Simplify quick start to prompt plus video path only

README.md

@@ -60,21 +60,6 @@ python quick_start/render_prediction_video.py \
   --input-jsonl quick_start/outputs/video.jsonl
 ```
 
-## Reproduce Bundled Examples
-
-You can reproduce the bundled reference outputs directly from the release root.
-
-Single example:
-
-```bash
-python quick_start/run_example.py \
-  --model-path /path/to/VLAC2-Qwen3VL-30B-A3B-Progress \
-  --metadata-path examples/example_01/metadata.json \
-  --output-jsonl quick_start/outputs/example_01.jsonl
-
-python quick_start/render_prediction_video.py \
-  --input-jsonl quick_start/outputs/example_01.jsonl \
-  --output-video quick_start/outputs/example_01_pred_progress.mp4
-```
+Bundled videos under `examples/` can be used with the same interface by passing the video path and prompt text directly.
 
 More detailed usage is provided in `quick_start/README.md`.

quick_start/README.md

@@ -25,6 +25,14 @@ python quick_start/run_example.py \
   --task-instruction "把洋葱放进快递箱里。"
 ```
 
+Bundled videos under `examples/` are used the same way:
+
+```bash
+python quick_start/run_example.py \
+  --video-path examples/example_01/episode.mp4 \
+  --prompt $'任务描述和具体规划: 抓取紫色方块使其从方形洞口落入积木桶中\n爪夹开始移动：0%\n爪夹接近紫色方块：20%\n爪夹抓紧紫色方块：40%\n爪夹抓紧紫色方块接近方形洞口：60%\n爪夹将紫色方块对准方形洞口：80%\n紫色方块从方形洞口落入积木桶中，爪夹移开：100%\n\n请根据任务描述和具体规划，找到并逐点生成视频中的关键动作点和相应的进度标注。输出格式要求：每个关键点一行，格式为：\n时间: X.Xs, 进度: Y%\n\n请严格按照上述格式输出，不要输出额外说明。'
+```
+
 If you have a more detailed task plan, pass it directly as text:
 
 ```bash
@@ -51,38 +59,6 @@ python quick_start/run_example.py \
   --task-instruction "把洋葱放进快递箱里。"
 ```
 
-## Use Bundled Examples
-
-The bundled examples already provide `metadata.json` files with task information, so you can reproduce the reference outputs directly from the release root.
-
-Single example:
-
-```bash
-python quick_start/run_example.py \
-  --model-path /path/to/VLAC2-Qwen3VL-30B-A3B-Progress \
-  --metadata-path examples/example_01/metadata.json \
-  --output-jsonl quick_start/outputs/example_01.jsonl
-
-python quick_start/render_prediction_video.py \
-  --input-jsonl quick_start/outputs/example_01.jsonl \
-  --output-video quick_start/outputs/example_01_pred_progress.mp4
-```
-
-All three bundled examples:
-
-```bash
-for ex in example_01 example_02 example_03; do
-  python quick_start/run_example.py \
-    --model-path /path/to/VLAC2-Qwen3VL-30B-A3B-Progress \
-    --metadata-path "examples/${ex}/metadata.json" \
-    --output-jsonl "quick_start/outputs/${ex}.jsonl"
-
-  python quick_start/render_prediction_video.py \
-    --input-jsonl "quick_start/outputs/${ex}.jsonl" \
-    --output-video "quick_start/outputs/${ex}_pred_progress.mp4"
-done
-```
-
 ## Output
 
 By default the inference script writes:
@@ -92,7 +68,7 @@ By default the inference script writes:
 Each output file contains one JSONL row with:
 
 - input video path
-- optional metadata fields when `--metadata-path` is used
+- optional task instruction and task plan text
 - sampled frame indices and timestamps
 - decoded video statistics
 - prompt text

quick_start/run_example.py

@@ -7,7 +7,6 @@ import os
 import re
 import tempfile
 from pathlib import Path
-from typing import Any
 
 import numpy as np
 from PIL import Image
@@ -38,14 +37,8 @@ def parse_args() -> argparse.Namespace:
     parser.add_argument(
         "--video-path",
         type=Path,
-        default=None,
-        help="Path to the input video. Optional when --metadata-path is provided and metadata contains video_path.",
-    )
-    parser.add_argument(
-        "--metadata-path",
-        type=Path,
-        default=None,
-        help="Optional metadata JSON path. If provided, task fields and relative video_path can be inferred from it.",
+        required=True,
+        help="Path to the input video.",
     )
     parser.add_argument(
         "--task-instruction",
@@ -86,29 +79,6 @@ def parse_args() -> argparse.Namespace:
     return parser.parse_args()
 
