cx-viewer 1.0.3 → 1.0.4

package/concepts/pt-BR/GlobalSettings.md

@@ -1,232 +1,230 @@
-# CC-Viewer 全局配置参考
+# CX-Viewer Configuration Reference
 
-## 一、全局设置面板（UI）
+## 1. Global Settings Panel (UI)
 
-通过左上角菜单 → "全局设置" 打开。
+Open via top-left menu → "Global Settings".
 
-| 配置项 | 类型 | 默认值 | 说明 |
-|--------|------|--------|------|
-| 过滤无关请求 | 开关 | 开 | 隐藏心跳、count_tokens、子代理等非主代理请求 |
-| 默认展开 Body Diff JSON | 开关 | 关 | 请求详情面板中的 Body Diff 区域默认展开 |
-| 日志目录设置 | 文本输入 | `~/.claude/cc-viewer` | 项目日志的读写根目录，支持 `~/` 展开。修改后回车或失焦保存，立即生效 |
+| Setting | Type | Default | Description |
+|---------|------|---------|-------------|
+| Filter Irrelevant Requests | Switch | On | Hide heartbeat, count_tokens, sub-agent and other non-main-agent requests |
+| Expand Body Diff JSON | Switch | Off | Expand Body Diff section by default in request detail panel |
+| Log Directory | Text Input | `~/.codex/cx-viewer` | Root directory for project log read/write. Supports `~/` expansion. Takes effect immediately on Enter or blur |
 
-## 二、显示设置面板（UI）
+## 2. Display Settings Panel (UI)
 
-通过左上角菜单 → "显示设置" 打开。
+Open via top-left menu → "Display Settings".
 
-| 配置项 | 类型 | 默认值 | 说明 |
-|--------|------|--------|------|
-| 折叠工具结果 | 开关 | 开 | 聊天视图中折叠工具调用结果块 |
-| 展开思考过程 | 开关 | 开 | 默认展开 Claude 的思考/推理过程块 |
-| 完整展示所有内容 | 开关 | 关 | 显示完整的工具调用内容，不截断 |
-| 自动恢复会话 | 开关 + 选项 | 关 | 遇到会话恢复提示时自动选择：`继续` 或 `新建` |
+| Setting | Type | Default | Description |
+|---------|------|---------|-------------|
+| Collapse Tool Results | Switch | On | Collapse tool call result blocks in chat view |
+| Expand Thinking | Switch | On | Expand Codex reasoning/thinking blocks by default |
+| Show Full Tool Content | Switch | Off | Show full untruncated tool call content |
+| Auto Resume Session | Switch + Options | Off | Automatically choose when session resume prompt appears: `Continue` or `New` |
 
-## 三、偏好设置文件
+## 3. Preferences File
 
-所有 UI 设置持久化到 `<日志目录>/preferences.json`，通过 `/api/preferences` 接口读写。
+All UI settings are persisted to `<log_dir>/preferences.json` via the `/api/preferences` API.
 
 ```json
 {
-  "lang": "zh",
+  "lang": "en",
   "filterIrrelevant": true,
   "expandDiff": false,
   "collapseToolResults": true,
   "expandThinking": true,
   "showFullToolContent": false,
-  "logDir": "~/.claude/cc-viewer",
+  "logDir": "~/.codex/cx-viewer",
   "resumeAutoChoice": null,
   "disabledPlugins": [],
   "presetShortcuts": []
 }
 ```
 
