Handbook
L1.1 — Function against provided tests
Status: Demonstrated — retro-tagged L1.1b (Blueprints Example 1, poc-sandbox-offline)
Updated
Sub-level at a glance
| Parent level | L1 — Function |
| Autonomous unit | Single function against provided tests |
| Distinct assay evidence | Provided test file unchanged, turns green |
| Grade today | b (retro-tag) |
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 (L1 — Function) apply unchanged. Declaring this sub-level adds the distinct check:
- Provided test file unchanged in the diff, and it turns green after the change
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-l1-1.md — workcell-skeleton prompt declaring this sub-level, its evidence-to-return shape, and human gates.
Worked case
| Field | Value |
|---|---|
| Repo | forge-dark-factory PoC — sandbox fixture (poc-boundary campaign) |
| Goal | Fix failing multiply test with deterministic fake worker (zero tokens) |
| Evidence produced | runs/campaigns/poc-boundary/poc-sandbox-offline/run-20260702T093454-f9bdcf/{machine,human}/ — machine/run.json, machine/assay.json, machine/proof.json |
| Assay pass rationale | Core L1 evidence: final_status: pass, tests green. L1.1 _check_sublevel: provided_test_files declared and unchanged in changed_files (calculator.py only); provided test turns green without modification |
Related
- L1 — Function — parent level
- Autonomy levels hub