mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-06-09 17:12:01 +00:00
* 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>
196 lines
7.4 KiB
Python
196 lines
7.4 KiB
Python
import base64
|
|
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
|
|
|
|
img = load("image-generation")
|
|
|
|
|
|
@pytest.fixture(autouse=True)
|
|
def clean_env(monkeypatch):
|
|
for k in ["GEMINI_API_KEY", "MINIMAX_API_KEY", "IMAGE_GENERATION_PROVIDER",
|
|
"MINIMAX_API_HOST", "MINIMAX_IMAGE_MODEL"]:
|
|
monkeypatch.delenv(k, raising=False)
|
|
|
|
|
|
def test_resolve_prefers_gemini(monkeypatch):
|
|
monkeypatch.setenv("GEMINI_API_KEY", "g")
|
|
monkeypatch.setenv("MINIMAX_API_KEY", "m")
|
|
assert img._resolve_provider("IMAGE_GENERATION_PROVIDER", "gemini", True) == "gemini"
|
|
|
|
|
|
def test_resolve_falls_back_to_minimax(monkeypatch):
|
|
monkeypatch.setenv("MINIMAX_API_KEY", "m")
|
|
assert img._resolve_provider("IMAGE_GENERATION_PROVIDER", "gemini", False) == "minimax"
|
|
|
|
|
|
def test_resolve_override_wins(monkeypatch):
|
|
monkeypatch.setenv("GEMINI_API_KEY", "g")
|
|
monkeypatch.setenv("IMAGE_GENERATION_PROVIDER", "MiniMax")
|
|
assert img._resolve_provider("IMAGE_GENERATION_PROVIDER", "gemini", True) == "minimax"
|
|
|
|
|
|
def test_resolve_errors_when_none(monkeypatch):
|
|
with pytest.raises(ValueError):
|
|
img._resolve_provider("IMAGE_GENERATION_PROVIDER", "gemini", False)
|
|
|
|
|
|
def test_minimax_builds_payload_and_writes(monkeypatch, tmp_path):
|
|
monkeypatch.setenv("MINIMAX_API_KEY", "m")
|
|
raw = b"PNGBYTES"
|
|
captured = {}
|
|
|
|
def fake_post(url, headers=None, json=None, **kw):
|
|
captured["url"] = url
|
|
captured["headers"] = headers
|
|
captured["json"] = json
|
|
return FakeResp({"data": {"image_base64": [base64.b64encode(raw).decode()]},
|
|
"base_resp": {"status_code": 0, "status_msg": "success"}})
|
|
|
|
monkeypatch.setattr(img.requests, "post", fake_post)
|
|
out = tmp_path / "o.jpg"
|
|
prompt_file = tmp_path / "p.json"
|
|
prompt_file.write_text("a red apple", encoding="utf-8")
|
|
msg = img.generate_image(str(prompt_file), [], str(out), "16:9")
|
|
|
|
assert out.read_bytes() == raw
|
|
assert captured["url"].endswith("/v1/image_generation")
|
|
assert captured["headers"]["Authorization"] == "Bearer m"
|
|
assert captured["json"]["model"] == "image-01"
|
|
assert captured["json"]["response_format"] == "base64"
|
|
assert captured["json"]["aspect_ratio"] == "16:9"
|
|
assert captured["json"]["n"] == 1
|
|
assert captured["json"]["prompt_optimizer"] is True
|
|
assert "Successfully generated image" in msg
|
|
|
|
|
|
def test_minimax_reference_image_as_data_url(monkeypatch, tmp_path):
|
|
monkeypatch.setenv("MINIMAX_API_KEY", "m")
|
|
captured = {}
|
|
|
|
def fake_post(url, headers=None, json=None, **kw):
|
|
captured["json"] = json
|
|
return FakeResp({"data": {"image_base64": [base64.b64encode(b"x").decode()]},
|
|
"base_resp": {"status_code": 0}})
|
|
|
|
monkeypatch.setattr(img.requests, "post", fake_post)
|
|
ref = tmp_path / "ref.jpg"
|
|
ref.write_bytes(b"\xff\xd8refbytes")
|
|
prompt_file = tmp_path / "p.json"
|
|
prompt_file.write_text("scene", encoding="utf-8")
|
|
img.generate_image(str(prompt_file), [str(ref)], str(tmp_path / "o.jpg"), "1:1")
|
|
|
|
subj = captured["json"]["subject_reference"]
|
|
assert subj[0]["type"] == "character"
|
|
assert subj[0]["image_file"].startswith("data:image/jpeg;base64,")
|
|
import base64 as _b64
|
|
encoded = subj[0]["image_file"].split(",", 1)[1]
|
|
assert _b64.b64decode(encoded) == b"\xff\xd8refbytes"
|
|
|
|
|
|
