feat: 计划模式 + 后续消息 + 会话分支接云端 (#65)
- 计划模式：tasks 加 plan 列；plan 与 approval=full / goal 冲突时
400；执行器在 approval 参数后追加 --sandbox read-only（本地
dispatch/run/goal/popen 与 Docker 内层命令全覆盖），host 任务
存下 sandbox 后续轮次自动继承只读。
- 后续消息：新表 task_followups；POST/GET /tasks/{id}/followups
（仅 queued/running 的非 goal 任务；direct 立即往链路追加
phase=followup-direct 条目，本轮跑完后优先于排队执行；排队
按 direct 优先、队内先来先服务逐条再跑一轮，同一 thread；
一条失败即停、剩余 pending 留给重试入口；取消时回 pending）。
- 会话分支：POST /tasks/{id}/fork（仅终态任务；继承 executor/
模型/强度/权限/计划，goal 字段置空）；worker 先 fork 再跑首轮，
首轮失败不自动重试、不重复分叉，失败后走重试入口重跑首轮。
- 修任务级模型被覆盖：worker 此前无条件写成主模型，控制台
选的模型实际不生效；现为任务级 > worker 主模型 > 配置。
- Docker 租户准备抽成 _docker_task_context，供普通尝试与 fork 共用。
- console：新建任务计划勾选（含冲突拦截）、详情计划徽标与
分支来源、分支按钮与表单、后续消息区、列表 [计划]/[分支] 标记。
- 测试：cloud/tests/test_task_links.py 17 个（server 校验与继承、
worker 模型优先、只读命令、排空顺序与停排、goal 不排空、
fork 单次性）；全量 cloud 542、host 49、deploy 14。
Co-authored-by: host <host@test.local>
This commit is contained in:
openqjandhost authored and GitHub committed
1 parent
6da3745127
commit
f4443dca4f
7 files changed
+1120
-74
No files matched your search
+255
-3
@@ -445,6 +445,10 @@ def migrate_tasks_table(conn):
|
||||
"model": "TEXT",
|
||||
"effort": "TEXT",
|
||||
"approval": "TEXT",
|
||||
# 计划模式（只读）与分支来源：plan=1 时 worker 用
|
||||
# read-only 沙箱；forked_from 记源任务 id（非分支为 NULL）。
|
||||
"plan": "INTEGER",
|
||||
"forked_from": "TEXT",
|
||||
}
|
||||
for name, coltype in new_cols.items():
|
||||
if name not in cols:
|
||||
@@ -468,6 +472,41 @@ def migrate_projects_table(conn):
|
||||
conn.execute("ALTER TABLE projects ADD COLUMN auto_pr INTEGER")
|
||||
|
||||
|
||||
def _ensure_followups_table(conn):
|
||||
"""幂等建后续消息表：server init_db 与各 followup 接口都调它，
|
||||
老库第一次跑到这里时自动补表，不丢数据。DOUBLE PRECISION 在
|
||||
SQLite 与 Postgres 下都可用（SQLite 按 NUMERIC 亲和处理）。"""
|
||||
conn.execute(
|
||||
"CREATE TABLE IF NOT EXISTS task_followups("
|
||||
"id TEXT PRIMARY KEY, "
|
||||
"task_id TEXT, "
|
||||
"project_id TEXT, "
|
||||
"body TEXT, "
|
||||
"mode TEXT, "
|
||||
"status TEXT, "
|
||||
"created_by TEXT, "
|
||||
"created_at DOUBLE PRECISION, "
|
||||
"updated_at DOUBLE PRECISION)"
|
||||
)
|
||||
conn.execute(
|
||||
"CREATE INDEX IF NOT EXISTS idx_followups_task"
|
||||
" ON task_followups(task_id, status)")
|
||||
|
||||
|
||||
def _followup_to_dict(row):
|
||||
return {
|
||||
"id": row["id"],
|
||||
"task_id": row["task_id"],
|
||||
"project_id": row["project_id"],
|
||||
"body": row["body"],
|
||||
"mode": row["mode"],
|
||||
"status": row["status"],
|
||||
"created_by": row["created_by"],
|
||||
"created_at": row["created_at"],
|
||||
"updated_at": row["updated_at"],
|
||||
}
|
||||
|
||||
|
||||
def _is_postgres_backend():
|
||||
backend = os.environ.get("CLOUD_DB_BACKEND") or "sqlite"
|
||||
return str(backend).strip().lower() in ("postgres", "postgresql")
|
||||
@@ -487,6 +526,7 @@ def init_db(db_path):
|
||||
_init_postgres_schema(conn)
|
||||
migrate_tasks_table(conn)
|
||||
migrate_projects_table(conn)
|
||||
_ensure_followups_table(conn)
|
||||
conn.commit()
|
||||
return
|
||||
conn.execute(
|
||||
@@ -515,6 +555,7 @@ def init_db(db_path):
|
||||
)
|
||||
migrate_tasks_table(conn)
|
||||
migrate_projects_table(conn)
|
||||
_ensure_followups_table(conn)
|
||||
# worker 每轮 poll 都按 status 取任务（见 load_tasks 的
|
||||
# WHERE status IN (...)），无索引时是全表扫描；任务表随
|
||||
# 时间变大后索引是必须的。IF NOT EXISTS 保证老库幂等。
|
||||
@@ -583,6 +624,8 @@ def _task_to_dict(row):
|
||||
"model": _row_get(row, "model"),
