daily-robots/daily/narrative_axis.py

"""叙事轴硬互斥：代码选定轴，注入 Agent Step1 并强制覆写。"""

from __future__ import annotations

import json
import logging
import random
from collections import defaultdict
from datetime import datetime, timedelta
from typing import Any

from daily.config import OUTPUT_DIR, narrative_axis_days

logger = logging.getLogger(__name__)

NARRATIVE_AXES: tuple[str, ...] = (
    "政策监管",
    "模型发布",
    "工具链/Agent",
    "芯片算力",
    "开源生态",
    "应用落地",
    "安全/诉讼",
)


def pick_narrative_axis(
    used: set[str],
    *,
    rng: random.Random | None = None,
) -> str:
    """从固定轴枚举中排除已用轴后随机选取；全用尽则回退全表。"""
    available = [a for a in NARRATIVE_AXES if a not in used]
    pool = available or list(NARRATIVE_AXES)
    picker = rng or random.Random()
    return picker.choice(pool)


def load_recent_axes(date_str: str, days: int | None = None) -> list[str]:
    """近 N 日 data.narrative_axis（不含当日，按时间从近到远）。"""
    lookback = days if days is not None else narrative_axis_days()
    try:
        dt = datetime.strptime(date_str, "%Y-%m-%d")
    except ValueError:
        return []
    axes: list[str] = []
    for day_offset in range(1, lookback + 1):
        prev = (dt - timedelta(days=day_offset)).strftime("%Y-%m-%d")
        path = OUTPUT_DIR / f"{prev}.data.json"
        if not path.exists():
            continue
        try:
            payload = json.loads(path.read_text(encoding="utf-8"))
        except (OSError, ValueError) as exc:
            logger.warning("读取 narrative_axis %s 失败：%s", path, exc)
            continue
        data = payload.get("data") if isinstance(payload, dict) else None
        if not isinstance(data, dict):
            continue
        axis = str(data.get("narrative_axis") or "").strip()
        if axis:
            axes.append(axis)
    return axes


def load_recent_theme_summaries(date_str: str, days: int) -> list[str]:
    """近 N 日 theme/opening 摘要，供 Step1 软禁参考。"""
    try:
        dt = datetime.strptime(date_str, "%Y-%m-%d")
    except ValueError:
        return []
    summaries: list[str] = []
    for day_offset in range(1, days + 1):
        prev = (dt - timedelta(days=day_offset)).strftime("%Y-%m-%d")
        path = OUTPUT_DIR / f"{prev}.data.json"
        if not path.exists():
            continue
        try:
            payload = json.loads(path.read_text(encoding="utf-8"))
        except (OSError, ValueError):
            continue
        data = payload.get("data") if isinstance(payload, dict) else None
        if not isinstance(data, dict):
            continue
        theme = str(data.get("theme") or data.get("editorial_theme") or "").strip()
        opening = ""
        trends = data.get("trends") if isinstance(data.get("trends"), dict) else {}
        if isinstance(trends, dict):
            opening = str(trends.get("opening") or "").strip()
            if not theme:
                themes = trends.get("themes") or []
                if themes and isinstance(themes[0], dict):
                    theme = str(themes[0].get("title") or "").strip()
        bit = " · ".join(x for x in (prev, theme, opening[:40]) if x)
        if bit:
            summaries.append(bit)
    return summaries


def enforce_narrative_axis(trends: dict[str, Any], axis: str) -> dict[str, Any]:
    """强制 trends['narrative_axis'] = axis。"""
    out = dict(trends)
    out["narrative_axis"] = axis
    return out


def theme_clusters(
    feed: dict[str, Any],
    *,
    limit: int = 5,
    theme_rules: list[tuple[str, str, list[str]]],
    skill_id_fn: Any,
) -> list[tuple[str, list[str]]]:
    """按 THEME_RULES 把 feed 的 topTrending/topHot 聚成 (主题, 示例列表)。

    从 generate.py 迁入（原私有 _theme_clusters）。theme_rules 与 skill_id_fn
    由调用方注入，避免对 generate.py 的反向依赖（防循环 import）。
    """
    buckets: dict[str, list[str]] = defaultdict(list)
    seen: set[str] = set()
    for board in ("topTrending", "topHot"):
        for item in feed.get(board, [])[:20]:
            item_id = skill_id_fn(item)
            if item_id in seen:
                continue
            seen.add(item_id)
            haystack = " ".join(
                [item.get("title", ""), item.get("source", ""), item.get("description", "")]
            ).lower()
            for _icon, theme, keywords in theme_rules:
                if any(k in haystack for k in keywords):
                    label = f"**{item.get('title')}** (`{item.get('source')}`)"
                    if label not in buckets[theme]:
                        buckets[theme].append(label)
                    break
    return [(theme, examples[:limit]) for theme, examples in buckets.items() if examples]


def theme_names(
    feed: dict[str, Any],
    *,
    theme_rules: list[tuple[str, str, list[str]]],
    skill_id_fn: Any,
    limit: int = 3,
) -> list[str]:
    """仅取主题名（不含 markdown 示例），供「今日看点/theme_line」回退文案。"""
    return [theme for theme, _ in theme_clusters(
        feed, theme_rules=theme_rules, skill_id_fn=skill_id_fn
    )][:limit]