 
-def load_metadata(metadata_path: Path | None) -> tuple[Path | None, dict[str, Any] | None]:
-    if metadata_path is None:
-        return None, None
-    resolved = metadata_path.resolve()
-    if not resolved.exists():
-        raise SystemExit(f"Missing metadata JSON: {resolved}")
-    payload = json.loads(resolved.read_text(encoding="utf-8"))
-    if not isinstance(payload, dict):
-        raise SystemExit(f"Metadata JSON must contain an object: {resolved}")
-    return resolved, payload
-
-
-def extract_plan_text(task_instruction: str, task_description: str) -> str:
-    lines = [line.strip() for line in str(task_description or "").splitlines() if line.strip()]
-    if not lines:
-        return ""
-    first_line = lines[0].rstrip("：:")
-    normalized_instruction = str(task_instruction or "").strip().rstrip("：:")
-    if normalized_instruction and first_line == normalized_instruction:
-        lines = lines[1:]
-    return "\n".join(lines).strip()
-
-
 def build_chunk_all_prompt(task_instruction: str, task_plan: str | None) -> str:
     task_instruction = task_instruction.strip()
     task_plan = (task_plan or "").strip()
@@ -122,54 +92,26 @@ def build_chunk_all_prompt(task_instruction: str, task_plan: str | None) -> str:
     )
 
 
-def resolve_prompt(args: argparse.Namespace, metadata: dict[str, Any] | None) -> tuple[str, str, str | None, str | None]:
+def resolve_prompt(args: argparse.Namespace) -> tuple[str, str, str | None, str | None]:
     prompt = args.prompt.strip() if args.prompt else None
     task_plan = args.task_plan.strip() if args.task_plan else None
-
-    metadata_task_instruction = None
-    metadata_task_plan = None
-    if metadata is not None:
-        metadata_task_instruction = str(metadata.get("task_instruction") or "").strip() or None
-        metadata_task_description = str(metadata.get("task_description") or "").strip()
-        if metadata_task_instruction and metadata_task_description:
-            metadata_task_plan = extract_plan_text(metadata_task_instruction, metadata_task_description) or None
-
-    task_instruction = args.task_instruction.strip() if args.task_instruction else metadata_task_instruction
-    if task_plan is None:
-        task_plan = metadata_task_plan
+    task_instruction = args.task_instruction.strip() if args.task_instruction else None
 
     if prompt:
         return prompt, "raw_prompt", task_instruction, task_plan
 
     if not task_instruction:
         raise SystemExit(
-            "Either provide --prompt, or provide --task-instruction, "
-            "or provide --metadata-path with task_instruction."
+            "Either provide --prompt, or provide --task-instruction with optional --task-plan."
         )
 
     return build_chunk_all_prompt(task_instruction, task_plan), "task_instruction_plus_plan", task_instruction, task_plan
 
 
-def resolve_video_path(
-    video_path_arg: Path | None,
-    metadata: dict[str, Any] | None,
-) -> Path:
-    if video_path_arg is not None:
-        video_path = video_path_arg.resolve()
-        if not video_path.exists():
-            raise SystemExit(f"Missing video: {video_path}")
-        return video_path
-
-    if metadata is None or not metadata.get("video_path"):
-        raise SystemExit("Either provide --video-path, or provide --metadata-path with video_path.")
-
-    metadata_video_path = Path(str(metadata["video_path"]))
-    if metadata_video_path.is_absolute():
-        video_path = metadata_video_path
-    else:
-        video_path = (MODEL_ROOT / metadata_video_path).resolve()
+def resolve_video_path(video_path_arg: Path) -> Path:
+    video_path = video_path_arg.resolve()
     if not video_path.exists():
-        raise SystemExit(f"Missing video resolved from metadata: {video_path}")
+        raise SystemExit(f"Missing video: {video_path}")
     return video_path
 
 
@@ -333,13 +275,12 @@ def parse_point_blocks(text: str) -> tuple[list[float], list[float]]:
 
 def main() -> int:
     args = parse_args()
-    metadata_path, metadata = load_metadata(args.metadata_path)
     model_path = args.model_path.resolve()
     if not model_path.exists():
         raise SystemExit(f"Missing model path: {model_path}")
 
-    prompt, prompt_source, task_instruction, task_plan = resolve_prompt(args, metadata)
-    video_path = resolve_video_path(args.video_path, metadata)
+    prompt, prompt_source, task_instruction, task_plan = resolve_prompt(args)
+    video_path = resolve_video_path(args.video_path)
     video_path_for_output = maybe_relativize_to_model_root(video_path)
     output_path = args.output_jsonl or (THIS_DIR / "outputs" / f"{video_path.stem}.jsonl")
     output_path.parent.mkdir(parents=True, exist_ok=True)
@@ -377,17 +318,11 @@ def main() -> int:
 
     pred_point_times_sec, pred_point_progress = parse_point_blocks(response)
 
-    output_row: dict[str, Any] = {}
-    if metadata is not None:
-        for key in ("example_id", "bucket", "global_episode_id", "task_instruction", "task_description"):
-            if key in metadata:
-                output_row[key] = metadata.get(key)
-    if "task_instruction" not in output_row and task_instruction is not None:
+    output_row: dict[str, object] = {}
+    if task_instruction is not None:
         output_row["task_instruction"] = task_instruction
     if task_plan:
         output_row["task_plan"] = task_plan
-    if metadata_path is not None:
-        output_row["metadata_path"] = maybe_relativize_to_model_root(metadata_path)
 
     output_row.update(
         {