开关默认关(generate/use),设置接口 GET/PUT /users/me/auto-memory-settings,任务级覆盖 POST /tasks/{id}/auto-memory-flags,手动触发 POST /users/me/auto-memory/run,日志 GET /users/me/auto-memory-log。
提取:worker run_loop 轮次边界扫 completed 任务,闲置/时长/长度/外部上下文/配额剩余百分比五道门,脱敏后写 project 级 identity_memories,同一任务去重、同一目标 supersede 合并;只写 project 级,不跨项目泄漏。
注入:worker run_one 首轮把最新各 5 条用户/项目记忆拼进内存 prompt 副本(goal 任务同步改内存 goal),库原 prompt 不动;续跑/断点/协调员不注入,注入失败 fail-open。
v1 诚实边界:extract/consolidation 模型只存设置不调模型;MCP/web 线程内调用暂无 tasks 表标记,外部上下文门只认任务间消息与协调员子任务;无控制台 UI。
257 lines
10 KiB
Python
257 lines
10 KiB
Python
"""SQLite -> Postgres 迁移(控制面状态库)。
|
||
|
||
只做一件事:把一个 SQLite 库文件里的行原样插进 Postgres,
|
||
表名与列名不改。幂等:Postgres 侧用 ``ON CONFLICT DO NOTHING``,
|
||
跑两次不重复插(第二次各表 inserted 为 0)。
|
||
|
||
- schema 来自 cloud.db.POSTGRES_SCHEMA / init_postgres_schema,
|
||
本模块不另发明表结构;迁移前先建表(若目标库已有表,
|
||
CREATE TABLE IF NOT EXISTS 是 no-op)。
|
||
- P2-ops 对齐:MIGRATION_TABLES 必须等于 POSTGRES_SCHEMA 的
|
||
表集合(见 migration_coverage 与 test_p2_migrations.py)。
|
||
以前漏掉的 uploads、task_attachments、task_followups、
|
||
environments 已补进清单;补进时发现 task_followups 在
|
||
SQLite 侧比 PG schema 多一列 sender_task_id(peer_messages
|
||
的运行时 ensure_followups_table 会在 PG 上 ALTER 补列,
|
||
POSTGRES_SCHEMA 里没有它),迁移时按同样方式先补列再插,
|
||
否则整批迁移会在该表上撞未知列失败。
|
||
- kb_fts(SQLite FTS5 虚拟表)不迁移:Postgres 没有 FTS5,
|
||
KBStore 在 PG 上走 LIKE 分支,kb_docs 的 content 已足够。
|
||
- sqlite_sequence(AUTOINCREMENT 内部表)不迁移。
|
||
- UNMIGRATED_TABLES:SQLite 各 store 建出、但 POSTGRES_SCHEMA
|
||
里没有的表(api_keys、评审、自动化、GitHub App、网关 key
|
||
等)。它们不是“被跳过”,而是本模块无法迁移——迁移报告
|
||
(migration_coverage / CLI 输出)逐项列出,调用方不得
|
||
把“迁移成功”读成“全部数据都过去了”。
|
||
- 不打印、不返回任何密码或密钥:函数只返回 {表: inserted},
|
||
CLI 只打印表名与行数。
|
||
- Postgres 连接参数只走 CLOUD_DB_* 环境变量(见 cloud.db),
|
||
本模块不读、不拼连接串、不接受命令行密码参数。
|
||
"""
|
||
|
||
import os
|
||
import re
|
||
import sqlite3
|
||
|
||
from cloud.db import (
|
||
POSTGRES_SCHEMA,
|
||
PostgresDatabase,
|
||
init_postgres_schema,
|
||
)
