mirror of
https://github.com/deepseek-ai/deepseek-harness
synced 2026-08-15 21:04:50 +00:00
dafb81be7b
The seam vocabulary (SubagentStartRequest.outputSchema, SubagentResult .structured) existed but no in-process backend honored it — spawn/fork advertised outputSchema: false. This lands the missing half: - dsh-tools gains a structured-output JSON Schema subset (json-schema.ts): StructuredOutputSchema, assertSupportedOutputSchema (rejects loud outside the enforced subset, every violation listed), validateStructuredValue (path-qualified issues, total). outputSchema's seam type becomes this raw JSON-Schema subset instead of the author-facing SchemaSpec DSL — the schema travels verbatim to the model as a forced tool's parameters. - dsh-subagent-inprocess gains the shared structured runtime: one global structured_output capture tool (placeholder parameters) + a prepend:true agent/request listener doing FINAL-REQUEST enforcement (strip for plain agents, per-run schema for structured children — survives downstream request-replacing listeners) + an agent/turn-continuation veto that stops a child's turn once captured (no wasted extra model step). Lifetime is refcounted by backends (plugin lifetime) AND live runs (start→settle). - startInProcessRun drives the capture: subset asserted before the child exists, instruction appended to the child's system prompt, clean-finish nudge loop (structuredNudgeRetries, backend Config, default 1), captured value on result.structured; a clean finish without a capture settles 'error' (never a silent success with a missing field). - spawn + fork flip outputSchema: true and inject 'tools'.
50 lines
2.0 KiB
TypeScript
50 lines
2.0 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)
|
|
await ctx.plugin(SystemPrompt)
|
|
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()
|
|
}
|
|
})
|
|
})
|
|
}
|