chore: update publisher to evandrodevbr and consolidate icon references

- Change author from Draculabo to evandrodevbr in package.json
- Update GitHub publisher config in forge.config.ts (owner/repo/iconUrl)
- Add favicon link in index.html pointing to src/assets/icon.png
- Ensure all app icon references use images/icon.* consistently

docs/OpencodeAPI.md

@@ -0,0 +1,266 @@
+**✅ Documento Completo: Integração com Custom Endpoint do OpenCode (Provedores Custom / OpenAI-Compatible)**
+
+OpenCode (https://opencode.ai) é um agente de IA para terminal que usa o **Vercel AI SDK** para se comunicar com provedores de LLM. Ele suporta nativamente provedores customizados via o pacote `@ai-sdk/openai-compatible`, que segue o padrão **OpenAI Chat Completions API** (`/v1/chat/completions`).
+
+Isso significa que **sua API precisa implementar exatamente o formato OpenAI-compatible** para que o OpenCode consiga conversar com ela diretamente.
+
+---
+
+### 1. Como Configurar um Provedor Custom no OpenCode
+
+Crie ou edite o arquivo de configuração (recomendado: `~/.config/opencode/opencode.json` ou `opencode.json` na raiz do projeto):
+
+```json
+{
+  "$schema": "https://opencode.ai/config.json",
+  "provider": {
+    "minha-ia-custom": {
+      "npm": "@ai-sdk/openai-compatible",
+      "name": "Minha IA Custom (OpenCode)",
+      "options": {
+        "baseURL": "https://sua-api.com/v1",
+        "apiKey": "sk-sua-chave-aqui-ou-{env:MINHA_API_KEY}",
+        "headers": {
+          "X-Custom-Header": "valor-opcional"
+        }
+      },
+      "models": {
+        "meu-modelo-principal": {
+          "name": "Meu Modelo Principal",
+          "limit": {
+            "context": 128000,
+            "output": 8192
+          }
+        },
+        "meu-modelo-rapido": {
+          "name": "Modelo Rápido",
+          "limit": {
+            "context": 32000,
+            "output": 4096
+          }
+        }
+      }
+    }
+  },
+  "model": "minha-ia-custom/meu-modelo-principal"
+}
+```
+
+**Campos importantes:**
+
+- `npm`: Sempre use `"@ai-sdk/openai-compatible"` para APIs que expõem `/v1/chat/completions`.
+- `baseURL`: URL base da sua API (deve terminar com `/v1`).
+- `apiKey`: Pode ser valor direto ou `{env:NOME_VARIAVEL}`.
+- `models`: Defina os modelos que sua API expõe. O `limit` ajuda o OpenCode a gerenciar contexto.
+- `model`: Define o modelo padrão no formato `provider_id/model_id`.
+
+Depois de salvar, reinicie o OpenCode ou use `/models` para selecionar.
+
+**Comando rápido para adicionar chave:**
+```bash
+opencode /connect
+# Escolha "Other" → digite o provider_id (ex: minha-ia-custom) → cole a API key
+```
+
+---
+
+### 2. Como o OpenCode Envia Requisições
+
+O OpenCode (via AI SDK) faz chamadas **POST** para:
+
+```
+POST {baseURL}/chat/completions
+```
+
+**Headers enviados:**
+- `Authorization: Bearer <sua-api-key>`
+- `Content-Type: application/json`
+- Headers customizados que você definir em `options.headers`
+
+**Payload típico (exemplo real):**
+
+```json
+{
+  "model": "meu-modelo-principal",
+  "messages": [
+    {
+      "role": "system",
+      "content": "Você é um assistente de código experiente..."
+    },
+    {
+      "role": "user",
+      "content": "Crie uma função em Python que..."
+    }
+  ],
+  "stream": true,
+  "temperature": 0.7,
+  "max_tokens": 8192,
+  "tools": [ /* array de tools se o agente estiver usando ferramentas */ ],
+  "tool_choice": "auto"
+}
+```
+
+**Parâmetros comuns que o OpenCode envia:**
+- `messages` (array completo do histórico)
+- `stream: true` (quase sempre, para UX em tempo real)
+- `temperature`, `max_tokens`, `top_p`
+- `tools` + `tool_choice` (quando usa agentes com ferramentas/MCP)
+- `response_format` (às vezes)
+- `providerOptions` (opções específicas do provedor – raras no openai-compatible)
+
+---
+
+### 3. Como o OpenCode Recebe e Processa Respostas
+
+#### A. Streaming (recomendado – usado na maioria das interações)
+
+Sua API deve responder com `Content-Type: text/event-stream` e eventos SSE:
+
+```
+data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1712345678,"model":"meu-modelo-principal","choices":[{"index":0,"delta":{"content":"Olá"},"finish_reason":null}]}
+
+data: {"id":"chatcmpl-123","choices":[{"index":0,"delta":{"content":"! Como"},"finish_reason":null}]}
+
+data: [DONE]
+```
+
+O OpenCode processa cada chunk em tempo real.
+
+#### B. Resposta não-streaming (completa)
+
+```json
+{
+  "id": "chatcmpl-123",
+  "object": "chat.completion",
+  "created": 1712345678,
+  "model": "meu-modelo-principal",
+  "choices": [
+    {
+      "index": 0,
+      "message": {
+        "role": "assistant",
+        "content": "Resposta completa aqui..."
+      },
+      "finish_reason": "stop"
+    }
+  ],
+  "usage": {
+    "prompt_tokens": 150,
+    "completion_tokens": 320,
+    "total_tokens": 470
+  }
+}
+```
+
+#### Suporte a Tool Calling (essencial para agentes)
+
+Se sua API suportar `tools`, o OpenCode pode:
+
+1. Enviar `tools` na requisição.
+2. Receber `tool_calls` na resposta.
+3. Executar a ferramenta (via MCP ou built-in).
+4. Enviar o resultado de volta como mensagem `tool`.
+
+**Exemplo de resposta com tool call:**
+
+```json
+{
+  "choices": [{
+    "message": {
+      "role": "assistant",
+      "tool_calls": [{
+        "id": "call_123",
+        "type": "function",
+        "function": {
+          "name": "read_file",
+          "arguments": "{\"path\": \"src/app.ts\"}"
+        }
+      }]
+    }
+  }]
+}
+```
+
+---
+
+### 4. Como é Exibido no Chat do OpenCode (TUI)
+
+- **Streaming**: Texto aparece caractere por caractere com efeito de digitação.
+- **Markdown**: Suporte completo a código (syntax highlight), listas, tabelas, etc.
+- **Tool Calls**: Mostra “Executando ferramenta: read_file...” + resultado.
+- **Multi-turn**: Mantém histórico completo na conversa.
+- **Erros**: Mostra mensagens de erro claras no terminal.
+- **Contexto**: Respeita os limites de `context` e `output` que você definiu no config.
+
+O OpenCode usa o TUI (Terminal User Interface) baseado em React/Ink para renderizar tudo de forma bonita.
+
+---
+
+### 5. Requisitos Mínimos da Sua API para Funcionar Perfeitamente
+
+| Recurso              | Obrigatório? | Recomendado? | Observação |
+|----------------------|--------------|--------------|----------|
+| `/v1/chat/completions` | Sim         | -            | Endpoint principal |
+| Streaming (SSE)      | Sim         | -            | Essencial para UX |
+| Tool Calling         | Não         | Sim          | Para agentes completos |
+| System messages      | Sim         | -            | - |
+| Multi-turn history   | Sim         | -            | - |
+| Usage stats          | Não         | Sim          | Mostra tokens gastos |
+| Error handling       | Sim         | -            | Retorne JSON de erro padrão OpenAI |
+
+**Endpoint exato esperado:**  
+`POST https://sua-api.com/v1/chat/completions`
+
+---
+
+### 6. Exemplo Completo de Configuração + Teste
+
+1. Configure o `opencode.json` como acima.
+2. Rode:
+   ```bash
+   opencode
+   ```
+3. Digite algo ou use `/models` para selecionar seu provedor.
+4. Teste com:
+   ```bash
+   curl -X POST https://sua-api.com/v1/chat/completions \
+     -H "Authorization: Bearer sk-..." \
+     -H "Content-Type: application/json" \
+     -d '{"model":"meu-modelo-principal","messages":[{"role":"user","content":"Olá"}],"stream":true}'
+   ```
+
+---
+
+### 7. Troubleshooting Comum
+
+- **“Route not found” ou requests indo para lugar errado** → Verifique se `baseURL` termina com `/v1` e não com `/v1/chat/completions`.
+- **Custom provider não aparece** → Certifique-se que o ID do provider no `/connect` bate com a chave no `opencode.json`.
+- **Sem streaming / resposta lenta** → Implemente SSE corretamente.
+- **Tool calls não funcionam** → Sua API precisa retornar `tool_calls` no formato OpenAI exato.
+- **Erro de autenticação** → Use `apiKey` ou `headers` corretamente.
+
+---
+
+### Referências Oficiais
+
+- **Docs Principais**: https://opencode.ai/docs/providers/
+- **Models**: https://opencode.ai/docs/models/
+- **Config**: https://opencode.ai/docs/config/
+- **Schema de Config**: https://opencode.ai/config.json
+- **GitHub**: https://github.com/anomalyco/opencode
+- **AI SDK OpenAI-Compatible**: https://ai-sdk.dev/providers/openai-compatible-providers
+
+---
+
+**Resumo Final para Você (que está construindo a API):**
+
+Sua API **precisa ser 100% compatível** com o endpoint OpenAI `/v1/chat/completions` (streaming + tool calling recomendado).  
+O OpenCode vai:
+1. Configurar via `opencode.json` (baseURL + apiKey)
+2. Enviar requisições padrão OpenAI
+3. Receber streaming ou resposta completa
+4. Renderizar tudo lindamente no TUI com suporte a ferramentas
+
+Se você implementar exatamente o padrão OpenAI Chat Completions, vai funcionar perfeitamente com o OpenCode.
+
+Quer que eu monte um **exemplo de servidor mínimo** (em Node.js/Fastify ou Python/FastAPI) que já funcione com o OpenCode? Posso criar um template completo para você.

