Skip to content

fix: improve Vertex AI redirect handling - #8685

Merged
mattwittwer merged 4 commits into
mainfrom
mwittwer/vertex_ai_restricted_endpoint
Mar 11, 2026
Merged

fix: improve Vertex AI redirect handling#8685
mattwittwer merged 4 commits into
mainfrom
mwittwer/vertex_ai_restricted_endpoint

Conversation

@mattwittwer

@mattwittwer mattwittwer commented Mar 6, 2026

Copy link
Copy Markdown
Contributor

What does the PR do?

Restrict X-Vertex-Ai-Triton-Redirect to read-only routes and block repository control and shared-memory mutation requests from being tunneled through /predict.

Add test coverage for restricted vs allowed redirect targets, statistics access, and input-size enforcement

Checklist

  • PR title reflects the change and is of format <commit_type>: <Title>
  • Changes are described in the pull request.
  • Related issues are referenced.
  • Populated github labels field
  • Added test plan and verified test passes.
  • Verified that the PR passes existing CI.
  • Verified copyright is correct on all changed files.
  • Added succinct git squash message before merging ref.
  • All template sections are filled out.
  • Optional: Additional screenshots for behavior/output changes with before/after.

Commit Type:

Check the conventional commit type
box here and add the label to the github PR.

  • build
  • ci
  • docs
  • feat
  • fix
  • perf
  • refactor
  • revert
  • style
  • test

Related PRs:

This PR is closely related to this Vertex AI endpoint improvement: #8680

Where should the reviewer start?

Test plan:

  • CI Pipeline ID:

45551039

Caveats:

Background

Related Issues: (use one of the action keywords Closes / Fixes / Resolves / Relates to)

  • closes GitHub issue: #xxx

@mattwittwer
mattwittwer force-pushed the mwittwer/vertex_ai_restricted_endpoint branch from 02f7d1c to ffee72e Compare March 6, 2026 20:40
@mattwittwer mattwittwer changed the title draft: prevent vertex ai redirection fix: improve Vertex AI redirect handling Mar 6, 2026
@mattwittwer mattwittwer self-assigned this Mar 6, 2026
@mattwittwer
mattwittwer changed the base branch from main to spolisetty/tri-669-psirt-triton-inference-server-vertex-ai-integration-access March 7, 2026 00:27
Base automatically changed from spolisetty/tri-669-psirt-triton-inference-server-vertex-ai-integration-access to main March 7, 2026 12:09
whoisj
whoisj previously approved these changes Mar 9, 2026

@whoisj whoisj left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM. Also looks near identical to you other PR, interesting.

@mattwittwer
mattwittwer force-pushed the mwittwer/vertex_ai_restricted_endpoint branch from ffee72e to 93df24c Compare March 11, 2026 23:00
@mattwittwer

Copy link
Copy Markdown
Contributor Author

Rebased this branch onto current main to resolve the conflict with Vertex AI changes from #8680.

@mattwittwer
mattwittwer merged commit d8f1616 into main Mar 11, 2026
3 checks passed
@mattwittwer
mattwittwer deleted the mwittwer/vertex_ai_restricted_endpoint branch March 11, 2026 23:03
mattwittwer added a commit that referenced this pull request Mar 11, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Development

Successfully merging this pull request may close these issues.

3 participants