|
||
|
||
# 迁移顺序:无外键约束,顺序只影响日志可读性;用户表在前,
|
||
# 审计/成本等追加表在后。kb_fts 与 sqlite_sequence 明确排除。
|
||
MIGRATION_TABLES = (
|
||
"users",
|
||
"projects",
|
||
"project_members",
|
||
"tasks",
|
||
"audit_log",
|
||
"summaries",
|
||
"kb_docs",
|
||
"cost_records",
|
||
"oauth_states",
|
||
"slack_users",
|
||
"push_subscriptions",
|
||
# P0 安全批:配额行必须随库迁移,否则迁后用户变回无行
|
||
# (本批后无行按默认额度处理,不再是无限额,但显式
|
||
# 管理员额度仍需原样迁过去,不能丢)。
|
||
"user_quotas",
|
||
# P2-ops 对齐:以下 4 张表在 POSTGRES_SCHEMA 里有、
|
||
# 原清单里没有,补进后清单与 schema 表集合一致。
|
||
# uploads / task_attachments:附件包与任务附件;
|
||
# task_followups:任务间互发消息的后续消息队列;
|
||
# environments:项目环境(分支/executor)。
|
||
# 四张表主键均为 TEXT 或复合主键,没有身份列,
|
||
# 不需要序列拨动(见 SEQUENCE_TABLES)。
|
||
"uploads",
|
||
"task_attachments",
|
||
"task_followups",
|
||
"environments",
|
||
# Cloud identity batch: TEXT primary keys, no sequence to sync.
|
||
"user_profiles",
|
||
"identity_memories",
|
||
# Auto memory batch: same TEXT-primary-key pattern.
|
||
"memory_settings",
|
||
"task_memory_flags",
|
||
"memory_extraction_log",
|
||
)
|
||
|
||
_SKIP_TABLES = frozenset({"kb_fts", "sqlite_sequence"})
|
||
|
||
# 身份列的表:POSTGRES_SCHEMA 里唯一用
|
||
# ``BIGINT GENERATED BY DEFAULT AS IDENTITY`` 的 4 张表。
|
||
# 迁移时显式插 id 不会推序列,迁完必须 setval 到 MAX(id),
|
||
# 否则后续省略 id 的 INSERT 会撞主键。新增身份列表必须
|
||
# 同步改这里,test_p2_migrations.py 会拿 schema 实测对齐。
|
||
SEQUENCE_TABLES = (
|
||
"audit_log",
|
||
"summaries",
|
||
"kb_docs",
|
||
"cost_records",
|
||
)
|
||
|
||
# SQLite 各 store 建出、但 POSTGRES_SCHEMA 里没有的表:
|
||
# 本迁移模块无法把它们迁到 Postgres(目标库无此表),
|
||
# 不是静默跳过——migration_coverage() 与 CLI 逐项报告。
|
||
# 其中 rate_limit_hits / workers 是易失的限流与心跳数据,
|
||
# 丢了只影响限流窗口与 worker 可见性,不影响业务数据;
|
||
# 其余(api_keys、task_reviews、automations、GitHub App、
|
||
# user_gateway_keys 等)丢了就是真丢,迁库前必须另行
|
||
# 处理(重建/重绑/重发 key),不能只跑本迁移就宣称迁完。
|
||
UNMIGRATED_TABLES = (
|
||
"api_keys",
|
||
"task_approvals",
|
||
"task_reviews",
|
||
"automations",
|
||
"automation_runs",
|
||
"github_app_setup_states",
|
||
"github_app_config",
|
||
"github_app_installations",
|
||
"github_fix_review_dedup",
|
||
"external_identities",
|
||
"pr_jobs",
|
||
"task_handoffs",
|
||
"task_worktree_snapshots",
|
||
"task_refs",
|
||
"automation_bindings",
|
||
"rate_limit_hits",
|
||
"user_gateway_keys",
|
||
"webhook_deliveries",
|
||
"workers",
|
||
)
|
||
|
||
|
||
def schema_tables():
|
||
"""POSTGRES_SCHEMA 里的表名集合(只认 CREATE TABLE 语句)。"""
|
||
names = set()
|
||
for statement in POSTGRES_SCHEMA:
|
||
m = re.search(r"CREATE TABLE IF NOT EXISTS (\w+)",
|
||
statement)
|
||
if m:
|
||
names.add(m.group(1))
|
||
return names
|
||
|
||
|
||
def migration_coverage():
|
||
"""迁移覆盖报告:清单、schema、未迁移项三者一次给全。
|
||
|
||
migrated:本次迁移模块会迁的表(= MIGRATION_TABLES);
|
||
schema_tables:POSTGRES_SCHEMA 里的表;
|
||
missing_from_migration:schema 里有、清单里没有的表
|
||
(本批后应为空;非空即对齐回归,调用方应报错
|
||
而不是继续跑迁移);
|
||
unmigrated_no_pg_schema:UNMIGRATED_TABLES(目标库
|
||
无此表,无法迁移,须另行处理);
|
||
skipped_by_design:kb_fts / sqlite_sequence(设计上不迁)。
|
||
不含任何密钥或行内容,只含表名。
|
||
"""
|
||
schema = schema_tables()
|
||
return {
|
||
"migrated": tuple(MIGRATION_TABLES),
|
||