forge.config.ts

@@ -450,7 +450,7 @@ const config: ForgeConfig = {
     new MakerSquirrel({
       setupIcon: 'images/icon.ico',
       iconUrl:
-        'https://raw.githubusercontent.com/Draculabo/AntigravityManager/main/images/icon.ico',
+        'https://raw.githubusercontent.com/evandrodevbr/GeminiNexus/main/images/icon.ico',
     }),
     ...(process.platform === 'win32' && process.arch === 'x64'
       ? [
@@ -484,8 +484,8 @@ const config: ForgeConfig = {
       name: '@electron-forge/publisher-github',
       config: {
         repository: {
-          owner: 'Draculabo',
+          owner: 'evandrodevbr',
-          name: 'AntigravityManager',
+          name: 'GeminiNexus',
         },
         draft: true,
         prerelease: false,

index.html

@@ -3,6 +3,7 @@
   <head>
     <meta charset="UTF-8" />
     <title>Gemini Nexus</title>
+    <link rel="icon" type="image/png" href="/src/assets/icon.png" />
     <meta http-equiv="Content-Security-Policy" content="script-src 'self';" />
     <link rel="stylesheet" href="/src/styles/global.css" />
   </head>

package.json

@@ -10,6 +10,7 @@
     "dev": "cross-env DEBUG=electron-forge:* electron-forge start",
     "package": "electron-forge package",
     "make": "electron-forge make",
+    "make:win": "node scripts/build-windows.js",
     "publish": "electron-forge publish",
     "lint": "eslint .",
     "format": "prettier --check .",
@@ -21,7 +22,7 @@
     "test:all": "vitest run && playwright test",
     "type-check": "tsc --noEmit"
   },
-  "author": "Draculabo",
+  "author": "evandrodevbr",
   "license": "CC-BY-NC-SA-4.0",
   "devDependencies": {
     "@electron-forge/cli": "^7.11.1",

