feat: G7 分层 fail-open/fail-closed + G8 Docker 轮询掐断 + G9 worker 忽略 host 预算 + G13/G14 归属(第三批)

- G7:认领门 closed 时查配额异常回 quota_check_unavailable、标 interrupted(可重试/续跑);轮询与轮次边界用 open,异常时回 quota_check_failed——新回合边界拒绝,执行中轮询经 _quota_hit 闭包过滤此串、只记 warning 不杀在跑任务,确认超限才掐断;查询函数本身不吞异常冒充不限额。
- G8:Docker 路径加 _docker_call_with_quota_poll(后台线程跑阻塞式 docker 调用,主循环每 quota_poll_interval_seconds 缺省 30 秒查一次,确认超限按容器名真杀容器,结果改写 quota_exceeded 走统一收尾:interrupted、成本照记、续跑消息保留,配额命中后不走 ALREADY_EXISTS 回落);同步路径保持边界检查。
- G9:worker 路径默认忽略 host max_daily_turns(host.py 顶层 --ignore-host-budget 只清该项,Local/Docker 执行器在子命令前追加,worker CLI 缺省开、--no-ignore-host-budget 关);standalone 直接跑 host.py 时预算照常。
- G13/G14:/pr 不再走 system 豁免,建任务前按请求用户查配额(402/503 均不排队不改状态),队列路 pr_jobs.created_by 记请求用户(老表 ALTER 补列),worker 跑 pr 任务时审计操作人用 created_by(老行回落 system)。注意:G14 原案的 system 豁免(服务端与 worker 写死)与 P1 冲突(P1:system 按普通属主走默认额度,不另设无限额系统预算),本次 rebase 未合入该豁免,system 豁免需另行决策。
- 配额口径与 P0/P1 对齐:无配额行按默认额度(非不限额),只有显式 NULL 行才不限额;无价上限只计 source='actual' 行;缺属主(含父任务回查仍无)拒绝新回合。
- README 配额节同步以上口径与 G15 接受现状(best-effort 超支、UTC 月切分、在跑任务只在轮询/轮次边界响应配额改动)。G4 与 G15 不在本批。
This commit is contained in:
host committed 2026-10-28 11:14:10 +08:00
1 parent 5883169c82
commit e31fcc6cba
11 files changed
+786 -176

No files matched your search

+293 -144
View File
@@ -372,7 +372,9 @@ class Worker:
upload_dir=None,
digest_interval_seconds=3600,
outbox_backoff_seconds=60,
outbox_max_attempts=3):
outbox_max_attempts=3,
quota_poll_interval_seconds=30,
ignore_host_budget=True):
self.db_path = str(db_path)
self.host_py_path = host_py_path
self.config_path = config_path
@@ -385,6 +387,17 @@ class Worker:
self.digest_interval_seconds = digest_interval_seconds
self.outbox_backoff_seconds = outbox_backoff_seconds
self.outbox_max_attempts = outbox_max_attempts
# G8:配额轮询间隔(秒),Local popen 与 Docker 路径共用,
# 缺省 30;单测可传很小的值加速,生产不要改小(会打爆库)。
# None 当 30 用。
self.quota_poll_interval_seconds = (
30 if quota_poll_interval_seconds is None
else quota_poll_interval_seconds)
# G9:worker 路径默认忽略 host 的 max_daily_turns 预算。
# 云端已有 per-user USD 配额 + worker 认领/轮询门,host
# 的单机 turn 数预算再拦一次只会误拦云端已批的任务;
# standalone 直接跑 host.py 时不受此开关影响,预算照常。
self.ignore_host_budget = bool(ignore_host_budget)
self._last_digest_sent = 0.0
# env 只用于 key 存在性检查:默认接进程环境,单测可注入
# 一个普通 dict;worker 永远不把 env 里的值写出。
@@ -416,7 +429,15 @@ class Worker:
else:
