869 lines
35 KiB
Python
869 lines
35 KiB
Python
"""任务内标记工具（marker tools）：task-create / task-poll / task-read /
|
||
wait-threads / task-cancel / task-retry / todo-list / todo-create /
|
||
todo-update。
|
||
|
||
设计（与 peer_messages、task_spawn 同款原则，不另起一套）：
|
||
|
||
- agent 不用联网、不用凭证：agent 只在回合输出里写标记块，
|
||
可信的 worker 在 completed 轮次后解析并执行——本地与
|
||
Docker 执行器都通（两者都经 sandbox 的结果解析提取标记块，
|
||
与 task-message 同款）。
|
||
- 异步语义：写块 → 回合结束 → worker 执行 → 报告拼成后续
|
||
消息、下一轮才回到父任务。不是同轮函数返回；轮询与等待
|
||
在 worker 执行期间循环查库、占 worker 槽位（与协调员等齐
|
||
同款代价），超时或父任务被取消时中止。
|
||
- 只收不发：goal 任务与协调员任务不解析这些标记块。本批
|
||
工具是给“普通任务当项目经理、自己派生员工”那条路用的，
|
||
不是给协调员 PM 用的——协调员任务本身不跑模型回合，等齐
|
||
循环也不会在中途排空后续消息做判断。
|
||
- 拒绝只记报告与审计、不炸任务、不改目标状态：非法 JSON、
|
||
超长、超上限、跨项目、自操作、已终态、goal、已合并、门禁
|
||
不过，全部按“跳过 + 报告里写清原因”处理。
|
||
|
||
四个工具的分工，不要混：
|
||
|
||
- task-create：新建一个平级主线任务（不是子代理，也不是
|
||
fork）。新任务 prompt 由标记块给，不继承父任务的历史；
|
||
环境基线继承父任务的 environment_id，但 worker 会给它独立
|
||
的 tenant/worktree，不动父任务的 cwd。父任务未提交的改动
|
||
不会自动带过去。模型/强度继承优先级：块里显式写 >
|
||
父任务的 child_model / child_effort（派生默认）> 父任务
|
||
自身的 model / effort > worker 默认（NULL 时由认领方补）。
|
||
子任务行上同时记下父任务的 child_model / child_effort，
|
||
这样隔代派生时派生默认仍然沿用，不会因为中间一层没写
|
||
就丢回 worker 默认。
|
||
- task-poll / task-read：按任务 id 轮询阅读。task-poll 按
|
||
interval 查库直到终态或超时；task-read 是同款别名，
|
||
不传 wait_seconds 时立即读一次快照，传了则等这么久再读
|
||
一次。read-thread / read_thread 是同款别名。
|
||
- wait-threads：一次等多个目标任务，并行查库（每轮查一次
|
||
全部目标，不是逐个串行等超时相加），全部终态或超时后把
|
||
每目标快照一起排回父任务。
|
||
- task-cancel / task-retry：对已存在的任务做取消 / 重试。
|
||
取消复用 worker 现有的取消路径语义（取消后状态为
|
||
interrupted）；重试与服务端 POST /tasks/{id}/retry 对齐
|
||
（仅 failed / interrupted / merge-failed 可重试，重试时
|
||
清空上一轮 result_text / error_text / actual_model、状态
|
||
回 queued、prompt 与模型等原样保留）。
|
||
- todo-list / todo-create / todo-update：项目待办的读与写，
|
||
直接复用 todos 模块的校验与状态机（completed 记
|
||
completed_at、离开 completed 清掉）。todo-list 不传 status
|
||
时只返回未完成项（pending / in_progress / blocked），
|
||
查已完成项须显式传 status；写操作只在本项目内生效，
|
||
跨项目待办一律按“不存在”拒绝；删除不走标记块（硬删除
|
||
只在控制台 / REST DELETE 里做，避免模型误删整条）。
|
||
|
||
上限口径（本模块最终定的值，文档与代码一致）：
|
||
|
||
- 每轮创建、轮询、取消、重试各最多 5 块；todo-list、
|
||
todo-create、todo-update 各最多 5 块；wait 每轮最多
|
||
2 块，每块最多 8 个目标。8 这个数是刻意与服务端
|
||
POST /tasks/{id}/wait 的“一次最多 8 个线程”对齐的；
|
||
spawn 分支原先的每块 10 个在此收紧到 8 个，不要再用 10。
|
||
- 超时口径与服务端 /wait 不同，且是故意的：服务端 /wait
|
||
是给外部调用方持 HTTP 连接等的，上限 120 秒；标记 wait
|
||
是 worker 在回合后直连库循环查，不持 HTTP 连接，超时
|
||
钳制与 task-poll 同款（0-3600 秒，0 = 立即快照），占的
|
||
是 worker 槽位而不是 HTTP 连接。两者不要混用、不要互抄
|
||
上限。
|
||
- 派生护栏：创建 prompt 1-20000 字，name 可选 1-100 字
|
||
（仅用于派生报告，tasks 表没有 name 列，不落库）；
|
||
model 不做白名单；effort 必须是 codex 的 effort 档位；
|
||
executor 必须是 local / docker / cloud，未指定时继承父任务；
|
||
派生深度上限 3 代、单个父任务直接派生上限 20 个。
|
||
|
||
门禁（task-cancel / task-retry，纯函数层 + worker 权限层）：
|
||
|
||
- 纯函数层（本模块 check_control_gate）：目标存在、同项目、
|
||
非自己、非 goal、状态符合 kind（取消要求非终态，重试
|
||
要求仅三态）、关系为派生链内或同创建人，二选一满足即可。
|
||
“同项目猜到 id 就能取消任何人的任务”在此被挡住。
|
||
- worker 权限层（worker.py _deliver_marker_tools）：取消要求
|
||
发送方创建人有项目 create_task 权限（与服务端取消口径
|
||
同款），重试要求有 approve_merge 权限（与服务端重试口
|
||
径同款）。权限检查本身抛异常时收紧到仅派生链内可用，
|
||
同创建人-only 的目标一律拒绝，并把原因写进报告——绝不
|
||
在查不到权限时静默放宽。
|
||
|
||
本模块只依赖标准库，不 import cloud 其它模块，避免循环
|
||
import。DB 助手函数只用 ? 占位符，与 peer_messages 同款写法。
|
||
"""
|
||
|
||
import json
|
||
import re
|
||
import time
|
||
import uuid
|
||
|
||
MAX_CREATES_PER_TURN = 5
|
||
MAX_POLLS_PER_TURN = 5
|
||
