Chapter 6 lab — the linear paradigms
# Chapter 6 lab — the linear paradigms
Three recipes, one per linear paradigm, plus the captured validation story.
# Files
add_truncate.erpe— pipeline: plan stage (read-only) → implement stage (write + pytest). Second stage reads the first stage’s capture.summarize_funcs.erpe— chainer: three links, eachprompt+from+capture. Links takeprompt, nevergoal.polish_docstring.erpe— reflection:reviewwritesscratch.review/scratch.review_issues;revise when scratch.review contains issues:runs a declared fixer agent.
# Reproduce
relurplint --check recipes --workspace . # 0 diagnostics
# restart relurpish so all three register, then pin and dispatch each:
# /recipe euclo.thoughtrecipe.add_truncate
# /recipe euclo.thoughtrecipe.summarize_funcs
# /recipe euclo.thoughtrecipe.polish_docstringRead the receipts after each dispatch:
jq -c 'select(.resourceLogs) | .resourceLogs[]?.scopeLogs[]?.logRecords[]?
| select(.eventName=="euclo.execution.complete")' \
.relurpify_state/telemetry/otlp/*.jsonl | tail -1# Captured validation story (verification machine, gemma4:e4b on CPU)
| Layer | What it catches | Captured example |
|---|---|---|
| lint | grammar, types, declarations | [error recipes.lower] ...:21:9: unknown agent "fixer" |
| boot | vocabulary + prompt-import resolution | (Ch 4–5 recipes) |
| runtime | execution-only requirements | chainer link "link" requires a prompt clause (goal-shaped links, v1 draft) |
Also captured:
- Infrastructure rejection: a second relurpish instance held the
Badger lock →
boot.degraded+task.rejectedwithCannot acquire directory lock on ".../memory/ast_index". One workspace, one relurpish. - Anomalous receipt, flagged not explained: the corrected chainer
completed with
outcome: "success",llm_calls: "0"— flagged[NEEDS CONFIRMATION: chainer link execution and counters at your pin]. - Paradigm contract pointers: react (react_think_node.go — decision parse/repair), reflection (contract.go — scratch.review guarantee), pipeline (contract.go — stage order), chainer (named/euclo/thoughtrecipes/chain_builder.go — link requirements).
- Cost expectation: 1–5 minutes per model call on the verification CPU; two-phase recipes multiply. Run on your hardware; read receipts.