feat(improve): proposals from plane memory through the unchanged gate (harnessx-removal task 3)

improve/memory.py: rules M1 (enabled->shadow on repeated false alerts across
>=2 repositories, no agreed or site_match hit) and M2 (shadow->enabled on
>=2 agreed declared sites no enabled rule catches); M3 disputed families are
advisory (signals.json) and never reach the validator. The train-on-test
guard drops rows of --qualify-population, gated benchmark cases and holdout
pair repositories before any rule sees a row. run_round(proposals=...) adds
memory edits after the benchmark's through the unchanged validator and gate;
provenance (row ids, object keys and versions, counts, exclusions, index
digest) goes to memory_proposals.jsonl and the journal's evidence field;
proposal_outcome rows are written back after a non-dry run.
ousast improve --memory is opt-in; default improve output is byte-identical
to the task-1 baseline.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
Claude-Session: https://claude.ai/code/session_01EmM1j46qgKMh3zqD1QMwEo

.kiro/specs/harnessx-removal/tasks.md

@@ -22,7 +22,7 @@ and passed its fixture test. Every task is a commit gated on the full suite's ow
   - Fixture tests: rows from a recorded Run, reuse on an unchanged pin, recompute on a changed one, disk refusal.
   - _Requirements: 6.1, 6.4_
 
-- [ ] 3. Proposals from memory
+- [x] 3. Proposals from memory
   - `improve/memory.py` with rules M1 (demote) and M2 (promote) and the advisory disputed-family signal;
     `run_round(proposals=...)`; `ousast improve --memory` (opt-in; default output byte-identical); provenance per
     proposal in the sidecar and journal; the train-on-test guard (qualification population, gated benchmark cases,