135 lines
3.9 KiB
Python
135 lines
3.9 KiB
Python
"""Agent 工作流：趋势分析 → 叙事化企微早报。"""
|
||
|
||
from __future__ import annotations
|
||
|
||
import json
|
||
import logging
|
||
import re
|
||
from pathlib import Path
|
||
from typing import Any
|
||
|
||
from daily.config import OUTPUT_DIR, ROOT, env
|
||
from daily.llm_client import extract_json_object, has_llm_configured, llm_chat
|
||
from daily.report_data import save_json
|
||
|
||
logger = logging.getLogger(__name__)
|
||
|
||
_SKILL_DIR = ROOT / "skills" / "daily-agent"
|
||
_MD_BLOCK = re.compile(r"```(?:markdown|md)?\s*([\s\S]*?)```", re.IGNORECASE)
|
||
_WECOM_NEW_ENTRY_NOTE = re.compile(r"（新入[^）]*）")
|
||
|
||
|
||
def _strip_new_entry_notes(md: str) -> str:
|
||
md = _WECOM_NEW_ENTRY_NOTE.sub("", md)
|
||
return re.sub(r"\*\*—", "** —", md)
|
||
|
||
|
||
def report_mode() -> str:
|
||
return (env("DAILY_REPORT_MODE") or "classic").strip().lower()
|
||
|
||
|
||
def is_agent_mode() -> bool:
|
||
if report_mode() != "agent":
|
||
return False
|
||
if not has_llm_configured():
|
||
logger.warning("DAILY_REPORT_MODE=agent 但未配置 LLM，回退 classic")
|
||
return False
|
||
return True
|
||
|
||
|
||
def trends_json_path(date_str: str) -> Path:
|
||
return OUTPUT_DIR / f"{date_str}.trends.json"
|
||
|
||
|
||
def _load_skill() -> str:
|
||
path = _SKILL_DIR / "SKILL.md"
|
||
if path.exists():
|
||
return path.read_text(encoding="utf-8").strip()
|
||
return "你是早报主编 Agent。"
|
||
|
||
|
||
def _extract_markdown(text: str) -> str:
|
||
text = text.strip()
|
||
match = _MD_BLOCK.search(text)
|
||
if match:
|
||
return match.group(1).strip()
|
||
if text.startswith("📰"):
|
||
return text
|
||
return text
|
||
|
||
|
||
def analyze_trends(llm_input: dict[str, Any], *, date_str: str) -> dict[str, Any] | None:
|
||
skill = _load_skill()
|
||
system = (
|
||
f"{skill}\n\n"
|
||
"当前执行 **Step 1：趋势分析**。\n"
|
||
"只输出 trends JSON（headline, opening, themes, top_picks, signals），不要 Markdown。"
|
||
)
|
||
user = json.dumps(llm_input, ensure_ascii=False, indent=2)
|
||
try:
|
||
raw = llm_chat(system, user)
|
||
except Exception as exc:
|
||
logger.warning("Agent Step1 趋势分析失败：%s", exc)
|
||
return None
|
||
if not raw:
|
||
return None
|
||
parsed = extract_json_object(raw)
|
||
if not parsed.get("headline") and not parsed.get("opening"):
|
||
logger.warning("Agent Step1 JSON 无效")
|
||
return None
|
||
save_json(trends_json_path(date_str), parsed)
|
||
logger.info("Agent Step1 完成：%s", parsed.get("headline", "?"))
|
||
return parsed
|
||
|
||
|
||
def write_wecom_report(
|
||
llm_input: dict[str, Any],
|
||
trends: dict[str, Any],
|
||
*,
|
||
date_str: str,
|
||
time_str: str,
|
||
updated: str,
|
||
) -> str | None:
|
||
skill = _load_skill()
|
||
system = (
|
||
f"{skill}\n\n"
|
||
"当前执行 **Step 2：撰写企微早报**。\n"
|
||
f"日期={date_str}，时间={time_str}，数据截至={updated}。\n"
|
||
"只输出企微 Markdown 正文，不要代码块，不要 JSON。"
|
||
)
|
||
payload = {"data": llm_input, "trends": trends}
|
||
user = json.dumps(payload, ensure_ascii=False, indent=2)
|
||
try:
|
||
raw = llm_chat(system, user)
|
||
except Exception as exc:
|
||
logger.warning("Agent Step2 写稿失败：%s", exc)
|
||
return None
|
||
if not raw:
|
||
return None
|
||
md = _extract_markdown(raw)
|
||
if not md.startswith("📰"):
|
||
md = f"📰 **早报 · {date_str}**\n> ⏱ {time_str} · 数据截至 {updated}\n\n{md}"
|
||
md = _strip_new_entry_notes(md)
|
||
logger.info("Agent Step2 完成：%d bytes", len(md.encode("utf-8")))
|
||
return md
|
||
|
||
|
||
def run_agent_workflow(
|
||
llm_input: dict[str, Any],
|
||
*,
|
||
date_str: str,
|
||
time_str: str,
|
||
updated: str,
|
||
) -> str | None:
|
||
"""两步 Agent 工作流；成功返回企微 Markdown，失败返回 None。"""
|
||
trends = analyze_trends(llm_input, date_str=date_str)
|
||
if not trends:
|
||
return None
|
||
return write_wecom_report(
|
||
llm_input,
|
||
trends,
|
||
date_str=date_str,
|
||
time_str=time_str,
|
||
updated=updated,
|
||
)
|