P0 会话可靠性收口(根治"模型思考着会话就停止"): - P0-1 finish_reason 全链路贯通:DONE 事件与 IterationStep 新增 finishReason,OpenAI 共享 SSE / Anthropic message_delta.stop_reason / Ollama done_reason 三路采集,TRACE 层弃用硬编码 'stop' 记录真值 - P0-2 空响应守卫 + 降级重试:零产出流→可重试错误走退避;思考耗尽输出预算(reasoning-only + length)→自动关闭思考降级重试一次;仍失败→OUTPUT_LENGTH_EXCEEDED 结构化错误 + 故障转移;附带根治 abort 恰逢零工具调用轮被 COMPLETED 抢占的真实缺陷 - P0-3 思考×能力×预算三对齐:DeepSeek/MiMo/Agnes/Ollama 四家 supportsThinking=false 强制不发思考参数;小输出预算告警;设置页联动提示 - P0-4 渲染层可见性:截断/空完成/友好错误三类提示,i18n 全部出层 - P0-5 回归四件套:reasoning-only 终止判定、集成级空闲超时、504 引擎重试归类、思考中 abort→USER_INTERRUPT、P4-2 强制收尾路径 FEAT-1:LLM 设置新增「最大输出上限」——Provider 支持矩阵显隐 + 模型上限钳制提示 + 超限保存警告 + llm.maxTokens 热生效 P1 修复面收口: - 渲染层三缺陷根治:后台会话回放缓冲(2000 条/4MB 有界 + agent:getReplayState + 事件总线)+ abort 双层自愈 + sendMessage 收尾兜底 + 中断卡片清扫 - 工具 abort 信号全覆盖:web_search/web_fetch/http_request/code_search/git 系列/delegate_task 全部接入引擎中断;web_search 时间预算收敛(720s→≤240s);移除伪造 ToolExecutionContext 与死代码 - 安全:本地 Pinned CONNECT 代理根治浏览器通道 DNS rebinding(校验期 IP pinning,可注入 resolver 表测);配置 URL 域名解析深校验(DeepCheckSoftFailure 软失败);SSE 空 error 帧防御修复;Ollama generate/embed AbortSignal.any 合并 - 缺陷清单:UTF-16 BOM 读取、tmp 同毫秒碰撞(nanoid 后缀)、code_search JS 回退参数对称(case_sensitive/前后文独立)、list_directory include_node_modules、崩溃自愈退避(60s 窗 ≥3 次停 reload)、MemoryViewer/Sidebar i18n 收口 P2 能力演进: - 会话回收站:SCHEMA_VERSION 3 + 迁移 10(deleted_at,存在性守卫),软删除/恢复/彻底删除/30 天自动清理(启动+24h),searchMessages 聚合剔除,Sidebar 回收站面板 - 会话回放播放器:sessions:listRecordings/readRecording(白名单+目录边界+20MB 上限),SessionReplayPlayer 时间轴/步进/变速,Trace 面板入口 - electron-updater 自动更新:双轨(手动 feed 比对保留),生产环境启动静默检查 + update:status 广播 + app:updateInstall + LogsSettings UpdatePanel + builder publish 配置 - @ 文件提及:workspace.listFiles/readFileClip(边界/512KB/NUL 拒绝/MEMORY.md 保护),ChatInput Fuse 联想+键盘导航+附件管线注入 - MCP Resources/Prompts 发现:可选能力 try/catch 降级,mcp:listServerContents,MCPSettings 展开视图 - 文档对齐:内部 API 标准 HTML(Adapter 清单补 MiMo/已实现注记/STREAM_RESET/DONE.finishReason/ repetition_truncation 映射);README v0.8.0 亮点表 P3 测试基建: - 新增 4 个测试文件:engine-stream-contract(6)、engine-stream-reliability(4:集成空闲超时/504 重试/思考中 abort/P4-2 强制收尾)、thinking-capability-gate(7)、pinned-proxy(9,含深校验 5)、session-trash(5,DB 域)、use-agent-stream hook 级(5)、agent.test 回放缓冲(2) - 契约更新:orchestrator 被中断 SubAgent success=false(abort 优先级修复语义)、SSE 空 error 帧、UTF-16 正常读取、DeepSeek 未配置思考显式 disabled、迁移矩阵 v2→3 - 弱断言根治:registry WEBP 单向断言、hooks-contracts 自比恒真、memory 空 token 补强 全量验证:typecheck 0 错误 / lint 0 问题 / 系统 Node 2144 通过(301 DB 用例按 ABI 跳过)/ Electron ABI 2445/2445 全量通过 0 跳过
148 lines
5.3 KiB
TypeScript
148 lines
5.3 KiB
TypeScript
/**
|
||