self.executor = LocalExecutor(
host_py_path, config_path=config_path, runner=runner,
repo=repo)
repo=repo, ignore_host_budget=self.ignore_host_budget)
# 外部传入的执行器(CLI 的 DockerExecutor 等)同样同步
# G9 开关:worker 的 ignore_host_budget 是唯一口径,执行
# 器自己的缺省值不另起一套。假执行器没有该属性时跳过。
if hasattr(self.executor, "ignore_host_budget"):
try:
self.executor.ignore_host_budget = self.ignore_host_budget
except Exception:
pass
self._cost_store = cost_store
self._cancel_requested = set()
# 真取消用:process_factory 可注入(单测用它返回一个假长跑
@@ -961,7 +982,73 @@ class Worker:
return budget_exceeded(self.usage_turns, self.max_turns,
self.usage_cost_usd, self.max_cost_usd)
def _quota_exceeded(self, task, usage_total):
def _quota_limit_and_used(self, owner):
"""查某人当月配额与已记账用量,返回
(quota, used, month, unpriced_used)。
quota 为 None 表示不限额(只限行里 quota 为 NULL 的
显式不限额;无配额行按默认配额
_default_quota_usd_micros() 算,与服务端 _quota_status
的 P0 口径一致)。查询失败时抛异常,由调用方按
fail-open / fail-closed 分层决定——本函数自己绝不吞
异常后冒充“不限额”,否则调用方分不清“真不限额”与
“查不出来”。
unpriced_used 是当月 usd IS NULL 且 source='actual'
的成本行 input + output 之和(与服务端
_check_unpriced_token_cap 同口径,估算行不计);
quota 为 None 时它仍返回实数,但调用方
_quota_exceeded 在 quota 为 None 时先返回 None,
所以显式不限额用户不受无价上限约束,与服务端一致。
"""
month = datetime.now(timezone.utc).strftime("%Y-%m")
conn = _db_connect(self.db_path)
try:
conn.execute(
"CREATE TABLE IF NOT EXISTS user_quotas("
"user_id TEXT PRIMARY KEY, quota_usd_micros BIGINT,"
" updated_at DOUBLE PRECISION)")
conn.commit()
row = conn.execute(
"SELECT quota_usd_micros FROM user_quotas"
" WHERE user_id = ?",
(owner,)).fetchone()
if row is None:
# P0/P1 口径:无行按默认额度,不是不限额(只有
# 显式 NULL 行才是不限额,见下)。
quota = _default_quota_usd_micros()
else:
quota = row[0]
if quota is None:
return None, 0, month, 0
# cost_records 由 CostStore 懒建:全新库上它还不存
# 在,直接 JOIN 会报错——先实例化一次建表再查(与
# 服务端 _quota_status 同款做法),否则 quota=0
#(一分钱也不能花)在全新库上会被误放行。
_cost_store = CostStore(self.db_path)
try:
_cost_store._conn.close()
except Exception:
pass
used_row = conn.execute(
"SELECT COALESCE(SUM(c.usd_micros), 0)"
" FROM cost_records c JOIN tasks t"
" ON c.task_id = t.id"
" WHERE t.created_by = ? AND c.day LIKE ?",
(owner, month + "%")).fetchone()
used = used_row[0] if used_row else 0
unpriced_row = conn.execute(
"SELECT COALESCE(SUM(c.input_tokens + c.output_tokens), 0)"
" FROM cost_records c JOIN tasks t"
" ON c.task_id = t.id"
" WHERE t.created_by = ? AND c.day LIKE ?"
