Files
deepseek-harness/packages/agent-loop
Tianyi Cui 825b57aff9 feat(llm): structured error taxonomy with a shared HarnessError base (RFC 005 pt 2)
Introduce HarnessError in dsh-llm (the leaf package): a stable machine-routable
code distinct from the message, cause chaining, name from the subclass, plus
isHarnessError. LlmError, ToolArgsError, and InvariantError now extend it.

Tool failures carry the structure end-to-end: ToolExecutionResult gains
error: { name, code } (populated from a thrown HarnessError), and the loop
forwards it onto the tool/result session event (which gained the same optional
field) for retry/sandbox plugins and replay. The loop's toError wraps non-Error
throws in a HarnessError(code: UNKNOWN, cause) instead of a bare Error.

Landed last and in isolation so it's a pure upgrade over the plain Error+code
the earlier PRs used — independently revertible. Graduates RFC 005 pt 2 ->
ADR 0015; RFC 005 now fully implemented.
2026-06-14 01:07:28 +08:00
..
2026-06-11 10:54:31 +08:00
2026-06-11 10:54:31 +08:00

dsh-agent-loop

THE concrete agent plugin: LoopAgent and the loop driver. Implements the Agent interface and drives the session/turn/step lifecycle.

This is the only package in the harness that contains concrete loop logic. Everything else is an abstract service or a plugin against extension seams — new behavior goes into plugins, not here.

Service: AgentLoop (ctx key: agentLoop)

Public API

  • ctx.agentLoop.create(id: string, options?: AgentOptions): LoopAgent Create an agent, start its loop, and register it in ctx.agents. Disposed with the calling fiber.

Injected services

agents, sessions, llm, tools, systemPrompt — all five interface services.

Configuration (schemastery)

interface Config {
  agents: Array<{
    id: string                 // required
    model?: string
    systemPrompt?: string
  }>
}

Agents listed in config are auto-created at startup.

Classes

  • LoopAgent — the concrete Agent implementation. Owns the inbox (Inbox), the per-step AbortController, and the loop driver. Everything observable happens through session events and the agent/* event taxonomy.
  • Inbox — per-agent queued + steering FIFOs (enqueue, steer, drainQueued, drainSteering, waitForQueued).

Loop lifecycle (loop.ts)

One invocation of runLoop() drives one agent for its whole lifetime:

forever:
  wait for queued messages (idle)
  TURN (error-contained):
    drain queued → session('user/message') → 'turn/start'
    STEP loop:
      drain steering
      assembly = systemPrompt.assemble()
      request = waterfall agent/request
      stream llm.stream(request) → session('assistant/chunk')
      message = waterfall agent/step-result
      session('assistant/message')
      each tool-call: session('tool/call') → tools.execute() → session('tool/result')
      drain steering → session('steering/message')
      cont = waterfall agent/turn-continuation
      if !cont: break
    session('turn/end')
    await session/flush
    re-enqueue leftover steering as queued
  idle unless more queued

Error containment: a throwing plugin ends the turn, never the loop. Dispose mid-turn emits agent/status('disposed') and ends with reason disposed.

What is NOT here

Everything that goes beyond "call the model, run the tools, repeat" belongs to plugins listening on the event taxonomy:

  • Hooks: agent/request, agent/step-result, tools/execute, agent/turn-continuation
  • Compaction: agent/request
  • Sandbox, permission, plan mode: tools/execute
  • Sub-agents: TODO seam on AgentLoop.create()
  • Persistence: session/event + session/flush
  • UI: agent/stream-chunk + agent/* events