457 lines
26 KiB
Python
457 lines
26 KiB
Python
import argparse
|
||
import base64
|
||
import csv
|
||
import io
|
||
import json
|
||
import os
|
||
import secrets
|
||
import sqlite3
|
||
import tempfile
|
||
import threading
|
||
import urllib.error
|
||
import urllib.parse
|
||
import urllib.request
|
||
import webbrowser
|
||
from datetime import datetime, timezone
|
||
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
|
||
from pathlib import Path
|
||
|
||
from . import store
|
||
from .analysis import (SYSTEM_PROMPT, STRATEGIES, SIGNALS, Redactor, extract_events,
|
||
local_cards, make_card, prepare_plan, validate_model_cards)
|
||
from .importer import import_rows, read_rows, offset_zone
|
||
|
||
STATIC = Path(__file__).parent / 'static'
|
||
MAX_UPLOAD = 64 * 1024 * 1024
|
||
|
||
|
||
def now():
|
||
return datetime.now(timezone.utc).isoformat()
|
||
|
||
|
||
def validate_api(config):
|
||
endpoint = str(config.get('endpoint', '')).strip()
|
||
parsed = urllib.parse.urlsplit(endpoint)
|
||
if parsed.username or parsed.password or parsed.query or parsed.fragment:
|
||
raise ValueError('API 地址不能包含账号、密码、查询参数或片段')
|
||
if parsed.scheme != 'https' and not (parsed.scheme == 'http' and parsed.hostname in ('127.0.0.1', 'localhost', '::1')):
|
||
raise ValueError('远程模型 API 必须使用 HTTPS，本地模型可使用 localhost HTTP')
|
||
if not parsed.hostname or not parsed.path.endswith('/chat/completions'):
|
||
raise ValueError('请填写完整的兼容接口地址，以 /chat/completions 结尾')
|
||
model = str(config.get('model', '')).strip()
|
||
if not model or len(model) > 200:
|
||
raise ValueError('请填写模型名称')
|
||
return {'endpoint': endpoint, 'model': model}
|
||
|
||
|
||
class NoRedirect(urllib.request.HTTPRedirectHandler):
|
||
def redirect_request(self, *args, **kwargs):
|
||
raise ValueError('API 重定向已拒绝，避免脱敏文本和密钥被转发到其他地址')
|
||
|
||
|
||
def call_model(config, key, body):
|
||
if key and (not key.isascii() or any(ord(char) < 33 or ord(char) > 126 for char in key)):
|
||
raise ValueError('API 密钥含无效字符，请重新填写（不包含空格或换行）')
|
||
headers = {'Content-Type': 'application/json', 'Accept': 'application/json'}
|
||
if key:
|
||
headers['Authorization'] = 'Bearer ' + key
|
||
req = urllib.request.Request(config['endpoint'], data=json.dumps(body, ensure_ascii=False).encode(), headers=headers)
|
||
try:
|
||
# Do not implicitly route chat text through system HTTP proxies.
|
||
opener = urllib.request.build_opener(urllib.request.ProxyHandler({}), NoRedirect())
|
||
with opener.open(req, timeout=120) as response:
|
||
data = response.read(8 * 1024 * 1024 + 1)
|
||
if len(data) > 8 * 1024 * 1024:
|
||
raise ValueError('模型响应过大')
|
||
result = json.loads(data)
|
||
if not isinstance(result, dict):
|
||
raise ValueError('模型接口返回格式错误')
|
||
choices = result.get('choices')
|
||
if not isinstance(choices, list) or not choices:
|
||
raise ValueError('模型接口未返回 choices')
|
||
text = choices[0].get('message', {}).get('content')
|
||
if not isinstance(text, str):
|
||
raise ValueError('模型没有返回文本结果')
|
||
text = text.strip()
|
||
if text.startswith('```'):
|
||
text = text.split('\n', 1)[1].rsplit('```', 1)[0].strip()
|
||
return json.loads(text)
|
||
except urllib.error.HTTPError as exc:
