test(acp): update filesystem tests for error code-based ENOENT handling

fix(cli): isolate modelConfigUtils tests from system env vars

README.md

@@ -25,7 +25,7 @@ Qwen Code is an open-source AI agent for the terminal, optimized for [Qwen3-Code
 - **OpenAI-compatible, OAuth free tier**: use an OpenAI-compatible API, or sign in with Qwen OAuth to get 2,000 free requests/day.
 - **Open-source, co-evolving**: both the framework and the Qwen3-Coder model are open-source—and they ship and evolve together.
 - **Agentic workflow, feature-rich**: rich built-in tools (Skills, SubAgents, Plan Mode) for a full agentic workflow and a Claude Code-like experience.
-- **Terminal-first, IDE-friendly**: built for developers who live in the command line, with optional integration for VS Code and Zed.
+- **Terminal-first, IDE-friendly**: built for developers who live in the command line, with optional integration for VS Code, Zed, and JetBrains IDEs.
 
 ## Installation
 
@@ -137,10 +137,11 @@ Use `-p` to run Qwen Code without the interactive UI—ideal for scripts, automa
 
 #### IDE integration
 
-Use Qwen Code inside your editor (VS Code and Zed):
+Use Qwen Code inside your editor (VS Code, Zed, and JetBrains IDEs):
 
 - [Use in VS Code](https://qwenlm.github.io/qwen-code-docs/en/users/integration-vscode/)
 - [Use in Zed](https://qwenlm.github.io/qwen-code-docs/en/users/integration-zed/)
+- [Use in JetBrains IDEs](https://qwenlm.github.io/qwen-code-docs/en/users/integration-jetbrains/)
 
 #### TypeScript SDK
 
@@ -200,6 +201,11 @@ If you encounter issues, check the [troubleshooting guide](https://qwenlm.github
 
 To report a bug from within the CLI, run `/bug` and include a short title and repro steps.
 
+## Connect with Us
+
+- Discord: https://discord.gg/ycKBjdNd
+- Dingtalk: https://qr.dingtalk.com/action/joingroup?code=v1,k1,+FX6Gf/ZDlTahTIRi8AEQhIaBlqykA0j+eBKKdhLeAE=&_dt_no_comment=1&origin=1
+
 ## Acknowledgments
 
 This project is based on [Google Gemini CLI](https://github.com/google-gemini/gemini-cli). We acknowledge and appreciate the excellent work of the Gemini CLI team. Our main contribution focuses on parser-level adaptations to better support Qwen-Coder models.

docs/developers/tools/_meta.ts

@@ -10,4 +10,5 @@ export default {
   'web-search': 'Web Search',
   memory: 'Memory',
   'mcp-server': 'MCP Servers',
+  sandbox: 'Sandboxing',
 };

docs/developers/tools/sandbox.md

@@ -0,0 +1,90 @@
+## Customizing the sandbox environment (Docker/Podman)
+
+### Currently, the project does not support the use of the BUILD_SANDBOX function after installation through the npm package
+
+1. To build a custom sandbox, you need to access the build scripts (scripts/build_sandbox.js) in the source code repository.
+2. These build scripts are not included in the packages released by npm.
+3. The code contains hard-coded path checks that explicitly reject build requests from non-source code environments.
+
+If you need extra tools inside the container (e.g., `git`, `python`, `rg`), create a custom Dockerfile, The specific operation is as follows
+
+#### 1、Clone qwen code project first, https://github.com/QwenLM/qwen-code.git
+
+#### 2、Make sure you perform the following operation in the source code repository directory
+
+```bash
+# 1. First, install the dependencies of the project
+npm install
+
+# 2. Build the Qwen Code project
+npm run build
+
+# 3. Verify that the dist directory has been generated
+ls -la packages/cli/dist/
+
+# 4. Create a global link in the CLI package directory
+cd packages/cli
+npm link
+
+# 5. Verification link (it should now point to the source code)
+which qwen
+# Expected output: /xxx/xxx/.nvm/versions/node/v24.11.1/bin/qwen
+# Or similar paths, but it should be a symbolic link
+
+# 6. For details of the symbolic link, you can see the specific source code path
+ls -la $(dirname $(which qwen))/../lib/node_modules/@qwen-code/qwen-code
+# It should show that this is a symbolic link pointing to your source code directory
+
+# 7.Test the version of qwen
+qwen -v
+# npm link will overwrite the global qwen. To avoid being unable to distinguish the same version number, you can uninstall the global CLI first
+```
+
+#### 3、Create your sandbox Dockerfile under the root directory of your own project
+
+- Path: `.qwen/sandbox.Dockerfile`
+
+- Official mirror image address:https://github.com/QwenLM/qwen-code/pkgs/container/qwen-code
+
+```bash
+# Based on the official Qwen sandbox image (It is recommended to explicitly specify the version)
+FROM ghcr.io/qwenlm/qwen-code:sha-570ec43
+# Add your extra tools here
+RUN apt-get update && apt-get install -y \
+    git \
+    python3 \
+    ripgrep
+```
+
+#### 4、Create the first sandbox image under the root directory of your project
+
+```bash
+GEMINI_SANDBOX=docker BUILD_SANDBOX=1 qwen -s
+# Observe whether the sandbox version of the tool you launched is consistent with the version of your custom image. If they are consistent, the startup will be successful
+```
+
+This builds a project-specific image based on the default sandbox image.
+
+#### Remove npm link
+
+- If you want to restore the official CLI of qwen, please remove the npm link
+
+```bash
+# Method 1: Unlink globally
+npm unlink -g @qwen-code/qwen-code
+
+# Method 2: Remove it in the packages/cli directory
+cd packages/cli
+npm unlink
+
+# Verification has been lifted
+which qwen
+# It should display "qwen not found"
+
+# Reinstall the global version if necessary
+npm install -g @qwen-code/qwen-code
+
+# Verification Recovery
+which qwen
+qwen --version
+```

docs/users/_meta.ts

@@ -12,6 +12,7 @@ export default {
   },
   'integration-vscode': 'Visual Studio Code',
   'integration-zed': 'Zed IDE',
+  'integration-jetbrains': 'JetBrains IDEs',
   'integration-github-action': 'Github Actions',
   'Code with Qwen Code': {
     type: 'separator',

docs/users/configuration/auth.md

@@ -5,11 +5,13 @@ Qwen Code supports two authentication methods. Pick the one that matches how you
 - **Qwen OAuth (recommended)**: sign in with your `qwen.ai` account in a browser.
 - **OpenAI-compatible API**: use an API key (OpenAI or any OpenAI-compatible provider / endpoint).
 
+![](https://img.alicdn.com/imgextra/i2/O1CN01IxI1bt1sNO543AVTT_!!6000000005754-0-tps-1958-822.jpg)
+
 ## Option 1: Qwen OAuth (recommended & free) 👍
 
-Use this if you want the simplest setup and you’re using Qwen models.
+Use this if you want the simplest setup and you're using Qwen models.
 
-- **How it works**: on first start, Qwen Code opens a browser login page. After you finish, credentials are cached locally so you usually won’t need to log in again.
+- **How it works**: on first start, Qwen Code opens a browser login page. After you finish, credentials are cached locally so you usually won't need to log in again.
 - **Requirements**: a `qwen.ai` account + internet access (at least for the first login).
 - **Benefits**: no API key management, automatic credential refresh.
 - **Cost & quota**: free, with a quota of **60 requests/minute** and **2,000 requests/day**.
@@ -24,15 +26,54 @@ qwen
 
 Use this if you want to use OpenAI models or any provider that exposes an OpenAI-compatible API (e.g. OpenAI, Azure OpenAI, OpenRouter, ModelScope, Alibaba Cloud Bailian, or a self-hosted compatible endpoint).
 
