fix: prevent AI PR Review agents from failing checks on large PRs

[imran-siddique]

Description

Fixes AI PR Review workflow checks (Code Review, Security Scan, Breaking Changes, Docs Sync, Test Coverage) showing as red X failures on large PRs like #2236.

Root Cause

1. Diff truncation limit (24k chars) exceeded model context windows, causing HTTP 413 from GitHub Models API
2. Fallback model (gpt-4o-mini) has only 8k token limit, too small for any PR review
3. Catch block set \process.exitCode = 1, making informational checks appear as CI failures

Changes

• Reduce diff truncation from 24k to 12k chars to stay within model context windows
• 413 retry with truncation: on payload-too-large, halve the user prompt before retrying
• Graceful failure: replace \process.exitCode = 1\ with ::warning::\ annotation so AI agents don't produce red X marks in the checks list
• Better fallback: use gpt-4o as fallback instead of gpt-4o-mini

Type of Change

• Bug fix (non-breaking change that fixes an issue)

Package(s) Affected

• docs / root

Checklist

• My code follows the project style guidelines (ruff check)
• All new and existing tests pass (pytest)
• I have signed the Microsoft CLA

AI Assistance

• I can explain every meaningful change in this PR
• I have run tests and verification appropriate for this change
• No part of this PR was autonomously submitted by an AI agent without my review

GitHub Copilot assisted with drafting commit messages.

[github-actions]

🤖 AI Agent: test-generator — `.github/actions/ai-agent-runner/action.yml`

.github/actions/ai-agent-runner/action.yml

• test_diff_truncation -- Validate that diffs exceeding 12k characters are truncated correctly.
• test_413_retry_logic -- Ensure the retry mechanism halves the user prompt on HTTP 413 errors.
• test_graceful_failure -- Confirm that errors log warnings instead of failing the workflow.

.github/workflows/ai-pr-review.yml

• test_fallback_model_switch -- Verify that the fallback model switches to gpt-4o instead of gpt-4o-mini.

[github-actions]

🤖 AI Agent: security-scanner — View details

No security issues found.

[github-actions]

🤖 AI Agent: breaking-change-detector — API Compatibility

API Compatibility

No breaking changes detected.

[github-actions]

🤖 AI Agent: code-reviewer — Action Items:

TL;DR: 0 blockers, 1 warning. Fix improves robustness of AI PR review checks but requires further testing for edge cases.

#	Sev	Issue	Where
1	Warn	Edge cases for 413 retry truncation logic	.github/actions/ai-agent-runner

Action Items:

• None.

Warnings:

#	Issue	Where	Follow-up
1	Edge cases for 413 retry truncation logic	.github/actions/ai-agent-runner	Fine as follow-up PRs.

[github-actions]

🤖 AI Agent: docs-sync-checker — Docs Sync

Docs Sync

Documentation is in sync.

[github-actions]

PR Review Summary

Check	Status	Details
🔍 Code Review	⚠️ Warning	See details
🛡️ Security Scan	✅ Passed	No issues found
🔄 Breaking Changes	✅ Passed	No issues found
📝 Docs Sync	✅ Passed	No issues found
🧪 Test Coverage	✅ Completed	Analysis complete

Verdict: ⚠️ Ready for human review