dexverse-cli 0.0.2__tar.gz → 0.0.4__tar.gz

{dexverse_cli-0.0.2 → dexverse_cli-0.0.4}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.4
+Metadata-Version: 2.5
 Name: dexverse-cli
-Version: 0.0.2
+Version: 0.0.4
 Summary: DexVerse dataset downloader for S3-compatible robot training datasets
 Author: DexVerse
 License: Apache-2.0
@@ -86,7 +86,7 @@ Raw backend output is accepted directly:
   "storage_path": "datasets/.../20260429_180359.hdf5",
   "file_name": "20260429_180359.hdf5",
   "file_size": 14994636,
-  "task_instruction": {
+  "additional_info": {
     "aaa": "111",
     "aaaa": 222,
     "ewrwrwe": 1.1111111111111112e+54
@@ -100,7 +100,7 @@ Result:
 D:\DexVerse\20260429_180359.hdf5
 ```
 
-`task_instruction` is optional and must be a JSON object. If multiple manifest
+`additional_info` is optional and must be a JSON object. If multiple manifest
 items resolve to the same local path (for example, repeated `file_name`
 values), the first item wins and later duplicates are ignored.
 
@@ -133,8 +133,8 @@ dexverse-dl repair  --manifest PATH --out /data/dexverse [--backend http|python|
 ### 还原 HDF5 → 可训练数据
 
 下载完成后，把落盘的 `.hdf5` 还原为原始录制结构（逐帧 JPEG + `pose_record_*.json`
-+ `metadata.jsonl`）。如果对应 manifest 带有 `task_instruction`，还会自动生成
-`task_instruction.json`：
++ `metadata.jsonl`）。如果对应 manifest 带有 `additional_info`，还会自动生成
+`additional_info.json`：
 
 ```bash
 # 单文件
@@ -153,11 +153,11 @@ dexverse-dl convert --input-dir /data/dexverse -o /data/dexverse/restored
   hand/right/000000.jpg ...
   pose_record_20260429_180359.json
   metadata.jsonl
-  task_instruction.json
+  additional_info.json
 ```
 
-`task_instruction.json` 的内容就是 manifest 中的对象本身，不增加外层包装。
-下载器会把转换所需的映射保存在 `.dexverse/task-instructions/`，无需为
+`additional_info.json` 的内容就是 manifest 中的对象本身，不增加外层包装。
+下载器会把转换所需的映射保存在 `.dexverse/additional-info/`，无需为
 `convert` 增加额外参数。独立来源且没有该隐藏元数据的 HDF5 仍按原行为还原。
 
 该命令依赖 `h5py` / `numpy` / `av` / `pillow`，已列入核心依赖，安装时随包装上。
@@ -180,7 +180,7 @@ State files live under `<out>/.dexverse/` and never mix into the dataset tree:
 
 ```text
 /data/dexverse/
-  .dexverse/task-instructions/
+  .dexverse/additional-info/
     20260429_180359.hdf5.json
   .dexverse/tasks/<taskId>/
     manifest.json

{dexverse_cli-0.0.2 → dexverse_cli-0.0.4}/README.md

@@ -56,7 +56,7 @@ Raw backend output is accepted directly:
   "storage_path": "datasets/.../20260429_180359.hdf5",
   "file_name": "20260429_180359.hdf5",
   "file_size": 14994636,
-  "task_instruction": {
+  "additional_info": {
     "aaa": "111",
     "aaaa": 222,
     "ewrwrwe": 1.1111111111111112e+54
@@ -70,7 +70,7 @@ Result:
 D:\DexVerse\20260429_180359.hdf5
 ```
 
-`task_instruction` is optional and must be a JSON object. If multiple manifest
+`additional_info` is optional and must be a JSON object. If multiple manifest
 items resolve to the same local path (for example, repeated `file_name`
 values), the first item wins and later duplicates are ignored.
 
@@ -103,8 +103,8 @@ dexverse-dl repair  --manifest PATH --out /data/dexverse [--backend http|python|
 ### 还原 HDF5 → 可训练数据
 
 下载完成后，把落盘的 `.hdf5` 还原为原始录制结构（逐帧 JPEG + `pose_record_*.json`
-+ `metadata.jsonl`）。如果对应 manifest 带有 `task_instruction`，还会自动生成
-`task_instruction.json`：
++ `metadata.jsonl`）。如果对应 manifest 带有 `additional_info`，还会自动生成
+`additional_info.json`：
 