|
||||
"effort": _row_get(row, "effort"),
|
||||
"approval": _row_get(row, "approval"),
|
||||
"plan": _row_get(row, "plan") or 0,
|
||||
"forked_from": _row_get(row, "forked_from"),
|
||||
}
|
||||
|
||||
|
||||
@@ -911,6 +954,12 @@ class CloudControlPlaneHandler(BaseHTTPRequestHandler):
|
||||
self._retry_task(user_id, rest[: -len("/retry")])
|
||||
elif rest.endswith("/heartbeat") and method == "POST":
|
||||
self._heartbeat_task(user_id, rest[: -len("/heartbeat")])
|
||||
elif rest.endswith("/followups") and method == "POST":
|
||||
self._create_followup(user_id, rest[: -len("/followups")])
|
||||
elif rest.endswith("/followups") and method == "GET":
|
||||
self._list_followups(user_id, rest[: -len("/followups")])
|
||||
elif rest.endswith("/fork") and method == "POST":
|
||||
self._fork_task(user_id, rest[: -len("/fork")])
|
||||
else:
|
||||
self._send_json(404, {"error": "not found"})
|
||||
else:
|
||||
@@ -1484,6 +1533,13 @@ class CloudControlPlaneHandler(BaseHTTPRequestHandler):
|
||||
self._send_json(400, {
|
||||
"error": "approval must be ask, auto or full"})
|
||||
return
|
||||
# 计划模式：只读沙箱，不改任何文件；与“完全访问”
|
||||
# （danger-full-access）语义直接冲突，拒绝建任务。
|
||||
plan = 1 if body.get("plan") in (True, 1) else 0
|
||||
if plan and approval == "full":
|
||||
self._send_json(400, {
|
||||
"error": "plan 模式与 approval=full 冲突（只读 vs 完全访问）"})
|
||||
return
|
||||
# goal 字段：verify_command 非空即 goal 模式（worker 走
|
||||
# host.py goal 循环）；goal 文本缺省用 prompt；轮次缺省 3
|
||||
# （与 host.py 默认一致），非法值 400 且不建任务。
|
||||
@@ -1497,6 +1553,12 @@ class CloudControlPlaneHandler(BaseHTTPRequestHandler):
|
||||
self._send_json(400, {
|
||||
"error": "verify_command must be a string"})
|
||||
return
|
||||
# 计划模式与 goal 模式也冲突：goal 循环就是要改文件
|
||||
# 直到验测通过，只读沙箱下它永远做不成。
|
||||
if plan and verify_command:
|
||||
self._send_json(400, {
|
||||
"error": "plan 模式与 goal 模式冲突（只读 vs 改文件）"})
|
||||
return
|
||||
try:
|
||||
goal_max_rounds = int(body.get("goal_max_rounds", 3))
|
||||
except (TypeError, ValueError):
|
||||
@@ -1534,13 +1596,13 @@ class CloudControlPlaneHandler(BaseHTTPRequestHandler):
|
||||
" idempotency_key, depends_on, priority, created_by,"
|
||||
" created_at, updated_at, last_heartbeat, executor,"
|
||||
" goal, verify_command, goal_max_rounds,"
|
||||
" model, effort, approval)"
|
||||
" model, effort, approval, plan)"
|
||||
" VALUES(?, ?, ?, 'queued', ?, ?, ?, ?, ?, ?, NULL, ?,"
|
||||
" ?, ?, ?, ?, ?, ?)",
|
||||
" ?, ?, ?, ?, ?, ?, ?)",
|
||||
(task_id, project_id, prompt, idempotency_key,
|
||||
json.dumps(depends_on), priority, user_id, now, now,
|
||||
executor, goal, verify_command, goal_max_rounds,
|
||||
model, effort, approval),
|
||||
model, effort, approval, plan),
|
||||
)
|
||||
conn.commit()
|
||||
except (sqlite3.IntegrityError, _PgIntegrityError):
|
||||
@@ -1705,6 +1767,196 @@ class CloudControlPlaneHandler(BaseHTTPRequestHandler):
|
||||
_emit({"type": "done", "status": task["status"],
|
||||
"reason": "timeout"})
|
||||
|
||||
def _create_followup(self, user_id, task_id):
|
||||
"""给进行中任务发后续消息：排队 / 直接发送。
|
||||
|
||||
语义（用户定稿）：排队进队尾，不打断本轮，本轮结束
|
||||
后按序每条再跑一轮；直接发送也不中断本轮——消息立即
|
||||
送达（链路里可见），本轮跑完后立刻以它开下一轮，且
|
||||
优先于排队中的消息。v1 只做运行时（含排队中）的任务：
|
||||
已终态的任务 409；goal 任务 409（goal 循环自有轮次）。
|
||||
权限与取消同款：项目 create_task（写操作，不能只读）。
|
||||
"""
|
||||
body, err = self._read_json()
|
||||
if err:
|
||||
self._send_json(400, {"error": err})
|
||||
return
|
||||
row = self._fetch_task(task_id)