|
||
# Never persist provider response bodies: they can echo the prompt/key.
|
||
raise ValueError(f'模型 API 返回 HTTP {exc.code}，请检查地址、密钥、模型和额度') from None
|
||
except (urllib.error.URLError, TimeoutError, OSError):
|
||
raise ValueError('模型 API 连接失败或超时，请检查网络与接口地址') from None
|
||
except (json.JSONDecodeError, IndexError, KeyError, AttributeError):
|
||
raise ValueError('模型响应不是可用的 JSON，未保存不完整分析') from None
|
||
|
||
|
||
def sqlite_rows(data, table=None, schema_only=False):
|
||
if not data.startswith(b'SQLite format 3\x00'):
|
||
raise ValueError('这不是明文 SQLite 数据库。微信加密数据库需先在 Mac 上取得可读导出；本工具不冒充已完成解密。')
|
||
with tempfile.TemporaryDirectory(prefix='wechat-import-') as directory:
|
||
path = Path(directory) / 'input.sqlite3'
|
||
path.write_bytes(data)
|
||
db = sqlite3.connect(path.as_uri() + '?mode=ro&immutable=1', uri=True)
|
||
db.row_factory = sqlite3.Row
|
||
try:
|
||
db.execute('PRAGMA query_only=ON')
|
||
tables = [r[0] for r in db.execute("SELECT name FROM sqlite_master WHERE type='table' AND name NOT LIKE 'sqlite_%'")]
|
||
def quoted(name):
|
||
return '"' + name.replace('"', '""') + '"'
|
||
if schema_only:
|
||
return [{'table': name, 'columns': [r[1] for r in db.execute('PRAGMA table_info(' + quoted(name) + ')')]} for name in tables]
|
||
if table not in tables:
|
||
raise ValueError('请选择数据库中存在的消息表')
|
||
rows = db.execute('SELECT * FROM ' + quoted(table) + ' LIMIT 500001').fetchall()
|
||
if len(rows) > 500000:
|
||
raise ValueError('单次最多导入 50 万条，请拆分文件')
|
||
return [dict(r) for r in rows]
|
||
finally:
|
||
db.close()
|
||
|
||
|
||
class Workbench(ThreadingHTTPServer):
|
||
daemon_threads = True
|
||
|
||
def __init__(self, address, data):
|
||
super().__init__(address, Handler)
|
||
self.data = Path(data).resolve()
|
||
self.token = secrets.token_urlsafe(32)
|
||
self.lock = threading.RLock()
|
||
self.plans = {}
|
||
self.api_key = os.environ.get('WECHAT_MODEL_API_KEY', '')
|
||
db = store.connect(self.data)
|
||
if not store.setting(db, 'salt'):
|
||
store.set_setting(db, 'salt', secrets.token_hex(32))
|
||
# Interrupted API jobs cannot be silently resumed or automatically re-sent.
|
||
db.execute("UPDATE runs SET status='failed',error='服务重启中断了任务；不会自动重新发送，请重新预览后执行' WHERE status='running'")
|
||
db.commit()
|
||
db.close()
|
||
|
||
def db(self):
|
||
return store.connect(self.data)
|
||
|
||
|
||
class Handler(BaseHTTPRequestHandler):
|
||
server_version = 'WeChatWorkbench/0.1'
|
||
|
||
def log_message(self, *args):
|
||
pass # Neither chat payloads nor credentials belong in request logs.
