fix(web-app,agent-presets): keep the task registry on the host plane

`tool-bash` resolves the background-task registry with `ctx.get('tasks')`,
and it sits at the preset's top level. The registry sat inside an
entry-local `isolate: { tasks: true }` realm, which is invisible to every
sibling row outside it, while the Web surface disabled the host row — so
both lookups missed and every `run_in_background` call answered
"background tasks unavailable" with `task_output`, `task_list`, and
`task_kill` still listed in the catalog. `task_list` returning
"(no background tasks)" is what made the outage read as an empty queue
rather than a severed producer.

That is the `goals` criterion read from inside the preset: a Service a row
outside its realm READS belongs to the plane both can see. `tasks` already
keys access by owning agent (`assertAccess` compares `task.owner.id`) and
mints an independent token per `attachSurface` call, so one host instance
serves every session exactly as before presets — the per-preset-standing-mounts
note records that sharing `tasks-local` is a return to its design.

`minimal` mounts no `tool-tasks`, and the `start()` control-surface gate is
a service-wide set that another preset's controls would open for it, so its
`tool-bash` disables `run_in_background` and drops the parameter from the
schema.

Fixes #2141
This commit is contained in:
Yichen Jiang
2026-08-10 14:18:41 +08:00
parent 6648ff984a
commit 5d86a284e5
6 changed files with 107 additions and 36 deletions

View File

@@ -22,8 +22,16 @@
# never reached the model's shell at all. `tool-bash` consumes the host registry
# from here; the executor behind it (`bash-sandbox`) is host-plane too, where the
# sandbox policy owns it.
#
# `run_in_background` is off because this preset mounts no `tool-tasks`: the
# host task registry gates starts on SOME control surface being attached, and
# that set is process-wide, so another preset's controls would let this agent
# start work it has no `task_output` to collect. Disabling drops the parameter
# from the schema too, which is the honest surface for a two-tool benchmark.
- id: tool-bash
name: '@deepseek-ai/dsh-tool-bash'
config:
enableRunInBackground: false
- id: tool-str-replace-editor
name: '@deepseek-ai/dsh-tool-str-replace-editor'