fix: v0.5.3 模型能力完整性修复 — MCP 工具动态同步 + maxTokens 模型上限钳制
背景:v0.5.2 工具调用失效修复后,对模型全能力矩阵(工具/思考/多模态/流式/ 压缩/摘要/记忆/故障转移/余额)做契约级核查,发现并修复两处同类时序/边界缺陷。 P1 MCP 工具运行中增删不同步引擎: - 症状:运行中添加/启用 MCP server 后,已打开会话拿不到新工具;断开 server 后已有引擎仍持有失效工具定义(模型发起调用才报 Unknown tool) - 根因:setToolsAll 仅在启动期与工具开关时调用,MCP 连接/断开路径缺失 (与 v0.5.2 修复的懒创建陷阱同类——"变更点 × 同步路径"未全覆盖) - 修复:MCPManager 新增 setOnToolsChanged 回调,connectServer 注册完成 / disconnectServer 注销完成后触发;main.ts 注入回调同步全部已存在引擎。 懒创建引擎由 createEngine 实时拉取(v0.5.2),三条路径(启动/懒创建/ 运行中变更)全覆盖。README"无需重启动态发现"的宣称至此真实成立。 P1 maxTokens 超模型上限直接 400: - 症状:引擎默认 maxTokens=63488,OpenAI gpt-4o(16384)/gpt-4.1(32768)、 Anthropic opus/haiku(32000)、MiMo standard(32768) 每次请求 400,等于不可用 - 修复:五个 adapter(DeepSeek/Agnes/MiMo/OpenAI/Anthropic)统一按 MODEL_INFO.maxOutputTokens 钳制;MiMo 保留 thinking 兜底 32768 语义; Anthropic thinking budget 在钳制后的 max_tokens 内二分,自动跟随 测试(224 → 236 用例): - 新增 maxTokens 钳制契约测试 ×9(max-tokens-clamp.test.ts):mock fetch 记录真实请求体断言——超限钳制(MiMo standard/OpenAI gpt-4o/Anthropic opus)/ 未超限原样传递(DeepSeek/Agnes/MiMo pro/o3-mini/sonnet)/ 推理模型字段名 / 未配置默认值安全性 - 新增 MCP 动态同步端到端测试 ×3(mcp-tools-sync.test.ts):mock MCP SDK + 真实 MCPManager/ToolRegistry/AgentEngineManager——先建引擎再连 server,断言同一会话请求的 tools 动态更新 / 断开后移除失效定义 / 回调异常不阻断 MCP 主流程 能力矩阵核查结论(无回归确认): 工具调用主链路 ✓(v0.5.2)/ SubAgent 工具 ✓(delegate 实时 resolveTools)/ thinking 热更新 ✓(baseConfig 合并 路径无懒创建陷阱)/ 多模态当轮 ✓ / 压缩与孤立 tool 消息配对 ✓ / 摘要分层 ✓ / 记忆注入 ✓ / 故障转移 ✓ / 余额 ✓(v0.5.2)。已知设计限制:历史轮图片不 回传(attachments 仅存缩略图,图片只在发送当轮注入上下文)。 验证: lint 0 / typecheck 双工程 0 / test:electron 236 全过 / build 成功
This commit is contained in:
@@ -69,21 +69,25 @@ export class OpenAIAdapter extends BaseAdapter {
|
||||
async send(request: MetonaRequest): Promise<MetonaResponse> {
|
||||
const body = this.toNativeRequest(request, false);
|
||||
|
||||
const response = await this.fetchWithTimeout(`${this.config.baseURL}/chat/completions`, {
|
||||
method: 'POST',
|
||||
headers: {
|
||||
'Content-Type': 'application/json',
|
||||
Authorization: `Bearer ${this.config.apiKey}`,
|
||||
...this.config.headers,
|
||||
const response = await this.fetchWithTimeout(
|
||||
`${this.config.baseURL}/chat/completions`,
|
||||
{
|
||||
method: 'POST',
|
||||
headers: {
|
||||
'Content-Type': 'application/json',
|
||||
Authorization: `Bearer ${this.config.apiKey}`,
|
||||
...this.config.headers,
|
||||
},
|
||||
body: JSON.stringify(body),
|
||||
},
|
||||
body: JSON.stringify(body),
|
||||
}, this.config.timeoutMs ?? 120_000);
|
||||
this.config.timeoutMs ?? 120_000,
|
||||
);
|
||||
|
||||
if (!response.ok) {
|
||||
await this.throwHttpError(response, 'OpenAI API error');
|
||||
}
|
||||
|
||||
const data = await response.json() as Record<string, unknown>;
|
||||
const data = (await response.json()) as Record<string, unknown>;
|
||||
const parsed = parseOpenAICompatibleResponse(data);
|
||||
|
||||
return {
|
||||
@@ -107,15 +111,19 @@ export class OpenAIAdapter extends BaseAdapter {
|
||||
async *sendStream(request: MetonaRequest): AsyncIterable<MetonaStreamEvent> {
|
||||
