deer-flow/tests/skills/test_music_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

136 lines
5.2 KiB
Python

import sys
from pathlib import Path
import pytest
sys.path.insert(0, str(Path(__file__).resolve().parent))
from skill_loader import FakeResp, load # noqa: E402
mus = load("music-generation")
@pytest.fixture(autouse=True)
def clean_env(monkeypatch):
for k in ["MINIMAX_API_KEY", "MINIMAX_API_HOST", "MINIMAX_MUSIC_MODEL"]:
monkeypatch.delenv(k, raising=False)
def _post_ok(captured):
def fake_post(url, headers=None, json=None, **kw):
captured["url"] = url
captured["headers"] = headers
captured["json"] = json
return FakeResp({"data": {"audio": b"songbytes".hex(), "status": 2},
"base_resp": {"status_code": 0}})
return fake_post
def test_with_lyrics_payload_and_writes(monkeypatch, tmp_path):
monkeypatch.setenv("MINIMAX_API_KEY", "m")
captured = {}
monkeypatch.setattr(mus.requests, "post", _post_ok(captured))
spec = tmp_path / "s.json"
spec.write_text('{"title":"X","prompt":"pop, happy","lyrics":"[verse]\\nla la"}',
encoding="utf-8")
out = tmp_path / "o.mp3"
msg = mus.generate_music(str(spec), str(out))
assert out.read_bytes() == b"songbytes"
assert captured["url"].endswith("/v1/music_generation")
assert captured["headers"]["Authorization"] == "Bearer m"
assert captured["json"]["model"] == "music-2.6-free"
assert captured["json"]["lyrics"] == "[verse]\nla la"
assert captured["json"]["output_format"] == "hex"
assert "Successfully generated music" in msg
def test_instrumental_sets_flag(monkeypatch, tmp_path):
monkeypatch.setenv("MINIMAX_API_KEY", "m")
captured = {}
monkeypatch.setattr(mus.requests, "post", _post_ok(captured))
spec = tmp_path / "s.json"
spec.write_text('{"prompt":"lofi beats","is_instrumental":true}', encoding="utf-8")
mus.generate_music(str(spec), str(tmp_path / "o.mp3"))
assert captured["json"]["is_instrumental"] is True
assert "lyrics" not in captured["json"]
assert "lyrics_optimizer" not in captured["json"]
def test_no_lyrics_uses_optimizer(monkeypatch, tmp_path):
monkeypatch.setenv("MINIMAX_API_KEY", "m")
captured = {}
monkeypatch.setattr(mus.requests, "post", _post_ok(captured))
spec = tmp_path / "s.json"
spec.write_text('{"prompt":"sad ballad"}', encoding="utf-8")
mus.generate_music(str(spec), str(tmp_path / "o.mp3"))
assert captured["json"]["lyrics_optimizer"] is True
assert "lyrics" not in captured["json"]
def test_model_override(monkeypatch, tmp_path):
monkeypatch.setenv("MINIMAX_API_KEY", "m")
monkeypatch.setenv("MINIMAX_MUSIC_MODEL", "music-2.6")
captured = {}
monkeypatch.setattr(mus.requests, "post", _post_ok(captured))
spec = tmp_path / "s.json"
spec.write_text('{"prompt":"jazz","lyrics":"[verse]\\nhi"}', encoding="utf-8")
mus.generate_music(str(spec), str(tmp_path / "o.mp3"))
assert captured["json"]["model"] == "music-2.6"
def test_raises_on_base_resp_error(monkeypatch, tmp_path):
monkeypatch.setenv("MINIMAX_API_KEY", "m")
def fake_post(url, headers=None, json=None, **kw):
return FakeResp({"base_resp": {"status_code": 1008, "status_msg": "no balance"}})
monkeypatch.setattr(mus.requests, "post", fake_post)
spec = tmp_path / "s.json"
spec.write_text('{"prompt":"x","lyrics":"[verse]\\ny"}', encoding="utf-8")
with pytest.raises(Exception) as e:
mus.generate_music(str(spec), str(tmp_path / "o.mp3"))
assert "1008" in str(e.value)
def test_missing_api_key_returns_message(monkeypatch, tmp_path):
spec = tmp_path / "s.json"
spec.write_text('{"prompt":"x"}', encoding="utf-8")
msg = mus.generate_music(str(spec), str(tmp_path / "o.mp3"))
assert "MINIMAX_API_KEY" in msg
def test_raises_on_missing_audio_data(monkeypatch, tmp_path):
monkeypatch.setenv("MINIMAX_API_KEY", "m")
def fake_post(url, headers=None, json=None, **kw):
return FakeResp({"base_resp": {"status_code": 0}}) # no "data" key
monkeypatch.setattr(mus.requests, "post", fake_post)
spec = tmp_path / "s.json"
spec.write_text('{"prompt":"x"}', encoding="utf-8")
with pytest.raises(Exception, match="no audio data"):
mus.generate_music(str(spec), str(tmp_path / "o.mp3"))
def test_empty_prompt_raises(monkeypatch, tmp_path):
monkeypatch.setenv("MINIMAX_API_KEY", "m")
def fake_post(url, headers=None, json=None, **kw): # pragma: no cover
raise AssertionError("must not call the API when prompt is missing")
monkeypatch.setattr(mus.requests, "post", fake_post)
spec = tmp_path / "s.json"
spec.write_text('{"title":"X","lyrics":"[verse]\\nhi"}', encoding="utf-8") # no prompt
with pytest.raises(ValueError, match="prompt"):
mus.generate_music(str(spec), str(tmp_path / "o.mp3"))
def test_empty_lyrics_falls_back_to_optimizer(monkeypatch, tmp_path):
monkeypatch.setenv("MINIMAX_API_KEY", "m")
captured = {}
monkeypatch.setattr(mus.requests, "post", _post_ok(captured))
spec = tmp_path / "s.json"
spec.write_text('{"prompt":"x","lyrics":""}', encoding="utf-8")
mus.generate_music(str(spec), str(tmp_path / "o.mp3"))
assert captured["json"]["lyrics_optimizer"] is True
assert "lyrics" not in captured["json"]