-| 字段 | 类型 | 说明 |
-|------|------|------|
-| `lang` | string | 界面语言（zh/en/zh-TW/ko/ja/de/es/fr/it/da/pl/ru/ar/no/pt-BR/th/tr/uk） |
-| `filterIrrelevant` | boolean | 过滤无关请求 |
-| `expandDiff` | boolean | 默认展开 Body Diff JSON |
-| `collapseToolResults` | boolean | 折叠工具结果 |
-| `expandThinking` | boolean | 展开思考过程 |
-| `showFullToolContent` | boolean | 完整展示内容 |
-| `logDir` | string | 日志目录路径 |
-| `resumeAutoChoice` | null / "continue" / "new" | 自动恢复会话选择 |
-| `disabledPlugins` | string[] | 已禁用的插件文件名列表 |
-| `presetShortcuts` | array | Agent Team 快捷指令预设 |
-
-## 四、环境变量
-
-### CC-Viewer 专有
-
-| 变量名 | 默认值 | 说明 |
-|--------|--------|------|
-| `CCV_LOG_DIR` | `~/.claude/cc-viewer` | 日志存储根目录。特殊值：`tmp`/`temp` 使用系统临时目录 |
-| `CCV_CLI_MODE` | 未设置 | `=1` 启用 CLI 模式（PTY 终端） |
-| `CCV_SDK_MODE` | 未设置 | `=1` 启用 Agent SDK 模式（无终端） |
-| `CCV_WORKSPACE_MODE` | 未设置 | `=1` 启用工作空间选择模式 |
-| `CCV_PROJECT_DIR` | `process.cwd()` | 项目工作目录，用于文件操作和 Git 命令 |
-| `CCV_PROXY_PORT` | 未设置 | 本地 MITM 代理端口 |
-| `CCV_BYPASS_PERMISSIONS` | 未设置 | `=1` 跳过工具权限审批（配合 `--dangerously-skip-permissions`） |
-| `CCV_DISABLE_DELTA` | 未设置 | `=1` 禁用增量日志存储，每次写入完整消息 |
-| `CCV_DEBUG` | 未设置 | `=1` 启用 HTTP 代理调试日志 |
-| `CCV_DEBUG_PLUGINS` | 未设置 | `=1` 启用插件加载调试日志 |
-
-### 内部 IPC
-
-| 变量名 | 说明 |
-|--------|------|
-| `CCVIEWER_PORT` | 服务端口，供 ask-bridge/perm-bridge 通信 |
-| `CCV_EDITOR_PORT` | 服务端口，供 ccv-editor 文件编辑桥接 |
-
-### 外部变量（读取）
-
-| 变量名 | 说明 |
-|--------|------|
-| `ANTHROPIC_BASE_URL` | 自定义 Anthropic API 地址 |
-| `SHELL` | 用户 Shell（PTY 启动和 Shell 配置检测） |
-| `http_proxy` / `HTTPS_PROXY` 等 | HTTP 代理配置（通过 undici EnvHttpProxyAgent） |
-
-## 五、CLI 命令参数
+| Field | Type | Description |
+|-------|------|-------------|
+| `lang` | string | UI language (zh/en/zh-TW/ko/ja/de/es/fr/it/da/pl/ru/ar/no/pt-BR/th/tr/uk) |
+| `filterIrrelevant` | boolean | Filter irrelevant requests |
+| `expandDiff` | boolean | Expand Body Diff JSON by default |
+| `collapseToolResults` | boolean | Collapse tool results |
+| `expandThinking` | boolean | Expand thinking blocks |
+| `showFullToolContent` | boolean | Show full content |
+| `logDir` | string | Log directory path |
+| `resumeAutoChoice` | null / "continue" / "new" | Auto resume session choice |
+| `disabledPlugins` | string[] | Disabled plugin filenames |
+| `presetShortcuts` | array | Agent Team preset shortcuts |
+
+## 4. Environment Variables
+
+### CX-Viewer Specific
+
+| Variable | Default | Description |
+|----------|---------|-------------|
+| `CXV_LOG_DIR` | `~/.codex/cx-viewer` | Log storage root directory. Special values: `tmp`/`temp` use system temp dir |
+| `CXV_CLI_MODE` | unset | `=1` enables CLI mode (PTY terminal) |
+| `CXV_SDK_MODE` | unset | `=1` enables Codex SDK mode (no terminal) |
+| `CXV_WORKSPACE_MODE` | unset | `=1` enables workspace selection mode |
+| `CXV_PROJECT_DIR` | `process.cwd()` | Project working directory for file operations and Git commands |
+| `CXV_PROXY_PORT` | unset | Local Codex proxy port |
+| `CXV_BYPASS_PERMISSIONS` | unset | `=1` skip tool permission approval with Codex bypass mode |
+| `CXV_DISABLE_DELTA` | unset | `=1` disable incremental log storage, write full messages every time |
+| `CXV_DEBUG` | unset | `=1` enable debug logging |
+| `CXV_DEBUG_PLUGINS` | unset | `=1` enable plugin loading debug logging |
+
+### Internal IPC
+
+| Variable | Description |
+|----------|-------------|
+| `CXVIEWER_PORT` | Server port for ask-bridge/perm-bridge communication |
+| `CXV_EDITOR_PORT` | Server port for cxv-editor file editing bridge |
+
+### External (Read-only)
+
+| Variable | Description |
+|----------|-------------|
+| `OPENAI_BASE_URL` | Custom OpenAI-compatible API base URL |
+| `SHELL` | User's shell (PTY spawn and shell config detection) |
+| `http_proxy` / `HTTPS_PROXY` etc. | HTTP proxy config (via undici EnvHttpProxyAgent) |
+
+## 5. CLI Arguments
 
 ```
-ccv [选项] [claude 参数...]
+cxv [options] [codex args...]
 ```
 