const body = this.toNativeRequest(request, true);
|
||||
|
||||
const response = await this.fetchWithTimeout(`${this.config.baseURL}/chat/completions`, {
|
||||
method: 'POST',
|
||||
headers: {
|
||||
'Content-Type': 'application/json',
|
||||
Authorization: `Bearer ${this.config.apiKey}`,
|
||||
...this.config.headers,
|
||||
const response = await this.fetchWithTimeout(
|
||||
`${this.config.baseURL}/chat/completions`,
|
||||
{
|
||||
method: 'POST',
|
||||
headers: {
|
||||
'Content-Type': 'application/json',
|
||||
Authorization: `Bearer ${this.config.apiKey}`,
|
||||
...this.config.headers,
|
||||
},
|
||||
body: JSON.stringify(body),
|
||||
},
|
||||
body: JSON.stringify(body),
|
||||
}, this.config.timeoutMs ?? 300_000);
|
||||
this.config.timeoutMs ?? 300_000,
|
||||
);
|
||||
|
||||
if (!response.ok || !response.body) {
|
||||
await this.throwHttpError(response, 'OpenAI stream error');
|
||||
@@ -139,7 +147,7 @@ export class OpenAIAdapter extends BaseAdapter {
|
||||
signal: AbortSignal.timeout(10_000),
|
||||
});
|
||||
if (response.ok) {
|
||||
const data = await response.json() as { data?: Array<{ id: string }> };
|
||||
const data = (await response.json()) as { data?: Array<{ id: string }> };
|
||||
if (data.data?.length) {
|
||||
return data.data.map((m) => OpenAIAdapter.MODEL_INFO[m.id] ?? { id: m.id });
|
||||
}
|
||||
@@ -208,15 +216,19 @@ export class OpenAIAdapter extends BaseAdapter {
|
||||
};
|
||||
|
||||
// Token 上限参数:o 系列/gpt-5 使用 max_completion_tokens
|
||||
if (request.params.maxTokens) {
|
||||
// v0.5.3: 按模型上限钳制(gpt-4o 16384 / gpt-4.1 32768 / o3-mini 100000)—
|
||||
// 引擎默认 63488 超过 gpt-4o/gpt-4.1 上限时 API 直接 400
|
||||
const oaMaxOutput = OpenAIAdapter.MODEL_INFO[model]?.maxOutputTokens ?? 128_000;
|
||||
const oaMaxTokens = Math.min(
|
||||
request.params.maxTokens ?? (isReasoningModel ? 32_768 : oaMaxOutput),
|
||||
oaMaxOutput,
|
||||
);
|
||||
if (oaMaxTokens) {
|
||||
if (isReasoningModel) {
|
||||
body.max_completion_tokens = request.params.maxTokens;
|
||||
body.max_completion_tokens = oaMaxTokens;
|
||||
} else {
|
||||
body.max_tokens = request.params.maxTokens;
|
||||
body.max_tokens = oaMaxTokens;
|
||||
}
|
||||
} else if (isReasoningModel) {
|
||||
// 推理模型未配置时使用兜底值(thinking 占用 token 配额,默认值过小会被截断)
|
||||
body.max_completion_tokens = 32_768;
|
||||
}
|
||||
|
||||
if (stream) {
|
||||
@@ -229,7 +241,12 @@ export class OpenAIAdapter extends BaseAdapter {
|
||||
|
||||
// Thinking 模式:推理模型映射 reasoning_effort;非推理模型忽略
|
||||
if (request.params.thinkingEnabled && isReasoningModel) {
|
||||
const effortMap: Record<string, string> = { low: 'low', medium: 'medium', high: 'high', max: 'high' };
|
||||
const effortMap: Record<string, string> = {
|
||||
low: 'low',
|
||||
medium: 'medium',
|
||||
high: 'high',
|
||||
max: 'high',
|
||||
};
|
||||
body.reasoning_effort = effortMap[request.params.thinkingEffort ?? 'high'] ?? 'high';
|
||||
} else if (!isReasoningModel) {
|
||||
// 非推理模型使用温度控制
|
||||
|
||||
Reference in New Issue
Block a user