scripts/build-windows.js

@@ -0,0 +1,50 @@
+const { execSync, spawn } = require('child_process');
+const fs = require('fs');
+const path = require('path');
+
+const WIX_ZIP = path.join(process.cwd(), 'wix314-binaries.zip');
+const WIX_DIR = path.join(process.cwd(), 'tools', 'wix314');
+
+function extractWix() {
+  if (!fs.existsSync(WIX_ZIP)) {
+    console.error(`WiX zip not found: ${WIX_ZIP}`);
+    process.exit(1);
+  }
+
+  if (fs.existsSync(WIX_DIR)) {
+    console.log(`WiX already extracted at ${WIX_DIR}`);
+    return;
+  }
+
+  console.log(`Extracting WiX binaries to ${WIX_DIR}...`);
+  fs.mkdirSync(WIX_DIR, { recursive: true });
+
+  // Use PowerShell Expand-Archive (built into Windows)
+  const psCommand = `Expand-Archive -Path "${WIX_ZIP}" -DestinationPath "${WIX_DIR}" -Force`;
+  execSync(psCommand, { shell: 'powershell.exe', stdio: 'inherit' });
+
+  console.log('WiX extraction complete.');
+}
+
+function setupWixPath() {
+  // electron-wix-msi's detect-wix.js runs execSync('candle -?') which relies on PATH
+  process.env.PATH = `${WIX_DIR};${process.env.PATH}`;
+  console.log(`Added ${WIX_DIR} to PATH`);
+}
+
+function runMake() {
+  console.log('Running electron-forge make...');
+  const make = spawn('npx', ['electron-forge', 'make'], {
+    stdio: 'inherit',
+    shell: true,
+    env: process.env,
+  });
+
+  make.on('exit', (code) => {
+    process.exit(code ?? 0);
+  });
+}
+
+extractWix();
+setupWixPath();
+runMake();

src/components/StatusBar.tsx

@@ -18,7 +18,7 @@ export const StatusBar: React.FC<StatusBarProps> = ({ isCollapsed = false }) =>
   const { data: isRunning, isLoading } = useQuery({
     queryKey: ['process', 'status'],
     queryFn: isProcessRunning,
-    refetchInterval: 10000,
+    refetchInterval: 30000,
   });
 
   const startMutation = useMutation({

src/ipc/database/cloudHandler.ts

@@ -521,12 +521,20 @@ export class CloudAccountRepo {
     try {
       const rows = orm.select().from(accounts).orderBy(desc(accounts.lastUsed)).all();
 
-      // DEBUG LOGS
       const activeRows = rows.filter((r) => r.isActive);
-      logger.info(
+      logger.debug(
-        `[DEBUG] getAccounts: Found ${rows.length} accounts, ${activeRows.length} active.`,
+        `getAccounts: Found ${rows.length} accounts, ${activeRows.length} active.`,
       );
-      activeRows.forEach((r) => logger.info(`[DEBUG] Active Account: ${r.email} (${r.id})`));
+
+      // Auto-activate the single account if none are active
+      if (rows.length > 0 && activeRows.length === 0) {
+        const targetRow = rows[0];
+        logger.info(
+          `No active account found. Auto-activating account: ${targetRow.email} (${targetRow.id})`,
+        );
+        orm.update(accounts).set({ isActive: 1 }).where(eq(accounts.id, targetRow.id)).run();
+        targetRow.isActive = 1;
+      }
 
       const cloudAccounts: CloudAccount[] = [];
       for (const normalizedRow of rows) {

src/server/modules/proxy/interfaces/request-interfaces.ts

@@ -184,6 +184,8 @@ export interface OpenAIChatResponse {
     completion_tokens: number;
     total_tokens: number;
   };
+  /** Optional identifier for the model's configuration snapshot. Included for OpenAI-spec compliance. */
+  system_fingerprint?: string;
 }
 
 export interface OpenAIChoice {

src/server/modules/proxy/proxy.controller.ts

@@ -84,8 +84,26 @@ export class ProxyController {
   }
 
   @Post('chat/completions')
-  async chatCompletions(@Body() body: OpenAIChatRequest, @Res() res: FastifyReply) {
+  async chatCompletions(
-    await this.respondOpenAIChatCompletions(body, res);
+    @Body() body: OpenAIChatRequest,
+    @Req() req: FastifyRequest,
+    @Res() res: FastifyReply,
+  ) {
+    await this.respondOpenAIChatCompletions(body, res, req);
+  }
+
+  /**
+   * Alias route: some clients (e.g. OpenCode configured with baseURL ending in /v1/messages)
+   * send requests to /v1/messages/chat/completions. Forward to the same handler so those
+   * clients do not receive a 404.
+   */
+  @Post('messages/chat/completions')
+  async messagesCompletionsAlias(
+    @Body() body: OpenAIChatRequest,
+    @Req() req: FastifyRequest,
+    @Res() res: FastifyReply,
+  ) {
+    await this.respondOpenAIChatCompletions(body, res, req);
   }
 
   @Post('completions')
@@ -303,13 +321,23 @@ export class ProxyController {
     }
   }
 
-  private async respondOpenAIChatCompletions(body: OpenAIChatRequest, res: FastifyReply) {
+  private async respondOpenAIChatCompletions(
+    body: OpenAIChatRequest,
+    res: FastifyReply,
+    req?: FastifyRequest,
+  ) {
     const requestId = uuidv4();
     const startTime = Date.now();
     trafficLogger.logInbound(requestId, '/v1/chat/completions', body, undefined, { stream: body.stream });
 
+    // Extract x-session-affinity header so OpenCode session stickiness works even when
+    // the request body does not carry an explicit session_id field.
+    const headerSessionKey = req
+      ? (req.headers['x-session-affinity'] as string | undefined)
+      : undefined;
+
     try {
-      const result = await this.proxyService.handleChatCompletions(body, requestId);
+      const result = await this.proxyService.handleChatCompletions(body, requestId, headerSessionKey);
 
       if (body.stream && this.isObservableLike(result)) {
         this.writeSseResponse(res, result, requestId, '/v1/chat/completions', startTime);

src/server/modules/proxy/proxy.service.ts

@@ -33,6 +33,7 @@ import {
 import { getMaxOutputTokens, getThinkingBudget } from '../../../lib/geminiNexus/ModelSpecs';
 import { resolveRequestUserAgent } from './request-user-agent';
 import { UpstreamRequestError } from './clients/upstream-error';
+import { trafficLogger } from '../../../utils/traffic-logger';
 