|
||||
if row is None:
|
||||
self._send_json(404, {"error": "task not found"})
|
||||
return
|
||||
task = _task_to_dict(row)
|
||||
with _auth_store(self.server.db_path) as store:
|
||||
if not store.check_permission(
|
||||
user_id, task["project_id"], "create_task"):
|
||||
self._send_json(403, {"error": "forbidden"})
|
||||
return
|
||||
text = body.get("body")
|
||||
if not text or not isinstance(text, str) or not text.strip():
|
||||
self._send_json(400, {"error": "body required"})
|
||||
return
|
||||
text = text.strip()
|
||||
if len(text) > 20000:
|
||||
self._send_json(400, {"error": "body too long"})
|
||||
return
|
||||
mode = body.get("mode", "queued")
|
||||
if mode not in ("queued", "direct"):
|
||||
self._send_json(400, {
|
||||
"error": "mode must be queued or direct"})
|
||||
return
|
||||
if task["status"] not in ("queued", "running"):
|
||||
self._send_json(409, {
|
||||
"error": "后续消息仅支持进行中任务",
|
||||
"status": task["status"],
|
||||
})
|
||||
return
|
||||
if task.get("verify_command"):
|
||||
self._send_json(409, {"error": "goal 任务暂不支持后续消息"})
|
||||
return
|
||||
now = time.time()
|
||||
conn = self._db()
|
||||
try:
|
||||
_ensure_followups_table(conn)
|
||||
fu_id = uuid.uuid4().hex
|
||||
conn.execute(
|
||||
"INSERT INTO task_followups(id, task_id, project_id,"
|
||||
" body, mode, status, created_by, created_at,"
|
||||
" updated_at) VALUES(?, ?, ?, ?, ?, 'pending', ?, ?, ?)",
|
||||
(fu_id, task_id, task["project_id"], text, mode,
|
||||
user_id, now, now),
|
||||
)
|
||||
conn.commit()
|
||||
fu = _followup_to_dict(
|
||||
conn.execute(
|
||||
"SELECT * FROM task_followups WHERE id = ?",
|
||||
(fu_id,),
|
||||
).fetchone()
|
||||
)
|
||||
finally:
|
||||
conn.close()
|
||||
if mode == "direct":
|
||||
self._append_direct_trace(task, fu_id, text)
|
||||
with _auth_store(self.server.db_path) as store:
|
||||
store.audit(user_id, task["project_id"],
|
||||
"followup_created", "%s:%s" % (task_id, fu_id))
|
||||
self._send_json(201, fu)
|
||||
|
||||
def _append_direct_trace(self, task, fu_id, text):
|
||||
"""直接发送的消息立即进链路：往 host 的 jsonl 里追加一条
|
||||
message 条目（phase=followup-direct），运行中的链路流
|
||||
下一轮 poll 就能看到它。只尽力而为：worktree 在别机时
|
||||
本机文件不是 worker 写的那份，跳过（与 _trace_snapshot
|
||||
的多机降级同规则）；写失败也绝不让 POST 失败。"""
|
||||
try:
|
||||
worktree_host = task.get("worktree_host")
|
||||
if worktree_host and worktree_host != socket.gethostname():
|
||||
return
|
||||
d = _trace_dir_for(self.server)
|
||||
os.makedirs(d, exist_ok=True)
|
||||
entry = {"kind": "message", "id": "fu-" + fu_id,
|
||||
"ts": int(time.time() * 1000),
|
||||
"phase": "followup-direct", "text": text[:300]}
|
||||
with open(os.path.join(
|
||||
d, _trace_file_name(task["id"]) + ".jsonl"),
|
||||
"a", encoding="utf-8") as f:
|
||||
f.write(json.dumps(entry, ensure_ascii=False) + "\n")
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
def _list_followups(self, user_id, task_id):
|
||||
row = self._fetch_task(task_id)
|
||||
if row is None:
|
||||
self._send_json(404, {"error": "task not found"})
|
||||
return
|
||||
task = _task_to_dict(row)
|
||||
with _auth_store(self.server.db_path) as store:
|
||||
if not store.check_permission(
|
||||
user_id, task["project_id"], "read"):
|
||||
self._send_json(403, {"error": "forbidden"})
|
||||
return
|
||||
conn = self._db()
|
||||
try:
|
||||
_ensure_followups_table(conn)
|
||||
rows = conn.execute(
|
||||
"SELECT * FROM task_followups WHERE task_id = ?"
