feat: v0.7.3 成本收口 · 状态一致 · 死账清理 — Prompt Cache 根治 + SSRF DNS Pinning + 87 用例扩充全量回归
CI / 类型检查 + Lint + 单元测试 (push) Failing after 5m47s
CI / 全量测试 (Electron ABI) (push) Failing after 5m19s
CI / 产物编译验证 (push) Successful in 9m55s

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
This commit is contained in:
2026-08-30 09:44:43 +08:00
parent 26169b7be4
commit ebe45482b0
68 changed files with 4568 additions and 664 deletions
@@ -0,0 +1,133 @@
/**
* 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_controlP1-1', () => {
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');
});
});