Batch manual-sprint planner checkpoint reviews

[rica-v3]

Summary

• gate requirement checkpoint reviews on both a successful TODO outcome and at least one valid pending requirement candidate
• share the same review policy between manual and autonomous sprint execution
• batch all currently pending candidates into one existing planner reconciliation request
• document the optimized manual-sprint review behavior

Why

Manual sprints previously forced an ongoing_review planner call after every completed or committed TODO, even when no requirement candidates existed. Planner runs with xhigh reasoning by default, so these no-op reviews added deterministic model cost and critical-path latency without changing sprint scope.

Impact

For a manual sprint with N successful TODOs, no new requirements, and execution within one configured review interval, forced ongoing planner reviews fall from N to 0.

Pending requirements still trigger a review at the next completed or committed TODO checkpoint. Multiple candidates are carried in one reconciliation request. Initial/recovery reviews, interval-based reviews, TODO execution, architecture review, QA, version control, and closeout behavior are unchanged.

Validation

• python -m unittest discover -s teams_runtime/tests - 760 tests passed
• focused sprint lifecycle and execution suites - 69 tests passed
• python -m compileall -q teams_runtime - passed
• git diff --check - passed
• no test-started runtime process remained after validation