"schema_tables": tuple(sorted(schema)),
|
||
"missing_from_migration": tuple(
|
||
sorted(schema - set(MIGRATION_TABLES))),
|
||
"unmigrated_no_pg_schema": tuple(UNMIGRATED_TABLES),
|
||
"skipped_by_design": tuple(sorted(_SKIP_TABLES)),
|
||
}
|
||
|
||
|
||
def migrate_sqlite_to_postgres(sqlite_path, pg_conn=None, tables=None):
|
||
"""迁移并返回 {表名: 本次插入行数}。
|
||
|
||
pg_conn 为 None 时用 PostgresDatabase().connect() 新建连接
|
||
(驱动缺失时抛 PostgresDriverMissingError,绝不回落);
|
||
传入连接时调用方负责关闭,本函数不关闭它。tables 为 None
|
||
时迁 MIGRATION_TABLES 全量;显式传表名时只迁其中在
|
||
SQLite 里存在的表,不存在的表在结果里记 0(不报错,
|
||
因为老库可能还没建出某张表,例如未用过的 push 表)。
|
||
"""
|
||
wanted = tuple(tables) if tables is not None else MIGRATION_TABLES
|
||
src = sqlite3.connect(str(sqlite_path))
|
||
src.row_factory = sqlite3.Row
|
||
own_conn = pg_conn is None
|
||
if own_conn:
|
||
pg_conn = PostgresDatabase().connect()
|
||
try:
|
||
init_postgres_schema(pg_conn)
|
||
result = {}
|
||
for table in wanted:
|
||
if table in _SKIP_TABLES:
|
||
result[table] = 0
|
||
continue
|
||
try:
|
||
rows = src.execute(
|
||
'SELECT * FROM "%s"' % table).fetchall()
|
||
except sqlite3.OperationalError:
|
||
# 老库里没有这张表:记 0,不中断其余表。
|
||
result[table] = 0
|
||
continue
|
||
if not rows:
|
||
result[table] = 0
|
||
continue
|
||
columns = [d[0] for d in src.execute(
|
||
'SELECT * FROM "%s" LIMIT 0' % table).description]
|
||
if table == "task_followups" and "sender_task_id" in columns:
|
||
# SQLite 侧有、POSTGRES_SCHEMA 里没有的列:
|
||
# 与 peer_messages.ensure_followups_table 同款,
|
||
# 先查现有列、缺了再 ALTER 补列,已有列是 no-op。
|
||
# PRAGMA 经适配层翻译成 information_schema 查询,
|
||
# 取 row[1] 即列名(与 init_postgres_schema 同款)。
|
||
# 补列失败也不在这里吞掉迁移:INSERT 时若列仍
|
||
# 缺失会直接报错(大声失败,绝不静默丢列)。
|
||
try:
|
||
existing = {row[1] for row in pg_conn.execute(
|
||
"PRAGMA table_info(task_followups)").fetchall()}
|
||
except Exception:
|
||
existing = set()
|
||
if "sender_task_id" not in existing:
|
||
try:
|
||
pg_conn.execute(
|
||
"ALTER TABLE task_followups"
|
||
" ADD COLUMN sender_task_id TEXT")
|
||
except Exception:
|
||
pass
|
||
placeholders = ", ".join("?" for _ in columns)
|
||
col_list = ", ".join('"%s"' % c for c in columns)
|
||
inserted = 0
|
||
for row in rows:
|
||
cur = pg_conn.execute(
|
||
'INSERT INTO "%s" (%s) VALUES (%s)'
|
||
" ON CONFLICT DO NOTHING"
|
||
% (table, col_list, placeholders),
|
||
tuple(row[c] for c in columns))
|
||
if cur.rowcount:
|
||
inserted += cur.rowcount
|
||
# 身份列的序列不会因显式插 id 自动前进:迁完把序列
|
||
# 拨到当前最大 id,否则后续省略 id 的 INSERT 会撞主键。
|
||
if table in SEQUENCE_TABLES and "id" in columns:
|
||
try:
|
||
pg_conn.execute(
|
||
"SELECT setval(pg_get_serial_sequence(?, ?),"
|
||
" COALESCE((SELECT MAX(id) FROM \"%s\"), 1), true)"
|
||
% table,
|
||
(table, "id"))
|
||
except Exception:
|
||
pass
|
||
pg_conn.commit()
|
||
result[table] = inserted
|
||
return result
|
||
finally:
|
||
src.close()
|
||
if own_conn:
|
||
try:
|
||
pg_conn.close()
|
||
except Exception:
|
||
pass
|
||
|
||
|
||
__all__ = [
|
||
"MIGRATION_TABLES",
|
||
"SEQUENCE_TABLES",
|
||
"UNMIGRATED_TABLES",
|
||
"migration_coverage",
|
||
"migrate_sqlite_to_postgres",
|
||
"schema_tables",
|
||
]
|