-### CC-Viewer 专有选项
+### CX-Viewer Options
 
-| 参数 | 说明 |
-|------|------|
-| `-logger` | 安装/修复 Claude Code hooks |
-| `--uninstall` / `-uninstall` | 卸载所有 CC-Viewer 集成 |
-| `--help` / `-h` / `help` | 显示帮助信息 |
-| `--version` / `-v` | 显示版本号 |
-| `-SDK` / `--sdk` | 使用 Agent SDK 模式 |
-| `--d` | `--dangerously-skip-permissions` 简写 |
-| `--ad` | `--allow-dangerously-skip-permissions` 简写 |
-| `run` | 通过代理运行命令（`ccv run -- claude ...`） |
+| Argument | Description |
+|----------|-------------|
+| `-logger` | Install/repair Codex logger integration |
+| `--uninstall` / `-uninstall` | Remove all CX-Viewer integration |
+| `--help` / `-h` / `help` | Show help text |
+| `--version` / `-v` | Show version |
+| `-SDK` / `--sdk` | Use Agent SDK mode |
+| `--d` | Shortcut for `--dangerously-bypass-approvals-and-sandbox` |
+| `--ad` | Legacy compatibility flag for CXV-side bypass toggles |
+| `run` | Run command through the CXV wrapper (`cxv run -- codex ...`) |
 
-### Claude 透传参数（常用）
+### Codex Pass-through (common)
 
-| 参数 | 说明 |
-|------|------|
-| `-c` / `--continue` | 继续上一次会话 |
-| `-r` / `--resume` | 恢复指定会话 |
-| `-p` / `--print` | 非交互式输出 |
-| `--model` | 指定模型 |
-| `--permission-mode` | 权限模式 |
-| `--system-prompt` | 自定义系统提示词 |
-| `--max-budget-usd` | 最大预算 |
+| Argument | Description |
+|----------|-------------|
+| `continue` | Resume the last session (`codex resume --last`) |
+| `resume [session-id]` | Resume a specific session |
+| `exec [prompt]` | Non-interactive Codex execution |
+| `--model` | Specify model |
+| `--search` | Enable live web search mode |
+| `-C` / `--cd` | Set working directory |
+| `--sandbox` | Set sandbox mode |
+| `--ask-for-approval` | Set approval policy |
 
-## 六、Hook 配置
+## 6. Hook Configuration
 
-CC-Viewer 自动注册到 `~/.claude/settings.json` 的 `hooks.PreToolUse` 中：
+CX-Viewer's Codex integration primarily uses the local wrapper/proxy path. Hook bridges use current Codex tool names only.
 
