Add Codex MCP multi-LLM workflow builder and guide

[2-Coatl]

Summary

• add the CodexMCPWorkflow builder with provider-aware briefs and expose it from the orchestrators package
• document Codex MCP single and multi agent workflows, update the ExecPlan, and publish the new agent catalog entry
• extend documentation alignment tests to protect the new guide and cross-linking

Testing

• pytest scripts/coding/tests/ai/orchestrators/test_codex_mcp_workflow.py
• pytest docs/testing/test_documentation_alignment.py

---

Codex Task

[chatgpt-codex-connector]

💡 Codex Review

https://github.com/2-Coatl/IACT---project/blob/7d7345039c5a3ac60a194539262dc9effec792b4/.github/workflows/code-quality.yml#L26-L28
Allow code-quality workflow to fail on test errors

The new code-quality.yml workflow invokes ./scripts/run_all_tests.sh … || true (lines 26‑28). Because the command is forcibly marked successful, any failing test suite is ignored and the job still exits 0, defeating the purpose of adding this quality gate. Remove the || true (or otherwise propagate the exit status) so regressions in run_all_tests.sh actually break the CI check instead of passing silently.

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".