P1 修复面收口: Prompt Cache 根治(日期/记忆/附件三类易变内容出 system 入用户消息 前置块 user-context.ts, system 跨 run 字节级稳定; Anthropic system 块数组化 + cache_control ephemeral 断言, DeepSeek 自动缓存前缀命中 — 多轮对话输入 token 成本降数量级); 编辑重发/重新生成幽灵 Trace 双侧根治(DB truncateMessagesAfter 同步过滤 metadata.traceSteps + 前端 trimTraceStepsByAnchor 镜像, 严格小于锚点 时间戳, 同毫秒等值判废); sessions:deleteMessage 死通道全链路删除(渲染层零调用 + message_count 漂移面); Ollama vision 能力门控全链路(MetonaModelInfo .supportsVision 贯穿 adapter/IPC/store/UI, model-capabilities.ts 三道判定纯函数, 未知保守放行); 记忆固化节流(consolidation-policy 纯函数: 总开关 + 内容门控 [回答>=200字符或存在成功工具调用] + 会话级 10 分钟频率窗口, 三 memory.* 配置键) P2 安全纵深: SSRF DNS Pinning 关闭 rebinding 窗口(ssrf-guard 重构 resolvePublicAddresses 单源; ssrf-dispatcher 以 undici Agent.connect.lookup 钉死校验 IP, TLS SNI 保持原域名, 一次性 dispatcher 用后即毁; 代理激活显式 退化为仅入口校验); web_fetch 重写手动逐跳重定向循环(每跳先校验后连接, 替代 redirect:follow 内核跟跳的中间跳裸奔, 上限 5 跳); http_request 换用 pinned fetch; web_search 可达性预检加固(私有 URL 零请求 + 不跟跳, 3xx 视为 可达); Agent 浏览器 CORS 通配收紧为 Origin 回显 + Vary: Origin; ConfirmationHook.forgetSession 会话终态清理(会话删除/abort 联动/SubAgent 终结三处接线, 根治 rememberedDecisions 泄漏) P3 架构还债: agent.enableReflection 死配置全链路接线(main→shared→引擎→ Orchestrator→设置开关, REFLECTING 状态真实可达); AgentLoopConfig.timeoutMs 死字段删除; MemoryManager.cleanupExpired 挂入健康检查周期(expires_at 回收 管道真实化); buildSafeEnv 收敛 utils/safe-env.ts 单源(run_command 与 MCP stdio 共用, 终结双实现漂移); Trace 生命周期治理(metadata 只保留最近 20 个 run — keepRecentRuns 纯函数; JSONL 录制启动自动清理保留 200 个 + 设置页 手动清理); SLO/健康快照可视化(app:healthSnapshot IPC + 设置页只读卡片 + 审计链一键校验) P4 能力演进: 会话标题 LLM 自动生成(TitleGenerator — 每会话幂等/并发重入复用 同一 Promise/自定义标题不覆盖/失败静默回退, Sidebar 经 config:changed 实时 刷新); MCP 自动重连(5s/15s/60s 退避最多 3 次, reconnecting 状态机, teardownConnection 内部拆除保留簿记 — 用户断开/开关关闭即时取消, 设置页 显示第 N/3 次); 死循环检测 ABAB 乒乓模式(最近4轮 A→B→A→B 交替判定, 补齐 docs 第五章"两状态反复切换"检测契约); i18n 第三阶段(ChatInput/LLMSettings/ OnboardingWizard/MemoryViewer 主链路文案出层, zh-CN + en-US 双字典补齐) 测试: 737 → 824 用例(+87, 新增 8 个测试文件 + 扩展 3 个)。新覆盖: user-context 分组/空值收缩/拼接契约、context-builder 字节级稳定性、Anthropic cache_control 四态、consolidation-policy 九路判定矩阵、ssrf-dispatcher(pinned lookup/重定向 解析/IP 校验)、forget-session 会话隔离、trace-lifecycle run 淘汰、 trace-trim 严格小于边界、safe-env 净化矩阵、mcp-reconnect 退避状态机 (fake timers)、title-generator 并发重入、SQLite 侧 truncate×TRACE 联动 (Electron ABI)。测试驱动修复: GIT_*/ 注释终止块注释、重连计数被自身重试 前置断开重置(拆 teardownConnection 保留簿记)、TitleGenerator 幂等占位与 并发去重的检查顺序竞态(去重先于幂等) 版本: 0.7.3; README 同步(配置表新增 agent.enableReflection/memory.*/mcp.autoReconnect) 回归: typecheck 双端 0 错误; ESLint 0/0; 系统 Node 771 通过 53 跳过 (better-sqlite3 ABI); Electron ABI 全量 824/824 零跳过
134 lines
4.3 KiB
TypeScript
134 lines
4.3 KiB
TypeScript
/**
|
||
* Anthropic system cache_control 断言测试(v0.7.3 P1-1)
|
||
*
|
||
* Anthropic 缓存按"内容块前缀"命中:system 必须以块数组传递并在块上打
|
||
* cache_control 才可缓存。本文件锁定:
|
||
* C1 非空 system → 块数组 + {type:'ephemeral'};
|
||
* C2 空 system → 保持空字符串(不发空块);
|
||
* C3 thinking 模式下断言仍然存在(cache 与 thinking 不互斥);
|
||
* C4 system 块文本为四分区完整拼接(roleDefinition/outputConstraints/
|
||
* safetyGuidelines/dynamicReminders)。
|
||
*/
|
||
|
||
import { describe, it, expect, vi, afterEach } from 'vitest';
|
||
|
||
vi.mock('electron-log', () => ({
|
||
default: { info: vi.fn(), warn: vi.fn(), error: vi.fn(), debug: vi.fn() },
|
||
}));
|
||
|
||
import { AnthropicAdapter } from '../anthropic.adapter';
|
||
import type { MetonaRequest } from '../../types';
|
||
|
||
function captureFetch(): { bodies: Array<Record<string, unknown>> } {
|
||
const bodies: Array<Record<string, unknown>> = [];
|
||
const genericBody = {