-### 1. AskUserQuestion 桥接
-- **匹配器**: `"AskUserQuestion"`
-- **命令**: `node <安装目录>/lib/ask-bridge.js`
-- **作用**: 将 Claude 的问题转发到 Web UI，等待用户回答
+### 1. request_user_input Bridge
+- **Matcher**: `"request_user_input"`
+- **Command**: `node <install_dir>/lib/ask-bridge.js`
+- **Purpose**: Forward tool/user approval prompts to the Web UI when a bridge path is active
 
-### 2. 权限审批桥接
-- **匹配器**: `""` (空 = 匹配所有工具)
-- **命令**: `node <安装目录>/lib/perm-bridge.js`
-- **作用**: 仅 `Bash`/`Edit`/`Write`/`NotebookEdit` 需要 Web UI 审批，其余自动放行
+### 2. Permission Approval Bridge
+- **Matcher**: `""` (empty = match all tools)
+- **Command**: `node <install_dir>/lib/perm-bridge.js`
+- **Purpose**: Mutating or external tools such as `shell_command`, `apply_patch`, `web_search`, and `image_generation` require Web UI approval; others pass through
 
-## 七、Shell 集成
+## 7. Shell Integration
 
-CC-Viewer 在 `~/.zshrc`（或 `.bashrc`）中注入 `claude()` 函数：
+CX-Viewer can inject a `codex()` wrapper into `~/.zshrc` (or `.bashrc`) in logger mode:
 
 ```bash
-# >>> CC-Viewer Auto-Inject >>>
-claude() { ... }
-# <<< CC-Viewer Auto-Inject <<<
+# >>> CX-Viewer Auto-Inject >>>
+codex() { ... }
+# <<< CX-Viewer Auto-Inject <<<
 ```
 
-所有 `claude` 命令自动通过 CC-Viewer 代理，实现日志捕获和 Web UI 功能。
+Interactive `codex` commands are routed through CX-Viewer for log capture and Web UI features, while pass-through commands such as `codex --help` and `codex auth` continue to run directly.
 
-卸载：`ccv --uninstall` 或手动删除标记之间的内容。
+Uninstall: `cxv --uninstall` or manually delete content between the markers.
 
-## 八、代理配置（Proxy Profile）
+## 8. Proxy Configuration (Proxy Profile)
 
-存储在 `<日志目录>/profile.json`，通过 UI 的"代理切换"面板管理。
+Stored in `<log_dir>/profile.json`, managed via the "Proxy Switch" panel in the UI.
 
 ```json
 {
   "active": "max",
   "profiles": [
     { "id": "max", "name": "Default" },
-    { "id": "my-proxy", "name": "自定义", "baseURL": "https://...", "apiKey": "sk-..." }
+    { "id": "my-proxy", "name": "Custom", "baseURL": "https://...", "apiKey": "sk-..." }
   ]
 }
 ```
 
-| 字段 | 说明 |
-|------|------|
-| `active` | 当前激活的配置 ID（`"max"` = 直连，无代理） |
-| `id` | 唯一标识 |
-| `name` | 显示名称 |
-| `baseURL` | 代理 API 地址（替换请求 origin） |
-| `apiKey` | 代理 API 密钥（替换认证头） |
-| `models` | 可用模型列表 |
-| `activeModel` | 当前选中的模型 |
+| Field | Description |
+|-------|-------------|
+| `active` | Active profile ID (`"max"` = direct connection, no proxy) |
+| `id` | Unique identifier |
+| `name` | Display name |
+| `baseURL` | Proxy API address (replaces request origin) |
+| `apiKey` | Proxy API key (replaces auth headers) |
+| `models` | Available model list |
+| `activeModel` | Currently selected model |
 
