161 lines
6.2 KiB
Bash
Executable File
161 lines
6.2 KiB
Bash
Executable File
#!/bin/sh
|
|
set -eu
|
|
cd "$(dirname "$0")/.."
|
|
|
|
if [ "${1:-}" = "--cleanup-failure" ] && [ -z "${PREPROCESS_SMOKE_CHILD:-}" ]; then
|
|
child_project="thoth-preprocess-failure-$$"
|
|
child_tmp=$(mktemp -d "${TMPDIR:-/tmp}/thoth-preprocess-failure.XXXXXX")
|
|
set +e
|
|
PREPROCESS_SMOKE_CHILD=1 PREPROCESS_SMOKE_INJECT_FAILURE=1 \
|
|
PREPROCESS_SMOKE_PROJECT="$child_project" PREPROCESS_SMOKE_TMP="$child_tmp" "$0"
|
|
child_status=$?
|
|
set -e
|
|
test "$child_status" -eq 97
|
|
test ! -e "$child_tmp"
|
|
test -z "$(docker ps -aq --filter "label=com.docker.compose.project=$child_project")"
|
|
test -z "$(docker volume ls -q --filter "label=com.docker.compose.project=$child_project")"
|
|
test -z "$(docker network ls -q --filter "label=com.docker.compose.project=$child_project")"
|
|
echo "injected preprocessing failure preserved status and cleaned every owned resource."
|
|
exit 0
|
|
fi
|
|
|
|
tmp=${PREPROCESS_SMOKE_TMP:-$(mktemp -d "${TMPDIR:-/tmp}/thoth-preprocess.XXXXXX")}
|
|
project=${PREPROCESS_SMOKE_PROJECT:-thoth-preprocess-$$}
|
|
compose=""
|
|
cleanup() {
|
|
original_status=$?
|
|
cleanup_failed=0
|
|
set +e
|
|
if [ -n "$compose" ]; then
|
|
$compose down --volumes >/dev/null
|
|
test "$?" -eq 0 || cleanup_failed=1
|
|
fi
|
|
test -z "$(docker ps -aq --filter "label=com.docker.compose.project=$project")" || cleanup_failed=1
|
|
test -z "$(docker volume ls -q --filter "label=com.docker.compose.project=$project")" || cleanup_failed=1
|
|
test -z "$(docker network ls -q --filter "label=com.docker.compose.project=$project")" || cleanup_failed=1
|
|
rm -rf "$tmp"
|
|
test ! -e "$tmp" || cleanup_failed=1
|
|
if [ "$original_status" -ne 0 ]; then
|
|
exit "$original_status"
|
|
fi
|
|
if [ "$cleanup_failed" -ne 0 ]; then
|
|
exit 1
|
|
fi
|
|
}
|
|
trap cleanup EXIT
|
|
trap 'exit 129' HUP
|
|
trap 'exit 130' INT
|
|
trap 'exit 143' TERM
|
|
|
|
mkdir -p "$tmp/source/evidence"
|
|
printf '%s\n' '# Evidence' 'generation one' >"$tmp/source/evidence/a.md"
|
|
bundle="$tmp/thothii.secrets"
|
|
printf '%s\n' 'THT_MODEL_API_KEY=smoke-model-key' >"$bundle"
|
|
chmod 0600 "$bundle"
|
|
printf '%s\n' '{}' >"$tmp/pi-auth.json"
|
|
printf '%s' 'smoke-dwh-password' >"$tmp/dwh-password"
|
|
chmod 0600 "$tmp/pi-auth.json" "$tmp/dwh-password"
|
|
printf '%s\n' \
|
|
'THT_WORKSPACE_GIT_REMOTE=https://git.example.invalid/platform/thoth-workspaces.git' \
|
|
"PI_AUTH_FILE=$tmp/pi-auth.json" \
|
|
"THT_SECRETS_FILE=$bundle" >"$tmp/operator.env"
|
|
|
|
cat >"$tmp/smoke.yaml" <<YAML
|
|
services:
|
|
embedding:
|
|
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] * 1023 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 do_GET(self):
|
|
body = b'{"models":[{"name":"qwen3-embedding:0.6b"}]}'
|
|
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", 11434), H).serve_forever()
|
|
embedding-model-init:
|
|
profiles: [preprocess]
|
|
image: busybox:1.37.0
|
|
entrypoint: [sh, -ec]
|
|
command: ["exit 0"]
|
|
depends_on:
|
|
embedding: {condition: service_started}
|
|
dwh:
|
|
image: postgres:16-alpine
|
|
profiles: [preprocess]
|
|
environment:
|
|
POSTGRES_DB: warehouse
|
|
POSTGRES_USER: thoth_reader
|
|
POSTGRES_PASSWORD: smoke-dwh-password
|
|
healthcheck:
|
|
test: ["CMD-SHELL", "pg_isready -U thoth_reader -d warehouse"]
|
|
interval: 5s
|
|
timeout: 3s
|
|
retries: 20
|
|
start_period: 10s
|
|
preprocess-evidence:
|
|
volumes:
|
|
- $tmp/source:/data/source:ro
|
|
preprocess-dwh:
|
|
environment:
|
|
THT_PREPROCESS_DWH_HOST: dwh
|
|
THT_PREPROCESS_DWH_PORT: "5432"
|
|
THT_PREPROCESS_DWH_DATABASE: warehouse
|
|
THT_PREPROCESS_DWH_SCHEMA: public
|
|
THT_PREPROCESS_DWH_USER: thoth_reader
|
|
THT_PREPROCESS_DWH_PASSWORD_FILE: /run/secrets/preprocess-dwh-password
|
|
volumes:
|
|
- $tmp/dwh-password:/run/secrets/preprocess-dwh-password:ro
|
|
depends_on:
|
|
dwh: {condition: service_healthy}
|
|
YAML
|
|
|
|
compose="docker compose --env-file $tmp/operator.env -f compose.yaml -f deploy/compose.preprocess.yaml -f $tmp/smoke.yaml --project-name $project --profile preprocess"
|
|
$compose build preprocess-evidence
|
|
if [ "${PREPROCESS_SMOKE_INJECT_FAILURE:-0}" = "1" ]; then
|
|
sh -c 'exit 97'
|
|
fi
|
|
generation_count() {
|
|
$compose run --rm --no-deps --entrypoint /opt/venv/bin/python preprocess-evidence -c \
|
|
'import pathlib,re; root=pathlib.Path("/data/workspaces/preprocess-evidence/corpus"); print(sum(1 for p in root.iterdir() if p.is_dir() and re.fullmatch(r"gen-[0-9a-f]{32}",p.name)) if root.exists() else 0)'
|
|
}
|
|
before=0
|
|
first=$($compose run --rm preprocess-evidence)
|
|
after_first=$(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 a["published"] and not b["published"] and c["published"]
|
|
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."
|