-### Quick start (interactive, recommended for local use)
+### Recommended: Coding Plan (subscription-based) 🚀
 
-When you choose the OpenAI-compatible option in the CLI, it will prompt you for:
+Use this if you want predictable costs with higher usage quotas for the qwen3-coder-plus model.
 
-- **API key**
-- **Base URL** (default: `https://api.openai.com/v1`)
-- **Model** (default: `gpt-4o`)
+> [!IMPORTANT]
+>
+> Coding Plan is only available for users in China mainland (Beijing region).
 
-> **Note:** the CLI may display the key in plain text for verification. Make sure your terminal is not being recorded or shared.
+- **How it works**: subscribe to the Coding Plan with a fixed monthly fee, then configure Qwen Code to use the dedicated endpoint and your subscription API key.
+- **Requirements**: an active Coding Plan subscription from [Alibaba Cloud Bailian](https://bailian.console.aliyun.com/cn-beijing/?tab=globalset#/efm/coding_plan).
+- **Benefits**: higher usage quotas, predictable monthly costs, access to latest qwen3-coder-plus model.
+- **Cost & quota**: varies by plan (see table below).
+
+#### Coding Plan Pricing & Quotas
+
+| Feature             | Lite Basic Plan       | Pro Advanced Plan     |
+| :------------------ | :-------------------- | :-------------------- |
+| **Price**           | ¥40/month             | ¥200/month            |
+| **5-Hour Limit**    | Up to 1,200 requests  | Up to 6,000 requests  |
+| **Weekly Limit**    | Up to 9,000 requests  | Up to 45,000 requests |
+| **Monthly Limit**   | Up to 18,000 requests | Up to 90,000 requests |
+| **Supported Model** | qwen3-coder-plus      | qwen3-coder-plus      |
+
+#### Quick Setup for Coding Plan
+
+When you select the OpenAI-compatible option in the CLI, enter these values:
+
+- **API key**: `sk-sp-xxxxx`
+- **Base URL**: `https://coding.dashscope.aliyuncs.com/v1`
+- **Model**: `qwen3-coder-plus`
+
+> **Note**: Coding Plan API keys have the format `sk-sp-xxxxx`, which is different from standard Alibaba Cloud API keys.
+
+#### Configure via Environment Variables
+
+Set these environment variables to use Coding Plan:
+
+```bash
+export OPENAI_API_KEY="your-coding-plan-api-key"  # Format: sk-sp-xxxxx
+export OPENAI_BASE_URL="https://coding.dashscope.aliyuncs.com/v1"
+export OPENAI_MODEL="qwen3-coder-plus"
+```
+
+For more details about Coding Plan, including subscription options and troubleshooting, see the [full Coding Plan documentation](https://bailian.console.aliyun.com/cn-beijing/?tab=doc#/doc/?type=model&url=3005961).
+
+### Other OpenAI-compatible Providers
+
+If you are using other providers (OpenAI, Azure, local LLMs, etc.), use the following configuration methods.
 
 ### Configure via command-line arguments
 

docs/users/configuration/settings.md

@@ -104,7 +104,7 @@ Settings are organized into categories. All settings should be placed within the
 | `model.name`                                       | string  | The Qwen model to use for conversations.                                                                                                                                                                                                                                                                                                                               | `undefined` |
 | `model.maxSessionTurns`                            | number  | Maximum number of user/model/tool turns to keep in a session. -1 means unlimited.                                                                                                                                                                                                                                                                                      | `-1`        |
 | `model.summarizeToolOutput`                        | object  | Enables or disables the summarization of tool output. You can specify the token budget for the summarization using the `tokenBudget` setting. Note: Currently only the `run_shell_command` tool is supported. For example `{"run_shell_command": {"tokenBudget": 2000}}`                                                                                               | `undefined` |
-| `model.generationConfig`                           | object  | Advanced overrides passed to the underlying content generator. Supports request controls such as `timeout`, `maxRetries`, and `disableCacheControl`, along with fine-tuning knobs under `samplingParams` (for example `temperature`, `top_p`, `max_tokens`). Leave unset to rely on provider defaults.                                                                 | `undefined` |
+| `model.generationConfig`                           | object  | Advanced overrides passed to the underlying content generator. Supports request controls such as `timeout`, `maxRetries`, `disableCacheControl`, and `customHeaders` (custom HTTP headers for API requests), along with fine-tuning knobs under `samplingParams` (for example `temperature`, `top_p`, `max_tokens`). Leave unset to rely on provider defaults.         | `undefined` |
 | `model.chatCompression.contextPercentageThreshold` | number  | Sets the threshold for chat history compression as a percentage of the model's total token limit. This is a value between 0 and 1 that applies to both automatic compression and the manual `/compress` command. For example, a value of `0.6` will trigger compression when the chat history exceeds 60% of the token limit. Use `0` to disable compression entirely. | `0.7`       |
 | `model.skipNextSpeakerCheck`                       | boolean | Skip the next speaker check.                                                                                                                                                                                                                                                                                                                                           | `false`     |
 | `model.skipLoopDetection`                          | boolean | Disables loop detection checks. Loop detection prevents infinite loops in AI responses but can generate false positives that interrupt legitimate workflows. Enable this option if you experience frequent false positive loop detection interruptions.                                                                                                                | `false`     |
@@ -114,12 +114,16 @@ Settings are organized into categories. All settings should be placed within the
 
