Files
LLeMbas/src/lembas/api/admin_agents.py
T
Jaroslav Beneš e16bede85b Work handed to a second model, which may not ask
subagent_run gives a self-contained piece of work to a helper carrying the
parent's connection, directory, model and effort, and hands its answer back as
the tool result. The mechanism is the one scheduled runs already use -- a hidden
chat, one turn, wake_chat, and a poll -- so tools, rounds, budgets, metrics and
steps all work with no second implementation. The two alternatives were
rejected where they had already been rejected once: a nested Generation is two
replies writing one transcript, and a one-shot complete() has no tools, which
schedule/runner.py records as useless for exactly this case.

Every restriction is a property of the child's row, applied by resolve_tools
after the gates, because a rule that lives in a system message is one a page the
model just read can argue with. No questions, no recursion, nothing that writes
unless the call asked for it and the parent's own mode would not have stopped
first, and commands only from a fixed read-only list -- in every mode including
Auto, because the task text can have come from a page.

Withdrawing ask_user turned out to be half of "nobody is watching". An approval
still built a card nobody could see and parked the reply until approval_timeout,
which from every screen is the feature not working. Chat.unattended is the
question now, and not the kind: _authorise answers with a refusal instead. A
scheduled task's chat had the same hole and is covered by the same flag.

Three bounds, counted where each is knowable: per reply on the parent's
Generation, instance-wide in a set a restart clears, and per helper in settings
of its own so one runs out of room long before the reply that asked. Past the
clock the helper is stopped rather than abandoned, so a partial answer comes
back with a sentence saying so.

Also: four gates had shipped into the scope menu with no name, taking the first
tool's label instead -- the canvas switch read "Canvas written". There is a test
that refuses a family without one.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-06 15:05:30 +02:00