|
||
|
||
def respond(self, value, status=200, mime='application/json; charset=utf-8', filename=None):
|
||
data = json.dumps(value, ensure_ascii=False).encode() if mime.startswith('application/json') else value.encode() if isinstance(value, str) else value
|
||
self.send_response(status)
|
||
self.send_header('Content-Type', mime)
|
||
self.send_header('Content-Length', str(len(data)))
|
||
self.send_header('Cache-Control', 'no-store')
|
||
self.send_header('X-Content-Type-Options', 'nosniff')
|
||
self.send_header('Referrer-Policy', 'no-referrer')
|
||
self.send_header('Content-Security-Policy', "default-src 'self'; script-src 'self'; style-src 'self'; connect-src 'self'; img-src 'self' data:; frame-ancestors 'none'; base-uri 'none'; form-action 'self'")
|
||
if filename:
|
||
self.send_header('Content-Disposition', 'attachment; filename="' + filename + '"')
|
||
self.end_headers()
|
||
self.wfile.write(data)
|
||
|
||
def check_request(self, mutation=False):
|
||
expected = f'127.0.0.1:{self.server.server_port}'
|
||
if self.headers.get('Host') != expected:
|
||
raise PermissionError('只允许通过本机 127.0.0.1 访问')
|
||
origin = self.headers.get('Origin')
|
||
if origin and origin != 'http://' + expected:
|
||
raise PermissionError('拒绝跨站请求')
|
||
if self.headers.get('Sec-Fetch-Site') in ('cross-site', 'same-site'):
|
||
raise PermissionError('拒绝跨站请求')
|
||
if mutation and not secrets.compare_digest(self.headers.get('X-Workbench-Token', ''), self.server.token):
|
||
raise PermissionError('页面会话失效，请刷新')
|
||
|
||
def do_GET(self):
|
||
self.dispatch(False)
|
||
|
||
def do_POST(self):
|
||
self.dispatch(True)
|
||
|
||
def dispatch(self, post):
|
||
db = None
|
||
try:
|
||
self.check_request(post)
|
||
parts = urllib.parse.urlsplit(self.path)
|
||
path = parts.path
|
||
if not post and path in ('/', '/app.js', '/style.css'):
|
||
file = STATIC / ('index.html' if path == '/' else path[1:])
|
||
text = file.read_text(encoding='utf-8').replace('__SESSION_TOKEN__', self.server.token)
|
||
return self.respond(text, mime={'/': 'text/html; charset=utf-8', '/app.js': 'text/javascript; charset=utf-8', '/style.css': 'text/css; charset=utf-8'}[path])
|
||
body = {}
|
||
if post:
|
||
length = int(self.headers.get('Content-Length', '0'))
|
||
if not 0 < length <= MAX_UPLOAD:
|
||
raise ValueError('请求为空或超过 64 MB（文件 base64 后约增大三分之一）')
|
||
if 'application/json' not in self.headers.get('Content-Type', ''):
|
||
raise ValueError('请求必须是 JSON')
|
||
body = json.loads(self.rfile.read(length))
|
||
if not isinstance(body, dict):
|
||
raise ValueError('请求必须是对象')
|
||
query = urllib.parse.parse_qs(parts.query)
|
||
db = self.server.db()
|
||
if not post:
|
||
return self.get_route(db, path, query)
|
||
return self.post_route(db, path, body)
|
||
except PermissionError as exc:
|
||
self.respond({'error': str(exc)}, 403)
|
||
except (ValueError, TypeError, sqlite3.Error, KeyError, OverflowError) as exc:
