// Run metareview post-merge learning after a PR or local merge completes; curates reusable review knowledge, records discarded low-value candidates, and appends reviewer calibration.
Review a spec, plan, design, decomposition, architecture doc, pre-mortem, runbook, or acceptance report with metareview.
Run metareview's deterministic epic-ready gate before closing or landing an epic; checks child review evidence, unresolved blockers, integration contradictions, and intent drift.
Run metareview's deterministic PR-ready gate before pushing or opening a PR; checks unresolved blockers, validation evidence, branch diff risks, generated PR evidence, and optional GitHub review context.
Run metareview's deterministic task-done code review gate before claiming a local task is complete; use for task closure, chunk review, or pre-PR local review when code changed.
Detect repository mode and prepare metareview review artifacts without overwriting metaswarm or Beads-owned files.
Show metareview repository mode, available integrations, and unresolved review state.
| name | learn-post-merge |
| description | Run metareview post-merge learning after a PR or local merge completes; curates reusable review knowledge, records discarded low-value candidates, and appends reviewer calibration. |
Run this after a PR merge or after a local epic lands.
metareview learn --post-merge <pr-number> --base <pre-merge-ref> [--github-pr <number>] [--session-root <path>]
Use --base for the final reviewed diff, --github-pr when the GitHub PR number differs from the merge identifier, and --session-root when the relevant coding session history is in a nonstandard location.
docs/metareview/learning/.GitHub and session history are optional local context. Missing adapters are recorded as unavailable context rather than failing learning.
In a metaswarm flow:
metareview review task-done <task-id-or-path> runs when a work unit claims done.metareview review epic-ready <epic-id-or-path> runs before an epic is called locally complete.metareview review pr-ready --base <base-ref> runs before PR push or merge readiness.metareview learn --post-merge <pr-number> --base <pre-merge-ref> runs after confirmed PR merge.Post-merge learning is advisory by default. In strict mode, the caller treats a nonzero learning exit as blocking release cleanup until the run succeeds or is explicitly waived.