feat: Jira Peer Review Integration & Zhipu AI Provider

[ipanov-ritech]

Summary

This PR adds two major features to PR Agent:

1. 🎫 Jira Peer Review Integration

Validates PRs against linked Jira tickets like a senior developer would:

• Extracts ticket references from PR title, branch name, or commit messages
• Fetches ticket details from Jira (description, acceptance criteria, story points)
• Rates ticket quality to identify poorly-defined requirements
• Validates implementation against derived requirements
• Provides verdict with blockers, warnings, and recommendations

2. 🤖 Zhipu AI Provider

Adds support for Zhipu AI using their Anthropic-compatible API endpoint.

Changes

• Add ZhipuProvider class with Anthropic-compatible API
• Add peerReview section to Zod config validation schema (was being stripped)
• Make criteriaId optional in AC validation to prevent parsing errors
• Update README with comprehensive peer review documentation
• Update README with Zhipu AI provider details
• Add verbose debug output for troubleshooting

Configuration

{
  "peerReview": {
    "enabled": true,
    "provider": "jira",
    "instanceUrl": "https://your-company.atlassian.net",
    "email": "your-email@company.com",
    "apiToken": "your-jira-api-token",
    "defaultProject": "PROJ"
  }
}

Example Output

🔍 PEER REVIEW ANALYSIS

📋 LINKED TICKET: PROJ-123
📊 TICKET QUALITY: 85/100 (GOOD)
✅ COMPLIANCE: 92%

🎯 VERDICT: ✅ APPROVED (Confidence: 85%)

Test Plan

• Tested with Zhipu AI provider on real PR
• Tested peer review integration with Jira Cloud
• Verified ticket extraction from PR title/branch
• Verified requirements validation against acceptance criteria

🤖 Generated with Claude Code