Update dependency langsmith to v0.7.31 [SECURITY]#487
Open
renovate[bot] wants to merge 1 commit intomainfrom
Open
Update dependency langsmith to v0.7.31 [SECURITY]#487renovate[bot] wants to merge 1 commit intomainfrom
renovate[bot] wants to merge 1 commit intomainfrom
Conversation
8108543 to
529a898
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This PR contains the following updates:
0.7.20→0.7.31GitHub Vulnerability Alerts
GHSA-rr7j-v2q5-chgv
Summary
The LangSmith SDK's output redaction controls (hideOutputs in JS, hide_outputs in Python) do not apply to streaming token events. When an LLM run produces streaming output, each chunk is recorded as a new_token event containing the raw token value. These events bypass the redaction pipeline entirely — prepareRunCreateOrUpdateInputs (JS) and _hide_run_outputs (Python) only process the inputs and outputs fields on a run, never the events array. As a result, applications relying on output redaction to prevent sensitive LLM output from being stored in LangSmith will still leak the full streamed content via run events.
Details
Both JS and Python SDKs are affected. The same pattern exists in both:
traceable.ts:997-1003andtraceable.ts:1044-1050run_helpers.py:1924andrun_helpers.py:1996In both SDKs,
new_tokenevents with rawkwargs.tokenvalues are added during streaming, and the redaction pipeline (hideOutputsin JS,hide_outputsin Python) only processesinputs/outputs— neverevents.Severity
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:NLangSmith SDK: Streaming token events bypass output redaction
GHSA-rr7j-v2q5-chgv
More information
Details
Summary
The LangSmith SDK's output redaction controls (hideOutputs in JS, hide_outputs in Python) do not apply to streaming token events. When an LLM run produces streaming output, each chunk is recorded as a new_token event containing the raw token value. These events bypass the redaction pipeline entirely — prepareRunCreateOrUpdateInputs (JS) and _hide_run_outputs (Python) only process the inputs and outputs fields on a run, never the events array. As a result, applications relying on output redaction to prevent sensitive LLM output from being stored in LangSmith will still leak the full streamed content via run events.
Details
Both JS and Python SDKs are affected. The same pattern exists in both:
traceable.ts:997-1003andtraceable.ts:1044-1050run_helpers.py:1924andrun_helpers.py:1996In both SDKs,
new_tokenevents with rawkwargs.tokenvalues are added during streaming, and the redaction pipeline (hideOutputsin JS,hide_outputsin Python) only processesinputs/outputs— neverevents.Severity
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:NReferences
This data is provided by OSV and the GitHub Advisory Database (CC-BY 4.0).
Release Notes
langchain-ai/langsmith-sdk (langsmith)
v0.7.31Compare Source
What's Changed
Full Changelog: langchain-ai/langsmith-sdk@v0.7.30...v0.7.31
v0.7.30Compare Source
What's Changed
Full Changelog: langchain-ai/langsmith-sdk@v0.7.29...v0.7.30
v0.7.29Compare Source
What's Changed
Full Changelog: langchain-ai/langsmith-sdk@v0.7.28...v0.7.29
v0.7.28Compare Source
What's Changed
New Contributors
Full Changelog: langchain-ai/langsmith-sdk@v0.7.27...v0.7.28
v0.7.27Compare Source
What's Changed
New Contributors
Full Changelog: langchain-ai/langsmith-sdk@v0.7.26...v0.7.27
v0.7.26Compare Source
What's Changed
Full Changelog: langchain-ai/langsmith-sdk@v0.7.25...v0.7.26
v0.7.25Compare Source
What's Changed
New Contributors
Full Changelog: langchain-ai/langsmith-sdk@v0.7.24...v0.7.25
v0.7.24Compare Source
What's Changed
Full Changelog: langchain-ai/langsmith-sdk@v0.7.23...v0.7.24
v0.7.23Compare Source
What's Changed
New Contributors
Full Changelog: langchain-ai/langsmith-sdk@v0.7.22...v0.7.23
v0.7.22Compare Source
What's Changed
Full Changelog: langchain-ai/langsmith-sdk@v0.7.21...v0.7.22
v0.7.21Compare Source
What's Changed
Full Changelog: langchain-ai/langsmith-sdk@v0.7.20...v0.7.21
Configuration
📅 Schedule: (in timezone US/Eastern)
🚦 Automerge: Enabled.
♻ Rebasing: Whenever PR is behind base branch, or you tick the rebase/retry checkbox.
🔕 Ignore: Close this PR and you won't be reminded about this update again.
This PR was generated by Mend Renovate. View the repository job log.