 **Example model.generationConfig:**
 
-```
+```json
 {
   "model": {
     "generationConfig": {
       "timeout": 60000,
       "disableCacheControl": false,
+      "customHeaders": {
+        "X-Request-ID": "req-123",
+        "X-User-ID": "user-456"
+      },
       "samplingParams": {
         "temperature": 0.2,
         "top_p": 0.8,
@@ -130,6 +134,8 @@ Settings are organized into categories. All settings should be placed within the
 }
 ```
 
+The `customHeaders` field allows you to add custom HTTP headers to all API requests. This is useful for request tracing, monitoring, API gateway routing, or when different models require different headers. If `customHeaders` is defined in `modelProviders[].generationConfig.customHeaders`, it will be used directly; otherwise, headers from `model.generationConfig.customHeaders` will be used. No merging occurs between the two levels.
+
 **model.openAILoggingDir examples:**
 
 - `"~/qwen-logs"` - Logs to `~/qwen-logs` directory
@@ -154,6 +160,10 @@ Use `modelProviders` to declare curated model lists per auth type that the `/mod
         "generationConfig": {
           "timeout": 60000,
           "maxRetries": 3,
+          "customHeaders": {
+            "X-Model-Version": "v1.0",
+            "X-Request-Priority": "high"
+          },
           "samplingParams": { "temperature": 0.2 }
         }
       }
@@ -215,7 +225,7 @@ Per-field precedence for `generationConfig`:
 3. `settings.model.generationConfig`
 4. Content-generator defaults (`getDefaultGenerationConfig` for OpenAI, `getParameterValue` for Gemini, etc.)
 
-`samplingParams` is treated atomically; provider values replace the entire object. Defaults from the content generator apply last so each provider retains its tuned baseline.
+`samplingParams` and `customHeaders` are both treated atomically; provider values replace the entire object. If `modelProviders[].generationConfig` defines these fields, they are used directly; otherwise, values from `model.generationConfig` are used. No merging occurs between provider and global configuration levels. Defaults from the content generator apply last so each provider retains its tuned baseline.
 
 ##### Selection persistence and recommendations
 
@@ -231,7 +241,6 @@ Per-field precedence for `generationConfig`:
 | ------------------------------------------------- | -------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------- |
 | `context.fileName`                                | string or array of strings | The name of the context file(s).                                                                                                                                                                                                                                                                                                                                      | `undefined` |
 | `context.importFormat`                            | string                     | The format to use when importing memory.                                                                                                                                                                                                                                                                                                                              | `undefined` |
-| `context.discoveryMaxDirs`                        | number                     | Maximum number of directories to search for memory.                                                                                                                                                                                                                                                                                                                   | `200`       |
 | `context.includeDirectories`                      | array                      | Additional directories to include in the workspace context. Specifies an array of additional absolute or relative paths to include in the workspace context. Missing directories will be skipped with a warning by default. Paths can use `~` to refer to the user's home directory. This setting can be combined with the `--include-directories` command-line flag. | `[]`        |
 | `context.loadFromIncludeDirectories`              | boolean                    | Controls the behavior of the `/memory refresh` command. If set to `true`, `QWEN.md` files should be loaded from all directories that are added. If set to `false`, `QWEN.md` should only be loaded from the current directory.                                                                                                                                        | `false`     |
 | `context.fileFiltering.respectGitIgnore`          | boolean                    | Respect .gitignore files when searching.                                                                                                                                                                                                                                                                                                                              | `true`      |
@@ -301,6 +310,12 @@ If you are experiencing performance issues with file searching (e.g., with `@` c
 >
 > **Note about advanced.tavilyApiKey:** This is a legacy configuration format. For Qwen OAuth users, DashScope provider is automatically available without any configuration. For other authentication types, configure Tavily or Google providers using the new `webSearch` configuration format.
 
+#### experimental
+
+| Setting               | Type    | Description                      | Default |
+| --------------------- | ------- | -------------------------------- | ------- |
+| `experimental.skills` | boolean | Enable experimental Agent Skills | `false` |
+
 #### mcpServers
 
 Configures connections to one or more Model-Context Protocol (MCP) servers for discovering and using custom tools. Qwen Code attempts to connect to each configured MCP server to discover available tools. If multiple MCP servers expose a tool with the same name, the tool names will be prefixed with the server alias you defined in the configuration (e.g., `serverAlias__actualToolName`) to avoid conflicts. Note that the system might strip certain schema properties from MCP tool definitions for compatibility. At least one of `command`, `url`, or `httpUrl` must be provided. If multiple are specified, the order of precedence is `httpUrl`, then `url`, then `command`.
@@ -470,7 +485,7 @@ Arguments passed directly when running the CLI can override other configurations
 | `--telemetry-otlp-protocol`  |       | Sets the OTLP protocol for telemetry (`grpc` or `http`).                                                                                                                                |                                        | Defaults to `grpc`. See [telemetry](../../developers/development/telemetry) for more information.                                                                                                                                                                                                                                                                                                                                                                                                                                                               |
 | `--telemetry-log-prompts`    |       | Enables logging of prompts for telemetry.                                                                                                                                               |                                        | See [telemetry](../../developers/development/telemetry) for more information.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   |
 | `--checkpointing`            |       | Enables [checkpointing](../features/checkpointing).                                                                                                                                     |                                        |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 |
-| `--acp`                      |       | Enables ACP mode (Agent Control Protocol). Useful for IDE/editor integrations like [Zed](../integration-zed).                                                                           |                                        | Stable. Replaces the deprecated `--experimental-acp` flag.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      |
+| `--acp`                      |       | Enables ACP mode (Agent Client Protocol). Useful for IDE/editor integrations like [Zed](../integration-zed).                                                                            |                                        | Stable. Replaces the deprecated `--experimental-acp` flag.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      |
 | `--experimental-skills`      |       | Enables experimental [Agent Skills](../features/skills) (registers the `skill` tool and loads Skills from `.qwen/skills/` and `~/.qwen/skills/`).                                       |                                        | Experimental.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   |
 | `--extensions`               | `-e`  | Specifies a list of extensions to use for the session.                                                                                                                                  | Extension names                        | If not provided, all available extensions are used. Use the special term `qwen -e none` to disable all extensions. Example: `qwen -e my-extension -e my-other-extension`                                                                                                                                                                                                                                                                                                                                                                                        |
 | `--list-extensions`          | `-l`  | Lists all available extensions and exits.                                                                                                                                               |                                        |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 |
@@ -519,16 +534,13 @@ Here's a conceptual example of what a context file at the root of a TypeScript p
 
 This example demonstrates how you can provide general project context, specific coding conventions, and even notes about particular files or components. The more relevant and precise your context files are, the better the AI can assist you. Project-specific context files are highly encouraged to establish conventions and context.
 
-- **Hierarchical Loading and Precedence:** The CLI implements a sophisticated hierarchical memory system by loading context files (e.g., `QWEN.md`) from several locations. Content from files lower in this list (more specific) typically overrides or supplements content from files higher up (more general). The exact concatenation order and final context can be inspected using the `/memory show` command. The typical loading order is:
+- **Hierarchical Loading and Precedence:** The CLI implements a hierarchical memory system by loading context files (e.g., `QWEN.md`) from several locations. Content from files lower in this list (more specific) typically overrides or supplements content from files higher up (more general). The exact concatenation order and final context can be inspected using the `/memory show` command. The typical loading order is:
   1. **Global Context File:**
      - Location: `~/.qwen/<configured-context-filename>` (e.g., `~/.qwen/QWEN.md` in your user home directory).
      - Scope: Provides default instructions for all your projects.
   2. **Project Root & Ancestors Context Files:**
      - Location: The CLI searches for the configured context file in the current working directory and then in each parent directory up to either the project root (identified by a `.git` folder) or your home directory.
      - Scope: Provides context relevant to the entire project or a significant portion of it.
-  3. **Sub-directory Context Files (Contextual/Local):**
-     - Location: The CLI also scans for the configured context file in subdirectories _below_ the current working directory (respecting common ignore patterns like `node_modules`, `.git`, etc.). The breadth of this search is limited to 200 directories by default, but can be configured with the `context.discoveryMaxDirs` setting in your `settings.json` file.
-     - Scope: Allows for highly specific instructions relevant to a particular component, module, or subsection of your project.
 - **Concatenation & UI Indication:** The contents of all found context files are concatenated (with separators indicating their origin and path) and provided as part of the system prompt. The CLI footer displays the count of loaded context files, giving you a quick visual cue about the active instructional context.
 - **Importing Content:** You can modularize your context files by importing other Markdown files using the `@path/to/file.md` syntax. For more details, see the [Memory Import Processor documentation](../configuration/memory).
 - **Commands for Memory Management:**

docs/users/features/commands.md

@@ -59,6 +59,7 @@ Commands for managing AI tools and models.
 | ---------------- | --------------------------------------------- | --------------------------------------------- |
 | `/mcp`           | List configured MCP servers and tools         | `/mcp`, `/mcp desc`                           |
 | `/tools`         | Display currently available tool list         | `/tools`, `/tools desc`                       |
+| `/skills`        | List and run available skills (experimental)  | `/skills`, `/skills <name>`                   |
 | `/approval-mode` | Change approval mode for tool usage           | `/approval-mode <mode (auto-edit)> --project` |
 | →`plan`          | Analysis only, no execution                   | Secure review                                 |
 | →`default`       | Require approval for edits                    | Daily use                                     |

docs/users/features/sandbox.md

@@ -166,15 +166,6 @@ export SANDBOX_SET_UID_GID=true   # Force host UID/GID
 export SANDBOX_SET_UID_GID=false  # Disable UID/GID mapping
 ```
 
-## Customizing the sandbox environment (Docker/Podman)
-
-If you need extra tools inside the container (e.g., `git`, `python`, `rg`), create a custom Dockerfile:
-
-- Path: `.qwen/sandbox.Dockerfile`
-- Then run with: `BUILD_SANDBOX=1 qwen -s ...`
-
-This builds a project-specific image based on the default sandbox image.
-
 ## Troubleshooting
 
 ### Common issues

docs/users/features/skills.md

@@ -11,12 +11,29 @@ This guide shows you how to create, use, and manage Agent Skills in **Qwen Code*
 ## Prerequisites
 
 - Qwen Code (recent version)
-- Run with the experimental flag enabled:
+
+## How to enable
+
+### Via CLI flag
 
 ```bash
 qwen --experimental-skills
 ```
 
+### Via settings.json
+
+Add to your `~/.qwen/settings.json` or project's `.qwen/settings.json`:
+
+```json
+{
+  "tools": {
+    "experimental": {
+      "skills": true
+    }
+  }
+}
+```
+
 - Basic familiarity with Qwen Code ([Quickstart](../quickstart.md))
 
 ## What are Agent Skills?
@@ -27,6 +44,14 @@ Agent Skills package expertise into discoverable capabilities. Each Skill consis
 
 Skills are **model-invoked** — the model autonomously decides when to use them based on your request and the Skill’s description. This is different from slash commands, which are **user-invoked** (you explicitly type `/command`).
 