 ```bash
 # 单文件
@@ -123,11 +123,11 @@ dexverse-dl convert --input-dir /data/dexverse -o /data/dexverse/restored
   hand/right/000000.jpg ...
   pose_record_20260429_180359.json
   metadata.jsonl
-  task_instruction.json
+  additional_info.json
 ```
 
-`task_instruction.json` 的内容就是 manifest 中的对象本身，不增加外层包装。
-下载器会把转换所需的映射保存在 `.dexverse/task-instructions/`，无需为
+`additional_info.json` 的内容就是 manifest 中的对象本身，不增加外层包装。
+下载器会把转换所需的映射保存在 `.dexverse/additional-info/`，无需为
 `convert` 增加额外参数。独立来源且没有该隐藏元数据的 HDF5 仍按原行为还原。
 
 该命令依赖 `h5py` / `numpy` / `av` / `pillow`，已列入核心依赖，安装时随包装上。
@@ -150,7 +150,7 @@ State files live under `<out>/.dexverse/` and never mix into the dataset tree:
 
 ```text
 /data/dexverse/
-  .dexverse/task-instructions/
+  .dexverse/additional-info/
     20260429_180359.hdf5.json
   .dexverse/tasks/<taskId>/
     manifest.json

{dexverse_cli-0.0.2 → dexverse_cli-0.0.4}/dexverse/__init__.py

@@ -32,7 +32,7 @@ def _resolve_version() -> str:
         if isinstance(project_version, str):
             return project_version
     try:
-        return version("dexverse")
+        return version("dexverse-cli")
     except PackageNotFoundError:
         return "0.0.0+unknown"
 

{dexverse_cli-0.0.2 → dexverse_cli-0.0.4}/dexverse/convert/hdf5_to_raw.py

@@ -35,7 +35,7 @@ from ..downloader import state as download_state
 from .image_video_encode import decode_mp4_bytes_to_rgb_images
 
 
-TASK_INSTRUCTION_FILENAME = "task_instruction.json"
+ADDITIONAL_INFO_FILENAME = "additional_info.json"
 
 
 def _find_download_root(hdf5_path: Path) -> Optional[Path]:
@@ -47,26 +47,26 @@ def _find_download_root(hdf5_path: Path) -> Optional[Path]:
     return None
 
 
-def _sync_restored_task_instruction(
+def _sync_restored_additional_info(
     hdf5_path: Path,
     output_dir: Path,
 ) -> None:
-    """Copy a downloaded file's hidden instruction into its restored session."""
+    """Copy a downloaded file's hidden additional info into its restored session."""
     download_root = _find_download_root(hdf5_path)
     if download_root is None:
         return
 
     resolved_hdf5 = Path(hdf5_path).expanduser().resolve()
     relpath = resolved_hdf5.relative_to(download_root).as_posix()
-    source = download_state.task_instruction_path(download_root, relpath)
-    destination = Path(output_dir) / TASK_INSTRUCTION_FILENAME
+    source = download_state.additional_info_path(download_root, relpath)
+    destination = Path(output_dir) / ADDITIONAL_INFO_FILENAME
 
     if source.is_file():
-        instruction = json.loads(source.read_text(encoding="utf-8"))
-        if not isinstance(instruction, dict):
-            raise ValueError(f"task instruction must be a JSON object: {source}")
+        additional_info = json.loads(source.read_text(encoding="utf-8"))
+        if not isinstance(additional_info, dict):
+            raise ValueError(f"additional info must be a JSON object: {source}")
         destination.write_text(
-            json.dumps(instruction, ensure_ascii=False, indent=2) + "\n",
+            json.dumps(additional_info, ensure_ascii=False, indent=2) + "\n",
             encoding="utf-8",
         )
     else:
@@ -249,7 +249,7 @@ class HDF5ToRawConverter:
                         img = Image.open(_io.BytesIO(jpg_bytes)).convert("RGB")
                         img.save(cam_dir / f"{i:06d}.jpg", "JPEG", quality=95)
 
