One binary: the lint and the trainer are commands of portal

portal serve runs a site; portal lint is what iris was; portal plan,
build, report and the rest are what portal-trainer was. One source at
one version, so the three never disagree about what content means.
Both histories are merged in (subtree). The release attaches the bare
binary for a content repo's CI. The trainer's plans, intakes, engines
and reference prompt come along; its runs stay in the old repo.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01GT37Z1Xtfd9pUuQtMTg6Yt

engines/ollama.sh

@@ -0,0 +1,18 @@
+#!/bin/sh
+# LLM backend for portal-trainer on a local Ollama: prompt on stdin,
+# text on stdout. MODEL, OLLAMA_HOST, NUM_CTX and TIMEOUT override.
+# Thinking is off: the generator wants files, the answerer wants JSONL.
+# The simulator sets SEED (so the same case replays the same way
+# against two versions of a site), FORMAT=json and TEMPERATURE.
+set -eu
+jq -Rs --arg model "${MODEL:-qwen3:8b}" --argjson ctx "${NUM_CTX:-32768}" \
+  --argjson temp "${TEMPERATURE:-0.2}" --arg seed "${SEED:-}" --arg format "${FORMAT:-}" \
+  '{model: $model, stream: false, think: false,
+    options: ({num_ctx: $ctx, temperature: $temp}
+              + (if $seed == "" then {} else {seed: ($seed | tonumber)} end)),
+    messages: [{role: "user", content: .}]}
+   + (if $format == "json" then {format: "json"} else {} end)' |
+curl -sS --fail-with-body --max-time "${TIMEOUT:-1800}" \
+  "${OLLAMA_HOST:-http://127.0.0.1:11434}/api/chat" \
+  -H "content-type: application/json" --data-binary @- |
+jq -er '.message.content'