Engine Self-Improving

Timeline

1. 1

   Start

   Feedback reviewed

   6 evolutions proposed — prioritized gate effectiveness + promotion review as highest leverage

2. 2

   20m

   Schema updated

   gate_checks gains prevented_spin/evidence/missed_issue; promotion_review block added

3. 3

   35m

   _TEMPLATE.json updated

   New blocks pre-scaffolded for every future session

4. 4

   60m

   build-trends.mjs updated

   Gate effectiveness aggregation, promotion pipeline aggregation, engine health scoring factors, console signals

5. 5

   70m

   Verified + committed

   build:trends runs clean, engine-health.md updated, committed

What shipped

• gate_checks[].prevented_spin — bool/null: did this gate catch a real spin?

• gate_checks[].evidence — string/null: what spin would have occurred without it?

• gate_checks[].missed_issue — string/null: what did the gate fail to catch?

• promotion_review block — observations[], promoted[] (with destination+type+reason), not_promoted[] (with reason)

• build-trends.mjs §Gate Effectiveness — aggregates per-gate: times run, prevented, clean, uncertain, missed issues

• build-trends.mjs §Promotion Pipeline — aggregates promoted/not-promoted across sessions, flags repeated non-promotions

• Engine health scoring: +3/proven gate (cap 9), -4/theater gate; +5 for promotion rate ≥60%, -6 for 0 promotions after 3+ sessions

• engine-health.md §Gate Effectiveness + §Promotion Pipeline sections with tables

• Console signals: theater gate warnings, proven gate confirmations, repeated non-promotion flags

• _TEMPLATE.json pre-scaffolded with both new blocks

• _SCHEMA.md documented with usage guidance, including 'theater vs proven' framing