deer-flow/tests/skills/test_video_generation.py
DanielWalnut cd5bedaa74
feat: MiniMax provider for image/video/podcast skills + new music-generation skill (#3437)
* docs(spec): MiniMax integration for generation skills + new music skill

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* docs(plan): MiniMax generation providers implementation plan

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* test(skills): add importlib loader + FakeResp for skill tests

* test(skills): register loaded module in sys.modules; raise requests.HTTPError in FakeResp

* feat(image-generation): add MiniMax provider with env auto-detect

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* refactor(image-generation): guard unknown provider, derive ref MIME, strengthen tests

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* feat(video-generation): add MiniMax provider with async poll/download

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* refactor(video-generation): surface base_resp errors while polling; add timeout test

* feat(podcast-generation): add MiniMax t2a_v2 provider with env auto-detect

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* refactor(podcast-generation): restore TTS credential guard; add volcengine + voice tests

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* feat(music-generation): new MiniMax music skill via skill-creator

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* refactor(music-generation): treat empty lyrics as absent; test no-audio-data path

* refactor(skills): add request timeouts to MiniMax network calls

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* Potential fix for pull request finding 'Explicit returns mixed with implicit (fall through) returns'

Co-authored-by: Copilot Autofix powered by AI <223894421+github-code-quality[bot]@users.noreply.github.com>

* fix(models): strip inconsistent user-message names for MiniMax chat

DeerFlow middlewares tag user messages with provenance names (user-input, summary, loop_warning); langchain serializes them into the OpenAI-compatible payload and MiniMax rejects mismatched user-message names with "user name must be consistent (2013)". PatchedChatMiniMax now drops the per-message name from user-role messages. Point the config.example MiniMax models at PatchedChatMiniMax so they also get reasoning_content mapping.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* feat(image-generation): MiniMax sends JSON prompt field, guard 1500-char limit

MiniMax image-01 takes one text string capped at 1500 chars, but the skill was sending the whole structured JSON. The MiniMax provider now extracts the JSON `prompt` field (relying on prompt_optimizer to expand it) and fails fast with a clear error before calling the API when that field exceeds 1500 chars. Authoring stays provider-agnostic; Gemini still receives the full JSON.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* feat(podcast-generation): per-provider TTS concurrency and retry/backoff

Each TTS provider owns its concurrency internally — MiniMax runs single-threaded to reduce rate-limit failures, Volcengine keeps 4 workers — with automatic retry and backoff on transient HTTP and base_resp errors. No caller-facing concurrency knob.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* fix(skills): address Copilot review comments on generation skills

- video: add raise_for_status + timeout to the Gemini download/POST/poll calls so non-2xx responses surface as clear HTTP errors instead of JSON/KeyError or hangs
- video: check the task Fail status before the generic base_resp check so the failure keeps its task_id context
- video/image: create the output file parent directory before writing (matching music-generation) so nested output paths do not raise FileNotFoundError
- music: require a non-empty prompt and fail fast with ValueError instead of sending an empty prompt to the API

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* fix(scripts): reclaim dev ports across worktrees in make stop/dev

All deer-flow worktrees (main checkout + linked worktrees) hardcode the same dev ports (8001/3000/2026), so a service started from any worktree must be reclaimable from another. stop_all now resolves the set of worktree roots (DEERFLOW_ROOTS) and treats a process as deer-flow-owned when its open files live under any of them. It also force-kills survivors on 2026 alongside 8001/3000, fixing `make dev` aborting on the nginx port preflight when a prior nginx lingered on 2026.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* fix(view-image): hide the injected image-context message from the UI

ViewImageMiddleware injects a HumanMessage (text + base64 images) so the vision model can see viewed images, but it was the only internal injector that set neither hide_from_ui nor a hidden name, so it leaked into the chat UI (and IM channels) as a user bubble reading "Here are the images you've viewed:". Mark it with additional_kwargs={"hide_from_ui": True}, matching todo/dynamic_context injections, which the frontend isHiddenFromUIMessage and the channel sender already honor. The model still receives the full content.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* fix(minimax): mark M2.7 models as text-only (no vision)

MiniMax M2.7 / M2.7-highspeed do not support vision; only M3 does. The
provider config asserted vision support for M2.7 in four places.