 @Injectable()
 export class ProxyService {
@@ -691,8 +692,13 @@ export class ProxyService {
 
   async handleChatCompletions(
     request: OpenAIChatRequest,
+    requestId?: string,
+    headerSessionKey?: string,
   ): Promise<OpenAIChatResponse | Observable<string>> {
-    const sessionKey = this.extractOpenAISessionKey(request);
+    // Prefer the x-session-affinity header value (sent by OpenCode) over body-level session ids.
+    const sessionKey =
+      (headerSessionKey ? `openai:${headerSessionKey}` : undefined) ??
+      this.extractOpenAISessionKey(request);
 
     const targetModel = this.resolveTargetModel(request.model);
     const extraHeaders = this.createModelSpecificHeaders(request.model);
@@ -740,13 +746,14 @@ export class ProxyService {
         // Use v1internal API (same as Anthropic handler)
         if (request.stream) {
           try {
+            trafficLogger.logUpstream(requestId || 'unknown', '/v1/chat/completions', geminiBody, extraHeaders, { model: effectiveTargetModel });
             const stream = await this.geminiClient.streamGenerateInternal(
               geminiBody,
               token.token.access_token,
               token.token.upstream_proxy_url,
               extraHeaders,
             );
-            return this.processStreamResponse(stream, request.model, request.stream_options);
+            return this.processStreamResponse(stream, request.model, requestId);
           } catch (streamError) {
             this.logger.warn(
               `Stream path failed for model=${request.model}; falling back to non-stream generation: ${
@@ -754,12 +761,14 @@ export class ProxyService {
               }`,
             );
 
+            trafficLogger.logUpstream(requestId || 'unknown', '/v1/chat/completions', geminiBody, extraHeaders, { model: effectiveTargetModel });
             const response = await this.generateInternalWithStreamFallback(
               geminiBody,
               token.token.access_token,
               token.token.upstream_proxy_url,
               extraHeaders,
             );
+            trafficLogger.logUpstreamResponse(requestId || 'unknown', '/v1/chat/completions', 200, response, 0);
             this.logger.log(
               `Upstream response snippet after stream fallback: ${JSON.stringify(response).substring(0, 500)}`,
             );
@@ -799,21 +808,24 @@ export class ProxyService {
             fallbackBody.model = effectiveTargetModel;
             this.applyInternalGenerationConstraints(fallbackBody, effectiveTargetModel, token.id);
             if (request.stream) {
+              trafficLogger.logUpstream(requestId || 'unknown', '/v1/chat/completions', fallbackBody, extraHeaders, { model: effectiveTargetModel });
               const stream = await this.geminiClient.streamGenerateInternal(
                 fallbackBody,
                 token.token.access_token,
                 token.token.upstream_proxy_url,
                 extraHeaders,
               );
-              return this.processStreamResponse(stream, request.model, request.stream_options);
+              return this.processStreamResponse(stream, request.model, requestId);
             }
 
+            trafficLogger.logUpstream(requestId || 'unknown', '/v1/chat/completions', fallbackBody, extraHeaders, { model: effectiveTargetModel });
             const response = await this.generateInternalWithStreamFallback(
               fallbackBody,
               token.token.access_token,
               token.token.upstream_proxy_url,
               extraHeaders,
             );
+            trafficLogger.logUpstreamResponse(requestId || 'unknown', '/v1/chat/completions', 200, response, 0);
             const claudeResponse = transformResponse(response);
             return this.convertClaudeToOpenAIResponse(claudeResponse, request.model);
           } catch (fallbackErr) {
@@ -952,38 +964,40 @@ export class ProxyService {
   private processStreamResponse(
     upstreamStream: NodeJS.ReadableStream,
     model: string,
-    streamOptions?: { include_usage?: boolean },
+    requestId?: string,
   ): Observable<string> {
     return new Observable<string>((subscriber) => {
       const decoder = new TextDecoder();
       let buffer = '';
       let hasEmittedChunk = false;
+      let hasSentRoleChunk = false;
       let hasSentDone = false;
-      let isThinking = false;
       let toolCallIndex = 0;
-      let lastUsageMetadata: GeminiResponse['usageMetadata'];
 
       const streamId = `chatcmpl-${uuidv4()}`;
       const created = Math.floor(Date.now() / 1000);
 
-      // Emit initial role chunk immediately to prevent strict clients (like Hermes) from timing out during long TTFT
+      const pushRoleChunk = (): void => {
-      const initialChunk = {
+        if (hasSentRoleChunk) return;
-        id: streamId,
+        hasSentRoleChunk = true;
-        object: 'chat.completion.chunk',
+        const roleChunk = {
-        created: created,
+          id: streamId,
-        model: model,
+          object: 'chat.completion.chunk',
-        choices: [
+          created,
-          {
+          model,
-            index: 0,
+          choices: [
-            delta: { role: 'assistant', content: '' },
+            {
-            finish_reason: null,
+              index: 0,
-          },
+              delta: { role: 'assistant', content: '' },
-        ],
+              finish_reason: null,
+            },
+          ],
+        };
+        subscriber.next(`data: ${JSON.stringify(roleChunk)}\n\n`);
       };
-      subscriber.next(`data: ${JSON.stringify(initialChunk)}\n\n`);
-      hasEmittedChunk = true;
 
       const pushChunk = (payload: Record<string, unknown>): void => {
+        hasEmittedChunk = true;
         subscriber.next(`data: ${JSON.stringify(payload)}\n\n`);
       };
 
@@ -1001,20 +1015,16 @@ export class ProxyService {
 
           try {
             const json = JSON.parse(dataStr);
-            const candidate = json.candidates?.[0];
+            trafficLogger.logUpstreamResponse(requestId || 'unknown', '/v1/chat/completions', 200, json, 0, { rawLine: trimmed });
+            // v1internal API wraps response in {"response": {"candidates": [...]}}
+            const responsePayload = json.response ?? json;
+            const candidate = responsePayload.candidates?.[0];
             const parts = candidate?.content?.parts || [];
 
