Migrate product-data exports to skill scripts

skills/product-data/scripts/normalize_dataset_draft.py

@@ -1,7 +1,5 @@
 from __future__ import annotations
 
-from pathlib import Path
-
 from product_data_portable import (
     DEFAULT_REQUEST_ID,
     DEFAULT_TIMESTAMP_STEP_MS,
@@ -9,6 +7,7 @@ from product_data_portable import (
     emit_success,
     load_json_payload,
     normalize_dataset_draft,
+    resolve_portable_path,
 )
 
 
@@ -17,15 +16,21 @@ def main() -> int:
         payload = load_json_payload()
         draft_text = str(payload.get("draft_text") or "")
         if not draft_text and payload.get("draft_path"):
-            draft_text = Path(str(payload["draft_path"])).expanduser().read_text(encoding="utf-8")
+            draft_text = resolve_portable_path(str(payload["draft_path"])).read_text(encoding="utf-8")
+        source_type = str(payload.get("source_type") or "generated")
+        confirmed_plan_id = str(payload.get("confirmed_plan_id") or "").strip()
+        if source_type == "generated" and not confirmed_plan_id:
+            raise ValueError("confirmed_plan_id is required for generated data")
         result = normalize_dataset_draft(
             draft_text,
             batch_id=str(payload.get("batch_id") or DEFAULT_REQUEST_ID),
-            source_type=str(payload.get("source_type") or "generated"),
+            source_type=source_type,
             base_timestamp=payload.get("base_timestamp"),
             timestamp_step_ms=int(payload.get("timestamp_step_ms") or DEFAULT_TIMESTAMP_STEP_MS),
             default_request_id=str(payload.get("default_request_id") or DEFAULT_REQUEST_ID),
         )
+        if confirmed_plan_id:
+            result["confirmed_plan_id"] = confirmed_plan_id
         emit_success(result)
         return 0
     except Exception as exc:  # noqa: BLE001 - CLI 需要把错误稳定转成 JSON

skills/product-data/scripts/product_data_portable.py

@@ -9,6 +9,7 @@ from __future__ import annotations
 import argparse
 import csv
 import json
+import os
 import re
 import sys
 import time
@@ -79,7 +80,7 @@ def load_records(payload: dict[str, Any]) -> list[dict[str, Any]]:
 
 
 def read_records_file(path: str) -> list[dict[str, Any]]:
-    file_path = Path(path).expanduser()
+    file_path = resolve_portable_path(path)
     text = file_path.read_text(encoding="utf-8")
     if file_path.suffix.lower() == ".jsonl":
         records: list[dict[str, Any]] = []
@@ -814,40 +815,82 @@ def default_output_path(payload: dict[str, Any]) -> str:
     output_format = str(payload.get("output_format") or "jsonl")
     filename = "records.json" if output_format == "json" else "records.jsonl"
     if isinstance(payload.get("output_path"), str) and payload["output_path"].strip():
-        return payload["output_path"].strip()
+        return str(resolve_portable_path(payload["output_path"].strip()))
     if isinstance(payload.get("output_dir"), str) and payload["output_dir"].strip():
-        return str(Path(payload["output_dir"]).expanduser() / filename)
-    return str(Path("output") / filename)
+        return str(resolve_portable_path(payload["output_dir"].strip()) / filename)
+    return str(default_output_root() / filename)
 
 
 def default_table_output_path(payload: dict[str, Any]) -> str:
     if isinstance(payload.get("output_path"), str) and payload["output_path"].strip():
-        return payload["output_path"].strip()
+        return str(resolve_portable_path(payload["output_path"].strip()))
     if isinstance(payload.get("output_dir"), str) and payload["output_dir"].strip():
-        return str(Path(payload["output_dir"]).expanduser() / "records.csv")
+        return str(resolve_portable_path(payload["output_dir"].strip()) / "records.csv")
     if isinstance(payload.get("records_path"), str) and payload["records_path"].strip():
-        return str(Path(payload["records_path"]).expanduser().with_name("records.csv"))
-    return str(Path("output") / "records.csv")
+        return str(resolve_portable_path(payload["records_path"].strip()).with_name("records.csv"))
+    return str(default_output_root() / "records.csv")
 