MAX_WAITS_PER_TURN = 2
|
||
MAX_WAIT_TARGETS_PER_BLOCK = 8
|
||
MAX_CONTROLS_PER_TURN = 5
|
||
MAX_PROMPT_CHARS = 20000
|
||
MAX_NAME_CHARS = 100
|
||
MAX_SPAWN_DEPTH = 3
|
||
MAX_DIRECT_CHILDREN = 20
|
||
DEFAULT_POLL_INTERVAL_SECONDS = 5
|
||
DEFAULT_POLL_TIMEOUT_SECONDS = 300
|
||
MAX_POLL_TIMEOUT_SECONDS = 3600
|
||
DEFAULT_SNAPSHOT_CHARS = 2000
|
||
MAX_SNAPSHOT_CHARS = 8000
|
||
TERMINAL_STATUSES = ("completed", "failed", "interrupted", "merged",
|
||
"merge-failed")
|
||
RETRYABLE_STATUSES = ("failed", "interrupted", "merge-failed")
|
||
EFFORTS = ("low", "medium", "high", "xhigh", "max")
|
||
EXECUTORS = ("local", "docker", "cloud")
|
||
TODO_STATUSES = ("pending", "in_progress", "blocked", "completed",
|
||
"cancelled")
|
||
TODO_PRIORITIES = ("low", "medium", "high")
|
||
MAX_TODO_LISTS_PER_TURN = 5
|
||
MAX_TODO_CREATES_PER_TURN = 5
|
||
MAX_TODO_UPDATES_PER_TURN = 5
|
||
MAX_TODO_TITLE_CHARS = 500
|
||
MAX_TODO_DESCRIPTION_CHARS = 20000
|
||
MAX_TODO_QUERY_CHARS = 500
|
||
|
||
_CREATE_RE = re.compile(r"```task-create\s*\n(.*?)\n```", re.DOTALL)
|
||
_POLL_RE = re.compile(
|
||
r"```(task-poll|task_poll|task-read|task_read|read-thread|read_thread)"
|
||
r"\s*\n(.*?)\n```", re.DOTALL)
|
||
_WAIT_RE = re.compile(r"```(wait-threads|wait_threads)\s*\n(.*?)\n```",
|
||
re.DOTALL)
|
||
_CANCEL_RE = re.compile(r"```(task-cancel|task_cancel)\s*\n(.*?)\n```",
|
||
re.DOTALL)
|
||
_RETRY_RE = re.compile(r"```(task-retry|task_retry)\s*\n(.*?)\n```",
|
||
re.DOTALL)
|
||
_TODO_LIST_RE = re.compile(
|
||
r"```(todo-list|todo_list)\s*\n(.*?)\n```", re.DOTALL)
|
||
_TODO_CREATE_RE = re.compile(
|
||
r"```(todo-create|todo_create)\s*\n(.*?)\n```", re.DOTALL)
|
||
_TODO_UPDATE_RE = re.compile(
|
||
r"```(todo-update|todo_update)\s*\n(.*?)\n```", re.DOTALL)
|
||
|
||
|
||
def row_get(row, name):
|
||
"""与 peer_messages.row_get 同款容错取值。"""
|
||
try:
|
||
return row[name]
|
||
except (KeyError, IndexError, TypeError):
|
||
return None
|
||
|
||
|
||
def _as_int(value, default):
|
||
if isinstance(value, bool):
|
||
return default
|
||
if isinstance(value, int):
|
||
return value
|
||
if isinstance(value, float) and value.is_integer():
|
||
return int(value)
|
||
return default
|
||
|
||
|
||
def _clamp(value, low, high, default):
|
||
value = _as_int(value, default)
|
||
if value < low:
|
||
return low
|
||
if value > high:
|
||
return high
|
||
return value
|
||
|
||
|
||
def extract_task_creates(text):
|
||
"""提取 task-create 块；prompt 缺失/空串/超长、name 超长、
|
||
effort/executor 非法时整块跳过；每轮最多 5 块；正文里的围栏
|
||
会把块截断成非法 JSON 而被跳过（与 task-message 同款非贪婪
|
||
匹配）。"""
|
||
if not text:
|
||
return []
|
||
out = []
|
||
for match in _CREATE_RE.finditer(str(text)):
|
||
if len(out) >= MAX_CREATES_PER_TURN:
|
||
break
|
||
try:
|
||
payload = json.loads(match.group(1))
|
||
except (TypeError, ValueError):
|
||
continue
|
||
if not isinstance(payload, dict):
|
||
continue
|
||
prompt = payload.get("prompt")
|
||
if not isinstance(prompt, str) or not prompt.strip():
|
||
continue
|
||
prompt = prompt.strip()
|
||
if len(prompt) > MAX_PROMPT_CHARS:
|
||
continue
|
||
name = payload.get("name")
|
||
if name is not None:
|
||
if not isinstance(name, str) or not name.strip():
|
||
continue
|
||
name = name.strip()
|
||
if len(name) > MAX_NAME_CHARS:
|
||
continue
|
||
model = payload.get("model")
|
||
if model is not None:
|
||
if not isinstance(model, str) or not model.strip():
|
||
continue
|
||
