v2.2.19: Cloud Model Providers Support (OpenRouter, Anthropic, Gemini)

src/agent.ts

@@ -731,8 +731,16 @@ export class AgentExecutor {
                 this.abortController?.abort();
             }, timeout);
 
-            const engine = resolveEngine(ollamaUrl);
-            const useLmStudioSdk = engine === 'lmstudio' && !!this.options.lmStudioStreamer;
+            // Cloud provider 라우팅 — actualModel 의 prefix 가 cloud 면 SDK / 로컬 REST 경로 둘 다 우회.
+            // SSE 파서 입장에서는 동일한 OpenAI 호환 stream 이 들어오므로 consumer 변경 없음.
+            const _cloudHit = (() => {
+                try {
+                    const { parseModelPrefix } = require('./features/providers') as typeof import('./features/providers');
+                    return parseModelPrefix(actualModel);
+                } catch { return null; }
+            })();
+            const engine = _cloudHit ? 'lmstudio' : resolveEngine(ollamaUrl);
+            const useLmStudioSdk = !_cloudHit && engine === 'lmstudio' && !!this.options.lmStudioStreamer;
             let apiUrl = '';
             let aiResponseText = '';
             let buffer = '';
@@ -2754,6 +2762,35 @@ export class AgentExecutor {
     }): Promise<{ response: Response; engine: 'lmstudio' | 'ollama'; apiUrl: string }> {
         const { baseUrl, modelName, reqMessages, temperature } = params;
         const maxTokens = Math.max(256, params.maxTokens ?? 4096);
+
+        // Cloud provider 라우팅 — model id 가 'openrouter:' / 'anthropic:' / 'gemini:' 로 시작하면
+        // 해당 adapter 호출. body 는 OpenAI 호환 SSE 로 transform 되어 반환되므로
+        // 아래 로컬 엔진 경로의 consumer 가 동일하게 처리.
+        try {
+            const { parseModelPrefix, streamCloudCompletion } =
+                require('./features/providers') as typeof import('./features/providers');
+            const hit = parseModelPrefix(modelName);
+            if (hit) {
+                logInfo('AI streaming request (cloud).', { provider: hit.provider, model: hit.model });
+                const response = await streamCloudCompletion(this.context, hit, {
+                    messages: reqMessages.map((m) => ({ role: m.role as any, content: m.content })),
+                    temperature,
+                    maxTokens,
+                    signal: this.abortController?.signal,
+                });
+                if (!response.ok) {
+                    const errText = await response.text();
+                    throw new Error(`Cloud (${hit.provider}) ${response.status}: ${summarizeText(errText, 300)}`);
+                }
+                return { response, engine: 'lmstudio', apiUrl: `cloud://${hit.provider}/${hit.model}` };
+            }
+        } catch (e) {
+            // 모듈 로드 실패 / 매칭 안 됨 — 로컬 경로로 fall through.
+            // (단, 명시적으로 cloud routing 했는데 실패한 경우는 throw 되어 위에서 catch 됨.)
+            const msg = (e as Error)?.message ?? '';
+            if (msg.startsWith('Cloud (')) throw e;
+        }
+
         const numCtx = Math.max(2048, params.contextLength ?? 32768);
         const engine = resolveEngine(baseUrl);  // 사용자가 설정한 엔진만 사용
         const apiUrl = buildApiUrl(baseUrl, engine, 'chat');
@@ -2860,6 +2897,45 @@ export class AgentExecutor {
     }): Promise<{ text: string; stopReason?: string }> {
         const { baseUrl, modelName, engine, messages, temperature, signal } = params;
         const maxTokens = Math.max(256, params.maxTokens ?? 4096);
+
+        // Cloud routing — streaming Response 를 받아 끝까지 모아서 텍스트로 환원.
+        // Non-streaming 전용 endpoint 를 따로 두지 않고 stream 결과를 모으는 게 단순.
+        try {
+            const { parseModelPrefix, streamCloudCompletion } =
+                require('./features/providers') as typeof import('./features/providers');
+            const hit = parseModelPrefix(modelName);
+            if (hit) {
+                const response = await streamCloudCompletion(this.context, hit, {
+                    messages: messages.map((m) => ({ role: m.role as any, content: m.content })),
+                    temperature,
+                    maxTokens,
+                    signal,
+                });
+                if (!response.ok) {
+                    const errText = await response.text().catch(() => '');
+                    throw new Error(`Cloud (${hit.provider}) ${response.status}: ${summarizeText(errText, 200)}`);
+                }
+                // OpenAI 호환 SSE 를 통째로 읽어 delta.content 합치기.
+                const raw = await response.text();
+                let acc = '';
+                for (const line of raw.split('\n')) {
+                    const t = line.trim();
+                    if (!t.startsWith('data:')) continue;
+                    const payload = t.slice(5).trim();
+                    if (!payload || payload === '[DONE]') continue;
+                    try {
+                        const obj = JSON.parse(payload);
+                        const delta = obj?.choices?.[0]?.delta?.content;
+                        if (typeof delta === 'string') acc += delta;
+                    } catch { /* skip malformed */ }
+                }
+                return { text: acc, stopReason: 'stop' };
+            }
+        } catch (e) {
+            const msg = (e as Error)?.message ?? '';
+            if (msg.startsWith('Cloud (')) throw e;
+        }
+
         const numCtx = Math.max(2048, params.contextLength ?? 32768);
         const apiUrl = buildApiUrl(baseUrl, engine, 'chat');
         const variants = this.buildEngineMessageVariants(messages, engine);