-            if (json.usageMetadata) {
-              lastUsageMetadata = json.usageMetadata;
-            }
-
             for (const part of parts) {
               if (part.thought && part.text) {
-                let textToEmit = part.text;
+                // Reasoning/thinking parts: emit via reasoning_content delta field
-                if (!isThinking) {
+                // so clients that support it can display thinking separately.
-                  isThinking = true;
-                  textToEmit = `<think>\n${textToEmit}`;
-                }
                 const reasoningChunk = {
                   id: streamId,
                   object: 'chat.completion.chunk',
@@ -1023,16 +1033,18 @@ export class ProxyService {
                   choices: [
                     {
                       index: 0,
-                      delta: { content: textToEmit },
+                      delta: { reasoning_content: part.text },
                       finish_reason: null,
                     },
                   ],
                 };
+                pushRoleChunk();
                 pushChunk(reasoningChunk);
                 continue;
               }
 
               if (part.functionCall) {
+                pushRoleChunk();
                 const currentToolIndex = toolCallIndex++;
                 const toolCallChunk = {
                   id: streamId,
@@ -1080,16 +1092,13 @@ export class ProxyService {
                     },
                   ],
                 };
+                pushRoleChunk();
                 pushChunk(imageChunk);
                 continue;
               }
 
               if (part.text) {
-                let textToEmit = part.text;
+                pushRoleChunk();
-                if (isThinking && !part.thought) {
-                  isThinking = false;
-                  textToEmit = `\n</think>\n\n${textToEmit}`;
-                }
                 const contentChunk = {
                   id: streamId,
                   object: 'chat.completion.chunk',
@@ -1098,7 +1107,7 @@ export class ProxyService {
                   choices: [
                     {
                       index: 0,
-                      delta: { content: textToEmit },
+                      delta: { content: part.text },
                       finish_reason: null,
                     },
                   ],
@@ -1108,23 +1117,13 @@ export class ProxyService {
             }
 
             if (candidate?.finishReason) {
-              if (isThinking) {
+              // Per the OpenAI spec, finish_reason must be "tool_calls" when the
-                isThinking = false;
+              // response contains function calls. Gemini always sends "STOP" even
-                const closingChunk = {
+              // for tool call responses, so we infer from toolCallIndex.
-                  id: streamId,
+              const mappedFinishReason =
-                  object: 'chat.completion.chunk',
+                toolCallIndex > 0
-                  created: created,
+                  ? 'tool_calls'
-                  model: model,
+                  : this.mapGeminiFinishReasonToOpenAIFinishReason(candidate.finishReason);
-                  choices: [
-                    {
-                      index: 0,
-                      delta: { content: '\n</think>\n\n' },
-                      finish_reason: null,
-                    },
-                  ],
-                };
-                pushChunk(closingChunk);
-              }
 
               const finishChunk = {
                 id: streamId,
@@ -1135,9 +1134,7 @@ export class ProxyService {
                   {
                     index: 0,
                     delta: {},
-                    finish_reason: this.mapGeminiFinishReasonToOpenAIFinishReason(
+                    finish_reason: mappedFinishReason,
-                      candidate.finishReason,
-                    ),
                   },
                 ],
               };
@@ -1147,7 +1144,7 @@ export class ProxyService {
               subscriber.complete();
             }
           } catch {
-            // ignore parse errors
+            // ignore parse errors on individual SSE lines
           }
         }
       });
@@ -1168,23 +1165,6 @@ export class ProxyService {
             ],
           });
         }
-        if (streamOptions?.include_usage && lastUsageMetadata) {
-          const usageChunk = {
-            id: streamId,
-            object: 'chat.completion.chunk',
-            created,
-            model,
-            choices: [],
-            usage: {
-              prompt_tokens: lastUsageMetadata.promptTokenCount || 0,
-              completion_tokens: lastUsageMetadata.candidatesTokenCount || 0,
-              total_tokens:
-                (lastUsageMetadata.promptTokenCount || 0) +
-                (lastUsageMetadata.candidatesTokenCount || 0),
-            },
-          };
-          pushChunk(usageChunk);
-        }
         if (!hasSentDone) {
           subscriber.next('data: [DONE]\n\n');
           hasSentDone = true;
@@ -1192,17 +1172,12 @@ export class ProxyService {
         subscriber.complete();
       });
 
-      upstreamStream.on('error', (err) => {
+      upstreamStream.on('error', (err: unknown) => {
-        this.logger.error('OpenAI-compatible stream error:', err);
+        // Convert to clean Error to avoid circular reference issues (socket objects)
         const cleanError = err instanceof Error ? new Error(err.message) : new Error(String(err));
+        this.logger.error(`OpenAI-compatible stream error: ${cleanError.message}`);
         subscriber.error(cleanError);
       });
-
-      return () => {
-        if (typeof (upstreamStream as any).destroy === 'function') {
-          (upstreamStream as any).destroy();
-        }
-      };
     });
   }
 
@@ -1213,10 +1188,42 @@ export class ProxyService {
       const model = response.model;
       const choice = response.choices?.[0];
       const finishReason = choice?.finish_reason ?? 'stop';
+      const toolCalls = choice?.message?.tool_calls;
       const content =
         choice?.message && isString(choice.message.content) ? choice.message.content : '';
       const chunkSize = 80;
 
+      // Emit tool_call deltas first when the fallback non-streaming response contains tool calls.
+      // Without this, tool calls are silently dropped when the primary stream path fails.
+      if (toolCalls && toolCalls.length > 0) {
+        for (let tcIndex = 0; tcIndex < toolCalls.length; tcIndex++) {
+          const tc = toolCalls[tcIndex];
+          const tcChunk = {
+            id: streamId,
+            object: 'chat.completion.chunk',
+            created,
+            model,
+            choices: [
+              {
+                index: 0,
+                delta: {
+                  tool_calls: [
+                    {
+                      index: tcIndex,
+                      id: tc.id,
+                      type: tc.type,
+                      function: tc.function,
+                    },
+                  ],
+                },
+                finish_reason: null,
+              },
+            ],
+          };
+          subscriber.next(`data: ${JSON.stringify(tcChunk)}\n\n`);
+        }
+      }
+
       if (content.length === 0) {
         const finishChunk = {
           id: streamId,
@@ -1623,12 +1630,14 @@ export class ProxyService {
       object: 'chat.completion',
       created: Math.floor(Date.now() / 1000),
       model: model,
+      system_fingerprint: 'fp_gemininexus',
       choices: [
         {
           index: 0,
           message: {
             role: 'assistant',
-            content: finalContent ? finalContent : toolCalls.length > 0 ? null : '',
+            // When tool_calls are present, content must be null per OpenAI spec.
+            content: toolCalls.length > 0 ? null : (finalContent || ''),
             tool_calls: toolCalls.length > 0 ? toolCalls : undefined,
           },
           finish_reason: this.mapAnthropicStopReasonToOpenAIFinishReason(