-## 九、插件系统
+## 9. Plugin System
 
-插件目录：`<日志目录>/plugins/`
+Plugin directory: `<log_dir>/plugins/`
 
-### 支持的 Hook 类型
+### Supported Hook Types
 
-| Hook | 类型 | 说明 |
-|------|------|------|
-| `httpsOptions` | 瀑布 | 提供 HTTPS 证书（返回 `{ cert, key }` 或 `{ pfx }`） |
-| `localUrl` | 瀑布 | 修改本地访问 URL |
-| `serverStarted` | 并行 | 服务器启动通知 |
-| `serverStopping` | 并行 | 服务器停止通知 |
-| `onNewEntry` | 并行 | 新日志条目写入通知 |
+| Hook | Type | Description |
+|------|------|-------------|
+| `httpsOptions` | Waterfall | Provide HTTPS certificate (return `{ cert, key }` or `{ pfx }`) |
+| `localUrl` | Waterfall | Modify local access URL |
+| `serverStarted` | Parallel | Server startup notification |
+| `serverStopping` | Parallel | Server shutdown notification |
+| `onNewEntry` | Parallel | New log entry written notification |
 
-插件启用/禁用通过 `preferences.json` 的 `disabledPlugins` 数组管理。
+Plugin enable/disable managed via `disabledPlugins` array in `preferences.json`.
 
-## 十、目录结构
+## 10. Directory Structure
 
 ```
-~/.claude/cc-viewer/               # 日志根目录
-├── preferences.json               # 用户偏好设置
-├── workspaces.json                # 工作空间注册表
-├── profile.json                   # 代理配置
-├── plugins/                       # 插件目录
+~/.codex/cx-viewer/                # Log root directory
+├── preferences.json               # User preferences
+├── workspaces.json                # Workspace registry
+├── profile.json                   # Proxy configuration
+├── plugins/                       # Plugin directory
 │   └── my-plugin.js
-├── <项目名>/                       # 每个项目的日志目录
-│   ├── <项目名>_20260404_123456.jsonl  # JSONL 日志文件
-│   ├── <项目名>.json              # 统计数据（后台生成）
-│   └── images/                    # 上传图片的持久副本
+├── <project>/                     # Per-project log directory
+│   ├── <project>_20260404_123456.jsonl  # JSONL log files
+│   ├── <project>.json             # Stats data (background generated)
+│   └── images/                    # Persistent uploaded image copies
 └── ...
 
-/tmp/cc-viewer-uploads/            # 临时上传文件目录
+/tmp/cx-viewer-uploads/            # Temporary upload file directory
 ```
 
-## 十一、服务器配置
-
-| 配置 | 值 | 说明 |
-|------|-----|------|
-| 端口范围 | 7008-7099 | 自动扫描可用端口 |
-| 绑定地址 | 0.0.0.0 | 所有网络接口 |
-| 访问令牌 | 随机 16 字节 hex | 局域网访问需要 `?token=xxx`，本机免认证 |
-| HTTPS | 仅通过插件 | 需要插件提供 `httpsOptions` hook |
-| CORS | `*` | 允许所有来源 |
-| 上传限制 | 50MB | 单文件最大上传大小 |
-
-## 十二、URL 参数
-
-| 参数 | 说明 |
-|------|------|
-| `?token=xxx` | 局域网访问认证令牌 |
-| `?logfile=path` | 打开指定历史日志文件（只读模式） |
-
-## 十三、localStorage 配置
-
-| 键 | 说明 |
-|-----|------|
-| `cxv_cacheExpireAt` | 缓存倒计时到期时间 |
-| `cxv_cacheType` | 缓存类型标签 |
-| `ccv_sseSlim` | 启用 SSE 增量裁剪（桌面端性能优化） |
-| `ccv_calibrationModel` | KV-Cache 上下文窗口校准模型 |
-| `ccv_fileExplorerOpen` | 文件浏览器面板开关 |
-| `cc-viewer-terminal-width` | 终端面板宽度（像素） |
+## 11. Server Configuration
+
+| Setting | Value | Description |
+|---------|-------|-------------|
+| Port range | 7008-7099 | Auto-scans for available port |
+| Bind address | 0.0.0.0 | All network interfaces |
+| Access token | Random 16-byte hex | LAN access requires `?token=xxx`; localhost is exempt |
+| HTTPS | Plugin only | Requires plugin providing `httpsOptions` hook |
+| CORS | `*` | All origins allowed |
+| Upload limit | 50MB | Maximum single file upload size |
+
+## 12. URL Parameters
+
+| Parameter | Description |
+|-----------|-------------|
+| `?token=xxx` | LAN access authentication token |
+| `?logfile=path` | Open specific historical log file (read-only mode) |
+
+## 13. localStorage Settings
+
+| Key | Description |
+|-----|-------------|
+| `cxv_viewMode` | Current responsive view mode override |
+| `cxv_fileExplorerOpen` | File explorer panel toggle |
+| `cx-viewer-terminal-width` | Terminal panel width (pixels) |