+If you want to invoke a Skill explicitly, use the `/skills` slash command:
+
+```bash
+/skills <skill-name>
+```
+
+The `/skills` command is only available when you run with `--experimental-skills`. Use autocomplete to browse available Skills and descriptions.
+
 ### Benefits
 
 - Extend Qwen Code for your workflows

docs/users/integration-jetbrains.md

@@ -0,0 +1,57 @@
+# JetBrains IDEs
+
+> JetBrains IDEs provide native support for AI coding assistants through the Agent Client Protocol (ACP). This integration allows you to use Qwen Code directly within your JetBrains IDE with real-time code suggestions.
+
+### Features
+
+- **Native agent experience**: Integrated AI assistant panel within your JetBrains IDE
+- **Agent Client Protocol**: Full support for ACP enabling advanced IDE interactions
+- **Symbol management**: #-mention files to add them to the conversation context
+- **Conversation history**: Access to past conversations within the IDE
+
+### Requirements
+
+- JetBrains IDE with ACP support (IntelliJ IDEA, WebStorm, PyCharm, etc.)
+- Qwen Code CLI installed
+
+### Installation
+
+1. Install Qwen Code CLI:
+
+   ```bash
+   npm install -g @qwen-code/qwen-code
+   ```
+
+2. Open your JetBrains IDE and navigate to AI Chat tool window.
+
+3. Click the 3-dot menu in the upper-right corner and select **Configure ACP Agent** and configure Qwen Code with the following settings:
+
+```json
+{
+  "agent_servers": {
+    "qwen": {
+      "command": "/path/to/qwen",
+      "args": ["--acp"],
+      "env": {}
+    }
+  }
+}
+```
+
+4. The Qwen Code agent should now be available in the AI Assistant panel
+
+![Qwen Code in JetBrains AI Chat](https://img.alicdn.com/imgextra/i3/O1CN01ZxYel21y433Ci6eg0_!!6000000006524-2-tps-2774-1494.png)
+
+## Troubleshooting
+
+### Agent not appearing
+
+- Run `qwen --version` in terminal to verify installation
+- Ensure your JetBrains IDE version supports ACP
+- Restart your JetBrains IDE
+
+### Qwen Code not responding
+
+- Check your internet connection
+- Verify CLI works by running `qwen` in terminal
+- [File an issue on GitHub](https://github.com/qwenlm/qwen-code/issues) if the problem persists

docs/users/integration-vscode.md

@@ -22,13 +22,7 @@
 
 ### Installation
 
-1. Install Qwen Code CLI:
-
-   ```bash
-   npm install -g qwen-code
-   ```
-
-2. Download and install the extension from the [Visual Studio Code Extension Marketplace](https://marketplace.visualstudio.com/items?itemName=qwenlm.qwen-code-vscode-ide-companion).
+Download and install the extension from the [Visual Studio Code Extension Marketplace](https://marketplace.visualstudio.com/items?itemName=qwenlm.qwen-code-vscode-ide-companion).
 
 ## Troubleshooting
 

docs/users/integration-zed.md

@@ -1,6 +1,6 @@
 # Zed Editor
 
-> Zed Editor provides native support for AI coding assistants through the Agent Control Protocol (ACP). This integration allows you to use Qwen Code directly within Zed's interface with real-time code suggestions.
+> Zed Editor provides native support for AI coding assistants through the Agent Client Protocol (ACP). This integration allows you to use Qwen Code directly within Zed's interface with real-time code suggestions.
 
 ![Zed Editor Overview](https://img.alicdn.com/imgextra/i1/O1CN01aAhU311GwEoNh27FP_!!6000000000686-2-tps-3024-1898.png)
 
@@ -20,9 +20,9 @@
 
 1. Install Qwen Code CLI:
 
-   ```bash
-   npm install -g qwen-code
-   ```
+```bash
+npm install -g @qwen-code/qwen-code
+```
 
 2. Download and install [Zed Editor](https://zed.dev/)
 

docs/users/quickstart.md

@@ -159,7 +159,7 @@ Qwen Code will:
 
 ### Test out other common workflows
 
-There are a number of ways to work with Claude:
+There are a number of ways to work with Qwen Code:
 
 **Refactor code**
 

integration-tests/acp-integration.test.ts

@@ -311,9 +311,9 @@ function setupAcpTest(
     }
   });
 
-  it('returns modes on initialize and allows setting approval mode', async () => {
+  it('returns modes on initialize and allows setting mode and model', async () => {
     const rig = new TestRig();
-    rig.setup('acp approval mode');
+    rig.setup('acp mode and model');
 
     const { sendRequest, cleanup, stderr } = setupAcpTest(rig);
 
@@ -366,8 +366,14 @@ function setupAcpTest(
       const newSession = (await sendRequest('session/new', {
         cwd: rig.testDir!,
         mcpServers: [],
-      })) as { sessionId: string };
+      })) as {
+        sessionId: string;
+        models: {
+          availableModels: Array<{ modelId: string }>;
+        };
+      };
       expect(newSession.sessionId).toBeTruthy();
+      expect(newSession.models.availableModels.length).toBeGreaterThan(0);
 
       // Test 4: Set approval mode to 'yolo'
       const setModeResult = (await sendRequest('session/set_mode', {
@@ -392,6 +398,15 @@ function setupAcpTest(
       })) as { modeId: string };
       expect(setModeResult3).toBeDefined();
       expect(setModeResult3.modeId).toBe('default');
+
+      // Test 7: Set model using first available model
+      const firstModel = newSession.models.availableModels[0];
+      const setModelResult = (await sendRequest('session/set_model', {
+        sessionId: newSession.sessionId,
+        modelId: firstModel.modelId,
+      })) as { modelId: string };
+      expect(setModelResult).toBeDefined();
+      expect(setModelResult.modelId).toBeTruthy();
     } catch (e) {
       if (stderr.length) {
         console.error('Agent stderr:', stderr.join(''));

integration-tests/sdk-typescript/permission-control.test.ts

@@ -831,7 +831,7 @@ describe('Permission Control (E2E)', () => {
         TEST_TIMEOUT,
       );
 
