浅念
601451f22b
Overlay ~150 upstream items onto our V8.12 base, preserving trade-pro
theme, registry tests, and design docs. Re-applied our patch set
(discovery/env_for/blocks.css/type-mapping/theme_color/frontend entries,
test_theme_pro_v3 mods) — all anchors survived upstream evolution.
New platform enhancement (fixes upgrade-introduced regression):
multilingual.site_locale now honors settings_json.locale, plus
PUT /api/i18n/sites/{id}/locale — standalone English sites get
<html lang='en'> under the V8.15 locale-rewrite pipeline.
compose: adopt V8.21.3 (image 8.21.3-dev.1, /api/ready probes, MySQL/S3
env) with project name pinned to siteforge-v8-10 (data volumes).
Tests: 356 passed / 11 failed — all 11 confirmed pre-existing in
pristine V8.21.3 on this host (10 upstream Windows env + our build test
now green after locale fix). Patch registry updated in plan doc.
Co-Authored-By: Claude Code <noreply@anthropic.com>
180 lines
11 KiB
Python
180 lines
11 KiB
Python
'''Durable build queue: SQLite single-host or PostgreSQL with DB-owned leases.
|
||
|
||
Redis is an optional wake-up signal, not an authoritative queue. PostgreSQL
|
||
lock/lease semantics require actual multi-worker acceptance on infrastructure.
|
||
'''
|
||
from __future__ import annotations
|
||
import hashlib
|
||
import json
|
||
import sqlite3
|
||
import os
|
||
import uuid
|
||
from datetime import datetime, timedelta, timezone
|
||
from fastapi import HTTPException
|
||
from . import db
|
||
|
||
class JobConflict(ValueError): pass
|
||
|
||
class JobCapacityError(ValueError): pass
|
||
|
||
def _limit(name, default, minimum=1, maximum=10000):
|
||
try:return max(minimum,min(maximum,int(os.environ.get(name, default))))
|
||
except ValueError:return default
|
||
|
||
def iso_after(seconds: int) -> str:
|
||
return (datetime.now(timezone.utc)+timedelta(seconds=seconds)).isoformat(timespec='seconds')
|
||
|
||
def migrate():
|
||
with db.connect() as c:
|
||
existing={r['name'] for r in c.execute('PRAGMA table_info(build_jobs)')}
|
||
columns={
|
||
'payload_json':"TEXT NOT NULL DEFAULT '{}'",
|
||
'idempotency_key':"TEXT",
|
||
'max_attempts':"INTEGER NOT NULL DEFAULT 3",
|
||
'timeout_seconds':"INTEGER NOT NULL DEFAULT 300",
|
||
'available_at':"TEXT",
|
||
'cancel_requested':"INTEGER NOT NULL DEFAULT 0",
|
||
'worker_id':"TEXT",
|
||
'lease_until':"TEXT",
|
||
'heartbeat_at':"TEXT",
|
||
}
|
||
for column,definition in columns.items():
|
||
if column not in existing:c.execute(f'ALTER TABLE build_jobs ADD COLUMN {column} {definition}')
|
||
c.execute("CREATE UNIQUE INDEX IF NOT EXISTS idx_build_key ON build_jobs(site_id,idempotency_key) WHERE idempotency_key IS NOT NULL")
|
||
c.execute("CREATE INDEX IF NOT EXISTS idx_build_available ON build_jobs(state,available_at,created_at)")
|
||
|
||
def submit(site_id, payload:dict, actor:str, key:str|None=None) -> dict:
|
||
normalized=json.dumps({'mirror_images':bool(payload.get('mirror_images',False))},sort_keys=True,separators=(',',':'))
|
||
if key is not None:
|
||
if not (8<=len(key)<=128 and all(c.isalnum() or c in '_-:.' for c in key)):
|
||
raise JobConflict('幂等键必须为 8–128 位字母、数字或 _-:.')
|
||
# No client key: de-duplicate pending jobs with identical payload for a site.
|
||
with db.connect() as c:
|
||
c.execute('BEGIN IMMEDIATE')
|
||
if key:
|
||
prior=c.execute('SELECT * FROM build_jobs WHERE site_id=? AND idempotency_key=?',(site_id,key)).fetchone()
|
||
if prior:
|
||
if prior['payload_json']!=normalized:raise JobConflict('同一幂等键不能对应不同构建参数')
|
||
return {'id':prior['id'],'state':prior['state'],'existing':True}
|
||
else:
|
||
prior=c.execute("SELECT id,state FROM build_jobs WHERE site_id=? AND kind='build' AND state IN ('queued','running','retrying') AND payload_json=? ORDER BY created_at LIMIT 1",(site_id,normalized)).fetchone()
