Add align/recheck/compare, plugins, and refresh Agent docs.
selftest / selftest (push) Canceled after 0s

Wire deliver_report/listen_pack/retry hooks; gen --auto-retry and intro light check; make AGENTS_MIN the up-to-date agent entry with full command map.

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
swl
2026-10-10 13:03:44 +08:00
co-authored by Cursor
parent b1afe68f3c
commit 6d79ab93a2
20 changed files with 780 additions and 91 deletions
+57 -4
View File
@@ -340,6 +340,9 @@ def cmd_gen(args):
dry_run=True)
run.save_json("manifest.json", man_dry)
catmod.append_entry(cfg, catmod.entry_from_gen(run.dir, man_dry))
from ..plugins.hooks import bus
bus.emit("after_gen", run_dir=run.dir, manifest=man_dry,
cfg=cfg, args=args)
log.info("dry-run 结束", seeds=seeds)
log.close()
return 0
@@ -351,8 +354,21 @@ def cmd_gen(args):
if not ok:
raise ServerError("ComfyUI 不可达: %s" % info)
from ..plugins.hooks import bus
from .extras import run_intro_check
from ..plugins.retry_on_intro_fail.plugin import should_retry_intro_blob
cro = pmod.comfy_root(cfg=cfg)
music = pmod.music_dir(cfg, cro)
auto_retry = int(getattr(args, "auto_retry", 0) or 0)
do_recheck = not bool(getattr(args, "skip_recheck", False))
jobs = list(built)
results = []
for sd, wf, wf_path, sub in built:
retries_left = auto_retry
ji = 0
while ji < len(jobs):
sd, wf, wf_path, sub = jobs[ji]
ji += 1
pid = eng.submit_retry(wfmod.render(wf))
log.info("已提交", seed=sd, prompt_id=pid)
@@ -364,7 +380,40 @@ def cmd_gen(args):
results.append(dict(seed=sd, prompt_id=pid, files=outs,
workflow=os.path.basename(wf_path)))
cro = pmod.comfy_root(cfg=cfg)
if not do_recheck or not outs:
continue
audio = None
for fn in outs:
p = fn if os.path.isabs(fn) else os.path.join(
music, os.path.basename(fn))
if os.path.isfile(p):
audio = p
break
if not audio:
continue
_code, blob = run_intro_check(
cfg, audio, bpm=st["bpm"], intro_bars=ibars, lang=lang)
run.save_json("intro_check.json", blob or {})
log.info("开曲轻检", ok=(blob or {}).get("ok"))
if should_retry_intro_blob(blob) and retries_left > 0:
retries_left -= 1
sd2 = seed_base + len(jobs)
sub2 = "%s/%s-s%d-%s-%s" % (
prefix, safe_title, len(jobs) + 1, style_tag, date_stamp)
wf2 = wfmod.build_workflow(
template, title=title, tags=tags, lyrics=lyrics, seed=sd2,
bpm=st["bpm"], duration=st["duration"], keyscale=st["key"],
sampler=cfg["sampler"], encode=cfg["encode"],
model=cfg["model"], output_prefix=sub2, output_format=fmt,
language=lang,
timesignature=cfg["song"]["time_signature"])
wf_path2 = run.path("wf_%s_s%d.json" % (safe_title, len(jobs) + 1))
with open(wf_path2, "w", encoding="utf-8") as f:
json.dump(wf2, f, ensure_ascii=False, indent=1)
jobs.append((sd2, wf2, wf_path2, sub2))
log.warn("开曲轻检 FAIL,追加 seed 重试", seed=sd2,
left=retries_left)
manifest = dict(
run_id=run.run_id, title=title, style=args.style,
bpm=st["bpm"], key=st["key"], duration=st["duration"],
@@ -375,16 +424,18 @@ def cmd_gen(args):
intro_bars=ibars,
sampler=cfg["sampler"], encode=cfg["encode"], model=cfg["model"],
density=stats, results=results,
output_dir=pmod.music_dir(cfg, cro),
output_dir=music,
created=datetime.datetime.now().isoformat(timespec="seconds"),
)
mpath = run.save_json("manifest.json", manifest)
catmod.append_entry(cfg, catmod.entry_from_gen(run.dir, manifest))
