feat(agent-loop): config-driven session resume via RESUME_SESSION_ID

A config agent with `resumeSessionId` set continues a persisted session
instead of starting a fresh `${id}-session-<uuid>`. The id is sourced from
an env var in cordis.yml, so the coding-agent demo can resume a prior
conversation without code changes. The resume is deferred until the
`sessionPersistence` backend loads (via ctx.inject) and is contained: a
missing/unreadable id logs a warning and starts no agent. Adds a real-API
resume e2e proving cross-process continuity through the JSONL backend.
This commit is contained in:
Tianyi Cui
2026-06-16 22:28:01 +08:00
parent 8511b9639c
commit 0000cdb2c2
6 changed files with 212 additions and 7 deletions
+6 -1
View File
@@ -9,6 +9,7 @@ import AgentLoop, { LoopAgent } 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'
/**
* Shared harness for the coding-agent e2e suites: the full plugin stack
@@ -20,7 +21,7 @@ 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.'
export async function codingHarness(workdir: string): Promise<Context> {
export async function codingHarness(workdir: string, persistenceRoot?: string): Promise<Context> {
const ctx = new Context()
await ctx.plugin(LlmService)
await ctx.plugin(SessionStore)
@@ -31,6 +32,10 @@ export async function codingHarness(workdir: string): Promise<Context> {
await ctx.plugin(LlmDeepSeek, { models: ['deepseek-v4-flash'] })
await ctx.plugin(LocalBashExecutor, { cwd: workdir, timeoutMs: 30_000 })
await ctx.plugin(ToolBash)
// 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 (persistenceRoot !== undefined) await ctx.plugin(SessionPersistenceJsonl, { root: persistenceRoot })
return ctx
}
+69
View File
@@ -0,0 +1,69 @@
import { mkdtemp, rm } from 'node:fs/promises'
import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { afterEach, describe, expect, it } from 'vitest'
import type { Context } from 'cordis'
import type { LoopAgent } from '@deepseek-ai/dsh-agent-loop'
import { codingHarness, finalText, SYSTEM_PROMPT, waitForIdle } from './harness.ts'
/**
* Proves durable conversation continuity end-to-end: run 1 tells the REAL model
* a fact and persists the turn to JSONL; run 2 is a fresh harness (new Context,
* same `.sessions` root) that RESUMES the persisted session id and asks the
* model to recall the fact. The recall can only come from the rehydrated event
* log — a fresh session would have no idea. Key-gated like the other e2es.
*/
const SECRET = 'plum-galaxy-1791'
const SESSION_ID = 'resume-e2e-session'
let ctx: Context | undefined
let root: string | undefined
afterEach(async () => {
// Dispose even on failure/retry: agent-loop teardown stops the loop and the
// JSONL backend flushes; then drop the on-disk session log.
await ctx?.fiber.dispose()
ctx = undefined
if (root !== undefined) await rm(root, { recursive: true, force: true })
root = undefined
})
describe.skipIf(!process.env.DEEPSEEK_API_KEY)('resume: continue a persisted session across processes', () => {
it('recalls a fact stored in a prior, separately-disposed session', async () => {
root = await mkdtemp(join(tmpdir(), 'dsh-resume-e2e-'))
// Run 1: a fresh agent on a KNOWN session id learns a secret, then we
// dispose the whole context (simulating process exit) so only the JSONL
// log on disk survives.
ctx = await codingHarness(process.cwd(), root)
const first = ctx.agents.create({
agentId: 'resume-1',
sessionId: SESSION_ID,
agentOptions: { model: 'deepseek-v4-flash', systemPrompt: SYSTEM_PROMPT },
}) as LoopAgent
first.send([{ type: 'text', text: `Remember this code for later: ${SECRET}. Just acknowledge it.` }])
await waitForIdle(ctx, first)
await ctx.fiber.dispose()
ctx = undefined
// Run 2: a brand-new context over the SAME root resumes the persisted
// session. The loaded event log seeds the live session, so the model sees
// run 1's exchange as conversation history.
ctx = await codingHarness(process.cwd(), root)
const resumed = await ctx.agents.resume({
agentId: 'resume-2',
resumeSessionId: SESSION_ID,
agentOptions: { model: 'deepseek-v4-flash', systemPrompt: SYSTEM_PROMPT },
}) as LoopAgent
expect(resumed.session.id).toBe(SESSION_ID)
// The prior user turn is in the rehydrated log before the model is asked.
expect(JSON.stringify(resumed.session.deriveMessages())).toContain(SECRET)
resumed.send([{ type: 'text', text: 'What was the code I asked you to remember? Reply with just the code.' }])
await waitForIdle(ctx, resumed)
// The model recalls it — only possible from the resumed history.
expect(finalText([...resumed.session.events])).toContain(SECRET)
}, 180_000)
})