model = model.strip()
|
||
effort = payload.get("effort")
|
||
if effort is not None and effort not in EFFORTS:
|
||
continue
|
||
executor = payload.get("executor")
|
||
if executor is not None and executor not in EXECUTORS:
|
||
continue
|
||
out.append({"name": name, "prompt": prompt, "model": model,
|
||
"effort": effort, "executor": executor})
|
||
return out
|
||
|
||
|
||
def _todo_due_at(value):
|
||
"""标记块 due_at 校验：与 todos._validate_due_at 同款语义
|
||
（epoch 秒，>=1e11 按毫秒除 1000）；非法返回 (False, None)，
|
||
不在本层抛异常——非法块整块跳过。"""
|
||
if value is None or value == "":
|
||
return True, None
|
||
if isinstance(value, bool) or not isinstance(value, (int, float)):
|
||
return False, None
|
||
value = float(value)
|
||
if value >= 1e11:
|
||
value = value / 1000.0
|
||
return True, value
|
||
|
||
|
||
def extract_todo_lists(text):
|
||
"""提取 todo-list 块；不传 status 时查未完成项（pending /
|
||
in_progress / blocked），不返回 completed / cancelled——
|
||
报告要短，查已完成项须显式传 status。status 非法、q 非
|
||
字符串或超长时整块跳过；每轮最多 5 块。"""
|
||
if not text:
|
||
return []
|
||
out = []
|
||
for match in _TODO_LIST_RE.finditer(str(text)):
|
||
if len(out) >= MAX_TODO_LISTS_PER_TURN:
|
||
break
|
||
try:
|
||
payload = json.loads(match.group(2))
|
||
except (TypeError, ValueError):
|
||
continue
|
||
if not isinstance(payload, dict):
|
||
continue
|
||
status = payload.get("status")
|
||
if status is not None and status not in TODO_STATUSES:
|
||
continue
|
||
q = payload.get("q")
|
||
if q is not None:
|
||
if not isinstance(q, str) or not q.strip():
|
||
continue
|
||
q = q.strip()
|
||
if len(q) > MAX_TODO_QUERY_CHARS:
|
||
continue
|
||
out.append({"status": status, "q": q})
|
||
return out
|
||
|
||
|
||
def extract_todo_creates(text):
|
||
"""提取 todo-create 块；title 必填 1-500 字，description
|
||
可选 <=20000 字，status / priority 只能是枚举值，task_id
|
||
只能是字符串，due_at 按 _todo_due_at 校验；任一项非法时
|
||
整块跳过；每轮最多 5 块。"""
|
||
if not text:
|
||
return []
|
||
out = []
|
||
for match in _TODO_CREATE_RE.finditer(str(text)):
|
||
if len(out) >= MAX_TODO_CREATES_PER_TURN:
|
||
break
|
||
try:
|
||
payload = json.loads(match.group(2))
|
||
except (TypeError, ValueError):
|
||
continue
|
||
if not isinstance(payload, dict):
|
||
continue
|
||
title = payload.get("title")
|
||
if not isinstance(title, str) or not title.strip():
|
||
continue
|
||
title = title.strip()
|
||
if len(title) > MAX_TODO_TITLE_CHARS:
|
||
continue
|
||
description = payload.get("description")
|
||
if description is not None:
|
||
if not isinstance(description, str):
|
||
continue
|
||
if len(description) > MAX_TODO_DESCRIPTION_CHARS:
|
||
continue
|
||
status = payload.get("status")
|
||
if status is not None and status not in TODO_STATUSES:
|
||
continue
|
||
priority = payload.get("priority")
|
||
if priority is not None and priority not in TODO_PRIORITIES:
|
||
continue
|
||
task_id = payload.get("task_id")
|
||
if task_id is not None:
|
||
if not isinstance(task_id, str):
|
||
continue
|
||
task_id = task_id.strip() or None
|
||
ok, due_at = _todo_due_at(payload.get("due_at"))
|
||
if not ok:
|
||
continue
|
||
sort_order = payload.get("sort_order")
|
||
if sort_order is not None and (
|
||
isinstance(sort_order, bool)
|
||
or not isinstance(sort_order, int)):
|
||
continue
|
||
out.append({"title": title, "description": description,
|
||
"status": status, "priority": priority,
|
||
"task_id": task_id, "due_at": due_at,
|
||
"sort_order": sort_order})