bus.emit("after_gen", run_dir=run.dir, manifest=manifest, cfg=cfg, args=args)
log.info("全部完成", run=run.run_id, manifest=os.path.basename(mpath))
print("\n生成完成 run_id=%s" % run.run_id)
print(" 时长 %ds BPM %d %s 种子 %s"
% (st["duration"], st["bpm"], st["key"], seeds))
% (st["duration"], st["bpm"], st["key"],
[r["seed"] for r in results]))
if inst:
print(" [纯器乐] 无可唱歌词,密度闸门不适用")
else:
@@ -395,6 +446,8 @@ def cmd_gen(args):
print(" seed=%s -> %s" % (r["seed"], ", ".join(r["files"] or ["无输出"])))
print(" 产物目录: %s" % run.dir)
print(" 音频输出: %s" % manifest["output_dir"])
if os.path.isfile(run.path("report.md")):
print(" 报告: %s" % run.path("report.md"))
log.close()
return 0
+196
View File
@@ -0,0 +1,196 @@
# -*- coding: utf-8 -*-
"""扩展命令:compare / align / recheck。"""
import json
import os
import subprocess
from ..config import loader
from ..core import catalog as catmod
from ..core import paths as pmod
from ..lyrics import align as alignmod
from ..lyrics import meter
from .common import build_cfg, resolve_profile, runs_root, style_of
from .qc import find_qc_python
def _load_run(cfg, run_id):
rundir = catmod.find_run_dir(runs_root(cfg), run_id)
if not rundir:
return None, None, None
man = {}
mp = os.path.join(rundir, "manifest.json")
if os.path.isfile(mp):
with open(mp, encoding="utf-8") as f:
man = json.load(f)
qc = {}
qp = os.path.join(rundir, "qc.json")
if os.path.isfile(qp):
with open(qp, encoding="utf-8") as f:
qc = json.load(f)
return rundir, man, qc
def _qc_rows(qc):
if not qc:
return []
return qc.get("rows") or qc.get("results") or []
def _first_audio(cfg, man, rundir):
music = man.get("output_dir") or pmod.music_dir(cfg, pmod.comfy_root(cfg=cfg))
for r in man.get("results") or []:
for fn in r.get("files") or []:
p = fn if os.path.isabs(fn) else os.path.join(music, os.path.basename(fn))
if os.path.isfile(p):
return p
# 也搜 rundir
p2 = os.path.join(rundir, os.path.basename(fn))
if os.path.isfile(p2):
return p2
return None
def cmd_compare(args):
cfg = loader.load({})
ids = []
for part in (args.runs or []):
ids.extend([x.strip() for x in part.split(",") if x.strip()])
if len(ids) < 2:
print("[错误] 至少两个 run:songforge compare --runs a,b")
return 2
print("%-26s %-8s %-5s %-5s %-6s %-8s %-7s %-8s %s"
% ("run_id", "style", "BPM", "dur", "QC", "onset", "衬词比",
"voice_nn", "title"))
for rid in ids:
rundir, man, qc = _load_run(cfg, rid)
if not rundir:
print("%-26s (找不到)" % rid)
continue
rows = [r for r in _qc_rows(qc) if r.get("group") != "baseline"]
r0 = rows[0] if rows else {}
verd = None
for v in (qc.get("verdicts") or []):
verd = v.get("verdict")
break
if not verd:
verd = man.get("qc_verdict") or "-"
print("%-26s %-8s %-5s %-5s %-6s %-8s %-7s %-8s %s"
% ((man.get("run_id") or rid)[:26],
(man.get("style") or "-")[:8],
man.get("bpm") or "-",
man.get("duration") or "-",
(verd or "-")[:6],
r0.get("vocal_onset") if r0.get("vocal_onset") is not None else "-",
("%.0f%%" % (float(r0.get("intro_filler_ratio") or 0) * 100))
if r0 else "-",
(str(r0.get("voice_nn") or "-"))[:8],
(man.get("title") or "-")[:16]))
return 0
def cmd_align(args):
cfg = build_cfg(args)
st = style_of(cfg, args.style, args)
if args.lyrics_file:
with open(args.lyrics_file, encoding="utf-8") as f:
raw = f.read()
elif args.lyrics:
raw = args.lyrics
else:
print("[错误] 需要 --lyrics-file 或 --lyrics")
