feat: v0.8.0 流语义补全 · 会话可靠 · 恢复力 — finish_reason 全链路贯通根治"思考中停止" · 2445 用例全量回归
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
This commit is contained in:
@@ -238,8 +238,10 @@ describe('DeepSeek vision 模型多模态请求格式（v0.5.4）', () => {
|
||||
} as MetonaRequest);
|
||||
|
||||
const body = requestBody();
|
||||
// vision 模型 supportsThinking=false，但参数仍透传 thinking enabled（引擎决定）
|
||||
expect(body.thinking).toEqual({ type: 'enabled' });
|
||||
// v0.8.0 P0-3 能力门控: vision 模型 supportsThinking=false → 显式 disabled，
|
||||
// 且不发送 reasoning_effort（思考会耗尽该模型 8192 输出预算 —— 生产事故根因）
|
||||
expect(body.thinking).toEqual({ type: 'disabled' });
|
||||
expect(body.reasoning_effort).toBeUndefined();
|
||||
});
|
||||
|
||||
it('vision 模型 messages 数组首位始终为 system 消息', async () => {
|
||||
|
||||
@@ -757,11 +757,14 @@ describe('DeepSeekAdapter — thinking 映射矩阵', () => {
|
||||
expect(bodies[0].reasoning_effort).toBeUndefined();
|
||||
});
|
||||
|
||||
it('thinkingEnabled 未配置 → 不发送 thinking 字段', async () => {
|
||||
it('thinkingEnabled 未配置 → 显式 disabled（v0.8.0 P0-3 确定性契约）', async () => {
|
||||
// v0.8.0 P0-3 契约变更: DeepSeek 服务端默认 thinking.enabled，未配置即发请求
|
||||
// 会得到隐式思考 —— 现在未配置一律显式 disabled，行为不依赖服务端隐式默认
|
||||
//（与 Agnes/MiMo 的显式口径对齐；引擎路径恒传布尔值，此处为兜底确定性）。
|
||||
const adapter = makeAdapter();
|
||||
const { bodies } = captureFetch();
|
||||
await adapter.send(makeRequest({ params: { maxTokens: 4096, temperature: 0, stream: false } }));
|
||||
expect(bodies[0].thinking).toBeUndefined();
|
||||
expect(bodies[0].thinking).toEqual({ type: 'disabled' });
|
||||
});
|
||||
|
||||
it('effort 未配置缺省 high → reasoning_effort=high', async () => {
|
||||
|
||||
@@ -11,7 +11,7 @@ import {
|
||||
readStreamChunkWithIdleTimeout,
|
||||
SseUpstreamError,
|
||||
} from '../shared/sse-stream';
|
||||
import { MetonaStreamEventType } from '../../types';
|
||||
import { MetonaStreamEventType, type MetonaStreamEvent } from '../../types';
|
||||
|
||||
/** 构造 SSE 测试流 */
|
||||
function makeStream(chunks: string[]): ReadableStream<Uint8Array> {
|
||||
@@ -586,13 +586,33 @@ describe('parseSSEStream — 上游错误帧 status 推断矩阵', () => {
|
||||
expect((err as SseUpstreamError).status).toBe(503);
|
||||
});
|
||||
|
||||
it('error 为空对象 → 回退 message 为 {}（JSON.stringify 兜底使其仍被识别为错误帧）', async () => {
|
||||
// 源码注明的防御意图是无害空对象不报错，但 message 兜底取 JSON.stringify({})='{}'，
|
||||
// 恒真值使该防御分支失效 —— 此处锁定实际行为并留档（见报告）。
|
||||
const err = await collectError({ error: {} });
|
||||
it('error 为空对象 → 不构成错误帧（v0.8.0 P1-3.1 防御分支根治后契约）', async () => {
|
||||
// v0.8.0 P1-3.1 根治: 旧实现 message 兜底取 JSON.stringify({})='{}' 恒真值，
|
||||
// `{"error":{}}` 被误判为错误帧抛 SseUpstreamError 并触发不必要的重试。
|
||||
// 新契约：无 message 且无 status/code 标识的空对象为无害帧，静默跳过。
|
||||
const events: MetonaStreamEvent[] = [];
|
||||
let error: Error | null = null;
|
||||
try {
|
||||
for await (const ev of parseSSEStream(
|
||||
makeStream(['data: {"error":{}}\n\n', 'data: [DONE]\n\n']),
|
||||
'r',
|
||||
's',
|
||||
1,
|
||||
)) {
|
||||
events.push(ev);
|
||||
}
|
||||
} catch (e) {
|
||||
error = e as Error;
|
||||
}
|
||||
expect(error).toBeNull();
|
||||
expect(events.some((ev) => ev.type === MetonaStreamEventType.DONE)).toBe(true);
|
||||
});
|
||||
|
||||
it('error 有 code 无 message → 仍构成错误帧（标识存在，占位文案兜底）', async () => {
|
||||
const err = await collectError({ error: { code: 'rate_limit_exceeded' } });
|
||||
expect(err).toBeInstanceOf(SseUpstreamError);
|
||||
expect((err as Error).message).toContain('upstream_error');
|
||||
expect((err as SseUpstreamError).status).toBeUndefined();
|
||||
expect((err as SseUpstreamError).status).toBe(429);
|
||||
});
|
||||
|
||||
it('error 为空白字符串 → 不算错误帧', async () => {
|
||||
|
||||
@@ -0,0 +1,159 @@
|
||||
/**
|
||||
* v0.8.0 P0-3: 思考参数 × 模型能力 门控矩阵。
|
||||
*
|
||||
* 根因回顾：MODEL_INFO 标注 supportsThinking:false 的模型（如
|
||||
* deepseek-v4-flash-vision-exp）此前仍被发送 thinking 参数 —— 思考耗尽输出
|
||||
* 预算（8192 上限）导致 finish_reason=length 空回复、会话静默停止。
|
||||
* 本文件钉住四家 Provider 的能力门控行为与输出预算告警前置条件。
|
||||
*/
|
||||
|
||||
import { describe, it, expect } from 'vitest';
|
||||
import { DeepSeekAdapter } from '../deepseek.adapter';
|
||||
import { AgnesAdapter } from '../agnes-ai.adapter';
|
||||
import { MimoAdapter } from '../mimo.adapter';
|
||||
import { OllamaAdapter } from '../ollama.adapter';
|
||||
import type { MetonaRequest } from '../../types';
|
||||
|
||||
const SYSTEM_PROMPT = {
|
||||
roleDefinition: 'test',
|
||||
outputConstraints: '',
|
||||
safetyGuidelines: '',
|
||||
};
|
||||
|
||||
function makeRequest(overrides?: Partial<MetonaRequest['params']>): MetonaRequest {
|
||||
return {
|
||||
meta: {
|
||||
sessionId: 's',
|
||||
iteration: 1,
|
||||
requestId: 'r',
|
||||
timestamp: Date.now(),
|
||||
agentVersion: '1.0.0',
|
||||
},
|
||||
systemPrompt: SYSTEM_PROMPT,
|
||||
messages: [{ role: 'user', content: 'hi', timestamp: Date.now() }],
|
||||
params: {
|
||||
maxTokens: 63488,
|
||||
temperature: 0,
|
||||
stream: true,
|
||||
thinkingEnabled: true,
|
||||
thinkingEffort: 'max',
|
||||
...overrides,
|
||||
},
|
||||
};
|
||||
}
|
||||
|
||||
function asNative(
|
||||
adapter: unknown,
|
||||
): (req: MetonaRequest, stream: boolean) => Record<string, unknown> {
|
||||
return (
|
||||
adapter as { toNativeRequest: (r: MetonaRequest, s: boolean) => Record<string, unknown> }
|
||||
).toNativeRequest.bind(adapter);
|
||||
}
|
||||
|
||||
describe('P0-3 thinking capability gate', () => {
|
||||
it('DeepSeek: vision-exp (supportsThinking:false) → thinking disabled, no reasoning_effort, max_tokens clamped to 8192', async () => {
|
||||
const adapter = new DeepSeekAdapter({
|
||||
provider: 'deepseek',
|
||||
baseURL: 'https://api.deepseek.com',
|
||||
apiKey: 'k',
|
||||
defaultModel: 'deepseek-v4-flash-vision-exp',
|
||||
});
|
||||
const body = asNative(adapter)(makeRequest(), false);
|
||||
expect(body.thinking).toEqual({ type: 'disabled' });
|
||||
expect(body.reasoning_effort).toBeUndefined();
|
||||
expect(body.max_tokens).toBe(8192);
|
||||
});
|
||||
|
||||
it('DeepSeek: pro (supportsThinking:true) → thinking enabled + reasoning_effort mapped (max→max)', async () => {
|
||||
const adapter = new DeepSeekAdapter({
|
||||
provider: 'deepseek',
|
||||
baseURL: 'https://api.deepseek.com',
|
||||
apiKey: 'k',
|
||||
defaultModel: 'deepseek-v4-pro',
|
||||
});
|
||||
const body = asNative(adapter)(makeRequest(), false);
|
||||
expect(body.thinking).toEqual({ type: 'enabled' });
|
||||
expect(body.reasoning_effort).toBe('max');
|
||||
});
|
||||
|
||||
it('Agnes: supportsThinking:false model → enable_thinking:false', async () => {
|
||||
const adapter = new AgnesAdapter({
|
||||
provider: 'agnes',
|
||||
baseURL: 'https://apihub.agnes-ai.com/v1',
|
||||
apiKey: 'k',
|
||||
defaultModel: 'agnes-2.0-flash',
|
||||
});
|
||||
// 临时改写元信息模拟"不支持思考"的模型，结束后恢复
|
||||
const table = AgnesAdapter['MODEL_INFO'] as Record<string, { supportsThinking: boolean }>;
|
||||
const original = table['agnes-2.0-flash'].supportsThinking;
|
||||
table['agnes-2.0-flash'].supportsThinking = false;
|
||||
try {
|
||||
const body = asNative(adapter)(makeRequest(), false);
|
||||
expect(body.chat_template_kwargs).toEqual({ enable_thinking: false });
|
||||
} finally {
|
||||
table['agnes-2.0-flash'].supportsThinking = original;
|
||||
}
|
||||
});
|
||||
|
||||
it('Agnes: supportsThinking:true model → enable_thinking:true', async () => {
|
||||
const adapter = new AgnesAdapter({
|
||||
provider: 'agnes',
|
||||
baseURL: 'https://apihub.agnes-ai.com/v1',
|
||||
apiKey: 'k',
|
||||
defaultModel: 'agnes-2.0-flash',
|
||||
});
|
||||
const body = asNative(adapter)(makeRequest(), false);
|
||||
expect(body.chat_template_kwargs).toEqual({ enable_thinking: true });
|
||||
});
|
||||
|
||||
it('MiMo: supportsThinking:false model → thinking disabled + temperature passthrough', async () => {
|
||||
const adapter = new MimoAdapter({
|
||||
provider: 'mimo',
|
||||
baseURL: 'https://api.xiaomimimo.com/v1',
|
||||
apiKey: 'k',
|
||||
defaultModel: 'mimo-v2.5-pro',
|
||||
});
|
||||
const table = MimoAdapter['MODEL_INFO'] as Record<string, { supportsThinking: boolean }>;
|
||||
const original = table['mimo-v2.5-pro'].supportsThinking;
|
||||
table['mimo-v2.5-pro'].supportsThinking = false;
|
||||
try {
|
||||
const body = asNative(adapter)(makeRequest(), false);
|
||||
expect(body.thinking).toEqual({ type: 'disabled' });
|
||||
expect(body.temperature).toBe(0);
|
||||
} finally {
|
||||
table['mimo-v2.5-pro'].supportsThinking = original;
|
||||
}
|
||||
});
|
||||
|
||||
it('Ollama: probed no-thinking (cachedThinkingSupport=false) → no think parameter', async () => {
|
||||
const adapter = new OllamaAdapter({
|
||||
provider: 'ollama',
|
||||
baseURL: 'http://localhost:11434',
|
||||
apiKey: '',
|
||||
defaultModel: 'qwen3:latest',
|
||||
});
|
||||
(adapter as unknown as { cachedThinkingSupport: boolean | null }).cachedThinkingSupport = false;
|
||||
const body = await (
|
||||
adapter as unknown as {
|
||||
toNativeRequest: (r: MetonaRequest) => Promise<Record<string, unknown>>;
|
||||
}
|
||||
).toNativeRequest(makeRequest());
|
||||
expect(body.think).toBeUndefined();
|
||||
});
|
||||
|
||||
it('Ollama: probe unknown (null) fails open → think parameter present', async () => {
|
||||
const adapter = new OllamaAdapter({
|
||||
provider: 'ollama',
|
||||
baseURL: 'http://localhost:11434',
|
||||
apiKey: '',
|
||||
defaultModel: 'qwen3:latest',
|
||||
});
|
||||
(adapter as unknown as { cachedThinkingSupport: boolean | null }).cachedThinkingSupport = null;
|
||||
const body = await (
|
||||
adapter as unknown as {
|
||||
toNativeRequest: (r: MetonaRequest) => Promise<Record<string, unknown>>;
|
||||
}
|
||||
).toNativeRequest(makeRequest());
|
||||
expect(body.think).toBe(true); // effort=max → true
|
||||
});
|
||||
});
|
||||
@@ -56,7 +56,10 @@ export class AgnesAdapter extends OpenAICompatibleAdapter {
|
||||
|
||||
// ========== 协议参数映射（Agnes 差异点） ==========
|
||||
|
||||
protected override toNativeRequest(request: MetonaRequest, stream: boolean): Record<string, unknown> {
|
||||
protected override toNativeRequest(
|
||||
request: MetonaRequest,
|
||||
stream: boolean,
|
||||
): Record<string, unknown> {
|
||||
// v0.6.2: images 处理收敛至共享层（原索引对齐循环在孤立 tool 过滤后会错位）
|
||||
const messages = buildOpenAICompatibleMessages(request, true);
|
||||
const tools = buildOpenAICompatibleTools(request.tools);
|
||||
@@ -96,12 +99,21 @@ export class AgnesAdapter extends OpenAICompatibleAdapter {
|
||||
// 显式发送 enable_thinking:false —— 原实现只在 thinkingEnabled===true 时写该字段，
|
||||
// 若服务端默认开启思考，客户端没有任何路径把它关掉（DeepSeek/MiMo 均显式发送
|
||||
// disabled 保持对称，唯独此处漏了）。
|
||||
// v0.8.0 P0-3: 模型能力门控 —— supportsThinking===false 的模型强制关闭思考
|
||||
{
|
||||
const effort = request.params.thinkingEffort ?? 'high';
|
||||
const modelThinkingSupported =
|
||||
AgnesAdapter.MODEL_INFO[this.config.defaultModel]?.supportsThinking !== false;
|
||||
// 未配置 thinkingEnabled 一律显式关闭 —— 与 DeepSeek/MiMo 的"服务端默认开启，
|
||||
// 必须显式发送 disabled"口径对齐，让行为确定性不依赖服务端隐式默认。
|
||||
const wantThinking = request.params.thinkingEnabled === true && effort !== 'low';
|
||||
const wantThinking =
|
||||
request.params.thinkingEnabled === true && effort !== 'low' && modelThinkingSupported;
|
||||
body.chat_template_kwargs = { enable_thinking: wantThinking };
|
||||
if (request.params.thinkingEnabled === true && !modelThinkingSupported) {
|
||||
log.warn(
|
||||
`[Agnes] model "${this.config.defaultModel}" does not support thinking — sending enable_thinking:false (P0-3 capability gate)`,
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
// 停止序列
|
||||
|
||||
@@ -24,6 +24,28 @@ import type { MetonaRequest, MetonaResponse, MetonaStreamEvent } from '../types'
|
||||
import { MetonaFinishReason, MetonaStreamEventType } from '../types';
|
||||
import type { MetonaModelInfo } from '../types/metona-adapter';
|
||||
|
||||
/**
|
||||
* v0.8.0 P0-1: Anthropic stop_reason → 归一化 OpenAI 语义（与 MetonaFinishReason
|
||||
* 的非流式映射语义一致）。pause_turn（长回复暂停续传标记）视为自然停止。
|
||||
*/
|
||||
function mapAnthropicStopReason(reason: string): string {
|
||||
switch (reason) {
|
||||
case 'max_tokens':
|
||||
return 'length';
|
||||
case 'tool_use':
|
||||
return 'tool_calls';
|
||||
case 'refusal':
|
||||
case 'content_filter':
|
||||
return 'content_filter';
|
||||
case 'end_turn':
|
||||
case 'pause_turn':
|
||||
case 'stop_sequence':
|
||||
return 'stop';
|
||||
default:
|
||||
return 'stop';
|
||||
}
|
||||
}
|
||||
|
||||
export class AnthropicAdapter extends BaseAdapter {
|
||||
override readonly providerId: string = 'anthropic';
|
||||
readonly supportedModels = ['claude-sonnet-4-5', 'claude-opus-4-1', 'claude-haiku-4-5'];
|
||||
@@ -116,6 +138,10 @@ export class AnthropicAdapter extends BaseAdapter {
|
||||
let buffer = '';
|
||||
let eventName = '';
|
||||
let streamEndedNormally = false;
|
||||
// v0.8.0 P0-1: 采集 message_delta.delta.stop_reason —— Anthropic 的停止原因
|
||||
// 在 message_delta（而非 message_stop）事件携带；旧实现只读 usage，
|
||||
// max_tokens 截断在流式路径完全不可见（与 OpenAI 共享层 finish_reason 缺口同源）
|
||||
let streamStopReason: string | undefined;
|
||||
|
||||
// 工具调用缓冲：content block index → { id, name, argsBuffer }
|
||||
const toolBlocks = new Map<number, { id: string; name: string; argsBuffer: string }>();
|
||||
@@ -256,11 +282,22 @@ export class AnthropicAdapter extends BaseAdapter {
|
||||
},
|
||||
});
|
||||
}
|
||||
// v0.8.0 P0-1: 采集停止原因（message_delta.delta.stop_reason，可能在
|
||||
// 多个 message_delta 中重复出现，取任一即可；归一化为 OpenAI 语义）
|
||||
const delta = data.delta as Record<string, unknown> | undefined;
|
||||
if (delta && typeof delta.stop_reason === 'string') {
|
||||
streamStopReason = mapAnthropicStopReason(delta.stop_reason);
|
||||
}
|
||||
break;
|
||||
}
|
||||
case 'message_stop': {
|
||||
streamEndedNormally = true;
|
||||
events.push({ type: MetonaStreamEventType.DONE, ...base() });
|
||||
events.push({
|
||||
type: MetonaStreamEventType.DONE,
|
||||
...base(),
|
||||
// v0.8.0 P0-1: 携带归一化停止原因
|
||||
...(streamStopReason ? { finishReason: streamStopReason } : {}),
|
||||
});
|
||||
break;
|
||||
}
|
||||
case 'error': {
|
||||
@@ -362,7 +399,13 @@ export class AnthropicAdapter extends BaseAdapter {
|
||||
log.warn('[Anthropic] Stream ended without message_stop (connection likely dropped)');
|
||||
}
|
||||
toolBlocks.clear();
|
||||
yield { type: MetonaStreamEventType.DONE, ...base() };
|
||||
yield {
|
||||
type: MetonaStreamEventType.DONE,
|
||||
...base(),
|
||||
// v0.8.0 P0-1: 断流合成路径同样携带已观察到的停止原因
|
||||
//（断流时多为 undefined —— 引擎据此走空响应守卫/重试而非误判自然结束）
|
||||
...(streamStopReason ? { finishReason: streamStopReason } : {}),
|
||||
};
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -164,7 +164,10 @@ export class DeepSeekAdapter extends OpenAICompatibleAdapter {
|
||||
|
||||
// ========== 协议参数映射（DeepSeek 差异点） ==========
|
||||
|
||||
protected override toNativeRequest(request: MetonaRequest, stream: boolean): Record<string, unknown> {
|
||||
protected override toNativeRequest(
|
||||
request: MetonaRequest,
|
||||
stream: boolean,
|
||||
): Record<string, unknown> {
|
||||
// v0.6.2: images 处理收敛至共享层（includeImages = vision 模型才转换，
|
||||
// 非 vision 静默丢弃——正确行为，见 openai-format.ts #27 记录）
|
||||
