chore(deps): bump @langchain/core from 0.3.80 to 1.2.17

[dependabot]

Bumps @langchain/core from 0.3.80 to 1.2.17.

Release notes

Sourced from @​langchain/core's releases.

@​langchain/core@​1.2.17

Patch Changes

• #11849 b1d9c7a Thanks @​KyleCodes! - Preserve runtime context in ambient runnable config across tool calls, nested runnables, and streaming.

@​langchain/core@​1.2.16

Patch Changes

• #11847 bb50952 Thanks @​hntrl! - fix(core): expose branded class type for provider declarations

@​langchain/core@​1.2.14

Patch Changes

• #11771 bbed273 Thanks @​thushanth-bengre-langchain! - Add fileMimeTypes to ModelProfile so models can advertise the MIME types they accept as generic file inputs. OpenAI Responses API models now report the file types input_file supports; Chat Completions profiles are unchanged.

@​langchain/core@​1.2.13

Patch Changes

• #11714 a83dfb1 Thanks @​ccurme! - Abbreviate long tool-call IDs when formatting chat messages as strings, keeping original messages unchanged.

@​langchain/core@​1.2.12

Patch Changes

• #11675 030a726 Thanks @​hntrl! - Preserve structured tool arguments in tracer run inputs.

@​langchain/core@​1.2.11

Patch Changes

• #11603 fec9cd8 Thanks @​thushanth-bengre-langchain! - fix(core): build streaming llmOutput.tokenUsage from the fully-accumulated chunk instead of whichever individual chunk's usage_metadata arrived last

  Affects both core streaming paths — .stream()/.streamEvents() (_streamIterator) and .invoke()/.generate() when a streaming-preferring callback is attached (_generateWithCache's hasStreamingHandler branch). Previously, llmOutput.tokenUsage was overwritten by each chunk in turn, so only the last chunk carrying usage_metadata won — correct for providers that emit one cumulative total on a final chunk, but wrong for providers (e.g. @langchain/google, @langchain/anthropic) that emit usage_metadata as a per-chunk delta across multiple chunks, where the values must be summed.

  Note for provider authors: this assumes each streamed chunk's usage_metadata is either a per-chunk delta or appears only on a single final chunk. A provider that instead repeats a cumulative total on every chunk will now see it summed (and inflated) in llmOutput.tokenUsage, matching the existing behavior of the correctly-working message.usage_metadata field.

  Also fixes @langchain/google's invoke({streaming: true}) path (no streaming-preferring callback attached), where llmOutput was never populated at all.

• #11590 ffebdc2 Thanks @​thushanth-bengre-langchain! - Fix OpenAI Responses API replay under Zero Data Retention when a response contains more than one reasoning item, for both v0 and v1. In v0, the default replay path now reuses response_metadata.output directly, preserving every reasoning item's id/encrypted_content in original order. In v1, AIMessage.contentBlocks (outputVersion: "v1") is fixed the same way. additional_kwargs.reasoning is unchanged.

@​langchain/core@​1.2.10

Patch Changes

• #10047 ff1248f Thanks @​afirstenberg! - fix(core): BaseMessage.text use contentBlocks

Commits

• 59776b1 chore: version packages (#11874)
• b1d9c7a fix(core): preserve ambient runtime context across tool calls (#11849)
• 5dfb0cb chore: version packages (#11848)
• bb50952 fix(core): expose branded class type for provider declarations (#11847)
• 5a86552 chore: version packages (#11826)
• 1b5ac16 fix(mcp-adapters): use a single underscore for server tool prefixes (#11845)
• 0552450 fix(mcp-adapters): keep the SDK error as cause after an HTTP→SSE fallback (#1...
• f2ff71c chore(deps): bump the minor-and-patch group across 1 directory with 48 update...
• 71ede02 chore(deps): bump the build-and-test group across 1 directory with 8 updates ...
• c4dba61 chore(deps): bump the langchain group across 1 directory with 4 updates (#11791)
• Additional commits viewable in compare view

[dependabot]

Labels

The following labels could not be found: npm. Please create it before Dependabot can add it to a pull request.

Please fix the above issues or remove invalid values from dependabot.yml.