|
||
return out
|
||
|
||
|
||
def extract_todo_updates(text):
|
||
"""提取 todo-update 块；id 必填，至少改一个字段；各字段
|
||
校验与 todo-create 同款（status / priority 枚举、title
|
||
1-500 字、description <=20000 字、due_at 毫秒容忍、
|
||
sort_order 整数）；任一项非法或无有效字段时整块跳过；
|
||
每轮最多 5 块。未知字段忽略，不因此跳过。"""
|
||
if not text:
|
||
return []
|
||
out = []
|
||
for match in _TODO_UPDATE_RE.finditer(str(text)):
|
||
if len(out) >= MAX_TODO_UPDATES_PER_TURN:
|
||
break
|
||
try:
|
||
payload = json.loads(match.group(2))
|
||
except (TypeError, ValueError):
|
||
continue
|
||
if not isinstance(payload, dict):
|
||
continue
|
||
todo_id = payload.get("id")
|
||
if not isinstance(todo_id, str) or not todo_id.strip():
|
||
continue
|
||
fields = {}
|
||
if "title" in payload:
|
||
title = payload["title"]
|
||
if not isinstance(title, str) or not title.strip():
|
||
continue
|
||
title = title.strip()
|
||
if len(title) > MAX_TODO_TITLE_CHARS:
|
||
continue
|
||
fields["title"] = title
|
||
if "description" in payload:
|
||
description = payload["description"]
|
||
if not isinstance(description, str):
|
||
continue
|
||
if len(description) > MAX_TODO_DESCRIPTION_CHARS:
|
||
continue
|
||
fields["description"] = description
|
||
if "status" in payload:
|
||
if payload["status"] not in TODO_STATUSES:
|
||
continue
|
||
fields["status"] = payload["status"]
|
||
if "priority" in payload:
|
||
if payload["priority"] not in TODO_PRIORITIES:
|
||
continue
|
||
fields["priority"] = payload["priority"]
|
||
if "task_id" in payload:
|
||
task_id = payload["task_id"]
|
||
if task_id is not None and not isinstance(task_id, str):
|
||
continue
|
||
fields["task_id"] = (task_id.strip() or None
|
||
if isinstance(task_id, str) else None)
|
||
if "due_at" in payload:
|
||
ok, due_at = _todo_due_at(payload["due_at"])
|
||
if not ok:
|
||
continue
|
||
fields["due_at"] = due_at
|
||
if "sort_order" in payload:
|
||
sort_order = payload["sort_order"]
|
||
if sort_order is not None and (
|
||
isinstance(sort_order, bool)
|
||
or not isinstance(sort_order, int)):
|
||
continue
|
||
if sort_order is not None:
|
||
fields["sort_order"] = sort_order
|
||
if not fields:
|
||
continue
|
||
out.append({"id": todo_id.strip(), "fields": fields})
|
||
return out
|
||
|
||
|
||
_SPAWN_SUBJECT_ZH = ("新建的任务", "派生任务", "新建任务",
|
||
"子任务", "子代理", "新任务", "新会话")
|
||
_SPAWN_SUBJECT_EN = ("child tasks", "spawned tasks", "new tasks",
|
||
"new sessions", "subtasks", "subtask",
|
||
"child task", "new task", "new session")
|
||
|
||
|
||
def _effort_after(text, start):
|
||
"""在 model 后的同一子句里找强度：先找“强度/effort + 值”，
|
||
再找紧跟 model 的裸强度词（如“gpt-6-luna max”）。子句以
|
||
句号/换行/分号截断，跨子句的强度词不算，避免把下一句的
|
||
词误当成这一句的强度。"""
|
||
clause = str(text)[start:start + 60]
|
||
for stop in ("。", "\n", "；", ";"):
|
||
cut = clause.find(stop)
|
||
if cut >= 0:
|
||
clause = clause[:cut]
|
||
labelled = re.search(
|
||
r"(?:强度|effort)\s*[：:=\s]\s*(low|medium|high|xhigh|max)",
|
||
clause, re.IGNORECASE)
|
||
if labelled:
|
||
return labelled.group(1).lower()
|
||
trailing = re.search(
|
||
r"^\s*[，,、\s]*(low|medium|high|xhigh|max)\b",
|
||
clause, re.IGNORECASE)
|
||
if trailing:
|
||
return trailing.group(1).lower()
|
||
return None
|
||
|
||
|
||
def _model_from_match(text, match, token_group):
|
||
"""从一次正则命中里取 (model, effort)：model 词本身若是
|
||
强度词（如“子任务用 max”），只当强度、不当模型；模型词
|
||
尾部的句点是句子标点、不是模型名的一部分，要去掉。"""
|
||
token = match.group(token_group).rstrip(".")