const messages = buildOpenAICompatibleMessages(request, this.isVisionModel());
|
||||
@@ -200,10 +203,17 @@ export class DeepSeekAdapter extends OpenAICompatibleAdapter {
|
||||
}
|
||||
|
||||
// Thinking 模式
|
||||
// v0.8.0 P0-3 根治: 模型能力门控 —— MODEL_INFO.supportsThinking === false 的
|
||||
// 模型（如 deepseek-v4-flash-vision-exp）一律不发思考参数并显式 disabled，
|
||||
// 防止思考消耗输出预算（生产事故：vision-exp 8192 输出预算被 max 档思考
|
||||
// 全部烧光 → finish_reason=length 空回复 → 会话静默停止）。
|
||||
const modelThinkingSupported =
|
||||
DeepSeekAdapter.MODEL_INFO[this.config.defaultModel]?.supportsThinking !== false;
|
||||
const wantThinking = request.params.thinkingEnabled === true && modelThinkingSupported;
|
||||
// API 默认 thinking.type = "enabled"，必须显式发送 disabled 才能关闭
|
||||
if (request.params.thinkingEnabled === false) {
|
||||
if (!wantThinking) {
|
||||
body.thinking = { type: 'disabled' };
|
||||
} else if (request.params.thinkingEnabled) {
|
||||
} else {
|
||||
body.thinking = { type: 'enabled' };
|
||||
const effortMap: Record<string, string> = {
|
||||
low: 'high',
|
||||
@@ -213,6 +223,13 @@ export class DeepSeekAdapter extends OpenAICompatibleAdapter {
|
||||
};
|
||||
// DeepSeek API 仅支持 high / max 两档，low/medium 映射为 high
|
||||
body.reasoning_effort = effortMap[request.params.thinkingEffort ?? 'high'] ?? 'high';
|
||||
// v0.8.0 P0-3: 思考会占用输出预算 —— 钳制后预算过小时显式告警
|
||||
//（思考 token 计入 max_tokens，预算过小会出现"思考耗尽正文为零"截断）
|
||||
if (maxTokens < 8192) {
|
||||
log.warn(
|
||||
`[DeepSeek] thinking enabled with small output budget (${maxTokens} tokens after model clamp) — reasoning may consume the entire budget and truncate the answer`,
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
// 停止序列
|
||||
|
||||
@@ -11,6 +11,7 @@
|
||||
* @see apis/mimo-api-docs-20260715.html
|
||||
*/
|
||||
|
||||
import log from 'electron-log';
|
||||
import type { MetonaRequest } from '../types';
|
||||
import type { MetonaModelInfo } from '../types/metona-adapter';
|
||||
import { buildOpenAICompatibleMessages, buildOpenAICompatibleTools } from './shared/openai-format';
|
||||
@@ -72,7 +73,10 @@ export class MimoAdapter extends OpenAICompatibleAdapter {
|
||||
|
||||
// ========== 协议参数映射（MiMo 差异点） ==========
|
||||
|
||||
protected override toNativeRequest(request: MetonaRequest, stream: boolean): Record<string, unknown> {
|
||||
protected override toNativeRequest(
|
||||
request: MetonaRequest,
|
||||
stream: boolean,
|
||||
): Record<string, unknown> {
|
||||
// v0.6.2: images 处理收敛至共享层（原索引对齐循环在孤立 tool 过滤后会错位）
|
||||
const messages = buildOpenAICompatibleMessages(request, true);
|
||||
const tools = buildOpenAICompatibleTools(request.tools);
|
||||
@@ -122,7 +126,12 @@ export class MimoAdapter extends OpenAICompatibleAdapter {
|
||||
|
||||
// Thinking 模式（与 DeepSeek 参数结构一致）
|
||||
// MiMo API 默认 thinking.type = "enabled"，必须显式发送 disabled 才能关闭
|
||||
if (request.params.thinkingEnabled === false) {
|
||||
// v0.8.0 P0-3: 模型能力门控 —— supportsThinking===false 的模型强制 disabled
|
||||
//（思考 token 计入 max_completion_tokens，能力不符的模型上会耗尽输出预算）
|
||||
const modelThinkingSupported =
|
||||
MimoAdapter.MODEL_INFO[this.config.defaultModel]?.supportsThinking !== false;
|
||||
const wantThinking = request.params.thinkingEnabled !== false && modelThinkingSupported;
|
||||
if (!wantThinking) {
|
||||
// 显式禁用思考：传 disabled + temperature/top_p（非思考模式下这两个参数有效）
|
||||
body.thinking = { type: 'disabled' };
|
||||
body.temperature = request.params.temperature;
|
||||
@@ -131,6 +140,13 @@ export class MimoAdapter extends OpenAICompatibleAdapter {
|
||||
// 启用思考（包括 undefined，因为 MiMo 默认 enabled）
|
||||
// 思考模式下 temperature/top_p 被 API 强制覆盖为 1.0/0.95，不传
|
||||
body.thinking = { type: 'enabled' };
|
||||
// v0.8.0 P0-3: 思考占用输出预算 —— 钳制后预算过小时显式告警
|
||||
const effectiveMax = body.max_completion_tokens as number;
|
||||
if (typeof effectiveMax === 'number' && effectiveMax < 8192) {
|
||||
log.warn(
|
||||
`[MiMo] thinking enabled with small output budget (${effectiveMax} tokens after model clamp) — reasoning may consume the entire budget and truncate the answer`,
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
// 停止序列
|
||||
|
||||
@@ -192,6 +192,14 @@ export class OllamaAdapter extends BaseAdapter {
|
||||
// 流结束
|
||||
if (chunk.done) {
|
||||
streamEndedNormally = true;
|
||||
// v0.8.0 P0-1: 采集 done_reason —— Ollama 的停止原因在最终 done chunk
|
||||
// 携带；旧实现流式路径完全忽略（length 截断不可见），现归一化后随
|
||||
// DONE 事件上交引擎
|
||||
const doneReason = mapOllamaDoneReason(
|
||||
chunk.done_reason as string | undefined,
|
||||
Array.isArray(chunk.message?.tool_calls) && chunk.message.tool_calls.length > 0,
|
||||
);
|
||||
const finishReason = doneReason === MetonaFinishReason.LENGTH ? 'length' : undefined;
|
||||
// 发送 usage 信息
|
||||
yield {
|
||||
type: MetonaStreamEventType.USAGE,
|
||||
@@ -214,6 +222,9 @@ export class OllamaAdapter extends BaseAdapter {
|
||||
iteration: request.meta.iteration,
|
||||
seq: seq++,
|
||||
timestamp: Date.now(),
|
||||
// v0.8.0 P0-1: 仅 length 需要显式上交（stop/tool_calls 语义由
|
||||
// 事件流本身表达；load/unload 属本地引擎状态非响应语义）
|
||||
...(finishReason ? { finishReason } : {}),
|
||||
};
|
||||
return;
|
||||
}
|
||||
@@ -252,6 +263,8 @@ export class OllamaAdapter extends BaseAdapter {
|
||||
format?: string | object;
|
||||
images?: string[];
|
||||
options?: Record<string, unknown>;
|
||||
/** v0.8.0 P1-3.2: 外部取消信号（与固定 300s 超时合并，任一触发即中止） */
|
||||
signal?: AbortSignal;
|
||||
}): Promise<{
|
||||
response: string;
|
||||
thinking?: string;
|
||||
@@ -262,8 +275,13 @@ export class OllamaAdapter extends BaseAdapter {
|
||||
const response = await fetch(`${this.baseURL}/api/generate`, {
|
||||
method: 'POST',
|
||||
headers: { 'Content-Type': 'application/json' },
|
||||
body: JSON.stringify({ ...params, stream: false }),
|
||||
signal: AbortSignal.timeout(300_000),
|
||||
body: JSON.stringify({ ...params, stream: false, signal: undefined }),
|
||||
// v0.8.0 P1-3.2 根治: 旧实现固定 AbortSignal.timeout(300_000) —— 外部中断
|
||||
// 无法取消该请求（最长 5 分钟资源悬挂）。现用 AbortSignal.any 合并外部
|
||||
// signal 与超时信号，任一触发即中止（Node ≥20.3 / Electron 35 满足）。
|
||||
signal: params.signal
|
||||
? AbortSignal.any([params.signal, AbortSignal.timeout(300_000)])
|
||||
: AbortSignal.timeout(300_000),
|
||||
});
|
||||
|
||||
if (!response.ok) throw new Error(`Ollama generate error: ${response.status}`);
|
||||
@@ -290,12 +308,17 @@ export class OllamaAdapter extends BaseAdapter {
|
||||
model: string;
|
||||
input: string | string[];
|
||||
dimensions?: number;
|
||||
/** v0.8.0 P1-3.2: 外部取消信号（与固定 60s 超时合并） */
|
||||
signal?: AbortSignal;
|
||||
}): Promise<{ embeddings: number[][]; totalDuration: number }> {
|
||||
const response = await fetch(`${this.baseURL}/api/embed`, {
|
||||
method: 'POST',
|
||||
headers: { 'Content-Type': 'application/json' },
|
||||
body: JSON.stringify(params),
|
||||
signal: AbortSignal.timeout(60_000),
|
||||
// v0.8.0 P1-3.2: 与 generate 同口径 —— 外部 signal 与超时合并
|
||||
signal: params.signal
|
||||
? AbortSignal.any([params.signal, AbortSignal.timeout(60_000)])
|
||||
: AbortSignal.timeout(60_000),
|
||||
});
|
||||
|
||||
if (!response.ok) throw new Error(`Ollama embed error: ${response.status}`);
|
||||
@@ -381,9 +404,18 @@ export class OllamaAdapter extends BaseAdapter {
|
||||
*/
|
||||
private cachedContextWindow: number | null = null;
|
||||
private refreshingContextWindow = false;
|
||||
/** v0.8.0 P0-3: /api/show 探测只发一次（构造函数发起），失败不重试（fail-open） */
|
||||
private probeAttempted = false;
|
||||
/**
|
||||
* v0.8.0 P0-3: /api/show capabilities 探测缓存 —— 模型是否支持思考。
|
||||
* null = 未探测/探测失败（fail-open 放行，与 listModels 能力回退策略一致）；
|
||||
* false = 服务端明确不支持 → toNativeRequest 不发 think 参数。
|
||||
*/
|
||||
private cachedThinkingSupport: boolean | null = null;
|
||||
|
||||
private refreshContextWindow(): void {
|
||||
if (this.refreshingContextWindow) return;
|
||||
if (this.refreshingContextWindow || this.probeAttempted) return;
|
||||
this.probeAttempted = true;
|
||||
this.refreshingContextWindow = true;
|
||||
void this.showModel(this.config.defaultModel)
|
||||
.then((info) => {
|
||||
@@ -396,6 +428,10 @@ export class OllamaAdapter extends BaseAdapter {
|
||||
log.info(`[Ollama] Context window (num_ctx) detected: ${value}`);
|
||||
}
|
||||
}
|
||||
// v0.8.0 P0-3: 同一次探测顺带缓存思考能力（供 toNativeRequest 同步门控）
|
||||
if (Array.isArray(info.capabilities)) {
|
||||
this.cachedThinkingSupport = info.capabilities.map(String).includes('thinking');
|
||||
}
|
||||
})
|
||||
.catch(() => {
|
||||
/* 模型探测失败不阻塞对话 */
|
||||
@@ -573,6 +609,9 @@ export class OllamaAdapter extends BaseAdapter {
|
||||
}
|
||||
|
||||
private async toNativeRequest(request: MetonaRequest): Promise<Record<string, unknown>> {
|
||||
// 说明：能力/num_ctx 探测由构造函数 fire-and-forget 发起（probeAttempts 上限
|
||||
// 1 次）—— 此处不再重复探测，避免每次请求都打 /api/show（也保持测试环境的
|
||||
// fetch 捕获不受污染）。探测失败时 cachedThinkingSupport=null → 门控 fail-open。
|
||||
const messages: Record<string, unknown>[] = [
|
||||
{
|
||||
role: 'system',
|
||||
@@ -662,14 +701,32 @@ export class OllamaAdapter extends BaseAdapter {
|
||||
}
|
||||
|
||||
// Thinking 模式
|
||||
// v0.8.0 P0-3: 模型能力门控 —— /api/show capabilities 探测为不支持思考
|
||||
//（cachedThinkingSupport === false）时不发 think 参数（Ollama 服务端默认关闭）；
|
||||
// 未探测/探测失败（null）fail-open 放行，与 listModels 能力回退策略一致。
|
||||
// 探测在适配器实例创建时 fire-and-forget 发起（refreshContextWindow）。
|
||||
if (request.params.thinkingEnabled) {
|
||||
const effortMap: Record<string, string | boolean> = {
|
||||
low: 'low',
|
||||
medium: 'medium',
|
||||
high: 'high',
|
||||
max: true,
|
||||
};
|
||||
body.think = effortMap[request.params.thinkingEffort ?? 'high'] ?? true;
|
||||
const modelThinkingSupported = this.cachedThinkingSupport !== false;
|
||||
if (modelThinkingSupported) {
|
||||
const effortMap: Record<string, string | boolean> = {
|
||||
low: 'low',
|
||||
medium: 'medium',
|
||||
high: 'high',
|
||||
max: true,
|
||||
};
|
||||
body.think = effortMap[request.params.thinkingEffort ?? 'high'] ?? true;
|
||||
// v0.8.0 P0-3: 思考占用 num_predict 输出预算 —— 预算过小时显式告警
|
||||
const numPredict = request.params.maxTokens;
|
||||
if (typeof numPredict === 'number' && numPredict < 8192) {
|
||||
log.warn(
|
||||
`[Ollama] thinking enabled with small num_predict budget (${numPredict}) — reasoning may consume the entire budget and truncate the answer`,
|
||||
);
|
||||
}
|
||||
} else {
|
||||
log.warn(
|
||||
`[Ollama] model "${this.config.defaultModel}" does not support thinking (per /api/show capabilities) — omitting think parameter (P0-3 capability gate)`,
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
return body;
|
||||
|
||||
@@ -12,13 +12,11 @@
|
||||
* @see https://platform.openai.com/docs/api-reference/chat
|
||||
*/
|
||||
|
||||
import log from 'electron-log';
|
||||
import type { MetonaRequest } from '../types';
|
||||
import type { MetonaModelInfo } from '../types/metona-adapter';
|
||||
import { buildOpenAICompatibleMessages, buildOpenAICompatibleTools } from './shared/openai-format';
|
||||
import {
|
||||
ModelCapabilityError,
|
||||
OpenAICompatibleAdapter,
|
||||
} from './shared/openai-compatible-base';
|
||||
import { ModelCapabilityError, OpenAICompatibleAdapter } from './shared/openai-compatible-base';
|
||||
|
||||
export class OpenAIAdapter extends OpenAICompatibleAdapter {
|
||||
override readonly providerId: string = 'openai';
|
||||
@@ -110,7 +108,10 @@ export class OpenAIAdapter extends OpenAICompatibleAdapter {
|
||||
|
||||
// ========== 协议参数映射（OpenAI 差异点） ==========
|
||||
|
||||
protected override toNativeRequest(request: MetonaRequest, stream: boolean): Record<string, unknown> {
|
||||
protected override toNativeRequest(
|
||||
request: MetonaRequest,
|
||||
stream: boolean,
|
||||
): Record<string, unknown> {
|
||||
// 推理模型检测（o 系列使用新参数名）
|
||||
const model = this.config.defaultModel;
|
||||
const isReasoningModel = /^(o\d|gpt-5)/.test(model);
|
||||
@@ -168,6 +169,12 @@ export class OpenAIAdapter extends OpenAICompatibleAdapter {
|
||||
max: 'high',
|
||||
};
|
||||
body.reasoning_effort = effortMap[request.params.thinkingEffort ?? 'high'] ?? 'high';
|
||||
// v0.8.0 P0-3: 推理 token 计入 max_completion_tokens —— 钳制后预算过小时告警
|
||||
if (oaMaxTokens < 8192) {
|
||||
log.warn(
|
||||
`[OpenAI] reasoning enabled with small output budget (${oaMaxTokens} tokens after model clamp) — reasoning may consume the entire budget and truncate the answer`,
|
||||
);
|
||||
}
|
||||
} else if (!isReasoningModel) {
|
||||
// 非推理模型使用温度控制
|
||||
body.temperature = request.params.temperature;
|
||||
|
||||
@@ -139,17 +139,17 @@ function extractUpstreamErrorFrame(
|
||||
? e.status_code
|
||||
: undefined;
|
||||
const rawCode = typeof e.code === 'string' ? e.code : typeof e.type === 'string' ? e.type : '';
|
||||
const message =
|
||||
typeof e.message === 'string'
|
||||
? e.message
|
||||
: typeof e.msg === 'string'
|
||||
? e.msg
|
||||
: JSON.stringify(errObj);
|
||||
|
||||
// 无消息且无状态码的无害空对象不算错误（防御性）
|
||||
if (!message && rawStatus === undefined && !rawCode) return null;
|
||||
// v0.8.0 P1-3.1 根治: 旧实现 message 兜底取 JSON.stringify(errObj) —— '{}' 恒为
|
||||
// 真值，使本防御分支永不可达，`{"error":{}}` 被误判为错误帧抛 SseUpstreamError
|
||||
// （原行为被 sse-stream.test.ts 锁定留档，本次随修复同步改约）。
|
||||
// 现契约：仅当存在显式 message/msg 或 status/code 标识之一才构成错误帧；
|
||||
// 描述文本只在有标识但无显式文本时由序列化/占位生成。
|
||||
const explicitMessage =
|
||||
typeof e.message === 'string' ? e.message : typeof e.msg === 'string' ? e.msg : '';
|
||||
if (!explicitMessage && rawStatus === undefined && !rawCode) return null;
|
||||
return {
|
||||
message: message || `upstream error (${rawCode || rawStatus})`,
|
||||
message: explicitMessage || `upstream error (${rawCode || rawStatus})`,
|
||||
status: rawStatus,
|
||||
code: rawCode || undefined,
|
||||
};
|
||||
@@ -326,6 +326,10 @@ export async function* parseSSEStream(
|
||||
let buffer = '';
|
||||
// v0.6.3: 是否收到过 [DONE]（流断开兜底用）
|
||||
let sawDone = false;
|
||||
// v0.8.0 P0-1: 跟踪 Provider 原生 finish_reason，随 DONE 事件携带给引擎
|
||||
// （'stop' | 'length' | 'tool_calls' | 'content_filter' 等；引擎据此区分
|
||||
// 自然完成与输出上限截断，此前 length 仅落日志、引擎不可见）
|
||||
let lastFinishReason: string | undefined;
|
||||
|
||||
// v0.7.4 P1-2: 流空闲超时 — 服务器保活但不再推送数据（连接挂死）时，
|
||||
// reader.read() 会无限挂起，totalTimeoutMs 只在迭代之间检查，无法兜底。
|
||||
@@ -369,6 +373,8 @@ export async function* parseSSEStream(
|
||||
iteration,
|
||||
seq: seqRef.seq++,
|
||||
timestamp: Date.now(),
|
||||
// v0.8.0 P0-1: 携带 Provider 原生 finish_reason（未见任何帧时 undefined）
|
||||
...(lastFinishReason ? { finishReason: lastFinishReason } : {}),
|
||||
};
|
||||
return;
|
||||
}
|
||||
@@ -480,6 +486,11 @@ export async function* parseSSEStream(
|
||||
|
||||
// 非 [DONE] 但 finish_reason 为 tool_calls 时提前 flush 缓冲区
|
||||
const finishReason = chunk.choices?.[0]?.finish_reason as string | undefined;
|
||||
// v0.8.0 P0-1: 记录最近一次 finish_reason（最终帧通常携带于最后一个
|
||||
// 含 choices 的 chunk），随 DONE 事件上交通知引擎与前端
|
||||
if (finishReason) {
|
||||
lastFinishReason = finishReason;
|
||||
}
|
||||
if (finishReason === 'tool_calls') {
|
||||
// L-4 修复: 使用 flushToolCallBuffer 替代重复的遍历代码
|
||||
yield* flushToolCallBuffer(toolCallsBuffer, requestId, sessionId, iteration, seqRef);
|
||||
@@ -528,6 +539,10 @@ export async function* parseSSEStream(
|
||||
iteration,
|
||||
seq: seqRef.seq++,
|
||||