-      it(
+      it.skip(
         'should execute dangerous commands without confirmation',
         async () => {
           const q = query({

package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "@qwen-code/qwen-code",
-  "version": "0.7.0",
+  "version": "0.7.1",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "@qwen-code/qwen-code",
-      "version": "0.7.0",
+      "version": "0.7.1",
       "workspaces": [
         "packages/*"
       ],
@@ -6216,10 +6216,7 @@
       "version": "4.0.3",
       "resolved": "https://registry.npmjs.org/chokidar/-/chokidar-4.0.3.tgz",
       "integrity": "sha512-Qgzu8kfBvo+cA4962jnP1KkS6Dop5NS6g7R5LFYJr4b8Ub94PPQXUksCw9PvXoeXPRRddRNC5C1JQUR2SMGtnA==",
-      "dev": true,
       "license": "MIT",
-      "optional": true,
-      "peer": true,
       "dependencies": {
         "readdirp": "^4.0.1"
       },
@@ -13882,10 +13879,7 @@
       "version": "4.1.2",
       "resolved": "https://registry.npmjs.org/readdirp/-/readdirp-4.1.2.tgz",
       "integrity": "sha512-GDhwkLfywWL2s6vEjyhri+eXmfH6j1L7JE27WhqLeYzoh/A3DBaYGEj2H/HFZCn/kMfim73FXxEJTw06WtxQwg==",
-      "dev": true,
       "license": "MIT",
-      "optional": true,
-      "peer": true,
       "engines": {
         "node": ">= 14.18.0"
       },
@@ -17316,7 +17310,7 @@
     },
     "packages/cli": {
       "name": "@qwen-code/qwen-code",
-      "version": "0.7.0",
+      "version": "0.7.1",
       "dependencies": {
         "@google/genai": "1.30.0",
         "@iarna/toml": "^2.2.5",
@@ -17953,7 +17947,7 @@
     },
     "packages/core": {
       "name": "@qwen-code/qwen-code-core",
-      "version": "0.7.0",
+      "version": "0.7.1",
       "hasInstallScript": true,
       "dependencies": {
         "@anthropic-ai/sdk": "^0.36.1",
@@ -17974,6 +17968,7 @@
         "ajv-formats": "^3.0.0",
         "async-mutex": "^0.5.0",
         "chardet": "^2.1.0",
+        "chokidar": "^4.0.3",
         "diff": "^7.0.0",
         "dotenv": "^17.1.0",
         "fast-levenshtein": "^2.0.6",
@@ -18593,7 +18588,7 @@
     },
     "packages/sdk-typescript": {
       "name": "@qwen-code/sdk",
-      "version": "0.1.2",
+      "version": "0.1.3",
       "license": "Apache-2.0",
       "dependencies": {
         "@modelcontextprotocol/sdk": "^1.25.1",
@@ -21413,7 +21408,7 @@
     },
     "packages/test-utils": {
       "name": "@qwen-code/qwen-code-test-utils",
-      "version": "0.7.0",
+      "version": "0.7.1",
       "dev": true,
       "license": "Apache-2.0",
       "devDependencies": {
@@ -21425,7 +21420,7 @@
     },
     "packages/vscode-ide-companion": {
       "name": "qwen-code-vscode-ide-companion",
-      "version": "0.7.0",
+      "version": "0.7.1",
       "license": "LICENSE",
       "dependencies": {
         "@modelcontextprotocol/sdk": "^1.25.1",

package.json

@@ -1,6 +1,6 @@
 {
   "name": "@qwen-code/qwen-code",
-  "version": "0.7.0",
+  "version": "0.7.1",
   "engines": {
     "node": ">=20.0.0"
   },
@@ -13,7 +13,7 @@
     "url": "git+https://github.com/QwenLM/qwen-code.git"
   },
   "config": {
-    "sandboxImageUri": "ghcr.io/qwenlm/qwen-code:0.7.0"
+    "sandboxImageUri": "ghcr.io/qwenlm/qwen-code:0.7.1"
   },
   "scripts": {
     "start": "cross-env node scripts/start.js",
@@ -23,8 +23,6 @@
     "build-and-start": "npm run build && npm run start",
     "build:vscode": "node scripts/build_vscode_companion.js",
     "build:all": "npm run build && npm run build:sandbox && npm run build:vscode",
-    "build:native": "node scripts/build_native.js",
-    "build:native:all": "node scripts/build_native.js --all",
     "build:packages": "npm run build --workspaces",
     "build:sandbox": "node scripts/build_sandbox.js",
     "bundle": "npm run generate && node esbuild.config.js && node scripts/copy_bundle_assets.js",

packages/cli/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@qwen-code/qwen-code",
-  "version": "0.7.0",
+  "version": "0.7.1",
   "description": "Qwen Code",
   "repository": {
     "type": "git",
@@ -33,7 +33,7 @@
     "dist"
   ],
   "config": {
-    "sandboxImageUri": "ghcr.io/qwenlm/qwen-code:0.7.0"
+    "sandboxImageUri": "ghcr.io/qwenlm/qwen-code:0.7.1"
   },
   "dependencies": {
     "@google/genai": "1.30.0",

packages/cli/src/acp-integration/acp.ts

@@ -8,6 +8,7 @@
 
 import { z } from 'zod';
 import * as schema from './schema.js';
+import { ACP_ERROR_CODES } from './errorCodes.js';
 export * from './schema.js';
 
 import type { WritableStream, ReadableStream } from 'node:stream/web';
@@ -70,6 +71,13 @@ export class AgentSideConnection implements Client {
           const validatedParams = schema.setModeRequestSchema.parse(params);
           return agent.setMode(validatedParams);
         }
+        case schema.AGENT_METHODS.session_set_model: {
+          if (!agent.setModel) {
+            throw RequestError.methodNotFound();
+          }
+          const validatedParams = schema.setModelRequestSchema.parse(params);
+          return agent.setModel(validatedParams);
+        }
         default:
           throw RequestError.methodNotFound(method);
       }
@@ -342,27 +350,51 @@ export class RequestError extends Error {
   }
 
   static parseError(details?: string): RequestError {
-    return new RequestError(-32700, 'Parse error', details);
+    return new RequestError(
+      ACP_ERROR_CODES.PARSE_ERROR,
+      'Parse error',
+      details,
+    );
   }
 
   static invalidRequest(details?: string): RequestError {
-    return new RequestError(-32600, 'Invalid request', details);
+    return new RequestError(
+      ACP_ERROR_CODES.INVALID_REQUEST,
+      'Invalid request',
+      details,
+    );
   }
 
   static methodNotFound(details?: string): RequestError {
-    return new RequestError(-32601, 'Method not found', details);
+    return new RequestError(
+      ACP_ERROR_CODES.METHOD_NOT_FOUND,
+      'Method not found',
+      details,
+    );
   }
 
   static invalidParams(details?: string): RequestError {
-    return new RequestError(-32602, 'Invalid params', details);
+    return new RequestError(
+      ACP_ERROR_CODES.INVALID_PARAMS,
+      'Invalid params',
+      details,
+    );
   }
 
   static internalError(details?: string): RequestError {
-    return new RequestError(-32603, 'Internal error', details);
+    return new RequestError(
+      ACP_ERROR_CODES.INTERNAL_ERROR,
+      'Internal error',
+      details,
+    );
   }
 
   static authRequired(details?: string): RequestError {
-    return new RequestError(-32000, 'Authentication required', details);
+    return new RequestError(
+      ACP_ERROR_CODES.AUTH_REQUIRED,
+      'Authentication required',
+      details,
+    );
   }
 
   toResult<T>(): Result<T> {
@@ -408,4 +440,5 @@ export interface Agent {
   prompt(params: schema.PromptRequest): Promise<schema.PromptResponse>;
   cancel(params: schema.CancelNotification): Promise<void>;
   setMode?(params: schema.SetModeRequest): Promise<schema.SetModeResponse>;
+  setModel?(params: schema.SetModelRequest): Promise<schema.SetModelResponse>;
 }

packages/cli/src/acp-integration/acpAgent.ts

@@ -165,30 +165,11 @@ class GeminiAgent {
     this.setupFileSystem(config);
 
     const session = await this.createAndStoreSession(config);
-    const configuredModel = (
-      config.getModel() ||
-      this.config.getModel() ||
-      ''
-    ).trim();
-    const modelId = configuredModel || 'default';
-    const modelName = configuredModel || modelId;
+    const availableModels = this.buildAvailableModels(config);
 
     return {
       sessionId: session.getId(),
-      models: {
-        currentModelId: modelId,
-        availableModels: [
-          {
-            modelId,
-            name: modelName,
-            description: null,
-            _meta: {
-              contextLimit: tokenLimit(modelId),
-            },
-          },
-        ],
-        _meta: null,
-      },
+      models: availableModels,
     };
   }
 