|
||
if not token:
|
||
return None, None
|
||
if token.lower() in EFFORTS:
|
||
return None, token.lower()
|
||
return token, _effort_after(text, match.end(token_group))
|
||
|
||
|
||
def parse_spawn_defaults(text):
|
||
"""从主线 prompt 里解析派生默认模型/强度，只认显式指令。
|
||
|
||
认的句式（主语必须是派生对象，裸说“主线用 X”不算，
|
||
那是本任务自己的模型、应走建任务的 model 字段）：
|
||
- 中文：子任务/子代理/派生任务/新建任务/新任务/新会话 +
|
||
用/使用/采用/模型：/模型是 + 模型词，可跟强度词或
|
||
“强度/effort + 强度词”，如“子代理用 gpt-6-luna max”、
|
||
“子任务模型：gpt-6-luna，强度：max”。
|
||
- 英文：subtask/child task/spawned task/new task/session +
|
||
use/using/with model/model: + 模型词，如
|
||
“subtasks use gpt-6-luna with effort max”。
|
||
- 中文倒装：用 + 模型词 + … + 子任务/子代理，如
|
||
“用 gpt-6-luna max 跑子任务”。
|
||
只取第一条命中；模型词只认 ASCII 词（中转模型 id 都是
|
||
ASCII），“用默认模型”这类中文词不会被误当成模型。
|
||
显式传了 child_model / child_effort 的任务不走本函数，
|
||
本函数只在建任务时两者缺省才作兜底，且结果落在任务行
|
||
的 child_model / child_effort 上、调用方可直接检查。
|
||
返回 dict，只含解析到的键（都没解析到时为空 dict）。"""
|
||
if not text:
|
||
return {}
|
||
text = str(text)
|
||
zh_subject = "|".join(_SPAWN_SUBJECT_ZH)
|
||
zh_pattern = re.compile(
|
||
r"(?:%s)[^。\n；;]{0,50}?(?:用\s*|使用\s*|采用\s*"
|
||
r"|模型\s*[：:]\s*|模型\s*是\s*)"
|
||
r"([A-Za-z][A-Za-z0-9._-]{1,63})" % zh_subject)
|
||
match = zh_pattern.search(text)
|
||
if match:
|
||
model, effort = _model_from_match(text, match, 1)
|
||
out = {}
|
||
if model:
|
||
out["model"] = model
|
||
if effort:
|
||
out["effort"] = effort
|
||
if out:
|
||
return out
|
||
en_subject = "|".join(_SPAWN_SUBJECT_EN)
|
||
en_pattern = re.compile(
|
||
r"(?:%s)\b[^.\n]{0,50}?(?:use\s+|using\s+|with\s+model\s+"
|
||
r"|model\s*[:=]\s*)"
|
||
r"([A-Za-z][A-Za-z0-9._-]{1,63})" % en_subject,
|
||
re.IGNORECASE)
|
||
match = en_pattern.search(text)
|
||
if match:
|
||
model, effort = _model_from_match(text, match, 1)
|
||
out = {}
|
||
if model:
|
||
out["model"] = model
|
||
if effort:
|
||
out["effort"] = effort
|
||
if out:
|
||
return out
|
||
rev_pattern = re.compile(
|
||
r"(?:用|使用|采用)\s*([A-Za-z][A-Za-z0-9._-]{1,63})"
|
||
r"[^。\n；;]{0,30}?(?:%s)" % zh_subject)
|
||
match = rev_pattern.search(text)
|
||
if match:
|
||
model, effort = _model_from_match(text, match, 1)
|
||
out = {}
|
||
if model:
|
||
out["model"] = model
|
||
if effort:
|
||
out["effort"] = effort
|
||
if out:
|
||
return out
|
||
return {}
|
||
|
||
|
||
def extract_task_polls(text):
|
||
"""提取 task-poll / task-read（含 read-thread 别名）块。
|
||
|
||
task-read 不传 wait_seconds 时立即读一次快照（timeout=0）；
|
||
传了则等这么久再读一次。interval 钳制 1-60 秒，timeout
|
||
钳制 0-3600 秒，chars 钳制 200-8000 字；各类块合计每轮
|
||
最多 5 块，多余的忽略。"""
|
||
if not text:
|
||
return []
|
||
out = []
|
||
for match in _POLL_RE.finditer(str(text)):
|
||
if len(out) >= MAX_POLLS_PER_TURN:
|
||
break
|
||
kind, raw = match.group(1), match.group(2)
|
||
try:
|
||
payload = json.loads(raw)
|
||
except (TypeError, ValueError):
|
||
continue
|
||
if not isinstance(payload, dict):
|
||
continue
|
||
task_id = payload.get("task_id") or payload.get("to") \
|
||
or payload.get("to_task_id")
|
||
if not isinstance(task_id, str) or not task_id.strip():
|
||
continue
|
||
chars = _clamp(payload.get("chars"), 200, MAX_SNAPSHOT_CHARS,
|
||
DEFAULT_SNAPSHOT_CHARS)
|
||
if kind in ("task-read", "task_read", "read-thread",
|
||
"read_thread"):
|
||
wait = payload.get("wait_seconds")
|
||
if wait is None:
|
||
interval = DEFAULT_POLL_INTERVAL_SECONDS
|
||
timeout = 0
|
||
else:
|
||
timeout = _clamp(wait, 0, MAX_POLL_TIMEOUT_SECONDS, 0)
|
||
interval = timeout if timeout > 0 \
|
||
else DEFAULT_POLL_INTERVAL_SECONDS
|
||
else:
|
||
interval = _clamp(payload.get("interval_seconds"), 1, 60,
|
||
DEFAULT_POLL_INTERVAL_SECONDS)
|
||
timeout = _clamp(payload.get("timeout_seconds"), 0,
|
||