timestamp: Date.now(),
|
||||
// v0.8.0 P0-1: 断流合成路径同样携带已观察到的 finish_reason
|
||||
//（注意：断流时 finishReason 多为 undefined —— 引擎据此走空响应守卫/重试，
|
||||
// 而不是误判为模型自然说完了）
|
||||
...(lastFinishReason ? { finishReason: lastFinishReason } : {}),
|
||||
};
|
||||
}
|
||||
}
|
||||
|
||||
@@ -0,0 +1,230 @@
|
||||
/**
|
||||
* v0.8.0 P0-5: 引擎流结束契约测试 —— "模型思考着会话停止"根治回归防线。
|
||||
*
|
||||
* 钉住 chatStreamWithRetry 的流结束契约（P0-2）与 finish_reason 贯通（P0-1）：
|
||||
* 1. 零产出流 → EmptyResponseError → 退避重试 → 重试耗尽 ERROR；
|
||||
* 2. reasoning-only + finish_reason=length → 一次性降级重试（thinkingEnabled=false）
|
||||
* → 降级后成功 COMPLETED；
|
||||
* 3. 降级重试仍 length → OutputTruncatedError → ERROR 事件携带
|
||||
* MetonaErrorCode.OUTPUT_LENGTH_EXCEEDED；
|
||||
* 4. 有正文 + length → COMPLETED 且最终 DONE 事件携带 finishReason='length'；
|
||||
* 5. 引擎最终 DONE 贯通最后一轮 step.finishReason。
|
||||
*/
|
||||
|
||||
import { describe, it, expect } from 'vitest';
|
||||
import { AgentLoopEngine } from '../engine';
|
||||
import type { AgentLoopOutput } from '../types';
|
||||
import type {
|
||||
MetonaRequest,
|
||||
MetonaStreamEvent,
|
||||
IMetonaProviderAdapter,
|
||||
MetonaResponse,
|
||||
} from '../../types';
|
||||
import { MetonaStreamEventType, MetonaErrorCode } from '../../types';
|
||||
|
||||
const SYSTEM_PROMPT = {
|
||||
roleDefinition: 'test',
|
||||
outputConstraints: '',
|
||||
safetyGuidelines: '',
|
||||
};
|
||||
|
||||
function makeAdapter(
|
||||
script: (request: MetonaRequest) => MetonaStreamEvent[],
|
||||
): IMetonaProviderAdapter & { calls: MetonaRequest[] } {
|
||||
const calls: MetonaRequest[] = [];
|
||||
const adapter = {
|
||||
providerId: 'mock' as const,
|
||||
supportedModels: ['m'],
|
||||
supportsToolCalling: true,
|
||||
supportsThinking: true,
|
||||
calls,
|
||||
getContextWindow(): number {
|
||||
return 128_000;
|
||||
},
|
||||
async send(_request: MetonaRequest): Promise<MetonaResponse> {
|
||||
throw new Error('send() not expected in this test');
|
||||
},
|
||||
async *sendStream(request: MetonaRequest): AsyncIterable<MetonaStreamEvent> {
|
||||
calls.push(request);
|
||||
for (const ev of script(request)) {
|
||||
yield ev;
|
||||
}
|
||||
},
|
||||
};
|
||||
return adapter as unknown as IMetonaProviderAdapter & { calls: MetonaRequest[] };
|
||||
}
|
||||
|
||||
function makeEngine(adapter: IMetonaProviderAdapter, retryCount = 1): AgentLoopEngine {
|
||||
return new AgentLoopEngine(
|
||||
{
|
||||
maxIterations: 3,
|
||||
totalTimeoutMs: 10_000,
|
||||
retryCount,
|
||||
thinkingEnabled: true,
|
||||
thinkingEffort: 'high',
|
||||
contextWindow: 128_000,
|
||||
},
|
||||
adapter,
|
||||
);
|
||||
}
|
||||
|
||||
function textDelta(t: string): MetonaStreamEvent {
|
||||
return {
|
||||
type: MetonaStreamEventType.TEXT_DELTA,
|
||||
requestId: 'r',
|
||||
sessionId: 's',
|
||||
iteration: 1,
|
||||
seq: 0,
|
||||
timestamp: Date.now(),
|
||||
delta: t,
|
||||
};
|
||||
}
|
||||
|
||||
function reasoningDelta(t: string): MetonaStreamEvent {
|
||||
return {
|
||||
type: MetonaStreamEventType.REASONING_DELTA,
|
||||
requestId: 'r',
|
||||
sessionId: 's',
|
||||
iteration: 1,
|
||||
seq: 0,
|
||||
timestamp: Date.now(),
|
||||
delta: t,
|
||||
};
|
||||
}
|
||||
|
||||
function doneEvent(finishReason?: string): MetonaStreamEvent {
|
||||
return {
|
||||
type: MetonaStreamEventType.DONE,
|
||||
requestId: 'r',
|
||||
sessionId: 's',
|
||||
iteration: 1,
|
||||
seq: 0,
|
||||
timestamp: Date.now(),
|
||||
...(finishReason ? { finishReason } : {}),
|
||||
};
|
||||
}
|
||||
|
||||
describe('engine stream-end contract (v0.8.0 P0-2)', () => {
|
||||
it('scenario 2: reasoning-only + length → one degraded retry with thinking disabled → COMPLETED', async () => {
|
||||
let call = 0;
|
||||
const adapter = makeAdapter((req) => {
|
||||
call++;
|
||||
if (call === 1) {
|
||||
// 第一次：思考烧满输出预算（reasoning-only + length 截断）
|
||||
expect(req.params.thinkingEnabled).toBe(true);
|
||||
return [reasoningDelta('thinking...'), doneEvent('length')];
|
||||
}
|
||||
// 降级重试：thinkingEnabled 必须已被引擎置 false
|
||||
expect(req.params.thinkingEnabled).toBe(false);
|
||||
return [textDelta('answer'), doneEvent('stop')];
|
||||
});
|
||||
const engine = makeEngine(adapter);
|
||||
const events: MetonaStreamEvent[] = [];
|
||||
engine.on('streamEvent', (e: MetonaStreamEvent) => events.push(e));
|
||||
|
||||
const output = await engine.runStream(
|
||||
{ role: 'user', content: 'hi', timestamp: Date.now() },
|
||||
's1',
|
||||
[],
|
||||
SYSTEM_PROMPT,
|
||||
);
|
||||
|
||||
expect(output.terminationReason).toBe('completed');
|
||||
expect(output.finalAnswer).toBe('answer');
|
||||
expect(adapter.calls.length).toBe(2);
|
||||
// 降级重试经过 RETRY 事件（引擎消费后向渲染层转 STREAM_RESET）
|
||||
expect(events.some((e) => e.type === MetonaStreamEventType.STREAM_RESET)).toBe(true);
|
||||
});
|
||||
|
||||
it('scenario 2b: degraded retry still length → OUTPUT_LENGTH_EXCEEDED error (no infinite retry)', async () => {
|
||||
const adapter = makeAdapter(() => [reasoningDelta('thinking...'), doneEvent('length')]);
|
||||
const engine = makeEngine(adapter);
|
||||
const events: MetonaStreamEvent[] = [];
|
||||
engine.on('streamEvent', (e: MetonaStreamEvent) => events.push(e));
|
||||
|
||||
const output: AgentLoopOutput = await engine.runStream(
|
||||
{ role: 'user', content: 'hi', timestamp: Date.now() },
|
||||
's1',
|
||||
[],
|
||||
SYSTEM_PROMPT,
|
||||
);
|
||||
|
||||
// 恰好两次调用（原始 + 一次性降级重试），随后终止
|
||||
expect(adapter.calls.length).toBe(2);
|
||||
expect(output.terminationReason).toBe('error');
|
||||
const errorEvent = events.find((e) => e.type === MetonaStreamEventType.ERROR);
|
||||
expect(errorEvent).toBeDefined();
|
||||
expect(errorEvent?.error?.code).toBe(MetonaErrorCode.OUTPUT_LENGTH_EXCEEDED);
|
||||
});
|
||||
|
||||
it('scenario 1: zero-content stream → retryable → retry exhausted → ERROR', async () => {
|
||||
const adapter = makeAdapter(() => []);
|
||||
const engine = makeEngine(adapter, 1);
|
||||
const events: MetonaStreamEvent[] = [];
|
||||
engine.on('streamEvent', (e: MetonaStreamEvent) => events.push(e));
|
||||
|
||||
const output = await engine.runStream(
|
||||
{ role: 'user', content: 'hi', timestamp: Date.now() },
|
||||
's1',
|
||||
[],
|
||||
SYSTEM_PROMPT,
|
||||
);
|
||||
|
||||
expect(output.terminationReason).toBe('error');
|
||||
expect(adapter.calls.length).toBe(2); // 原始 1 次 + 重试 1 次（retryCount=1）
|
||||
const errorEvent = events.find((e) => e.type === MetonaStreamEventType.ERROR);
|
||||
expect(errorEvent?.error?.message).toContain('empty stream');
|
||||
});
|
||||
|
||||
it('scenario 4: text + length → COMPLETED with DONE.finishReason=length (no retry)', async () => {
|
||||
const adapter = makeAdapter(() => [textDelta('partial answer'), doneEvent('length')]);
|
||||
const engine = makeEngine(adapter);
|
||||
const events: MetonaStreamEvent[] = [];
|
||||
engine.on('streamEvent', (e: MetonaStreamEvent) => events.push(e));
|
||||
|
||||
const output = await engine.runStream(
|
||||
{ role: 'user', content: 'hi', timestamp: Date.now() },
|
||||
's1',
|
||||
[],
|
||||
SYSTEM_PROMPT,
|
||||
);
|
||||
|
||||
expect(output.terminationReason).toBe('completed');
|
||||
expect(output.finalAnswer).toBe('partial answer');
|
||||
expect(adapter.calls.length).toBe(1); // 有产出不重试
|
||||
const done = events.find((e) => e.type === MetonaStreamEventType.DONE);
|
||||
expect(done?.finishReason).toBe('length');
|
||||
});
|
||||
|
||||
it('P0-1: normal stop → DONE carries finishReason=stop from adapter', async () => {
|
||||
const adapter = makeAdapter(() => [textDelta('ok'), doneEvent('stop')]);
|
||||
const engine = makeEngine(adapter);
|
||||
const events: MetonaStreamEvent[] = [];
|
||||
engine.on('streamEvent', (e: MetonaStreamEvent) => events.push(e));
|
||||
|
||||
const output = await engine.runStream(
|
||||
{ role: 'user', content: 'hi', timestamp: Date.now() },
|
||||
's1',
|
||||
[],
|
||||
SYSTEM_PROMPT,
|
||||
);
|
||||
|
||||
expect(output.terminationReason).toBe('completed');
|
||||
const done = events.find((e) => e.type === MetonaStreamEventType.DONE);
|
||||
expect(done?.finishReason).toBe('stop');
|
||||
});
|
||||
|
||||
it('reasoning-only + natural stop (no length) → retryable empty response path', async () => {
|
||||
const adapter = makeAdapter(() => [reasoningDelta('hmm'), doneEvent('stop')]);
|
||||
const engine = makeEngine(adapter, 1);
|
||||
const output = await engine.runStream(
|
||||
{ role: 'user', content: 'hi', timestamp: Date.now() },
|
||||
's1',
|
||||
[],
|
||||
SYSTEM_PROMPT,
|
||||
);
|
||||
// 无产出且非 length 截断 → EmptyResponseError（可重试）→ 重试耗尽 ERROR
|
||||
expect(output.terminationReason).toBe('error');
|
||||
expect(adapter.calls.length).toBe(2);
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,243 @@
|
||||
/**
|
||||
* v0.8.0 P0-5 回归测试（第二批）：流可靠性四件套的剩余项。
|
||||
*
|
||||
* 1. parseSSEStream 集成级空闲超时：挂死 ReadableStream → 60s 无数据 →
|
||||
* SseUpstreamError(504)（P1-2 防线的集成真实性，此前仅纯函数层覆盖）；
|
||||
* 2. SseUpstreamError(504) 经引擎 isRetryableError 归类 → 退避重试后成功；
|
||||
* 3. REASONING_DELTA 持续输出中 abort → USER_INTERRUPT（"思考中点停止"场景）；
|
||||
* 4. 引擎 P4-2：上一 run 卡死（不响应 abort）→ 新 run 等待 30s → 强制 abort
|
||||
* → 再等 5s → 抛错（防"会话永久排队"）。
|
||||
*/
|
||||
|
||||
import { describe, it, expect, vi, afterEach } from 'vitest';
|
||||
import { parseSSEStream, SseUpstreamError } from '../../adapters/shared/sse-stream';
|
||||
import { AgentLoopEngine } from '../engine';
|
||||
import type { MetonaRequest, MetonaStreamEvent, IMetonaProviderAdapter } from '../../types';
|
||||
import { MetonaStreamEventType } from '../../types';
|
||||
|
||||
const SYSTEM_PROMPT = {
|
||||
roleDefinition: 'test',
|
||||
outputConstraints: '',
|
||||
safetyGuidelines: '',
|
||||
};
|
||||
|
||||
afterEach(() => {
|
||||
vi.useRealTimers();
|
||||
});
|
||||
|
||||
// ===== 1. 集成级空闲超时 =====
|
||||
|
||||
describe('parseSSEStream integrated idle timeout (P0-5 #2)', () => {
|
||||
function makeHungBody(): ReadableStream<Uint8Array> {
|
||||
return {
|
||||
getReader: () => ({
|
||||
// 永不 resolve 的 read —— 模拟"服务器保活但不再推数据"
|
||||
read: () => new Promise<never>(() => {}),
|
||||
releaseLock: () => {},
|
||||
}),
|
||||
} as unknown as ReadableStream<Uint8Array>;
|
||||
}
|
||||
|
||||
it('挂死流 60s 无数据 → SseUpstreamError(504)', async () => {
|
||||
vi.useFakeTimers();
|
||||
const iterator = parseSSEStream(makeHungBody(), 'r', 's', 1);
|
||||
let thrown: unknown = null;
|
||||
const firstRead = iterator.next().catch((e: unknown) => {
|
||||
thrown = e;
|
||||
return { done: true, value: undefined } as const;
|
||||
});
|
||||
// 推进 61s：IDLE_TIMEOUT_MS=60_000 触发 idle controller → read() 竞速失败
|
||||
await vi.advanceTimersByTimeAsync(61_000);
|
||||
await firstRead;
|
||||
expect(thrown).toBeInstanceOf(SseUpstreamError);
|
||||
expect((thrown as SseUpstreamError).status).toBe(504);
|
||||
expect((thrown as Error).message).toContain('idle timeout');
|
||||
});
|
||||
});
|
||||
|
||||
// ===== 2. SseUpstreamError(504) → 引擎重试 =====
|
||||
|
||||
describe('engine: SseUpstreamError(504) retry classification (P0-5 #3)', () => {
|
||||
it('504 首败 → 退避重试 → 第二次流成功 → COMPLETED', async () => {
|
||||
let call = 0;
|
||||
const adapter = {
|
||||
providerId: 'mock' as const,
|
||||
supportedModels: ['m'],
|
||||
supportsToolCalling: true,
|
||||
supportsThinking: true,
|
||||
getContextWindow: () => 128_000,
|
||||
async send(): Promise<unknown> {
|
||||
throw new Error('not used');
|
||||
},
|
||||
async *sendStream(_r: MetonaRequest): AsyncIterable<MetonaStreamEvent> {
|
||||
call++;
|
||||
if (call === 1) {
|
||||
throw new SseUpstreamError('Stream idle timeout after 60000ms (no data received)', {
|
||||
status: 504,
|
||||
});
|
||||
}
|
||||
yield {
|
||||
type: MetonaStreamEventType.TEXT_DELTA,
|
||||
requestId: 'r',
|
||||
sessionId: 's',
|
||||
iteration: 1,
|
||||
seq: 0,
|
||||
timestamp: Date.now(),
|
||||
delta: 'recovered',
|
||||
};
|
||||
yield {
|
||||
type: MetonaStreamEventType.DONE,
|
||||
requestId: 'r',
|
||||
sessionId: 's',
|
||||
iteration: 1,
|
||||
seq: 1,
|
||||
timestamp: Date.now(),
|
||||
finishReason: 'stop',
|
||||
};
|
||||
},
|
||||
} as unknown as IMetonaProviderAdapter;
|
||||
|
||||
const engine = new AgentLoopEngine(
|
||||
{ maxIterations: 3, totalTimeoutMs: 15_000, retryCount: 2, contextWindow: 128_000 },
|
||||
adapter,
|
||||
);
|
||||
const events: MetonaStreamEvent[] = [];
|
||||
engine.on('streamEvent', (e: MetonaStreamEvent) => events.push(e));
|
||||
const output = await engine.runStream(
|
||||
{ role: 'user', content: 'hi', timestamp: Date.now() },
|
||||
's1',
|
||||
[],
|
||||
SYSTEM_PROMPT,
|
||||
);
|
||||
expect(output.terminationReason).toBe('completed');
|
||||
expect(output.finalAnswer).toBe('recovered');
|
||||
expect(call).toBe(2);
|
||||
// 重试经过 RETRY 事件（引擎消费后向渲染层转 STREAM_RESET）
|
||||
expect(events.some((e) => e.type === MetonaStreamEventType.STREAM_RESET)).toBe(true);
|
||||
});
|
||||
});
|
||||
|
||||
// ===== 3. REASONING_DELTA 中途 abort =====
|
||||
|
||||
describe('engine: abort during reasoning stream (P0-5 #4)', () => {
|
||||
it('思考增量持续输出中 abort → USER_INTERRUPT，迟到 reasoning 不再产出事件', async () => {
|
||||
const adapter = {
|
||||
providerId: 'mock' as const,
|
||||
supportedModels: ['m'],
|
||||
supportsToolCalling: true,
|
||||
supportsThinking: true,
|
||||
getContextWindow: () => 128_000,
|
||||
async send(): Promise<unknown> {
|
||||
throw new Error('not used');
|
||||
},
|
||||
// 持续每 10ms 推送一个 reasoning delta，直到 abort 或 500 个（挂起）
|
||||
async *sendStream(_r: MetonaRequest): AsyncIterable<MetonaStreamEvent> {
|
||||
for (let i = 0; i < 500; i++) {
|
||||
if (_r.params.thinkingEnabled === false) return;
|
||||
yield {
|
||||
type: MetonaStreamEventType.REASONING_DELTA,
|
||||
requestId: 'r',
|
||||
sessionId: 's',
|
||||
iteration: 1,
|
||||
seq: i,
|
||||
timestamp: Date.now(),
|
||||
delta: `t${i};`,
|
||||
};
|
||||
await new Promise((r) => setTimeout(r, 10));
|
||||
}
|
||||
yield {
|
||||
type: MetonaStreamEventType.DONE,
|
||||
requestId: 'r',
|
||||
sessionId: 's',
|
||||
iteration: 1,
|
||||
seq: 999,
|
||||
timestamp: Date.now(),
|
||||
};
|
||||
},
|
||||
} as unknown as IMetonaProviderAdapter;
|
||||
|
||||
const engine = new AgentLoopEngine(
|
||||
{ maxIterations: 3, totalTimeoutMs: 30_000, retryCount: 0, contextWindow: 128_000 },
|
||||
adapter,
|
||||
);
|
||||
const events: MetonaStreamEvent[] = [];
|
||||
engine.on('streamEvent', (e: MetonaStreamEvent) => events.push(e));
|
||||
|
||||
const run = engine.runStream(
|
||||
{ role: 'user', content: 'hi', timestamp: Date.now() },
|
||||
's1',
|
||||
[],
|
||||
SYSTEM_PROMPT,
|
||||
);
|
||||
// 等待至少 3 个 reasoning delta 到达（确认流确实在思考态输出中）
|
||||
await new Promise((r) => setTimeout(r, 80));
|
||||
expect(
|
||||
events.filter((e) => e.type === MetonaStreamEventType.REASONING_DELTA).length,
|
||||
).toBeGreaterThanOrEqual(3);
|
||||
engine.abort();
|
||||
const output = await run;
|
||||
expect(output.terminationReason).toBe('user_interrupt');
|
||||
const lastReasoningIdx = events
|
||||
.map((e) => e.type)
|
||||
.lastIndexOf(MetonaStreamEventType.REASONING_DELTA);
|
||||
const doneIdx = events.findIndex((e) => e.type === MetonaStreamEventType.DONE);
|
||||