|
||
if prior:return {'id':prior['id'],'state':prior['state'],'existing':True}
|
||
# Capacity gates run inside the same immediate write transaction as
|
||
# INSERT so simultaneous callers cannot bypass the limits.
|
||
global_cap=_limit('SITEFORGE_MAX_PENDING_JOBS',100)
|
||
site_cap=_limit('SITEFORGE_MAX_PENDING_JOBS_PER_SITE',5)
|
||
active="state IN ('queued','running','retrying')"
|
||
global_count=c.execute(f'SELECT COUNT(*) FROM build_jobs WHERE {active}').fetchone()[0]
|
||
site_count=c.execute(f'SELECT COUNT(*) FROM build_jobs WHERE {active} AND site_id=?',(site_id,)).fetchone()[0]
|
||
if global_count>=global_cap:raise JobCapacityError('全局待处理任务达到上限')
|
||
if site_count>=site_cap:raise JobCapacityError('该网站待处理任务达到上限')
|
||
job_id=uuid.uuid4().hex[:16]
|
||
max_attempts=max(1,min(6,int(os.getenv('SITEFORGE_BUILD_MAX_ATTEMPTS','3'))))
|
||
timeout=max(10,min(3600,int(os.getenv('SITEFORGE_BUILD_TIMEOUT_SECONDS','300'))))
|
||
c.execute('''INSERT INTO build_jobs(id,site_id,kind,state,created_by,created_at,
|
||
payload_json,idempotency_key,max_attempts,timeout_seconds,available_at)
|
||
VALUES (?,?,?,?,?,?,?,?,?,?,?)''',(job_id,site_id,'build','queued',actor,db.now(),normalized,key,max_attempts,timeout,db.now()))
|
||
from . import redis_signal
|
||
redis_signal.notify()
|
||
return {'id':job_id,'state':'queued','existing':False}
|
||
|
||
def cancel(site_id,job_id):
|
||
with db.connect() as c:
|
||
c.execute('BEGIN IMMEDIATE')
|
||
row=c.execute('SELECT state FROM build_jobs WHERE site_id=? AND id=?',(site_id,job_id)).fetchone()
|
||
if row is None:raise HTTPException(404,'任务不存在')
|
||
if row['state'] in ('done','failed','cancelled'):
|
||
return {'id':job_id,'state':row['state'],'cancelled':False}
|
||
if row['state'] in ('queued','retrying'):
|
||
c.execute("UPDATE build_jobs SET state='cancelled',cancel_requested=1,finished_at=? WHERE id=?",(db.now(),job_id))
|
||
return {'id':job_id,'state':'cancelled','cancelled':True}
|
||
c.execute('UPDATE build_jobs SET cancel_requested=1 WHERE id=?',(job_id,))
|
||
return {'id':job_id,'state':'cancelling','cancelled':True}
|
||
|
||
def recover_expired():
|
||
# Claims are recoverable after a worker crashes. Running jobs are never
|
||
# blindly duplicated while their lease is live.
|
||
with db.connect() as c:
|
||
c.execute('BEGIN IMMEDIATE')
|
||
rows=c.execute("SELECT * FROM build_jobs WHERE state='running' AND (lease_until IS NULL OR lease_until < ?)",(db.now(),)).fetchall()
|
||
for row in rows:
|
||
if row['cancel_requested']:
|
||
state='cancelled'
|
||
else:
|
||
# Publishing is an external side effect: it may have completed remotely
|
||
# even though the Worker lost its lease. Never automatically replay it.
|
||
state=('failed' if row['kind'] in ('remote_deploy','remote_rollback')
|
||
else ('retrying' if row['attempts']<row['max_attempts'] else 'failed'))
|
||
message=('Release lease expired; reconcile remote release before manual retry'
|
||
if row['kind'] in ('remote_deploy','remote_rollback') else
|
||
'Worker lease expired; verify partial builds')
|
||
c.execute('UPDATE build_jobs SET state=?,worker_id=NULL,lease_until=NULL,available_at=?,error=? WHERE id=?',
|
||
(state,db.now(),message,row['id']))
|
||
return len(rows)
|
||
|
||
|
||
def submit_migration(site_id,session_id,actor,key=None):
|
||
# Queue WordPress migration through the shared lease-based Worker.
|
||
from .wp_migration_v81 import _one
|
||
_one(site_id,session_id)
|
||
if key is not None and not (8<=len(key)<=128 and all(c.isalnum() or c in '_-:.' for c in key)):
|
||
raise JobConflict('幂等键必须为 8–128 位字母、数字或 _-:.')
