v1.1.1: 升级 AI 续聘建议为 LLM + Playwright RPA 采集 SmartCampus 平台材料

新增：

- scripts/service/platform_collector.py：Playwright RPA（持久化 browser profile 复用登录态），抓合同表（姓名/单位/到期日/剩余天数/预警/建议），逐行点"续聘材料包"按钮下载 PDF/Word 到 data/materials/

- scripts/service/material_parser.py：PDF/Word 文本提取（pypdf → pdf2image + pytesseract OCR 扫描件兜底；python-docx 抽 docx；antiword 兜底 .doc）

- scripts/service/llm_decision.py：AI 决策统一入口（优先调宿主 jiangchang_skill_core.llm_manager.call_llm_json；本地降级到规则版；输出 decision_source ∈ {llm, rules, rules_no_materials}）

- scripts/db/migrations.py：idempotent ALTER/CREATE，建 materials_content 表 + renewal_tasks 加 decision_source / materials_summary 列

修改：

- scripts/db/connection.py：init_db() 自动调 apply_all() 应用 v1.1.1 迁移

- scripts/db/repository.py：加 insert_material / list_materials_for_contract / list_pending_materials / summarize_materials / get_task_full

- scripts/service/task_generator.py：AI 决策统一改为调 llm_decision.decide_suggestion(materials_summary=...)；reason 文案加「已结合材料包（X 份文件，Y 字 / 待解析）综合判断：...」

- scripts/service/html_renderer.py：ctx 加 DECISION_SOURCE（LLM 推理 / 本地规则 / 本地规则（无材料））+ MATERIALS_COUNT

- scripts/templates/task.html.j2：footer 加 "AI 建议来源：{{DECISION_SOURCE}} · 已审阅材料 {{MATERIALS_COUNT}} 份"

- scripts/cli/app.py：新增 2 个 CLI（collect-from-platform / parse-materials）；现有 9 个不动

- requirements.txt：playwright / pypdf / python-docx / pdf2image / pytesseract / Pillow

- .env.example：SMARTCAMPUS_BASE_URL / SMARTCAMPUS_PROFILE_DIR / MATERIALS_DOWNLOAD_DIR / OCR_LANG / LLM_MODEL_NAME / LLM_API_BASE_URL / LLM_API_TOKEN

- SKILL.md：version 1.1.0 → 1.1.1；用户意图路由表加 2 行；新增「数据来源」段（三层来源 + AI 决策透明化）

- README.md：使用前要准备 → 加 playwright install chromium 步骤

- CHANGELOG.md：v1.1.1 条目

- scripts/util/constants.py：SKILL_VERSION 1.1.0 → 1.1.1

本地验证：11 个 CLI 全部 exit 0；decision_source=rules；reason 含「已结合材料包（6 份文件，待解析）」；HTML footer 含决策来源。

Co-Authored-By: Claude Code <noreply@anthropic.com>

scripts/service/material_parser.py

@@ -0,0 +1,143 @@
+"""材料包 PDF / Word 文档文本提取。
+
+策略（自动降级）：
+- .pdf : pypdf 直接抽 → 若 < 200 字视为扫描件，pdf2image + pytesseract OCR 兜底
+- .docx: python-docx 抽取段落
+- .doc : 调 antiword 兜底（不在 win32 默认安装，仅 best-effort）
+- 其他 : 返回 ("", "failed")
+
+依赖均为可选：导入失败返回空串，让上层降级到规则版。
+"""
+
+from __future__ import annotations
+
+from pathlib import Path
+
+from util.logging_setup import get_skill_logger
+
+logger = get_skill_logger()
+
+# 单个材料文件 OCR 后保留的最大长度，避免 LLM context 爆栈
+MAX_TEXT_PER_FILE = 8000
+# LLM Prompt 里允许的总材料摘要上限
+MAX_TOTAL_SUMMARY = 16000
+
+
+def _pdf_pypdf(path: Path) -> str:
+    try:
+        from pypdf import PdfReader
+    except ImportError:
+        return ""
+    try:
+        reader = PdfReader(str(path))
+        out = []
+        for page in reader.pages:
+            t = page.extract_text() or ""
+            if t:
+                out.append(t)
+        return "\n".join(out)
+    except Exception as e:
+        logger.warning("pypdf 解析失败 %s: %s", path.name, e)
+        return ""
+
+
+def _pdf_ocr(path: Path) -> str:
+    try:
+        from pdf2image import convert_from_path
+        import pytesseract
+    except ImportError:
+        logger.warning("OCR 依赖未安装（pdf2image / pytesseract）")
+        return ""
+    try:
+        images = convert_from_path(str(path), dpi=200)
+        return "\n".join(
+            pytesseract.image_to_string(img, lang="chi_sim+eng") for img in images
+        )
+    except Exception as e:
+        logger.warning("OCR 解析失败 %s: %s", path.name, e)
+        return ""
+
+
+def _docx_text(path: Path) -> str:
+    try:
+        from docx import Document
+    except ImportError:
+        return ""
+    try:
+        doc = Document(str(path))
+        return "\n".join(p.text for p in doc.paragraphs if p.text)
+    except Exception as e:
+        logger.warning("docx 解析失败 %s: %s", path.name, e)
+        return ""
+
+
+def _doc_antiword(path: Path) -> str:
+    """legacy .doc：调系统 antiword 命令行。"""
+    import shutil, subprocess
+
+    if not shutil.which("antiword"):
+        return ""
+    try:
+        r = subprocess.run(
+            ["antiword", str(path)], capture_output=True, text=True, timeout=30
+        )
+        return r.stdout if r.returncode == 0 else ""
+    except Exception as e:
+        logger.warning("antiword 解析失败 %s: %s", path.name, e)
+        return ""
+
+
+def extract_text(path: Path) -> tuple[str, str]:
+    """返回 (text, method)。method ∈ {'pypdf','docx','ocr','antiword','empty'}。
+
+    text 为空时 method='empty'，调用方应据此判断是否降级到规则版。
+    """
+    if not path.exists():
+        logger.warning("材料文件不存在: %s", path)
+        return ("", "empty")
+
+    suffix = path.suffix.lower()
+    text = ""
+    method = "empty"
+
+    if suffix == ".pdf":
+        text = _pdf_pypdf(path)
+        method = "pypdf" if text else "empty"
+        if len(text.strip()) < 200:
+            ocr_text = _pdf_ocr(path)
+            if ocr_text:
+                text = ocr_text
+                method = "ocr"
+    elif suffix == ".docx":
+        text = _docx_text(path)
+        method = "docx" if text else "empty"
+    elif suffix == ".doc":
+        text = _doc_antiword(path)
+        method = "antiword" if text else "empty"
+
+    if text:
+        text = text[:MAX_TEXT_PER_FILE]
+
+    return (text, method)
+
+
+def summarize(texts: list[tuple[str, str, str]]) -> tuple[str, list[str]]:
+    """把多份材料的 (file_name, text, method) 汇总为 LLM 摘要。
+
+    返回 (summary, methods)。summary 截断到 MAX_TOTAL_SUMMARY 字以内。
+    """
+    if not texts:
+        return ("", [])
+
+    parts: list[str] = []
+    methods: list[str] = []
+    for file_name, text, method in texts:
+        if not text:
+            continue
+        methods.append(f"{file_name} ({method})")
+        parts.append(f"### {file_name}\n{text}")
+
+    joined = "\n\n".join(parts)
+    if len(joined) > MAX_TOTAL_SUMMARY:
+        joined = joined[:MAX_TOTAL_SUMMARY] + "\n...(以下材料内容过长已截断)"
+    return (joined, methods)