* truncateMessagesAfter × TRACE metadata 联动测试(v0.7.3 P1-2)
|
||
*
|
||
* 根治契约:编辑重发/重新生成截断消息时,sessions.metadata 中的 traceSteps
|
||
* 必须按 startedAt <= 锚点消息 created_at 同步过滤,否则 Trace 面板出现
|
||
* "幽灵步骤"(v0.7.2 A1 只修了 /clear 路径的 metadata 残留)。
|
||
*
|
||
* 运行要求:better-sqlite3 为 Electron ABI 构建,需 test:electron 模式执行;
|
||
* 系统 Node 下自动跳过。
|
||
*/
|
||
|
||
import { describe, it, expect, beforeAll, afterAll, vi } from 'vitest';
|
||
|
||
vi.mock('electron-log', () => ({
|
||
default: { info: vi.fn(), warn: vi.fn(), error: vi.fn(), debug: vi.fn() },
|
||
}));
|
||
|
||
let dbAvailable = true;
|
||
let Database: typeof import('better-sqlite3');
|
||
try {
|
||
// eslint-disable-next-line @typescript-eslint/no-require-imports
|
||
Database = require('better-sqlite3');
|
||
const probe = new Database(':memory:');
|
||
probe.close();
|
||
} catch {
|
||
dbAvailable = false;
|
||
}
|
||
|
||
describe.skipIf(!dbAvailable)('truncateMessagesAfter × TRACE metadata 过滤(P1-2)', () => {
|
||
let db: import('better-sqlite3').Database;
|
||
// 测试域宽松类型:SessionService 依赖 Electron ABI 的 better-sqlite3 实例,
|
||
// 直接持有真实实例即可(同 session-summary.test.ts 的既有写法)
|
||
// eslint(next-line 无需禁用:测试文件未启用 no-explicit-any)
|
||
let sessionService: any;
|
||
|
||
beforeAll(async () => {
|
||
const { SessionService } = await import('../session.service');
|
||
db = new Database(':memory:');
|
||
db.exec(`
|
||
CREATE TABLE sessions (
|
||
id TEXT PRIMARY KEY,
|
||
title TEXT DEFAULT '新会话',
|
||
created_at INTEGER NOT NULL,
|
||
updated_at INTEGER NOT NULL,
|
||
message_count INTEGER DEFAULT 0,
|
||
pinned INTEGER DEFAULT 0,
|
||
archived INTEGER DEFAULT 0,
|
||
deleted_at INTEGER,
|
||
metadata TEXT DEFAULT '{}'
|
||
);
|
||
CREATE TABLE messages (
|
||
id TEXT PRIMARY KEY,
|
||
session_id TEXT NOT NULL,
|
||
role TEXT NOT NULL,
|
||
content TEXT,
|
||
reasoning_content TEXT,
|
||
tool_calls TEXT,
|
||
tool_result TEXT,
|
||
attachments TEXT,
|
||
iteration INTEGER,
|
||
created_at INTEGER NOT NULL
|
||
);
|
||
CREATE TABLE session_summaries (
|
||
session_id TEXT PRIMARY KEY,
|
||
summary TEXT NOT NULL,
|
||
summarized_until_rowid INTEGER NOT NULL,
|
||
updated_at INTEGER NOT NULL DEFAULT (unixepoch() * 1000)
|
||
);
|
||
`);
|
||
db.prepare(
|
||
'INSERT INTO sessions (id, created_at, updated_at, message_count) VALUES (?, ?, ?, 0)',
|
||
).run('s_trace', Date.now(), Date.now());
|
||
sessionService = new SessionService(() => db);
|
||
});
|
||
|
||
afterAll(() => {
|
||
try {
|
||
db?.close();
|
||
} catch {
|
||
/* ignore */
|
||
}
|
||
});
|
||
|
||
