#!/usr/bin/env bash # 单算子本地一键调试:模拟 worker 在 Kubernetes Job 里调用 operator-runner 的同一套方式。 # # 用法: # scripts/local/run-operator.sh [输入文件或目录] # # 示例: # scripts/local/run-operator.sh json_to_csv local-samples/json_to_csv/input.json # scripts/local/run-operator.sh video_slice local-samples/video_slice/input.json # # 说明: # - 是 operator-repos/builtin/ 下的目录名(如 video_slice) # - 输入文件是 JSON Artifact 列表(形如 [{"name":..., "path":..., "type":...}, ...]); # 若省略则使用 local-samples//input.json(存在时),否则用空输入 # - 产物固定写到 ./local-runs//<时间戳>/,包含 outputs/、result.json、stage-manifest.json # - 调试 operator-repos 源码副本改动时无需任何额外参数:脚本默认用 # DROBOTICFLOW_OPERATOR_SOURCE 直接指向 operator-repos/builtin//src/operator.py # - 附加超参:OPERATOR_EXTRA_HYPERPARAMS='[{"key":"K","value":"V"}]' 变量传入 # - 使用仓库 .venv 里的 Python(含 numpy/opencv 等算子依赖);.venv 不存在时回退 python3 set -euo pipefail REPO_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/../.." && pwd)" cd "$REPO_ROOT" slug="${1:-}" if [[ -z "$slug" ]]; then echo "用法: scripts/local/run-operator.sh [输入artifact列表JSON文件]" >&2 echo "示例: scripts/local/run-operator.sh json_to_csv local-samples/json_to_csv/input.json" >&2 exit 1 fi op_dir="operator-repos/builtin/$slug" if [[ ! -f "$op_dir/operator.json" ]]; then echo "错误: 找不到算子 $slug($op_dir/operator.json 不存在)" >&2 echo "可用算子: ls operator-repos/builtin/" >&2 exit 1 fi # 从 operator.json / runtime_contract.json 读取算子名和 handler op_name="$(python3 -c "import json; print(json.load(open('$op_dir/operator.json'))['name'])")" handler="$(python3 -c "import json; print(json.load(open('$op_dir/runtime_contract.json'))['handler'])")" # 输入 artifact 列表:命令行 > local-samples 默认 > 空列表 input_file="${2:-}" if [[ -z "$input_file" && -f "local-samples/$slug/input.json" ]]; then input_file="local-samples/$slug/input.json" fi if [[ -n "$input_file" && ! -f "$input_file" ]]; then echo "错误: 输入文件不存在: $input_file" >&2 exit 1 fi run_dir="$REPO_ROOT/local-runs/$slug/$(date +%Y%m%d-%H%M%S)" mkdir -p "$run_dir/outputs" # 组装 NODE_DATA_JSON:label 用于日志显示,outputs 占位一个端口 extra_hyperparams="${OPERATOR_EXTRA_HYPERPARAMS:-[]}" node_data_json="$(slug_label="$op_name" extra_hyperparams="$extra_hyperparams" python3 - <<'PY' import json, os print(json.dumps({ "label": os.environ["slug_label"], "hyperparams": json.loads(os.environ["extra_hyperparams"]), "outputs": [{"id": "out-1", "name": "output", "type": "json"}], }, ensure_ascii=False)) PY )" # 输入 artifact:文件形式给 INPUT_ARTIFACTS_PATH(>64KiB 或含路径引用时更贴近真实) if [[ -n "$input_file" ]]; then cp "$input_file" "$run_dir/input-artifacts.json" input_env=("INPUT_ARTIFACTS_PATH=$run_dir/input-artifacts.json") else input_env=("INPUT_ARTIFACTS_JSON=[]") fi # Python 解释器:优先仓库 .venv(有 numpy/opencv/h5py 等依赖) if [[ -x ".venv/bin/python" ]]; then PY=".venv/bin/python" else PY="python3" echo "[提示] .venv 不存在,使用系统 python3;视频/科学计算类算子可能缺依赖" >&2 echo "[提示] 建议执行: python3 -m venv .venv && .venv/bin/pip install -r requirements-dev.txt" >&2 fi echo "====== 单算子本地调试 ======" echo "算子: $slug / $op_name" echo "handler: $handler" echo "输入: ${input_file:-(空输入)}" echo "产物目录: $run_dir" echo "============================" env \ RUN_ID="run-local-$slug" \ WORKFLOW_ID="wf-local" \ NODE_ID="node-local-$slug" \ NODE_LABEL="$op_name" \ NODE_DATA_JSON="$node_data_json" \ "${input_env[@]}" \ OUTPUT_DIR="$run_dir/outputs" \ RESULT_OUTPUT_PATH="$run_dir/result.json" \ STAGE_MANIFEST_PATH="$run_dir/stage-manifest.json" \ DROBOTICFLOW_OPERATOR_HANDLER="$handler" \ DROBOTICFLOW_OPERATOR_SOURCE="$op_dir/src/operator.py" \ "$PY" backend/operator-runner/main.py echo echo "====== 执行完成 ======" echo "result.json: $run_dir/result.json" echo "stage-manifest: $run_dir/stage-manifest.json" echo "outputs/: $run_dir/outputs/" if [[ -f "$run_dir/result.json" ]]; then python3 - "$run_dir/result.json" <<'PY' import json, sys try: result = json.load(open(sys.argv[1])) except Exception as exc: print(f"(result.json 解析失败: {exc})") raise SystemExit(0) artifacts = result.get("artifacts", []) print(f"产物 artifact 数: {len(artifacts)}") for artifact in artifacts: print(f" - {artifact.get('name')} (type={artifact.get('type')}, path={artifact.get('path')})") logs = result.get("logs", []) errors = [entry for entry in logs if entry.get("level", "").lower() in ("error", "warn")] if errors: print(f"日志中的告警/错误 {len(errors)} 条(前 3 条):") for entry in errors[:3]: print(f" [{entry.get('level')}] {entry.get('message', '')[:160]}") PY fi