docs(context): add RULESET.TESTS.boundary-coverage + LEARNING.prompt-budget.boundary-gap

Adds four predicates derived from PR #3708 post-mortem:
- RULESET.TESTS.boundary-coverage — must test {limit-1, limit, limit+1} and near-reserve-distance inputs
- RULESET.TESTS.boundary-coverage.fixtures — required fixtures for budget/limit/quota/threshold code
- RULESET.TESTS.boundary-coverage.anti-pattern — names the trivially-large + trivially-small pairing as the failure mode
- LEARNING.prompt-budget.boundary-gap — full post-mortem of the UNNEEDED_TRIM + FALSE_HARDFAIL regressions