-        _sync_restored_task_instruction(hdf5_path, output_dir)
+        _sync_restored_additional_info(hdf5_path, output_dir)
         return frames_count
 
     def _extract_frames(self, h5_file: h5py.File) -> List[AlignedFrame]:

{dexverse_cli-0.0.2 → dexverse_cli-0.0.4}/dexverse/downloader/manager.py

@@ -43,26 +43,26 @@ def _persist_manifest_copy(out: Path, task_id: str, manifest: Manifest) -> None:
         pass
 
 
-def _sync_task_instructions(
+def _sync_additional_info(
     out: Path,
     manifest: Manifest,
     task_state: st.TaskState,
 ) -> None:
-    """Synchronize per-file task instructions after download/verification."""
+    """Synchronize per-file additional info after download/verification."""
     successful_statuses = {st.DOWNLOADED, st.SKIPPED, st.VERIFIED}
     for file_spec in manifest.files:
         key = file_spec.effective_key()
         file_state = task_state.files.get(key)
-        instruction_path = st.task_instruction_path(out, file_spec.relpath())
+        info_path = st.additional_info_path(out, file_spec.relpath())
         if (
             file_state is not None
             and file_state.status in successful_statuses
-            and file_spec.taskInstruction is not None
+            and file_spec.additionalInfo is not None
         ):
-            instruction_path.parent.mkdir(parents=True, exist_ok=True)
-            instruction_path.write_text(
+            info_path.parent.mkdir(parents=True, exist_ok=True)
+            info_path.write_text(
                 json.dumps(
-                    file_spec.taskInstruction,
+                    file_spec.additionalInfo,
                     ensure_ascii=False,
                     indent=2,
                 )
@@ -70,7 +70,7 @@ def _sync_task_instructions(
                 encoding="utf-8",
             )
         else:
-            instruction_path.unlink(missing_ok=True)
+            info_path.unlink(missing_ok=True)
 
 
 def get_backend(name: str, **kwargs) -> Backend:
@@ -280,7 +280,7 @@ class DownloadManager:
                 verified += 1
                 task_state.mark(key, st.VERIFIED)
 
-        _sync_task_instructions(self.out, manifest, task_state)
+        _sync_additional_info(self.out, manifest, task_state)
         task_state.finish()
         task_state.save()
 

{dexverse_cli-0.0.2 → dexverse_cli-0.0.4}/dexverse/downloader/state.py

@@ -17,7 +17,7 @@ from ..manifest import Manifest, resolve_dest
 
 STATE_DIRNAME = ".dexverse"
 TASKS_DIRNAME = "tasks"
-TASK_INSTRUCTIONS_DIRNAME = "task-instructions"
+ADDITIONAL_INFO_DIRNAME = "additional-info"
 
 # file statuses
 PENDING = "pending"
@@ -36,13 +36,13 @@ def task_dir(out: Path, task_id: str) -> Path:
     return dexverse_root(out) / TASKS_DIRNAME / task_id
 
 
-def task_instructions_dir(out: Path) -> Path:
-    return dexverse_root(out) / TASK_INSTRUCTIONS_DIRNAME
+def additional_info_dir(out: Path) -> Path:
+    return dexverse_root(out) / ADDITIONAL_INFO_DIRNAME
 
 
-def task_instruction_path(out: Path, relpath: str) -> Path:
+def additional_info_path(out: Path, relpath: str) -> Path:
     """Hidden metadata path for one downloaded dataset file."""
-    return resolve_dest(task_instructions_dir(out), f"{relpath}.json")
+    return resolve_dest(additional_info_dir(out), f"{relpath}.json")
 
 
 def state_file_path(out: Path, task_id: str) -> Path:

{dexverse_cli-0.0.2 → dexverse_cli-0.0.4}/dexverse/manifest.py

@@ -160,11 +160,33 @@ class FileSpec(BaseModel):
     # Consumed only by the ``http`` backend; ignored by s5cmd/python.
     presignedUrl: Optional[str] = Field(
         None, validation_alias=AliasChoices("presignedUrl", "download_url", "url", "downloadUrl"))
-    taskInstruction: Optional[Dict[str, Any]] = Field(
+    additionalInfo: Optional[Dict[str, Any]] = Field(
         None,
-        validation_alias=AliasChoices("taskInstruction", "task_instruction"),
+        validation_alias=AliasChoices("additionalInfo", "additional_info"),
     )
 
+    @model_validator(mode="before")
+    @classmethod
+    def validate_metadata_fields(cls, data: Any) -> Any:
+        """Reject ambiguous aliases and removed names before extras are kept."""
+        if isinstance(data, dict):
+            if "additional_info" in data and "additionalInfo" in data:
+                raise ValueError(
+                    "fields 'additional_info' and 'additionalInfo' cannot be "
+                    "used together; provide exactly one"
+                )
+            removed = [
+                name
+                for name in ("task_instruction", "taskInstruction")
+                if name in data
+            ]
+            if removed:
+                names = ", ".join(repr(name) for name in removed)
+                raise ValueError(
+                    f"removed field(s) {names}; use 'additional_info' instead"
+                )
+        return data
+
     def relpath(self) -> str:
         """The local landing path relative to out (POSIX, normalized)."""
         return resolve_relpath(self.relativePath, self.originalPath, self.objectKey)
@@ -217,7 +239,7 @@ class Manifest(BaseModel):
 
         Backend-native manifests commonly provide only ``file_name`` as the
         landing path. Keeping the first occurrence makes duplicate names
-        deterministic and ensures the downloaded file and its task instruction
+        deterministic and ensures the downloaded file and its additional info
         always come from the same manifest entry.
         """
         seen = set()

{dexverse_cli-0.0.2 → dexverse_cli-0.0.4}/examples/download (7).json

@@ -3,14 +3,14 @@
     {
       "download_url": "https://192.168.3.55:8443/dexverse/datasets/2606261645500010275566473183232/2607240417070338897362032267265/20260710_181607.hdf5?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=admin%2F20260724%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20260724T070457Z&X-Amz-Expires=86400&X-Amz-SignedHeaders=host&X-Amz-Signature=333996e3875a8a7cdc65f26edd12de30298a99f68a4e24ec10a7a187d65099c1",
       "file_name": "20260710_181607.hdf5",
-      "task_instruction": {
+      "additional_info": {
         "aaa33333": "111"
       }
     },
     {
       "download_url": "https://192.168.3.55:8443/dexverse/datasets/2606261645500010275566473183232/2607230920230338611294116515841/20260630_152359.hdf5?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=admin%2F20260724%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20260724T070457Z&X-Amz-Expires=86400&X-Amz-SignedHeaders=host&X-Amz-Signature=0207422c867030015aa31c66aac264b70d9f67d508b2c08e9278b5dc85074a23",
       "file_name": "20260630_152359.hdf5",
-      "task_instruction": {
+      "additional_info": {
         "aaa": "111",
         "aaaa": 222,
         "ewrwrwe": 1.1111111111111112e+54
@@ -19,37 +19,37 @@
     {
       "download_url": "https://192.168.3.55:8443/dexverse/datasets/2606261645500010275566473183232/2607230304150338516637072232449/20260617_122549.hdf5?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=admin%2F20260724%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20260724T070457Z&X-Amz-Expires=86400&X-Amz-SignedHeaders=host&X-Amz-Signature=8b0228bd8e53e023081295c2e4811625d03b0f4998f3631c5d868c85c6c19cb3",
       "file_name": "20260617_122549.hdf5",
-      "task_instruction": {
+      "additional_info": {
         "aaa": "5555"
       }
     },
     {
       "download_url": "https://192.168.3.55:8443/dexverse/datasets/2606261645500010275566473183232/2607230255400338514476854677505/20260630_152119.hdf5?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=admin%2F20260724%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20260724T070457Z&X-Amz-Expires=86400&X-Amz-SignedHeaders=host&X-Amz-Signature=5ec492d0d867d9b4e5c714e2b530da8949851c58585504b5e6d6843134073078",
       "file_name": "20260630_152119.hdf5",
-      "task_instruction": {
+      "additional_info": {
         "aaa": "111"
       }
     },
     {
       "download_url": "https://192.168.3.55:8443/dexverse/datasets/2606261645500010275566473183232/2607230251340338513446729420801/20260710_181607.hdf5?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=admin%2F20260724%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20260724T070457Z&X-Amz-Expires=86400&X-Amz-SignedHeaders=host&X-Amz-Signature=21703ed3690b5ea9d008e6ad541e6f1682f75a811cc4a7c0d47ff7e952ce4e65",
       "file_name": "20260710_181607.hdf5",
-      "task_instruction": {
+      "additional_info": {
         "aaa": "111"
       }
     },
     {
       "download_url": "https://192.168.3.55:8443/dexverse/datasets/2606261645500010275566473183232/2607230250150338513114959974401/20260630_152428.hdf5?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=admin%2F20260724%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20260724T070457Z&X-Amz-Expires=86400&X-Amz-SignedHeaders=host&X-Amz-Signature=608bb92fb07b871567f33d16729c33fb6a97c9d1960644da9b472e83009550b9",
       "file_name": "20260630_152428.hdf5",
-      "task_instruction": {
+      "additional_info": {
         "aaa": "111"
       }
     },
     {
       "download_url": "https://192.168.3.55:8443/dexverse/datasets/2606261645500010275566473183232/2607221248330338301292864606209/20260408_212630.hdf5?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=admin%2F20260724%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20260724T070457Z&X-Amz-Expires=86400&X-Amz-SignedHeaders=host&X-Amz-Signature=33e59a77325ad81b3c1f5294126ede617366cdbf3416d7ab79678fda75d65747",
       "file_name": "20260408_212630.hdf5",
-      "task_instruction": {
+      "additional_info": {
         "aaa": "111"
       }
     }
   ]
-}
+}

