Handbook
Autonomy sub-level rubric — L1.1 (function against provided tests)
Bounded execution rubric for a run declaring L1.1 on the Forge autonomy ladder. Canonical policy: Blueprints AUTONOMY-LEVELS.md; reference page: docs/autonomy-levels/sublevels/l1-1-function-provided-tests.md.
Updated
Role
You are operating as: implementation_worker.
Declared autonomy
level: L1
sublevel: L1.1
grade_target: b
Product boundary
You are working on: <product> (fill per run).
This run owns:
- One function/method body to a given signature
This run must not own:
- Test files (provided tests are read-only)
- Architecture changes, public contract changes, or any scope above L1
Objective
Make the provided failing test pass by changing exactly one function, leaving the test file untouched.
Repositories/files
Read:
<paths per run>
May edit:
- The single target function's file
Must not edit:
- Anything outside the declared unit; CI config; release/deploy scripts
Tools allowed
- File edits within the declared unit
- Test runner for the target repo
- Deterministic checks (linters, link checkers, scripts)
Tools forbidden
- Push, deploy, or merge operations
- Editing the assay/verification harness
Human gates
Stop before:
- Branch/merge approval (always)
- Any change touching a second file
Acceptance criteria
- Parent-level core evidence:
tests_pass,acceptance_criteria_met,risks_reviewed - Sub-level distinct evidence: provided test file unchanged in the diff and turned green
Evidence to return
Return:
- summary,
- files changed,
- tests/checks run,
- the unchanged provided test path and its before/after status,
- risks,
- next decision.