mirror of https://github.com/deepseek-ai/deepseek-harness synced 2026-08-15 21:04:50 +00:00

Files

Yichen Jiang bd59fddacd refactor(tasks): declare-then-execute — ctx.tasks.start() replaces register()

start({ kind, label, owner, run }) preflights everything that can fail
(the attachSurface fence, validation, the owner-cleanup attach) BEFORE
invoking the producer's run() starter, then commits atomically —
'work started but never got a collectable id' is now structurally
impossible instead of a producer try/catch rollback obligation (the
P1 review fix, rebuilt on #185's declare/execute split). Producers
lose their catch-wraps; the leak tests now pin the stronger property
that a failed preflight never spawns anything. TaskRegistration splits
into TaskStart (identity + run) and TaskHooks (cancel/done/readOutput);
docs, type-equiv manifest, catalogs, and both RFCs move with it.

2026-07-09 21:55:07 +08:00

src

refactor(tasks): declare-then-execute — ctx.tasks.start() replaces register()

2026-07-09 21:55:07 +08:00

tests

refactor(tasks): declare-then-execute — ctx.tasks.start() replaces register()

2026-07-09 21:55:07 +08:00

package.json

feat(tasks): background task runtime, generic task_* control tools, bash/subagent producers

2026-07-09 21:22:54 +08:00

README.md

refactor(tasks): declare-then-execute — ctx.tasks.start() replaces register()

2026-07-09 21:55:07 +08:00

tsconfig.json

feat(tasks): background task runtime, generic task_* control tools, bash/subagent producers

2026-07-09 21:22:54 +08:00

README.md

@deepseek-ai/dsh-tool-tasks

The model-facing background task control surface over ctx.tasks: three kind-agnostic tools, the completion-notice injection, and the prompt section that teaches the background habit. Loading this plugin calls ctx.tasks.attachSurface('tool-tasks'), which is what arms producers' ctx.tasks.start().

Tools

task_output(task_id, wait?, timeout_ms?) — non-blocking read by default (stream kinds: the consuming delta since the previous read; final kinds: the final answer once terminal); every response ends with a [status: …] line (generic status + producer detail, e.g. [status: completed, exit code: 0]). wait: true blocks until settlement, bounded by waitTimeoutMs/maxWaitTimeoutMs config; a timed-out wait returns [status: running] and leaves the task alive.
task_list() — the caller's tasks, <id> [<kind>] <status> — <label> per line.
task_kill(task_id, reason?) — requests cancellation and returns immediately; the logged reason is forwarded to the producer. An already-terminal task is described via a non-consuming snapshot (never eats a pending delta).

ACP render intent: all three are generic cards (read/read/execute) — a task read is not a terminal.

Completion notices

On onTaskDone, injects background task <id> (<kind>: <label>) finished [status: …]. Read its output with task_output. into the owning agent's session (agent.inject() — durable context for the next request, not a wake-up). Suppressed when the snapshot is reported (the model already killed it, or a read/wait returned the end) — never a redundant "finished". The disposed-owner race is contained; a missing agent registry drops the notice.

Config

key	default	meaning
`waitTimeoutMs`	`30000`	wait duration when `task_output` sets `wait` without `timeout_ms`
`maxWaitTimeoutMs`	`600000`	hard cap; larger model-supplied `timeout_ms` values are clamped

A config whose default exceeds the cap fails loud at load.