mirror of
https://github.com/mudler/LocalAI.git
synced 2026-10-28 17:18:49 -04:00
mudler-agentandEttore Di Giacinto
ae8092e1c6
* feat(sound): expand simple prompts with chat models Allow callers to select an installed chat model for sound prompt expansion. Validate its JSON before audio generation and preserve explicit instrumental and language controls. Keep backend defaults when expansion is omitted, including native Python ACE-Step sampling. Assisted-by: Codex:gpt-6 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(sound): map expansion by loaded audio family Map neutral expanded fields where the resolved audio family is known. Keep unmarked requests unchanged and reject unsupported expansion before inference. Clear YuE2 and HeartMuLa transcripts to prevent lyric fallback. Assisted-by: Codex:gpt-6.1-sol Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(sound): choose a prompt expansion model Require an explicit Simple choice and remember it separately from chat. Clear unavailable choices instead of silently switching language models. Preserve the choice in history and restore it when editing a past result. Keep Backend default and Advanced requests compatible with existing APIs. Document family support and align the published optional request schema. Verify selection, request fields, persistence and history in the browser. Assisted-by: Codex:gpt-6.1-sol Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(sound): authorize both generation models Check the resolved audio model and explicit expansion model before loading either. Permission lookup failures stop generation. Assisted-by: Codex:gpt-6 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(sound): enforce JSON during prompt expansion Constrain expansion output with the existing JSON grammar before decoding. Require a llama-cpp chat model so unsupported backends cannot ignore it. Keep strict field validation and fail before generating audio. Assisted-by: Codex:gpt-6 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
52 lines
2.3 KiB
Python
52 lines
2.3 KiB
Python
# SPDX-License-Identifier: MIT
|
|
"""Test the Sound request adapter without importing model dependencies."""
|
|
import ast
|
|
from pathlib import Path
|
|
from types import SimpleNamespace
|
|
import unittest
|
|
|
|
|
|
class SoundExpansionTests(unittest.TestCase):
|
|
def setUp(self):
|
|
source = ast.parse(Path(__file__).with_name("backend.py").read_text())
|
|
service = next(node for node in source.body
|
|
if isinstance(node, ast.ClassDef) and node.name == "BackendServicer")
|
|
method = next(node for node in service.body
|
|
if isinstance(node, ast.FunctionDef) and node.name == "SoundGeneration")
|
|
self.calls = []
|
|
namespace = {
|
|
"backend_pb2": SimpleNamespace(Result=lambda **fields: SimpleNamespace(**fields)),
|
|
"_generate_audio_sync": lambda owner, payload, dst: self.calls.append(payload),
|
|
}
|
|
exec(compile(ast.Module(body=[method], type_ignores=[]), "backend.py", "exec"), namespace)
|
|
self.generate = namespace["SoundGeneration"]
|
|
|
|
def request(self, **fields):
|
|
values = dict(dst="output.wav", text="original description", expanded=False,
|
|
language="it", instrumental=True, caption="piano", lyrics="",
|
|
think=False, src="", bpm=120, keyscale="", timesignature="", duration=0)
|
|
values.update(fields)
|
|
values["HasField"] = lambda name: name in {"instrumental", "bpm"}
|
|
return SimpleNamespace(**values)
|
|
|
|
def test_omission_preserves_native_sample_query(self):
|
|
self.generate(None, self.request(), None)
|
|
self.assertEqual(self.calls[0]["sample_query"], "original description")
|
|
self.assertTrue(self.calls[0]["sample_mode"])
|
|
|
|
def test_expanded_uses_structured_caption_and_empty_lyrics(self):
|
|
self.generate(None, self.request(expanded=True, text=""), None)
|
|
self.assertEqual(self.calls[0]["prompt"], "piano")
|
|
self.assertEqual(self.calls[0]["lyrics"], "")
|
|
self.assertEqual(self.calls[0]["bpm"], 120)
|
|
self.assertNotIn("sample_query", self.calls[0])
|
|
|
|
def test_marker_prevents_native_expansion_even_with_stale_text(self):
|
|
self.generate(None, self.request(expanded=True), None)
|
|
self.assertEqual(self.calls[0]["prompt"], "piano")
|
|
self.assertNotIn("sample_query", self.calls[0])
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|