{dexverse_cli-0.0.2 → dexverse_cli-0.0.4}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "dexverse-cli"
-version = "0.0.2"
+version = "0.0.4"
 description = "DexVerse dataset downloader for S3-compatible robot training datasets"
 readme = "README.md"
 requires-python = ">=3.9"
@@ -48,6 +48,12 @@ dexverse-mock-server = "dexverse.mock.server:main"
 [tool.hatch.build.targets.wheel]
 packages = ["dexverse"]
 
+[tool.hatch.build]
+exclude = [
+  "/dexverse/dexe_cloud_upload/**",
+  "/648584.hdf5",
+]
+
 [tool.pytest.ini_options]
 testpaths = ["tests"]
 addopts = "-ra -q"

{dexverse_cli-0.0.2 → dexverse_cli-0.0.4}/set-creds.ps1

@@ -1,3 +1,3 @@
-$env:AWS_ACCESS_KEY_ID="AKIA...真实access_key"
-$env:AWS_SECRET_ACCESS_KEY="真实secret_key"
-$env:AWS_REGION="us-east-1"
+$env:AWS_ACCESS_KEY_ID="AKIA...真实access_key"
+$env:AWS_SECRET_ACCESS_KEY="真实secret_key"
+$env:AWS_REGION="us-east-1"

dexverse_cli-0.0.2/tests/test_convert_task_instruction.py → dexverse_cli-0.0.4/tests/test_convert_additional_info.py

@@ -20,22 +20,22 @@ def _write_minimal_hdf5(path: Path) -> None:
         joints.attrs["columns"] = json.dumps(["joint"])
 
 
-def _write_hidden_instruction(root: Path, relpath: str, instruction: dict) -> Path:
-    path = st.task_instruction_path(root, relpath)
+def _write_hidden_additional_info(root: Path, relpath: str, info: dict) -> Path:
+    path = st.additional_info_path(root, relpath)
     path.parent.mkdir(parents=True, exist_ok=True)
     path.write_text(
-        json.dumps(instruction, ensure_ascii=False, indent=2) + "\n",
+        json.dumps(info, ensure_ascii=False, indent=2) + "\n",
         encoding="utf-8",
     )
     return path
 
