feat: add request timeout and retry controls

Author: yuefengw

docs/configuration.md

@@ -31,6 +31,8 @@ Deep Code 使用 `settings.json` 设置文件进行持久化配置，支持两
 | `thinkingEnabled`    | boolean   | 是否启用思考模式（DeepSeek V4 系列默认启用）                         |
 | `reasoningEffort`    | string    | 推理强度，可选 `"high"` 或 `"max"`（默认 `"max"`）                  |
 | `debugLogEnabled`    | boolean   | 是否启用调试日志输出（默认 `false`）                                 |
+| `requestTimeoutMs`   | number    | 主模型请求超时时间，单位毫秒。`0` 表示不启用超时（默认 `0`）           |
+| `maxRetries`         | number    | 主模型请求遇到临时网络错误时的最大重试次数（默认 `2`，最大 `10`）      |
 | `notify`             | string    | 任务完成通知脚本的完整路径（如 Slack 通知脚本）                      |
 | `webSearchTool`      | string    | 自定义联网搜索脚本的完整路径                                         |
 | `mcpServers`         | object    | MCP 服务器配置（键为服务名，值为 McpServerConfig 对象）              |
@@ -45,6 +47,8 @@ Deep Code 使用 `settings.json` 设置文件进行持久化配置，支持两
 | `THINKING_ENABLED`  | string | 是否启用思考模式                                         |
 | `REASONING_EFFORT`  | string | 推理强度                                                |
 | `DEBUG_LOG_ENABLED`  | string | 是否启用调试日志输出                                     |
+| `REQUEST_TIMEOUT_MS` | string | 主模型请求超时时间，单位毫秒。`0` 表示不启用超时          |
+| `MAX_RETRIES`        | string | 主模型请求遇到临时网络错误时的最大重试次数                |
 | `<其他任意KEY>` | string | 自定义环境变量 |
 
 #### `thinkingEnabled` — 思考模式
@@ -130,6 +134,22 @@ MCP（Model Context Protocol）服务器配置。值是键值对，键为服务
 
 设为 `true` 可让程序输出详细的调试日志（默认 `false`），用于排查 API 调用和工具执行的问题。
 
+#### `requestTimeoutMs` 与 `maxRetries` — 请求超时与重试
+
+用于控制主模型 Chat Completion 请求的超时和自动重试：
+
+```json
+{
+  "requestTimeoutMs": 300000,
+  "maxRetries": 2
+}
+```
+
+- `requestTimeoutMs` 单位为毫秒。默认 `0` 表示不启用请求超时，避免长时间思考或长输出被意外中断。
+- `maxRetries` 默认 `2`，最大 `10`。仅对临时错误重试，例如网络断开、请求超时、HTTP `408`、`409`、`425`、`429` 和 `5xx`。
+- 用户主动中断、权限拒绝、HTTP `400`、`401`、`403`、`404` 等配置或请求错误不会自动重试。
+- 也可以通过环境变量配置：`DEEPCODE_REQUEST_TIMEOUT_MS=300000`、`DEEPCODE_MAX_RETRIES=2`。
+
 ## 环境变量优先级
 
 环境变量是配置应用程序的常用方式，尤其适用于敏感信息（如 api-key）或可能在不同环境之间更改的设置。

docs/configuration_en.md

@@ -31,6 +31,8 @@ The following are all the top-level fields supported in `settings.json`, along w
 | `thinkingEnabled`  | boolean | Whether to enable thinking mode (enabled by default for DeepSeek V4 series)|
 | `reasoningEffort`  | string  | Reasoning intensity, either `"high"` or `"max"` (default `"max"`)          |
 | `debugLogEnabled`  | boolean | Enable debug log output (default `false`)                                   |
+| `requestTimeoutMs` | number  | Main model request timeout in milliseconds. `0` disables the timeout (default `0`) |
+| `maxRetries`       | number  | Maximum retry count for transient main model request failures (default `2`, max `10`) |
 | `notify`           | string  | Full path to a task-completion notification script (e.g., Slack notification script) |
 | `webSearchTool`    | string  | Full path to a custom web search script                                     |
 | `mcpServers`       | object  | MCP server configurations (keys are service names, values are McpServerConfig objects) |
@@ -45,6 +47,8 @@ The following are all the top-level fields supported in `settings.json`, along w
 | `THINKING_ENABLED`| string | Enable thinking mode                                            |
 | `REASONING_EFFORT`| string | Reasoning intensity                                             |
 | `DEBUG_LOG_ENABLED`| string| Enable debug log output                                         |
+| `REQUEST_TIMEOUT_MS`| string | Main model request timeout in milliseconds. `0` disables the timeout |
+| `MAX_RETRIES`     | string | Maximum retry count for transient main model request failures   |
 | `<any other KEY>` | string | Custom environment variable                                     |
 
 #### `thinkingEnabled` — Thinking Mode
@@ -129,6 +133,22 @@ For detailed MCP usage instructions, refer to [mcp.md](mcp.md).
 