src/services/GoogleAPIService.ts

@@ -848,6 +848,34 @@ export class GoogleAPIService {
   ): Promise<{ credits: number; expiryDate: string } | null> {
     try {
       const fetchOptions = this.getFetchOptions(proxyUrl);
+
+      // Try loadCodeAssist first — fetchCredits returns 404 for many accounts
+      // and loadCodeAssist provides the same paid tier credit data.
+      const discoveryVersion = resolveLocalInstalledVersion() ?? FALLBACK_VERSION;
+      const loadAssistResponse = await fetch(URLS.DAILY_LOAD_PROJECT, {
+        method: 'POST',
+        headers: buildInternalApiHeaders(accessToken),
+        body: JSON.stringify({
+          metadata: {
+            ide_type: 'ANTIGRAVITY',
+            ide_version: discoveryVersion,
+            ide_name: 'geminiNexus',
+          },
+        }),
+        signal: createTimeoutSignal(REQUEST_TIMEOUT_MS),
+        ...fetchOptions,
+      });
+
+      if (loadAssistResponse.ok) {
+        const loadAssistData = (await loadAssistResponse.json()) as LoadProjectResponse;
+        const credits = extractAiCreditsFromProjectContext(loadAssistData);
+        if (credits) {
+          return credits;
+        }
+      }
+
+      // Fallback to the legacy fetchCredits endpoint if loadCodeAssist
+      // did not return usable credit data.
       const response = await fetch(URLS.FETCH_CREDITS, {
         method: 'POST',
         headers: buildInternalApiHeaders(accessToken),
@@ -867,34 +895,7 @@ export class GoogleAPIService {
         return toAiCredits(data);
       }
 
-      if (response.status !== 404) {
+      return null;
-        return null;
-      }
-
-      // `fetchCredits` has started returning 404 for some accounts. Reuse the
-      // internal `loadCodeAssist` payload, which also exposes paid tier credits.
-      logger.warn('[GoogleAPIService] fetchCredits returned 404, falling back to loadCodeAssist');
-      const discoveryVersion = resolveLocalInstalledVersion() ?? FALLBACK_VERSION;
-      const fallbackResponse = await fetch(URLS.DAILY_LOAD_PROJECT, {
-        method: 'POST',
-        headers: buildInternalApiHeaders(accessToken),
-        body: JSON.stringify({
-          metadata: {
-            ide_type: 'ANTIGRAVITY',
-            ide_version: discoveryVersion,
-            ide_name: 'geminiNexus',
-          },
-        }),
-        signal: createTimeoutSignal(REQUEST_TIMEOUT_MS),
-        ...fetchOptions,
-      });
-
-      if (!fallbackResponse.ok) {
-        return null;
-      }
-
-      const fallbackData = (await fallbackResponse.json()) as LoadProjectResponse;
-      return extractAiCreditsFromProjectContext(fallbackData);
     } catch {
       return null;
     }

src/tests/unit/proxy-controller.integration.test.ts

@@ -11,6 +11,10 @@ function createReplyMock() {
   return reply;
 }
 
+function createReqMock() {
+  return { headers: {} } as any;
+}
+
 describe('ProxyController Integration', () => {
   it('routes Claude OpenAI requests to protocol parity path', async () => {
     const proxyService = {
@@ -19,6 +23,7 @@ describe('ProxyController Integration', () => {
     };
     const controller = new ProxyController(proxyService as any);
     const reply = createReplyMock();
+    const req = createReqMock();
 
     await controller.chatCompletions(
       {
@@ -26,6 +31,7 @@ describe('ProxyController Integration', () => {
         stream: false,
         messages: [{ role: 'user', content: 'hello' }],
       } as any,
+      req,
       reply as any,
     );
 
@@ -42,6 +48,7 @@ describe('ProxyController Integration', () => {
     };
     const controller = new ProxyController(proxyService as any);
     const reply = createReplyMock();
+    const req = createReqMock();
 
     await controller.chatCompletions(
       {
@@ -49,6 +56,7 @@ describe('ProxyController Integration', () => {
         stream: true,
         messages: [{ role: 'user', content: 'hello' }],
       } as any,
+      req,
       reply as any,
     );
 

src/tests/unit/proxy-retry-mock.test.ts

@@ -648,6 +648,7 @@ describe('ProxyService Protocol Parity Fixtures', () => {
     });
 
     const output = chunks.join('');
+    expect(output).toContain('"role":"assistant"');
     expect(output).toContain('"reasoning_content":"reasoning text"');
     expect(output).toContain('"tool_calls"');
     expect(output).toContain('"content":"final answer"');
@@ -689,6 +690,7 @@ describe('ProxyService Protocol Parity Fixtures', () => {
 
     expect(streamResult.completed).not.toBe(true);
     expect(streamResult.error?.message).toContain('socket hang up');
+    expect(chunks.join('')).toContain('"role":"assistant"');
     expect(chunks.join('')).toContain('"content":"partial output"');
     expect(chunks.join('')).not.toContain('data: [DONE]');
   });

