Handbook

L2.1 — Mechanical multi-file change

Status: Defined

Updated

Sub-level at a glance
Parent level L2 — Change-set
Autonomous unit Mechanical multi-file (rename / apply-pattern)
Distinct assay evidence ≥2 files with same-shaped hunks; no behavior-test delta
Grade today a

Canonical policy, grades a-d, and promotion criteria: Autonomy levels (Blueprints). Per-project scoring: Autonomy maturity framework (Blueprints).

Gates and evidence

All gates and core evidence of the parent level (L2 — Change-set) apply unchanged. Declaring this sub-level adds the distinct check:

  • ≥2 files with same-shaped hunks (identical added/removed-line-count signature) and no behavior-test delta

A run that fails the sub-level check may still be reported at the plain parent-level grain if the parent's evidence holds — sub-level claims are strictly additive.

Prompt pack

Execution rubric (repo path, nav-hidden): prompts/autonomy/sublevel-l2-1.md — workcell-skeleton prompt declaring this sub-level, its evidence-to-return shape, and human gates.

Worked case

Hypothetical case — worked-through narrative in Blueprints Example 8; no matching campaign run exists.

Field Value
Repo forge-lenses (hypothetical branch)
Goal Mechanical rename legacy_id → record_id across utils/helpers.py and utils/compat.py
Evidence produced Pattern: runs/campaigns/<campaign>/<item>/run-*/machine/ with hunk_shapes: [(1,1),(1,1)] and no test files in diff
Assay pass rationale L2.1 _check_sublevel: hunk_shapes has ≥2 entries with identical tuple; no _is_test_file in changed_files
Assay fail example If tests/test_helpers.py were modified → L2.1 evidence: behavior-test delta present (test files changed)