@lemoncat7/dsh-partner 2.4.2 → 2.7.0

package/resources/skills/drama-production/upstream/skills/short-drama-produce/references/providers/seedance.md

@@ -0,0 +1,64 @@
+# Seedance adapter
+
+Adapter command:
+
+```json
+{"command": ["python3", "/absolute/path/provider_adapters.py", "seedance"], "timeout_seconds": 3600}
+```
+
+Required environment:
+
+- `ARK_API_KEY`: Volcengine Ark API key.
+- `SEEDANCE_MODEL`: the exact enabled model/endpoint ID. There is intentionally no model default; in particular the
+  adapter never assumes Seedance 2.0.
+
+Optional environment:
+
+- `SEEDANCE_BASE_URL` (default `https://ark.cn-beijing.volces.com/api/v3`)
+- `SEEDANCE_POLL_INTERVAL` (default `5` seconds)
+- `SEEDANCE_TIMEOUT_SECONDS` (default `1800` seconds)
+- `SEEDANCE_ALLOWED_RATIOS`: comma-separated subset explicitly supported by
+  the configured model, such as `9:16,16:9`.
+- `SEEDANCE_MIN_DURATION` and `SEEDANCE_MAX_DURATION`: the configured model's
+  explicit inclusive duration range. Set both or neither. Official integer profiles are `4–15`
+  for Seedance 2.0 and `4–30` for Seedance 2.5.
+
+The job must have modality `video` and exactly one `.mp4` output. Optional
+`duration` and `ratio` parameters are accepted only when the external runtime
+profile above explicitly permits their values, then sent as the API's top-level fields. Optional
+`generate_audio` is a boolean. The broad compiler envelope remains configurable rather than proving
+that every Seedance release supports every value.
+
+The compiler also forwards `duration: -1` without applying the positive-integer range. For ordinary
+Seedance 2.0/2.5 generation this asks the model to choose within its native range; for 2.5 `edit` it
+preserves the source video's duration instead. The adapter does not estimate spoken dialogue or
+lengthen a short job. Fixed-duration delivery needs an explicit accepted duration; auto-duration
+output needs its actual media length and speech checked before timing is accepted. The API response's
+integer `duration` rounds down the frame-based duration, so it is not a precise media measurement.
+
+`compile_seedance_payload` accepts explicit `reference_image`, `reference_video`, and
+`reference_audio` roles with matching HTTPS, `asset://` or base64 data URI values. It emits the matching multimodal
+content type and uses `@图片N`、`@视频N`、`@音频N` in its appended reference contract. The bundled
+runtime sends a project-relative reference inline as a `data:<mime>;base64,<...>` URI, which the
+official contract lists alongside a public URL and `asset://`, so binding an image in the creator
+documents is enough to run the job. Each file's bytes must match the media type its extension claims.
+Volcengine publishes no per-file size numbers, so this adapter applies the same conservative guard as
+the MiniMax path — 30MB per image, 50MB per video, 15MB per audio clip, 64MB per request after base64
+expansion — and fails closed above them rather than sending a body the provider may reject. Each
+reference takes its provider role from the confirmed job's `reference_bindings[].role`; a job with
+references but no bindings fails closed rather than guessing.
+
+Prompt wording for Seedance 2.0 is version-specific: normal reference uses “参考 @视频1”, while
+continuation says “向后延长 @视频1” and binds the actual tail as `@图片1`. See the video-prompt
+skill's `references/seedance-2.0.md`.
+
+Seedance 2.5 has a separate `references/seedance-2.5.md` dialect and may carry
+`omni_reference_task_type: reference|edit|extend|auto`. The compiler enforces the documented hard
+parameter combinations for `edit` (`adaptive`, `-1`, reference video) and `extend` (`adaptive`,
+reference video). It does not infer the task type from prompt keywords, because the API checks that
+the explicit type and semantic intent agree.
+
+The adapter creates an asynchronous task, polls `GET /contents/generations/tasks/{id}` until a terminal state, and
+downloads `content.video_url` into a private temporary directory. Any unknown status fails closed.
+
+Protocol reference: [Volcengine video generation API](https://www.volcengine.com/docs/82379/1520757).

package/resources/skills/drama-production/upstream/skills/short-drama-produce/scripts/fixture_adapter.py

@@ -0,0 +1,77 @@
+#!/usr/bin/env python3
+"""Offline adapter fixture for image, video, TTS, and music production tests."""
+
+from __future__ import annotations
+
+import argparse
+import base64
+import json
+import struct
+import sys
+import wave
+from pathlib import Path
+
+MINIMUM_PYTHON = (3, 9)
+if sys.version_info < MINIMUM_PYTHON:
+    raise SystemExit(
+        "short-drama-produce fixture needs Python {}.{} or newer".format(
+            *MINIMUM_PYTHON
+        )
+    )
+
+PNG = base64.b64decode(
+    "iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAQAAAC1HAwCAAAAC0lEQVR42mNk+A8AAQUBAScY42YAAAAASUVORK5CYII="
+)
+
+
+def main() -> int:
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--fail", action="store_true")
+    # A real video provider bills at submission and can be interrupted at any
+    # point afterwards. `--submit-then-fail` reproduces exactly that: record the
+    # handle the way a live adapter does, then die before returning anything.
+    parser.add_argument("--submit-then-fail", action="store_true")
+    args = parser.parse_args()
+    job = json.load(sys.stdin.buffer)
+    collecting = job.get("collect_provider_job_id")
+    if args.submit_then_fail and not collecting:
+        destination = job.get("handle_path")
+        if isinstance(destination, str) and destination:
+            path = Path(destination)
+            path.parent.mkdir(parents=True, exist_ok=True)
+            path.write_text(
+                json.dumps({"provider_job_id": "fixture-task-1"}), encoding="utf-8"
+            )
+        return 7
+    if args.fail:
+        return 7
+    directory_raw = job.get("output_root")
+    if not isinstance(directory_raw, str):
+        return 8
+    directory = Path(directory_raw)
+    if not directory.is_absolute() or not directory.is_dir() or directory.is_symlink():
+        return 8
+    outputs = []
+    for index, target in enumerate(job["outputs"]):
+        suffix = Path(target).suffix.lower()
+        path = directory / f"output-{index}{suffix}"
+        if job["modality"] == "image":
+            path.write_bytes(PNG)
+        elif job["modality"] == "video":
+            path.write_bytes(b"\x00\x00\x00\x18ftypisom" + b"\x00" * 24)
+        else:
+            with wave.open(str(path), "wb") as handle:
+                handle.setnchannels(1)
+                handle.setsampwidth(2)
+                handle.setframerate(8000)
+                handle.writeframes(struct.pack("<h", 0) * 80)
+        outputs.append({"target": target, "source": str(path)})
+    response = {"outputs": outputs, "provider_job_id": "fixture-local"}
+    if isinstance(collecting, str) and collecting:
+        response["provider_job_id"] = collecting
+    json.dump(response, sys.stdout)
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())