 
 def default_training_output_path(payload: dict[str, Any]) -> str:
     if isinstance(payload.get("output_path"), str) and payload["output_path"].strip():
-        return payload["output_path"].strip()
+        return str(resolve_portable_path(payload["output_path"].strip()))
     if isinstance(payload.get("output_dir"), str) and payload["output_dir"].strip():
-        return str(Path(payload["output_dir"]).expanduser() / "training.jsonl")
+        return str(resolve_portable_path(payload["output_dir"].strip()) / "training.jsonl")
     if isinstance(payload.get("records_path"), str) and payload["records_path"].strip():
-        return str(Path(payload["records_path"]).expanduser().with_name("training.jsonl"))
-    return str(Path("output") / "training.jsonl")
+        return str(resolve_portable_path(payload["records_path"].strip()).with_name("training.jsonl"))
+    return str(default_output_root() / "training.jsonl")
 
 
 def default_planning_eval_output_path(payload: dict[str, Any]) -> str:
     if isinstance(payload.get("output_path"), str) and payload["output_path"].strip():
-        return payload["output_path"].strip()
+        return str(resolve_portable_path(payload["output_path"].strip()))
     if isinstance(payload.get("output_dir"), str) and payload["output_dir"].strip():
-        return str(Path(payload["output_dir"]).expanduser() / "eval_planning.csv")
+        return str(resolve_portable_path(payload["output_dir"].strip()) / "eval_planning.csv")
     if isinstance(payload.get("records_path"), str) and payload["records_path"].strip():
-        return str(Path(payload["records_path"]).expanduser().with_name("eval_planning.csv"))
-    return str(Path("output") / "eval_planning.csv")
+        return str(resolve_portable_path(payload["records_path"].strip()).with_name("eval_planning.csv"))
+    return str(default_output_root() / "eval_planning.csv")
+
+
+def default_output_root() -> Path:
+    """返回 portable 脚本默认输出目录。
+
+    在 ZK Data Agent 中，python_exec 的 cwd 是当前会话 scratchpad；
+    通过 PYTHON_EXEC_SCRATCHPAD 可以定位同级 output 目录。离开平台独立
+    运行时，保持原来的相对 output/ 行为。
+    """
+
+    scratchpad = os.environ.get("PYTHON_EXEC_SCRATCHPAD")
+    if scratchpad:
+        return Path(scratchpad).expanduser().parent / "output"
+    return Path("output")
+
+
+def resolve_portable_path(path: str) -> Path:
+    """解析 portable 脚本路径，并兼容平台逻辑路径。
+
+    平台内运行时，把 output/、scratchpad/、input/ 映射到当前会话目录；
+    其他相对路径仍按当前 cwd 解析，便于普通 Python 环境复用。
+    """
+
+    raw_path = Path(path).expanduser()
+    if raw_path.is_absolute():
+        return raw_path
+    scratchpad = os.environ.get("PYTHON_EXEC_SCRATCHPAD")
+    if not scratchpad:
+        return raw_path
+    session_root = Path(scratchpad).expanduser().parent
+    parts = raw_path.parts
+    if not parts:
+        return raw_path
+    head, *tail = parts
+    tail_path = Path(*tail) if tail else Path()
+    if head in {"output", "outputs"}:
+        return session_root / "output" / tail_path
+    if head in {"scratchpad", "scratch"}:
+        return Path(scratchpad).expanduser() / tail_path
+    if head in {"input", "inputs"}:
+        return session_root / "input" / tail_path
+    return raw_path
 
 
 def normalize_target_expression(target: str) -> str: