feat: LLM intent router, direct chat execution, and Memory V2 light intervention
Wire chat intent routing with direct_chat on regular sessions, skill-selected short-circuit to Agent, memory light/heavy intervention tiers, and fix direct chat UI stuck streaming after completion. Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
+132
-23
@@ -1,4 +1,5 @@
|
||||
import crypto from 'node:crypto';
|
||||
import { MEMORY_INTERVENTION_LIMIT } from './memory-intervention.mjs';
|
||||
|
||||
export const DIRECT_CHAT_SESSION_PREFIX = 'h5direct_';
|
||||
|
||||
@@ -117,11 +118,22 @@ function renderMemoryLines(memories) {
|
||||
].join('\n');
|
||||
}
|
||||
|
||||
function buildModelMessages({ previousMessages, userMessage, memories }) {
|
||||
function buildMemorySystemBlock({ memories, routingMemoryContent } = {}) {
|
||||
const routed = String(routingMemoryContent ?? '').trim();
|
||||
if (routed) {
|
||||
return [
|
||||
'以下是当前用户的长期记忆,只用于改善回答,不要主动暴露记忆来源:',
|
||||
routed,
|
||||
].join('\n');
|
||||
}
|
||||
return renderMemoryLines(memories);
|
||||
}
|
||||
|
||||
function buildModelMessages({ previousMessages, userMessage, memories, routingMemoryContent }) {
|
||||
const system = [
|
||||
'你是 TKMind H5 聊天助手。',
|
||||
'优先直接回答用户问题;不要调用工具;涉及需要执行代码、改文件、生成页面或操作外部系统的任务时,简要说明已交由后台任务处理或请用户确认具体任务。',
|
||||
renderMemoryLines(memories),
|
||||
buildMemorySystemBlock({ memories, routingMemoryContent }),
|
||||
].filter(Boolean).join('\n\n');
|
||||
|
||||
const history = Array.isArray(previousMessages) ? previousMessages.slice(-12) : [];
|
||||
@@ -146,10 +158,56 @@ function buildAssistantMessage(reply, { requestId, now }) {
|
||||
metadata: {
|
||||
userVisible: true,
|
||||
source: 'portal-direct-chat',
|
||||
chatRequestId: requestId || undefined,
|
||||
},
|
||||
};
|
||||
}
|
||||
|
||||
function evaluateCanHandle({
|
||||
sessionId = null,
|
||||
toolMode = 'chat',
|
||||
userMessage,
|
||||
routingDecision = null,
|
||||
enabled: enabledOverride,
|
||||
userAuth,
|
||||
llmProviderService,
|
||||
sessionSnapshotService,
|
||||
} = {}) {
|
||||
const resolvedEnabled = enabledOverride ?? true;
|
||||
if (!resolvedEnabled) return { ok: false, reason: 'disabled' };
|
||||
if (toolMode !== 'chat') return { ok: false, reason: 'tool_mode_not_chat' };
|
||||
if (routingDecision === 'agent_orchestration') {
|
||||
return { ok: false, reason: 'routing_agent_orchestration' };
|
||||
}
|
||||
if (
|
||||
sessionId &&
|
||||
!isDirectChatSessionId(sessionId) &&
|
||||
routingDecision !== 'direct_chat'
|
||||
) {
|
||||
return { ok: false, reason: 'session_not_direct_chat' };
|
||||
}
|
||||
if (!isTextOnlyUserMessage(userMessage)) {
|
||||
return { ok: false, reason: 'non_text_message' };
|
||||
}
|
||||
if (routingDecision !== 'direct_chat' && requiresTaskExecution(userMessage)) {
|
||||
return { ok: false, reason: 'task_execution_required' };
|
||||
}
|
||||
if (!userAuth || !llmProviderService || !sessionSnapshotService) {
|
||||
return { ok: false, reason: 'dependencies_unavailable' };
|
||||
}
|
||||
return { ok: true, reason: null };
|
||||
}
|
||||
|
||||
export function isPortalDirectChatSnapshot(snapshot) {
|
||||
const messages = Array.isArray(snapshot?.messages) ? snapshot.messages : [];
|
||||
const lastAssistant = [...messages].reverse().find((message) => message?.role === 'assistant');
|
||||
if (lastAssistant?.metadata?.source !== 'portal-direct-chat') return false;
|
||||
const updatedAtRaw = snapshot?.session?.updated_at ?? snapshot?.meta?.saved_at ?? 0;
|
||||
const updatedAt = Date.parse(String(updatedAtRaw)) || Number(updatedAtRaw) || 0;
|
||||
if (!updatedAt) return true;
|
||||
return Date.now() - updatedAt <= 5 * 60 * 1000;
|
||||
}
|
||||
|
||||
function normalizeUsageForBilling(usage, previousState) {
|
||||
if (!usage) return null;
|
||||
const input = Math.max(0, Number(usage.inputTokens ?? 0) || 0);
|
||||
@@ -167,7 +225,7 @@ export function createDirectChatService({
|
||||
sessionSnapshotService,
|
||||
memoryV2 = null,
|
||||
conversationMemoryService = null,
|
||||
enabled = envFlag(process.env.MEMIND_DIRECT_CHAT_ENABLED, false),
|
||||
enabled = envFlag(process.env.MEMIND_DIRECT_CHAT_ENABLED, true),
|
||||
} = {}) {
|
||||
function getStatus() {
|
||||
return {
|
||||
@@ -176,29 +234,48 @@ export function createDirectChatService({
|
||||
};
|
||||
}
|
||||
|
||||
function canHandle({ sessionId = null, toolMode = 'chat', userMessage } = {}) {
|
||||
if (!enabled) return false;
|
||||
if (toolMode !== 'chat') return false;
|
||||
if (sessionId && !isDirectChatSessionId(sessionId)) return false;
|
||||
if (!isTextOnlyUserMessage(userMessage)) return false;
|
||||
if (requiresTaskExecution(userMessage)) return false;
|
||||
return Boolean(userAuth && llmProviderService && sessionSnapshotService);
|
||||
function canHandle(input = {}) {
|
||||
return evaluateCanHandle({
|
||||
...input,
|
||||
enabled,
|
||||
userAuth,
|
||||
llmProviderService,
|
||||
sessionSnapshotService,
|
||||
}).ok;
|
||||
}
|
||||
|
||||
async function resolveMemories(userId, sessionId, query) {
|
||||
if (!userId) return [];
|
||||
function explainCanHandle(input = {}) {
|
||||
return evaluateCanHandle({
|
||||
...input,
|
||||
enabled,
|
||||
userAuth,
|
||||
llmProviderService,
|
||||
sessionSnapshotService,
|
||||
});
|
||||
}
|
||||
|
||||
async function resolveMemories(userId, sessionId, query, { limit = MEMORY_INTERVENTION_LIMIT.LIGHT_DIRECT_CHAT } = {}) {
|
||||
if (!userId || limit <= 0) return [];
|
||||
if (memoryV2?.resolve) {
|
||||
const result = await memoryV2.resolve({ userId, sessionId, query, limit: 40 }).catch(() => null);
|
||||
const result = await memoryV2.resolve({ userId, sessionId, query, limit }).catch(() => null);
|
||||
return Array.isArray(result?.memories) ? result.memories : [];
|
||||
}
|
||||
if (conversationMemoryService?.listMemories) {
|
||||
return conversationMemoryService.listMemories(userId, { limit: 40 }).catch(() => []);
|
||||
return conversationMemoryService.listMemories(userId, { limit }).catch(() => []);
|
||||
}
|
||||
return [];
|
||||
}
|
||||
|
||||
async function run({ userId, sessionId = null, requestId, userMessage } = {}) {
|
||||
if (!canHandle({ sessionId, toolMode: 'chat', userMessage })) {
|
||||
async function run({
|
||||
userId,
|
||||
sessionId = null,
|
||||
requestId,
|
||||
userMessage,
|
||||
routingDecision = null,
|
||||
routingMemory = null,
|
||||
onSessionReady = null,
|
||||
} = {}) {
|
||||
if (!canHandle({ sessionId, toolMode: 'chat', userMessage, routingDecision })) {
|
||||
const err = new Error('Direct chat is not available for this run');
|
||||
err.code = 'DIRECT_CHAT_UNAVAILABLE';
|
||||
err.retryable = false;
|
||||
@@ -208,9 +285,44 @@ export function createDirectChatService({
|
||||
const activeSessionId = sessionId || createDirectSessionId();
|
||||
const snapshot = await sessionSnapshotService.get(activeSessionId).catch(() => null);
|
||||
const previousMessages = Array.isArray(snapshot?.messages) ? snapshot.messages : [];
|
||||
const memories = await resolveMemories(userId, activeSessionId, messageText(userMessage));
|
||||
const now = new Date().toISOString();
|
||||
if (!sessionId) {
|
||||
await userAuth.registerAgentSession(userId, activeSessionId, 'h5-direct');
|
||||
}
|
||||
if (typeof onSessionReady === 'function') {
|
||||
await onSessionReady(activeSessionId);
|
||||
}
|
||||
const pendingMessages = [...previousMessages, userMessage];
|
||||
await sessionSnapshotService.save(
|
||||
activeSessionId,
|
||||
userId,
|
||||
{
|
||||
id: activeSessionId,
|
||||
name: snapshot?.session?.name ?? 'New Chat',
|
||||
working_dir: snapshot?.session?.working_dir ?? '',
|
||||
message_count: pendingMessages.length,
|
||||
created_at: snapshot?.session?.created_at ?? now,
|
||||
updated_at: now,
|
||||
user_set_name: snapshot?.session?.user_set_name ?? false,
|
||||
recipe: snapshot?.session?.recipe ?? null,
|
||||
conversation: pendingMessages,
|
||||
},
|
||||
pendingMessages,
|
||||
);
|
||||
const routedMemoryContent =
|
||||
routingMemory && !routingMemory.skipped && !routingMemory.degraded
|
||||
? String(routingMemory.content ?? '').trim()
|
||||
: '';
|
||||
const memories = routedMemoryContent
|
||||
? []
|
||||
: await resolveMemories(userId, activeSessionId, messageText(userMessage));
|
||||
const completion = await llmProviderService.createChatCompletion({
|
||||
messages: buildModelMessages({ previousMessages, userMessage, memories }),
|
||||
messages: buildModelMessages({
|
||||
previousMessages,
|
||||
userMessage,
|
||||
memories,
|
||||
routingMemoryContent: routedMemoryContent,
|
||||
}),
|
||||
});
|
||||
if (!completion?.ok) {
|
||||
const err = new Error(completion?.message ?? 'Portal 直连聊天失败');
|
||||
@@ -218,9 +330,8 @@ export function createDirectChatService({
|
||||
throw err;
|
||||
}
|
||||
|
||||
const now = new Date().toISOString();
|
||||
const assistantMessage = buildAssistantMessage(completion.reply, { requestId, now });
|
||||
const messages = [...previousMessages, userMessage, assistantMessage];
|
||||
const messages = [...pendingMessages, assistantMessage];
|
||||
const session = {
|
||||
id: activeSessionId,
|
||||
name: snapshot?.session?.name ?? 'New Chat',
|
||||
@@ -232,9 +343,6 @@ export function createDirectChatService({
|
||||
recipe: snapshot?.session?.recipe ?? null,
|
||||
conversation: messages,
|
||||
};
|
||||
if (!sessionId) {
|
||||
await userAuth.registerAgentSession(userId, activeSessionId, 'h5-direct');
|
||||
}
|
||||
await sessionSnapshotService.save(activeSessionId, userId, session, messages);
|
||||
|
||||
let billing = null;
|
||||
@@ -264,6 +372,7 @@ export function createDirectChatService({
|
||||
return {
|
||||
getStatus,
|
||||
canHandle,
|
||||
explainCanHandle,
|
||||
run,
|
||||
};
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user