|
||
# Type/key/sql errors do not contain user payloads in supported routes.
|
||
error = str(exc) if isinstance(exc, ValueError) else '请求格式或数据库结构不符合要求，请检查字段和输入'
|
||
self.respond({'error': error}, 400)
|
||
except (BrokenPipeError, ConnectionResetError):
|
||
pass
|
||
except Exception:
|
||
self.respond({'error': '内部错误，数据未发送到新的地址。请重启后重试或运行测试诊断。'}, 500)
|
||
finally:
|
||
if db:
|
||
db.close()
|
||
|
||
def get_route(self, db, path, query):
|
||
if path == '/api/overview':
|
||
result = store.overview(db)
|
||
result['runs'] = [dict(r) for r in db.execute('SELECT id,created,mode,status,error,coverage FROM runs ORDER BY created DESC')]
|
||
for r in result['runs']:
|
||
r['coverage'] = json.loads(r['coverage'])
|
||
return self.respond(result)
|
||
if path == '/api/settings':
|
||
return self.respond({'api': store.setting(db, 'api', {}), 'custom': store.setting(db, 'custom', []),
|
||
'utc_offset': store.setting(db, 'utc_offset', '+08:00'), 'has_key': bool(self.server.api_key)})
|
||
if path == '/api/run':
|
||
run = self.get_run(db, query.get('id', [''])[0])
|
||
return self.respond(run)
|
||
if path == '/api/evidence':
|
||
ids = [int(i) for i in query.get('ids', [''])[0].split(',') if i]
|
||
if len(ids) > 1000:
|
||
raise ValueError('一次最多读取 1000 条证据')
|
||
rows = [dict(r) for r in db.execute('SELECT * FROM messages WHERE id IN (' + ','.join('?' for _ in ids) + ') ORDER BY timestamp,id', ids)] if ids else []
|
||
return self.respond(rows)
|
||
if path == '/api/context':
|
||
run = self.get_run(db, query.get('run_id', [''])[0])
|
||
card = next((c for c in run['cards'] if c['id'] == query.get('card_id', [''])[0]), None)
|
||
if not card:
|
||
raise ValueError('卡片不存在')
|
||
events = self.run_events(db, run['id'])
|
||
return self.respond([e for e in events if e['id'] in card['event_ids']])
|
||
if path == '/api/export':
|
||
run = self.get_run(db, query.get('id', [''])[0])
|
||
fmt = query.get('format', ['md'])[0]
|
||
if fmt == 'csv':
|
||
out = io.StringIO(newline='')
|
||
writer = csv.writer(out)
|
||
writer.writerow(['主题', '摘要', '事件数', '优先级(启发式)', '信号', '状态', '策略', '审核', '证据ID', '会话', '答复候选', '适用边界', '备注', '经验提供者候选'])
|
||
for c in run['cards']:
|
||
vals = [c['title'], c['summary'], c['event_count'], c['priority'], '、'.join(SIGNALS[s] for s in c['signals']), c['status'], c['strategy'], '已审核' if c['reviewed'] else '待审核', ','.join(map(str, c['evidence_ids'])), '、'.join(c['conversations']), c['answer'], c['boundaries'], c.get('notes', ''), '、'.join(c['responders'])]
|
||
# Neutralize spreadsheet formula injection from messages/model output.
|
||
writer.writerow(["'" + str(v) if str(v).lstrip().startswith(('=', '+', '-', '@', '\t', '\r')) else v for v in vals])
|
||
return self.respond('\ufeff' + out.getvalue(), mime='text/csv; charset=utf-8', filename='knowledge-needs.csv')
|
||
lines = ['# 微信知识需求清单', '', '生成时间：' + run['created'], '', '覆盖范围：' + json.dumps(run['coverage'], ensure_ascii=False), '', '模型结果和本地规则均为候选判断；人工审核不等于实践验证。', '']
|
||
for c in run['cards']:
|
||
lines.extend(['## ' + c['title'].replace('\n', ' '), '', c['summary'], '', f"- 独立事件候选数：{c['event_count']}；优先级（启发式）：{c['priority']}", '- 信号：' + '、'.join(SIGNALS[s] for s in c['signals']), '- 状态：' + c['status'], '- 处理策略：' + c['strategy'], '- 人工审核：' + ('已审核' if c['reviewed'] else '待审核'), '- 证据消息 ID：' + ', '.join(map(str, c['evidence_ids'])), '', '### 经验候选', '', c['answer'], '', '### 边界与缺口', '', c['boundaries'], '', c.get('notes', ''), ''])
|
||
lines.extend(['经验提供者候选（需核实）：' + '、'.join(c['responders']), ''])
|
||
return self.respond('\n'.join(lines), mime='text/markdown; charset=utf-8', filename='knowledge-needs.md')
|
||
return self.respond({'error': '不存在的接口'}, 404)
|
||
|
||
def get_run(self, db, run_id):
|
||
row = db.execute('SELECT * FROM runs WHERE id=?', (run_id,)).fetchone()
|
||
if not row:
|
||
raise ValueError('分析任务不存在')
