test(skills): harden dpgen-run validation

Author: SchrodingersCattt

skills/dpgen-run/references/machine-json.md

@@ -27,7 +27,9 @@ Keep separate `train`, `model_devi`, and `fp` blocks. For each stage, collect or
 - `resources.source_list` for scheduler runtime activation
 - queue, partition, account, and custom scheduler flags when applicable
 
-Typical commands are `dp` for training, `lmp` for LAMMPS exploration, and a backend executable such as `vasp_std`, `cp2k.popt`, `abacus`, `pw.x`, or `g16` for labeling. Preserve known working commands.
+`train_backend` does not rewrite the machine command. `dp` selects the DeePMD installation's default backend; a DeePMD-kit 3.x PyTorch installation may require `dp --pt`. Verify the installed entry point with `dp train -h` or `dp --pt train -h`, then make the `train` command agree with `train_backend`.
+
+Typical later-stage commands are `lmp` for LAMMPS exploration and a backend executable such as `vasp_std`, `cp2k.popt`, `abacus`, `pw.x`, or `g16` for labeling. Preserve known working commands.
 
 ## Context and batch compatibility
 
@@ -51,6 +53,6 @@ Patch the closest existing working configuration. Do not transplant site-specifi
 - Keep CPU, GPU, node, and grouping requests explicit.
 - Require explicit `source_list` activation for scheduler stages.
 - Preserve working local omissions and installed-version aliases.
-- Ensure commands match the scientific stack selected in `param.json`.
+- Ensure the training command selects the same backend as `train_backend` and all commands match the scientific stack selected in `param.json`.
 
 External machine reference: https://docs.deepmodeling.com/projects/dpgen/en/latest/run/mdata.html

skills/dpgen-run/references/validation-and-run.md

@@ -52,6 +52,7 @@ Compare every `type_map.raw` line-for-line with `param.json.type_map`. Verify ev
 Confirm:
 
 - DeePMD-kit version, backend, descriptor, and training-input layout agree
+- `train_backend` and the machine `train.command` select the same backend; for DeePMD-kit 3.x PyTorch, verify `dp --pt train -h` and use `dp --pt` when required
 - each exploration job references valid systems and MD settings
 - force trust thresholds are ordered and scientifically intentional
 - FP inputs and support files match `fp_style`

tests/test_dpgen_run_skill.py

@@ -1,8 +1,15 @@
+import copy
 import json
 import re
 import unittest
 from pathlib import Path
 
+from dargs.dargs import (
+    ArgumentKeyError,
+    ArgumentTypeError,
+    ArgumentValueError,
+)
+
 from dpgen.generator.arginfo import run_jdata_arginfo
 from dpgen.remote.decide_machine import convert_mdata
 from dpgen.util import normalize
@@ -88,6 +95,72 @@ def test_linked_parameter_examples_use_current_schema(self):
                 self.assertIsInstance(normalized, dict)
                 self.assertTrue(normalized)
 
+    def test_documented_parameter_schema_invariants(self):
+        repository_root = Path(__file__).resolve().parents[1]
+        example = (
+            repository_root
+            / "examples"
+            / "run"
+            / "dp2.x-lammps-cp2k"
+            / "param_CH4_deepmd-kit-2.0.1.json"
+        )
+        parameter_data = json.loads(example.read_text())
+        normalized = normalize(
+            run_jdata_arginfo(),
+            copy.deepcopy(parameter_data),
+            strict_check=False,
+        )
+
+        self.assertEqual(normalized["model_devi_engine"], "lammps")
+        self.assertEqual(normalized["train_backend"], "tensorflow")
+
+        without_mass_map = copy.deepcopy(parameter_data)
+        without_mass_map.pop("mass_map", None)
+        normalized_without_mass_map = normalize(
+            run_jdata_arginfo(),
+            without_mass_map,
+            strict_check=False,
+        )
+        self.assertEqual(normalized_without_mass_map["mass_map"], "auto")
+
+        invalid_fp_style = copy.deepcopy(parameter_data)
+        invalid_fp_style["fp_style"] = "none"
+        with self.assertRaises(ArgumentValueError):
+            normalize(
+                run_jdata_arginfo(),
+                invalid_fp_style,
+                strict_check=False,
+            )
+
+        missing_model_devi_skip = copy.deepcopy(parameter_data)
+        missing_model_devi_skip.pop("model_devi_skip")
+        with self.assertRaises(ArgumentKeyError):
+            normalize(
+                run_jdata_arginfo(),
+                missing_model_devi_skip,
+                strict_check=False,
+            )
+
+        flat_sys_configs = copy.deepcopy(parameter_data)
+        flat_sys_configs["sys_configs"] = ["POSCAR"]
+        with self.assertRaises(ArgumentTypeError):
+            normalize(
+                run_jdata_arginfo(),
+                flat_sys_configs,
+                strict_check=False,
+            )
+
+        for backend in ("tensorflow", "pytorch"):
+            with self.subTest(backend=backend):
+                backend_data = copy.deepcopy(parameter_data)
+                backend_data["train_backend"] = backend
+                normalized_backend = normalize(
+                    run_jdata_arginfo(),
+                    backend_data,
+                    strict_check=False,
+                )
+                self.assertEqual(normalized_backend["train_backend"], backend)
+
     def test_linked_machine_examples_use_current_schema(self):
         repository_root = Path(__file__).resolve().parents[1]
         examples_root = repository_root / "examples" / "machine"