 
-def test_convert_single_file_writes_and_updates_raw_task_instruction(tmp_path):
+def test_convert_single_file_writes_and_updates_raw_additional_info(tmp_path):
     download_root = tmp_path / "download"
     source = download_root / "session.hdf5"
     restored = tmp_path / "restored" / "session"
     _write_minimal_hdf5(source)
-    instruction_path = _write_hidden_instruction(
+    info_path = _write_hidden_additional_info(
         download_root,
         "session.hdf5",
         {"aaa": "中文", "number": 1.1111111111111112e+54},
@@ -44,36 +44,34 @@ def test_convert_single_file_writes_and_updates_raw_task_instruction(tmp_path):
     frames = convert_hdf5(source, restored)
 
     assert frames == 1
-    output_path = restored / "task_instruction.json"
+    output_path = restored / "additional_info.json"
     assert json.loads(output_path.read_text(encoding="utf-8")) == {
         "aaa": "中文",
         "number": 1.1111111111111112e+54,
     }
-    assert '"task_instruction"' not in output_path.read_text(encoding="utf-8")
-
-    instruction_path.write_text('{"updated": 2}\n', encoding="utf-8")
+    info_path.write_text('{"updated": 2}\n', encoding="utf-8")
     convert_hdf5(source, restored)
     assert json.loads(output_path.read_text(encoding="utf-8")) == {"updated": 2}
 
-    instruction_path.unlink()
+    info_path.unlink()
     convert_hdf5(source, restored)
     assert not output_path.exists()
 
 
-def test_convert_batch_preserves_paths_for_task_instruction(tmp_path):
+def test_convert_batch_preserves_paths_for_additional_info(tmp_path):
     download_root = tmp_path / "download"
     source = download_root / "nested" / "batch.hdf5"
     restored_root = tmp_path / "restored"
     _write_minimal_hdf5(source)
-    instruction = {"task": "batch"}
-    _write_hidden_instruction(download_root, "nested/batch.hdf5", instruction)
+    info = {"task": "batch"}
+    _write_hidden_additional_info(download_root, "nested/batch.hdf5", info)
 
     success, frames = convert_batch(download_root, restored_root)
 
     assert success == 1
     assert frames == 1
-    output_path = restored_root / "nested" / "batch" / "task_instruction.json"
-    assert json.loads(output_path.read_text(encoding="utf-8")) == instruction
+    output_path = restored_root / "nested" / "batch" / "additional_info.json"
+    assert json.loads(output_path.read_text(encoding="utf-8")) == info
 
 
 def test_standalone_hdf5_without_downloader_metadata_stays_compatible(tmp_path):
@@ -84,4 +82,4 @@ def test_standalone_hdf5_without_downloader_metadata_stays_compatible(tmp_path):
     frames = convert_hdf5(source, restored)
 
     assert frames == 1
-    assert not (restored / "task_instruction.json").exists()
+    assert not (restored / "additional_info.json").exists()

{dexverse_cli-0.0.2 → dexverse_cli-0.0.4}/tests/test_http_backend.py

@@ -265,7 +265,7 @@ def test_minimal_two_field_manifest_downloads(tmp_path, http_server):
     assert (out / "ep.hdf5").read_bytes() == body
 
