​langchain/openai@​1.5.9

@​langchain/classic@​1.0.43

Patch Changes

• Updated dependencies [3b0e4c4]:
  • @​langchain/openai@​1.5.8

@​langchain/classic@​1.0.42

Patch Changes

• Updated dependencies [3fe4c43]:
  • @​langchain/openai@​1.5.7

@​langchain/classic@​1.0.41

Patch Changes

• Updated dependencies [e654022]:
  • @​langchain/openai@​1.5.6

Commits

• 21fff39 chore: version packages (#11517)
• 6b613fe fix(infra): add oxfmt formatter
• b522160 chore(infra): update to changesets 3 (#11516)
• ba81a3c chore: version packages (#11462)
• e927605 fix(aws): recognize claude 5 models in supportedToolChoiceValuesForModel (#11...
• ffadf85 chore(deps): bump the minor-and-patch group across 1 directory with 39 update...
• 679f79b chore(deps): bump the aws group across 1 directory with 7 updates (#11484)
• 0f54ed6 chore(deps): bump the build-and-test group across 1 directory with 3 updates ...
• 147e082 chore(deps): bump google-auth-library from 10.9.1 to 11.0.2 in the google gro...
• 7969427 chore(deps): bump changesets/action from 1.9.0 to 2.1.1 in the gh-actions-maj...
• Additional commits viewable in compare view

Updates @langchain/core from 1.2.3 to 1.2.9

Release notes

Sourced from @​langchain/core's releases.

@​langchain/core@​1.2.9

Patch Changes

• #11402 43e4396 Thanks @​thushanth-bengre-langchain! - Fix ChatVertexAI/ChatGoogle content blocks: include tool_call blocks from message.tool_calls and skip spurious empty text blocks in contentBlocks.

@​langchain/core@​1.2.8

Patch Changes

• #11369 d6ad973 Thanks @​hntrl! - fix(langchain): use unified endpoint for gateway

• #11342 3b0e4c4 Thanks @​thushanth-bengre-langchain! - feat(core): mark errors as retryable or not, and stop retrying the ones that aren't

  Retry middleware retried every failure up to maxRetries, including deterministic ones like a bad API key or an unknown model. Retries also nest, so a single such failure could cost dozens of API calls.

  @langchain/core/errors adds stampRetryable(error, retryable) and getRetryable(error). Marking an error leaves its class and shape untouched, so a provider SDK error can be classified without breaking instanceof. getRetryable returns undefined for errors nobody classified, and both are exported so tool authors can mark their own failures.

  modelRetryMiddleware and toolRetryMiddleware now respect the mark by default, and retries stop as soon as one is found rather than each layer spending its own budget. Aborted calls, context overflow, and oversized payloads are marked non-retryable out of the box. Models accept a per-call maxRetries so a surrounding retry loop can take over.

  Behavior change: errors marked non-retryable now fail on the first attempt. Unclassified errors — including any from third-party integrations or custom tools — retry exactly as before. Pass retryOn: () => true to restore the old default. A custom onFailedAttempt replaces the built-in handler and opts out of marking.

@​langchain/core@​1.2.7

Patch Changes

• #11366 c068bbf Thanks @​hntrl! - fix(core,langchain): patch and release core, update peer dependencies

@​langchain/core@​1.2.6

Patch Changes

• #11344 f08e0c6 Thanks @​hntrl! - fix: apply [Symbol.hasInstance] method to all comparable properties using .isInstance()

  We have some internal schemas that rely on z.instanceof(). This uses a strict instanceof check which can conflict if there are multiple versions of core installed. This overrides the Symbol.hasInstance method to use the same logic as .isInstance() to compare objects at runtime.

@​langchain/core@​1.2.5

Patch Changes

• #11305 e654022 Thanks @​jacoblee93! - Add LangSmith Gateway environment configuration to OpenAI, Anthropic, and Fireworks chat models.

• #11295 1a1b347 Thanks @​vladislav-nechakhin! - fix(core): pass the mustache escape override per render call

@​langchain/core@​1.2.4

Patch Changes

• #11190 9654bde Thanks @​pawel-twardziak! - Coalesce nested LangChain tracer callbacks that share run bookkeeping.

