feat: auto-select model/reasoning and add persistent user config

CLAUDE.md

@@ -35,6 +35,7 @@ codex-collab health
 - Communicates with Codex via `codex app-server` JSON-RPC protocol over stdio
 - Threads stored in `~/.codex-collab/threads.json` as short ID → full ID mapping
 - Logs stored in `~/.codex-collab/logs/` per thread
+- User defaults stored in `~/.codex-collab/config.json` (model, reasoning, sandbox, approval, timeout)
 - Approval requests use file-based IPC in `~/.codex-collab/approvals/`
 - Short IDs are 8-char hex, support prefix resolution
 - Bun is the TypeScript runtime — never use npm/yarn/pnpm for running

README.md

@@ -105,8 +105,8 @@ codex-collab run --resume <id> "now check error handling" --content-only
 | Flag | Description |
 |------|-------------|
 | `-d, --dir <path>` | Working directory |
-| `-m, --model <model>` | Model name |
-| `-r, --reasoning <level>` | low, medium, high, xhigh (default: xhigh) |
+| `-m, --model <model>` | Model name (default: auto — latest available) |
+| `-r, --reasoning <level>` | low, medium, high, xhigh (default: auto — highest for model) |
 | `-s, --sandbox <mode>` | read-only, workspace-write, danger-full-access (default: workspace-write; review always uses read-only) |
 | `--mode <mode>` | Review mode: pr, uncommitted, commit, custom |
 | `--ref <hash>` | Commit ref for `--mode commit` |
@@ -118,6 +118,39 @@ codex-collab run --resume <id> "now check error handling" --content-only
 
 </details>
 
+## Defaults & Configuration
+
+By default, codex-collab auto-selects the **latest model** (preferring `-codex` variants) and the **highest reasoning effort** supported by that model. No configuration needed — it stays current as new models are released.
+
+To override defaults persistently, use `codex-collab config`:
+
+```bash
+# Show current config
+codex-collab config
+
+# Set a preferred model
+codex-collab config model gpt-5.3-codex
+
+# Set default reasoning effort
+codex-collab config reasoning high
+
+# Unset a key (return to auto-detection)
+codex-collab config model --unset
+
+# Unset all keys
+codex-collab config --unset
+```
+
+Available keys: `model`, `reasoning`, `sandbox`, `approval`, `timeout`
+
+CLI flags always take precedence over config, and config takes precedence over auto-detection:
+
+```
+CLI flag  >  config file  >  auto-detected
+```
+
+Config is stored in `~/.codex-collab/config.json`.
+
 ## Contributing
 
 See [CONTRIBUTING.md](CONTRIBUTING.md) for development setup and guidelines. This project follows the [Contributor Covenant](CODE_OF_CONDUCT.md) code of conduct.

README.zh-CN.md

@@ -105,8 +105,8 @@ codex-collab run --resume <id> "现在检查错误处理" --content-only
 | 参数 | 说明 |
 |------|------|
 | `-d, --dir <path>` | 工作目录 |
-| `-m, --model <model>` | 模型名称 |
-| `-r, --reasoning <level>` | low, medium, high, xhigh（默认: xhigh） |
+| `-m, --model <model>` | 模型名称（默认: 自动选择最新可用模型） |
+| `-r, --reasoning <level>` | low, medium, high, xhigh（默认: 自动选择模型支持的最高级别） |
 | `-s, --sandbox <mode>` | read-only, workspace-write, danger-full-access（默认: workspace-write；review 始终使用 read-only） |
 | `--mode <mode>` | 审查模式: pr, uncommitted, commit, custom |
 | `--ref <hash>` | 指定 commit 哈希（配合 `--mode commit`） |
@@ -118,6 +118,26 @@ codex-collab run --resume <id> "现在检查错误处理" --content-only
 
 </details>
 
+## 默认值与配置
+
+默认情况下，codex-collab 自动选择**最新模型**（优先选择 `-codex` 变体）及该模型支持的**最高推理级别**。无需配置——新模型发布后自动更新。
+
+使用 `codex-collab config` 持久化覆盖默认值：
+
+```bash
+codex-collab config                     # 查看当前配置
+codex-collab config model gpt-5.3-codex # 设置默认模型
+codex-collab config reasoning high      # 设置默认推理级别
+codex-collab config model --unset       # 取消单个设置（恢复自动检测）
+codex-collab config --unset             # 取消所有设置
+```
+
+可配置项: `model`、`reasoning`、`sandbox`、`approval`、`timeout`
+
+优先级: `CLI 参数 > 配置文件 > 自动检测`
+
+配置存储于 `~/.codex-collab/config.json`。
+
 ## 参与贡献
 
 欢迎贡献！开发环境搭建及贡献流程详见 [CONTRIBUTING.md](CONTRIBUTING.md)。本项目遵循 [Contributor Covenant](CODE_OF_CONDUCT.md) 行为准则。

SKILL.md

@@ -106,7 +106,7 @@ codex-collab progress <id>
 
 Progress lines stream in real-time during execution:
 ```
-[codex] Thread a1b2c3d4 started (gpt-5.3-codex, workspace-write)
+[codex] Thread a1b2c3d4 started (gpt-5.4, workspace-write)
 [codex] Turn started
 [codex] Running: npm test
 [codex] Edited: src/auth.ts (update)
@@ -177,6 +177,10 @@ codex-collab clean                      # Delete old logs and stale mappings
 ### Utility
 
 ```bash
+codex-collab config                     # Show persistent defaults
+codex-collab config model gpt-5.3-codex # Set default model
+codex-collab config model --unset       # Unset a key (return to auto)
+codex-collab config --unset             # Unset all keys (return to auto)
 codex-collab models                     # List available models
 codex-collab approve <id>              # Approve a pending request
 codex-collab decline <id>              # Decline a pending request
@@ -187,8 +191,8 @@ codex-collab health                     # Check prerequisites
 
 | Flag | Description |
 |------|-------------|
-| `-m, --model <model>` | Model name (default: gpt-5.3-codex) |
-| `-r, --reasoning <level>` | Reasoning effort: low, medium, high, xhigh (default: xhigh) |
+| `-m, --model <model>` | Model name (default: auto — latest available) |
+| `-r, --reasoning <level>` | Reasoning effort: low, medium, high, xhigh (default: auto — highest for model) |
 | `-s, --sandbox <mode>` | Sandbox: read-only, workspace-write, danger-full-access (default: workspace-write; review always uses read-only) |
 | `-d, --dir <path>` | Working directory (default: cwd) |
 | `--resume <id>` | Resume existing thread (run and review) |