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

Files

Tianyi Cui 9c1048f2b5 Honor an already-aborted request signal in the subagent driver (Codex review round 2)

A request signal aborted BEFORE the run starts never fires an `abort` event
(`addEventListener` only fires on the transition), so the backend-level bridge
missed it and ran the child to `completed`. The driver now checks
`request.signal?.aborted` at the top of the result path and settles `aborted`
without running the child. Regression test proven red on the pre-fix code.

Also refresh two stale RFC prose blocks the round-1 fix left behind: the
subagent RFC's Problem statement (cited the removed `TODO(sub-agents)` markers
and claimed nothing existed yet) and the unify-id RFC's fork/spawn risk bullet
(described the seam as "explicitly deferred" via `AgentLoop.create`'s old TODO),
now pointing at the realized seam.

2026-06-22 07:32:09 +08:00

src

Honor an already-aborted request signal in the subagent driver (Codex review round 2)

2026-06-22 07:32:09 +08:00

tests

Honor an already-aborted request signal in the subagent driver (Codex review round 2)

2026-06-22 07:32:09 +08:00

package.json

Add in-process subagent backends: spawn (fresh) and fork (seeded)

2026-06-22 05:58:40 +08:00

README.md

Add in-process subagent backends: spawn (fresh) and fork (seeded)

2026-06-22 05:58:40 +08:00

tsconfig.json

Add in-process subagent backends: spawn (fresh) and fork (seeded)

2026-06-22 05:58:40 +08:00

README.md

@deepseek-ai/dsh-subagent-spawn

The in-process spawn subagent backend: a SubagentProvider that runs each child as a fresh child Agent on the same cordis context (ctx.agents) — its own session, its own (or the parent's) model, zero inherited conversation. The cheapest transport, reusing the agent factory's quiescent AgentHandle teardown.

It also exports the shared in-process run driver (startInProcessRun) that the fork backend builds on — spawn and fork differ only in the session seed.

What it does

start(request) →

computes child depth = depthOf(parent) + 1; if request.maxDepth is set and exceeded, throws SubagentDepthError (the depthLimit capability);
creates a child via ctx.agents.create with a fresh AgentId/SessionId, the parent's cwd + parentSession lineage, and agentOptions (the child inherits the parent's model by default — a child with no model can't run — overridable via request.agentOptions.model; the system prompt is NOT inherited);
drives the one-shot: child.send(prompt) then await child.whenIdle() (ordering matters — send enqueues synchronously, so whenIdle observes the queued work and resolves on the child's running → idle transition, never before the turn starts);
reads the result: the last assistant/message content (deep-cloned — the log is frozen) and the last turn/end.reason mapped to a SubagentStopReason.

dispose() delegates to AgentHandle.dispose() (stop loop → await quiescence → remove session); cancel() cancels the child's in-flight turn.

Capabilities

{ outputSchema: false, depthLimit: true, toolFilter: false }. It constructs the child, so it enforces a recursion cap; structured output and tool-scoping are deferred (the service rejects a request needing either before start runs).

Config

Key	Meaning
`providerName`	Registry name on `ctx.subagents` (default `spawn`).

Depth tracking

Delegation depth rides on a merge-extensible AgentOptions.subagentDepth field (0 for a top-level agent, parent + 1 for a child), so a nested spawn reads its parent's depth from parent.options.subagentDepth. Read it with the exported depthOf(agent).