Recipe 41: Approval scope review #41

Recipe 41 of 60 · Level 4 (Advanced) · Trust & security · Noul

Use case

Flag semantic mismatches between an approved task and a proposed tool action while Python enforces exact permissions and approval bindings.

What to build

The folder recipes/41-approval-scope-review/ with notebook.ipynb, README.md, and fixtures/, meeting the recipe contract. Start from python tools/new_recipe.py 41 and the template in recipes/_template/.

Build notes

• A Noul flags a semantic mismatch between the approved task and the proposed tool action.
• Python enforces exact permissions and approval bindings independently of the model.
• A test shows the model's answer can add a hold and can never grant an action.

Decision design

• Noul. Write each proposition as a statement that is true or false. One independent question per label or concern, sent together in one request. Noul has no confidence field, so each threshold is chosen from examples and evaluated.

Level 4 scope

Stateful workflows, provenance, adversarial cases, model calibration, or several integrated decision stages.

Acceptance criteria

• recipes/41-approval-scope-review/notebook.ipynb runs top to bottom offline, with no key and no network, and its outputs are committed
• Live mode is opt-in (JEV_COOKBOOK_LIVE=1 with TYPESAFE_API_KEY) and uses the same question definitions as the offline run
• Fixtures are synthetic, include the hard cases named in the build notes, carry gold labels, and pass the fixture validator
• Every response fixture records its provenance, and the notebook states which mode it ran in
• Evaluation: Precision and recall on mismatch fixtures, and the enforcement test.
• State, provenance, or policy rules are enforced in helpers.py and covered by tests that hold for any model answer
• Fixtures include adversarial, conflicting, or stateful cases, and the notebook walks through at least one
• No statement about Jev's quality, latency, or cost appears without recorded live inference; in a synthetic run, metrics are labelled as pipeline checks
• recipes/41-approval-scope-review/README.md says what the recipe teaches, how to run it, and what was and was not measured live
• The pull request changes only recipes/41-approval-scope-review/ and CI is green

Dependencies

• Blocked by Foundation: CI executes every notebook offline and validates fixtures #69 (CI executes every notebook offline and validates fixtures)
• Builds on Recipe 27: Function selection #27 (Function selection). Merge those first and reuse their patterns; do not copy their fixtures.
• Tracked in Epic: Level 4 · Advanced recipes #78

Sources

Read these before writing the questions.

• S02 · TypeSafe AI: Primitives (Questions): Choice, Noul, Score, independent questions, and dependent follow-up calls.
• S03 · TypeSafe AI: Confidence: Distribution-derived confidence and task-specific thresholds informed by observed outcomes.
• S04 · TypeSafe AI: How to build with TypeSafe: Narrow semantic judgments integrated with workflows, deterministic logic, and side effects controlled by code.
• S07 · TypeSafe AI: Jev 1.13 jaggedness: Version-specific limitations affecting arithmetic, context selection, adversarial content, and generation.

Out of scope

• Changes to shared code, the catalog, or the root README. If the shared package is missing something, open a foundation issue and link it here.
• Real side effects of any kind. Actions are simulated.