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>
56 lines
2.0 KiB
Python
56 lines
2.0 KiB
Python
"""增量迁移:在 init_db 之外支持 idempotent ALTER/CREATE。
|
||
|
||
v1.1.1 新增:
|
||
- materials_content 表(材料包 PDF/Word 解析缓存)
|
||
- renewal_tasks.decision_source 列(AI 建议来源透明化)
|
||
- renewal_tasks.materials_summary 列(材料摘要缓存,便于离线渲染)
|
||
"""
|
||
|
||
from __future__ import annotations
|
||
|
||
import sqlite3
|
||
|
||
|
||
def _column_exists(conn: sqlite3.Connection, table: str, column: str) -> bool:
|
||
rows = conn.execute(f"PRAGMA table_info({table})").fetchall()
|
||
return any(r["name"] == column for r in rows)
|
||
|
||
|
||
def ensure_materials_content_schema(conn: sqlite3.Connection) -> None:
|
||
"""创建 materials_content 表(如不存在)。幂等。"""
|
||
conn.execute(
|
||
"""
|
||
CREATE TABLE IF NOT EXISTS materials_content (
|
||
contract_id TEXT NOT NULL,
|
||
file_name TEXT NOT NULL,
|
||
file_path TEXT NOT NULL,
|
||
extracted_text TEXT,
|
||
parse_method TEXT,
|
||
parsed_at TEXT NOT NULL,
|
||
PRIMARY KEY (contract_id, file_name),
|
||
FOREIGN KEY (contract_id) REFERENCES contracts(contract_id)
|
||
);
|
||
"""
|
||
)
|
||
conn.execute(
|
||
"CREATE INDEX IF NOT EXISTS idx_materials_contract "
|
||
"ON materials_content(contract_id);"
|
||
)
|
||
|
||
|
||
def ensure_renewal_tasks_columns(conn: sqlite3.Connection) -> None:
|
||
"""为 renewal_tasks 加 decision_source / materials_summary 列(如不存在)。"""
|
||
if not _column_exists(conn, "renewal_tasks", "decision_source"):
|
||
conn.execute(
|
||
"ALTER TABLE renewal_tasks ADD COLUMN decision_source TEXT DEFAULT 'rules';"
|
||
)
|
||
if not _column_exists(conn, "renewal_tasks", "materials_summary"):
|
||
conn.execute(
|
||
"ALTER TABLE renewal_tasks ADD COLUMN materials_summary TEXT DEFAULT '';"
|
||
)
|
||
|
||
|
||
def apply_all(conn: sqlite3.Connection) -> None:
|
||
"""应用全部 v1.1.1 迁移。"""
|
||
ensure_materials_content_schema(conn)
|
||
ensure_renewal_tasks_columns(conn) |