MAX_POLL_TIMEOUT_SECONDS,
|
||
DEFAULT_POLL_TIMEOUT_SECONDS)
|
||
out.append({"task_id": task_id.strip(),
|
||
"interval_seconds": interval,
|
||
"timeout_seconds": timeout, "chars": chars})
|
||
return out
|
||
|
||
|
||
def extract_wait_threads(text):
|
||
"""提取 wait-threads / wait_threads 块：一次等多个目标。
|
||
|
||
块格式::
|
||
|
||
```wait-threads
|
||
{"task_ids": ["B", "C"], "interval_seconds": 5,
|
||
"timeout_seconds": 300, "chars": 2000}
|
||
```
|
||
|
||
task_ids 也接受 thread_ids / threads 两个别名。去重保序，
|
||
每块最多 8 个目标（与服务端 /wait 口径对齐，见模块头），
|
||
每轮最多 2 块；无有效 id 的块跳过。interval 钳制 1-60 秒，
|
||
timeout 钳制 0-3600 秒（worker 直连库口径，见模块头），
|
||
chars 钳制 200-8000 字。"""
|
||
if not text:
|
||
return []
|
||
out = []
|
||
for match in _WAIT_RE.finditer(str(text)):
|
||
if len(out) >= MAX_WAITS_PER_TURN:
|
||
break
|
||
try:
|
||
payload = json.loads(match.group(2))
|
||
except (TypeError, ValueError):
|
||
continue
|
||
if not isinstance(payload, dict):
|
||
continue
|
||
raw_ids = (payload.get("task_ids") or payload.get("thread_ids")
|
||
or payload.get("threads"))
|
||
if not isinstance(raw_ids, list):
|
||
continue
|
||
ids = []
|
||
for tid in raw_ids:
|
||
if isinstance(tid, str) and tid.strip() \
|
||
and tid.strip() not in ids:
|
||
ids.append(tid.strip())
|
||
if not ids:
|
||
continue
|
||
ids = ids[:MAX_WAIT_TARGETS_PER_BLOCK]
|
||
out.append({
|
||
"task_ids": ids,
|
||
"interval_seconds": _clamp(
|
||
payload.get("interval_seconds"), 1, 60,
|
||
DEFAULT_POLL_INTERVAL_SECONDS),
|
||
"timeout_seconds": _clamp(
|
||
payload.get("timeout_seconds"), 0,
|
||
MAX_POLL_TIMEOUT_SECONDS, DEFAULT_POLL_TIMEOUT_SECONDS),
|
||
"chars": _clamp(payload.get("chars"), 200,
|
||
MAX_SNAPSHOT_CHARS, DEFAULT_SNAPSHOT_CHARS),
|
||
})
|
||
return out
|
||
|
||
|
||
def _extract_controls(text, regex):
|
||
"""提取 task-cancel / task-retry 块的公共逻辑。
|
||
|
||
task_id 缺失/空串时整块跳过；to / to_task_id / thread_id
|
||
是同款别名；每种每轮最多 5 块，多余的忽略。"""
|
||
if not text:
|
||
return []
|
||
out = []
|
||
for match in regex.finditer(str(text)):
|
||
if len(out) >= MAX_CONTROLS_PER_TURN:
|
||
break
|
||
try:
|
||
payload = json.loads(match.group(2))
|
||
except (TypeError, ValueError):
|
||
continue
|
||
if not isinstance(payload, dict):
|
||
continue
|
||
task_id = (payload.get("task_id") or payload.get("to")
|
||
or payload.get("to_task_id")
|
||
or payload.get("thread_id"))
|
||
if not isinstance(task_id, str) or not task_id.strip():
|
||
continue
|
||
out.append({"task_id": task_id.strip()})
|
||
return out
|
||
|
||
|
||
def extract_task_cancels(text):
|
||
"""提取 task-cancel 块：{"task_id": "..."}。"""
|
||
return _extract_controls(text, _CANCEL_RE)
|
||
|
||
|
||
def extract_task_retries(text):
|
||
"""提取 task-retry 块：{"task_id": "..."}。"""
|
||
return _extract_controls(text, _RETRY_RE)
|
||
|
||
|
||
def parent_spawn_generation(conn, parent_id):
|
||
"""父任务自身的派生代数：普通任务 0，第一代派生任务 1，依此类推。
|
||
|
||
只数 parent_task_id 非空且 coordinator_part 为空的祖先链（即
|
||
派生链）；协调员子任务（coordinator_part 非空）本身不是派生
|
||
任务，代数为 0，链到此为止。走 32 步仍未到头时按已数到的算，
|
||
绝不死循环。"""
|
||
generation = 0
|
||
cur = parent_id
|
||
for _ in range(32):
|
||
if not cur:
|
||
break
|
||
row = conn.execute(
|
||
"SELECT parent_task_id, coordinator_part FROM tasks"
|
||
" WHERE id = ?", (cur,)).fetchone()
|
||
if row is None:
|
||
break
|
||
parent = row_get(row, "parent_task_id")
|
||
part = row_get(row, "coordinator_part")
|
||
if parent is not None and part is None:
|
||
generation += 1
|
||
cur = parent
|
||
continue
|
||
break
|
||
return generation
|
||
|
||
|
||
def count_direct_spawn_children(conn, parent_id):
|
||
"""单个父任务的直接派生子任务数（不含协调员子任务）。"""
|
||
row = conn.execute(
|
||
"SELECT COUNT(*) FROM tasks WHERE parent_task_id = ?"
