Improve monthly review audit controls

[Pigbibi]

Summary

This PR tightens the monthly audit handoff for the upstream crypto snapshot repository.

• require same-cycle shadow outputs before generating the monthly review briefing
• avoid duplicated Claude Primary Review headings when the primary review markdown is re-rendered with a secondary review
• align README/runbook documentation with the current AI review and monthly optimization automation model
• tighten the Binance zero-trade completion guard copied in the shared auto-optimization helper

Validation

• python3 -m pytest tests/test_monthly_review_briefing.py tests/test_render_monthly_ai_review.py tests/test_prepare_auto_optimization_pr.py

Refs QuantStrategyLab/AuditOrchestrator#1

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: e7b65e51e8

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

[chatgpt-codex-connector]

Enforce shadow output recency before generating review package

require_shadow_outputs currently checks only whether the two shadow files exist, so a stale monthly_shadow_build_summary.json/track_summary.csv from a previous month will still pass and let main() emit a review package. In that case the run can complete with only warnings even though the docs and commit intent require same-cycle shadow evidence, which can lead to monthly reviews being generated from mismatched data. Please validate the shadow artifacts’ as_of_date against the current cycle (or fail when mismatch warnings are present) before proceeding.

Useful? React with 👍 / 👎.