" AND c.usd_micros IS NULL AND c.source = 'actual'",
(owner, month + "%")).fetchone()
unpriced_used = unpriced_row[0] if unpriced_row else 0
return quota, int(used or 0), month, int(unpriced_used or 0)
finally:
conn.close()
def _quota_exceeded(self, task, usage_total, on_error="open"):
"""配额加固的执行时检查:返回超限时的错误文本,否则 None。
口径与服务端准入(_quota_status)一致:按任务创建者算,
@@ -970,29 +1057,27 @@ class Worker:
另有一道无价 token 上限(与服务端
_check_unpriced_token_cap 同口径):USD 配额不计量无价
模型,默认模型 terra 无价,若无此上限则配额对默认模型
永远不生效;有配额行的用户当月无价 token(input +
永远不生效;有额度约束的用户(无行按默认额度)当月无价
token(input +
output,已记账 + 本轮)达到上限即停。无价上限只计
source='actual' 的行:估算行(estimated)不是真实花费,
计入上限会把“没花钱”算成“花超了”,且与 cost.py
_report 的 unpriced_actual_tokens 口径一致。
P1 执行面三处收口(旧版三处都是 fail-open,已废):
属主与额度(P1 口径,与服务端 _quota_status 一致):
- 属主:任务 created_by 为空时先查父任务(协调员子任务
行可能无 created_by,属主跟父任务走);仍查不到时
拒绝新回合,不再返回 None 放行。created_by 字面为
"system" 的系统任务按普通属主算(无行时同样走默认
额度,不另设无限额的系统预算)。
- 无配额行:不再是不限额,按默认配额
_default_quota_usd_micros()($10/月)算;只有显式
NULL 行才是不限额(与 P0 的服务端口径一致,管理员
显式设 NULL 的行仍被尊重)。
- 查库失败:返回 "quota_check_failed: ..."(fail-closed),
绝不返回 None 放行。调用方分流:新回合边界(认领门、
重试/fallback/后续消息边界)见此串即拒绝新回合并记
worker_quota_stop 审计;执行中轮询(popen 轮询、
Docker 配额看门狗)见此串只记警告、不中途杀当前轮
——查询抖动不应杀掉已在跑的回合,但下一轮边界仍会
拒绝(见 run_one 的 _quota_hit 过滤)。查库失败的
审计由边界调用方记,这里只记日志,避免轮询高频写审计。
"system" 的系统任务按普通属主算,不另设无限额的
系统预算(G14 的 system 豁免与 P1 冲突,本次未合入)。
- 无配额行:按默认配额 _default_quota_usd_micros()
($10/月)算;只有显式 NULL 行才是不限额。
查库失败分层(G7 + P1):认领门传 on_error="closed",
返回 "quota_check_unavailable: ..."(调用方标
interrupted,可重试/续跑);默认 "open" 返回
"quota_check_failed: ..."——新回合边界(直接调用)
见此串即拒绝,执行中轮询经 _quota_hit 闭包过滤此串、
只记警告不杀当前轮。查询抖动不应杀掉已在跑的回合,
但下一轮边界仍会拒绝。
"""
owner = (task or {}).get("created_by")
if not owner and (task or {}).get("parent_task_id"):
@@ -1017,95 +1102,45 @@ class Worker:
return ("quota_exceeded: 任务缺少属主,无法查配额,"
"拒绝新回合(请归属真实用户后再排队)")
try:
month = datetime.now(timezone.utc).strftime("%Y-%m")
conn = _db_connect(self.db_path)
try:
conn.execute(
"CREATE TABLE IF NOT EXISTS user_quotas("
"user_id TEXT PRIMARY KEY, quota_usd_micros BIGINT,"
" updated_at DOUBLE PRECISION)")
conn.commit()
row = conn.execute(
"SELECT quota_usd_micros FROM user_quotas"
" WHERE user_id = ?",
(owner,)).fetchone()
if row is None:
# P1:无行按默认额度,不是不限额(P0 服务端
# 已在建号/登录时补行,worker 侧仍可能遇到
# 老库未补行的用户,这里按默认额度兜底,
# 不写行——写行是服务端的职责,worker 不抢)。
quota = _default_quota_usd_micros()
else:
quota = row[0]
if quota is None:
return None
# cost_records 由 CostStore 懒建:全新库上它还不存
# 在,直接 JOIN 会报错——先实例化一次建表再查(与
# 服务端 _quota_status 同款做法),否则 quota=0
#(一分钱也不能花)在全新库上会被误放行。
# P1 补:建表必须落在本连接上,不只 CostStore 的
# 连接上——文件库两者指向同一文件所以旧代码碰巧
# 能用,:memory: 库两者是不同空库,本连接查 JOIN
# 会直接报错并(P1 fail-closed 后)误拒全部任务。
_cost_store = CostStore(self.db_path)
try:
_cost_store._conn.close()
except Exception:
pass
try:
conn.execute(CostStore._COST_DDL)
conn.commit()
except Exception:
pass
used_row = conn.execute(
"SELECT COALESCE(SUM(c.usd_micros), 0)"
" FROM cost_records c JOIN tasks t"
" ON c.task_id = t.id"
" WHERE t.created_by = ? AND c.day LIKE ?",
(owner, month + "%")).fetchone()
used = used_row[0] if used_row else 0
unpriced_row = conn.execute(
"SELECT COALESCE(SUM(c.input_tokens + c.output_tokens), 0)"
" FROM cost_records c JOIN tasks t"
" ON c.task_id = t.id"
" WHERE t.created_by = ? AND c.day LIKE ?"
" AND c.usd_micros IS NULL AND c.source = 'actual'",
(owner, month + "%")).fetchone()
unpriced_used = unpriced_row[0] if unpriced_row else 0
finally:
conn.close()
if usage_total:
model = (task or {}).get("model") or self.model
micros = price_usd_micros(
model, usage_total.get("input_tokens", 0),
usage_total.get("cached_input_tokens", 0),
usage_total.get("output_tokens", 0))
used += micros or 0
if micros is None:
# 无价模型:本轮 token 计入无价上限(USD 口
# 径里它是 0,不会在上面那道里被拦住)。
unpriced_used += (
max(0, int(usage_total.get("input_tokens", 0)))
+ max(0, int(usage_total.get("output_tokens", 0))))
if used >= quota:
return ("quota_exceeded: 本月配额已用完(已用 %d / "
"配额 %d 微美元,%s)" % (used, quota, month))
cap = unpriced_token_cap()
if unpriced_used >= cap:
return ("quota_exceeded: 本月无价模型 token 已用完"
"(已用 %d / 上限 %d,%s)"
% (unpriced_used, cap, month))
return None
quota, used, month, unpriced_used = \
self._quota_limit_and_used(owner)
except Exception as exc:
# P1 fail-closed:查库失败不再返回 None。调用方按
# 前缀分流(见本函数 docstring):quota_check_failed
# 在新回合边界 = 拒绝,在执行中轮询 = 只警告不杀轮。
# 查库失败分层(见本函数 docstring):closed(认领门)
# 回 quota_check_unavailable,调用方标 interrupted;
# open 回 quota_check_failed,新回合边界拒绝,执行中
# 轮询经 _quota_hit 闭包过滤、只警告不杀轮。
try:
self.logger.warning("quota check failed: %s", exc)
except Exception:
pass
if on_error == "closed":
return "quota_check_unavailable: 配额查询失败,任务未开跑"
return ("quota_check_failed: 配额查询失败,拒绝新回合"
"(查库异常,非配额用完)")
if quota is None:
return None
if usage_total:
model = (task or {}).get("model") or self.model
micros = price_usd_micros(
model, usage_total.get("input_tokens", 0),
usage_total.get("cached_input_tokens", 0),
usage_total.get("output_tokens", 0))
used += micros or 0
if micros is None:
# 无价模型:本轮 token 计入无价上限(USD 口
# 径里它是 0,不会在上面那道里被拦住)。
unpriced_used += (
max(0, int(usage_total.get("input_tokens", 0)))
+ max(0, int(usage_total.get("output_tokens", 0))))
if used >= quota:
return ("quota_exceeded: 本月配额已用完(已用 %d / "
"配额 %d 微美元,%s)" % (used, quota, month))
cap = unpriced_token_cap()
if unpriced_used >= cap:
return ("quota_exceeded: 本月无价模型 token 已用完"
"(已用 %d / 上限 %d,%s)"
% (unpriced_used, cap, month))
return None
def _ready_tasks(self):
"""当前就绪任务列表(pick_next 的批量版)。
@@ -1511,11 +1546,13 @@ class Worker:
的标记,调用方据此保持 interrupted;deadline_seconds
到期时杀进程组并返回 status='timeout' 的标记,调用方
