Files
ThothII/scripts/preprocess-smoke.sh
T

108 lines
4.2 KiB
Bash
Executable File

#!/bin/sh
set -eu
cd "$(dirname "$0")/.."
tmp=$(mktemp -d "${TMPDIR:-/tmp}/thoth-preprocess.XXXXXX")
project="thoth-preprocess-$$"
compose=""
cleanup() {
trap - EXIT HUP INT TERM
if [ -n "$compose" ]; then
$compose down --volumes >/dev/null
fi
test -z "$(docker ps -aq --filter "label=com.docker.compose.project=$project")"
test -z "$(docker volume ls -q --filter "label=com.docker.compose.project=$project")"
test -z "$(docker network ls -q --filter "label=com.docker.compose.project=$project")"
rm -rf "$tmp"
}
trap cleanup EXIT HUP INT TERM
mkdir -p "$tmp/source/evidence"
printf '%s\n' '# Evidence' 'generation one' >"$tmp/source/evidence/a.md"
for name in bootstrap migrator reader writer; do
printf '%s' "smoke-$name-$project" >"$tmp/$name"
chmod 0600 "$tmp/$name"
done
export THT_VECTOR_BOOTSTRAP_PASSWORD_SECRET_FILE="$tmp/bootstrap"
export THT_VECTOR_MIGRATOR_PASSWORD_SECRET_FILE="$tmp/migrator"
export THT_VECTOR_READER_PASSWORD_SECRET_FILE="$tmp/reader"
export THT_VECTOR_WRITER_PASSWORD_SECRET_FILE="$tmp/writer"
export THT_OLLAMA_URL=http://mock-embeddings:8081
cat >"$tmp/smoke.yaml" <<YAML
services:
mock-embeddings:
image: thothii-core:local
profiles: [preprocess]
entrypoint: [/opt/venv/bin/python, -c]
command:
- |
import json
from http.server import BaseHTTPRequestHandler, HTTPServer
class H(BaseHTTPRequestHandler):
def do_POST(self):
n=len(json.loads(self.rfile.read(int(self.headers['Content-Length'])))['input'])
body=json.dumps({'embeddings': [[1.0]+[0.0]*767 for _ in range(n)]}).encode()
self.send_response(200); self.send_header('Content-Length', str(len(body))); self.end_headers(); self.wfile.write(body)
def log_message(self, *args): pass
HTTPServer(('0.0.0.0',8081),H).serve_forever()
preprocess-evidence:
volumes:
- $tmp/source:/data/source:ro
depends_on:
vector-migrate: {condition: service_completed_successfully}
mock-embeddings: {condition: service_started}
preprocess-dwh:
depends_on:
vector-migrate: {condition: service_completed_successfully}
YAML
compose="docker compose -f compose.yaml -f deploy/compose.local-vector.yaml -f deploy/compose.preprocess.yaml -f $tmp/smoke.yaml --project-name $project --profile local-vector --profile preprocess"
$compose build preprocess-evidence
$compose up -d vector-db mock-embeddings
$compose run --rm vector-reconcile >/dev/null
$compose run --rm --no-deps vector-migrate >/dev/null
if [ "${1:-}" = "--cleanup-failure" ]; then
cleanup
test ! -e "$tmp"
echo "injected preprocessing failure cleanup passed."
exit 0
fi
generation_count() {
$compose run --rm --no-deps --entrypoint sh preprocess-evidence -c \
'find /data/workspaces/preprocess-evidence/corpus/generations -mindepth 1 -maxdepth 1 -type d 2>/dev/null | wc -l'
}
before=$(generation_count)
first=$($compose run --rm preprocess-evidence)
after_first=$(generation_count)
second=$($compose run --rm preprocess-evidence)
after_second=$(generation_count)
printf '%s' 'generation two' >>"$tmp/source/evidence/a.md"
third=$($compose run --rm preprocess-evidence)
after_third=$(generation_count)
dwh=$($compose run --rm preprocess-dwh)
python3 - "$first" "$second" "$third" "$before" "$after_first" "$after_second" "$after_third" <<'PY'
import json, sys
a, b, c = map(json.loads, sys.argv[1:4])
before, first_count, second_count, third_count = map(int, sys.argv[4:])
assert len(a["changed"]) == 1 and not a["unchanged"]
assert len(b["unchanged"]) == 1 and not b["changed"]
assert len(c["changed"]) == 1 and c["generation"] != a["generation"]
assert all(row["published"] for row in (a, b, c))
assert first_count == before + 1
assert second_count == first_count
assert third_count == second_count + 1
PY
python3 - "$dwh" <<'PY'
import json, sys
assert json.loads(sys.argv[1])["status"] == "succeeded"
PY
active=$($compose run --rm --no-deps --entrypoint sh preprocess-evidence -c \
'cat /data/workspaces/preprocess-evidence/corpus/ACTIVE')
python3 - "$third" "$active" <<'PY'
import json, sys
assert json.loads(sys.argv[1])["generation"] == sys.argv[2].strip()
PY
echo "real Compose preprocessing unchanged rerun, mutation, DWH job, and ACTIVE publish passed."
cleanup
test ! -e "$tmp"