@@ -305,15 +286,29 @@ class GeminiAgent {
   async setMode(params: acp.SetModeRequest): Promise<acp.SetModeResponse> {
     const session = this.sessions.get(params.sessionId);
     if (!session) {
-      throw new Error(`Session not found: ${params.sessionId}`);
+      throw acp.RequestError.invalidParams(
+        `Session not found for id: ${params.sessionId}`,
+      );
     }
     return session.setMode(params);
   }
 
+  async setModel(params: acp.SetModelRequest): Promise<acp.SetModelResponse> {
+    const session = this.sessions.get(params.sessionId);
+    if (!session) {
+      throw acp.RequestError.invalidParams(
+        `Session not found for id: ${params.sessionId}`,
+      );
+    }
+    return session.setModel(params);
+  }
+
   private async ensureAuthenticated(config: Config): Promise<void> {
     const selectedType = this.settings.merged.security?.auth?.selectedType;
     if (!selectedType) {
-      throw acp.RequestError.authRequired('No Selected Type');
+      throw acp.RequestError.authRequired(
+        'Use Qwen Code CLI to authenticate first.',
+      );
     }
 
     try {
@@ -382,4 +377,43 @@ class GeminiAgent {
 
     return session;
   }
+
+  private buildAvailableModels(
+    config: Config,
+  ): acp.NewSessionResponse['models'] {
+    const currentModelId = (
+      config.getModel() ||
+      this.config.getModel() ||
+      ''
+    ).trim();
+    const availableModels = config.getAvailableModels();
+
+    const mappedAvailableModels = availableModels.map((model) => ({
+      modelId: model.id,
+      name: model.label,
+      description: model.description ?? null,
+      _meta: {
+        contextLimit: tokenLimit(model.id),
+      },
+    }));
+
+    if (
+      currentModelId &&
+      !mappedAvailableModels.some((model) => model.modelId === currentModelId)
+    ) {
+      mappedAvailableModels.unshift({
+        modelId: currentModelId,
+        name: currentModelId,
+        description: null,
+        _meta: {
+          contextLimit: tokenLimit(currentModelId),
+        },
+      });
+    }
+
+    return {
+      currentModelId,
+      availableModels: mappedAvailableModels,
+    };
+  }
 }

packages/cli/src/acp-integration/errorCodes.ts

@@ -0,0 +1,25 @@
+/**
+ * @license
+ * Copyright 2025 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+export const ACP_ERROR_CODES = {
+  // Parse error: invalid JSON received by server.
+  PARSE_ERROR: -32700,
+  // Invalid request: JSON is not a valid Request object.
+  INVALID_REQUEST: -32600,
+  // Method not found: method does not exist or is unavailable.
+  METHOD_NOT_FOUND: -32601,
+  // Invalid params: invalid method parameter(s).
+  INVALID_PARAMS: -32602,
+  // Internal error: implementation-defined server error.
+  INTERNAL_ERROR: -32603,
+  // Authentication required: must authenticate before operation.
+  AUTH_REQUIRED: -32000,
+  // Resource not found: e.g. missing file.
+  RESOURCE_NOT_FOUND: -32002,
+} as const;
+
+export type AcpErrorCode =
+  (typeof ACP_ERROR_CODES)[keyof typeof ACP_ERROR_CODES];

packages/cli/src/acp-integration/schema.ts

@@ -15,6 +15,7 @@ export const AGENT_METHODS = {
   session_prompt: 'session/prompt',
   session_list: 'session/list',
   session_set_mode: 'session/set_mode',
+  session_set_model: 'session/set_model',
 };
 
 export const CLIENT_METHODS = {
@@ -266,6 +267,18 @@ export const modelInfoSchema = z.object({
   name: z.string(),
 });
 
+export const setModelRequestSchema = z.object({
+  sessionId: z.string(),
+  modelId: z.string(),
+});
+
+export const setModelResponseSchema = z.object({
+  modelId: z.string(),
+});
+
+export type SetModelRequest = z.infer<typeof setModelRequestSchema>;
+export type SetModelResponse = z.infer<typeof setModelResponseSchema>;
+
 export const sessionModelStateSchema = z.object({
   _meta: acpMetaSchema,
   availableModels: z.array(modelInfoSchema),
@@ -592,6 +605,7 @@ export const agentResponseSchema = z.union([
   promptResponseSchema,
   listSessionsResponseSchema,
   setModeResponseSchema,
+  setModelResponseSchema,
 ]);
 
 export const requestPermissionRequestSchema = z.object({
@@ -624,6 +638,7 @@ export const agentRequestSchema = z.union([
   promptRequestSchema,
   listSessionsRequestSchema,
   setModeRequestSchema,
+  setModelRequestSchema,
 ]);
 
 export const agentNotificationSchema = sessionNotificationSchema;

packages/cli/src/acp-integration/service/filesystem.test.ts

@@ -7,6 +7,7 @@
 import { describe, expect, it, vi } from 'vitest';
 import type { FileSystemService } from '@qwen-code/qwen-code-core';
 import { AcpFileSystemService } from './filesystem.js';
+import { ACP_ERROR_CODES } from '../errorCodes.js';
 
 const createFallback = (): FileSystemService => ({
   readTextFile: vi.fn(),
@@ -16,11 +17,13 @@ const createFallback = (): FileSystemService => ({
 
 describe('AcpFileSystemService', () => {
   describe('readTextFile ENOENT handling', () => {
-    it('parses path from ACP ENOENT message (quoted)', async () => {
+    it('converts RESOURCE_NOT_FOUND error to ENOENT', async () => {
+      const resourceNotFoundError = {
+        code: ACP_ERROR_CODES.RESOURCE_NOT_FOUND,
+        message: 'File not found',
+      };
       const client = {
-        readTextFile: vi
-          .fn()
-          .mockResolvedValue({ content: 'ERROR: ENOENT: "/remote/file.txt"' }),
+        readTextFile: vi.fn().mockRejectedValue(resourceNotFoundError),
       } as unknown as import('../acp.js').Client;
 
       const svc = new AcpFileSystemService(
@@ -30,15 +33,20 @@ describe('AcpFileSystemService', () => {
         createFallback(),
       );
 
-      await expect(svc.readTextFile('/local/file.txt')).rejects.toMatchObject({
+      await expect(svc.readTextFile('/some/file.txt')).rejects.toMatchObject({
         code: 'ENOENT',
-        path: '/remote/file.txt',
+        errno: -2,
+        path: '/some/file.txt',
       });
     });
 
-    it('falls back to requested path when none provided', async () => {
+    it('re-throws other errors unchanged', async () => {
+      const otherError = {
+        code: ACP_ERROR_CODES.INTERNAL_ERROR,
+        message: 'Internal error',
+      };
       const client = {
-        readTextFile: vi.fn().mockResolvedValue({ content: 'ERROR: ENOENT:' }),
+        readTextFile: vi.fn().mockRejectedValue(otherError),
       } as unknown as import('../acp.js').Client;
 
       const svc = new AcpFileSystemService(
@@ -48,12 +56,34 @@ describe('AcpFileSystemService', () => {
         createFallback(),
       );
 
-      await expect(
-        svc.readTextFile('/fallback/path.txt'),
-      ).rejects.toMatchObject({
-        code: 'ENOENT',
-        path: '/fallback/path.txt',
+      await expect(svc.readTextFile('/some/file.txt')).rejects.toMatchObject({
+        code: ACP_ERROR_CODES.INTERNAL_ERROR,
+        message: 'Internal error',
       });
     });
+
+    it('uses fallback when readTextFile capability is disabled', async () => {
+      const client = {
+        readTextFile: vi.fn(),
+      } as unknown as import('../acp.js').Client;
+
+      const fallback = createFallback();
+      (fallback.readTextFile as ReturnType<typeof vi.fn>).mockResolvedValue(
+        'fallback content',
+      );
+
+      const svc = new AcpFileSystemService(
+        client,
+        'session-3',
+        { readTextFile: false, writeTextFile: true },
+        fallback,
+      );
+
+      const result = await svc.readTextFile('/some/file.txt');
+
+      expect(result).toBe('fallback content');
+      expect(fallback.readTextFile).toHaveBeenCalledWith('/some/file.txt');
+      expect(client.readTextFile).not.toHaveBeenCalled();
+    });
   });
 });

packages/cli/src/acp-integration/service/filesystem.ts

@@ -6,6 +6,7 @@
 
 import type { FileSystemService } from '@qwen-code/qwen-code-core';
 import type * as acp from '../acp.js';
+import { ACP_ERROR_CODES } from '../errorCodes.js';
 