return 2
prof = resolve_profile(args)
cfg_ly = meter.pick(cfg["lyrics"], prof)
out, diag = alignmod.align_lyrics(
raw, st["duration"], st["bpm"], cfg_ly, target=args.target)
dest = args.out or (args.lyrics_file and (
os.path.splitext(args.lyrics_file)[0] + "_aligned.txt"))
if not dest:
dest = os.path.join(pmod.tmp_today(cfg), "aligned.txt")
pmod.ensure_dir(os.path.dirname(dest))
with open(dest, "w", encoding="utf-8") as f:
f.write(out)
print("== align ==")
print(" 音节 %d -> %d 目标 %d 窗口 %d~%d ok=%s"
% (diag["before"], diag["after"], diag["want"],
diag["win_lo"], diag["win_hi"], diag.get("ok")))
print(" 写出: %s" % dest)
if not diag.get("ok"):
print(" [WARN] %s" % diag.get("note"))
return 1
return 0
def run_intro_check(cfg, audio_path, bpm=104, intro_bars=8, lang="zh"):
"""子进程开曲轻检。返回 (code, blob)。"""
py = find_qc_python(cfg)
if not py:
return 2, dict(error="no qc_python")
worker = os.path.join(pmod.PKG_ROOT, "tools", "intro_check_worker.py")
job = dict(file=os.path.abspath(audio_path), bpm=bpm,
intro_bars=intro_bars, lang=lang)
env = dict(os.environ)
env["PYTHONIOENCODING"] = "utf-8"
env["SONGFORGE_COMFY_ROOT"] = pmod.comfy_root(cfg=cfg)
try:
r = subprocess.run(
[py, worker, json.dumps(job, ensure_ascii=False)],
capture_output=True, env=env, timeout=600)
except subprocess.TimeoutExpired:
return 2, dict(error="timeout")
out = r.stdout.decode("utf-8", "replace")
if "###JSON###" not in out:
return 2, dict(error="no json", log=out[-800:])
blob = json.loads(out.split("###JSON###", 1)[1].strip())
return (0 if not blob.get("error") else 1), blob
def cmd_recheck(args):
cfg = loader.load({})
rundir, man, _qc = _load_run(cfg, args.run)
if not rundir:
print("[错误] 找不到 run: %s" % args.run)
return 2
audio = args.file or _first_audio(cfg, man, rundir)
if not audio or not os.path.isfile(audio):
print("[错误] 找不到音频。可传 --file")
return 2
bpm = args.bpm or man.get("bpm") or 104
bars = args.intro_bars or man.get("intro_bars") or 8
lang = args.lang or man.get("language") or "zh"
code, blob = run_intro_check(cfg, audio, bpm=bpm, intro_bars=bars, lang=lang)
outp = os.path.join(rundir, "intro_check.json")
with open(outp, "w", encoding="utf-8") as f:
json.dump(blob, f, ensure_ascii=False, indent=1)
print(json.dumps(blob, ensure_ascii=False, indent=1))
print("报告: %s" % outp)
if blob.get("error"):
return 2
return 0 if blob.get("ok") else 1
def add_extras(sub):
c = sub.add_parser("compare", help="对比多次 run 的 QC/开曲指标")
c.add_argument("--runs", action="append", required=True,
help="run_id 列表,逗号分隔,可多次")
c.set_defaults(func=cmd_compare)
a = sub.add_parser("align", help="歌词音节一键对齐到 target 放行窗")
a.add_argument("--style", required=True)
a.add_argument("--lyrics-file", dest="lyrics_file")
a.add_argument("--lyrics")
a.add_argument("--out", help="输出路径(默认 *_aligned.txt)")
a.add_argument("--bpm", type=int)
a.add_argument("--dur", type=int)
a.add_argument("--target", type=int, help="目标音节(默认取建议值)")
a.add_argument("--chill-vocal", dest="chill_vocal", action="store_true")
a.add_argument("--density-profile", dest="density_profile")
a.set_defaults(func=cmd_align)
r = sub.add_parser("recheck", help="开曲轻检(前奏窗 ASR 衬词)")
r.add_argument("--run", required=True)
r.add_argument("--file", help="直接指定音频")
r.add_argument("--bpm", type=int)
r.add_argument("--intro-bars", dest="intro_bars", type=int)