// abort 生效后不再有迟到 reasoning（abort 尾巴过滤在引擎侧）
|
||||
expect(lastReasoningIdx).toBeLessThan(doneIdx);
|
||||
}, 15_000);
|
||||
});
|
||||
|
||||
// ===== 4. P4-2: 上一 run 卡死 → 30s 强制 abort + 5s 再等待 → 抛错 =====
|
||||
|
||||
describe('engine: stuck previous run force-abort path (P4-2)', () => {
|
||||
it('上一 run 不响应 abort → 新 run 30s 超时强制 abort → 5s 后仍卡 → 抛错', async () => {
|
||||
vi.useFakeTimers();
|
||||
let released = false;
|
||||
const stuckAdapter = {
|
||||
providerId: 'mock' as const,
|
||||
supportedModels: ['m'],
|
||||
supportsToolCalling: true,
|
||||
supportsThinking: true,
|
||||
getContextWindow: () => 128_000,
|
||||
async send(): Promise<unknown> {
|
||||
throw new Error('not used');
|
||||
},
|
||||
// 第一次 run：永远挂起且不响应 abort（模拟卡死的底层 fetch）；
|
||||
// 挂起生成器无 yield 属场景定义（require-yield 由下行指令豁免）
|
||||
// eslint-disable-next-line require-yield
|
||||
async *sendStream(): AsyncIterable<MetonaStreamEvent> {
|
||||
while (!released) {
|
||||
await new Promise(() => {});
|
||||
}
|
||||
return;
|
||||
},
|
||||
} as unknown as IMetonaProviderAdapter;
|
||||
|
||||
const engine = new AgentLoopEngine(
|
||||
{ maxIterations: 3, totalTimeoutMs: 600_000, retryCount: 0, contextWindow: 128_000 },
|
||||
stuckAdapter,
|
||||
);
|
||||
const firstRun = engine.runStream(
|
||||
{ role: 'user', content: 'first', timestamp: Date.now() },
|
||||
's1',
|
||||
[],
|
||||
SYSTEM_PROMPT,
|
||||
);
|
||||
firstRun.catch(() => {});
|
||||
|
||||
// 新消息进入 → 等待上一 run 结束（30s 超时）→ 强制 abort → 5s 再等待 → 抛错
|
||||
const secondRun = engine.runStream(
|
||||
{ role: 'user', content: 'second', timestamp: Date.now() },
|
||||
's1',
|
||||
[],
|
||||
SYSTEM_PROMPT,
|
||||
);
|
||||
const expectation = expect(secondRun).rejects.toThrow(/Previous run did not finish/i);
|
||||
|
||||
// 驱动 30s 等待超时 + 5s 强制 abort 等待
|
||||
await vi.advanceTimersByTimeAsync(30_500);
|
||||
await vi.advanceTimersByTimeAsync(5_500);
|
||||
// 清理：放行挂死流，让 firstRun 收敛
|
||||
released = true;
|
||||
await expectation;
|
||||
}, 20_000);
|
||||
});
|
||||
@@ -48,6 +48,37 @@ class DeadLoopError extends Error {
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* v0.8.0 P0-2: 空响应错误 — 流结束但零产出（无 reasoning、无正文、无工具调用）。
|
||||
* 属可重试的瞬时故障（上游断流被 [DONE] 兜底合成 / 网关干净空响应），携带
|
||||
* status=503 使 engine.isRetryableError 的 5xx 分支命中，走指数退避重试；
|
||||
* 重试耗尽后以 ERROR 收尾并给用户明确文案（此前该形态被静默判定 COMPLETED，
|
||||
* 即"模型思考着会话就停止"的根因之一）。
|
||||
*/
|
||||
export class EmptyResponseError extends Error {
|
||||
readonly status = 503;
|
||||
constructor(message: string) {
|
||||
super(message);
|
||||
this.name = 'EmptyResponseError';
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* v0.8.0 P0-2: 输出截断错误 — 思考耗尽型截断（reasoning 烧满输出预算、正文零字节，
|
||||
* finish_reason=length），一次性降级重试（关闭思考）后仍复现时抛出。
|
||||
* 不可重试（status=400），携带 code=OUTPUT_LENGTH_EXCEEDED（IR 预留错误码首次
|
||||
* 投产），engine.finish() 据此向前端发送结构化错误；非可重试语义同时触发
|
||||
* Provider 故障转移（备用 Provider 输出预算更大时即构成自愈）。
|
||||
*/
|
||||
export class OutputTruncatedError extends Error {
|
||||
readonly status = 400;
|
||||
readonly code = MetonaErrorCode.OUTPUT_LENGTH_EXCEEDED;
|
||||
constructor(message: string) {
|
||||
super(message);
|
||||
this.name = 'OutputTruncatedError';
|
||||
}
|
||||
}
|
||||
|
||||
const DEFAULT_CONFIG: AgentLoopConfig = {
|
||||
maxIterations: 20,
|
||||
totalTimeoutMs: 600_000,
|
||||
@@ -88,6 +119,12 @@ export class AgentLoopEngine extends EventEmitter {
|
||||
private lastRealInputTokens = 0;
|
||||
/** 当前 run 的唯一标识（用于前端过滤旧流事件） */
|
||||
private runId: string = '';
|
||||
/**
|
||||
* v0.8.0 P0-1: 最近一轮 LLM 流的 Provider 原生停止原因（归一化 OpenAI 语义）。
|
||||
* 由 adapter DONE 事件携带、引擎捕获；finish() 据此在最终 DONE 事件上转发，
|
||||
* 前端/TRACE 据此区分自然完成与输出上限截断。
|
||||
*/
|
||||
private lastIterationFinishReason: string | undefined;
|
||||
/** 正在进行的 run Promise（用于 run lock，防止并发 run 污染状态） */
|
||||
private currentRunPromise: Promise<AgentLoopOutput> | null = null;
|
||||
|
||||
@@ -269,6 +306,8 @@ export class AgentLoopEngine extends EventEmitter {
|
||||
this.toolCallHistory = [];
|
||||
// v0.7.4 P4-1: 重置工具结果历史（进度信号，与调用历史按轮对应）
|
||||
this.toolResultHistory = [];
|
||||
// v0.8.0 P0-1: 重置最近一轮停止原因
|
||||
this.lastIterationFinishReason = undefined;
|
||||
|
||||
try {
|
||||
await this.transitionTo(AgentLoopState.INIT);
|
||||
@@ -316,6 +355,16 @@ export class AgentLoopEngine extends EventEmitter {
|
||||
|
||||
const step = await this.executeOneIterationStream(request, sessionId);
|
||||
this.iterations.push(step);
|
||||
// v0.8.0 P0-1: 记录最近一轮停止原因（供 finish() 的 DONE 事件转发）
|
||||
this.lastIterationFinishReason = step.finishReason;
|
||||
|
||||
// v0.8.0 P0-2 回归根治: abort 优先级 —— 旧实现该检查位于 while 循环
|
||||
// 末尾，若 abort 恰逢"零工具调用轮"（如思考中点停止），空轮会先命中
|
||||
// 下方 COMPLETED 分支，把 USER_INTERRUPT 静默吞成 completed（与新
|
||||
// 回归测试 engine-stream-reliability 同时发现）。此处前置检查修复。
|
||||
if (this.aborted) {
|
||||
return this.finish(TerminationReason.USER_INTERRUPT);
|
||||
}
|
||||
|
||||
// 将 assistant 回复加入消息历史
|
||||
// 崩溃修复（会话停止根因）: 原条件 `if (step.thought)` 在模型发起纯工具调用
|
||||
@@ -499,13 +548,20 @@ export class AgentLoopEngine extends EventEmitter {
|
||||
let reasoningContent = '';
|
||||
const toolCallsBuffer = new Map<number, { name: string; argsBuffer: string }>();
|
||||
let tokenUsage: TokenUsage | undefined;
|
||||
// v0.8.0 P0-1: 本轮流的 Provider 原生停止原因（adapter DONE 携带）
|
||||
let iterationFinishReason: string | undefined;
|
||||
|
||||
// 流式接收响应
|
||||
for await (const event of this.chatStreamWithRetry(request)) {
|
||||
if (this.aborted) break;
|
||||
|
||||
// 过滤掉每轮的 DONE 事件 — 只在全部迭代完成后发送一个最终 DONE
|
||||
if (event.type === MetonaStreamEventType.DONE) continue;
|
||||
// v0.8.0 P0-1: 先捕获 adapter 携带的 Provider 原生停止原因再过滤 ——
|
||||
// 引擎与 TRACE 据此区分自然完成与输出上限截断（length 此前完全不可见）
|
||||
if (event.type === MetonaStreamEventType.DONE) {
|
||||
if (event.finishReason) iterationFinishReason = event.finishReason;
|
||||
continue;
|
||||
}
|
||||
|
||||
// 过滤掉 RETRY 类型的 ERROR 事件 — 不转发到前端，避免触发虚假错误 UI
|
||||
// RETRY 事件仅用于 Engine 内部清空缓冲区（见下方 switch 分支）
|
||||
@@ -598,6 +654,11 @@ export class AgentLoopEngine extends EventEmitter {
|
||||
// === v0.2.0: PARSING 状态 — 解析流式缓冲区中的工具调用 ===
|
||||
await this.transitionTo(AgentLoopState.PARSING);
|
||||
|
||||
// v0.8.0 P0-1: 记录本轮停止原因到迭代步骤（TRACE/审计/前端提示的输入）
|
||||
if (iterationFinishReason) {
|
||||
step.finishReason = iterationFinishReason;
|
||||
}
|
||||
|
||||
// L-19 修复: 提取 finalizeToolCallsFromBuffer 子方法（PARSING 阶段）
|
||||
this.finalizeToolCallsFromBuffer(step, toolCallsBuffer);
|
||||
|
||||
@@ -1031,6 +1092,11 @@ export class AgentLoopEngine extends EventEmitter {
|
||||
let attempt = 0;
|
||||
let currentAdapter = this.adapter;
|
||||
let failoverUsed = false;
|
||||
// v0.8.0 P0-2: 降级重试状态。思考耗尽型截断（reasoning 烧满输出预算、正文
|
||||
// 零字节）时以 thinkingEnabled=false 重发一次（每 run 最多一次）；activeRequest
|
||||
// 被替换后，后续的重试与故障转移均使用降级版请求（降级跨故障转移保持）。
|
||||
let degradedThinkingRetryUsed = false;
|
||||
let activeRequest = request;
|
||||
|
||||
while (true) {
|
||||
try {
|
||||
@@ -1038,9 +1104,9 @@ export class AgentLoopEngine extends EventEmitter {
|
||||
// 重试时：先发送一个 retry 事件，让 UI 清空已接收的 delta
|
||||
yield {
|
||||
type: MetonaStreamEventType.ERROR,
|
||||
requestId: request.meta.requestId,
|
||||
sessionId: request.meta.sessionId,
|
||||
iteration: request.meta.iteration,
|
||||
requestId: activeRequest.meta.requestId,
|
||||
sessionId: activeRequest.meta.sessionId,
|
||||
iteration: activeRequest.meta.iteration,
|
||||
seq: 0,
|
||||
timestamp: Date.now(),
|
||||
error: {
|
||||
@@ -1050,7 +1116,86 @@ export class AgentLoopEngine extends EventEmitter {
|
||||
},
|
||||
};
|
||||
}
|
||||
yield* currentAdapter.sendStream(request);
|
||||
// v0.8.0 P0-2: 逐事件跟踪内容产出与停止原因（原 yield* 直通改显式转发）。
|
||||
// yield* 正常返回后执行流结束契约检查；异常路径不进入检查（走 catch 重试）。
|
||||
// - sawThought: 思考有产出（REASONING_DELTA）
|
||||
// - sawOutput: 正文/工具调用有产出（TEXT_DELTA / TOOL_CALL_*）
|
||||
// - lastFinishReason: adapter DONE 携带的 Provider 原生停止原因
|
||||
let sawThought = false;
|
||||
let sawOutput = false;
|
||||
let lastFinishReason: string | undefined;
|
||||
for await (const event of currentAdapter.sendStream(activeRequest)) {
|
||||
if (event.type === MetonaStreamEventType.REASONING_DELTA) {
|
||||
sawThought = true;
|
||||
}
|
||||
if (
|
||||
event.type === MetonaStreamEventType.TEXT_DELTA ||
|
||||
event.type === MetonaStreamEventType.TOOL_CALL_DELTA ||
|
||||
event.type === MetonaStreamEventType.TOOL_CALL_COMPLETE
|
||||
) {
|
||||
sawOutput = true;
|
||||
}
|
||||
if (event.type === MetonaStreamEventType.DONE && event.finishReason) {
|
||||
lastFinishReason = event.finishReason;
|
||||
}
|
||||
yield event;
|
||||
}
|
||||
|
||||
// ===== 流结束契约检查（根治"空回复 → 静默 COMPLETED → 会话无声停止"）=====
|
||||
if (!sawOutput) {
|
||||
if (!sawThought) {
|
||||
// 零产出流：连接中断被 [DONE] 兜底合成 / 上游干净空响应 —— 可重试
|
||||
// 瞬时故障（status=503 命中 5xx 重试分支），重试耗尽后 ERROR 收尾
|
||||
throw new EmptyResponseError(
|
||||
'Model returned an empty stream (no reasoning, no text, no tool calls). ' +
|
||||
'This is usually caused by an upstream connection drop or an output-limit cutoff.',
|
||||
);
|
||||
}
|
||||
if (lastFinishReason === 'length') {
|
||||
// 思考耗尽型截断（v0.7.4 生产事故形态：finish_reason=length、正文零
|
||||
// 字节）—— 先做一次性降级重试（临时关闭思考重发），仍复现则终止。
|
||||
if (!degradedThinkingRetryUsed && activeRequest.params.thinkingEnabled === true) {
|
||||
degradedThinkingRetryUsed = true;
|
||||
attempt = 0;
|
||||
activeRequest = {
|
||||
...activeRequest,
|
||||
params: { ...activeRequest.params, thinkingEnabled: false },
|
||||
};
|
||||
log.warn(
|
||||
'[AgentLoop] Output budget exhausted by reasoning (finish_reason=length, empty content) — retrying once with thinking disabled',
|
||||
);
|
||||
yield {
|
||||
type: MetonaStreamEventType.ERROR,
|
||||
requestId: activeRequest.meta.requestId,
|
||||
sessionId: activeRequest.meta.sessionId,
|
||||
iteration: activeRequest.meta.iteration,
|
||||
seq: 0,
|
||||
timestamp: Date.now(),
|
||||
error: {
|
||||
code: MetonaErrorCode.RETRY,
|
||||
message: 'Thinking consumed the output budget — retrying with thinking disabled',
|
||||
retryable: true,
|
||||
},
|
||||
};
|
||||
continue;
|
||||
}
|
||||
// 降级重试不可用（已用 / 思考本就关闭）仍截断 —— 终止：携带 IR 预留
|
||||
// 的 OUTPUT_LENGTH_EXCEEDED 码，finish() 映射为结构化错误事件，
|
||||
// 非 retryable 同时触发 Provider 故障转移（备用预算更大即自愈）。
|
||||
throw new OutputTruncatedError(
|
||||
'The model consumed the entire output token budget on reasoning and produced no answer ' +
|
||||
'(finish_reason=length). Raise the max output limit, disable thinking, or switch to a model with a larger output budget.',
|
||||
);
|
||||
}
|
||||
// 思考有产出但自然结束且零正文（罕见的服务端异常收尾）—— 与零产出流
|
||||
// 同按可重试空响应处理（retryCount 兜底防循环）
|
||||
throw new EmptyResponseError(
|
||||
'Model stream ended after reasoning without any answer content.',
|
||||
);
|
||||
}
|
||||
// sawOutput=true：正文/工具调用已有产出。length 截断场景不再重试 ——
|
||||
// 工具参数截断由 _truncatedArguments 自愈（v0.6.3 契约）、正文截断由
|
||||
// DONE.finishReason='length' 驱动前端截断提醒（P0-4）。
|
||||
return;
|
||||
} catch (error) {
|
||||
if (this.aborted) throw error;
|
||||
@@ -1136,6 +1281,11 @@ export class AgentLoopEngine extends EventEmitter {
|
||||
|
||||
/** 判断错误是否可重试 */
|
||||
private isRetryableError(error: unknown): boolean {
|
||||
// v0.8.0 P0-2: 流结束契约错误的显式归类（EmptyResponseError 自带 status=503、
|
||||
// OutputTruncatedError 自带 status=400，本可由下方 5xx/4xx 分支覆盖；此处
|
||||
// 显式 instanceof 使两类新错误的语义不依赖 status 字段约定）
|
||||
if (error instanceof EmptyResponseError) return true;
|
||||
if (error instanceof OutputTruncatedError) return false;
|
||||
const err = error as { status?: number; code?: string; message?: string };
|
||||
// 429 Too Many Requests — 可重试
|
||||
if (err.status === 429) return true;
|
||||
@@ -1482,9 +1632,17 @@ export class AgentLoopEngine extends EventEmitter {
|
||||
if ((reason === TerminationReason.ERROR || reason === TerminationReason.DEAD_LOOP) && error) {
|
||||
// v0.3.17: 识别 ContentFilterError，映射为 CONTENT_FILTERED 错误码 + 友好消息
|
||||
// v0.6.4: 流式路径的拦截以 err.code='content_filtered' 抵达（无 instanceof 上下文），一并识别
|
||||
// v0.8.0 P0-2: 透传流结束契约错误的结构化错误码（OUTPUT_LENGTH_EXCEEDED 等），
|
||||
// 前端据此展示针对性文案而非泛化 UNKNOWN
|
||||
const isContentFilter =
|
||||
error instanceof ContentFilterError ||
|
||||
(error as Error & { code?: string }).code === MetonaErrorCode.CONTENT_FILTERED;
|
||||
const rawErrorCode = (error as Error & { code?: string }).code;
|
||||
const errorCode = isContentFilter
|
||||
? MetonaErrorCode.CONTENT_FILTERED
|
||||
: rawErrorCode === MetonaErrorCode.OUTPUT_LENGTH_EXCEEDED
|
||||
? MetonaErrorCode.OUTPUT_LENGTH_EXCEEDED
|
||||
: MetonaErrorCode.UNKNOWN;
|
||||
this.emit('streamEvent', {
|
||||
type: MetonaStreamEventType.ERROR,
|
||||
requestId: this.currentRequestId,
|
||||
@@ -1494,7 +1652,7 @@ export class AgentLoopEngine extends EventEmitter {
|
||||
timestamp: Date.now(),
|
||||
runId: this.runId,
|
||||
error: {
|
||||
code: isContentFilter ? MetonaErrorCode.CONTENT_FILTERED : MetonaErrorCode.UNKNOWN,
|
||||
code: errorCode,
|
||||
message: isContentFilter
|
||||
? '内容被 Provider 安全审核拦截，请修改图片或文本后重试'
|
||||
: error.message,
|
||||
@@ -1513,6 +1671,9 @@ export class AgentLoopEngine extends EventEmitter {
|
||||
timestamp: Date.now(),
|
||||
runId: this.runId,
|
||||
terminationReason: reason,
|
||||
// v0.8.0 P0-1: 转发最后一轮的 Provider 原生停止原因（前端据此展示
|
||||
// "回答可能因输出上限被截断"等提示；无流式轮次时为 undefined）
|
||||
...(this.lastIterationFinishReason ? { finishReason: this.lastIterationFinishReason } : {}),
|
||||
});
|
||||
|
||||
// H-3: 通过 stateChange 发射 TERMINATED 状态（前端可据此清理 UI）
|
||||
|
||||
@@ -1,4 +1,6 @@
|
||||
export { AgentLoopEngine } from './engine';
|
||||
// v0.8.0 P0-2: 流结束契约错误（空响应重试 / 思考耗尽截断终止）—— 导出供测试断言
|
||||
export { EmptyResponseError, OutputTruncatedError } from './engine';
|
||||
export {
|
||||
AgentLoopState,
|
||||
TerminationReason,
|
||||
|
||||
@@ -48,6 +48,13 @@ export interface IterationStep {
|
||||
toolCalls?: MetonaToolCall[];
|
||||
toolResults?: MetonaToolResult[];
|
||||
tokenUsage?: TokenUsage;
|
||||
/**
|
||||
* v0.8.0 P0-1: 本轮 LLM 流的 Provider 原生停止原因（归一化 OpenAI 语义：
|
||||
* 'stop' | 'length' | 'tool_calls' | 'content_filter'）。
|
||||
* 由 adapter DONE 事件携带、引擎捕获；TRACE 层据此记录真值，
|
||||
* 引擎据此区分"自然完成"与"输出上限截断"（P0-2 空响应守卫的输入）。
|
||||
*/
|
||||
finishReason?: string;
|
||||
}
|
||||
|
||||
export interface TokenUsage {
|
||||
|
||||
@@ -248,7 +248,9 @@ describe('SecurityScanHook — 分级防护矩阵', () => {
|
||||
const hook = new SecurityScanHook(asDefender(sd));
|
||||
await hook.afterExecute(toolCall('web_fetch'), failRes, 's');
|
||||
await hook.afterExecute(toolCall('web_fetch'), zeroScoreRes, 's');
|
||||
expect(failRes.result).toBe(failRes.result);
|
||||
// v0.8.0 P3 根治: 旧断言 failRes.result 自比恒真 —— 现断言"失败结果不触发
|
||||
// 扫描、内容保持原样"（与下方 zero-score 计数互补）
|
||||
expect(failRes.result).toBe(longText('__low_score_'));
|
||||
expect(
|
||||
sd.detectSemantic.mock.calls.filter((c: unknown[]) => String(c[0]).includes('__zero')).length,
|
||||
).toBe(1);
|
||||
|
||||
@@ -157,6 +157,8 @@ describe.skipIf(!dbAvailable)('MemoryManager — tokenize 分词', () => {
|
||||
it('数字/纯符号文本产生空 token 列表（search 返回空）', () => {
|
||||
const tokens = tokensOf('12345 !@#');
|
||||
expect(Array.isArray(tokens)).toBe(true);
|
||||
// v0.8.0 P3: 补强断言 —— 旧断言只验数组类型未验为空
|