 /**
  * ACP client-based implementation of FileSystemService
@@ -23,25 +24,31 @@ export class AcpFileSystemService implements FileSystemService {
       return this.fallback.readTextFile(filePath);
     }
 
-    const response = await this.client.readTextFile({
-      path: filePath,
-      sessionId: this.sessionId,
-      line: null,
-      limit: null,
-    });
+    let response: { content: string };
+    try {
+      response = await this.client.readTextFile({
+        path: filePath,
+        sessionId: this.sessionId,
+        line: null,
+        limit: null,
+      });
+    } catch (error) {
+      const errorCode =
+        typeof error === 'object' && error !== null && 'code' in error
+          ? (error as { code?: unknown }).code
+          : undefined;
 
-    if (response.content.startsWith('ERROR: ENOENT:')) {
-      // Treat ACP error strings as structured ENOENT errors without
-      // assuming a specific platform format.
-      const match = /^ERROR:\s*ENOENT:\s*(?<path>.*)$/i.exec(response.content);
-      const err = new Error(response.content) as NodeJS.ErrnoException;
-      err.code = 'ENOENT';
-      err.errno = -2;
-      const rawPath = match?.groups?.['path']?.trim();
-      err['path'] = rawPath
-        ? rawPath.replace(/^['"]|['"]$/g, '') || filePath
-        : filePath;
-      throw err;
+      if (errorCode === ACP_ERROR_CODES.RESOURCE_NOT_FOUND) {
+        const err = new Error(
+          `File not found: ${filePath}`,
+        ) as NodeJS.ErrnoException;
+        err.code = 'ENOENT';
+        err.errno = -2;
+        err.path = filePath;
+        throw err;
+      }
+
+      throw error;
     }
 
     return response.content;

packages/cli/src/acp-integration/session/Session.test.ts

@@ -0,0 +1,174 @@
+/**
+ * @license
+ * Copyright 2025 Qwen
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { describe, it, expect, vi, beforeEach } from 'vitest';
+import { Session } from './Session.js';
+import type { Config, GeminiChat } from '@qwen-code/qwen-code-core';
+import { ApprovalMode } from '@qwen-code/qwen-code-core';
+import type * as acp from '../acp.js';
+import type { LoadedSettings } from '../../config/settings.js';
+import * as nonInteractiveCliCommands from '../../nonInteractiveCliCommands.js';
+
+vi.mock('../../nonInteractiveCliCommands.js', () => ({
+  getAvailableCommands: vi.fn(),
+  handleSlashCommand: vi.fn(),
+}));
+
+describe('Session', () => {
+  let mockChat: GeminiChat;
+  let mockConfig: Config;
+  let mockClient: acp.Client;
+  let mockSettings: LoadedSettings;
+  let session: Session;
+  let currentModel: string;
+  let setModelSpy: ReturnType<typeof vi.fn>;
+  let getAvailableCommandsSpy: ReturnType<typeof vi.fn>;
+
+  beforeEach(() => {
+    currentModel = 'qwen3-code-plus';
+    setModelSpy = vi.fn().mockImplementation(async (modelId: string) => {
+      currentModel = modelId;
+    });
+
+    mockChat = {
+      sendMessageStream: vi.fn(),
+      addHistory: vi.fn(),
+    } as unknown as GeminiChat;
+
+    mockConfig = {
+      setApprovalMode: vi.fn(),
+      setModel: setModelSpy,
+      getModel: vi.fn().mockImplementation(() => currentModel),
+    } as unknown as Config;
+
+    mockClient = {
+      sessionUpdate: vi.fn().mockResolvedValue(undefined),
+      requestPermission: vi.fn().mockResolvedValue({
+        outcome: { outcome: 'selected', optionId: 'proceed_once' },
+      }),
+      sendCustomNotification: vi.fn().mockResolvedValue(undefined),
+    } as unknown as acp.Client;
+
+    mockSettings = {
+      merged: {},
+    } as LoadedSettings;
+
+    getAvailableCommandsSpy = vi.mocked(nonInteractiveCliCommands)
+      .getAvailableCommands as unknown as ReturnType<typeof vi.fn>;
+    getAvailableCommandsSpy.mockResolvedValue([]);
+
+    session = new Session(
+      'test-session-id',
+      mockChat,
+      mockConfig,
+      mockClient,
+      mockSettings,
+    );
+  });
+
+  describe('setMode', () => {
+    it.each([
+      ['plan', ApprovalMode.PLAN],
+      ['default', ApprovalMode.DEFAULT],
+      ['auto-edit', ApprovalMode.AUTO_EDIT],
+      ['yolo', ApprovalMode.YOLO],
+    ] as const)('maps %s mode', async (modeId, expected) => {
+      const result = await session.setMode({
+        sessionId: 'test-session-id',
+        modeId,
+      });
+
+      expect(mockConfig.setApprovalMode).toHaveBeenCalledWith(expected);
+      expect(result).toEqual({ modeId });
+    });
+  });
+
+  describe('setModel', () => {
+    it('sets model via config and returns current model', async () => {
+      const result = await session.setModel({
+        sessionId: 'test-session-id',
+        modelId: '  qwen3-coder-plus  ',
+      });
+
+      expect(mockConfig.setModel).toHaveBeenCalledWith('qwen3-coder-plus', {
+        reason: 'user_request_acp',
+        context: 'session/set_model',
+      });
+      expect(mockConfig.getModel).toHaveBeenCalled();
+      expect(result).toEqual({ modelId: 'qwen3-coder-plus' });
+    });
+
+    it('rejects empty/whitespace model IDs', async () => {
+      await expect(
+        session.setModel({
+          sessionId: 'test-session-id',
+          modelId: '   ',
+        }),
+      ).rejects.toThrow('Invalid params');
+
+      expect(mockConfig.setModel).not.toHaveBeenCalled();
+    });
+
+    it('propagates errors from config.setModel', async () => {
+      const configError = new Error('Invalid model');
+      setModelSpy.mockRejectedValueOnce(configError);
+
+      await expect(
+        session.setModel({
+          sessionId: 'test-session-id',
+          modelId: 'invalid-model',
+        }),
+      ).rejects.toThrow('Invalid model');
+    });
+  });
+
+  describe('sendAvailableCommandsUpdate', () => {
+    it('sends available_commands_update from getAvailableCommands()', async () => {
+      getAvailableCommandsSpy.mockResolvedValueOnce([
+        {
+          name: 'init',
+          description: 'Initialize project context',
+        },
+      ]);
+
+      await session.sendAvailableCommandsUpdate();
+
+      expect(getAvailableCommandsSpy).toHaveBeenCalledWith(
+        mockConfig,
+        expect.any(AbortSignal),
+      );
+      expect(mockClient.sessionUpdate).toHaveBeenCalledWith({
+        sessionId: 'test-session-id',
+        update: {
+          sessionUpdate: 'available_commands_update',
+          availableCommands: [
+            {
+              name: 'init',
+              description: 'Initialize project context',
+              input: null,
+            },
+          ],
+        },
+      });
+    });
+
+    it('swallows errors and does not throw', async () => {
+      const consoleErrorSpy = vi
+        .spyOn(console, 'error')
+        .mockImplementation(() => undefined);
+      getAvailableCommandsSpy.mockRejectedValueOnce(
+        new Error('Command discovery failed'),
+      );
+
+      await expect(
+        session.sendAvailableCommandsUpdate(),
+      ).resolves.toBeUndefined();
+      expect(mockClient.sessionUpdate).not.toHaveBeenCalled();
+      expect(consoleErrorSpy).toHaveBeenCalled();
+      consoleErrorSpy.mockRestore();
+    });
+  });
+});

packages/cli/src/acp-integration/session/Session.ts

@@ -52,6 +52,8 @@ import type {
   AvailableCommandsUpdate,
   SetModeRequest,
   SetModeResponse,
+  SetModelRequest,
+  SetModelResponse,
   ApprovalModeValue,
   CurrentModeUpdate,
 } from '../schema.js';
@@ -348,6 +350,31 @@ export class Session implements SessionContext {
     return { modeId: params.modeId };
   }
 