|
||
result = dict(row)
|
||
result.pop('events', None)
|
||
for field in ('cards', 'filters', 'coverage'):
|
||
result[field] = json.loads(result[field])
|
||
return result
|
||
|
||
def run_events(self, db, run_id):
|
||
row = db.execute('SELECT events FROM runs WHERE id=?', (run_id,)).fetchone()
|
||
if not row:
|
||
raise ValueError('分析任务不存在')
|
||
return json.loads(row[0])
|
||
|
||
def selected(self, db, filters):
|
||
rows = store.messages(db, filters)
|
||
if not rows:
|
||
raise ValueError('筛选范围内没有记录')
|
||
if len(rows) > 200000:
|
||
raise ValueError('一次最多分析 20 万条，请缩小时间范围')
|
||
events = extract_events(rows)
|
||
coverage = {'messages': len(rows), 'events': len(events), 'conversations': len({m['conversation_id'] for m in rows}),
|
||
'first': rows[0]['timestamp'], 'last': rows[-1]['timestamp'], 'media': sum(m['message_type'] != 'text' for m in rows),
|
||
'source': '仅本机已导入记录；时间窗口为讨论候选，不代表完整问答或因果关系'}
|
||
return rows, events, coverage
|
||
|
||
def save_run(self, db, mode, filters, coverage, cards, events, status='complete'):
|
||
rid = secrets.token_hex(12)
|
||
db.execute('INSERT INTO runs (id,created,mode,filters,cards,coverage,status,error,events) VALUES (?,?,?,?,?,?,?,?,?)', (rid, now(), mode, json.dumps(filters, ensure_ascii=False), json.dumps(cards, ensure_ascii=False), json.dumps(coverage, ensure_ascii=False), status, '', json.dumps(events, ensure_ascii=False)))
|
||
db.commit()
|
||
return rid
|
||
|
||
def post_route(self, db, path, body):
|
||
if path == '/api/import':
|
||
data = base64.b64decode(body['data'], validate=True)
|
||
options = body.get('options') or {}
|
||
offset_zone(options.get('utc_offset', '+08:00'))
|
||
filename = Path(body['filename']).name
|
||
if filename.lower().endswith(('.db', '.sqlite', '.sqlite3')):
|
||
rows = sqlite_rows(data, options.get('table'))
|
||
else:
|
||
rows = read_rows(data, filename)
|
||
if len(rows) > 500000:
|
||
raise ValueError('单次最多导入 50 万条')
|
||
return self.respond(import_rows(db, rows, filename, options))
|
||
if path == '/api/schema':
|
||
return self.respond(sqlite_rows(base64.b64decode(body['data'], validate=True), schema_only=True))
|
||
if path == '/api/demo':
|
||
rows = json.loads((Path(__file__).parent.parent / 'examples' / 'demo.json').read_text(encoding='utf-8'))
|
||
return self.respond(import_rows(db, rows, 'demo.json（虚构样例）', {'utc_offset': '+08:00'}))
|
||
if path == '/api/settings':
|
||
api = validate_api(body['api']) if body.get('api', {}).get('endpoint') else {}
|
||
custom = body.get('custom', [])
|
||
if not isinstance(custom, list) or any(not isinstance(x, str) for x in custom) or len(custom) > 2000:
|
||
raise ValueError('自定义敏感词必须是字符串数组，最多 2000 项')
|
||
offset_zone(body.get('utc_offset', '+08:00'))
|
||
new_key = str(body.get('key', '')).strip()
|
||
if new_key and (not new_key.isascii() or any(ord(c) < 33 or ord(c) > 126 for c in new_key)):
|
||
raise ValueError('API 密钥含无效字符，请重新填写（不包含空格或换行）')
|
||
store.set_setting(db, 'api', api)
|
||
store.set_setting(db, 'custom', custom)
|
||
store.set_setting(db, 'utc_offset', body.get('utc_offset', '+08:00'))
|
||
with self.server.lock:
|
||
if body.get('clear_key'):
|
||
self.server.api_key = ''
|
||
elif body.get('key'):
|
||
self.server.api_key = new_key
|
||
self.server.plans.clear()
|
||
return self.respond({'saved': True})
|
||
if path in ('/api/analyze', '/api/preview'):
|
||
filters = body.get('filters') or {}
|
||
rows, events, coverage = self.selected(db, filters)
|
||
cross = bool(body.get('cross', True))
|
||
filters = dict(filters, cross=cross)
|
||
if path == '/api/analyze':
|
||
rid = self.save_run(db, 'local', filters, coverage, local_cards(events, cross), events)
|
||
return self.respond({'id': rid})
|
||
if not events:
|
||
raise ValueError('当前规则未找到问题或复用线索；可查看原文或调整范围')
|
||
config = validate_api(store.setting(db, 'api', {}))
