refactor: retire external vector deployment

scripts/test-preprocess-compose-config.sh

@@ -6,12 +6,7 @@ cd "$(dirname "$0")/.."
 tmp_bundle=$(mktemp)
 tmp_auth=$(mktemp)
 trap 'rm -f "$tmp_bundle" "$tmp_auth"' EXIT HUP INT TERM
-cat >"$tmp_bundle" <<'EOF'
-THT_VECTOR_BOOTSTRAP_PASSWORD=test-bootstrap
-THT_VECTOR_MIGRATOR_PASSWORD=test-migrator
-THT_VECTOR_READER_PASSWORD=test-reader
-THT_VECTOR_WRITER_PASSWORD=test-writer
-EOF
+printf '%s\n' 'THT_MODEL_API_KEY=test-model' >"$tmp_bundle"
 chmod 0600 "$tmp_bundle"
 printf '%s\n' '{}' >"$tmp_auth"
 chmod 0600 "$tmp_auth"
@@ -19,71 +14,44 @@ export THT_SECRETS_FILE="$tmp_bundle"
 export PI_AUTH_FILE="$tmp_auth"
 export THT_WORKSPACE_GIT_REMOTE=https://git.example.invalid/platform/thoth-workspaces.git
 
-local_files="-f compose.yaml -f deploy/compose.local-vector.yaml -f deploy/compose.preprocess.yaml -f deploy/compose.preprocess-local-vector.yaml"
-local_json=$(docker compose $local_files --profile local-vector --profile preprocess config --format json)
+config_json=$(docker compose -f compose.yaml -f deploy/compose.preprocess.yaml --profile preprocess config --format json)
 
-printf '%s' "$local_json" | python3 -c '
+printf '%s' "$config_json" | python3 -c '
 import json, sys
 
 config = json.load(sys.stdin)
 services = config["services"]
-assert "thothii_secrets" in config.get("secrets", {}), config.get("secrets")
-assert "vector_bootstrap_password" not in config.get("secrets", {})
-assert "vector_migrator_password" not in config.get("secrets", {})
-assert "vector_reader_password" not in config.get("secrets", {})
-assert "vector_writer_password" not in config.get("secrets", {})
-for name, service in services.items():
-    if name.startswith("vector-") or name.startswith("preprocess-") or name == "core":
-        assert any(item.get("target") == "thothii.secrets" for item in service.get("secrets", []) if isinstance(item, dict)), (name, service.get("secrets"))
-        assert "vector_reader_password" not in str(service)
-        assert "vector_writer_password" not in str(service)
-for name in ("preprocess-evidence", "preprocess-dwh"):
-    dependency = services[name].get("depends_on", {}).get("vector-migrate")
-    assert dependency is not None, f"{name} does not depend on vector-migrate"
-    assert dependency["condition"] == "service_completed_successfully", dependency
-'
-
-external_json=$(docker compose \
-  -f compose.yaml -f deploy/compose.preprocess.yaml \
-  --profile preprocess config --format json)
-
-printf '%s' "$external_json" | python3 -c '
-import json, sys
-
-config = json.load(sys.stdin)
-services = config["services"]
-assert "vector-db" not in services
-assert "vector-migrate" not in services
-assert "vector-reconcile" not in services
-for name in ("preprocess-evidence", "preprocess-dwh"):
+assert "qdrant" in services
+assert "embedding" in services
+assert "embedding-model-init" in services
+assert "preprocess-evidence" in services
+assert "preprocess-dwh" in services
+for name in ("preprocess-evidence", "preprocess-dwh", "core"):
     service = services[name]
-    assert "depends_on" not in service
-    assert all(item.get("target") == "thothii.secrets" for item in service.get("secrets", []) if isinstance(item, dict)), service.get("secrets")
-    assert "vector_reader_password" not in str(service)
-    assert "vector_writer_password" not in str(service)
+    assert any(item.get("target") == "thothii.secrets" for item in service.get("secrets", []) if isinstance(item, dict)), (name, service.get("secrets"))
+    assert "THT_OLLAMA_URL" not in str(service)
+    assert "THT_VECTOR_" not in str(service)
+assert services["preprocess-evidence"]["depends_on"]["qdrant"]["condition"] == "service_healthy"
+assert services["preprocess-evidence"]["depends_on"]["embedding-model-init"]["condition"] == "service_completed_successfully"
+assert "depends_on" not in services["preprocess-dwh"] or "vector-migrate" not in str(services["preprocess-dwh"]["depends_on"])
 '
 
 python3 - <<'PY'
-import os
 from pathlib import Path
 
-os.environ.update({
-    "THT_DB_NAME": "thoth",
-    "THT_DWH_REST_URL": "http://dwh.invalid",
-    "THT_DWH_API_KEY": "dwh",
-    "THT_VECTOR_DATABASE": "thoth",
-    "THT_VECTOR_READER_USER": "reader",
-    "THT_VECTOR_WRITER_USER": "writer",
-    "THT_VECTOR_READER_PASSWORD_FILE": "/tmp/generated-reader",
-    "THT_VECTOR_WRITER_PASSWORD_FILE": "/tmp/generated-writer",
-    "THT_DOCS_ROOT": "/data/source",
-    "THT_OLLAMA_URL": "http://ollama.invalid",
-})
-text = Path("deploy/workspaces/local-vector.yaml").read_text()
-assert "password_file: ${THT_VECTOR_READER_PASSWORD_FILE}" in text
-assert "password_file: ${THT_VECTOR_WRITER_PASSWORD_FILE}" in text
-assert "${THT_SECRETS_FILE}" not in text
-print("local-vector workspace resolution contract: ok")
+evidence = Path("deploy/workspaces/preprocess-evidence.yaml").read_text()
+dwh = Path("deploy/workspaces/preprocess-dwh.yaml").read_text()
+assert "type: qdrant" in evidence
+assert "base_url: http://qdrant:6333" in evidence
+assert "provider: ollama_internal" in evidence
+assert "base_url: http://embedding:11434" in evidence
+assert "qwen3-embedding:0.6b" in evidence
+assert "THT_VECTOR_" not in evidence
+assert "THT_OLLAMA_URL" not in evidence
+assert "pgvector" not in evidence
+assert "type: postgres_direct" in dwh
+assert "THT_PREPROCESS_DWH_HOST" in dwh
+print("preprocess workspace contract: ok")
 PY
 
 echo "preprocess compose config: ok"