• #11153 84ce6d6 Thanks @​parveshsaini! - fix(core): bind splitText when trimMessages receives a TextSplitter instance

Commits

• e493ed6 chore: version packages (#11393)
• 8384848 fix(google-common): release endpoint routing fix as patch (#11413)
• 8cfff4d feat(google): add gateway support for genai (#11405)
• 7df258c chore(langchain): update langgraph deps (#11412)
• 3ceef4b fix(anthropic): round-trip tool search server-tool result blocks (#11407)
• fe8eec1 fix(openai): drop Gemini functionCall content blocks in Chat Completions mess...
• 0e7c765 fix(google-genai): throw ContentBlockedError when Gemini candidate has no con...
• 5c9fdf2 fix(openai): retain cache_write_tokens, update to v7 sdk (#11399)
• 5ff9179 fix(google-genai): guard streaming chunks when candidate has no content (#10742)
• 43e4396 fix(core): include tool_call blocks and skip empty text blocks in ChatVertexA...
• Additional commits viewable in compare view

Updates @langchain/openai from 1.5.5 to 1.5.11

Release notes

Sourced from @​langchain/openai's releases.

@​langchain/openai@​1.5.11

Patch Changes

• #11448 53dbfc2 Thanks @​hntrl! - fix(openai): resolve encrypted content with zdr when streaming

  OpenAI recently changed the disposition of encrypted_content to contain the canonical payload on the final done event. Encrypted content also does not need to be a parameter in the include call options in order to propagate.

@​langchain/openai@​1.5.10

Patch Changes

• #11419 c26c87e Thanks @​chiliec! - fix(openai): send content null (not []) for tool-call-only v1 assistant messages

@​langchain/openai@​1.5.9

Patch Changes

• #11399 5c9fdf2 Thanks @​gethin-langchain! - update to v7 openai sdk

• #11403 fe8eec1 Thanks @​thushanth-bengre-langchain! - Drop Gemini-native functionCall content blocks (already carried in tool_calls) when converting messages to Chat Completions API params, fixing requests that fail when a ChatGoogleGenerativeAI message is passed to ChatOpenAI (e.g. a cross-provider handoff in LangGraph).

• #11399 5c9fdf2 Thanks @​gethin-langchain! - Map OpenAI's cache_write_tokens to cache_creation in usage_metadata.input_token_details, mirroring the existing cached_tokens -> cache_read mapping across the Chat Completions and Responses APIs. Previously, prompt cache-write token counts were silently dropped.

@​langchain/openai@​1.5.8

Patch Changes

• #11342 3b0e4c4 Thanks @​thushanth-bengre-langchain! - feat(openai): mark OpenAI provider errors as retryable or not

  Builds on stampRetryable in @langchain/core so the retry middleware can tell a transient failure from a deterministic one. Timeouts and rate limits are marked retryable; aborts, context overflow, invalid tool results, bad credentials, and unknown models non-retryable. Anything else stays unmarked and retries as before.

  Also forwards a per-call maxRetries to the retry loop, so a surrounding retry loop such as modelRetryMiddleware can take over instead of the two multiplying against each other.

  Errors keep their original class, so instanceof against the openai SDK error types is unaffected.

@​langchain/openai@​1.5.7

Patch Changes

• #11347 3fe4c43 Thanks @​talarari! - fix(openai): include usage in response_metadata when system_fingerprint is absent

@​langchain/openai@​1.5.6

Patch Changes

• #11305 e654022 Thanks @​jacoblee93! - Add LangSmith Gateway environment configuration to OpenAI, Anthropic, and Fireworks chat models.

Commits

• 21fff39 chore: version packages (#11517)
• 6b613fe fix(infra): add oxfmt formatter
• b522160 chore(infra): update to changesets 3 (#11516)
• ba81a3c chore: version packages (#11462)
• e927605 fix(aws): recognize claude 5 models in supportedToolChoiceValuesForModel (#11...
• ffadf85 chore(deps): bump the minor-and-patch group across 1 directory with 39 update...
• 679f79b chore(deps): bump the aws group across 1 directory with 7 updates (#11484)
• 0f54ed6 chore(deps): bump the build-and-test group across 1 directory with 3 updates ...
• 147e082 chore(deps): bump google-auth-library from 10.9.1 to 11.0.2 in the google gro...
• 7969427 chore(deps): bump changesets/action from 1.9.0 to 2.1.1 in the gh-actions-maj...
• Additional commits viewable in compare view

Updates langchain from 1.5.3 to 1.5.10

Release notes

Sourced from langchain's releases.

langchain@1.5.10

Patch Changes

• #11412 7df258c Thanks @​hntrl! - chore(langgraph): update langgraph deps to track serialization fix

langchain@1.5.9

Patch Changes

• #11369 d6ad973 Thanks @​hntrl! - fix(langchain): use unified endpoint for gateway

• #11342 3b0e4c4 Thanks @​thushanth-bengre-langchain! - feat(core): mark errors as retryable or not, and stop retrying the ones that aren't

  Retry middleware retried every failure up to maxRetries, including deterministic ones like a bad API key or an unknown model. Retries also nest, so a single such failure could cost dozens of API calls.