据此置 failed(超时是失败,不是取消)。quota_check 不为
空时每 30 秒查一次配额(轮询本身 50 毫秒一圈,逐圈查会
把库打爆),超限时同样杀进程组并返回 status=
'quota_exceeded' 的内部标记——调用方据此走配额中断收尾,
绝不能把这个标记原样写进 tasks.status(不在合法状态集
里)。Docker/同步路径没有这个轮询钩子,只走边界检查。
空时每 quota_poll_interval_seconds(缺省 30 秒)查一次
配额(轮询本身 50 毫秒一圈,逐圈查会把库打爆),超限时
同样杀进程组并返回 status='quota_exceeded' 的内部标记
——调用方据此走配额中断收尾,绝不能把这个标记原样写
进 tasks.status(不在合法状态集里)。Docker 路径见
_docker_call_with_quota_poll(同款轮询);同步路径没有
轮询钩子,只走边界检查。
"""
task_id = task["id"]
gateway_provider, gateway_env = self._ensure_gateway(task)
@@ -1539,6 +1576,10 @@ class Worker:
started = time.time()
last_quota_check = 0.0
last_db_cancel_check = 0.0
quota_interval = getattr(
self, "quota_poll_interval_seconds", 30)
if quota_interval is None:
quota_interval = 30
try:
while proc.poll() is None:
if task_id in self._cancel_requested or self._loop_stop:
@@ -1567,7 +1608,7 @@ class Worker:
self._kill_proc_group(proc)
break
if quota_check is not None and \
time.time() - last_quota_check >= 30:
time.time() - last_quota_check >= quota_interval:
last_quota_check = time.time()
try:
over = quota_check()
@@ -2205,6 +2246,80 @@ class Worker:
detail += " (" + "; ".join(rejected) + ")"
self._audit(task["project_id"], "worker_peer_messages", detail)
def _docker_call_with_quota_poll(self, task, fn, quota_check=None):
"""Docker 同步调用包一层配额轮询(G8),与 popen 路径同款。
fn 在后台线程里跑(DockerExecutor 的调用本身是阻塞的
docker run,无法像 popen 那样在主循环里轮询);主循环
每 quota_poll_interval_seconds(缺省 30 秒)调一次
quota_check,确认超限时按任务容器名真杀容器,fn 返回
后把结果状态改写成内部标记 'quota_exceeded',调用方
(run_one)据此走统一的配额中断收尾:状态 interrupted、
已花成本照记、续跑消息保留。quota_check 为 None 时
直接调 fn,不起线程。quota_check 本身抛异常时按
fail-open 处理(只记 warning,不杀容器),只有确认
超限才杀;取消时 cancel() 已按容器名杀过容器,线程
随之结束,轮询循环不再多杀一次。fn 抛异常时在主线程
原样重抛,由 _run_attempt 外层的 except 写成 failed,
与不包轮询时的行为一致。注意:轮询查的是已记账用量
(与 popen 路径同款),在跑回合的 token 只在回合结束
才回传,所以掐断粒度仍是轮询间隔,不是 token 级。
"""
if quota_check is None:
return fn()
box = {}
def _target():
try:
box["result"] = fn()
except Exception as exc: # noqa: BLE001 -- 主线程重抛
box["error"] = exc
thread = threading.Thread(target=_target, daemon=True)
thread.start()
interval = getattr(self, "quota_poll_interval_seconds", 30)
if interval is None:
interval = 30
last_check = 0.0
quota_hit = False
while thread.is_alive():
if task["id"] in self._cancel_requested or self._loop_stop:
break
now = time.time()
if now - last_check >= interval:
last_check = now
try:
over = bool(quota_check())
except Exception as exc:
try:
self.logger.warning(
"docker quota poll failed: %s", exc)
except Exception:
pass
over = False
if over:
quota_hit = True
container = None
try:
container = self.executor.container_name(task)
except Exception:
container = None
if container is not None and hasattr(
self.executor, "kill_container"):
try:
self.executor.kill_container(container)
