Bendik Aagaard LynghaugandClaude Fable 5.1
b6bdac6f62
`portal-trainer generate` turns a plain-words business intake into a content repo in three phases, each held to portal's question_lint: needs.yaml (then frozen, so the generator cannot weaken the spec to pass), structure (revised against the lint's findings until green), and wording (personas answered blind, misroutes fed back; a rewrite that breaks structure is reverted). Model output is written to disk only under aggregates.yaml, site.yaml and questions/**.yaml. `portal-trainer answer` is the blind answerer alone. The LLM is an external command, prompt on stdin, text on stdout: engines/ollama.sh (local Ollama), engines/anthropic.sh (API key), engines/mailbox.sh (hand each prompt to an agent or a person). portal-portal/ is the onboarding site as a portal content repo: the front door is the intake interview, records land in `onboardings` (open -> drafted <-> revising -> live | declined), and it passes its own needs spec. runs/uhhm-2026-09-21/ollama: qwen3:8b and granite4.1:8b as blind answerers on the same eight tasks. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01L4jrCgLiKKHAEFuZUJjckH
13 lines
447 B
Bash
Executable File
13 lines
447 B
Bash
Executable File
#!/bin/sh
|
|
# LLM backend that hands each prompt to whoever watches $MAILBOX:
|
|
# prompt-N.md goes out, the reply is read from reply-N.md. For driving
|
|
# the generator from an agent session, or by hand.
|
|
set -eu
|
|
: "${MAILBOX:?set MAILBOX to a directory}"
|
|
mkdir -p "$MAILBOX"
|
|
n=$(( $(ls "$MAILBOX" | grep -c '^prompt-' || true) + 1 ))
|
|
cat > "$MAILBOX/prompt-$n.md"
|
|
until [ -s "$MAILBOX/reply-$n.md" ]; do sleep 2; done
|
|
sleep 1
|
|
cat "$MAILBOX/reply-$n.md"
|