  @langchain/core/errors adds stampRetryable(error, retryable) and getRetryable(error). Marking an error leaves its class and shape untouched, so a provider SDK error can be classified without breaking instanceof. getRetryable returns undefined for errors nobody classified, and both are exported so tool authors can mark their own failures.

  modelRetryMiddleware and toolRetryMiddleware now respect the mark by default, and retries stop as soon as one is found rather than each layer spending its own budget. Aborted calls, context overflow, and oversized payloads are marked non-retryable out of the box. Models accept a per-call maxRetries so a surrounding retry loop can take over.

  Behavior change: errors marked non-retryable now fail on the first attempt. Unclassified errors — including any from third-party integrations or custom tools — retry exactly as before. Pass retryOn: () => true to restore the old default. A custom onFailedAttempt replaces the built-in handler and opts out of marking.

langchain@1.5.8

Patch Changes

• #11366 c068bbf Thanks @​hntrl! - fix(core,langchain): patch and release core, update peer dependencies

langchain@1.5.7

Patch Changes

• #11363 2d1f744 Thanks @​hntrl! - feat(langchain): add langsmith gateway to initChatModel- #11362

langchain@1.5.6

Patch Changes

• #11331 18765b0 Thanks @​thushanth-bengre-langchain! - fix(langchain): exclude middleware-internal model calls from the message projection

  Bookkeeping model calls made by summarizationMiddleware and toolEmulatorMiddleware no longer appear in run.messages or stream({ streamMode: "messages" }), and the summary summarizationMiddleware writes back to state is no longer projected as a new message. These calls remain observable via streamEvents({ version: "v2" }), identified by lc_source.

• #11344 f08e0c6 Thanks @​hntrl! - fix: apply [Symbol.hasInstance] method to all comparable properties using .isInstance()

  We have some internal schemas that rely on z.instanceof(). This uses a strict instanceof check which can conflict if there are multiple versions of core installed. This overrides the Symbol.hasInstance method to use the same logic as .isInstance() to compare objects at runtime.

langchain@1.5.5

Patch Changes

• #11277 0bd12f0 Thanks @​vladislav-nechakhin! - fix(langchain): resolve LocalFileStore keys with path.relative

langchain@1.5.4

Patch Changes

... (truncated)

Commits

• e493ed6 chore: version packages (#11393)
• 8384848 fix(google-common): release endpoint routing fix as patch (#11413)
• 8cfff4d feat(google): add gateway support for genai (#11405)
• 7df258c chore(langchain): update langgraph deps (#11412)
• 3ceef4b fix(anthropic): round-trip tool search server-tool result blocks (#11407)
• fe8eec1 fix(openai): drop Gemini functionCall content blocks in Chat Completions mess...
• 0e7c765 fix(google-genai): throw ContentBlockedError when Gemini candidate has no con...
• 5c9fdf2 fix(openai): retain cache_write_tokens, update to v7 sdk (#11399)
• 5ff9179 fix(google-genai): guard streaming chunks when candidate has no content (#10742)
• 43e4396 fix(core): include tool_call blocks and skip empty text blocks in ChatVertexA...
• Additional commits viewable in compare view

---

Note

Medium Risk
Transitive openai major upgrade and Node ≥22 engine requirements on OpenAI-related packages can break CI or local runs on older Node; inherited LangChain retry/error behavior may change failure handling for agent chat flows.

Overview
Bumps direct production deps @langchain/classic (^1.0.40 → ^1.0.46) and langchain (^1.5.3 → ^1.5.10) in package.json, with matching package-lock.json refreshes.

The lockfile also pulls newer transitive LangChain stack versions, including @langchain/core (1.2.3 → 1.2.9), @langchain/openai (1.5.5 → 1.5.11), LangGraph-related packages, and openai (v6 → v7). No application source changes—runtime behavior shifts come only from those library updates (e.g. OpenAI SDK v7, stricter Node ≥22 on openai / @langchain/openai, and core retry-classification changes noted in recent LangChain releases).

^{Reviewed by Cursor Bugbot for commit 09942db. Bugbot is set up for automated code reviews on this repo. Configure here.}