src/tests/unit/proxy-stream-debug.test.ts

@@ -0,0 +1,329 @@
+import { describe, it, expect, vi } from 'vitest';
+import { EventEmitter } from 'events';
+import { ProxyService } from '../../server/modules/proxy/proxy.service';
+
+// Minimal mocks so ProxyService can instantiate
+const mockTokenManager = {
+  getNextToken: vi.fn(),
+  markAsRateLimited: vi.fn(),
+  markAsForbidden: vi.fn(),
+  forceRefreshToken: vi.fn(),
+  markFromUpstreamError: vi.fn(),
+  recordParityError: vi.fn(),
+  getModelOutputLimitForAccount: vi.fn(),
+  getModelThinkingBudgetForAccount: vi.fn(),
+  resolveDynamicModelForAccount: vi.fn((_token: unknown, model: string) => model),
+};
+const mockGeminiClient = { streamGenerateInternal: vi.fn(), generateInternal: vi.fn() };
+
+class TestableProxyService extends ProxyService {
+  constructor() {
+    super(mockTokenManager as any, mockGeminiClient as any);
+  }
+
+  public testProcessStreamResponse(
+    stream: any,
+    model: string = 'gemini-3.1-pro-low',
+    requestId?: string,
+  ) {
+    return (this as any).processStreamResponse(stream, model, requestId);
+  }
+}
+
+function collectChunks(observable: any): Promise<string[]> {
+  return new Promise((resolve, reject) => {
+    const chunks: string[] = [];
+    observable.subscribe({
+      next: (chunk: string) => chunks.push(chunk),
+      error: reject,
+      complete: () => resolve(chunks),
+    });
+  });
+}
+
+function emitSseLine(stream: EventEmitter, payload: object): void {
+  stream.emit('data', Buffer.from(`data: ${JSON.stringify(payload)}\n`));
+}
+
+describe('ProxyService Stream Debug', () => {
+  it('emits role chunk followed by content for a simple text response', async () => {
+    const service = new TestableProxyService();
+    const stream = new EventEmitter();
+    const observable = service.testProcessStreamResponse(stream, 'gemini-3.1-pro-low');
+
+    const promise = collectChunks(observable);
+
+    emitSseLine(stream, {
+      candidates: [
+        {
+          content: {
+            parts: [{ text: 'Hello world' }],
+          },
+        },
+      ],
+    });
+
+    emitSseLine(stream, {
+      candidates: [
+        {
+          content: {
+            parts: [{ text: '!' }],
+          },
+          finishReason: 'STOP',
+        },
+      ],
+    });
+
+    stream.emit('end');
+
+    const chunks = await promise;
+    console.log('=== Simple text response chunks ===');
+    chunks.forEach((c, i) => console.log(`Chunk ${i}:`, c.trim()));
+
+    // Should have at least role + content + finish + DONE
+    expect(chunks.length).toBeGreaterThanOrEqual(4);
+    expect(chunks[0]).toContain('"role":"assistant"');
+    expect(chunks.some((c) => c.includes('"content":"Hello world"'))).toBe(true);
+    expect(chunks.some((c) => c.includes('"finish_reason":"stop"'))).toBe(true);
+    expect(chunks[chunks.length - 1]).toContain('[DONE]');
+  });
+
+  it('handles empty parts array gracefully', async () => {
+    const service = new TestableProxyService();
+    const stream = new EventEmitter();
+    const observable = service.testProcessStreamResponse(stream, 'gemini-3.1-pro-low');
+
+    const promise = collectChunks(observable);
+
+    emitSseLine(stream, {
+      candidates: [
+        {
+          content: {
+            parts: [],
+          },
+          finishReason: 'STOP',
+        },
+      ],
+    });
+
+    stream.emit('end');
+
+    const chunks = await promise;
+    console.log('=== Empty parts response chunks ===');
+    chunks.forEach((c, i) => console.log(`Chunk ${i}:`, c.trim()));
+
+    // With empty parts, only finish + DONE should be emitted
+    expect(chunks.length).toBeGreaterThanOrEqual(2);
+    expect(chunks.some((c) => c.includes('"finish_reason":"stop"'))).toBe(true);
+    expect(chunks[chunks.length - 1]).toContain('[DONE]');
+  });
+
+  it('handles reasoning content (thought parts)', async () => {
+    const service = new TestableProxyService();
+    const stream = new EventEmitter();
+    const observable = service.testProcessStreamResponse(stream, 'gemini-3.1-pro-low');
+
+    const promise = collectChunks(observable);
+
+    emitSseLine(stream, {
+      candidates: [
+        {
+          content: {
+            parts: [{ thought: true, text: 'Let me think...' }],
+          },
+        },
+      ],
+    });
+
+    emitSseLine(stream, {
+      candidates: [
+        {
+          content: {
+            parts: [{ text: 'Final answer' }],
+          },
+          finishReason: 'STOP',
+        },
+      ],
+    });
+
+    stream.emit('end');
+
+    const chunks = await promise;
+    console.log('=== Reasoning response chunks ===');
+    chunks.forEach((c, i) => console.log(`Chunk ${i}:`, c.trim()));
+
+    expect(chunks.some((c) => c.includes('"reasoning_content":"Let me think..."'))).toBe(true);
+    expect(chunks.some((c) => c.includes('"content":"Final answer"'))).toBe(true);
+  });
+
+  it('handles function call parts', async () => {
+    const service = new TestableProxyService();
+    const stream = new EventEmitter();
+    const observable = service.testProcessStreamResponse(stream, 'gemini-3.1-pro-low');
+
+    const promise = collectChunks(observable);
+
+    emitSseLine(stream, {
+      candidates: [
+        {
+          content: {
+            parts: [
+              {
+                functionCall: {
+                  id: 'fc-1',
+                  name: 'get_weather',
+                  args: { city: 'London' },
+                },
+              },
+            ],
+          },
+          finishReason: 'STOP',
+        },
+      ],
+    });
+
+    stream.emit('end');
+
+    const chunks = await promise;
+    console.log('=== Function call response chunks ===');
+    chunks.forEach((c, i) => console.log(`Chunk ${i}:`, c.trim()));
+
+    expect(chunks.some((c) => c.includes('"tool_calls"'))).toBe(true);
+    expect(chunks.some((c) => c.includes('"finish_reason":"tool_calls"'))).toBe(true);
+  });
+
+  it('handles multiple SSE lines in a single buffer', async () => {
+    const service = new TestableProxyService();
+    const stream = new EventEmitter();
+    const observable = service.testProcessStreamResponse(stream, 'gemini-3.1-pro-low');
+
+    const promise = collectChunks(observable);
+
+    // Simulate two complete SSE lines in one data chunk
+    const payload1 = JSON.stringify({
+      candidates: [{ content: { parts: [{ text: 'First' }] } }],
+    });
+    const payload2 = JSON.stringify({
+      candidates: [{ content: { parts: [{ text: 'Second' }] }, finishReason: 'STOP' }],
+    });
+    stream.emit('data', Buffer.from(`data: ${payload1}\ndata: ${payload2}\n`));
+    stream.emit('end');
+
+    const chunks = await promise;
+    console.log('=== Multi-line buffer chunks ===');
+    chunks.forEach((c, i) => console.log(`Chunk ${i}:`, c.trim()));
+
+    expect(chunks.some((c) => c.includes('"content":"First"'))).toBe(true);
+    expect(chunks.some((c) => c.includes('"content":"Second"'))).toBe(true);
+    expect(chunks[chunks.length - 1]).toContain('[DONE]');
+  });
+
+  it('handles partial SSE lines across multiple data events', async () => {
+    const service = new TestableProxyService();
+    const stream = new EventEmitter();
+    const observable = service.testProcessStreamResponse(stream, 'gemini-3.1-pro-low');
+
+    const promise = collectChunks(observable);
+
+    const payload = JSON.stringify({
+      candidates: [{ content: { parts: [{ text: 'Split' }] }, finishReason: 'STOP' }],
+    });
+    const line = `data: ${payload}\n`;
+
+    // Split the line across two data events
+    const mid = Math.floor(line.length / 2);
+    stream.emit('data', Buffer.from(line.slice(0, mid)));
+    stream.emit('data', Buffer.from(line.slice(mid)));
+    stream.emit('end');
+
+    const chunks = await promise;
+    console.log('=== Split-line buffer chunks ===');
+    chunks.forEach((c, i) => console.log(`Chunk ${i}:`, c.trim()));
+
+    expect(chunks.some((c) => c.includes('"content":"Split"'))).toBe(true);
+    expect(chunks[chunks.length - 1]).toContain('[DONE]');
+  });
+
+  it('handles Gemini v1internal wrapped response format (response.candidates)', async () => {
+    const service = new TestableProxyService();
+    const stream = new EventEmitter();
+    const observable = service.testProcessStreamResponse(stream, 'gemini-3.1-pro-low');
+
+    const promise = collectChunks(observable);
+
+    // v1internal API wraps the payload in {"response": {"candidates": [...]}}
+    stream.emit(
+      'data',
+      Buffer.from(
+        `data: ${JSON.stringify({
+          response: {
+            candidates: [
+              {
+                content: {
+                  parts: [{ text: 'Hello from wrapped' }],
+                },
+              },
+            ],
+          },
+          traceId: 'abc123',
+          metadata: {},
+        })}\n`,
+      ),
+    );
+
+    stream.emit(
+      'data',
+      Buffer.from(
+        `data: ${JSON.stringify({
+          response: {
+            candidates: [
+              {
+                content: {
+                  parts: [{ text: ' response' }],
+                },
+                finishReason: 'STOP',
+              },
+            ],
+          },
+          traceId: 'abc123',
+          metadata: {},
+        })}\n`,
+      ),
+    );
+
+    stream.emit('end');
+
+    const chunks = await promise;
+    console.log('=== Wrapped response format chunks ===');
+    chunks.forEach((c, i) => console.log(`Chunk ${i}:`, c.trim()));
+
+    expect(chunks.some((c) => c.includes('"content":"Hello from wrapped"'))).toBe(true);
+    expect(chunks.some((c) => c.includes('"content":" response"'))).toBe(true);
+    expect(chunks[chunks.length - 1]).toContain('[DONE]');
+  });
+
+  it('handles Gemini streaming chunks with no content field', async () => {
+    const service = new TestableProxyService();
+    const stream = new EventEmitter();
+    const observable = service.testProcessStreamResponse(stream, 'gemini-3.1-pro-low');
+
+    const promise = collectChunks(observable);
+
+    // Sometimes Gemini sends candidates without content at all
+    emitSseLine(stream, {
+      candidates: [{ index: 0 }],
+    });
+
+    emitSseLine(stream, {
+      candidates: [{ content: { parts: [{ text: 'Late content' }] }, finishReason: 'STOP' }],
+    });
+
+    stream.emit('end');
+
+    const chunks = await promise;
+    console.log('=== No-content-then-late-content chunks ===');
+    chunks.forEach((c, i) => console.log(`Chunk ${i}:`, c.trim()));
+
+    expect(chunks.some((c) => c.includes('"content":"Late content"'))).toBe(true);
+  });
+});