|
||
" AND coordinator_part IS NULL", (parent_id,)).fetchone()
|
||
try:
|
||
return int(row[0]) if row is not None else 0
|
||
except (TypeError, ValueError, IndexError):
|
||
return 0
|
||
|
||
|
||
def fetch_task_snapshot(conn, task_id):
|
||
"""取目标任务的快照行；不存在时回 None。
|
||
|
||
用 SELECT * 而不是列清单：老库/最小测试表缺列时 row_get
|
||
容错回 None，不炸；门禁要用的 created_by / parent_task_id /
|
||
coordinator_part / verify_command / goal_mode 一并带上。"""
|
||
row = conn.execute(
|
||
"SELECT * FROM tasks WHERE id = ?", (task_id,)).fetchone()
|
||
if row is None:
|
||
return None
|
||
return {"id": row_get(row, "id"),
|
||
"project_id": row_get(row, "project_id"),
|
||
"status": row_get(row, "status"),
|
||
"result_text": row_get(row, "result_text"),
|
||
"error_text": row_get(row, "error_text"),
|
||
"executor": row_get(row, "executor"),
|
||
"model": row_get(row, "model"),
|
||
"actual_model": row_get(row, "actual_model"),
|
||
"turn_id": row_get(row, "turn_id"),
|
||
"last_heartbeat": row_get(row, "last_heartbeat"),
|
||
"worktree_host": row_get(row, "worktree_host"),
|
||
"pr_url": row_get(row, "pr_url"),
|
||
"pr_number": row_get(row, "pr_number"),
|
||
"environment_id": row_get(row, "environment_id"),
|
||
"created_by": row_get(row, "created_by"),
|
||
"parent_task_id": row_get(row, "parent_task_id"),
|
||
"coordinator_part": row_get(row, "coordinator_part"),
|
||
"verify_command": row_get(row, "verify_command"),
|
||
"goal_mode": row_get(row, "goal_mode")}
|
||
|
||
|
||
def ancestry_relation(conn, sender, target):
|
||
"""发送方与目标的关系：descendant / same_creator / other。
|
||
|
||
descendant：沿目标的 parent_task_id 链（最多 32 步）能追溯
|
||
到发送方（直接派生、隔代派生都算；协调员子任务的链到
|
||
协调员为止，不会穿过协调员再往上算——因为协调员子任务的
|
||
coordinator_part 非空，链在此处按派生链定义截断，见
|
||
parent_spawn_generation 的同款处理；但本函数走的是
|
||
parent_task_id 原始链，目标本身若是协调员子任务、其父
|
||
是协调员时，发送方若恰好是该协调员也会算 descendant——
|
||
协调员任务不解析标记块，所以发送方不可能是协调员，
|
||
这一支在实际调用里到不了，不影响门禁）。
|
||
same_creator：链上追不到，但目标 created_by 与发送方
|
||
created_by 相同且非空。
|
||
other：两者都不是。"""
|
||
sender_id = (sender or {}).get("id")
|
||
target_parent = (target or {}).get("parent_task_id")
|
||
cur = target_parent
|
||
for _ in range(32):
|
||
if not cur:
|
||
break
|
||
if cur == sender_id:
|
||
return "descendant"
|
||
row = conn.execute(
|
||
"SELECT parent_task_id FROM tasks WHERE id = ?",
|
||
(cur,)).fetchone()
|
||
if row is None:
|
||
break
|
||
cur = row_get(row, "parent_task_id")
|
||
sender_creator = (sender or {}).get("created_by")
|
||
target_creator = (target or {}).get("created_by")
|
||
if sender_creator and target_creator \
|
||
and sender_creator == target_creator:
|
||
return "same_creator"
|
||
return "other"
|
||
|
||
|
||
def is_goal_task(task):
|
||
"""goal 任务判定：verify_command 非空或 goal_mode 为真。
|
||
|
||
与 worker run_one 的 goal 分支同款（verify_command 或
|
||
goal_mode）；goal 字段本身是 goal_mode=1 时 prompt 的副本，
|
||
不单独当判定条件，避免把普通任务的 goal 文本误判。"""
|
||
if not task:
|
||
return False
|
||
return bool(task.get("verify_command") or task.get("goal_mode"))
|
||
|
||
|
||
def check_control_gate(target, sender, relation, kind):
|
||
"""task-cancel / task-retry 的纯函数门禁，返回 (ok, reason)。
|
||
|
||
kind 只能是 "cancel" 或 "retry"，其它值一律拒绝。权限层
|
||
不在这里：worker 侧另查 create_task / approve_merge，见
|
||
模块头；本函数只管目标状态与关系，单测不需要 AuthStore。"""
|
||
if kind not in ("cancel", "retry"):
|
||
return False, "未知的控制操作"
|
||
if target is None:
|
||
return False, "目标任务不存在"
|
||