202 lines
8.9 KiB
Python

"""Whether agent chats exist here at all, and what they may spend.
An administrator's half of the feature. The other half -- which machines, whose
credentials -- belongs to whoever owns them and lives at `/agents`.
Nothing here is about isolation, because there is none to configure: commands
run on a host somebody chose, and its containment is that host's. The settings
are budgets, and the two lists that decide what a mode asks about.
"""
from __future__ import annotations
import logging
from fastapi import APIRouter, Form, Request, Response, status
from fastapi.responses import RedirectResponse
from sqlalchemy import func, select
from lembas.api.deps import AdminUser, Db
from lembas.db.models import SshProfile
from lembas.services import settings_store
from lembas.services.agent import hosts, policy
from lembas.services.agent import ssh as ssh_service
from lembas.services.agent import terminal as terminal_service
from lembas.web.templating import render
log = logging.getLogger(__name__)
router = APIRouter(prefix="/admin/agents", tags=["admin-agents"])
def _lines(text: str) -> list[str]:
"""One pattern per line, blanks dropped."""
return [line.strip() for line in (text or "").splitlines() if line.strip()]
@router.get("")
async def agents_page(request: Request, db: Db, user: AdminUser, saved: bool = False):
values = settings_store.agents(db)
return render(
request,
"admin/agents.html",
{
"values": values,
"allow_text": "\n".join(values.get("allow_default") or []),
"deny_text": "\n".join(values.get("deny_default") or []),
"problem": ssh_service.available(),
"profile_count": db.scalar(select(func.count()).select_from(SshProfile)) or 0,
"terminal_count": terminal_service.count(),
"modes": [(m, policy.MODE_LABELS[m], policy.MODE_HINTS[m]) for m in policy.MODES],
"loopback_modes": [
(m, hosts.MODE_LABELS[m], hosts.MODE_HINTS[m]) for m in hosts.MODES
],
# How many of this instance's connections the current position would
# stop. The number is the point of the card: "3 connections" beside
# a switch somebody is about to move is the difference between an
# informed change and a surprise.
"loopback_count": sum(
1
for p in db.scalars(select(SshProfile))
if hosts.is_loopback(p.host) or p.resolves_here
),
# A group of its own, saved by its own form. Subagents are not an
# agent-chat feature -- an ordinary chat can delegate too -- but
# this is the page somebody looks at when they want to know what a
# reply is allowed to set going on its own, and a nav entry for one
# card would be worse than the near-miss.
"subagents": settings_store.subagents(db),
"saved": saved,
},
)
@router.post("/subagents")
async def save_subagents(
db: Db,
user: AdminUser,
enabled: bool = Form(False),
max_per_reply: int = Form(4),
max_concurrent: int = Form(6),
max_rounds: int = Form(30),
wall_seconds: int = Form(600),
max_completion_tokens: int = Form(60_000),
keep_transcript: bool = Form(False),
) -> Response:
"""Its own route because it is its own settings group.
A single form writing two groups would mean one save handler deciding which
key each field belongs to, which is a mapping that goes wrong silently. Two
forms, two keys, and the browser posts only the one that was submitted.
"""
settings_store.update(
db,
{
"enabled": enabled,
# Clamped here as well as on read, for the reason the agent settings
# give: a number with no bound is a way to break the instance from a
# form. Zero is kept only for the token ceiling, where it means "no
# ceiling"; everywhere else a zero would be the feature switched off
# wearing the switch's clothes.
"max_per_reply": min(max(max_per_reply, 1), 20),
"max_concurrent": min(max(max_concurrent, 1), 50),
"max_rounds": min(max(max_rounds, 1), 200),
"wall_seconds": min(max(wall_seconds, 30), 7200),
"max_completion_tokens": min(max(max_completion_tokens, 0), 5_000_000),
"keep_transcript": keep_transcript,
},
key=settings_store.SUBAGENTS,
)
log.info("subagents %s by %s", "enabled" if enabled else "disabled", user.email)
return RedirectResponse("/admin/agents?saved=1", status_code=status.HTTP_303_SEE_OTHER)
@router.post("")
async def save_agents(
db: Db,
user: AdminUser,
enabled: bool = Form(False),
loopback: str = Form("off"),
loopback_port: int = Form(0),
default_timeout: int = Form(60),
max_timeout: int = Form(600),
max_output_bytes: int = Form(64 * 1024),
max_steps: int = Form(200),
max_wall_seconds: int = Form(900),
max_total_output_bytes: int = Form(1024 * 1024),
max_completion_tokens: int = Form(200_000),
approval_timeout: int = Form(900),
allow_default: str = Form(""),
deny_default: str = Form(""),
ask_free_text: bool = Form(False),
terminal_enabled: bool = Form(False),
terminal_idle_timeout: int = Form(1800),
terminal_max_sessions: int = Form(20),
terminal_max_per_user: int = Form(3),
terminal_integration: bool = Form(False),
index_enabled: bool = Form(False),
index_chars: int = Form(2000),
instructions_enabled: bool = Form(False),
instructions_chars: int = Form(4000),
nudge_unfinished: bool = Form(False),
background_enabled: bool = Form(False),
background_on_timeout: bool = Form(False),
background_notify: bool = Form(False),
background_max_jobs: int = Form(5),
) -> Response:
settings_store.update(
db,
{
"enabled": enabled,
# Anything unrecognised means off, here as well as on read: the one
# direction safe to get wrong is refusing a connection somebody has
# to re-allow, and the other is a shell on this host.
"loopback": loopback if loopback in hosts.MODES else hosts.MODE_OFF,
# Zero means "none named", which is what `port` needs in order to
# refuse rather than to allow. 22 is refused wherever it is stored.
"loopback_port": loopback_port if 1 <= loopback_port <= 65535 else 0,
# Clamped here as well as on read. A number with no bound is a way
# to break the instance from a form, which is the same reasoning
# the search settings carry.
"default_timeout": min(max(default_timeout, 1), 3600),
"max_timeout": min(max(max_timeout, 1), 3600),
"max_output_bytes": min(max(max_output_bytes, 1024), 1024 * 1024),
"max_steps": min(max(max_steps, 1), 1000),
"max_wall_seconds": min(max(max_wall_seconds, 30), 7200),
"max_total_output_bytes": min(max(max_total_output_bytes, 4096), 8 * 1024 * 1024),
# Floor of 0, not 1: zero is how "no ceiling" is said.
"max_completion_tokens": min(max(max_completion_tokens, 0), 5_000_000),
"approval_timeout": min(max(approval_timeout, 60), 3600),
"allow_default": _lines(allow_default),
"deny_default": _lines(deny_default),
"ask_free_text": ask_free_text,
"terminal_enabled": terminal_enabled,
"terminal_idle_timeout": min(max(terminal_idle_timeout, 60), 86400),
"terminal_max_sessions": min(max(terminal_max_sessions, 1), 500),
"terminal_max_per_user": min(max(terminal_max_per_user, 1), 50),
"terminal_integration": terminal_integration,
"index_enabled": index_enabled,
# Zero is kept rather than clamped up: it means "list the
# directory for the file picker but put none of it in the
# prompt", which nothing else can say.
"index_chars": min(max(index_chars, 0), 20_000),
"instructions_enabled": instructions_enabled,
"instructions_chars": min(max(instructions_chars, 0), 20_000),
"nudge_unfinished": nudge_unfinished,
"background_enabled": background_enabled,
"background_on_timeout": background_on_timeout,
"background_notify": background_notify,
"background_max_jobs": min(max(background_max_jobs, 1), 100),
},
key=settings_store.AGENTS,
)
log.info("agent execution %s by %s", "enabled" if enabled else "disabled", user.email)
if loopback != hosts.MODE_OFF:
log.warning(
"ssh connections to this machine allowed (%s%s) by %s",
loopback,
f", port {loopback_port}" if loopback == hosts.MODE_PORT else "",
user.email,
)
return RedirectResponse("/admin/agents?saved=1", status_code=status.HTTP_303_SEE_OTHER)