||||
expect(tokens).toHaveLength(0);
|
||||
});
|
||||
});
|
||||
|
||||
|
||||
@@ -39,12 +39,24 @@ const seenRequests: MetonaRequest[] = [];
|
||||
|
||||
function doneOnlyStream(request: MetonaRequest): AsyncGenerator<MetonaStreamEvent> {
|
||||
return (async function* () {
|
||||
// v0.8.0 P0-2 契约对齐: 引擎的流结束契约要求至少有一个产出事件
|
||||
//（TEXT/REASONING/TOOL_CALL），纯 DONE 空流会被 EmptyResponseError 守卫
|
||||
// 判为可重试空响应并触发退避重试。此处补一个 TEXT_DELTA 使流构成合法完成。
|
||||
yield {
|
||||
type: MetonaStreamEventType.TEXT_DELTA,
|
||||
requestId: request.meta.requestId,
|
||||
sessionId: request.meta.sessionId,
|
||||
iteration: request.meta.iteration,
|
||||
seq: 0,
|
||||
timestamp: Date.now(),
|
||||
delta: 'sub-agent done',
|
||||
} as MetonaStreamEvent;
|
||||
yield {
|
||||
type: MetonaStreamEventType.DONE,
|
||||
requestId: request.meta.requestId,
|
||||
sessionId: request.meta.sessionId,
|
||||
iteration: request.meta.iteration,
|
||||
seq: 0,
|
||||
seq: 1,
|
||||
timestamp: Date.now(),
|
||||
} as MetonaStreamEvent;
|
||||
})();
|
||||
@@ -314,8 +326,10 @@ describe('TaskOrchestrator — 中断契约', () => {
|
||||
|
||||
releases.forEach((r) => r());
|
||||
const results = await Promise.all([a, b]);
|
||||
// A 被中断、B 正常完成，两者都最终收尾
|
||||
expect(results.map((r) => r.success)).toEqual([true, true]);
|
||||
// A 被中断、B 正常完成，两者都最终收尾。
|
||||
// v0.8.0 P0-2 abort 优先级修复后：被中断的 A 以 USER_INTERRUPT 终止 →
|
||||
// success=false（旧实现 COMPLETED 抢占使 A 误报 success=true，属缺陷语义）。
|
||||
expect(results.map((r) => r.success)).toEqual([false, true]);
|
||||
expect(orchestrator.getActiveAgentsStatus()).toHaveLength(0);
|
||||
});
|
||||
|
||||
|
||||
@@ -129,6 +129,12 @@ export class TaskOrchestrator extends EventEmitter {
|
||||
parentSessionId: string;
|
||||
maxIterations?: number;
|
||||
tools?: string[];
|
||||
/**
|
||||
* v0.8.0 P1-2: 引擎级取消信号 —— delegate_task 工具透传 context.signal，
|
||||
* 用户中断父会话时 SubEngine 联动终止（此前工具被 registry 兜底超时杀掉，
|
||||
* SubEngine 仍在后台跑满剩余轮次）。
|
||||
*/
|
||||
signal?: AbortSignal;
|
||||
}): Promise<SubAgentResult> {
|
||||
const taskId = params.taskId ?? `sub_${nanoid(8)}`;
|
||||
const startMs = Date.now();
|
||||
@@ -183,6 +189,18 @@ export class TaskOrchestrator extends EventEmitter {
|
||||
subEngine.setFallbackAdapter(this.engines.getFallbackAdapter());
|
||||
subEngine.setWorkspacePath(this.engines.getWorkspacePath());
|
||||
|
||||
// v0.8.0 P1-2: 外部取消信号联动 —— signal 已中止或运行中触发 abort 时
|
||||
// 终止 SubEngine；finally 中解除监听防泄漏
|
||||
let onExternalAbort: (() => void) | null = null;
|
||||
if (params.signal) {
|
||||
if (params.signal.aborted) {
|
||||
subEngine.abort();
|
||||
} else {
|
||||
onExternalAbort = () => subEngine.abort();
|
||||
params.signal.addEventListener('abort', onExternalAbort, { once: true });
|
||||
}
|
||||
}
|
||||
|
||||
// v0.5.0: 转发 SubEngine 的流式/状态事件（供 TRACE 录制与前端可观测）
|
||||
// 事件以 taskId 为 sessionId，录制到独立 JSONL 文件，不污染父会话的流
|
||||
this.forwardSubEngineEvents(subEngine, taskId);
|
||||
@@ -283,6 +301,10 @@ export class TaskOrchestrator extends EventEmitter {
|
||||
|
||||
return result;
|
||||
} finally {
|
||||
// v0.8.0 P1-2: 解除外部取消信号监听（防事件循环泄漏）
|
||||
if (params.signal && onExternalAbort) {
|
||||
params.signal.removeEventListener('abort', onExternalAbort);
|
||||
}
|
||||
// #5 修复: 统一在 finally 块恢复 sessionDepth，覆盖正常完成/异常/abort 所有路径
|
||||
// 审查修复: 如果 abortAll 已 clear sessionDepth，不再恢复（避免覆盖紧急清理）。
|
||||
// 场景：用户紧急中断时 abortAll 先 clear，若 SubEngine 随后才返回执行 finally，
|
||||
|
||||
@@ -104,16 +104,13 @@ describe('ToolRegistry.truncateResult', () => {
|
||||
expect(truncate(shot)).toBe(shot);
|
||||
});
|
||||
|
||||
it('WEBP 魔数（RIFF....WEBP）的裸 base64 放行', () => {
|
||||
const shot = { image: `UklGRg==${'A'.repeat(200_000)}WEBP` };
|
||||
// RIFF 头 base64 'UklGRg==' 解码为 'RIFF\x00\x00\x00\x00'，WEBP 魔数在 8-11 字节
|
||||
const result = truncate(shot) as { image?: string; _truncated?: boolean };
|
||||
if (result._truncated === true) {
|
||||
// WEBP 魔数未命中（base64 头部 64 字节内未含完整 RIFF+WEBP）→ 走常规截断（保守）
|
||||
expect(result.image).toBeUndefined();
|
||||
} else {
|
||||
expect(result).toBe(shot);
|
||||
}
|
||||
it('WEBP 魔数（RIFF....WEBP）的裸 base64 放行（v0.8.0 P3: 单向断言替代恒真分支）', () => {
|
||||
// v0.8.0 P3 根治: 旧断言按 _truncated 分支双向放行（无论实现如何都通过，恒真）。
|
||||
// 现构造 8-11 字节确为 'WEBP' 的确定性载荷：base64('RIFF\0\0\0\0WEBP') 前缀，
|
||||
// isInlineImagePayload 必命中白名单 → 整段放行。
|
||||
const head = Buffer.from('RIFF\0\0\0\0WEBP', 'latin1').toString('base64');
|
||||
const shot = { image: head + 'A'.repeat(200_000) };
|
||||
expect(truncate(shot)).toBe(shot);
|
||||
});
|
||||
|
||||
it('image 字段但非图片内容（普通长文本）仍按常规 50KB 截断（堵住旧白名单漏洞）', () => {
|
||||
|
||||
@@ -248,22 +248,25 @@ describe('filesystem 工具 — read_file', () => {
|
||||
expect(String(r.content).charCodeAt(0)).not.toBe(0xfeff);
|
||||
});
|
||||
|
||||
it('UTF-16LE 文件被二进制检测拒绝（0x00 字节触发，编码探测死代码）', async () => {
|
||||
// 已知源码缺陷：isBinaryFile 的 NUL 字节检测拒绝一切 UTF-16 文件，
|
||||
// decodeBufferWithDetection 的 UTF-16 分支因此不可达。此处锁定实际契约。
|
||||
it('UTF-16LE 文件正常读取（v0.8.0 P1-3.3 BOM 检测根治后契约）', async () => {
|
||||
// v0.8.0 P1-3.3 根治: isBinaryFile 此前的 NUL 字节启发式拒绝一切 UTF-16
|
||||
// 文件，decodeBufferWithDetection 的 UTF-16 分支不可达（原缺陷被本测试
|
||||
// 锁定留档）。现 UTF-16 BOM（FF FE / FE FF）视为文本，编码探测生效。
|
||||
const r = (await tool.execute({ file_path: 'utf16le.txt' }, ctxFor(ws))) as {
|
||||
success: boolean;
|
||||
error?: string;
|
||||
content?: string;
|
||||
encoding?: string;
|
||||
};
|
||||
expect(r.success).toBe(false);
|
||||
expect(String((r as { error?: string }).error)).toContain('Binary');
|
||||
expect(r.success).toBe(true);
|
||||
expect(r.encoding).toBe('utf-16le');
|
||||
});
|
||||
|
||||
it('UTF-16BE 文件同样被二进制检测拒绝（实况契约）', async () => {
|
||||
it('UTF-16BE 文件正常读取（v0.8.0 P1-3.3）', async () => {
|
||||
const r = (await tool.execute({ file_path: 'utf16be.txt' }, ctxFor(ws))) as {
|
||||
success: boolean;
|
||||
content?: string;
|
||||
};
|
||||
expect(r.success).toBe(false);
|
||||
expect(r.success).toBe(true);
|
||||
});
|
||||
|
||||
it('GBK 字节样本 → 降级 gbk 编码并正确解码', async () => {
|
||||
|
||||
@@ -11,6 +11,9 @@ import { BrowserWindow, session } from 'electron';
|
||||
import log from 'electron-log';
|
||||
// v0.7.3 P2-2: CORS Origin 回显（纯函数在 network-utils，可表测）
|
||||
import { corsAllowOrigin, extractOriginHeader } from './network-utils';
|
||||
// v0.8.0 P1-4: 浏览器通道 SSRF 根治 —— 分区流量走本地 Pinned CONNECT 代理
|
||||
import { ensurePinnedProxy } from '../../../utils/pinned-proxy';
|
||||
import { isProxyActive } from '../../../utils/network-proxy';
|
||||
|
||||
/** Agent 浏览器专用 session partition — 与主应用 default session 完全隔离 */
|
||||
const AGENT_PARTITION = 'persist:metona-agent-browser';
|
||||
@@ -146,6 +149,28 @@ export class BrowserWindowManager {
|
||||
// 跨域 Origin / 无 Origin 一律不加 ACAO 头 —— 保持默认同源策略阻止读取，
|
||||
// 彻底堵死"第三方页面借该分区凭据读取跨域资源"的通道。
|
||||
const agentSession = session.fromPartition(AGENT_PARTITION);
|
||||
|
||||
// v0.8.0 P1-4 根治: 浏览器通道 SSRF —— 分区全部流量经本地 Pinned CONNECT
|
||||
// 代理（入口同源校验 + 校验期 IP pinning，Chromium 端 TLS/SNI 端到端不变），
|
||||
// 关闭"入口校验通过 → Chromium 独立 DNS 解析"之间的 rebinding 残余窗口。
|
||||
// 用户已显式配置 network.proxyUrl 时不启用（代理模式下 DNS 在代理端解析、
|
||||
// pinning 不可实现，保持 M7 已知限制口径）；代理启动失败降级可用性优先。
|
||||
if (!isProxyActive()) {
|
||||
const proxyPort = await ensurePinnedProxy();
|
||||
if (proxyPort) {
|
||||
try {
|
||||
await agentSession.setProxy({
|
||||
proxyRules: `http=127.0.0.1:${proxyPort};https=127.0.0.1:${proxyPort}`,
|
||||
});
|
||||
log.info(
|
||||
`[BrowserWindowManager] agent partition routed via pinned proxy :${proxyPort}`,
|
||||
);
|
||||
} catch (err) {
|
||||
log.warn('[BrowserWindowManager] pinned proxy setProxy failed:', err);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
agentSession.webRequest.onHeadersReceived((details, callback) => {
|
||||
// Electron 类型在此版本的 OnHeadersReceivedListenerDetails 上不暴露
|
||||
// requestHeaders —— 显式声明读取面（Origin 大小写不敏感提取）
|
||||
@@ -308,21 +333,48 @@ export class BrowserWindowManager {
|
||||
* 各自直接 open/evaluate 共享单例，后到者销毁前者的窗口（崩溃根因，
|
||||
* 见 openChain 注释）。排队后同一时刻只有一个抓取在使用窗口。
|
||||
*
|
||||
* v0.8.0 P1-2: 新增可选 abort signal —— 中断时停止页面加载（webContents.stop）
|
||||
* 并在序列各步骤间检查，终止整个 open→等待→evaluate 链。
|
||||
*
|
||||
* @returns 提取的页面正文；失败/内容过短返回 null（调用方走失败路径）
|
||||
*/
|
||||
async fetchPageText(url: string): Promise<string | null> {
|
||||
async fetchPageText(url: string, signal?: AbortSignal): Promise<string | null> {
|
||||
const run = async (): Promise<string | null> => {
|
||||
await this.openInternal({ url });
|
||||
await this.sleep(2_500);
|
||||
const text = (await this.evaluate(`
|
||||
(function() {
|
||||
var clone = document.body.cloneNode(true);
|
||||
var noise = clone.querySelectorAll('script, style, noscript, nav, header, footer, aside, iframe, svg');
|
||||
noise.forEach(function(el) { el.remove(); });
|
||||
return clone.innerText || '';
|
||||
})();
|
||||
`)) as string;
|
||||
return text && text.trim() ? text : null;
|
||||
const throwIfAborted = (): void => {
|
||||
if (signal?.aborted) throw new Error('Browser fetch aborted');
|
||||
};
|
||||
// abort 时停止页面加载 —— loadURL/evaluate 会以 ERR_ABORTED 拒绝，
|
||||
// 序列随之终止（窗口由单例管理，不在此销毁）
|
||||
let onAbort: (() => void) | null = null;
|
||||
if (signal && !signal.aborted) {
|
||||
onAbort = () => {
|
||||
try {
|
||||
this.win?.webContents.stop();
|
||||
} catch {
|
||||
/* 窗口可能已销毁 */
|
||||
}
|
||||
};
|
||||
signal.addEventListener('abort', onAbort, { once: true });
|
||||
}
|
||||
try {
|
||||
throwIfAborted();
|
||||
await this.openInternal({ url });
|
||||
throwIfAborted();
|
||||
await this.sleep(2_500);
|
||||
throwIfAborted();
|
||||
const text = (await this.evaluate(`
|
||||
(function() {
|
||||
var clone = document.body.cloneNode(true);
|
||||
var noise = clone.querySelectorAll('script, style, noscript, nav, header, footer, aside, iframe, svg');
|
||||
noise.forEach(function(el) { el.remove(); });
|
||||
return clone.innerText || '';
|
||||
})();
|
||||
`)) as string;
|
||||
throwIfAborted();
|
||||
return text && text.trim() ? text : null;
|
||||
} finally {
|
||||
if (signal && onAbort) signal.removeEventListener('abort', onAbort);
|
||||
}
|
||||
};
|
||||
this.openChain = this.openChain.then(run, run);
|
||||
return this.openChain as Promise<string | null>;
|
||||
|
||||
@@ -40,7 +40,8 @@ export class CodeSearchTool implements IMetonaTool {
|
||||
|
||||
readonly definition: MetonaToolDef = {
|
||||
name: 'code_search',
|
||||
description: 'Search code using ripgrep. Supports regex patterns, file type filtering, and context lines. Much faster than search_files for large codebases. Falls back to JS implementation if ripgrep is not installed.',
|
||||
description:
|
||||
'Search code using ripgrep. Supports regex patterns, file type filtering, and context lines. Much faster than search_files for large codebases. Falls back to JS implementation if ripgrep is not installed.',
|
||||
parameters: {
|
||||
type: 'object',
|
||||
properties: {
|
||||
@@ -48,8 +49,14 @@ export class CodeSearchTool implements IMetonaTool {
|
||||
path: { type: 'string', description: 'Search directory (default: workspace root)' },
|
||||
file_glob: { type: 'string', description: 'File name glob filter (e.g., "*.ts", "*.py")' },
|
||||
case_sensitive: { type: 'boolean', description: 'Case sensitive search (default false)' },
|
||||
context_before: { type: 'number', description: 'Lines of context before match (default 0, max 5)' },
|
||||
context_after: { type: 'number', description: 'Lines of context after match (default 0, max 5)' },
|
||||
context_before: {
|
||||
type: 'number',
|
||||
description: 'Lines of context before match (default 0, max 5)',
|
||||
},
|
||||
context_after: {
|
||||
type: 'number',
|
||||
description: 'Lines of context after match (default 0, max 5)',
|
||||
},
|
||||
max_results: { type: 'number', description: 'Maximum results (default 50, max 200)' },
|
||||
},
|
||||
required: ['pattern'],
|
||||
@@ -98,7 +105,13 @@ export class CodeSearchTool implements IMetonaTool {
|
||||
private async searchWithRipgrep(
|
||||
pattern: string,
|
||||
searchPath: string,
|
||||
opts: { fileGlob?: string; caseSensitive: boolean; contextBefore: number; contextAfter: number; maxResults: number },
|
||||
opts: {
|
||||
fileGlob?: string;
|
||||
caseSensitive: boolean;
|
||||
contextBefore: number;
|
||||
contextAfter: number;
|
||||
maxResults: number;
|
||||
},
|
||||
context: ToolExecutionContext,
|
||||
): Promise<unknown> {
|
||||
const rgArgs: string[] = ['--json'];
|
||||
@@ -118,12 +131,31 @@ export class CodeSearchTool implements IMetonaTool {
|
||||
const { stdout } = await execFileAsync('rg', rgArgs, {
|
||||
maxBuffer: 10 * 1024 * 1024,
|
||||
timeout: 25_000,
|
||||
// v0.8.0 P1-2: 引擎级 abort 信号 —— 用户中断会话时立即 kill rg 子进程
|
||||
//（Node execFile 原生支持 signal 选项，触发时以 AbortError 拒绝）
|
||||
signal: context.signal,
|
||||
});
|
||||
|
||||
const results = this.parseRipgrepJsonOutput(stdout);
|
||||
return { results: results.slice(0, opts.maxResults), count: results.length, engine: 'ripgrep' };
|
||||
return {
|
||||
results: results.slice(0, opts.maxResults),
|
||||
count: results.length,
|
||||
engine: 'ripgrep',
|
||||
};
|
||||
} catch (error) {
|
||||
const err = error as { code?: number; signal?: string; stdout?: string; stderr?: string; killed?: boolean; message?: string };
|
||||
const err = error as {
|
||||
code?: number;
|
||||
signal?: string;
|
||||
stdout?: string;
|
||||
stderr?: string;
|
||||
killed?: boolean;
|
||||
message?: string;
|
||||
name?: string;
|
||||
};
|
||||
// v0.8.0 P1-2: 引擎 abort → 直接以中断语义返回（不再回退 JS 搜索）
|
||||
if (err.name === 'AbortError' || context.signal?.aborted) {
|
||||
return { results: [], count: 0, error: 'Search aborted', engine: 'ripgrep', aborted: true };
|
||||
}
|
||||
// rg 退出码 1 = 无匹配，不是错误
|
||||
if (err.code === 1) {
|
||||
return { results: [], count: 0, engine: 'ripgrep' };
|
||||
@@ -148,10 +180,24 @@ export class CodeSearchTool implements IMetonaTool {
|
||||
before?: string[];
|
||||
after?: string[];
|
||||
}> {
|
||||
const results: Array<{ path: string; line: number; column: number; match: string; before?: string[]; after?: string[] }> = [];
|
||||
const results: Array<{
|
||||
path: string;
|
||||
line: number;
|
||||
column: number;
|
||||
match: string;
|
||||
before?: string[];
|
||||
after?: string[];
|
||||
}> = [];
|
||||
const lines = output.split('\n').filter((l) => l.trim());
|
||||
|
||||
let currentMatch: { path: string; line: number; column: number; match: string; before?: string[]; after?: string[] } | null = null;
|
||||
let currentMatch: {
|
||||
path: string;
|
||||
line: number;
|
||||
column: number;
|
||||
match: string;
|
||||
before?: string[];
|
||||
after?: string[];
|
||||
} | null = null;
|
||||
let beforeBuffer: string[] = [];
|
||||
let afterBuffer: string[] = [];
|
||||
|
||||
@@ -185,7 +231,9 @@ export class CodeSearchTool implements IMetonaTool {
|
||||
}
|
||||
|
||||
const text = (data.lines as { text?: string } | undefined)?.text ?? '';
|
||||
const submatches = (data.submatches as Array<{ match: { text?: string }; start?: number }> | undefined) ?? [];
|
||||
const submatches =
|
||||
(data.submatches as Array<{ match: { text?: string }; start?: number }> | undefined) ??
