Skip to content

feat: add sandbox image viewing tool - #179

Open
QueryPlanner wants to merge 1 commit into
mainfrom
feat/sandbox-image-viewer
Open

feat: add sandbox image viewing tool#179
QueryPlanner wants to merge 1 commit into
mainfrom
feat/sandbox-image-viewer

Conversation

@QueryPlanner

Copy link
Copy Markdown
Owner

Closes #178

Summary

  • add sandbox_view_image to read bounded image files from the active sandbox
  • validate sandbox paths, image signatures, MIME types, dimensions, and file size before attaching bytes
  • bridge returned google.genai.types.Part values through ADK as separate visual inputs, including multiple images
  • keep binary image data out of persisted tool responses and lifecycle logs
  • guide Telegram image-file uploads and restored attachments to the new tool
  • register, document, and test the new capability

Validation

  • uv run ruff format
  • uv run ruff check
  • uv run mypy .
  • proxy-free full suite: 1,910 passed, 100% coverage

The four Docker contract tests could not run in this environment because Docker is not installed.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

feat: add a sandbox image-viewing tool for agent vision tasks

1 participant