 Set to `true` to enable detailed debug logging (default `false`), useful for troubleshooting API calls and tool execution.
 
+#### `requestTimeoutMs` and `maxRetries` — Request Timeout and Retries
+
+Controls timeout and automatic retries for main model Chat Completion requests:
+
+```json
+{
+  "requestTimeoutMs": 300000,
+  "maxRetries": 2
+}
+```
+
+- `requestTimeoutMs` is in milliseconds. The default `0` disables request timeout so long thinking or long outputs are not interrupted unexpectedly.
+- `maxRetries` defaults to `2` and is capped at `10`. Retries apply only to transient failures, such as network disconnects, request timeouts, HTTP `408`, `409`, `425`, `429`, and `5xx`.
+- User interrupts, permission denials, HTTP `400`, `401`, `403`, `404`, and other request/configuration errors are not retried.
+- You can also configure these through environment variables: `DEEPCODE_REQUEST_TIMEOUT_MS=300000`, `DEEPCODE_MAX_RETRIES=2`.
+
 ## Environment Variable Priority
 
 Environment variables are a common way to configure applications, especially for sensitive information (such as api-key) or settings that may change between environments.
@@ -181,4 +201,4 @@ Applied in the following priority order (lower-numbered overridden by higher-num
 2. User-level settings.json: `{"env": {"MCP_GITHUB_PERSONAL_ACCESS_TOKEN": "..."}}`
 3. Project-level settings.json: `{"mcpServers":{"github":{"env":{"GITHUB_PERSONAL_ACCESS_TOKEN":"..."}}}}`
 4. Project-level settings.json: `{"env": {"MCP_GITHUB_PERSONAL_ACCESS_TOKEN": "..."}}`
-5. System environment variable: `DEEPCODE_MCP_GITHUB_PERSONAL_ACCESS_TOKEN=... deepcode`
+5. System environment variable: `DEEPCODE_MCP_GITHUB_PERSONAL_ACCESS_TOKEN=... deepcode`

src/common/openai-client.ts

@@ -26,6 +26,8 @@ export function createOpenAIClient(projectRoot: string = process.cwd()): {
   thinkingEnabled: boolean;
   reasoningEffort: "high" | "max";
   debugLogEnabled: boolean;
+  requestTimeoutMs: number;
+  maxRetries: number;
   notify?: string;
   webSearchTool?: string;
   env: Record<string, string>;
@@ -40,6 +42,8 @@ export function createOpenAIClient(projectRoot: string = process.cwd()): {
       thinkingEnabled: settings.thinkingEnabled,
       reasoningEffort: settings.reasoningEffort,
       debugLogEnabled: settings.debugLogEnabled,
+      requestTimeoutMs: settings.requestTimeoutMs,
+      maxRetries: settings.maxRetries,
       notify: settings.notify,
       webSearchTool: settings.webSearchTool,
       env: settings.env,
@@ -56,6 +60,8 @@ export function createOpenAIClient(projectRoot: string = process.cwd()): {
       thinkingEnabled: settings.thinkingEnabled,
       reasoningEffort: settings.reasoningEffort,
       debugLogEnabled: settings.debugLogEnabled,
+      requestTimeoutMs: settings.requestTimeoutMs,
+      maxRetries: settings.maxRetries,
       notify: settings.notify,
       webSearchTool: settings.webSearchTool,
       env: settings.env,
@@ -91,6 +97,8 @@ export function createOpenAIClient(projectRoot: string = process.cwd()): {
     thinkingEnabled: settings.thinkingEnabled,
     reasoningEffort: settings.reasoningEffort,
     debugLogEnabled: settings.debugLogEnabled,
+    requestTimeoutMs: settings.requestTimeoutMs,
+    maxRetries: settings.maxRetries,
     notify: settings.notify,
     webSearchTool: settings.webSearchTool,
     env: settings.env,