package/concepts/pt-BR/MainAgent.md

@@ -2,7 +2,7 @@
 
 ## Definição
 
-MainAgent é a cadeia de requisições principal do Claude Code quando não está no modo agent team. Cada interação do usuário com o Claude Code gera uma série de requisições à API, e as requisições do MainAgent formam a cadeia de diálogo central — elas carregam o system prompt completo, definições de ferramentas e histórico de mensagens.
+MainAgent é a cadeia de requisições principal do Codex quando não está no modo agent team. Cada interação do usuário com o Codex gera uma série de requisições à API, e as requisições do MainAgent formam a cadeia de diálogo central — elas carregam o system prompt completo, definições de ferramentas e histórico de mensagens.
 
 ## Como Identificar
 
@@ -11,13 +11,12 @@ No cc-viewer, o MainAgent é identificado por `req.mainAgent === true`, marcado
 Condições de identificação (todas devem ser atendidas):
 - O corpo da requisição contém o campo `system` (system prompt)
 - O corpo da requisição contém o array `tools` (definições de ferramentas)
-- O system prompt contém texto característico de "Claude Code"
+- O system prompt contém texto característico de "Codex"
 
 ## Diferença em Relação ao SubAgent
 
 | Característica | MainAgent | SubAgent |
 |------|-----------|----------|
-| system prompt | Prompt principal completo do Claude Code | Prompt simplificado específico para a tarefa |
+| system prompt | Prompt principal completo do Codex | Prompt simplificado específico para a tarefa |
 | array tools | Contém todas as ferramentas disponíveis | Geralmente contém apenas as poucas ferramentas necessárias para a tarefa |
 | Histórico de mensagens | Acumula o contexto completo da conversa | Contém apenas mensagens relacionadas à subtarefa |
-| Comportamento de cache | Possui prompt caching (TTL de 5 minutos) | Geralmente sem cache ou com cache menor |

package/concepts/pt-BR/ProxySwitch.md

@@ -2,9 +2,9 @@
 
 ## Overview
 
-Hot-Switch Proxy lets you dynamically redirect API requests to a different endpoint without restarting Claude Code. This is useful when using third-party API proxy services.
+Hot-Switch Proxy lets you dynamically redirect Codex/OpenAI API requests to a different endpoint without restarting the current CX Viewer session. This is useful when using a compatible third-party API proxy service.
 
-> ⚠️ Do not use this feature if you are a Claude Max subscriber.
+> Use only with endpoints and keys you are authorized to use. The active profile replaces request authentication and may route prompts, files, and tool context through the configured service.
 