|
||||
[];
|
||||
const matchText = submatches[0]?.match?.text ?? text;
|
||||
const column = (submatches[0]?.start ?? 0) + 1;
|
||||
|
||||
@@ -214,18 +262,33 @@ export class CodeSearchTool implements IMetonaTool {
|
||||
private async searchWithJs(
|
||||
pattern: string,
|
||||
searchPath: string,
|
||||
opts: { fileGlob?: string; caseSensitive: boolean; contextBefore: number; contextAfter: number; maxResults: number },
|
||||
opts: {
|
||||
fileGlob?: string;
|
||||
caseSensitive: boolean;
|
||||
contextBefore: number;
|
||||
contextAfter: number;
|
||||
maxResults: number;
|
||||
},
|
||||
context: ToolExecutionContext,
|
||||
): Promise<unknown> {
|
||||
// 动态导入以避免循环依赖
|
||||
const { SearchFilesTool } = await import('./filesystem');
|
||||
const searchTool = new SearchFilesTool();
|
||||
return searchTool.execute({
|
||||
pattern,
|
||||
target: 'content',
|
||||
path: searchPath,
|
||||
file_glob: opts.fileGlob,
|
||||
limit: opts.maxResults,
|
||||
}, context);
|
||||
// v0.8.0 P1-3.5 根治: 回退路径此前静默丢失 case_sensitive / context_before /
|
||||
// context_after —— 同一调用在 ripgrep 存在与否会产生不同结果（行为不对称）。
|
||||
// SearchFilesTool 现已支持这三个参数（filesystem.ts P1-3.5），原样透传。
|
||||
return searchTool.execute(
|
||||
{
|
||||
pattern,
|
||||
target: 'content',
|
||||
path: searchPath,
|
||||
file_glob: opts.fileGlob,
|
||||
limit: opts.maxResults,
|
||||
case_sensitive: opts.caseSensitive,
|
||||
context_before: opts.contextBefore,
|
||||
context_after: opts.contextAfter,
|
||||
},
|
||||
context,
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -15,18 +15,21 @@ import type { TaskOrchestrator } from '../../orchestration/orchestrator';
|
||||
export class DelegateTaskTool implements IMetonaTool {
|
||||
readonly definition: MetonaToolDef = {
|
||||
name: 'delegate_task',
|
||||
description: 'Delegate a sub-task to an independent SubAgent for parallel or isolated execution. The SubAgent runs its own ReAct loop and returns the final result. Use this for complex sub-tasks that benefit from focused reasoning.',
|
||||
description:
|
||||
'Delegate a sub-task to an independent SubAgent for parallel or isolated execution. The SubAgent runs its own ReAct loop and returns the final result. Use this for complex sub-tasks that benefit from focused reasoning.',
|
||||
parameters: {
|
||||
type: 'object',
|
||||
properties: {
|
||||
description: {
|
||||
type: 'string',
|
||||
description: 'Clear and detailed description of the sub-task to delegate. This will be the SubAgent\'s user message.',
|
||||
description:
|
||||
"Clear and detailed description of the sub-task to delegate. This will be the SubAgent's user message.",
|
||||
},
|
||||
tools: {
|
||||
type: 'array',
|
||||
items: { type: 'string', description: 'Tool name' },
|
||||
description: 'Optional whitelist of tool names the SubAgent can use (e.g. ["read_file", "web_search"]). If omitted, SubAgent inherits all tools.',
|
||||
description:
|
||||
'Optional whitelist of tool names the SubAgent can use (e.g. ["read_file", "web_search"]). If omitted, SubAgent inherits all tools.',
|
||||
},
|
||||
maxIterations: {
|
||||
type: 'number',
|
||||
@@ -58,6 +61,8 @@ export class DelegateTaskTool implements IMetonaTool {
|
||||
parentSessionId: context.sessionId,
|
||||
maxIterations,
|
||||
tools,
|
||||
// v0.8.0 P1-2: 引擎级 abort 信号透传 —— 用户中断会话时联动终止 SubAgent
|
||||
signal: context.signal,
|
||||
});
|
||||
|
||||
return {
|
||||
|
||||
@@ -19,6 +19,7 @@
|
||||
import { readFile, writeFile, rename, mkdir, stat, unlink } from 'fs/promises';
|
||||
import { dirname } from 'path';
|
||||
import { existsSync } from 'fs';
|
||||
import { nanoid } from 'nanoid';
|
||||
import type { IMetonaTool, ToolExecutionContext } from '../../types/metona-tool';
|
||||
import type { MetonaToolDef } from '../../../harness/types';
|
||||
import { MetonaToolCategory, MetonaRiskLevel } from '../../../harness/types';
|
||||
@@ -422,7 +423,8 @@ export class FileEditorTool implements IMetonaTool {
|
||||
|
||||
const newContent = newLines.join('\n');
|
||||
// F1.7: 原子写入 - 临时文件 + rename
|
||||
const tmpPath = `${filePath}.tmp_${Date.now()}`;
|
||||
// v0.8.0 P1-3.4: tmp 文件名追加 nanoid 随机段（同毫秒并发写防碰撞）
|
||||
const tmpPath = `${filePath}.tmp_${Date.now()}_${nanoid(6)}`;
|
||||
try {
|
||||
await writeFile(tmpPath, newContent, 'utf-8');
|
||||
await rename(tmpPath, filePath);
|
||||
|
||||
@@ -38,6 +38,7 @@ import {
|
||||
} from 'fs/promises';
|
||||
import { join, relative, resolve, dirname } from 'path';
|
||||
import { existsSync, realpathSync } from 'fs';
|
||||
import { nanoid } from 'nanoid';
|
||||
import type { IMetonaTool, ToolExecutionContext } from '../../types/metona-tool';
|
||||
import type { MetonaToolDef } from '../../../harness/types';
|
||||
import { MetonaToolCategory, MetonaRiskLevel } from '../../../harness/types';
|
||||
@@ -61,6 +62,13 @@ import {
|
||||
* v0.3.2 修复 FAIL: 使用 bytesRead 限制循环上界，而非 buffer.length。
|
||||
* Buffer.alloc(8192) 初始化为全 0，fd.read 只覆盖 [0, bytesRead) 区间，
|
||||
* 若用 buffer.length 遍历会误判所有 < 8192 字节的纯文本文件为二进制。
|
||||
*
|
||||
* v0.8.0 P1-3.3 根治: UTF-16 文件（LE: FF FE / BE: FE FF BOM）几乎每个字符
|
||||
* 都含 0x00 字节 —— NULL 字节启发式把一切 UTF-16 文本判为二进制并整体拒绝，
|
||||
* 使 decodeBufferWithDetection 的 UTF-16 解码分支不可达（原缺陷被
|
||||
* filesystem-tools.test.ts 锁定留档，本次随修复同步改约）。现先检测 UTF-16
|
||||
* BOM：命中即视为文本（UTF-16 解码由 decodeBufferWithDetection 承担），
|
||||
* 未命中 BOM 才走 NULL 字节启发式。
|
||||
*/
|
||||
async function isBinaryFile(filePath: string): Promise<boolean> {
|
||||
// M-20 修复: 使用 finally 块确保文件句柄关闭，防止 fd 泄漏
|
||||
@@ -69,6 +77,9 @@ async function isBinaryFile(filePath: string): Promise<boolean> {
|
||||
const buffer = Buffer.alloc(8192);
|
||||
fd = await open(filePath, 'r');
|
||||
const { bytesRead } = await fd.read(buffer, 0, 8192, 0);
|
||||
// v0.8.0 P1-3.3: UTF-16 LE/BE BOM → 文本（NUL 启发式对其无效）
|
||||
if (bytesRead >= 2 && buffer[0] === 0xff && buffer[1] === 0xfe) return false; // UTF-16 LE BOM
|
||||
if (bytesRead >= 2 && buffer[0] === 0xfe && buffer[1] === 0xff) return false; // UTF-16 BE BOM
|
||||
// 仅检查实际读取的字节范围 [0, bytesRead)
|
||||
// 含 NULL 字节 → 二进制；空文件（bytesRead=0）→ 非二进制
|
||||
for (let i = 0; i < bytesRead; i++) {
|
||||
@@ -346,7 +357,9 @@ export class WriteFileTool implements IMetonaTool {
|
||||
}
|
||||
|
||||
// v0.3.2: overwrite 模式使用原子写入（临时文件 + rename，与 file_editor 一致）
|
||||
const tmpPath = `${filePath}.tmp_${Date.now()}`;
|
||||
// v0.8.0 P1-3.4: tmp 文件名追加 nanoid 随机段 —— 同毫秒并发写同一文件时
|
||||
// Date.now() 精度的 tmp 名会互相覆盖（并行工具调用场景）
|
||||
const tmpPath = `${filePath}.tmp_${Date.now()}_${nanoid(6)}`;
|
||||
try {
|
||||
await writeFile(tmpPath, content, 'utf-8');
|
||||
await rename(tmpPath, filePath);
|
||||
@@ -395,6 +408,11 @@ export class ListDirectoryTool implements IMetonaTool {
|
||||
type: 'boolean',
|
||||
description: 'Include hidden files/dirs starting with "." (default false)',
|
||||
},
|
||||
include_node_modules: {
|
||||
type: 'boolean',
|
||||
description:
|
||||
'Include node_modules directories (default false — skipped for performance; set true to inspect dependency packages)',
|
||||
},
|
||||
},
|
||||
},
|
||||
category: MetonaToolCategory.FILESYSTEM,
|
||||
@@ -411,6 +429,8 @@ export class ListDirectoryTool implements IMetonaTool {
|
||||
const depth = Math.min(5, Math.max(1, (args.depth as number) ?? 1));
|
||||
const glob = args.glob as string | undefined;
|
||||
const includeHidden = (args.include_hidden as boolean) ?? false;
|
||||
// v0.8.0 P1-3.6: node_modules 可选纳入（默认跳过保持兼容）
|
||||
const includeNodeModules = (args.include_node_modules as boolean) ?? false;
|
||||
|
||||
// v0.3.2 修复 WARN-3: listDir 内部提前终止，避免大目录全量遍历
|
||||
const MAX_ENTRIES = 1000;
|
||||
@@ -421,7 +441,17 @@ export class ListDirectoryTool implements IMetonaTool {
|
||||
size?: number;
|
||||
modified?: string;
|
||||
}> = [];
|
||||
await this.listDir(dirPath, dirPath, depth, glob, includeHidden, 0, entries, MAX_ENTRIES);
|
||||
await this.listDir(
|
||||
dirPath,
|
||||
dirPath,
|
||||
depth,
|
||||
glob,
|
||||
includeHidden,
|
||||
includeNodeModules,
|
||||
0,
|
||||
entries,
|
||||
MAX_ENTRIES,
|
||||
);
|
||||
return {
|
||||
entries,
|
||||
count: entries.length,
|
||||
@@ -439,6 +469,7 @@ export class ListDirectoryTool implements IMetonaTool {
|
||||
maxDepth: number,
|
||||
glob: string | undefined,
|
||||
includeHidden: boolean,
|
||||
includeNodeModules: boolean,
|
||||
currentDepth: number,
|
||||
results: Array<{ name: string; path: string; type: string; size?: number; modified?: string }>,
|
||||
maxEntries: number,
|
||||
@@ -453,8 +484,9 @@ export class ListDirectoryTool implements IMetonaTool {
|
||||
if (results.length >= maxEntries) return;
|
||||
// v0.3.2: include_hidden 参数控制隐藏文件
|
||||
if (!includeHidden && entry.name.startsWith('.')) continue;
|
||||
// node_modules 始终跳过（太大）
|
||||
if (entry.name === 'node_modules') continue;
|
||||
// v0.8.0 P1-3.6: node_modules 默认跳过（太大）；include_node_modules=true
|
||||
// 时纳入（分析依赖包场景；上限保护仍生效）
|
||||
if (entry.name === 'node_modules' && !includeNodeModules) continue;
|
||||
|
||||
const fullPath = join(dirPath, entry.name);
|
||||
// 相对路径始终以根请求目录为基准
|
||||
@@ -470,6 +502,7 @@ export class ListDirectoryTool implements IMetonaTool {
|
||||
maxDepth,
|
||||
glob,
|
||||
includeHidden,
|
||||
includeNodeModules,
|
||||
currentDepth + 1,
|
||||
results,
|
||||
maxEntries,
|
||||
@@ -526,6 +559,19 @@ export class SearchFilesTool implements IMetonaTool {
|
||||
description:
|
||||
'Lines of context to show around content matches (default 0, max 5). Only for target="content".',
|
||||
},
|
||||
case_sensitive: {
|
||||
type: 'boolean',
|
||||
description:
|
||||
'Case sensitive search (default false — v0.8.0 P1-3.5: previously hardcoded case-insensitive, breaking code_search fallback symmetry)',
|
||||
},
|
||||
context_before: {
|
||||
type: 'number',
|
||||
description: 'Lines of context before match (default = context_lines, max 5)',
|
||||
},
|
||||
context_after: {
|
||||
type: 'number',
|
||||
description: 'Lines of context after match (default = context_lines, max 5)',
|
||||
},
|
||||
include_hidden: {
|
||||
type: 'boolean',
|
||||
description: 'Include hidden files/dirs starting with "." (default false)',
|
||||
@@ -549,6 +595,15 @@ export class SearchFilesTool implements IMetonaTool {
|
||||
const fileGlob = args.file_glob as string | undefined;
|
||||
const limit = Math.min(200, Math.max(1, (args.limit as number) ?? 50));
|
||||
const contextLines = Math.min(5, Math.max(0, (args.context_lines as number) ?? 0));
|
||||
// v0.8.0 P1-3.5: 与 code_search 参数对称 —— case_sensitive 此前被硬编码
|
||||
// 'gi' 忽略；context_before/after 此前在 code_search JS 回退路径静默丢失。
|
||||
// 缺省时回退 context_lines（向后兼容）。
|
||||
const caseSensitive = (args.case_sensitive as boolean) ?? false;
|
||||
const contextBefore = Math.min(
|
||||
5,
|
||||
Math.max(0, (args.context_before as number) ?? contextLines),
|
||||
);
|
||||
const contextAfter = Math.min(5, Math.max(0, (args.context_after as number) ?? contextLines));
|
||||
const includeHidden = (args.include_hidden as boolean) ?? false;
|
||||
|
||||
if (target === 'files') {
|
||||
@@ -566,7 +621,9 @@ export class SearchFilesTool implements IMetonaTool {
|
||||
pattern,
|
||||
fileGlob,
|
||||
limit,
|
||||
contextLines,
|
||||
contextBefore,
|
||||
contextAfter,
|
||||
caseSensitive,
|
||||
includeHidden,
|
||||
context.workspacePath,
|
||||
);
|
||||
@@ -606,7 +663,9 @@ export class SearchFilesTool implements IMetonaTool {
|
||||
pattern: string,
|
||||
fileGlob: string | undefined,
|
||||
limit: number,
|
||||
contextLines: number,
|
||||
contextBefore: number,
|
||||
contextAfter: number,
|
||||
caseSensitive: boolean,
|
||||
includeHidden: boolean,
|
||||
workspacePath: string,
|
||||
): Promise<unknown> {
|
||||
@@ -635,7 +694,8 @@ export class SearchFilesTool implements IMetonaTool {
|
||||
}
|
||||
let regex: RegExp;
|
||||
try {
|
||||
regex = new RegExp(pattern, 'gi');
|
||||
// v0.8.0 P1-3.5: case_sensitive 参数生效（此前硬编码 'gi' 恒大小写不敏感）
|
||||
regex = new RegExp(pattern, caseSensitive ? 'g' : 'gi');
|
||||
} catch {
|
||||
return { results: [], count: 0, error: `Invalid regex pattern: ${pattern}`, success: false };
|
||||
}
|
||||
@@ -668,10 +728,11 @@ export class SearchFilesTool implements IMetonaTool {
|
||||
if (regex.test(lines[i])) {
|
||||
const match = lines[i].trim().slice(0, 200);
|
||||
// v0.3.2: context lines 支持
|
||||
// v0.8.0 P1-3.5: 前后文行数独立（code_search 对称性）
|
||||
let context: string[] | undefined;
|
||||
if (contextLines > 0) {
|
||||
const start = Math.max(0, i - contextLines);
|
||||
const end = Math.min(lines.length - 1, i + contextLines);
|
||||
if (contextBefore > 0 || contextAfter > 0) {
|
||||
const start = Math.max(0, i - contextBefore);
|
||||
const end = Math.min(lines.length - 1, i + contextAfter);
|
||||
context = lines.slice(start, end + 1);
|
||||
}
|
||||
results.push({
|
||||
|
||||
@@ -28,18 +28,23 @@ const MAX_DIFF_SIZE = 50 * 1024;
|
||||
*
|
||||
* v0.3.1 修复 WARN-4: 允许调用方覆盖 maxBuffer，默认 1MB；
|
||||
* git_diff 传 5MB 以支持超大变更集（避免 maxBuffer exceeded 报错而非截断返回）。
|
||||
*
|
||||
* v0.8.0 P1-2: 新增可选 signal —— 引擎中断（用户停止/超时）时立即 kill git
|
||||
* 子进程（Node execFile 原生支持 AbortSignal 选项），各工具经 context 透传。
|
||||
*/
|
||||
async function runGit(
|
||||
args: string[],
|
||||
cwd: string,
|
||||
timeout = 10_000,
|
||||
maxBuffer = 1024 * 1024, // 默认 1MB
|
||||
signal?: AbortSignal,
|
||||
): Promise<string> {
|
||||
const { stdout } = await execFileAsync('git', args, {
|
||||
cwd,
|
||||
maxBuffer,
|
||||
timeout,
|
||||
encoding: 'utf-8',
|
||||
...(signal ? { signal } : {}),
|
||||
});
|
||||
return stdout;
|
||||
}
|
||||
@@ -84,11 +89,15 @@ function extractRenamedFile(file: string): string {
|
||||
export class GitStatusTool implements IMetonaTool {
|
||||
readonly definition: MetonaToolDef = {
|
||||
name: 'git_status',
|
||||
description: 'Show the working tree status. Returns current branch, ahead/behind counts, and lists of staged, unstaged, and untracked files.',
