Files
deepseek-harness/packages/tasks/tasks-local
Yichen Jiang 59e759ce13 fix(tasks-local): layer control surfaces and listeners by registering scope
One host registry serves every composition in the process, so its two
service-wide collections answered per-owner questions process-wide. `start()`
asked only whether SOME surface was attached, so an agent whose own composition
loads no `tool-tasks` could start work it has no tool to collect or stop as soon
as any other preset attached one — and the answer changed depending on which
sessions happened to be open. `settle()` walked every registered listener, so a
task settling without a waiter injected one completion notice per mounted
preset into the same owner.

Both collections now sit in `ScopedLayers`, the layered-registry primitive
`tools` and `skills` already use: a registration files into its registering
context's scope, and a read unions the global layer with the owner's scope
chain. A surface or listener registered from an unscoped context lands in the
global layer and serves every owner, which is exactly the host-plane
composition's own controls, so the TUI path is unchanged without a special
case.

This supersedes the consumer-side filter in the previous commit. That filter
produced the right notices but sat in the wrong layer: it left the `start()`
gate process-wide, it could not be enforced against a producer that resolves
the registry directly, and it made a Consumer carry scope knowledge that the
other layered registries keep in the registry. `tool-tasks` is scope-agnostic
again and the `dsh-scope` edge moves to `tasks-local`.

`start()`'s refusal is now owner-relative, so its model-visible text names the
agent rather than the process. The shipped `minimal` preset keeps
`enableRunInBackground: false`, no longer as the safety boundary — the registry
owns that now — but so an agent that could never collect a task is not offered
the parameter at all.

Refs #2141
2026-08-10 16:12:41 +08:00
..

@deepseek-ai/dsh-tasks-local

English | 中文

Process-local implementation of the @deepseek-ai/dsh-tasks registry contract: LocalTaskService keeps every record in memory, issues per-kind <kind>-N ids, and hands out fresh snapshots, never live state. It has no config; load it as a plugin and it registers as ctx.tasks.

Lifecycle

Tasks belong to their owner and backend, not the producer tool fiber, so producer and surface reloads do not stop them. The first task for an owner attaches one awaited effect to the exact Agent scope. Owner disposal cancels that object's tasks, awaits producer quiescence, and removes their snapshots; reused agent or session ids cannot redirect an old cleanup.

Service disposal closes listeners, cancels all live tasks, awaits their records, and detaches effects from surviving owner scopes. If teardown cancellation throws, the service force-fails the record and warns that work may be orphaned instead of deadlocking. A cancellation that returns but never settles done remains indistinguishable from a slow stop and can stall teardown.

Settlement is first-wins: the earliest terminal outcome — producer settlement, a rejected done contained as failed, or a teardown force-failure — records once, notifies listeners once with per-listener containment, and releases waiters. Pending waits mark the task reported before listeners run so completion surfaces do not duplicate notices.

Surfaces and listeners are layered by the scope that registered them, in the tools-registry shape: a registration files into its registering context's scope, and a read unions the global layer with the owner's scope chain. One process-wide registry therefore answers per-owner questions per owner — start() refuses background tasks unavailable: no control surface serves this agent (load @deepseek-ai/dsh-tool-tasks in its composition) for an owner whose own composition attaches none, however many other compositions attach theirs, and a settlement reaches only the listeners its owner's composition registered.

Model Experience

Indirectly, through producer plugins and dsh-tool-tasks, which render task ids, output, status, cancellation, and completion notices.

KV Cache effect

No direct invalidation; the named consumer owns any request-prefix changes.

Known Limitations and Deferred Work

  • Tasks are process-local — records die with the harness process; durable or cross-restart execution needs a separate backend implementing the seam.
  • A silently ineffective cancel can stall teardown — only an explicit throw can be force-failed safely.