 ## Fields
 
@@ -26,7 +26,7 @@ When a proxy is active, `interceptor.js` performs the following before each API
 
 ## Config File
 
-Configuration is stored at `~/.claude/cc-viewer/profile.json`. Click the folder icon in the title to open the directory:
+Configuration is stored at `~/.codex/cx-viewer/profile.json`. Click the folder icon in the title to open the directory:
 
 ```json
 {

package/concepts/pt-BR/QRCode.md

@@ -2,7 +2,7 @@
 
 ## Como funciona
 
-CC Viewer inicia um servidor HTTP e gera um **endereço LAN** (ex: `http://192.168.1.100:7008`). Escaneie o QR code para acessar o Claude Code do seu celular pela mesma rede WiFi.
+CC Viewer inicia um servidor HTTP e gera um **endereço LAN** (ex: `http://192.168.1.100:7008`). Escaneie o QR code para acessar o Codex do seu celular pela mesma rede WiFi.
 
 ## Por que não consigo conectar?
 

package/concepts/pt-BR/ResponseFields.md

@@ -1,50 +1,38 @@
-# Descrição dos campos do Response Body
+# Response Body Field Reference
 
-Descrição dos campos do corpo de resposta da API Claude `/v1/messages`.
+Field reference for CX-Viewer's normalized Codex response body.
 
-## Campos de nível superior
+## Top-Level Fields
 
-| Campo | Tipo | Descrição |
-|-------|------|-----------|
-| **model** | string | Nome do modelo efetivamente utilizado, ex.: `claude-opus-4-6` |
-| **id** | string | Identificador único desta resposta, ex.: `msg_01Tgsr2QeH8AVXGoP2wAXRvU` |
-| **type** | string | Sempre `"message"` |
-| **role** | string | Sempre `"assistant"` |
-| **content** | array | Array de blocos de conteúdo produzidos pelo modelo, incluindo texto, chamadas de ferramentas, processo de raciocínio, etc. |
-| **stop_reason** | string | Motivo da parada: `"end_turn"` (conclusão normal), `"tool_use"` (necessária execução de ferramenta), `"max_tokens"` (limite de tokens atingido) |
-| **stop_sequence** | string/null | A sequência que acionou a parada, geralmente `null` |
-| **usage** | object | Estatísticas de uso de tokens (veja abaixo) |
+| Field | Type | Description |
+|-------|------|-------------|
+| **model** | string | The model name actually used |
+| **id** | string | Unique response or streamed item identifier when available |
+| **type** | string | Always `"message"` |
+| **role** | string | Always `"assistant"` |
+| **content** | array | Array of content blocks output by the model, containing text, tool calls, thinking process, etc. |
+| **stop_reason** | string | Normalized reason/status for stopping, such as `"end_turn"`, `"completed"`, `"failed"`, or `"max_tokens"` |
+| **stop_sequence** | string/null | The sequence that triggered the stop, usually `null` |
+| **usage** | object | Token usage statistics (see below) |
 
-## Tipos de bloco content
+## content Block Types
 
-| Tipo | Descrição |
-|------|-----------|
-| **text** | Resposta em texto do modelo, contém o campo `text` |
-| **tool_use** | Requisição de chamada de ferramenta, contém `name` (nome da ferramenta), `input` (parâmetros), `id` (ID da chamada, usado para associar ao tool_result) |
-| **thinking** | Conteúdo do raciocínio estendido (aparece apenas com o modo thinking ativado), contém o campo `thinking` |
+| Type | Description |
+|------|-------------|
+| **text** | The model's text reply, contains a `text` field |
+| **tool_use** | Tool call request, contains `name` (tool name), `input` (parameters), `id` (call ID, used to match tool_result) |
+| **thinking** | Extended thinking content (only appears when thinking mode is enabled), contains a `thinking` field |
 
-## Detalhamento dos campos usage
+## usage Field Details
 
-| Campo | Descrição |
-|-------|-----------|
-| **input_tokens** | Número de tokens de entrada não encontrados no cache (cobrados pelo preço integral) |
-| **cache_creation_input_tokens** | Número de tokens para os quais um novo cache foi criado nesta requisição (escrita em cache, custo superior à entrada normal) |