- config.example.yaml: 4 M2.7 entries -> supports_vision: false
- backend/docs/CONFIGURATION.md: M2.7 + highspeed -> supports_vision: false
- wizard: add LLMProvider.model_vision_overrides + extra_config_for() so
  selecting an M2.7 model writes supports_vision: false while M3 (default)
  keeps vision; wire it through setup_wizard.py
- tests: M2.7-highspeed fixture -> supports_vision=False; add
  test_minimax_vision_is_per_model

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
Co-authored-by: Copilot Autofix powered by AI <223894421+github-code-quality[bot]@users.noreply.github.com>
2026-06-08 22:04:38 +08:00

188 lines
7.1 KiB
Python

import sys
from pathlib import Path
import pytest
import requests
sys.path.insert(0, str(Path(__file__).resolve().parent))
from skill_loader import FakeResp, load # noqa: E402
vid = load("video-generation")
@pytest.fixture(autouse=True)
def clean_env(monkeypatch):
for k in ["GEMINI_API_KEY", "MINIMAX_API_KEY", "VIDEO_GENERATION_PROVIDER",
"MINIMAX_API_HOST", "MINIMAX_VIDEO_MODEL"]:
monkeypatch.delenv(k, raising=False)
monkeypatch.setattr(vid.time, "sleep", lambda *_: None)
def test_resolve_prefers_gemini():
assert vid._resolve_provider("VIDEO_GENERATION_PROVIDER", "gemini", True) == "gemini"
def test_resolve_falls_back_to_minimax(monkeypatch):
monkeypatch.setenv("MINIMAX_API_KEY", "m")
assert vid._resolve_provider("VIDEO_GENERATION_PROVIDER", "gemini", False) == "minimax"
def test_resolve_override(monkeypatch):
monkeypatch.setenv("VIDEO_GENERATION_PROVIDER", "minimax")
assert vid._resolve_provider("VIDEO_GENERATION_PROVIDER", "gemini", True) == "minimax"
def test_unknown_provider_raises(monkeypatch, tmp_path):
monkeypatch.setenv("VIDEO_GENERATION_PROVIDER", "openai")
monkeypatch.setenv("GEMINI_API_KEY", "g")
pf = tmp_path / "p.json"
pf.write_text("x", encoding="utf-8")
with pytest.raises(ValueError):
vid.generate_video(str(pf), [], str(tmp_path / "v.mp4"), "16:9")
def test_minimax_full_flow(monkeypatch, tmp_path):
monkeypatch.setenv("MINIMAX_API_KEY", "m")
posts = {}
def fake_post(url, headers=None, json=None, **kw):
posts["url"] = url
posts["json"] = json
return FakeResp({"task_id": "T1", "base_resp": {"status_code": 0}})
def fake_get(url, headers=None, params=None, **kw):
if url.endswith("/v1/query/video_generation"):
assert params["task_id"] == "T1"
return FakeResp({"status": "Success", "file_id": "F1",
"base_resp": {"status_code": 0}})
if url.endswith("/v1/files/retrieve"):
assert params["file_id"] == "F1"
return FakeResp({"file": {"download_url": "https://dl/v.mp4"},
"base_resp": {"status_code": 0}})
return FakeResp(content=b"MP4DATA") # the actual download
monkeypatch.setattr(vid.requests, "post", fake_post)
monkeypatch.setattr(vid.requests, "get", fake_get)
out = tmp_path / "v.mp4"
pf = tmp_path / "p.json"
pf.write_text("a cat runs", encoding="utf-8")
msg = vid.generate_video(str(pf), [], str(out), "16:9")
assert out.read_bytes() == b"MP4DATA"
assert posts["url"].endswith("/v1/video_generation")
assert posts["json"]["model"] == "MiniMax-Hailuo-2.3"
assert "successfully" in msg.lower()
def test_minimax_reference_first_frame(monkeypatch, tmp_path):
monkeypatch.setenv("MINIMAX_API_KEY", "m")
posts = {}
def fake_post(url, headers=None, json=None, **kw):
posts["json"] = json
return FakeResp({"task_id": "T1", "base_resp": {"status_code": 0}})
def fake_get(url, headers=None, params=None, **kw):
if url.endswith("/v1/query/video_generation"):
return FakeResp({"status": "Success", "file_id": "F1", "base_resp": {"status_code": 0}})
if url.endswith("/v1/files/retrieve"):