 
-def test_duplicate_filename_download_and_instruction_keep_first(tmp_path, http_server):
+def test_duplicate_filename_download_and_additional_info_keep_first(tmp_path, http_server):
     first_body = b"first-body"
     second_body = b"second-body"
     _seed(tmp_path, {"first.hdf5": first_body, "second.hdf5": second_body})
@@ -273,12 +273,12 @@ def test_duplicate_filename_download_and_instruction_keep_first(tmp_path, http_s
         {
             "download_url": http_server.url("first.hdf5"),
             "file_name": "same.hdf5",
-            "task_instruction": {"source": "第一条", "value": 1.1111111111111112e+54},
+            "additional_info": {"source": "第一条", "value": 1.1111111111111112e+54},
         },
         {
             "download_url": http_server.url("second.hdf5"),
             "file_name": "same.hdf5",
-            "task_instruction": {"source": "第二条"},
+            "additional_info": {"source": "第二条"},
         },
     ]
     manifest = Manifest.from_payload(payload)
@@ -290,11 +290,11 @@ def test_duplicate_filename_download_and_instruction_keep_first(tmp_path, http_s
     assert report.total == 1
     assert report.downloaded == 1
     assert (out / "same.hdf5").read_bytes() == first_body
-    instruction_path = st.task_instruction_path(out, "same.hdf5")
-    assert json.loads(instruction_path.read_text(encoding="utf-8")) == payload[0]["task_instruction"]
+    info_path = st.additional_info_path(out, "same.hdf5")
+    assert json.loads(info_path.read_text(encoding="utf-8")) == payload[0]["additional_info"]
 
 
-def test_skipped_file_still_syncs_task_instruction(tmp_path, http_server):
+def test_skipped_file_still_syncs_additional_info(tmp_path, http_server):
     body = b"already-downloaded"
     out = tmp_path / "out"
     out.mkdir()
@@ -303,26 +303,26 @@ def test_skipped_file_still_syncs_task_instruction(tmp_path, http_server):
         "download_url": http_server.url("unused.hdf5"),
         "file_name": "ep.hdf5",
         "file_size": len(body),
-        "task_instruction": {"mode": "skip"},
+        "additional_info": {"mode": "skip"},
     }])
 
     report = DownloadManager(out, backend="http").run(manifest)
 
     assert report.ok
     assert report.skipped == 1
-    instruction_path = st.task_instruction_path(out, "ep.hdf5")
-    assert json.loads(instruction_path.read_text(encoding="utf-8")) == {"mode": "skip"}
+    info_path = st.additional_info_path(out, "ep.hdf5")
+    assert json.loads(info_path.read_text(encoding="utf-8")) == {"mode": "skip"}
 
 
-def test_failed_or_corrupt_file_does_not_keep_task_instruction(tmp_path, http_server):
+def test_failed_or_corrupt_file_does_not_keep_additional_info(tmp_path, http_server):
     out = tmp_path / "out"
-    stale_path = st.task_instruction_path(out, "ep.hdf5")
+    stale_path = st.additional_info_path(out, "ep.hdf5")
     stale_path.parent.mkdir(parents=True)
     stale_path.write_text('{"stale": true}', encoding="utf-8")
     failed = Manifest.from_payload([{
         "download_url": http_server.url("missing.hdf5"),
         "file_name": "ep.hdf5",
-        "task_instruction": {"new": True},
+        "additional_info": {"new": True},
     }])
 
     failed_report = DownloadManager(out, backend="http").run(failed)
@@ -337,7 +337,7 @@ def test_failed_or_corrupt_file_does_not_keep_task_instruction(tmp_path, http_se
         "file_name": "ep.hdf5",
         "file_size": len(body),
         "sha256": "0" * 64,
-        "task_instruction": {"new": True},
+        "additional_info": {"new": True},
     }])
 
     corrupt_report = DownloadManager(out, backend="http", deep=True).run(corrupt)
@@ -346,11 +346,11 @@ def test_failed_or_corrupt_file_does_not_keep_task_instruction(tmp_path, http_se
     assert not stale_path.exists()
 
 
-def test_missing_instruction_clears_stale_hidden_metadata(tmp_path, http_server):
+def test_missing_additional_info_clears_stale_hidden_metadata(tmp_path, http_server):
     body = b"fresh-body"
     _seed(tmp_path, {"ep.hdf5": body})
     out = tmp_path / "out"
-    stale_path = st.task_instruction_path(out, "ep.hdf5")
+    stale_path = st.additional_info_path(out, "ep.hdf5")
     stale_path.parent.mkdir(parents=True)
     stale_path.write_text('{"stale": true}', encoding="utf-8")
     manifest = Manifest.from_payload([{

