mirror of
https://github.com/deepseek-ai/deepseek-harness
synced 2026-08-15 21:04:50 +00:00
a8986c2c8a
Beyond the mechanical conflicts (provider capability lines vs master's new inheritsParentContext field; generated catalogs regenerated rather than hand-merged; knip/lockfile), three master-side reworks required semantic adaptation of this branch: - The persona rework removed AgentOptions.systemPrompt, which was the structured-output instruction's channel. The instruction now rides the SAME final-request enforcement listener that injects the schema'd tool: appended per request to final.system (per-request wire state, not agent prompt state). Tests assert the wire request (adapter.requests) instead of child.options; the bare-direct-dispatch test pins the no-system arm. - Tool guidance moved out of deployment prompts into per-tool prompt sections; the examples' workflow paragraph became a tool:<toolName> section contributed by dsh-tool-workflow (explicit-ask-only policy), and both example personas resolve to master's minimal identity+behavior form. tool-workflow gains inject: systemPrompt (+ peer dep, tsconfig ref); the export-shape guard updated. - The uniform-RFC-format gate: the dynamic-workflows RFC restructured to the implemented/ skeleton (bare Status line; Proposal -> Decision; What-was-rejected -> Alternatives considered; new Consequences), and the overall-run-timeout deferral is now recorded in the RFC's Deferred list. The doc-graphs atlas classification gains the workflows seam (workflow-vm implementation, tool-workflow consumer). Master's harness-identity section made "empty assembled prompt" states unreachable through the loop, so the instruction-append is a plain undefined-ternary and the structured tests assert append-not-replace. All snapshot goldens (including workflow-run) replay unchanged. Full local CI-equivalent gate sequence green on the merged tree.
53 lines
2.3 KiB
TypeScript
53 lines
2.3 KiB
TypeScript
import { Context } from 'cordis'
|
|
import LlmService from '@deepseek-ai/dsh-llm'
|
|
import SessionStore from '@deepseek-ai/dsh-session'
|
|
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
|
|
import ToolRegistry from '@deepseek-ai/dsh-tools'
|
|
import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
|
|
import AgentLoop from '@deepseek-ai/dsh-agent-loop'
|
|
import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local'
|
|
import * as ToolBash from '@deepseek-ai/dsh-tool-bash'
|
|
import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek'
|
|
import SubagentService from '@deepseek-ai/dsh-subagent'
|
|
import * as Spawn from '../src/index.ts'
|
|
import * as ToolSubagent from '@deepseek-ai/dsh-tool-subagent'
|
|
|
|
/**
|
|
* Shared harness for the spawn-backend e2e: the full real stack (DeepSeek
|
|
* adapter + real bash tool + the subagent tool bound to the spawn backend), so
|
|
* a real parent agent can delegate to a real in-process child that does real
|
|
* work (writes a file). Lives outside the *.e2e.ts pattern so importing it never
|
|
* re-registers another file's tests.
|
|
*/
|
|
export async function spawnHarness(workdir: string): Promise<Context> {
|
|
const ctx = new Context()
|
|
await ctx.plugin(LlmService)
|
|
await ctx.plugin(SessionStore)
|
|
// The deployment persona is context-wide (parent AND spawned children
|
|
// render it), so it stays neutral for both roles; the delegation nudge
|
|
// lives in the e2e's user prompt and the subagent tool's own description.
|
|
await ctx.plugin(SystemPrompt, { persona: 'You are a coding agent. Report only when the requested work is done.' })
|
|
await ctx.plugin(ToolRegistry)
|
|
await ctx.plugin(AgentRegistry)
|
|
await ctx.plugin(AgentLoop, { agents: [] })
|
|
await ctx.plugin(LlmDeepSeek, { models: ['deepseek-v4-flash'] })
|
|
await ctx.plugin(LocalBashExecutor, { cwd: workdir, timeoutMs: 30_000 })
|
|
await ctx.plugin(ToolBash)
|
|
await ctx.plugin(SubagentService)
|
|
await ctx.plugin(Spawn, { providerName: 'spawn', structuredNudgeRetries: 1 })
|
|
// The model-facing subagent tool, bound to the spawn backend.
|
|
await ctx.plugin(ToolSubagent, { provider: 'spawn' })
|
|
return ctx
|
|
}
|
|
|
|
export function waitForIdle(ctx: Context, agent: Agent): Promise<void> {
|
|
return new Promise((resolve) => {
|
|
const dispose = ctx.on('agent/status', (subject, status) => {
|
|
if (subject === agent && status === 'idle') {
|
|
dispose()
|
|
resolve()
|
|
}
|
|
})
|
|
})
|
|
}
|