|
||
payload=json.dumps({'session_id':session_id},sort_keys=True,separators=(',',':'))
|
||
with db.connect() as c:
|
||
c.execute('BEGIN IMMEDIATE')
|
||
if key:
|
||
row=c.execute('SELECT * FROM build_jobs WHERE site_id=? AND idempotency_key=?',(site_id,key)).fetchone()
|
||
if row:
|
||
if row['kind']!='wordpress_scan' or row['payload_json']!=payload:
|
||
raise JobConflict('同一幂等键不能对应不同迁移任务')
|
||
return {'id':row['id'],'state':row['state'],'existing':True}
|
||
row=c.execute("SELECT id,state FROM build_jobs WHERE kind='wordpress_scan' AND site_id=? AND payload_json=? AND state IN ('queued','running','retrying') ORDER BY created_at LIMIT 1",(site_id,payload)).fetchone()
|
||
if row:return {'id':row['id'],'state':row['state'],'existing':True}
|
||
global_cap=_limit('SITEFORGE_MAX_PENDING_JOBS',100)
|
||
site_cap=_limit('SITEFORGE_MAX_PENDING_JOBS_PER_SITE',5)
|
||
if c.execute("SELECT COUNT(*) FROM build_jobs WHERE state IN ('queued','running','retrying')").fetchone()[0]>=global_cap:
|
||
raise JobCapacityError('全局待处理任务达到上限')
|
||
if c.execute("SELECT COUNT(*) FROM build_jobs WHERE site_id=? AND state IN ('queued','running','retrying')",(site_id,)).fetchone()[0]>=site_cap:
|
||
raise JobCapacityError('该网站待处理任务达到上限')
|
||
job_id=uuid.uuid4().hex[:16]
|
||
attempts=max(1,min(6,int(os.getenv('SITEFORGE_WP_SCAN_MAX_ATTEMPTS','3'))))
|
||
timeout=max(60,min(3600,int(os.getenv('SITEFORGE_WP_SCAN_TIMEOUT_SECONDS','900'))))
|
||
c.execute('''INSERT INTO build_jobs(id,site_id,kind,state,created_by,created_at,
|
||
payload_json,idempotency_key,max_attempts,timeout_seconds,available_at)
|
||
VALUES(?,?,?,?,?,?,?,?,?,?,?)''',(job_id,site_id,'wordpress_scan','queued',actor,
|
||
db.now(),payload,key,attempts,timeout,db.now()))
|
||
from . import redis_signal
|
||
redis_signal.notify()
|
||
return {'id':job_id,'state':'queued','existing':False}
|
||
|
||
|
||
def submit_delivery(site_id,kind,payload,actor,key=None):
|
||
# One logical release per job; serialized with build jobs by Worker.
|
||
if kind not in ('remote_deploy','remote_rollback'):
|
||
raise JobConflict('Unknown delivery job kind')
|
||
if key is not None and not (8<=len(key)<=128 and all(c.isalnum() or c in '_-:.' for c in key)):
|
||
raise JobConflict('无效的幂等键')
|
||
normalized=json.dumps(payload,sort_keys=True,separators=(',',':'))
|
||
with db.connect() as c:
|
||
c.execute('BEGIN IMMEDIATE')
|
||
if key:
|
||
row=c.execute('SELECT * FROM build_jobs WHERE site_id=? AND idempotency_key=?',(site_id,key)).fetchone()
|
||
if row:
|
||
if row['kind']!=kind or row['payload_json']!=normalized:raise JobConflict('幂等键存在冲突')
|
||
return {'id':row['id'],'state':row['state'],'existing':True}
|
||
row=c.execute("SELECT id,state FROM build_jobs WHERE site_id=? AND kind=? AND payload_json=? AND state IN ('queued','running','retrying') ORDER BY created_at LIMIT 1",(site_id,kind,normalized)).fetchone()
|
||
if row:return {'id':row['id'],'state':row['state'],'existing':True}
|
||
active="state IN ('queued','running','retrying')"
|
||
if c.execute(f'SELECT COUNT(*) FROM build_jobs WHERE {active}').fetchone()[0]>=_limit('SITEFORGE_MAX_PENDING_JOBS',100):
|
||
raise JobCapacityError('系统任务队列已满')
|
||
if c.execute(f'SELECT COUNT(*) FROM build_jobs WHERE site_id=? AND {active}',(site_id,)).fetchone()[0]>=_limit('SITEFORGE_MAX_PENDING_JOBS_PER_SITE',5):
|
||
raise JobCapacityError('网站任务队列已满')
|
||
job_id=uuid.uuid4().hex[:16]
|
||
c.execute('''INSERT INTO build_jobs(id,site_id,kind,state,created_by,created_at,payload_json,
|
||
idempotency_key,max_attempts,timeout_seconds,available_at)
|
||
VALUES(?,?,?,?,?,?,?,?,?,?,?)''',
|
||
(job_id,site_id,kind,'queued',actor,db.now(),normalized,key,3,900,db.now()))
|
||
from . import redis_signal
|
||
redis_signal.notify()
|
||
return {'id':job_id,'state':'queued','existing':False}
|