refactor: retire external vector deployment

scripts/preprocess-smoke.sh

@@ -46,29 +46,23 @@ 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="$tmp/thothii.secrets"
-{
-  printf 'THT_VECTOR_BOOTSTRAP_PASSWORD=smoke-bootstrap-%s\n' "$project"
-  printf 'THT_VECTOR_MIGRATOR_PASSWORD=smoke-migrator-%s\n' "$project"
-  printf 'THT_VECTOR_READER_PASSWORD=smoke-reader-%s\n' "$project"
-  printf 'THT_VECTOR_WRITER_PASSWORD=smoke-writer-%s\n' "$project"
-} >"$bundle"
+printf '%s\n' 'THT_MODEL_API_KEY=smoke-model-key' >"$bundle"
 chmod 0600 "$bundle"
-export THT_SECRETS_FILE="$bundle"
-export THT_OLLAMA_URL=http://mock-embeddings:8081
 printf '%s\n' '{}' >"$tmp/pi-auth.json"
-chmod 0600 "$tmp/pi-auth.json"
+printf '%s' 'smoke-dwh-password' >"$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" \
-  'THT_OLLAMA_URL=http://mock-embeddings:8081' >"$tmp/operator.env"
+  "THT_SECRETS_FILE=$bundle" >"$tmp/operator.env"
 
 cat >"$tmp/smoke.yaml" <<YAML
 services:
-  mock-embeddings:
+  embedding:
     image: thothii-core:local
     profiles: [preprocess]
     entrypoint: [/opt/venv/bin/python, -c]
@@ -78,19 +72,52 @@ services:
         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)
+            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',8081),H).serve_forever()
+        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:
-      mock-embeddings: {condition: service_started}
+      dwh: {condition: service_healthy}
 YAML
 
-compose="docker compose --env-file $tmp/operator.env -f compose.yaml -f deploy/compose.local-vector.yaml -f deploy/compose.preprocess.yaml -f deploy/compose.preprocess-local-vector.yaml -f $tmp/smoke.yaml --project-name $project --profile local-vector --profile preprocess"
+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'