{dexverse_cli-0.0.2 → dexverse_cli-0.0.4}/tests/test_manifest_aliases.py

@@ -48,48 +48,88 @@ def test_manifest_from_files_wrapper_native():
     assert m.files[0].presignedUrl.startswith("https")
 
 
-def test_task_instruction_accepts_native_and_canonical_names():
-    instruction = {
+def test_additional_info_accepts_native_and_canonical_names():
+    info = {
         "aaa": "111",
         "aaaa": 222,
         "ewrwrwe": 1.1111111111111112e+54,
     }
     native = Manifest.from_payload({
-        "files": [{**_native_file(), "task_instruction": instruction}],
+        "files": [{**_native_file(), "additional_info": info}],
     })
     canonical = Manifest.from_payload({
-        "files": [{**_native_file(), "taskInstruction": instruction}],
+        "files": [{**_native_file(), "additionalInfo": info}],
     })
 
-    assert native.files[0].taskInstruction == instruction
-    assert canonical.files[0].taskInstruction == instruction
-    assert json.loads(native.model_dump_json())["files"][0]["taskInstruction"] == instruction
+    assert native.files[0].additionalInfo == info
+    assert canonical.files[0].additionalInfo == info
+    for manifest in (native, canonical):
+        dumped_file = json.loads(manifest.model_dump_json())["files"][0]
+        assert dumped_file["additionalInfo"] == info
+        assert "additional_info" not in dumped_file
+
+
+@pytest.mark.parametrize(
+    ("native_info", "canonical_info"),
+    [
+        ({"same": 1}, {"same": 1}),
+        ({"snake": 1}, {"camel": 2}),
+    ],
+    ids=["equal-values", "conflicting-values"],
+)
+def test_additional_info_aliases_cannot_be_used_together(
+    native_info,
+    canonical_info,
+):
+    with pytest.raises(ValidationError, match="cannot be used together"):
+        Manifest.from_payload({
+            "files": [{
+                **_native_file(),
+                "additional_info": native_info,
+                "additionalInfo": canonical_info,
+            }],
+        })
 
 
-def test_task_instruction_must_be_an_object():
+def test_additional_info_must_be_an_object():
     with pytest.raises(ValidationError):
         Manifest.from_payload({
-            "files": [{**_native_file(), "task_instruction": ["not", "an", "object"]}],
+            "files": [{**_native_file(), "additional_info": ["not", "an", "object"]}],
         })
 
 
-def test_duplicate_local_path_keeps_first_file_and_instruction():
+@pytest.mark.parametrize("legacy_field", ["task_instruction", "taskInstruction"])
+def test_removed_task_instruction_fields_are_rejected(legacy_field):
+    with pytest.raises(ValidationError, match="use 'additional_info' instead"):
+        Manifest.from_payload({
+            "files": [{**_native_file(), legacy_field: {"removed": True}}],
+        })
+
+
+def test_unrelated_extension_fields_remain_allowed():
+    manifest = Manifest.from_payload({
+        "files": [{**_native_file(), "additional_info": {"source": "native"}, "future": 1}],
+    })
+    assert manifest.files[0].model_extra == {"expires_at": "2026-07-07T04:04:14+00:00", "expires_in": 3600, "future": 1}
+
+
+def test_duplicate_local_path_keeps_first_file_and_additional_info():
     first = {
         **_native_file("first/source.hdf5", url="https://host/first/source.hdf5"),
         "file_name": "same.hdf5",
-        "task_instruction": {"source": "first"},
+        "additional_info": {"source": "first"},
     }
     second = {
         **_native_file("second/source.hdf5", url="https://host/second/source.hdf5"),
         "file_name": "same.hdf5",
-        "task_instruction": {"source": "second"},
+        "additional_info": {"source": "second"},
     }
 
     manifest = Manifest.from_payload({"files": [first, second]})
 
     assert len(manifest.files) == 1
     assert manifest.files[0].objectKey == "first/source.hdf5"
-    assert manifest.files[0].taskInstruction == {"source": "first"}
+    assert manifest.files[0].additionalInfo == {"source": "first"}
 
 
 def test_from_payload_accepts_json_string_and_list_string():