{"version":"2.1.290","anchor":"medium-and-high-effort-now-map-to-a-different-measured-profi","canonical_anchor":"medium-and-high-effort-now-map-to-a-different-measured-profi","heading":"\/code-review medium now runs the high-effort recipe on most models","tier":"notice","area":"Code Review","scope":"individual","heads_up":true,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.290\/e\/medium-and-high-effort-now-map-to-a-different-measured-profi","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.290","markdown":"### `\/code-review medium` now runs the high-effort recipe on most models\n\nOn every model without its own `\/code-review` row, Opus 5.5 included, `medium` now runs the eight-angle high recipe instead of a single pass. `high`, `xhigh` and Opus 5 are unchanged.\n\n**What**\n\n`\/code-review` (alias `\/review`) picks a review recipe from a table keyed by model and effort level. Only `claude-opus-5`, `claude-opus-4-8` and `claude-sonnet-5` have their own row; every other model, Opus 5.5 included, reads the `default` row. In that row `medium` moved from the `o5-bmin` recipe to `o48-high-v1`, so it now runs the same recipe as `high`.\n\n**Details**\n\n- `o5-bmin`, the old medium: one careful pass over the diff, up to 15 findings.\n\n- `o48-high-v1`, the new medium: eight finder angles run in the same context (line-by-line scan, removed behaviour, cross-file callers, cleanup, altitude, conventions), up to 6 candidates each, deduplicated with no verify step and biased toward recall, up to 10 findings unless `--max-findings` sets another limit.\n\n- `low`, `high`, `xhigh` and `max` are unchanged in the `default` row; `high` was already `o48-high-v1` in 2.1.289.\n\n- The `claude-opus-5` row still maps `medium` and `high` to `o5-bmin`. The Opus 4.8 and Sonnet 5 rows did not change.\n\n- This is not the session's `\/effort` setting, and the model's reasoning effort does not change: both recipes pass the level you typed through as the effort.\n\n**Why**\n\nOn Opus 5.5 or any other model without its own row, `\/code-review medium` is now a longer review that surfaces more uncertain findings than it did in 2.1.289, and its default cap drops from 15 findings to 10.\n\n**Evidence**\n\n`medium: { ...H(\"o48-high-v1\"), measuredExternal: !0 }`\n\n- Area: Code Review\n- Names: `\/code-review`\n- Tier: You'll notice\n- Useful: 3\/5\n- Signal: 2\/5\n- Scope: individual\n- Heads-up: yes"}