Recipe 46: Semantic context paging #46

Recipe 46 of 60 · Level 4 (Advanced) · Memory & context · Score

Use case

Judge stored context chunks for relevance to the current task so Python can retain, page out, or rehydrate them while preserving original content and source links.

What to build

The folder recipes/46-semantic-context-paging/ with notebook.ipynb, README.md, and fixtures/, meeting the recipe contract. Start from python tools/new_recipe.py 46 and the template in recipes/_template/.

Build notes

• One relevance Score per stored context chunk for the current task.
• Python retains, pages out, or rehydrates chunks under a budget, preserving original content and source links exactly.
• Baseline: keep the most recent chunks.

Decision design

• Score. Describe every rubric level in words, in order. Show the score and the distribution over levels. Mapping, weighting, and arithmetic on scores happen in Python.

Level 4 scope

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

Acceptance criteria

• recipes/46-semantic-context-paging/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: Recall of needed chunks under the budget against the recency baseline, and a lossless round-trip 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/46-semantic-context-paging/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/46-semantic-context-paging/ 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)
• Blocked by Foundation: simulation and state primitives #70 (simulation and state primitives)
• Builds on Recipe 17: Passage reranking #17 (Passage reranking). 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.

• S01 · TypeSafe AI: Introduction: Typed questions over supplied state and atomic judgments composed in code.
• 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.

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.