|
||||
" ORDER BY created_at, id",
|
||||
(task_id,),
|
||||
).fetchall()
|
||||
finally:
|
||||
conn.close()
|
||||
self._send_json(200, {
|
||||
"followups": [_followup_to_dict(r) for r in rows]})
|
||||
|
||||
def _fork_task(self, user_id, task_id):
|
||||
"""会话分支：从已结束任务的 thread 分叉出新任务。
|
||||
|
||||
新任务继承源任务的 executor/模型/强度/权限/计划模式，
|
||||
不继承 goal（分支是普通任务，首轮 prompt 就是这里传的
|
||||
message）。worker 认领后先调 host.py fork（分叉 thread
|
||||
历史 + 拷 worktree 文件），再以 message 跑首轮。
|
||||
只能从终态任务分支（进行中的 thread 正在变，分叉快照
|
||||
不可信）；message 必填——分支没有首条消息就没有方向。
|
||||
"""
|
||||
body, err = self._read_json()
|
||||
if err:
|
||||
self._send_json(400, {"error": err})
|
||||
return
|
||||
row = self._fetch_task(task_id)
|
||||
if row is None:
|
||||
self._send_json(404, {"error": "task not found"})
|
||||
return
|
||||
task = _task_to_dict(row)
|
||||
with _auth_store(self.server.db_path) as store:
|
||||
if not store.check_permission(
|
||||
user_id, task["project_id"], "create_task"):
|
||||
self._send_json(403, {"error": "forbidden"})
|
||||
return
|
||||
message = body.get("message")
|
||||
if not message or not isinstance(message, str) \
|
||||
or not message.strip():
|
||||
self._send_json(400, {"error": "message required"})
|
||||
return
|
||||
message = message.strip()
|
||||
if len(message) > 20000:
|
||||
self._send_json(400, {"error": "message too long"})
|
||||
return
|
||||
if task["status"] not in TERMINAL_STATUSES:
|
||||
self._send_json(409, {
|
||||
"error": "只能从已结束的任务分支",
|
||||
"status": task["status"],
|
||||
})
|
||||
return
|
||||
now = time.time()
|
||||
new_id = uuid.uuid4().hex
|
||||
conn = self._db()
|
||||
try:
|
||||
conn.execute(
|
||||
"INSERT INTO tasks(id, project_id, prompt, status,"
|
||||
" idempotency_key, depends_on, priority, created_by,"
|
||||
" created_at, updated_at, last_heartbeat, executor,"
|
||||
" goal, verify_command, goal_max_rounds,"
|
||||
" model, effort, approval, plan, forked_from)"
|
||||
" VALUES(?, ?, ?, 'queued', NULL, '[]', ?, ?, ?, ?,"
|
||||
" NULL, ?, NULL, NULL, ?, ?, ?, ?, ?, ?)",
|
||||
(new_id, task["project_id"], message, task["priority"],
|
||||
user_id, now, now, task["executor"],
|
||||
task["goal_max_rounds"] or 3, task["model"],
|
||||
task["effort"], task["approval"], task["plan"] or 0,
|
||||
task_id),
|
||||
)
|
||||
conn.commit()
|
||||
new_task = _task_to_dict(
|
||||
conn.execute(
|
||||
"SELECT * FROM tasks WHERE id = ?", (new_id,)
|
||||
).fetchone()
|
||||
)
|
||||
finally:
|
||||
conn.close()
|
||||
with _auth_store(self.server.db_path) as store:
|
||||
store.audit(user_id, task["project_id"], "task_forked",
|
||||
"%s -> %s" % (task_id, new_id))
|
||||
self._send_json(201, new_task)
|
||||
|
||||
def _cancel_task(self, user_id, task_id):
|
||||
row = self._fetch_task(task_id)
|
||||
if row is None:
|
||||
|
||||
Reference in new issue
Block a user