zizi 061010ba1b 框架: 共享运行时装成可安装包,切断 Skill 之间的 sys.path 互指
被多个 Skill 或看板消费的连接、模型、嵌入、Claude 运行时与声音账入口
各只保留一份实现;Skill 只留 CLI/落库,看板只读 muse-db,门禁锁死跨域注入。

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-20 00:45:20 +08:00

105 lines
5.5 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

#!/usr/bin/env python3
"""clean-book-text Skill:LLM 探测执行器——每窗一次受治理调用,产出 deletions JSON。
读 clean_prep 产出的 manifest.json,逐窗经 llm.chat_governed 探测垃圾段(只报逐字原文,不改写),
写 /tmp/muse-clean/<work>/deletions-NNN.json。断点续跑:已有产物的窗自动跳过。
模型降级与额度治理已上收 llm.chat_governed(全局 BUDGET_CHAIN + 5h 额度窗),本脚本不自写降级链。
删除动作不在本脚本:由 clean_apply 守卫裁决执行。
"""
import json
import pathlib
import sys
import time
import click
from muse_llm import chat_governed, extract_json
OUT = pathlib.Path("/tmp/muse-clean")
# 探测 prompt:与 SKILL.md 模板同源;要求纯 JSON 输出便于机器解析
PROMPT = """你是网文正文清洗探测器。下面是《{title}》第 {a}–{b} 章的原文(每章以【第N章 | 章题】标记行开头)。
找出**所有非正文垃圾**:
- 书站广告及变体(如「一秒记住♂粒÷小÷说→网」「天才一秒记住本站地址」)
- 网址/域名残留、"首发""手机版阅读""无弹窗"类导流语
- 求票拉票/求订阅收藏/打赏鸣谢段
- 章尾作者话(ps:… / PS:… / 附:…)、上架感言、请假条类整段
- 乱码水印、明显不属于故事的插入符号串
输出规则(只输出一个 JSON 对象,禁止任何其他文字):
{{"deletions": [{{"chapter_order": 章序号, "exact": "待删段逐字原文", "reason": "简短理由"}}]}}
硬性要求:
- `exact` 必须与原文**逐字一致**(含标点、空格),单项 ≤300 字;同一段垃圾一项,不合并多段;
- 只报确定是垃圾的,拿不准的不报;**情节正文一个字都不许报**;
- 【第N章 | 章题】标记行不报(即使含求票字样);
- 若该窗没有垃圾,输出 {{"deletions": []}}。
原文开始:
{text}"""
@click.command()
@click.option("--work-id", type=int, required=True)
@click.option("--win", "wins", type=int, multiple=True, help="指定窗号(可多次);不给则全部窗")
@click.option("--model", default="MiniMax-M3", show_default=True,
help="首选入口模型(兼容 hint);实际用哪个模型与降级由 llm.chat_governed 全局额度策略决定")
@click.option("--force", is_flag=True, help="已有产物也重跑")
def main(work_id, wins, model, force):
d = OUT / str(work_id)
manifest = json.loads((d / "manifest.json").read_text())
title = manifest["title"]
targets = [m for m in manifest["windows"] if not wins or m["win"] in wins]
total_in = total_out = n_del = n_skip = 0
for m in targets:
f_out = d / f"deletions-{m['win']:03d}.json"
if f_out.exists() and not force:
click.echo(f"win-{m['win']:03d} 已有产物,跳过(--force 重跑)", err=True)
continue
text = pathlib.Path(m["file"]).read_text()
t0 = time.time()
prompt = PROMPT.format(title=title, a=m["from"], b=m["to"], text=text)
# 降级与额度治理已上收 llm.chat_governed(全局 BUDGET_CHAIN + 5h 额度窗):撞内容安全/
# 模型不可用由它沿全局链自动换模型并按窗预算/调用数治理;本脚本不自写降级链。
# 单窗失败不中断整书——全链耗尽或输出无法解析时失败关闭:该窗不清洗、不返回假成功。
content, usage, used_model = chat_governed(prompt, model=model, caller="clean")
if used_model is None:
# 治理链全部耗尽(多为上游敏感词拦截):写空产物占位(含跳过原因),
# apply 端窗产物齐备可继续,审计可追——绝不拿空内容当成功
f_out.write_text(json.dumps(
{"deletions": [], "skipped": "治理链全部耗尽(多为上游敏感词拦截)"},
ensure_ascii=False, indent=1))
n_skip += 1
click.echo(f"win-{m['win']:03d}(第{m['from']}–{m['to']}章)探测跳过(治理链耗尽),该窗不清洗")
continue
try:
data = extract_json(content)
except ValueError as e:
# 成功调用但输出无法解析为 JSON:失败关闭,该窗不清洗、不返回假成功
f_out.write_text(json.dumps(
{"deletions": [], "skipped": f"LLM 输出无法解析为 JSON({type(e).__name__})"},
ensure_ascii=False, indent=1))
n_skip += 1
click.echo(f"win-{m['win']:03d}(第{m['from']}–{m['to']}章)输出解析失败,该窗不清洗")
continue
dels = data.get("deletions", data if isinstance(data, list) else [])
total_in += usage.get("prompt_tokens", 0)
total_out += usage.get("completion_tokens", 0)
f_out.write_text(json.dumps({"deletions": dels, "model": used_model},
ensure_ascii=False, indent=1))
n_del += len(dels)
tag = "" if used_model == model else f"(治理降级至 {used_model})"
click.echo(f"win-{m['win']:03d}(第{m['from']}–{m['to']}章)检出 {len(dels)} 段{tag} "
f"→ {f_out.name}({time.time() - t0:.0f}s)")
click.echo(f"探测完成:{len(targets)} 窗共检出 {n_del} 段(跳过 {n_skip} 窗);"
f"token in={total_in:,} out={total_out:,}")
if __name__ == "__main__":
try:
main()
except RuntimeError as e:
click.echo(f"[llm错误] {e}", err=True)
sys.exit(1)