except Exception:
pass
break
thread.join(timeout=0.05)
thread.join()
if "error" in box:
raise box["error"]
result = box.get("result")
if quota_hit and isinstance(result, dict):
result = dict(result, status="quota_exceeded")
return result
def _run_attempt(self, task, quota_check=None):
"""单次执行尝试(不含认领、key 门、重试、成本与最终审计)。
@@ -2337,12 +2452,16 @@ class Worker:
if task.get("_goal_resume_breakpoint"):
# G10 断点:Docker 路用无 --goal-text 的
# goal-resume-breakpoint 命令。
result = self.executor.goal_resume_breakpoint_task(
result = self._docker_call_with_quota_poll(
task,
timeout=effective_docker_timeout,
extra_mounts=tenant_mounts,
network=tenant_network,
extra_env=proxy_env)
lambda: self.executor.goal_resume_breakpoint_task(
task,
timeout=effective_docker_timeout,
extra_mounts=tenant_mounts,
network=tenant_network,
extra_env=_merge_env(proxy_env,
gateway_env)),
quota_check)
elif task.get("_resume"):
# P1 断点续跑传 None(不传 --goal-text,
# host 沿用原 goal+verify);开新目标
@@ -2350,31 +2469,41 @@ class Worker:
_resume_text = None if task.get(
"_resume_kind") == "breakpoint" \
else task["prompt"]
result = self.executor.goal_resume_task(
task, _resume_text,
timeout=effective_docker_timeout,
extra_mounts=tenant_mounts,
network=tenant_network,
extra_env=_merge_env(proxy_env,
gateway_env),
model_provider=gateway_provider)
result = self._docker_call_with_quota_poll(
task,
lambda: self.executor.goal_resume_task(
task, _resume_text,
timeout=effective_docker_timeout,
extra_mounts=tenant_mounts,
network=tenant_network,
extra_env=_merge_env(proxy_env,
gateway_env),
model_provider=gateway_provider),
quota_check)
else:
result = self.executor.goal_task(
result = self._docker_call_with_quota_poll(
task,
lambda: self.executor.goal_task(
task, timeout=effective_docker_timeout,
extra_mounts=tenant_mounts,
network=tenant_network,
extra_env=_merge_env(proxy_env,
gateway_env),
seed_host_dir=seed_host_dir,
model_provider=gateway_provider),
quota_check)
else:
result = self._docker_call_with_quota_poll(
task,
lambda: self.executor.dispatch_task(
task, timeout=effective_docker_timeout,
extra_mounts=tenant_mounts,
network=tenant_network,
extra_env=_merge_env(proxy_env,
gateway_env),
seed_host_dir=seed_host_dir,
model_provider=gateway_provider)
else:
result = self.executor.dispatch_task(
task, timeout=effective_docker_timeout,
extra_mounts=tenant_mounts,
network=tenant_network,
extra_env=_merge_env(proxy_env, gateway_env),
seed_host_dir=seed_host_dir,
model_provider=gateway_provider)
model_provider=gateway_provider),
quota_check)
else:
# seed 参数只传给 LocalExecutor:CloudExecutor
# 基类与测试假执行器的 goal_task/dispatch_task
@@ -2434,19 +2563,23 @@ class Worker:
result = self.executor.dispatch_task(task)
combined = (result.get("stdout", "") or "") + \
(result.get("stderr", "") or "")