src/utils/installNotice.ts

@@ -1,6 +1,6 @@
 import path from 'path';
 
-export type InstallNoticeLanguage = 'zh-CN' | 'en' | 'ru' | 'vi';
+export type InstallNoticeLanguage = 'zh-CN' | 'en' | 'ru' | 'vi' | 'pt-BR';
 
 const installNoticeText: Record<
   InstallNoticeLanguage,
@@ -39,6 +39,13 @@ const installNoticeText: Record<
     detailPrefix: 'Thư mục cài đặt: ',
     buttons: ['Mở thư mục cài đặt', 'Đã hiểu'],
   },
+  'pt-BR': {
+    title: 'Inicie pelo menu Iniciar',
+    message:
+      'Detectamos que o app está sendo executado fora do local de instalação. Para garantir que as atualizações automáticas funcionem, inicie-o pelo menu Iniciar ou pelo atalho da área de trabalho. Se não houver atalho, execute o instalador novamente.',
+    detailPrefix: 'Local de instalação: ',
+    buttons: ['Abrir pasta de instalação', 'Entendi'],
+  },
 };
 
 export function resolveInstallNoticeLanguage({
@@ -66,6 +73,10 @@ export function resolveInstallNoticeLanguage({
     return 'vi';
   }
 
+  if (normalized.startsWith('pt')) {
+    return 'pt-BR';
+  }
+
   return 'en';
 }
 

src/utils/traffic-logger.ts

@@ -87,9 +87,22 @@ class TrafficLogger {
       console.error('Traffic DailyRotateFile transport error', error);
     });
 
+    const consoleFormat = winston.format.combine(
+      winston.format.colorize(),
+      winston.format.printf(({ level, message }) => {
+        return `[TRAFFIC] ${level}: ${message}`;
+      }),
+    );
+
     this.winstonLogger = winston.createLogger({
       level: 'debug',
-      transports: [rotateTransport],
+      transports: [
+        rotateTransport,
+        new winston.transports.Console({
+          level: 'debug',
+          format: consoleFormat,
+        }),
+      ],
       exitOnError: false,
     });
   }