# Labs — Cooking Agentic Thoughts with Relurpify

This folder holds every artifact the book builds, exactly as it reads at the end of the chapter that introduced it. It is the book’s cumulative code listing; Appendix D is generated from it.

# Layout

• ch01-stringkit/ — the stringkit demo repo as seeded in Chapter 1 (buggy slugify, one intentionally failing test, captured transcript).
• ch02-first-turn/ — the Chapter 2 receipts command card and the captured two-turn session table.
• ch03-workspace-baseline/ — the annotated workspace.yaml, the counted tree inventory, and the captured Chapter 3 experiments.
• ch04-explain-test/ — the reader’s first recipe, the pin acknowledgment, and both route-selection receipts (pinned vs lattice).
• ch05-triage/ — the full-toolkit triage recipe, the zero-model gate_demo recipe, the captured linter errors, and the frame finding.
• ch06-linear-paradigms/ — the three linear-paradigm recipes, the three-layer validation story, and the contract pointers.
• ch07-planning-paradigms/ — the planning-family recipes, the captured governance catch, and the llm_calls counter flag.
• ch08-prompts/ — the edited react system prompt, the resolution receipt shape, and the two flagged doc-vs-build deltas.
• ch09-agent-tests/ — the stringkit regression suite, the red capture with its OSB receipt chain, and the three infra gotchas.
• ch10-house-style/ — the live prompts with the chapter’s edits, the drafting recipe, the wiring finding, and the ladder cheat.
• ch11-out-of-loop/ — the final exam: the queued repair’s transcript, diff, closing receipt, and the supervision command card.
• verify.sh — the tiered verifier. See below.

# Prerequisites

• The relurpify binaries built from tag BETA-RC1-FALL2026 (go build -o relurpish ./app/relurpish, go build -o relurplint ./app/relurplint). Source builds report relurpish dev (commit none, built unknown).
• Python 3 with pytest for the stringkit chapters.
• Ollama serving gemma4:e4b — the book’s model backend (the materialization default). The offline scripted backend appears only where the book says so (deterministic test tiers).
• Docker (and gVisor runsc on Linux for the default sandbox backend) for the tiers that boot the runtime.

# The verifier

./verify.sh ch01          # runs the Chapter 1 check

Tiers, and what each one honestly proves:

1. lint (Chapters 4+) — materializes a scratch workspace with relurpish doctor --workspace <scratch> (plain doctor materializes a fresh workspace without prompting; --fix re-materializes and asks before overwriting), overlays the chapter’s relurpify_cfg/ files, and runs relurplint --check recipes|prompts|all --workspace <scratch>. Proves grammar, schema, and load-time rules.
2. boot (Chapters 4+) — additionally registers the overlaid artifacts in a booted offline runtime. Proves what lint cannot: tool-vocabulary and prompt-import resolution happen at boot.
3. behavior (Chapter 9+) — runs agenttest suites offline and compares against recorded expectations.

The Chapter 1 check is simpler than all three tiers: it runs stringkit’s tests in a scratch copy and asserts the seeded failure — one test red, one green, exactly as captured in ch01-stringkit/expected-failure.txt.

# Honesty rules

• Every transcript in the labs was produced by a real run on a real machine (Linux, Docker + gVisor present, Python 3.14, pytest 9.1, Go 1.27).
• Where a transcript was path-normalized (for example a scratch directory rendered as ~/code/stringkit), the chapter or this README says so.
• Binaries built from the tree that became BETA-RC1-FALL2026; source builds report dev in --version.