return FakeResp({"file": {"download_url": "https://dl/v.mp4"}, "base_resp": {"status_code": 0}})
return FakeResp(content=b"X")
monkeypatch.setattr(vid.requests, "post", fake_post)
monkeypatch.setattr(vid.requests, "get", fake_get)
ref = tmp_path / "f.jpg"
ref.write_bytes(b"\xff\xd8img")
pf = tmp_path / "p.json"
pf.write_text("x", encoding="utf-8")
vid.generate_video(str(pf), [str(ref)], str(tmp_path / "v.mp4"), "16:9")
assert posts["json"]["first_frame_image"].startswith("data:image/jpeg;base64,")
def test_minimax_task_fail(monkeypatch, tmp_path):
monkeypatch.setenv("MINIMAX_API_KEY", "m")
def fake_post(url, headers=None, json=None, **kw):
return FakeResp({"task_id": "T1", "base_resp": {"status_code": 0}})
def fake_get(url, headers=None, params=None, **kw):
return FakeResp({"status": "Fail", "base_resp": {"status_code": 1027, "status_msg": "blocked"}})
monkeypatch.setattr(vid.requests, "post", fake_post)
monkeypatch.setattr(vid.requests, "get", fake_get)
pf = tmp_path / "p.json"
pf.write_text("x", encoding="utf-8")
with pytest.raises(Exception):
vid.generate_video(str(pf), [], str(tmp_path / "v.mp4"), "16:9")
def test_minimax_poll_timeout(monkeypatch):
def fake_get(url, headers=None, params=None, **kw):
return FakeResp({"status": "Processing", "base_resp": {"status_code": 0}})
monkeypatch.setattr(vid.requests, "get", fake_get)
with pytest.raises(Exception) as e:
vid._poll_video_task("https://h", "Bearer m", "T1", max_attempts=3, interval=0)
assert "timed out" in str(e.value)
def test_minimax_task_fail_keeps_task_context(monkeypatch, tmp_path):
# A Fail status takes priority over the generic base_resp check, so the
# error keeps the task_id and the task-level failure message.
monkeypatch.setenv("MINIMAX_API_KEY", "m")
def fake_post(url, headers=None, json=None, **kw):
return FakeResp({"task_id": "T1", "base_resp": {"status_code": 0}})
def fake_get(url, headers=None, params=None, **kw):
return FakeResp({"status": "Fail", "base_resp": {"status_code": 1027, "status_msg": "blocked"}})
monkeypatch.setattr(vid.requests, "post", fake_post)
monkeypatch.setattr(vid.requests, "get", fake_get)
pf = tmp_path / "p.json"
pf.write_text("x", encoding="utf-8")
with pytest.raises(Exception, match="task T1 failed"):
vid.generate_video(str(pf), [], str(tmp_path / "v.mp4"), "16:9")
def test_gemini_download_raises_on_http_error(monkeypatch, tmp_path):
monkeypatch.setenv("GEMINI_API_KEY", "g")
calls = {}
def fake_get(url, headers=None, **kw):
calls["timeout"] = kw.get("timeout")
return FakeResp(content=b"error page", status_code=500)
monkeypatch.setattr(vid.requests, "get", fake_get)
out = tmp_path / "sub" / "v.mp4"
with pytest.raises(requests.HTTPError):
vid.download("https://dl/v.mp4", str(out))
assert calls["timeout"] # a timeout is now passed
assert not out.exists()
def test_gemini_download_writes_nested_dir(monkeypatch, tmp_path):
monkeypatch.setenv("GEMINI_API_KEY", "g")
def fake_get(url, headers=None, **kw):
return FakeResp(content=b"VIDEO")
monkeypatch.setattr(vid.requests, "get", fake_get)
out = tmp_path / "nested" / "dir" / "v.mp4"
vid.download("https://dl/v.mp4", str(out))
assert out.read_bytes() == b"VIDEO"
def test_gemini_post_raises_on_http_error(monkeypatch, tmp_path):
monkeypatch.setenv("GEMINI_API_KEY", "g")
def fake_post(url, headers=None, json=None, **kw):
return FakeResp(status_code=503)
monkeypatch.setattr(vid.requests, "post", fake_post)
pf = tmp_path / "p.json"
pf.write_text("a cat", encoding="utf-8")
with pytest.raises(requests.HTTPError):
vid.generate_video(str(pf), [], str(tmp_path / "v.mp4"), "16:9")