Files
deepseek-harness/docs/cookbook/extension-cookbook.md
T
Tianyi Cui f6bd1468f2 simplify(agent): drop the unused public Agent.abort(), keep whenIdle()
The public Agent handle exposed abort() (step-only) and cancel() (queue-aware).
No production caller used abort() — ACP maps session/cancel to cancel(), and
lifecycle owners tear down via AgentHandle.dispose(); the loop's own stop paths
abort their per-step AbortController directly. So abort() is latent generality
that keeps a private loop mechanic public.

RFC-premise correction: the public-agent-stop-surface RFC proposed removing
whenIdle() too. Implementation found whenIdle() load-bearing — a real
quiescence primitive with a deliberate loop contract (settle-without-transition,
the replacement-turn race) and ACP test consumers; its proposed replacement
("observe the running->idle transition") is exactly the async-state race
AGENTS.md warns against. So only abort() is removed; whenIdle() stays. The RFC
is amended on the way to implemented/ to record the narrowed scope, and the new
AGENTS.md "RFCs are proposals, not golden truth" principle (PR1) gets its
worked example.

- Remove Agent.abort() from the interface + the ReactLoopAgent impl; the no-arg
  'aborted' default goes with it (cancel() keeps its 'cancelled' default).
- Migrate tests: empty-queue abort() -> cancel(reason); the two review-fixes
  tests whose subject is the in-flight step's AbortController drive that
  controller directly via the private currentAbort field (cancel() would clear
  the inbox and destroy the queued steering one of them proves survives a step
  abort). The no-arg-default test is dropped (cancel()'s default is already
  covered in cancel.spec.ts).
- Resulting public stop surface: cancel() + whenIdle(). Update agent/agent-loop
  READMEs, architecture.md, core.md type-equiv, the extension cookbook, the
  lifecycle RFC (short note), and the proposed ACP RFC.

Implements docs/rfc/implemented/simplification/2026-06-20-public-agent-stop-surface.md
2026-06-21 09:05:21 +08:00

4.6 KiB

Cookbook: extension plugin shapes

The three plugin shapes you write against the harness extension surface, as illustrative snippets (elided imports and helper stubs — not copy-paste-complete). For the full step-by-step guides see adding a package, adding a tool, and adding an LLM adapter; for the seams these hook into see docs/architecture.md.

A tool plugin

A tool registers on ctx.tools. The annotated defineTool example (typed execute args, result shaping, the run_in_background pattern) lives in adding-a-tool.md — that guide is the source of truth for the tool shape. Raw JSON-Schema ToolDefinitions are also accepted by ctx.tools.register() directly (that is how MCP-sourced tools arrive); defineTool is the typed sugar for first-party tools.

A hook plugin (permission gate)

A hook wraps the tools/execute waterfall to veto or rewrite a call — the seam where sandbox, permission, and plan-mode plugins live.

import type { Context } from 'cordis'
import type { ToolExecution } from '@deepseek-ai/dsh-tools'

declare function isAllowed(exec: ToolExecution): Promise<boolean>

export const name = 'permission-gate'

export function apply(ctx: Context) {
  ctx.on('tools/execute', async (exec, next) => {
    if (!(await isAllowed(exec))) {
      return {
        callId: exec.callId,
        content: [{ type: 'text', text: 'Denied by policy.' }],
        isError: true,
      }
    }
    return next()
  })
}

A UI plugin

A UI plugin consumes agent/stream-chunk and session events for rendering, and drives input back in via agent.send() / agent.steer().

import type { Context } from 'cordis'
import { AgentId } from '@deepseek-ai/dsh-agent'

declare function render(text: string): void
declare function onUserInput(handler: (text: string) => void): void

export const name = 'my-ui'
export const inject = ['agents']

export function apply(ctx: Context) {
  ctx.on('agent/stream-chunk', (agent, turn, step, chunk) => {
    if (chunk.type === 'text-delta') render(chunk.text)
  })
  onUserInput(text => ctx.agents.get(AgentId('main'))?.send([{ type: 'text', text }]))
}

A client-driver plugin (external protocol bridge)

A client driver is a UI plugin whose "user" is another program speaking a wire protocol rather than a human at a terminal. It owns the process's stdio (so it must run with no stdout logger — every non-protocol byte corrupts the stream), creates/resumes agents on demand through the dsh-agent factory seam, translates harness events (session/event, agent/*) into outbound protocol messages, and translates inbound requests back into agent.send() / agent.cancel(). Two harness-specific contracts make it correct: resolve each request exactly once off a settle signal (the turn can end without its agent/turn-end event firing — fall back through the logged turn/end record), and on disposal reach quiescence (handle disposal aborts in-flight work then awaits agent.whenIdle()), not just request it.

packages/ui/acp is the worked example: it bridges the agent to the Agent Client Protocol (JSON-RPC over stdio) so Zed and other ACP editors can drive it. See its README for the full method surface and the deferred-permission-gate note.

import type { Context } from 'cordis'

export const name = 'my-protocol-bridge'
export const inject = ['agents', 'sessions', 'sessionPersistence']

export function apply(ctx: Context) {
  // Stream every logged assistant text/reasoning delta out to the client.
  ctx.on('session/event', (_session, event) => {
    if (event.type === 'assistant/chunk') {
      const chunk = event.data.chunk
      if (chunk.type === 'text-delta') {
        // sendToClient({ kind: 'message_chunk', text: chunk.text })
      }
    }
  })
  // Inbound "prompt": create/resume an agent and feed it; settle on turn end.
  // Disposal awaits quiescence: handle disposal aborts, then await agent.whenIdle().
}

Runnable wirings

Three complete examples load their plugin trees from cordis.yml with HMR: examples/echo-agent (mock model + echo tool — the all-mock skeleton check, pnpm run demo:echo), examples/coding-agent (DeepSeek V4 + the bash tool suite — the real thing, pnpm run demo:coding), and examples/acp-agent (the same coding agent exposed as an ACP server over JSON-RPC stdio — the client-driver shape, pnpm run demo:acp). The two real demos share their provider/tool core via examples/base.yml.