mirror of
https://github.com/deepseek-ai/deepseek-harness
synced 2026-08-15 21:04:50 +00:00
Reform the compaction blueprint so a runaway turn survives and the design
stops drifting across review rounds:
- Drop in-flight-turn protection ("layer 2"). Retention is a uniform tail→head
whole-unit walk; the only structural guard is step-alignment. A single turn
that alone exceeds the window now compacts its own early closed steps instead
of being retained verbatim (the failure mode that motivated this).
- Move auto-compaction off the agent/request waterfall onto a new awaited
agent/pre-request loop seam, fired before history derivation. Compaction
mutates the surface; the loop derives once from the result — no double-derive,
and a listener structurally cannot act on not-yet-derived messages.
- Tighten compactIfNeeded to required (session, system, model, signal).
- Enforce a single-pass convergence invariant in resolveConfig: reject configs
where summarizationMaxTokens + retainTokens exceeds the threshold, so a
compaction can never immediately re-trigger.
- Document the crash vs recoverable failure taxonomy; core session repair stays
compaction-agnostic (a log-only orphaned compact/start is inert).
- Wire dsh-compact-basic into examples/coding-agent and add a with-key
compaction e2e (compaction's first real-world exercise + runaway net).
- Rewrite the RFC to encode the blueprint and move it to implemented/.
The runaway-turn snapshot is a named deferred follow-up: dsh-llm-replay cannot
yet serve the interleaved summarization model call.
78 lines
3.4 KiB
TypeScript
78 lines
3.4 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 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 tool. 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. Your only tool is bash; '
|
|
+ 'do file operations with cat/grep/heredocs, check [exit code: N] markers, '
|
|
+ 'and report results briefly.'
|
|
|
|
/** Options for {@link codingHarness}. */
|
|
export interface CodingHarnessOptions {
|
|
/** 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)
|
|
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)
|
|
// 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('')
|
|
}
|