if not goal_mode and result["status"] != "completed" and \
if not goal_mode and result["status"] not in (
"completed", "quota_exceeded") and \
_ALREADY_EXISTS_MARKER in combined:
if is_docker:
result = self.executor.run_task(
task, timeout=effective_docker_timeout,
extra_mounts=tenant_mounts
if self.tenant_isolation else None,
network=tenant_network
if self.tenant_isolation else None,
extra_env=_merge_env(
proxy_env if self.egress_proxy_port
else None, gateway_env),
model_provider=gateway_provider)
result = self._docker_call_with_quota_poll(
task,
lambda: self.executor.run_task(
task, timeout=effective_docker_timeout,
extra_mounts=tenant_mounts
if self.tenant_isolation else None,
network=tenant_network
if self.tenant_isolation else None,
extra_env=_merge_env(
proxy_env if self.egress_proxy_port
else None, gateway_env),
model_provider=gateway_provider),
quota_check)
else:
if gateway_provider and not isinstance(
self.executor, LocalExecutor):
@@ -3092,8 +3225,11 @@ class Worker:
# 再开跑——直接标 interrupted + 配额原因,不记成本(还没花
# 钱),续跑消息不消费,顶上来后重试/续跑可再跑。与 key
# 门、仓库门同款提前返回形状,区别是状态为 interrupted
#(可续跑)而非 failed。
quota_error = self._quota_exceeded(task, None)
#(可续跑)而非 failed。G7 分层:认领门用 closed——
# 查询异常时同样标 interrupted(quota_check_unavailable,
# 可重试/续跑),绝不在“不知道超没超”时开跑;轮询与
# 轮次边界仍用默认 open,查询抖动不杀在跑任务。
quota_error = self._quota_exceeded(task, None, on_error="closed")
if quota_error is not None:
self._set_status(task_id, "interrupted")
self._write_execution_result(
@@ -3696,8 +3832,11 @@ class Worker:
job_id = job["id"]
task_id = job["task_id"]
try:
# G13:审计操作人用 job 的费用归属人(请求 /pr 的
# 用户),老行没有 created_by 时回落 "system"。
result = execute_task_pr(
self.db_path, task_id, "system")
self.db_path, task_id,
job.get("created_by") or "system")
conn = _db_connect(self.db_path)
try:
finish_pr_job(conn, job_id, "completed",
@@ -4121,6 +4260,15 @@ def main(argv=None):
"列表里的第一个模型再跑一次,401/400"
"绝不 fallback,取消绝不 fallback)")
parser.add_argument("--max-turns", type=int, default=None)
parser.add_argument("--ignore-host-budget", dest="ignore_host_budget",
action="store_true", default=True,
help="G9(默认开):worker 路径忽略 host 的 "
"max_daily_turns 预算,云端 per-user USD "
"配额 + worker 门才是口径")
parser.add_argument("--no-ignore-host-budget",
dest="ignore_host_budget", action="store_false",
help="G9:关闭忽略,worker 调 host.py 时 host "
"的 max_daily_turns 预算照常生效(双重门)")
parser.add_argument("--max-tasks", type=int, default=None)
parser.add_argument("--executor", default="local",
choices=["local", "docker", "cloud"],
@@ -4219,6 +4367,7 @@ def main(argv=None):
args.fallback_models.split(",")]
if args.fallback_models else []),
max_turns=args.max_turns,
ignore_host_budget=args.ignore_host_budget,
executor=_build_cli_executor(args, host_py),
task_timeout=args.task_timeout,
max_retries=args.max_retries,