feat: expose agent session log location
This commit is contained in:
40 files changed
+526
-70
No files matched your search
@@ -1,8 +1,12 @@
|
||||
import { describe, expect, it } from 'vitest'
|
||||
import { afterEach, describe, expect, it } from 'vitest'
|
||||
import { Context } from 'cordis'
|
||||
import { existsSync, mkdtempSync, readFileSync, rmSync } from 'node:fs'
|
||||
import { tmpdir } from 'node:os'
|
||||
import { join } from 'node:path'
|
||||
import LlmService from '@deepseek-ai/dsh-llm'
|
||||
import SessionStore from '@deepseek-ai/dsh-session'
|
||||
import SessionStore, { SessionId } from '@deepseek-ai/dsh-session'
|
||||
import type { SessionEvent } from '@deepseek-ai/dsh-session'
|
||||
import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl'
|
||||
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
|
||||
import ToolRegistry from '@deepseek-ai/dsh-tools'
|
||||
import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent'
|
||||
@@ -17,10 +21,11 @@ import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent
|
||||
* through the agent loop, exercising the same seams a live model would
|
||||
* (tool/call + tool/result session events, agent.inject notifications).
|
||||
*/
|
||||
async function harness(adapter: MockAdapter) {
|
||||
async function harness(adapter: MockAdapter, sessionRoot?: string) {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(LlmService)
|
||||
await ctx.plugin(SessionStore)
|
||||
if (sessionRoot !== undefined) await ctx.plugin(SessionPersistenceJsonl, { root: sessionRoot })
|
||||
await ctx.plugin(SystemPrompt)
|
||||
await ctx.plugin(ToolRegistry)
|
||||
await ctx.plugin(AgentRegistry)
|
||||
@@ -31,6 +36,9 @@ async function harness(adapter: MockAdapter) {
|
||||
return ctx
|
||||
}
|
||||
|
||||
const dirs: string[] = []
|
||||
afterEach(() => { for (const dir of dirs.splice(0)) rmSync(dir, { recursive: true, force: true }) })
|
||||
|
||||
function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
|
||||
return new Promise((resolve) => {
|
||||
const dispose = ctx.on('agent/status', (subject, status) => {
|
||||
@@ -68,6 +76,37 @@ function resultText(event: SessionEvent): string {
|
||||
}
|
||||
|
||||
describe('bash tool through the agent loop', () => {
|
||||
it('first-turn bash receives session identity before the lazy JSONL file materializes', async () => {
|
||||
const root = mkdtempSync(join(tmpdir(), 'dsh-bash-session-env-'))
|
||||
dirs.push(root)
|
||||
const adapter = new MockAdapter([
|
||||
toolCallResponse('call-1', 'bash', {
|
||||
command: 'printf \'%s\\n%s\\n\' "$DSH_SESSION_ID" "$DSH_SESSION_JSONL"; if [ -e "$DSH_SESSION_JSONL" ]; then printf \'present\\n\'; else printf \'absent\\n\'; fi',
|
||||
description: 'inspect session environment',
|
||||
}),
|
||||
textResponse('Session environment inspected.'),
|
||||
])
|
||||
const ctx = await harness(adapter, root)
|
||||
const handle = ctx.agents.create({
|
||||
agentId: AgentId('session-env'),
|
||||
sessionId: SessionId('session-env-id'),
|
||||
agentOptions: { model: 'mock' },
|
||||
})
|
||||
const agent = handle.agent as ReactLoopAgent
|
||||
const location = ctx.sessionPersistence.locate(agent.session.header)
|
||||
expect(location?.kind).toBe('jsonl')
|
||||
|
||||
agent.send([{ type: 'text', text: 'inspect the current session' }])
|
||||
await waitForIdle(ctx, agent)
|
||||
|
||||
const result = findEvent(events(agent), 'tool/result')
|
||||
expect(resultText(result)).toBe(`session-env-id\n${location?.path}\nabsent\n`)
|
||||
expect(existsSync(location!.path)).toBe(true)
|
||||
const header = JSON.parse(readFileSync(location!.path, 'utf8').split('\n')[0]!) as { type: string; id: string }
|
||||
expect(header).toMatchObject({ type: 'session', id: 'session-env-id' })
|
||||
await handle.dispose()
|
||||
})
|
||||
|
||||
it('foreground: model calls bash, sees the result, replies', async () => {
|
||||
const adapter = new MockAdapter([
|
||||
toolCallResponse('call-1', 'bash', { command: 'echo integration-ok', description: 'test command' }, 'Running it.'),
|
||||
|
||||
@@ -10,6 +10,8 @@ import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
|
||||
import ToolRegistry from '@deepseek-ai/dsh-tools'
|
||||
import AgentRegistry from '@deepseek-ai/dsh-agent'
|
||||
import type { Agent } from '@deepseek-ai/dsh-agent'
|
||||
import SessionStore from '@deepseek-ai/dsh-session'
|
||||
import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl'
|
||||
import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local'
|
||||
import * as ToolBash from '@deepseek-ai/dsh-tool-bash'