|
||
# Collect names from all imported conversations, including excluded ones.
|
||
contacts = [dict(r) for r in db.execute('SELECT DISTINCT sender,sender_id,conversation,conversation_id FROM messages')]
|
||
redactor = Redactor(contacts, store.setting(db, 'salt'), store.setting(db, 'custom', []))
|
||
batches = prepare_plan(events, redactor, cross)
|
||
bodies = [{'model': config['model'], 'messages': [{'role': 'system', 'content': SYSTEM_PROMPT}, {'role': 'user', 'content': json.dumps(batch, ensure_ascii=False)}], 'temperature': 0.2} for batch in batches]
|
||
plan_id = secrets.token_hex(16)
|
||
plan = dict(config=config, bodies=bodies, events=events, filters=filters, coverage=coverage, created=datetime.now().timestamp())
|
||
with self.server.lock:
|
||
# Preview plaintext is redacted. Original event snapshot stays in memory.
|
||
if len(self.server.plans) >= 10:
|
||
self.server.plans.clear()
|
||
self.server.plans[plan_id] = plan
|
||
return self.respond({'plan_id': plan_id, 'endpoint': config['endpoint'], 'coverage': coverage, 'batches': len(bodies), 'characters': sum(len(json.dumps(b, ensure_ascii=False)) for b in bodies), 'requests': bodies})
|
||
if path == '/api/send':
|
||
with self.server.lock:
|
||
plan = self.server.plans.pop(body.get('plan_id', ''), None)
|
||
key = self.server.api_key
|
||
if not plan or datetime.now().timestamp() - plan['created'] > 1800:
|
||
raise ValueError('预览已失效或已发送，请重新生成预览')
|
||
coverage = dict(plan['coverage'], batches=len(plan['bodies']), cross_batch_merge=False)
|
||
rid = self.save_run(db, 'api', plan['filters'], coverage, [], plan['events'], 'running')
|
||
threading.Thread(target=self.run_ai, args=(rid, plan, key), daemon=True).start()
|
||
return self.respond({'id': rid})
|
||
if path == '/api/card':
|
||
with self.server.lock:
|
||
run = self.get_run(db, body['run_id'])
|
||
if run['status'] != 'complete':
|
||
raise ValueError('任务尚未完成')
|
||
cards = run['cards']
|
||
action = body.get('action', 'edit')
|
||
indices = [i for i, c in enumerate(cards) if c['id'] in body.get('ids', [])]
|
||
if not indices:
|
||
raise ValueError('请选择卡片')
|
||
if action == 'edit':
|
||
if len(indices) != 1:
|
||
raise ValueError('一次编辑一张卡片')
|
||
card = cards[indices[0]]
|
||
for field in ('title', 'summary', 'answer', 'boundaries', 'notes'):
|
||
if field in body:
|
||
card[field] = str(body[field])[:10000]
|
||
if body.get('strategy') in STRATEGIES:
|
||
card['strategy'] = body['strategy']
|
||
card['reviewed'] = bool(body.get('reviewed'))
|
||
elif action in ('merge', 'split'):
|
||
event_map = {e['id']: e for e in self.run_events(db, run['id'])}
|
||
if action == 'merge':
|
||
if len(indices) < 2:
|
||
raise ValueError('合并至少需要两张卡片')
|
||
events = [event_map[eid] for i in indices for eid in cards[i]['event_ids']]
|
||
if not run['filters'].get('cross', True) and len({e['conversation_id'] for e in events}) > 1:
|
||
raise ValueError('该任务按会话分析，不可跨会话合并')
|
||
new = make_card(events, body.get('title') or cards[indices[0]]['title'])
|
||
new['notes'] = '\n\n'.join(c['title'] + '\n' + c['summary'] + '\n' + c.get('notes', '') for i,c in enumerate(cards) if i in indices)
|
||
additions = [new]
|
||
else:
|
||
if len(indices) != 1:
|
||
raise ValueError('一次拆分一张卡片')
|
||
original = cards[indices[0]]
|
||
ids = original['event_ids']
|
||
chosen = body.get('event_ids', [])
|
||
if not chosen or not set(chosen) < set(ids):
|
||
raise ValueError('请选择要拆出的部分事件，不能选空或全选')
|
||
additions = [make_card([event_map[e] for e in ids if (e in chosen) == included]) for included in (True, False)]
|
||
for new in additions:
|
||
new['notes'] = '拆分前备注：' + original.get('notes', '')
|
||
cards = [c for i,c in enumerate(cards) if i not in indices] + additions
|
||
else:
|
||
raise ValueError('未知编辑操作')
|
||
db.execute('UPDATE runs SET cards=? WHERE id=?', (json.dumps(cards, ensure_ascii=False), run['id']))
|
||
db.commit()
|
||
return self.respond({'saved': True})
|
||
return self.respond({'error': '不存在的接口'}, 404)
|
||
|
||
def run_ai(self, rid, plan, key):
|
||
db = self.server.db()
|
||
try:
|
||
cards = []
|
||
event_map = {e['id']: e for e in plan['events']}
|
||
for body in plan['bodies']:
|
||
batch = json.loads(body['messages'][1]['content'])
|
||
events = [event_map[e['id']] for e in batch['events']]
|
||
result = call_model(plan['config'], key, body)
|
||
cards.extend(validate_model_cards(result, events, plan['filters']['cross']))
|
||
db.execute('UPDATE runs SET cards=?,status=? WHERE id=?', (json.dumps(cards, ensure_ascii=False), 'complete', rid))
|
||
db.commit()
|
||
except Exception as exc:
|
||
reason = str(exc) if isinstance(exc, ValueError) else '分析失败；未保存不完整卡片。请检查接口后重新预览执行。'
|
||
db.execute('UPDATE runs SET status=?,error=? WHERE id=?', ('failed', reason[:500], rid))
|
||
db.commit()
|
||
finally:
|
||
db.close()
|
||
|
||
|
||
def main():
|
||
parser = argparse.ArgumentParser(description='微信知识需求分析工具（仅绑定本机）')
|
||
parser.add_argument('--port', type=int, default=8765)
|
||
parser.add_argument('--data-dir', type=Path, default=store.DEFAULT_DATA)
|
||
parser.add_argument('--no-browser', action='store_true')
|
||
args = parser.parse_args()
|
||
try:
|
||
server = Workbench(('127.0.0.1', args.port), args.data_dir)
|
||
except OSError:
|
||
parser.exit(1, '端口被占用。请关闭旧进程，或使用 --port 8766。\n')
|
||
url = f'http://127.0.0.1:{server.server_port}'
|
||
print(f'WeChat knowledge workbench: {url}', flush=True)
|
||
print(f'Local data: {server.data}', flush=True)
|
||
if not args.no_browser:
|
||
webbrowser.open(url)
|
||
try:
|
||
server.serve_forever()
|
||
except KeyboardInterrupt:
|
||
print('\nStopped.')
|
||
finally:
|
||
server.server_close()
|
||
|
||
|
||
if __name__ == '__main__':
|
||
main()
|