import { afterEach, describe, expect, it, vi } 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, { 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' import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import { BashTaskId } from '@deepseek-ai/dsh-bash' import * as ToolBash from '@deepseek-ai/dsh-tool-bash' import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' /** * Full-loop integration: a scripted mock model drives the REAL bash tool * 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, sessionRoot?: string, dshHome?: 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) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 }) await ctx.plugin(ToolBash, dshHome === undefined ? {} : { dshHome }) ctx.llm.registerAdapter(['mock'], adapter) return ctx } const dirs: string[] = [] afterEach(() => { vi.unstubAllEnvs() for (const dir of dirs.splice(0)) rmSync(dir, { recursive: true, force: true }) }) function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { dispose() resolve() } }) }) } function events(agent: ReactLoopAgent): SessionEvent[] { return [...agent.session.events] } /** Find a session event by type, narrowed; throws when absent. */ function findEvent( log: SessionEvent[], type: T, position: 'first' | 'last' = 'first', ): Extract { const found = position === 'first' ? log.find(event => event.type === type) : log.findLast(event => event.type === type) if (!found) throw new Error(`no ${type} event in the session log`) return found as Extract } function resultText(event: SessionEvent): string { if (event.type !== 'tool/result') return '' return event.data.content .filter(block => block.type === 'text') .map(block => block.text) .join('') } describe('bash tool through the agent loop', () => { it('first-turn bash receives session identity before the lazy JSONL file materializes', async () => { const root = mkdtempSync(join(tmpdir(), 'dsh-bash-session-env-')) dirs.push(root) const dshHome = join(root, 'dsh-home') vi.stubEnv('DSH_STALE_PARENT', 'stale') const adapter = new MockAdapter([ toolCallResponse('call-1', 'bash', { command: 'printf \'%s\\n%s\\n%s\\n%s\\n%s\\n\' "$DSH_HOME" "$DSH_SHELL" "$DSH_SESSION_ID" "$DSH_SESSION_JSONL" "${DSH_STALE_PARENT-unset}"; if [ -e "$DSH_SESSION_JSONL" ]; then printf \'present\\n\'; else printf \'absent\\n\'; fi', description: 'inspect session environment', }), textResponse('Session environment inspected.'), ]) const ctx = await harness(adapter, root, dshHome) const handle = await ctx.agents.create({ agentId: AgentId('session-env'), sessionId: SessionId('session-env-id'), agentOptions: { model: 'mock' }, }) const agent = handle.agent as ReactLoopAgent const location = ctx.sessionPersistence.locate(agent.session.header) expect(location?.kind).toBe('jsonl') agent.send([{ type: 'text', text: 'inspect the current session' }]) await waitForIdle(ctx, agent) const result = findEvent(events(agent), 'tool/result') expect(resultText(result)).toBe(`${dshHome}\n1\nsession-env-id\n${location?.path}\nunset\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.'), textResponse('The command printed integration-ok.'), ]) const ctx = await harness(adapter) const agent = ctx.agentLoop.create(AgentId('it-fg'), { model: 'mock' }) agent.send([{ type: 'text', text: 'run echo integration-ok' }]) await waitForIdle(ctx, agent) const log = events(agent) const toolCall = findEvent(log, 'tool/call') expect(toolCall.data.name).toBe('bash') const toolResult = findEvent(log, 'tool/result') expect(toolResult.data.isError).toBe(false) expect(resultText(toolResult)).toBe('integration-ok\n') // The second model call saw the tool result in its derived history. const lastRequest = adapter.requests.at(-1) const toolResultBlocks = (lastRequest?.messages ?? []) .flatMap(message => message.content) .filter(block => block.type === 'tool-result') expect(toolResultBlocks).toHaveLength(1) const finalMessage = findEvent(log, 'assistant/message', 'last') expect(finalMessage.data.content.some( block => block.type === 'text' && block.text.includes('integration-ok'), )).toBe(true) }) it('foreground: non-zero exit is reported in the result text, not as isError', async () => { const adapter = new MockAdapter([ toolCallResponse('call-1', 'bash', { command: 'exit 9', description: 'test command' }), textResponse('It failed with code 9.'), ]) const ctx = await harness(adapter) const agent = ctx.agentLoop.create(AgentId('it-exit'), { model: 'mock' }) agent.send([{ type: 'text', text: 'run exit 9' }]) await waitForIdle(ctx, agent) const toolResult = findEvent(events(agent), 'tool/result') expect(toolResult.data.isError).toBe(false) expect(resultText(toolResult)).toContain('[exit code: 9]') }) it('background: start → poll → completion notice lands as context/message', async () => { const adapter = new MockAdapter([ toolCallResponse('call-1', 'bash', { command: 'echo bg-ok', description: 'test command', run_in_background: true }), // Each harness owns a fresh BashLocal service, whose first task id is // deterministically bash-1. Keep the scripted call faithful to what the // model sent; tool arguments are immutable once execution policy begins. toolCallResponse('call-2', 'bash_output', { task_id: 'bash-1' }, undefined), textResponse('Background task finished.'), ]) let taskId = '' const ctx = await harness(adapter) const agent = ctx.agentLoop.create(AgentId('it-bg'), { model: 'mock' }) // Capture the generated id so the deterministic fixture is checked against // the real executor instead of silently assuming it. ctx.on('session/event', (_session, event) => { if (event.type === 'tool/result' && taskId === '') { const match = /task (bash-\d+)/.exec(resultText(event)) if (match) taskId = match[1]! } }) agent.send([{ type: 'text', text: 'run echo bg-ok in the background' }]) await waitForIdle(ctx, agent) expect(taskId).toBe('bash-1') // Wait for the background task itself (completion may race turn end). const task = ctx.bash.get(BashTaskId(taskId)) if (!task) throw new Error(`task ${taskId} not registered`) await task.done const log = events(agent) const firstResult = findEvent(log, 'tool/result') expect(resultText(firstResult)).toBe(`started background task ${taskId}`) const notice = findEvent(log, 'context/message') expect(notice.data.content.some( block => block.type === 'text' && block.text.includes(`background bash task ${taskId} finished`), )).toBe(true) expect(notice.data.source).toEqual({ kind: 'plugin', plugin: 'tool-bash' }) }) })