|
||||
description:
|
||||
'Show the working tree status. Returns current branch, ahead/behind counts, and lists of staged, unstaged, and untracked files.',
|
||||
parameters: {
|
||||
type: 'object',
|
||||
properties: {
|
||||
pathspec: { type: 'string', description: 'Limit to a path scope, e.g. "src/" or "package.json"' },
|
||||
pathspec: {
|
||||
type: 'string',
|
||||
description: 'Limit to a path scope, e.g. "src/" or "package.json"',
|
||||
},
|
||||
},
|
||||
},
|
||||
category: MetonaToolCategory.FILESYSTEM,
|
||||
@@ -191,11 +200,15 @@ export class GitStatusTool implements IMetonaTool {
|
||||
export class GitDiffTool implements IMetonaTool {
|
||||
readonly definition: MetonaToolDef = {
|
||||
name: 'git_diff',
|
||||
description: 'Show changes between the working tree and the index (or staged changes). Returns unified diff text. Output is truncated at 50KB.',
|
||||
description:
|
||||
'Show changes between the working tree and the index (or staged changes). Returns unified diff text. Output is truncated at 50KB.',
|
||||
parameters: {
|
||||
type: 'object',
|
||||
properties: {
|
||||
cached: { type: 'boolean', description: 'Show only staged (cached) changes (default false)' },
|
||||
cached: {
|
||||
type: 'boolean',
|
||||
description: 'Show only staged (cached) changes (default false)',
|
||||
},
|
||||
pathspec: { type: 'string', description: 'Limit to a path scope, e.g. "src/"' },
|
||||
contextLines: { type: 'number', description: 'Number of context lines (default 3)' },
|
||||
},
|
||||
@@ -269,7 +282,8 @@ export class GitDiffTool implements IMetonaTool {
|
||||
export class GitLogTool implements IMetonaTool {
|
||||
readonly definition: MetonaToolDef = {
|
||||
name: 'git_log',
|
||||
description: 'Show commit history. Returns commits with hash, message, and optionally author/date. Supports filtering by author and path.',
|
||||
description:
|
||||
'Show commit history. Returns commits with hash, message, and optionally author/date. Supports filtering by author and path.',
|
||||
parameters: {
|
||||
type: 'object',
|
||||
properties: {
|
||||
@@ -357,17 +371,25 @@ export class GitLogTool implements IMetonaTool {
|
||||
export class GitCommitTool implements IMetonaTool {
|
||||
readonly definition: MetonaToolDef = {
|
||||
name: 'git_commit',
|
||||
description: 'Stage files and create a git commit. Supports amending the previous commit. In amend mode, message is optional (omitting it keeps the original commit message). Requires user confirmation.',
|
||||
description:
|
||||
'Stage files and create a git commit. Supports amending the previous commit. In amend mode, message is optional (omitting it keeps the original commit message). Requires user confirmation.',
|
||||
parameters: {
|
||||
type: 'object',
|
||||
properties: {
|
||||
message: { type: 'string', description: 'Commit message. Required for new commits. Optional in amend mode (omitting keeps original message).' },
|
||||
message: {
|
||||
type: 'string',
|
||||
description:
|
||||
'Commit message. Required for new commits. Optional in amend mode (omitting keeps original message).',
|
||||
},
|
||||
files: {
|
||||
type: 'array',
|
||||
items: { type: 'string', description: 'File path to stage' },
|
||||
description: 'Files to stage (default: all changes via git add -A)',
|
||||
},
|
||||
amend: { type: 'boolean', description: 'Amend the previous commit instead of creating a new one (default false)' },
|
||||
amend: {
|
||||
type: 'boolean',
|
||||
description: 'Amend the previous commit instead of creating a new one (default false)',
|
||||
},
|
||||
},
|
||||
// F1-3: message 不再硬性 required — amend 模式下可省略（保留原 message）
|
||||
// 校验在 execute 内根据 amend 标志动态进行
|
||||
@@ -385,11 +407,17 @@ export class GitCommitTool implements IMetonaTool {
|
||||
|
||||
// F1-3: 非 amend 模式必须有 message；amend 模式可省略（保留原 message）
|
||||
if (!amend && (!message || message.trim().length === 0)) {
|
||||
return { success: false, error: 'Commit message is required (use amend: true to reuse the previous message)' };
|
||||
return {
|
||||
success: false,
|
||||
error: 'Commit message is required (use amend: true to reuse the previous message)',
|
||||
};
|
||||
}
|
||||
// amend 模式下若提供 message，需校验非空字符串
|
||||
if (amend && message !== undefined && message.trim().length === 0) {
|
||||
return { success: false, error: 'Commit message must not be empty (or omit message field to keep original)' };
|
||||
return {
|
||||
success: false,
|
||||
error: 'Commit message must not be empty (or omit message field to keep original)',
|
||||
};
|
||||
}
|
||||
|
||||
try {
|
||||
@@ -402,7 +430,10 @@ export class GitCommitTool implements IMetonaTool {
|
||||
return {
|
||||
success: false,
|
||||
error: `File path outside workspace: ${f}`,
|
||||
commit: '', branch: '', message: '', filesChanged: 0,
|
||||
commit: '',
|
||||
branch: '',
|
||||
message: '',
|
||||
filesChanged: 0,
|
||||
};
|
||||
}
|
||||
}
|
||||
|
||||
@@ -82,7 +82,7 @@ export class HttpRequestTool implements IMetonaTool {
|
||||
timeoutMs: 30_000,
|
||||
};
|
||||
|
||||
async execute(args: Record<string, unknown>, _context: ToolExecutionContext): Promise<unknown> {
|
||||
async execute(args: Record<string, unknown>, context: ToolExecutionContext): Promise<unknown> {
|
||||
try {
|
||||
const url = args.url as string;
|
||||
const method = ((args.method as string) ?? 'GET').toUpperCase();
|
||||
@@ -127,7 +127,9 @@ export class HttpRequestTool implements IMetonaTool {
|
||||
|
||||
// v0.7.3 P2-1: pinned fetch —— 校验通过的 IP pin 到连接层，
|
||||
// 关闭校验-连接之间的 DNS rebinding 窗口
|
||||
const response = await ssrfPinnedFetch(url, fetchOptions, timeout);
|
||||
// v0.8.0 P1-2: 第 4 参透传引擎级 abort signal —— 用户中断会话时底层
|
||||
// fetch 立即取消（此前最长 60s 资源悬挂）
|
||||
const response = await ssrfPinnedFetch(url, fetchOptions, timeout, context.signal);
|
||||
const text = await response.text();
|
||||
|
||||
// 截断到 50KB
|
||||
|
||||
@@ -83,13 +83,23 @@ export async function fetchWithTimeout(
|
||||
url: string,
|
||||
options: RequestInit = {},
|
||||
timeoutMs = 20_000,
|
||||
externalSignal?: AbortSignal,
|
||||
): Promise<Response> {
|
||||
// v0.8.0 P1-2: 合并外部 abort 信号（引擎中断时立即取消，不再跑到自身超时）
|
||||
const controller = new AbortController();
|
||||
const onExternalAbort = (): void => controller.abort();
|
||||
if (externalSignal) {
|
||||
if (externalSignal.aborted) controller.abort();
|
||||
else externalSignal.addEventListener('abort', onExternalAbort, { once: true });
|
||||
}
|
||||
const timer = setTimeout(() => controller.abort(), timeoutMs);
|
||||
try {
|
||||
return await fetch(url, { ...options, signal: controller.signal });
|
||||
} finally {
|
||||
clearTimeout(timer);
|
||||
if (externalSignal) {
|
||||
externalSignal.removeEventListener('abort', onExternalAbort);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -17,6 +17,12 @@
|
||||
import { lookup } from 'node:dns/promises';
|
||||
import { isIP } from 'node:net';
|
||||
|
||||
/**
|
||||
* v0.8.0 P1-5: DNS lookup 可替换点 —— 生产恒为 node:dns/promises 的 lookup；
|
||||
* 测试通过替换 current 注入受控解析结果（ESM namespace 只读，无法直接打桩）。
|
||||
*/
|
||||
export const __dnsLookup: { current: typeof lookup } = { current: lookup };
|
||||
|
||||
/**
|
||||
* 检查 IP 是否为私有/内网/回环/元数据地址
|
||||
*
|
||||
@@ -98,7 +104,7 @@ export async function resolvePublicAddresses(url: string): Promise<string[]> {
|
||||
// 域名 — DNS 解析后检测所有 IP
|
||||
let addresses: Array<{ address: string }>;
|
||||
try {
|
||||
addresses = await lookup(hostname, { all: true });
|
||||
addresses = await __dnsLookup.current(hostname, { all: true });
|
||||
} catch (err) {
|
||||
throw new Error(
|
||||
`Blocked SSRF: DNS resolution failed for ${hostname}: ${(err as Error).message}`,
|
||||
@@ -231,3 +237,85 @@ export function assertSafeConfigTarget(url: string): void {
|
||||
}
|
||||
// 域名（非 IP）：允许（DNS 可能解析到内网，但用户显式配置的本地服务是合法场景）
|
||||
}
|
||||
|
||||
/**
|
||||
* v0.8.0 P1-5: 配置类 URL 的**深校验** —— 在 assertSafeConfigTarget 的静态规则
|
||||
* 之上对域名做真实 DNS 解析，任一解析结果命中高危段（链路本地/云元数据、0/8、
|
||||
* 组播保留、::ffff: 映射等价段）即拒绝。
|
||||
*
|
||||
* 与 assertSafeConfigTarget 的差异：后者对"域名放行"（不解析 DNS，本地实例
|
||||
* 域名合法）；本函数补上"域名解析到云元数据 IP"的绕过窗口
|
||||
* （如 attacker.example 解析到 169.254.169.254）。
|
||||
*
|
||||
* 放行语义不变：127.0.0.1 / RFC1918 私网（本地 MCP/SearXNG 合法）；DNS 解析
|
||||
* 失败也放行（配置期校验为纵深手段 —— 离线配置合法，且运行时工具路径仍有
|
||||
* 独立校验；失败仅 WARN 由调用方留痕）。
|
||||
*
|
||||
* @throws 如果 URL 解析结果指向高危目标或协议不被允许
|
||||
*/
|
||||
export async function assertSafeConfigTargetDeep(url: string): Promise<void> {
|
||||
// 先执行静态规则（协议白名单/元数据主机名/IP 字面量段位）
|
||||
assertSafeConfigTarget(url);
|
||||
|
||||
let parsed: URL;
|
||||
try {
|
||||
parsed = new URL(url);
|
||||
} catch {
|
||||
return; // assertSafeConfigTarget 已抛，此处不可达（防御）
|
||||
}
|
||||
const rawHostname = parsed.hostname.toLowerCase();
|
||||
// IPv6 字面量去方括号（与 assertSafeConfigTarget 同口径）
|
||||
const hostname =
|
||||
rawHostname.startsWith('[') && rawHostname.endsWith(']')
|
||||
? rawHostname.slice(1, -1)
|
||||
: rawHostname;
|
||||
if (isIP(hostname) !== 0) return; // IP 字面量已由静态规则判定，无需解析
|
||||
|
||||
let addresses: Array<{ address: string }>;
|
||||
try {
|
||||
addresses = await __dnsLookup.current(hostname, { all: true });
|
||||
} catch (err) {
|
||||
// DNS 解析失败：放行（配置期纵深校验不做可用性裁决），由调用方日志留痕
|
||||
throw new DeepCheckSoftFailure(
|
||||
`config target DNS resolution failed for ${hostname}: ${(err as Error).message}`,
|
||||
);
|
||||
}
|
||||
for (const { address } of addresses) {
|
||||
// 复用 isPrivateIP 的完整段位表做"高危段"判定？——不行：isPrivateIP 把
|
||||
// 回环/RFC1918 也判为私有，而配置路径放行它们。此处仅拦"静态规则拦不到、
|
||||
// 但解析后才暴露"的高危段：链路本地（含云元数据）、0/8、组播保留。
|
||||
if (isHighRiskResolvedIP(address)) {
|
||||
throw new Error(
|
||||
`Blocked: ${hostname} resolves to high-risk address ${address} (link-local/metadata/multicast)`,
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/** 高危段判定（仅配置深校验使用）：链路本地/0/8/组播保留，放行回环与 RFC1918 */
|
||||
function isHighRiskResolvedIP(ip: string): boolean {
|
||||
if (isIP(ip) === 4) {
|
||||
const parts = ip.split('.').map(Number);
|
||||
return (parts[0] === 169 && parts[1] === 254) || parts[0] === 0 || parts[0] >= 224;
|
||||
}
|
||||
if (isIP(ip) === 6) {
|
||||
const lower = ip.toLowerCase();
|
||||
if (lower.startsWith('fe80:') || lower.startsWith('ff')) return true;
|
||||
if (lower === '::') return true;
|
||||
const v4MappedMatch = lower.match(/::ffff:(\d+\.\d+\.\d+\.\d+)$/);
|
||||
if (v4MappedMatch) return isHighRiskResolvedIP(v4MappedMatch[1]);
|
||||
return false;
|
||||
}
|
||||
return false;
|
||||
}
|
||||
|
||||
/**
|
||||
* v0.8.0 P1-5: 深校验的"软失败"信号 —— DNS 解析失败不算配置错误（放行），
|
||||
* 但调用方需要区分"校验通过"与"跳过校验"以便日志留痕。
|
||||
*/
|
||||
export class DeepCheckSoftFailure extends Error {
|
||||
constructor(message: string) {
|
||||
super(message);
|
||||
this.name = 'DeepCheckSoftFailure';
|
||||
}
|
||||
}
|
||||
|
||||
@@ -84,7 +84,7 @@ export class WebFetchTool implements IMetonaTool {
|
||||
timeoutMs: 240_000,
|
||||
};
|
||||
|
||||
async execute(args: Record<string, unknown>, _context: ToolExecutionContext): Promise<unknown> {
|
||||
async execute(args: Record<string, unknown>, context: ToolExecutionContext): Promise<unknown> {
|
||||
const url = args.url as string;
|
||||
const mobileUA = (args.mobile_ua as boolean) ?? false;
|
||||
const enableRetry = (args.retry as boolean) ?? true;
|
||||
@@ -96,6 +96,11 @@ export class WebFetchTool implements IMetonaTool {
|
||||
return { url, content: '', success: false, error: 'URL must start with http:// or https://' };
|
||||
}
|
||||
|
||||
// v0.8.0 P1-2: abort 立即生效 —— 引擎中断（超时/用户停止）时不再继续后续阶段
|
||||
if (context.signal?.aborted) {
|
||||
return { url, content: '', success: false, error: 'Fetch aborted' };
|
||||
}
|
||||
|
||||
// v0.6.4 P2-2: SSRF 校验 —— 覆盖 Phase1 HTTP 与 Phase3 浏览器两条通道的入口。
|
||||
// 协议白名单 / 私有段 IP / 云元数据地址一律拒绝。
|
||||
try {
|
||||
@@ -117,7 +122,12 @@ export class WebFetchTool implements IMetonaTool {
|
||||
logTool('web_fetch', `Fetching: ${url}`);
|
||||
|
||||
// ===== Phase 1: HTTP 抓取 =====
|
||||
const phase1Result = await this.httpFetch(url, mobileUA, enableRetry);
|
||||
const phase1Result = await this.httpFetch(url, mobileUA, enableRetry, context.signal);
|
||||
|
||||
// v0.8.0 P1-2: HTTP 阶段被 abort —— 直接终止，不进浏览器回退
|
||||
if (context.signal?.aborted) {
|
||||
return { url, content: '', success: false, error: 'Fetch aborted' };
|
||||
}
|
||||
|
||||
if (phase1Result.success && !phase1Result.intercepted) {
|
||||
// 根据 extract_mode 选择返回内容：'html' 模式返回清理后的 HTML，'text' 模式返回纯文本
|
||||
@@ -136,7 +146,7 @@ export class WebFetchTool implements IMetonaTool {
|
||||
'web_fetch',
|
||||
`Phase 2: Content too short (${phase1Content.length} chars), upgrading to browser`,
|
||||
);
|
||||
const browserResult = await this.browserFetch(url);
|
||||
const browserResult = await this.browserFetch(url, context.signal);
|
||||
if (browserResult) {
|
||||
return this.buildSuccess(url, browserResult, 'browser', maxChars);
|
||||
}
|
||||
@@ -159,7 +169,7 @@ export class WebFetchTool implements IMetonaTool {
|
||||
};
|
||||
}
|
||||
logTool('web_fetch', `Phase 3: Falling back to browser (${phase1Result.reason})`);
|
||||
const browserResult = await this.browserFetch(url);
|
||||
const browserResult = await this.browserFetch(url, context.signal);
|
||||
if (browserResult) {
|
||||
return this.buildSuccess(url, browserResult, 'browser', maxChars);
|
||||
}
|
||||
@@ -179,6 +189,7 @@ export class WebFetchTool implements IMetonaTool {
|
||||
url: string,
|
||||
mobileUA: boolean,
|
||||
enableRetry: boolean,
|
||||
signal?: AbortSignal,
|
||||
): Promise<{
|
||||
success: boolean;
|
||||
html: string;
|
||||
@@ -206,7 +217,14 @@ export class WebFetchTool implements IMetonaTool {
|
||||
let redirectBlocked: string | null = null;
|
||||
|
||||
for (let hop = 0; hop <= MAX_REDIRECT_HOPS; hop++) {
|
||||
