Tianyi Cui
3f83a4ee96
Review round 2 (tianyicui inline comments): - dsh-system-prompt itself registers the harness:identity (-100) and deployment:persona (0) sections — they must survive a swapped loop plugin, so they leave dsh-agent-loop; the persona text is the plugin's own validated 'persona' config. The model/cwd variables STAY on the loop: runtime facts of the agents it drives. - AgentOptions.systemPrompt is deleted with all its forwarding plumbing: the app configs' systemPrompt keys become 'persona' routed through dsh-agent-core (schema = z.intersect of the owners'), the ACP bridge and tool-subagent stop carrying persona configuration, and subagent children now render the deployment persona like every other agent. - Example personas drop transport/interface trivia (ACP, CLI) — facts irrelevant to the model. - Root CONTEXT.md removed (not idiomatic); its persona definition was wrong under the new ownership anyway. - Docs, READMEs, the prompt-variables RFC, and generated catalogs updated; new loop test pins the assemble-waterfall escape valve (an emptied assembly sends NO system field).
92 lines
4.0 KiB
TypeScript
92 lines
4.0 KiB
TypeScript
import { Context } from 'cordis'
|
|
import LlmService from '@deepseek-ai/dsh-llm'
|
|
import SessionStore from '@deepseek-ai/dsh-session'
|
|
import type { SessionEvent } from '@deepseek-ai/dsh-session'
|
|
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
|
|
import ToolRegistry from '@deepseek-ai/dsh-tools'
|
|
import AgentRegistry from '@deepseek-ai/dsh-agent'
|
|
import AgentLoop, { ReactLoopAgent } 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 ToolTodo from '@deepseek-ai/dsh-tool-todo'
|
|
import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek'
|
|
import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl'
|
|
import { BasicCompactService } from '@deepseek-ai/dsh-compact-basic'
|
|
import type { BasicCompactConfig } from '@deepseek-ai/dsh-compact-basic'
|
|
|
|
/**
|
|
* Shared harness for the coding-agent e2e suites: the full plugin stack
|
|
* with the real DeepSeek adapter and the real bash + todo_write tools. Lives
|
|
* outside the *.e2e.ts pattern so importing it never re-registers another
|
|
* file's tests.
|
|
*/
|
|
|
|
export const SYSTEM_PROMPT = 'You are a coding agent. Use bash for file operations '
|
|
+ 'with cat/grep/heredocs; check [exit code: N] markers, '
|
|
+ 'and report results briefly.'
|
|
|
|
/** System prompt for the todo_write e2e: nudges the model to plan with the tool. */
|
|
export const TODO_SYSTEM_PROMPT = 'You are a coding agent. For multi-step work, '
|
|
+ 'use the todo_write tool to track a task list: send the WHOLE list each call, '
|
|
+ 'keep at most one task in_progress (exactly one while work remains), and mark '
|
|
+ 'a task completed as soon as it is done.'
|
|
|
|
/** Options for {@link codingHarness}. */
|
|
export interface CodingHarnessOptions {
|
|
/**
|
|
* Deployment persona for the tree (the system-prompt plugin's `persona`
|
|
* config — per-context, not per-agent). Omitted ⇒ no persona section.
|
|
*/
|
|
persona?: string
|
|
/** Durable JSONL persistence root (the resume suite needs it; others stay file-free). */
|
|
persistenceRoot?: string
|
|
/**
|
|
* Load {@link BasicCompactService} with this config so the compaction e2e can
|
|
* trigger compaction at a small, controlled history size. Omitted ⇒ no
|
|
* compaction plugin (the default suites run without it).
|
|
*/
|
|
compact?: BasicCompactConfig
|
|
}
|
|
|
|
export async function codingHarness(workdir: string, options: CodingHarnessOptions = {}): Promise<Context> {
|
|
const ctx = new Context()
|
|
await ctx.plugin(LlmService)
|
|
await ctx.plugin(SessionStore)
|
|
await ctx.plugin(SystemPrompt, { persona: options.persona ?? '' })
|
|
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(ToolTodo)
|
|
// Compaction is opt-in: only the compaction e2e loads it, with a lowered
|
|
// contextWindow/retainTokens so a short real session crosses the threshold.
|
|
if (options.compact !== undefined) await ctx.plugin(BasicCompactService, options.compact)
|
|
// Durable JSONL persistence is opt-in: only the resume e2e needs it, and the
|
|
// other suites stay file-free. Loaded last so a resume's deferred
|
|
// `ctx.inject(['sessionPersistence'])` resolves once this is present.
|
|
if (options.persistenceRoot !== undefined) await ctx.plugin(SessionPersistenceJsonl, { root: options.persistenceRoot })
|
|
return ctx
|
|
}
|
|
|
|
export function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
|
|
return new Promise((resolve) => {
|
|
const dispose = ctx.on('agent/status', (subject, status) => {
|
|
if (subject === agent && status === 'idle') {
|
|
dispose()
|
|
resolve()
|
|
}
|
|
})
|
|
})
|
|
}
|
|
|
|
export function finalText(events: SessionEvent[]): string {
|
|
const message = events.findLast(event => event.type === 'assistant/message')
|
|
if (message?.type !== 'assistant/message') return ''
|
|
return message.data.content
|
|
.filter(block => block.type === 'text')
|
|
.map(block => block.text)
|
|
.join('')
|
|
}
|