const insertMessage = (id: string, content: string, createdAt: number): number => {
|
||
db.prepare(
|
||
`INSERT INTO messages (id, session_id, role, content, created_at) VALUES (?, ?, 'user', ?, ?)`,
|
||
).run(id, 's_trace', content, createdAt);
|
||
const row = db.prepare('SELECT rowid AS rid FROM messages WHERE id = ?').get(id) as {
|
||
rid: number;
|
||
};
|
||
return row.rid;
|
||
};
|
||
|
||
const saveMetadata = (steps: Array<{ runId?: string; startedAt: number }>): void => {
|
||
db.prepare('UPDATE sessions SET metadata = ? WHERE id = ?').run(
|
||
JSON.stringify({ traceSteps: steps, tokenUsage: { totalTokens: 10 } }),
|
||
's_trace',
|
||
);
|
||
};
|
||
|
||
const loadMetadataSteps = (): Array<{ runId?: string; startedAt: number }> => {
|
||
const row = db.prepare('SELECT metadata FROM sessions WHERE id = ?').get('s_trace') as {
|
||
metadata: string;
|
||
};
|
||
const parsed = JSON.parse(row.metadata) as {
|
||
traceSteps?: Array<{ runId?: string; startedAt: number }>;
|
||
};
|
||
return parsed.traceSteps ?? [];
|
||
};
|
||
|
||
it('截断后:晚于锚点消息的 traceSteps 被过滤,早于/等于的保留', () => {
|
||
const anchorTs = 1_000_000;
|
||
const anchorId = 'm_anchor';
|
||
insertMessage('m_before', '更早的消息', anchorTs - 10_000);
|
||
insertMessage(anchorId, '锚点消息', anchorTs);
|
||
insertMessage('m_after', '锚点后的消息', anchorTs + 10_000);
|
||
|
||
saveMetadata([
|
||
{ runId: 'r_before', startedAt: anchorTs - 9_000 },
|
||
{ runId: 'r_anchor', startedAt: anchorTs }, // 锚点触发的 run(将被截)
|
||
{ runId: 'r_after', startedAt: anchorTs + 11_000 },
|
||
]);
|
||
|
||
const truncated = sessionService.truncateMessagesAfter('s_trace', anchorId, true);
|
||
expect(truncated).toBe(true);
|
||
|
||
const kept = loadMetadataSteps();
|
||
expect(kept.map((s) => s.runId)).toEqual(['r_before']);
|
||
});
|
||
|
||
it('metadata 缺失/损坏时不阻断截断主流程', () => {
|
||
db.prepare("UPDATE sessions SET metadata = 'not-json' WHERE id = ?").run('s_trace');
|
||
const anchorTs = 2_000_000;
|
||
const anchorId = 'm2';
|
||
insertMessage(anchorId, '锚点消息 2', anchorTs);
|
||
insertMessage('m2_after', '锚点 2 之后的消息', anchorTs + 1000);
|
||
|
||
expect(() => sessionService.truncateMessagesAfter('s_trace', anchorId, true)).not.toThrow();
|
||
expect(sessionService.truncateMessagesAfter('s_trace', anchorId, true)).toBe(false); // 已被上一句删过,无行可删
|
||
});
|
||
|
||
it('锚点不存在时返回 false 且不触碰 metadata', () => {
|
||
saveMetadata([{ runId: 'r_keep', startedAt: Date.now() }]);
|
||
expect(sessionService.truncateMessagesAfter('s_trace', 'm_missing', true)).toBe(false);
|
||
expect(loadMetadataSteps()).toHaveLength(1);
|
||
});
|
||
});
|