if (target.get("project_id") is not None
|
||
and sender.get("project_id") is not None
|
||
and target.get("project_id") != sender.get("project_id")):
|
||
return False, "跨项目任务不可操作"
|
||
if target.get("id") == sender.get("id"):
|
||
return False, "不能操作自己"
|
||
if is_goal_task(target):
|
||
return False, "goal 任务不可取消或重试（goal 循环自有轮次）"
|
||
status = target.get("status")
|
||
if kind == "cancel":
|
||
if status in TERMINAL_STATUSES:
|
||
return False, "目标已终态（%s），不可取消" % status
|
||
else:
|
||
if status not in RETRYABLE_STATUSES:
|
||
return False, ("仅 failed / interrupted / merge-failed"
|
||
" 可重试，当前状态为 %s" % status)
|
||
if relation not in ("descendant", "same_creator"):
|
||
return False, "目标不在发送方派生链上且创建人不同"
|
||
return True, ""
|
||
|
||
|
||
def _heartbeat_age_text(snapshot, now=None):
|
||
"""最后心跳距今秒数，无心跳时回空串（不编造）。"""
|
||
hb = snapshot.get("last_heartbeat")
|
||
if hb is None:
|
||
return ""
|
||
try:
|
||
age = int((now if now is None else now) - float(hb))
|
||
except (TypeError, ValueError):
|
||
return ""
|
||
if age < 0:
|
||
age = 0
|
||
return "%d 秒前" % age
|
||
|
||
|
||
def _progress_lines(snapshot, now=None):
|
||
"""快照的进度行：执行器、模型、工作树主机、心跳、turn。"""
|
||
lines = []
|
||
if snapshot.get("executor"):
|
||
lines.append("执行器：%s" % snapshot["executor"])
|
||
model = snapshot.get("actual_model") or snapshot.get("model")
|
||
if model:
|
||
lines.append("模型：%s" % model)
|
||
if snapshot.get("worktree_host"):
|
||
lines.append("工作树主机：%s" % snapshot["worktree_host"])
|
||
age = _heartbeat_age_text(snapshot, now=now)
|
||
if age:
|
||
lines.append("最后心跳：%s" % age)
|
||
if snapshot.get("turn_id"):
|
||
lines.append("回合：%s" % snapshot["turn_id"])
|
||
return lines
|
||
|
||
|
||
def format_snapshot(snapshot, chars, timed_out=False, cancelled=False):
|
||
"""把快照格式化成给父任务下一轮的报告正文（截断防上下文爆炸）。"""
|
||
task_id = snapshot["id"]
|
||
status = snapshot["status"] or "?"
|
||
lines = ["[任务 %s]" % task_id, "状态：%s" % status]
|
||
lines.extend(_progress_lines(snapshot))
|
||
if cancelled:
|
||
lines.append("说明：等待期间父任务被取消，轮询已中止。")
|
||
elif timed_out:
|
||
lines.append("说明：等待超时，目标任务仍未终态，可再轮询一次。")
|
||
elif status in TERMINAL_STATUSES:
|
||
result = (snapshot["result_text"] or "").strip()
|
||
error = (snapshot["error_text"] or "").strip()
|
||
if result:
|
||
lines.append("结果：%s" % result[:chars])
|
||
if error:
|
||
lines.append("错误：%s" % error[:chars])
|
||
if not result and not error:
|
||
lines.append("结果：（空）")
|
||
else:
|
||
lines.append("说明：目标任务仍在运行或排队，可再轮询一次。")
|
||
return "\n".join(lines)
|
||
|
||
|
||
def new_child_id():
|
||
return uuid.uuid4().hex
|
||
|
||
|
||
def marker_report_header():
|
||
return "[任务工具报告]"
|
||
|
||
|
||
def format_todo(todo, max_title=100):
|
||
"""待办单行（报告与首轮注入共用）：状态 + 标题（截断）+ id +
|
||
优先级，due_at 有值时附 UTC 时间；标题里的换行压成空格，
|
||
避免一行待办撑开多行报告。"""
|
||
title = str(todo.get("title") or "").replace("\n", " ").strip()
|
||
if len(title) > max_title:
|
||
title = title[:max_title] + "…"
|
||
parts = ["• [%s] %s (id=%s, priority=%s)"
|
||
% (todo.get("status"), title, todo.get("id"),
|
||
todo.get("priority"))]
|
||
due_at = todo.get("due_at")
|
||
if due_at:
|
||
try:
|
||
parts.append("due=%s" % time.strftime(
|
||
"%Y-%m-%dT%H:%M:%SZ", time.gmtime(float(due_at))))
|
||
except (TypeError, ValueError, OverflowError):
|
||
pass
|
||
task_id = todo.get("task_id")
|
||
if task_id:
|
||
parts.append("task_id=%s" % task_id)
|
||
return " ".join(parts)
|