|
||||
import { renderResult } from '@deepseek-ai/dsh-tool-bash'
|
||||
@@ -910,16 +912,111 @@ describe('the model-facing bash tool builds its request from named args only (no
|
||||
kill(): boolean { return false }
|
||||
}
|
||||
|
||||
async function setupRecording() {
|
||||
async function setupRecording(withJsonl = false) {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(SystemPrompt)
|
||||
await ctx.plugin(ToolRegistry)
|
||||
await ctx.plugin(AgentRegistry)
|
||||
if (withJsonl) {
|
||||
await ctx.plugin(SessionStore)
|
||||
await ctx.plugin(SessionPersistenceJsonl, { root: join(spillDir, 'jsonl') })
|
||||
}
|
||||
await ctx.plugin(RecordingBashExecutor)
|
||||
await ctx.plugin(ToolBash)
|
||||
return { ctx, bash: ctx.bash as RecordingBashExecutor }
|
||||
}
|
||||
|
||||
it('describes the trusted session variables to the model', async () => {
|
||||
const { ctx } = await setupRecording()
|
||||
const description = ctx.tools.get('bash')?.description ?? ''
|
||||
expect(description).toContain('DSH_SESSION_ID')
|
||||
expect(description).toContain('DSH_SESSION_JSONL')
|
||||
})
|
||||
|
||||
it('injects the session id and JSONL target path into a foreground request', async () => {
|
||||
const { ctx, bash } = await setupRecording(true)
|
||||
const agent = registerFakeAgent(ctx, 'request-fg', () => undefined)
|
||||
const path = ctx.sessionPersistence.locate(agent.session.header)?.path
|
||||
|
||||
await ctx.tools.execute({
|
||||
callId: CallId('session-env-fg'),
|
||||
name: 'bash',
|
||||
arguments: { command: 'true', description: 'run command' },
|
||||
agent,
|
||||
})
|
||||
|
||||
expect(bash.requests[0]?.env).toEqual({
|
||||
DSH_SESSION_ID: 'request-fg',
|
||||
DSH_SESSION_JSONL: path,
|
||||
})
|
||||
})
|
||||
|
||||
it('injects the same trusted variables into a background request without forwarding model env', async () => {
|
||||
const { ctx, bash } = await setupRecording(true)
|
||||
const agent = registerFakeAgent(ctx, 'request-bg', () => undefined)
|
||||
const path = ctx.sessionPersistence.locate(agent.session.header)?.path
|
||||
|
||||
await ctx.tools.execute({
|
||||
callId: CallId('session-env-bg'),
|
||||
name: 'bash',
|
||||
arguments: {
|
||||
command: 'sleep 1',
|
||||
description: 'run command',
|
||||
run_in_background: true,
|
||||
env: { DSH_SESSION_ID: 'spoofed', DSH_SESSION_JSONL: '/tmp/spoofed' },
|
||||
},
|
||||
agent,
|
||||
})
|
||||
|
||||
expect(bash.requests[0]?.env).toEqual({
|
||||
DSH_SESSION_ID: 'request-bg',
|
||||
DSH_SESSION_JSONL: path,
|
||||
})
|
||||
})
|
||||
|
||||
it('injects only the stable session id when no JSONL locator is available', async () => {
|
||||
const { ctx, bash } = await setupRecording()
|
||||
const agent = registerFakeAgent(ctx, 'request-id-only', () => undefined)
|
||||
const ambient = process.env.DSH_SESSION_ID
|
||||
|
||||
await ctx.tools.execute({
|
||||
callId: CallId('session-env-id-only'),
|
||||
name: 'bash',
|
||||
arguments: { command: 'true', description: 'run command' },
|
||||
agent,
|
||||
})
|
||||
|
||||
expect(bash.requests[0]?.env).toEqual({ DSH_SESSION_ID: 'request-id-only' })
|
||||
expect(process.env.DSH_SESSION_ID).toBe(ambient)
|
||||
})
|
||||
|
||||
it('keeps parent and child agent session environments isolated', async () => {
|
||||
const { ctx, bash } = await setupRecording(true)
|
||||
const parent = registerFakeAgent(ctx, 'request-parent', () => undefined)
|
||||
const child = registerFakeAgent(ctx, 'request-child', () => undefined)
|
||||
|
||||
for (const [callId, agent] of [['parent', parent], ['child', child]] as const) {
|
||||
await ctx.tools.execute({
|
||||
callId: CallId(`session-env-${callId}`),
|
||||
name: 'bash',
|
||||
arguments: { command: 'true', description: 'run command' },
|
||||
agent,
|
||||
})
|
||||
}
|
||||
|
||||
expect(bash.requests.map(request => request.env)).toEqual([
|
||||
{
|
||||
DSH_SESSION_ID: 'request-parent',
|
||||
DSH_SESSION_JSONL: ctx.sessionPersistence.locate(parent.session.header)?.path,
|
||||
},
|
||||
{
|
||||
DSH_SESSION_ID: 'request-child',
|
||||
DSH_SESSION_JSONL: ctx.sessionPersistence.locate(child.session.header)?.path,
|
||||
},
|
||||
])
|
||||
expect(bash.requests[0]?.env?.DSH_SESSION_JSONL).not.toBe(bash.requests[1]?.env?.DSH_SESSION_JSONL)
|
||||
})
|
||||
|
||||
it('does not forward env/stdin even when the model includes them as extra arguments', async () => {
|
||||
const { ctx, bash } = await setupRecording()
|
||||
// Extra args: the model includes `env` and `stdin` keys hoping they reach the
|
||||
|
||||
Reference in New Issue
Block a user