|
||
content: [{ type: 'text', text: 'ok' }],
|
||
usage: { input_tokens: 3, output_tokens: 2 },
|
||
stop_reason: 'end_turn',
|
||
};
|
||
const fetchMock = vi.fn(async (_url: string | URL, init?: RequestInit) => {
|
||
bodies.push(JSON.parse(String(init?.body ?? '{}')) as Record<string, unknown>);
|
||
return new Response(JSON.stringify(genericBody), {
|
||
status: 200,
|
||
headers: { 'Content-Type': 'application/json' },
|
||
});
|
||
});
|
||
vi.stubGlobal('fetch', fetchMock);
|
||
return { bodies };
|
||
}
|
||
|
||
afterEach(() => {
|
||
vi.unstubAllGlobals();
|
||
});
|
||
|
||
function makeAdapter(): AnthropicAdapter {
|
||
return new AnthropicAdapter({
|
||
provider: 'anthropic',
|
||
baseURL: 'http://a.test',
|
||
apiKey: 'k',
|
||
defaultModel: 'claude-sonnet-4-5',
|
||
});
|
||
}
|
||
|
||
function makeRequest(overrides?: Partial<MetonaRequest>): MetonaRequest {
|
||
return {
|
||
meta: {
|
||
sessionId: 's1',
|
||
iteration: 1,
|
||
requestId: 'r1',
|
||
timestamp: Date.now(),
|
||
agentVersion: 'test',
|
||
},
|
||
systemPrompt: {
|
||
roleDefinition: 'You are Metona.',
|
||
outputConstraints: 'Be concise.',
|
||
safetyGuidelines: 'Stay safe.',
|
||
dynamicReminders: '## Current Workspace\n`/ws`',
|
||
},
|
||
messages: [{ role: 'user', content: 'hi', timestamp: Date.now() }],
|
||
params: { maxTokens: 63_488, temperature: 0, stream: false },
|
||
...overrides,
|
||
};
|
||
}
|
||
|
||
describe('AnthropicAdapter — system cache_control(P1-1)', () => {
|
||
it('C1: 非空 system → 单 text 块 + cache_control ephemeral', async () => {
|
||
const adapter = makeAdapter();
|
||
const { bodies } = captureFetch();
|
||
await adapter.send(makeRequest());
|
||
|
||
const system = bodies[0].system as Array<{
|
||
type: string;
|
||
text: string;
|
||
cache_control: { type: string };
|
||
}>;
|
||
expect(Array.isArray(system)).toBe(true);
|
||
expect(system).toHaveLength(1);
|
||
expect(system[0].type).toBe('text');
|
||
expect(system[0].cache_control).toEqual({ type: 'ephemeral' });
|
||
});
|
||
|
||
it('C2: 空 system → 保持空字符串(不发空块)', async () => {
|
||
const adapter = makeAdapter();
|
||
const { bodies } = captureFetch();
|
||
await adapter.send(
|
||
makeRequest({
|
||
systemPrompt: { roleDefinition: '', outputConstraints: '', safetyGuidelines: '' },
|
||
}),
|
||
);
|
||
expect(bodies[0].system).toBe('');
|
||
});
|
||
|
||
it('C3: thinking 模式下 cache_control 断言仍然存在', async () => {
|
||
const adapter = makeAdapter();
|
||
const { bodies } = captureFetch();
|
||
await adapter.send(
|
||
makeRequest({
|
||
params: {
|
||
maxTokens: 8192,
|
||
temperature: 0,
|
||
stream: false,
|
||
thinkingEnabled: true,
|
||
thinkingEffort: 'high',
|
||
},
|
||
}),
|
||
);
|
||
const system = bodies[0].system as Array<{ cache_control: { type: string } }>;
|
||
expect(system[0].cache_control).toEqual({ type: 'ephemeral' });
|
||
// thinking 与 cache 共存:thinking 块也在请求体中
|
||
expect(bodies[0].thinking).toMatchObject({ type: 'enabled' });
|
||
});
|
||
|
||
it('C4: system 块文本为四分区完整拼接', async () => {
|
||
const adapter = makeAdapter();
|
||
const { bodies } = captureFetch();
|
||
await adapter.send(makeRequest());
|
||
|
||
const system = bodies[0].system as Array<{ text: string }>;
|
||
expect(system[0].text).toContain('You are Metona.');
|
||
expect(system[0].text).toContain('Be concise.');
|
||
expect(system[0].text).toContain('Stay safe.');
|
||
expect(system[0].text).toContain('## Current Workspace');
|
||
});
|
||
});
|