Files
AirCoding/packages/runtime/test/e2e/direct-mode-fixture.test.ts
AirCoding a773bac28c P0-P8: Full V1.0.0 Alpha implementation + audit reports
Implements 123 tasks across 9 phases (T-001..T-809) totaling 146 source files.

Monorepo (P0):
- 7-package Bun + Turborepo + TypeScript monorepo
- dependency-cruiser enforcing 7 forbidden edges + 5 deep-import rules

Contracts (P0):
- 16 type files (ids/error/event/runtime/ipc/task/worker-result/tool/artifact/evidence/project/provider/permission/ui/capability/platform)

Storage & Events (P1):
- DatabaseManager + MigrationRunner (19 tables, 22 indexes, 5 schema_meta seeds)
- 16 repositories (Repository<T,I,U> pattern, INV-1 status columns via EventStore.project only)
- EventSchemaRegistry (54 durable + 7 ephemeral), EventStore, EventBus, EventIngestor
- Project/Session/Artifact/Evidence stores + 8-step Recovery

Tools & Permission (P2):
- PathClassifier (8 categories), CommandRiskAnalyzer (10 categories), SecretRedactor
- PermissionEngine 6-layer evaluation (capability→profile→task_scope→risk→credential→user_prompt)
- ToolRegistry with 20+ tools across fs/shell/git/project/artifact/context/permission/doctor
- CapabilityManifestValidator + CapabilityRegistry

LLM & Context (P3):
- ModelConfigLoader, CapabilityMatrix, AnthropicCanonicalConverter
- AnthropicAdapter + OpenAICompatibleAdapter
- ProviderManager facade
- PromptLayerLoader (L0/L1/L3/L5), CompactionPolicy, ContextAssembler

Worker IPC & Scheduler (P4):
- WorkerProtocol (NDJSON), WorkerProcess (exit codes 0-5), WorkerManager (spawn/handshake)
- WorkerRuntime (INV-3: IPC only, no direct fs/shell/SQLite)
- 5 worker roles (Executor/Reviewer/Debugger/Compactor/ExperienceMiner)
- TaskGraph, WavePlanner, RetryPlanner, AgentMonitor, WorkspaceManager
- Scheduler (state machine), 8-step Recovery

C++ Toolchain (P5):
- DiagnosticParser, CppProjectDetector, CMakeConfigurator, CppBuilder
- CppTestRunner, CppcheckRunner, ClangdClient
- CppToolRegistrar + capability manifest

Projection & TUI (P6):
- ProjectionStore (hydrate/apply/snapshot/subscribe)
- TuiApp + 8 components (Session/Task/Agent/Tool/Diff/Evidence/Permission/Blocker/Hud)
- ProjectionClient in-process ref

Agents & Knowledge (P7):
- MainAgent, ArchitectureDesigner
- DebugKnowledgeStore + LearnedMemoryStore (single-writer, outbox model)
- Role integration wiring

CLI & Doctor & Release (P8):
- Logger + DeveloperLogEncryptor (AES-256-GCM)
- DoctorService (self_bootstrap first)
- RuntimeApp + ServiceRegistry
- 11 CLI commands: run/init/doctor/provider/resume/compact/history/session/restore/e2e/release
- CliEntrypoint + air<TODO>

Audit (in AirPlan/docs/):
- Deepseek开发阶段审计.md (97 findings)
- Opus开发阶段审计.md (140+ findings, 18 P0 blockers)
- MiniMaxM3开发阶段审计.md (18 P0 blockers, focuses on executability)
- AirPlan/TODO.md (technical debt + 42 TODOs by phase)

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-02 19:19:55 +08:00

75 lines
2.6 KiB
TypeScript
Executable File

/**
* Direct-mode fixture E2E test — P7 gate
* Test: MainAgent direct-mode lifecycle.
*
* @module packages/runtime/test/e2e/direct-mode-fixture.test
*/
import { describe, it, expect } from 'bun:test'
import { MainAgent } from '../../src/agents/main/MainAgent.js'
describe('Direct Mode Fixture (P7 gate)', () => {
const config = {
session_id: 'test-session',
project_id: 'test-project'
}
describe('MainAgent lifecycle', () => {
it('should start in IDLE state', () => {
const agent = new MainAgent(config)
expect(agent.state).toBe('IDLE')
})
it('should classify implementation requests as DELEGATING', async () => {
const agent = new MainAgent(config)
const result = await agent.handle_user_message('implement a new feature X')
expect(result.action).toBe('delegate')
expect(agent.state).toBe('DELEGATING')
})
it('should classify questions as ANSWERING', async () => {
const agent = new MainAgent(config)
const result = await agent.handle_user_message('what does this function do?')
expect(result.action).toBe('answer')
expect(agent.state).toBe('ANSWERING')
})
it('should handle confirmation and transition states', async () => {
const agent = new MainAgent(config)
agent.state = 'AWAITING_CONFIRMATION'
await agent.handle_confirmation(true)
expect(agent.state).toBe('DELEGATING')
})
it('should summarise and return to IDLE', () => {
const agent = new MainAgent(config)
agent.state = 'DELEGATING'
agent.summarize()
expect(agent.state).toBe('IDLE')
})
})
describe('ArchitectureDesigner', () => {
it('should assess impact and return silent_continue for low-risk changes', async () => {
const { ArchitectureDesigner } = await import('../../src/agents/architecture/ArchitectureDesigner.js')
const arch = new ArchitectureDesigner()
const impact = arch.assess_impact({
description: 'Add a new helper function',
files: ['packages/runtime/src/utils/helper.ts']
})
expect(impact.result).toBe('silent_continue')
})
it('should escalate high-risk contract changes', async () => {
const { ArchitectureDesigner } = await import('../../src/agents/architecture/ArchitectureDesigner.js')
const arch = new ArchitectureDesigner()
const impact = arch.assess_impact({
description: 'BREAKING: remove the session event type',
files: ['packages/contracts/src/event.ts', 'packages/runtime/src/events/EventStore.ts', 'packages/runtime/src/events/EventBus.ts']
})
expect(impact.result).toBe('reject_or_escalate')
})
})
})