feat(pillar): add automatic LiteLLM context headers

[eagle-p]

Title

feat(pillar): add automatic LiteLLM context headers to Pillar guardrail

Relevant issues

N/A

Pre-Submission checklist

• I have Added testing in the tests/litellm/ directory, Adding at least 1 test is a hard requirement
• I have added a screenshot of my new test passing locally
• My PR passes all unit tests on make test-unit
• My PR's scope is as isolated as possible, it only solves 1 specific problem

Type

🆕 New Feature

Changes

Summary

Automatically passes LiteLLM virtual key context as X-LiteLLM-* headers to Pillar guardrail for application/user tracking. No configuration required - works out of the box.

What Changed

• Automatic header passing: Extracts context from LiteLLM virtual keys and passes 7 standard headers
• Headers sent: X-LiteLLM-Key-Name, X-LiteLLM-Key-Alias, X-LiteLLM-User-Id, X-LiteLLM-User-Email, X-LiteLLM-Team-Id, X-LiteLLM-Team-Name, X-LiteLLM-Org-Id
• Security: Excludes sensitive data (metadata and API key tokens)
• Zero config: Always enabled - no additional setup needed

Files Changed

• litellm/proxy/guardrails/guardrail_hooks/pillar/pillar.py - Added header extraction logic
• tests/test_litellm/proxy/guardrails/test_pillar_guardrails.py - Added 30 comprehensive tests (all passing)
• docs/my-website/docs/proxy/guardrails/pillar_security.md - Updated documentation

Benefits

• Enables Pillar to track and analyze requests by application, user, team, and organization
• Engineers don't need to manually pass any headers
• Uses existing LiteLLM virtual key infrastructure

[vercel]

@eagle-p is attempting to deploy a commit to the CLERKIEAI Team on Vercel.

A member of the Team first needs to authorize it.