feat: support guarded Codex max reasoning

[LogicNetworksTech]

What Changed

• Enable Codex max reasoning for gpt-5.6-sol and reject unverified model/effort pairings before launch or metadata creation.
• Pin Codex launches with no selected effort to xhigh while preserving effort=default in task metadata.
• Update dispatch validation, documentation, and shell coverage for the model-bound effort rules and explicit exclusion of ultra.

Risk Assessment

✅ Low: FM/captain, the change is well-bounded, internally consistent, and introduces no substantiated merge-blocking risk.

Testing

Completed 1 recorded test check.

• Outcome: ⚠️ 1 error across 1 run (12m58s)

Pipeline

Updates from git push no-mistakes

⏭️ **intent** - skipped

✅ No issues found.

✅ **Rebase** - passed

✅ No issues found.

✅ **Review** - passed

✅ No issues found.

⚠️ **Test** - 1 error

• 🚨 tests failed with exit code 1
• command -v tmux >/dev/null || { echo "tmux is required for e2e tests" >&2; exit 1; }; tmux -V; rc=0; for t in tests/*.test.sh; do echo "== $t =="; bash "$t" || rc=1; done; exit "$rc"

✅ **Document** - passed

✅ No issues found.

✅ **Lint** - passed

✅ No issues found.

✅ **Push** - passed

✅ No issues found.