pod_trend_agent/graph/nodes/pinterest_search_node.py

"""Pinterest 参考模式节点 1/3：按需生成单个搜索词（pinterest_search）。

按需搜索：每次只生成 1 个搜索词（LLM json_schema + 动态注入已用词防重复），
带短袖/印花设计引导，保证搜索词适合短袖 T 恤印花。
不在此处持久化已用词 —— 只有爬取成功（真正用掉）才标记已用（见 pinterest_scrape）。

兜底链：LLM json_schema → json_object → 解析失败/调用失败 → 回退种子词池随机抽样。
带 with_fallback：任何异常都不中断，返回空列表由下游跳过。
"""
import random
from typing import Any, Dict, List

from graph.llms import get_backend
from graph.pinterest import (
    filter_search_terms,
    load_used_terms,
    merge_used,
    sample_seeds,
)
from graph.validate import with_fallback


@with_fallback("pinterest_search")
def pinterest_search_node(state: Dict[str, Any]) -> Dict[str, Any]:
    country = state["country"]
    config = state["config"]
    output_dir = state["output_dir"]
    errors = list(state.get("errors") or [])

    pcfg = config.get("pinterest") or {}
    if not pcfg.get("enabled", True):
        return {"pinterest_search_terms": [], "errors": errors}

    provider = str(pcfg.get("provider") or "openai").strip().lower()
    search_mode = str(pcfg.get("search_mode") or "direct").strip().lower()
    _raw_suffix = str(pcfg.get("search_term_suffix") if pcfg.get("search_term_suffix") is not None else " t-shirt design").strip()
    suffix = _raw_suffix if _raw_suffix else ""   # 配置留空则后缀为空（不追加），不再回退默认
    want = int(pcfg.get("search_terms_per_run", 1))   # 每次搜索词数量
    seed_sample = int(pcfg.get("seed_sample", 40))
    max_used_in_prompt = int(pcfg.get("max_used_terms_in_prompt", 100))
    blacklist = config.get("blacklist") or []

    # 1) 种子词池 + 已用搜索词 + 本轮已尝试词（防同轮重复，不持久化）
    seeds = sample_seeds(country, seed_sample)
    used = load_used_terms(output_dir, country)
    attempted = [str(t).strip() for t in (state.get("pinterest_attempted") or []) if str(t).strip()]
    rounds = int(state.get("pinterest_rounds") or 0) + 1
    if not seeds:
        print(f"[pinterest_search] {country} 无种子词，跳过搜索词生成")
        return {"pinterest_search_terms": [], "pinterest_rounds": rounds, "errors": errors}

    # 2) 生成搜索词：种子词不再由 LLM 给出，直接由内置国家种子词库随机抽取（优先未用过），
    #    追加 " t-shirt design"（保证 Pinterest 返回真正的 T 恤印花图）；llm 模式保留兼容
    terms: List[str] = []
    if search_mode == "direct":
        from graph.pinterest import load_pinterest_seeds
        pool = load_pinterest_seeds(country)
        used_set = {str(u).strip().lower() for u in merge_used(used, attempted)}
        fresh = [s for s in pool if s.lower() not in used_set]
        if not fresh:
            fresh = pool   # 库内词全部用过 → 允许复用（词库有限）
        terms = [f"{s} {suffix}".strip() if suffix and suffix not in s.lower() else s
                 for s in random.sample(fresh, min(want, len(fresh)))]
        print(f"[pinterest_search] direct 模式：国家种子词库随机抽 {len(terms)} 个 + 后缀「{suffix}」（{country}）")
    else:
        used_llm = merge_used(used, attempted)
        if max_used_in_prompt > 0:
            used_llm = used_llm[-max_used_in_prompt:]
        llm = None
        if provider != "static":
            try:
                llm = get_backend(provider)
                if hasattr(llm, "bind_config"):
                    llm.bind_config(config.get("llm_screen") or {})
                if provider not in ("mock",) and not getattr(llm, "has_key", False):
                    print(f"[pinterest_search] {provider} 未配置 API key，降级 mock")
                    llm = get_backend("mock")
            except Exception as e:  # noqa: BLE001
                print(f"[pinterest_search] LLM 初始化失败: {e}")
                llm = None

        if llm is not None and hasattr(llm, "generate_pinterest_terms"):
            try:
                ctx = {"country": country, "seeds": seeds, "used_terms": used_llm, "count": want,
                       "search_term_suffix": suffix}
                res = llm.generate_pinterest_terms(ctx)
                terms = [str(t).strip() for t in (res.get("search_terms") or []) if str(t).strip()]
                print(f"[pinterest_search] LLM 生成搜索词 {len(terms)} 个（{country}，已用词注入 {len(used_llm)}）")
            except Exception as e:  # noqa: BLE001
                print(f"[pinterest_search] LLM 生成失败，回退种子词池: {e}")
                terms = []

        # 3) 兜底：LLM 无结果 → 种子词池随机抽样
        if not terms:
            terms = [f"{s} {suffix}".strip() if suffix and suffix not in s.lower() else s
                     for s in random.sample(seeds, min(want, len(seeds)))]
            print(f"[pinterest_search] 兜底：从种子词池取 {len(terms)} 个")

    # 4) 全局过滤（已用/本轮已尝试/黑名单/不适合T恤/去重）——注意：不在此处持久化已用词
    #    direct 模式：抽样时已避开已用词（库内词有限，全部用过后允许复用），不再额外过滤
    if search_mode == "direct":
        filtered = terms
    else:
        filtered = filter_search_terms(terms, merge_used(used, attempted), blacklist)
        if not filtered and seeds:
            # 生成词全被过滤 → 从种子词池补充（同样过滤）
            extra = filter_search_terms(seeds, merge_used(used, attempted), blacklist)
            filtered = extra[:want]

    stats = dict(state.get("stats") or {})
    stats["pinterest_search"] = {
        "provider": provider,
        "round": rounds,
        "generated": len(terms),
        "filtered": len(filtered),
        "used_total": len(used),
    }
    print(f"[pinterest_search] 第 {rounds} 轮搜索词 {len(filtered)} 个（已用累计 {len(used)}）: "
          f"{', '.join(filtered[:3])}{'...' if len(filtered) > 3 else ''}")

    return {"pinterest_search_terms": filtered, "pinterest_rounds": rounds,
            "stats": stats, "errors": errors}