response = await ssrfPinnedFetch(currentUrl, { headers, redirect: 'manual' }, 20_000);
|
||||
// v0.8.0 P1-2: 每跳透传引擎级 abort signal —— 用户中断时底层 fetch
|
||||
// 立即取消（含重定向链中间跳）
|
||||
response = await ssrfPinnedFetch(
|
||||
currentUrl,
|
||||
{ headers, redirect: 'manual' },
|
||||
20_000,
|
||||
signal,
|
||||
);
|
||||
const next = resolveRedirectTarget(response, currentUrl);
|
||||
if (next === null) break; // 非重定向（或无/非法 Location）—— 当前响应即终态
|
||||
if (hop === MAX_REDIRECT_HOPS) {
|
||||
@@ -261,6 +279,7 @@ export class WebFetchTool implements IMetonaTool {
|
||||
if (response.status >= 500 && attempt < maxRetries - 1) {
|
||||
await this.sleep(
|
||||
backoffBase * Math.pow(2, attempt) + Math.random() * backoffBase * 0.6,
|
||||
signal,
|
||||
);
|
||||
continue;
|
||||
}
|
||||
@@ -293,9 +312,22 @@ export class WebFetchTool implements IMetonaTool {
|
||||
return { success: true, html, text, intercepted: false, reason: '' };
|
||||
} catch (err) {
|
||||
const errorMsg = (err as Error).message;
|
||||
// v0.8.0 P1-2: abort 语义 —— 不重试、不睡眠，直接终止本阶段
|
||||
if (signal?.aborted || (err as Error & { name?: string }).name === 'AbortError') {
|
||||
return {
|
||||
success: false,
|
||||
html: '',
|
||||
text: '',
|
||||
intercepted: false,
|
||||
reason: 'Fetch aborted',
|
||||
};
|
||||
}
|
||||
if (attempt < maxRetries - 1) {
|
||||
logTool('web_fetch', `Attempt ${attempt + 1} failed: ${errorMsg}, retrying...`);
|
||||
await this.sleep(backoffBase * Math.pow(2, attempt) + Math.random() * backoffBase * 0.6);
|
||||
await this.sleep(
|
||||
backoffBase * Math.pow(2, attempt) + Math.random() * backoffBase * 0.6,
|
||||
signal,
|
||||
);
|
||||
continue;
|
||||
}
|
||||
return { success: false, html: '', text: '', intercepted: false, reason: errorMsg };
|
||||
@@ -313,7 +345,7 @@ export class WebFetchTool implements IMetonaTool {
|
||||
|
||||
// ===== Phase 2/3: 浏览器回退（使用共享 BrowserWindowManager 单例） =====
|
||||
|
||||
private async browserFetch(url: string): Promise<string | null> {
|
||||
private async browserFetch(url: string, signal?: AbortSignal): Promise<string | null> {
|
||||
// 查缓存（浏览器阶段产出的是纯文本，与 text 模式同键）
|
||||
const cached = fetchCache.get(`text:${url}`);
|
||||
if (cached) {
|
||||
@@ -322,10 +354,13 @@ export class WebFetchTool implements IMetonaTool {
|
||||
}
|
||||
|
||||
try {
|
||||
// v0.8.0 P1-2: 引擎级 abort 透传 —— 中断时 BrowserWindowManager 停止页面
|
||||
// 加载并终止抓取序列（此前浏览器回退完全不受 abort 控制）
|
||||
if (signal?.aborted) return null;
|
||||
// 崩溃修复: 走 manager.fetchPageText（内部串行化完整的 open→等待→evaluate 序列）。
|
||||
// 原实现直接 open/evaluate 共享单例 —— web_search 并行抓取触发多个回退同时进入时，
|
||||
// 后到者销毁前者的窗口（ERR_ABORTED ×3 = 应用崩溃 ×3，见 manager 注释）。
|
||||
const text = await getBrowserManager().fetchPageText(url);
|
||||
const text = await getBrowserManager().fetchPageText(url, signal);
|
||||
|
||||
if (text && text.trim().length >= 80) {
|
||||
// 拦截检测（浏览器渲染后仍可能是验证码挑战页）
|
||||
@@ -383,7 +418,23 @@ export class WebFetchTool implements IMetonaTool {
|
||||
};
|
||||
}
|
||||
|
||||
private sleep(ms: number): Promise<void> {
|
||||
return new Promise((resolve) => setTimeout(resolve, ms));
|
||||
/** v0.8.0 P1-2: abort 感知的 sleep —— 中断期间不再等待退避间隔 */
|
||||
private sleep(ms: number, signal?: AbortSignal): Promise<void> {
|
||||
return new Promise((resolve) => {
|
||||
if (signal?.aborted) return resolve();
|
||||
const cleanup = (): void => {
|
||||
clearTimeout(timer);
|
||||
signal?.removeEventListener('abort', onAbort);
|
||||
};
|
||||
const onAbort = (): void => {
|
||||
cleanup();
|
||||
resolve();
|
||||
};
|
||||
const timer = setTimeout(() => {
|
||||
cleanup();
|
||||
resolve();
|
||||
}, ms);
|
||||
signal?.addEventListener('abort', onAbort, { once: true });
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
@@ -338,9 +338,15 @@ function parse360Regex(html: string): SearchResult[] {
|
||||
// 探测经 ssrfPinnedFetch（DNS pinning），重定向不自动跟随（3xx 即视为可达 ——
|
||||
// 链接活性已证明，且跟跳目标不再绕过校验）。
|
||||
|
||||
async function checkReachability(urls: string[], concurrency = 5): Promise<Map<string, boolean>> {
|
||||
async function checkReachability(
|
||||
urls: string[],
|
||||
signal?: AbortSignal,
|
||||
concurrency = 5,
|
||||
): Promise<Map<string, boolean>> {
|
||||
const result = new Map<string, boolean>();
|
||||
for (let i = 0; i < urls.length; i += concurrency) {
|
||||
// v0.8.0 P1-2: abort 后立即终止预检批次
|
||||
if (signal?.aborted) break;
|
||||
const batch = urls.slice(i, i + concurrency);
|
||||
const checks = batch.map(async (url) => {
|
||||
try {
|
||||
@@ -349,7 +355,13 @@ async function checkReachability(urls: string[], concurrency = 5): Promise<Map<s
|
||||
result.set(url, false);
|
||||
return;
|
||||
}
|
||||
const resp = await ssrfPinnedFetch(url, { method: 'HEAD', redirect: 'manual' }, 3_000);
|
||||
// v0.8.0 P1-2: 透传引擎级 abort signal
|
||||
const resp = await ssrfPinnedFetch(
|
||||
url,
|
||||
{ method: 'HEAD', redirect: 'manual' },
|
||||
3_000,
|
||||
signal,
|
||||
);
|
||||
result.set(url, resp.ok || (resp.status >= 300 && resp.status < 400));
|
||||
} catch {
|
||||
result.set(url, false);
|
||||
@@ -424,9 +436,14 @@ export class WebSearchTool implements IMetonaTool {
|
||||
private webFetchTool: WebFetchTool,
|
||||
) {}
|
||||
|
||||
async execute(args: Record<string, unknown>, _context: ToolExecutionContext): Promise<unknown> {
|
||||
async execute(args: Record<string, unknown>, context: ToolExecutionContext): Promise<unknown> {
|
||||
const query = args.query as string;
|
||||
|
||||
// v0.8.0 P1-2: abort 立即生效（后续各阶段均携带本 signal）
|
||||
if (context.signal?.aborted) {
|
||||
return { success: false, query, results: [], error: 'Search aborted' };
|
||||
}
|
||||
|
||||
// 读取 SearXNG 配置
|
||||
const searxngConfig = this.readSearXNGConfig();
|
||||
const useSearXNG = searxngConfig.enabled && !!searxngConfig.url;
|
||||
@@ -463,12 +480,23 @@ export class WebSearchTool implements IMetonaTool {
|
||||
let engineStats: Record<string, string>;
|
||||
|
||||
if (useSearXNG) {
|
||||
const searxResult = await this.searchSearXNG(query, searxngConfig, maxResults, timeRange);
|
||||
const searxResult = await this.searchSearXNG(
|
||||
query,
|
||||
searxngConfig,
|
||||
maxResults,
|
||||
timeRange,
|
||||
context.signal,
|
||||
);
|
||||
results = searxResult.results;
|
||||
mode = 'searxng';
|
||||
engineStats = searxResult.engineStats;
|
||||
} else {
|
||||
const builtinResult = await this.searchBuiltinEngines(query, maxResults, timeRange);
|
||||
const builtinResult = await this.searchBuiltinEngines(
|
||||
query,
|
||||
maxResults,
|
||||
timeRange,
|
||||
context.signal,
|
||||
);
|
||||
results = builtinResult.results;
|
||||
mode = 'builtin';
|
||||
engineStats = builtinResult.engineStats;
|
||||
@@ -479,7 +507,7 @@ export class WebSearchTool implements IMetonaTool {
|
||||
|
||||
// 可达性预检
|
||||
const topUrls = deduped.slice(0, Math.min(20, deduped.length)).map((r) => r.url);
|
||||
const reachabilityMap = await checkReachability(topUrls);
|
||||
const reachabilityMap = await checkReachability(topUrls, context.signal);
|
||||
for (const r of deduped) {
|
||||
r.reachable = reachabilityMap.get(r.url) ?? false;
|
||||
}
|
||||
@@ -489,11 +517,17 @@ export class WebSearchTool implements IMetonaTool {
|
||||
|
||||
// 摘要增强
|
||||
if (enhanceSnippets) {
|
||||
await this.enhanceSnippets(sorted, 3);
|
||||
await this.enhanceSnippets(sorted, 3, context);
|
||||
}
|
||||
|
||||
// 自动抓取完整内容
|
||||
const fetchedContent = await this.autoFetch(query, sorted, searxngConfig.fetch_mode, fetchTop);
|
||||
const fetchedContent = await this.autoFetch(
|
||||
query,
|
||||
sorted,
|
||||
searxngConfig.fetch_mode,
|
||||
fetchTop,
|
||||
context,
|
||||
);
|
||||
|
||||
// 格式化输出
|
||||
const formatted = this.formatResults(query, sorted);
|
||||
@@ -536,6 +570,7 @@ export class WebSearchTool implements IMetonaTool {
|
||||
config: SearXNGConfig,
|
||||
maxResults: number,
|
||||
timeRange: string,
|
||||
signal?: AbortSignal,
|
||||
): Promise<{ results: SearchResult[]; engineStats: Record<string, string> }> {
|
||||
const results: SearchResult[] = [];
|
||||
const engineStats: Record<string, string> = {};
|
||||
@@ -549,6 +584,8 @@ export class WebSearchTool implements IMetonaTool {
|
||||
let page = 1;
|
||||
|
||||
while (results.length < maxResults && page <= maxPages) {
|
||||
// v0.8.0 P1-2: abort 后停止翻页
|
||||
if (signal?.aborted) break;
|
||||
const params = new URLSearchParams();
|
||||
params.set('q', query);
|
||||
params.set('format', config.format || 'json');
|
||||
@@ -564,7 +601,8 @@ export class WebSearchTool implements IMetonaTool {
|
||||
const pageResults: SearchResult[] = [];
|
||||
|
||||
try {
|
||||
const response = await fetchWithTimeout(searchUrl, { headers }, 15_000);
|
||||
// v0.8.0 P1-2: SearXNG 请求携带引擎级 abort signal
|
||||
const response = await fetchWithTimeout(searchUrl, { headers }, 15_000, signal);
|
||||
if (!response.ok) {
|
||||
throw new Error(`SearXNG API error: ${response.status} ${response.statusText}`);
|
||||
}
|
||||
@@ -625,6 +663,7 @@ export class WebSearchTool implements IMetonaTool {
|
||||
query: string,
|
||||
maxResults: number,
|
||||
timeRange: string,
|
||||
signal?: AbortSignal,
|
||||
): Promise<{ results: SearchResult[]; engineStats: Record<string, string> }> {
|
||||
const searchPromises = ENGINES.map(async (engine) => {
|
||||
try {
|
||||
@@ -639,6 +678,7 @@ export class WebSearchTool implements IMetonaTool {
|
||||
},
|
||||
},
|
||||
8_000,
|
||||
signal,
|
||||
);
|
||||
|
||||
if (!response.ok) {
|
||||
@@ -689,16 +729,23 @@ export class WebSearchTool implements IMetonaTool {
|
||||
|
||||
// ===== 摘要增强（委托给 WebFetchTool） =====
|
||||
|
||||
private async enhanceSnippets(results: SearchResult[], maxEnhance: number): Promise<void> {
|
||||
private async enhanceSnippets(
|
||||
results: SearchResult[],
|
||||
maxEnhance: number,
|
||||
context: ToolExecutionContext,
|
||||
): Promise<void> {
|
||||
let enhanced = 0;
|
||||
for (const r of results) {
|
||||
// v0.8.0 P1-2: abort 后停止增强
|
||||
if (context.signal?.aborted) break;
|
||||
if (enhanced >= maxEnhance) break;
|
||||
if (r.snippet.length < 30 && r.reachable) {
|
||||
try {
|
||||
const fetchResult = (await this.webFetchTool.execute(
|
||||
{ url: r.url },
|
||||
{ sessionId: '', workspacePath: '', iteration: 0, requestId: '' },
|
||||
)) as { success: boolean; content?: string };
|
||||
// v0.8.0 P1-2: 透传真实执行上下文（signal）—— 移除"伪造空上下文"
|
||||
const fetchResult = (await this.webFetchTool.execute({ url: r.url }, context)) as {
|
||||
success: boolean;
|
||||
content?: string;
|
||||
};
|
||||
|
||||
if (fetchResult.success && fetchResult.content) {
|
||||
const text = fetchResult.content.slice(0, 200);
|
||||
@@ -729,13 +776,21 @@ export class WebSearchTool implements IMetonaTool {
|
||||
results: SearchResult[],
|
||||
fetchMode: string,
|
||||
fetchTop: number,
|
||||
context: ToolExecutionContext,
|
||||
): Promise<Array<{ url: string; title: string; content: string }>> {
|
||||
// v0.8.0 P1-2 根治: 时间预算收敛 —— 旧实现最坏耗时（8 条 × 3 并发 × 单次
|
||||
// web_fetch 240s ≈ 720s）远超工具自身 300s 超时，registry 层超时后整次调用
|
||||
// 作废（已抓取内容全部丢弃）。现以 deadline 为界：剩余预算不足一次最小
|
||||
// 抓取（30s）即停，已抓取内容照常返回。
|
||||
const BUDGET_RATIO = 0.8;
|
||||
const MIN_FETCH_BUDGET_MS = 30_000;
|
||||
const deadlineMs = Date.now() + 300_000 * BUDGET_RATIO;
|
||||
|
||||
// 相关性评分（不过滤，relevance=0 的结果也参与抓取候选）
|
||||
const withRelevance = results.map((r) => ({
|
||||
const filtered = results.map((r) => ({
|
||||
result: r,
|
||||
relevance: computeRelevance(query, r),
|
||||
}));
|
||||
const filtered = withRelevance.length > 0 ? withRelevance : [];
|
||||
|
||||
// 确定抓取数量：fetchTop 已在 execute() 中综合了配置面板和工具参数
|
||||
const topN = Math.min(fetchTop, 8, filtered.length);
|
||||
@@ -761,9 +816,10 @@ export class WebSearchTool implements IMetonaTool {
|
||||
}): Promise<{ url: string; title: string; content: string } | null> => {
|
||||
try {
|
||||
// 委托给 WebFetchTool — 享受三阶段回退策略（HTTP + 反爬 + 浏览器渲染）
|
||||
// v0.8.0 P1-2: 透传真实执行上下文（signal）—— 移除"伪造空上下文"
|
||||
const fetchResult = (await this.webFetchTool.execute(
|
||||
{ url: item.result.url },
|
||||
{ sessionId: '', workspacePath: '', iteration: 0, requestId: '' },
|
||||
context,
|
||||
)) as { success: boolean; content?: string };
|
||||
|
||||
if (fetchResult.success && fetchResult.content) {
|
||||
@@ -779,9 +835,18 @@ export class WebSearchTool implements IMetonaTool {
|
||||
}
|
||||
};
|
||||
|
||||
// 并行批次抓取（并发 3）
|
||||
// 并行批次抓取（并发 3，时间预算收敛）
|
||||
const CONCURRENCY = 3;
|
||||
for (let i = 0; i < toFetch.length; i += CONCURRENCY) {
|
||||
// v0.8.0 P1-2: 剩余预算不足一次最小抓取 → 停止，保留已抓取内容
|
||||
const remaining = deadlineMs - Date.now();
|
||||
if (context.signal?.aborted || remaining < MIN_FETCH_BUDGET_MS) {
|
||||
logTool(
|
||||
'web_search',
|
||||
`Auto-fetch budget stop: fetched=${fetched.length}, remaining=${Math.max(0, remaining)}ms, aborted=${!!context.signal?.aborted}`,
|
||||
);
|
||||
break;
|
||||
}
|
||||
const batch = toFetch.slice(i, i + CONCURRENCY);
|
||||
const settled = await Promise.allSettled(batch.map((item) => fetchOne(item)));
|
||||
for (const r of settled) {
|
||||
|
||||
@@ -144,6 +144,18 @@ export interface MetonaStreamEvent {
|
||||
|
||||
/** DONE — 终止原因（前端可据此区分正常完成/错误/中断） */
|
||||
terminationReason?: string;
|
||||
|
||||
/**
|
||||
* DONE — Provider 原生停止原因（v0.8.0 P0-1 finish_reason 全链路贯通）。
|
||||
*
|
||||
* 取值域为归一化后的 OpenAI 语义：'stop' | 'length' | 'tool_calls' |
|
||||
* 'content_filter'（Anthropic max_tokens→length、refusal→content_filter；
|
||||
* Ollama done_reason 同映射；MiMo repetition_truncation→stop）。
|
||||
* adapter 在流结束（真实 [DONE]/message_stop/done:true 或断流合成）时携带；
|
||||
* 引擎转发到最终 DONE 事件，前端据此展示截断/过滤提示；TRACE 层记录真值
|
||||
* （v0.7.4 及之前硬编码 'stop'，length 截断在录制文件中不可归因）。
|
||||
*/
|
||||
finishReason?: string;
|
||||
}
|
||||
|
||||
/** v0.4.1: 输出验证事件载荷 — OutputValidator 检出的疑似问题（幻觉/事实矛盾/敏感信息/格式） */
|
||||
|
||||
Reference in New Issue
Block a user