feat: deepen research intelligence output

[Techris93]

Summary

• request comprehensive evidence-led research assessments from bridge models
• normalize nested analyst brief fields from OpenCodex providers
• document the complete structured result contract

Verification

• 430 Core tests passed, 4 subtests passed
• MkDocs strict build passed
• git diff --check passed

[chatgpt-codex-connector]

You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard.
To continue using code reviews, you can upgrade your account or add credits to your account and enable them for code reviews in your settings.