Part of #100 (EPIC). Workstream M. One issue = one PR.
Source: zmem deep audit 2026-09-10 (https://claude.ai/code/artifact/39012f75-25f0-441b-978f-cc90a3bd3a9d) and issue plan v3 (https://claude.ai/code/artifact/59e74242-17da-4416-9b00-0b0cf347837c); dependency DAG computed over all open PRs (edge kinds: Depends on = merged artifact, Schema after = migration lane, Gated on = #100 measurement/decision gate).
Labels: enhancement, severity:medium. Depends on: none. Gated on: G-3 (#155). Blocks: none.
Design. After the selective gate: if (top − second) / top < ZMEM_INJECT_MARGIN (default 0, i.e. off; recommended 0.05) and neither row is decision/constraint, keep only the top row; log margin=<value>; explain verdict margin_pruned.
Acceptance criteria. (a) Fixture scores 0.80/0.79/0.60 with margin 0.05 → one row; margin 0 → three. (b) constraint at 0.79 kept. (c) tests/test_eval_inject_runner.py negative controls unchanged (committed expected JSON equal); eval_replay --compare-baseline eval/baseline-replay.json --fail-under miss_delta=0 exits 0 with margin 0.05.
Part of #100 (EPIC). Workstream M. One issue = one PR.
Source: zmem deep audit 2026-09-10 (https://claude.ai/code/artifact/39012f75-25f0-441b-978f-cc90a3bd3a9d) and issue plan v3 (https://claude.ai/code/artifact/59e74242-17da-4416-9b00-0b0cf347837c); dependency DAG computed over all open PRs (edge kinds: Depends on = merged artifact, Schema after = migration lane, Gated on = #100 measurement/decision gate).
Labels: enhancement, severity:medium. Depends on: none. Gated on: G-3 (#155). Blocks: none.
Design. After the selective gate: if
(top − second) / top < ZMEM_INJECT_MARGIN(default 0, i.e. off; recommended 0.05) and neither row isdecision/constraint, keep only the top row; logmargin=<value>; explain verdictmargin_pruned.Acceptance criteria. (a) Fixture scores 0.80/0.79/0.60 with margin 0.05 → one row; margin 0 → three. (b)
constraintat 0.79 kept. (c)tests/test_eval_inject_runner.pynegative controls unchanged (committed expected JSON equal);eval_replay --compare-baseline eval/baseline-replay.json --fail-under miss_delta=0exits 0 with margin 0.05.