-| **cache_read_input_tokens** | Número de tokens lidos do cache (leitura de cache, custo muito inferior à entrada normal) |
-| **output_tokens** | Número de tokens produzidos pelo modelo |
-| **service_tier** | Nível de serviço, ex.: `"standard"` |
-| **inference_geo** | Região de inferência, ex.: `"not_available"` indica que a informação de região não está disponível |
+| Field | Description |
+|-------|-------------|
+| **output_tokens** | Number of tokens output by the model |
+| **reasoning_output_tokens** | Reasoning tokens when the source reports them |
+| **total_tokens** | Total tokens reported by the source |
 
-## Subcampos de cache_creation
+## stop_reason Meanings
 
-| Campo | Descrição |
-|-------|-----------|
-| **ephemeral_5m_input_tokens** | Número de tokens para criação de cache de curto prazo com TTL de 5 minutos |
-| **ephemeral_1h_input_tokens** | Número de tokens para criação de cache de longo prazo com TTL de 1 hora |
-
-> **Sobre a tarifação do cache**: O preço unitário de `cache_read_input_tokens` é muito inferior ao de `input_tokens`, enquanto o preço unitário de `cache_creation_input_tokens` é ligeiramente superior ao da entrada normal. Portanto, manter uma alta taxa de acerto de cache em conversas contínuas pode reduzir significativamente os custos. Através da métrica "taxa de acerto" do cc-viewer é possível monitorar visualmente essa proporção.
-
-## Significado de stop_reason
-
-- **end_turn**: O modelo concluiu a resposta normalmente
-- **tool_use**: O modelo precisa chamar uma ferramenta; content conterá um bloco `tool_use`. Na próxima requisição é necessário adicionar um `tool_result` em messages para continuar a conversa
-- **max_tokens**: O limite `max_tokens` foi atingido, a resposta foi truncada e pode estar incompleta
+- **end_turn**: The model completed its reply normally
+- **tool_use**: The model needs to call a tool; CX-Viewer shows the matching tool result when the capture source provides it
+- **max_tokens**: The reply was truncated due to reaching the `max_tokens` limit and may be incomplete

package/concepts/pt-BR/SubAgent-Search.md

@@ -1,20 +1,20 @@
 # SubAgent: Search
 
-## Definição
+## Definition
 
-Search é um tipo de sub-agent gerado pelo agente principal do Claude Code para realizar buscas na base de código. Ele executa buscas direcionadas de arquivos e conteúdo usando ferramentas como Glob, Grep e Read, e então retorna os resultados ao agente pai.
+Search is a sub-agent type spawned by Codex's main agent to perform codebase searches. It discovers available search and reading capabilities through `tool_search`, then returns the results to the parent agent.
 
-## Comportamento
+## Behavior
 
-- Gerado automaticamente quando o agente principal precisa buscar ou explorar a base de código
-- Executa em um contexto isolado com acesso somente leitura
-- Usa Glob para correspondência de padrões de arquivos, Grep para busca de conteúdo e Read para inspeção de arquivos
-- Retorna resultados de busca ao agente pai para processamento adicional
+- Spawned automatically when the main agent needs to search or explore the codebase
+- Runs in an isolated context with read-only access
+- Uses current Codex/deferred tools for file pattern matching, content search, and file inspection
+- Returns search results to the parent agent for further processing
 
-## Quando aparece
+## When It Appears
 
-Sub-agents Search tipicamente aparecem quando:
+Search sub-agents typically appear when:
 
-1. O agente principal precisa encontrar arquivos, funções ou padrões de código específicos
-2. Uma exploração ampla da base de código é solicitada pelo usuário
-3. O agente está investigando dependências, referências ou padrões de uso
+1. The main agent needs to find specific files, functions, or code patterns
+2. A broad codebase exploration is requested by the user
+3. The agent is investigating dependencies, references, or usage patterns