Repository navigation
Python: Clarify binary content purview classification - #10103
westey (westey-m) merged 1 commit into
Conversation
There was a problem hiding this comment.
🟢 Approval recommended
No active review issues were identified in the documentation updates clarifying Purview binary-content classification and DLP policy behavior.
No open issues 🎉
What changed in this PR
This documentation-only PR clarifies how the Python and .NET Purview integrations classify binary content, aligning package documentation with consumer integration guidance.
Changes:
- Explains that binary prompts use
UploadTextand binary responses useDownloadText, rather than file activities. - Warns that DLP policies targeting only
UploadFileorDownloadFiledo not block binary content through these integrations.
| File | Description |
|---|---|
| skills/agent-framework-builder-python/references/integrations.md | Adds Python Purview activity and DLP policy guidance. |
| skills/agent-framework-builder-dotnet/references/integrations.md | Adds equivalent .NET Purview guidance. |
| python/packages/purview/README.md | Documents binary-content activity mapping for both Python middleware classes. |
| dotnet/src/Microsoft.Agents.AI.Purview/README.md | Documents binary-content activity mapping for agent and chat middleware. |
Review effort: Balanced
There was a problem hiding this comment.
MAF Automated Review — Iteration 1
Result: No findings
Scope: full PR (1 commit(s)): 4bd1f3ddf42e
Model: gpt-5.6-sol
Overview
This documentation-only change accurately clarifies that both Purview middleware implementations retain UploadText and DownloadText activities when submitting binary content. The .NET and Python conversion paths preserve non-empty binary payloads as Purview binary content without changing the middleware-selected activity, and existing tests pin both aspects of that contract. No publishable risk remains in the authoritative diff.
Reviewed the supplied pull-request change set across correctness, security/reliability, architecture, and failure behavior.
No publishable findings remained after source verification for this scope.
Motivation & Context
Improve documentation to explain how binary content is classified.
Description & Review Guide
Improve documentation to explain how binary content is classified.
Related Issue
Fixes #
AI Assistance
AI assistance details:
Contribution Checklist
breaking changelabel (or add "[BREAKING]" to the title prefix, before or after any language prefix) — a workflow keeps the label and title prefix in sync automatically.