Fix maintain intent alignment from scorecards

[saagpatel]

Summary

• Recompute portfolio intent alignment after scorecards are attached so on-track maintain repos stop carrying stale needs-review state.
• Add the canonical OrbitMechanics catalog contract while preserving the local checkout alias.
• Cover both the evaluator and scorecard-enrichment regression paths.

Verification

• pytest tests/test_portfolio_catalog.py tests/test_cli_hardening.py tests/test_weekly_command_center.py -q
• pytest tests/test_portfolio_catalog.py tests/test_cli_hardening.py tests/test_operator_acknowledgments.py tests/test_weekly_command_center.py -q
• python -m src.cli security-gate
• python -m src.cli saagpatel --repos OrbitMechanics AssistSupport CryptForge DeepTank LegalDocsReview ScreenshotAnnotate --scorecard --no-analyzer-cache --catalog config/portfolio-catalog.yaml --preflight-mode off
• python -m src.cli saagpatel --control-center

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 289ca0d84a

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]

Preserve urgent focus when trusting scorecards

For a maintain repo with an on-track scorecard but an operator queue state that resolves to Act Now or Revalidate (for example an urgent/blocked lane or revalidation-needed status), this unconditional scorecard fallback rewrites the intent alignment to aligned; _apply_scorecards then copies that status back onto the operator queue. That makes portfolio truth/control-center surfaces report an urgent or revalidation item as aligned, bypassing the existing focus guard just above that keeps maintain repos in review when there is active operator pressure.

Useful? React with 👍 / 👎.