r.add_argument("--lang", default=None)
r.set_defaults(func=cmd_recheck)
+8 -1
View File
@@ -3,7 +3,7 @@
命令:
doctor / styles / target / check / gen / runs / show / catalog /
prune / media / qc / selftest
prune / media / qc / compare / align / recheck / selftest
设计约束:所有业务参数来自配置/命令行,本文件不写死任何模型或采样常量。
实现见 common / assemble / commands / selftest / qc。
@@ -120,6 +120,10 @@ def build_parser():
help="注入完整 RULE_NEG(默认关闭;易诱发开曲衬词)")
g.add_argument("--dry-run", dest="dry_run", action="store_true",
help="只写 workflow 与 API 预览,不提交 ComfyUI")
g.add_argument("--auto-retry", dest="auto_retry", type=int, default=0,
help="开曲轻检 FAIL 时额外换 seed 重提次数(默认 0)")
g.add_argument("--skip-recheck", dest="skip_recheck", action="store_true",
help="生成后不做开曲轻检(默认会做并写 intro_check.json)")
g.set_defaults(func=cmds.cmd_gen)
r = sub.add_parser("runs", help="列出历史运行")
@@ -153,6 +157,9 @@ def build_parser():
from .qc import add_qc
add_qc(sub)
from .extras import add_extras
add_extras(sub)
return p
+13
View File
@@ -404,6 +404,19 @@ def _render(rep, args, rundir=None, cfg=None):
except Exception as e:
print("[WARN] catalog 更新失败: %s" % e)
if rundir and cfg:
try:
from ..plugins.hooks import bus
bus.emit("after_qc", run_dir=rundir, report=rep, verd=verd,
rows=rows, cfg=cfg, args=args)
except Exception as e:
print("[WARN] after_qc 插件: %s" % e)
if os.path.isfile(os.path.join(rundir, "report.md")):
print("交付报告: %s" % os.path.join(rundir, "report.md"))
listen = os.path.join(rundir, "listen")
if os.path.isdir(listen):
print("听感包: %s" % listen)
if not verd:
print("本次只有基线校准,没有待验收新歌 -> 退出码 0")
return 0
+21 -3
View File
@@ -778,6 +778,8 @@ def _t_plugins_and_lean_default():
"""微内核钩子已加载;默认 prefer_lean_tags;assemble 不注入 RULE_NEG 堆。"""
from ..plugins.hooks import bus
assert bus._handlers.get("after_assemble"), "intro_guard 未挂 after_assemble"
assert bus._handlers.get("after_gen"), "deliver_report 未挂 after_gen"
assert bus._handlers.get("after_qc"), "qc 插件未挂 after_qc"
cfg = loader.load({})
assert cfg["rules"].get("prefer_lean_tags") is True
@@ -791,7 +793,6 @@ def _t_plugins_and_lean_default():
st = {"bpm": 104, "duration": 180, "key": "F major",
"style": "Chinese pop", "instruments": "kick snare bass",
"mood": "bright", "extra": ""}
# 密度够过闸的短样
raw = ("[verse]\n" + "\n".join(
["街口的灯还亮着我往前走一步"] * 20))
tags, _ly = assemble(_A(), cfg, st, raw, "selftest")
@@ -799,8 +800,25 @@ def _t_plugins_and_lean_default():
"默认 lean 仍注入了 RULE_NEG opening 堆"
assert "no wordless vocals" in tags.lower()
assert "mm mm" not in tags.lower()
return [("微内核与 lean 默认",
"plugins.after_assemble 已挂;默认 tags 为 lean 且无音节点名")]
# align:过少歌词应能拉进窗口
from ..lyrics import align as alignmod
from ..lyrics import meter as mmod
thin = "[verse]\n太短了\n再一句\n"
out, diag = alignmod.align_lyrics(thin, 180, 104, cfg["lyrics"])
assert diag.get("ok"), "align 未能把过少歌词对齐: %s" % diag
assert diag["after"] >= diag["win_lo"]
# deliver_report 钩子可写报告
import tempfile
td = tempfile.mkdtemp(prefix="sf-rep-")
man = dict(run_id="t", title="测", style="pop", bpm=104, duration=180,
results=[dict(seed=1, files=["x.flac"])])
bus.emit("after_gen", run_dir=td, manifest=man, cfg=cfg, args=None)
assert os.path.isfile(os.path.join(td, "report.md")), "未写出 report.md"
return [("微内核/lean/align/报告",
"钩子齐;lean 默认;align 进窗;report.md 可写")]
def cmd_selftest(args):