def test_minimax_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": 1004, "status_msg": "auth failed"}})
|
|
|
|
monkeypatch.setattr(img.requests, "post", fake_post)
|
|
prompt_file = tmp_path / "p.json"
|
|
prompt_file.write_text("x", encoding="utf-8")
|
|
with pytest.raises(Exception) as e:
|
|
img.generate_image(str(prompt_file), [], str(tmp_path / "o.jpg"), "1:1")
|
|
assert "1004" in str(e.value)
|
|
|
|
|
|
def test_minimax_extracts_json_prompt_field(monkeypatch, tmp_path):
|
|
monkeypatch.setenv("MINIMAX_API_KEY", "m")
|
|
captured = {}
|
|
|
|
def fake_post(url, headers=None, json=None, **kw):
|
|
captured["json"] = json
|
|
return FakeResp({"data": {"image_base64": [base64.b64encode(b"x").decode()]},
|
|
"base_resp": {"status_code": 0}})
|
|
|
|
monkeypatch.setattr(img.requests, "post", fake_post)
|
|
prompt_file = tmp_path / "p.json"
|
|
prompt_file.write_text(
|
|
'{"prompt": "a red barn at dawn", "style": "watercolor", '
|
|
'"composition": "rule of thirds", "negative_prompt": "blurry"}',
|
|
encoding="utf-8",
|
|
)
|
|
img.generate_image(str(prompt_file), [], str(tmp_path / "o.jpg"), "16:9")
|
|
|
|
# Only the JSON `prompt` field reaches MiniMax — no other fields, no JSON syntax.
|
|
assert captured["json"]["prompt"] == "a red barn at dawn"
|
|
assert captured["json"]["prompt_optimizer"] is True
|
|
|
|
|
|
def test_minimax_plaintext_prompt_passes_through(monkeypatch, tmp_path):
|
|
monkeypatch.setenv("MINIMAX_API_KEY", "m")
|
|
captured = {}
|
|
|
|
def fake_post(url, headers=None, json=None, **kw):
|
|
captured["json"] = json
|
|
return FakeResp({"data": {"image_base64": [base64.b64encode(b"x").decode()]},
|
|
"base_resp": {"status_code": 0}})
|
|
|
|
monkeypatch.setattr(img.requests, "post", fake_post)
|
|
prompt_file = tmp_path / "p.txt"
|
|
prompt_file.write_text("a red apple on a table", encoding="utf-8")
|
|
img.generate_image(str(prompt_file), [], str(tmp_path / "o.jpg"), "1:1")
|
|
|
|
assert captured["json"]["prompt"] == "a red apple on a table"
|
|
|
|
|
|
def test_minimax_rejects_overlong_prompt_without_calling_api(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 the prompt is over the limit")
|
|
|
|
monkeypatch.setattr(img.requests, "post", fake_post)
|
|
prompt_file = tmp_path / "p.json"
|
|
prompt_file.write_text('{"prompt": "' + "x" * 1600 + '"}', encoding="utf-8")
|
|
out = tmp_path / "o.jpg"
|
|
msg = img.generate_image(str(prompt_file), [], str(out), "16:9")
|
|
|
|
assert "1500" in msg
|
|
assert "character" in msg.lower()
|
|
assert not out.exists()
|
|
|
|
|
|
def test_minimax_creates_nested_output_dir(monkeypatch, tmp_path):
|
|
monkeypatch.setenv("MINIMAX_API_KEY", "m")
|
|
|
|
def fake_post(url, headers=None, json=None, **kw):
|
|
return FakeResp({"data": {"image_base64": [base64.b64encode(b"img").decode()]},
|
|
"base_resp": {"status_code": 0}})
|
|
|
|
monkeypatch.setattr(img.requests, "post", fake_post)
|
|
prompt_file = tmp_path / "p.txt"
|
|
prompt_file.write_text("a cat", encoding="utf-8")
|
|
out = tmp_path / "nested" / "dir" / "o.jpg"
|
|
img.generate_image(str(prompt_file), [], str(out), "1:1")
|
|
|
|
assert out.read_bytes() == b"img"
|
|
|
|
|
|
def test_unknown_provider_raises(monkeypatch, tmp_path):
|
|
monkeypatch.setenv("IMAGE_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):
|
|
img.generate_image(str(pf), [], str(tmp_path / "o.jpg"), "1:1")
|
|
|
|
|
|
def test_guess_mime_by_extension():
|
|
assert img._guess_mime("/a/b.png") == "image/png"
|
|
assert img._guess_mime("/a/b.webp") == "image/webp"
|
|
assert img._guess_mime("/a/b.jpg") == "image/jpeg"
|
|
assert img._guess_mime("/a/b.unknown") == "image/jpeg"
|