+  /**
+   * Sets the model for the current session.
+   * Validates the model ID and switches the model via Config.
+   */
+  async setModel(params: SetModelRequest): Promise<SetModelResponse> {
+    const modelId = params.modelId.trim();
+
+    if (!modelId) {
+      throw acp.RequestError.invalidParams('modelId cannot be empty');
+    }
+
+    // Attempt to set the model using config
+    await this.config.setModel(modelId, {
+      reason: 'user_request_acp',
+      context: 'session/set_model',
+    });
+
+    // Get updated model info
+    const currentModel = this.config.getModel();
+
+    return {
+      modelId: currentModel,
+    };
+  }
+
   /**
    * Sends a current_mode_update notification to the client.
    * Called after the agent switches modes (e.g., from exit_plan_mode tool).

packages/cli/src/config/config.test.ts

@@ -1196,11 +1196,6 @@ describe('Hierarchical Memory Loading (config.ts) - Placeholder Suite', () => {
       ],
       true,
       'tree',
-      {
-        respectGitIgnore: false,
-        respectQwenIgnore: true,
-      },
-      undefined, // maxDirs
     );
   });
 

packages/cli/src/config/config.ts

@@ -9,7 +9,6 @@ import {
   AuthType,
   Config,
   DEFAULT_QWEN_EMBEDDING_MODEL,
-  DEFAULT_MEMORY_FILE_FILTERING_OPTIONS,
   FileDiscoveryService,
   getCurrentGeminiMdFilename,
   loadServerHierarchicalMemory,
@@ -22,7 +21,6 @@ import {
   isToolEnabled,
   SessionService,
   type ResumedSessionData,
-  type FileFilteringOptions,
   type MCPServerConfig,
   type ToolName,
   EditTool,
@@ -170,7 +168,17 @@ function normalizeOutputFormat(
 }
 
 export async function parseArguments(settings: Settings): Promise<CliArgs> {
-  const rawArgv = hideBin(process.argv);
+  let rawArgv = hideBin(process.argv);
+
+  // hack: if the first argument is the CLI entry point, remove it
+  if (
+    rawArgv.length > 0 &&
+    (rawArgv[0].endsWith('/dist/qwen-cli/cli.js') ||
+      rawArgv[0].endsWith('/dist/cli.js'))
+  ) {
+    rawArgv = rawArgv.slice(1);
+  }
+
   const yargsInstance = yargs(rawArgv)
     .locale('en')
     .scriptName('qwen')
@@ -324,7 +332,14 @@ export async function parseArguments(settings: Settings): Promise<CliArgs> {
         .option('experimental-skills', {
           type: 'boolean',
           description: 'Enable experimental Skills feature',
-          default: false,
+          default: (() => {
+            const legacySkills = (
+              settings as Settings & {
+                tools?: { experimental?: { skills?: boolean } };
+              }
+            ).tools?.experimental?.skills;
+            return settings.experimental?.skills ?? legacySkills ?? false;
+          })(),
         })
         .option('channel', {
           type: 'string',
@@ -633,7 +648,6 @@ export async function loadHierarchicalGeminiMemory(
   extensionContextFilePaths: string[] = [],
   folderTrust: boolean,
   memoryImportFormat: 'flat' | 'tree' = 'tree',
-  fileFilteringOptions?: FileFilteringOptions,
 ): Promise<{ memoryContent: string; fileCount: number }> {
   // FIX: Use real, canonical paths for a reliable comparison to handle symlinks.
   const realCwd = fs.realpathSync(path.resolve(currentWorkingDirectory));
@@ -659,8 +673,6 @@ export async function loadHierarchicalGeminiMemory(
     extensionContextFilePaths,
     folderTrust,
     memoryImportFormat,
-    fileFilteringOptions,
-    settings.context?.discoveryMaxDirs,
   );
 }
 
@@ -730,11 +742,6 @@ export async function loadCliConfig(
 
   const fileService = new FileDiscoveryService(cwd);
 
-  const fileFiltering = {
-    ...DEFAULT_MEMORY_FILE_FILTERING_OPTIONS,
-    ...settings.context?.fileFiltering,
-  };
-
   const includeDirectories = (settings.context?.includeDirectories || [])
     .map(resolvePath)
     .concat((argv.includeDirectories || []).map(resolvePath));
@@ -751,7 +758,6 @@ export async function loadCliConfig(
     extensionContextFilePaths,
     trustedFolder,
     memoryImportFormat,
-    fileFiltering,
   );
 
   let mcpServers = mergeMcpServers(settings, activeExtensions);
@@ -864,11 +870,10 @@ export async function loadCliConfig(
     }
   };
 
-  if (
-    !interactive &&
-    !argv.experimentalAcp &&
-    inputFormat !== InputFormat.STREAM_JSON
-  ) {
+  // ACP mode check: must include both --acp (current) and --experimental-acp (deprecated).
+  // Without this check, edit, write_file, run_shell_command would be excluded in ACP mode.
+  const isAcpMode = argv.acp || argv.experimentalAcp;
+  if (!interactive && !isAcpMode && inputFormat !== InputFormat.STREAM_JSON) {
     switch (approvalMode) {
       case ApprovalMode.PLAN:
       case ApprovalMode.DEFAULT:

packages/cli/src/config/keyBindings.ts

@@ -122,9 +122,10 @@ export const defaultKeyBindings: KeyBindingConfig = {
 
   // Auto-completion
   [Command.ACCEPT_SUGGESTION]: [{ key: 'tab' }, { key: 'return', ctrl: false }],
-  // Completion navigation (arrow or Ctrl+P/N)
-  [Command.COMPLETION_UP]: [{ key: 'up' }, { key: 'p', ctrl: true }],
-  [Command.COMPLETION_DOWN]: [{ key: 'down' }, { key: 'n', ctrl: true }],
+  // Completion navigation uses only arrow keys
+  // Ctrl+P/N are reserved for history navigation (HISTORY_UP/DOWN)
+  [Command.COMPLETION_UP]: [{ key: 'up' }],
+  [Command.COMPLETION_DOWN]: [{ key: 'down' }],
 
   // Text input
   // Must also exclude shift to allow shift+enter for newline

packages/cli/src/config/settings.ts

@@ -106,7 +106,6 @@ const MIGRATION_MAP: Record<string, string> = {
   mcpServers: 'mcpServers',
   mcpServerCommand: 'mcp.serverCommand',
   memoryImportFormat: 'context.importFormat',
-  memoryDiscoveryMaxDirs: 'context.discoveryMaxDirs',
   model: 'model.name',
   preferredEditor: 'general.preferredEditor',
   sandbox: 'tools.sandbox',
@@ -922,6 +921,21 @@ export function migrateDeprecatedSettings(
 
       loadedSettings.setValue(scope, 'extensions', newExtensionsValue);
     }
+
+    const legacySkills = (
+      settings as Settings & {
+        tools?: { experimental?: { skills?: boolean } };
+      }
+    ).tools?.experimental?.skills;
+    if (
+      legacySkills !== undefined &&
+      settings.experimental?.skills === undefined
+    ) {
+      console.log(
+        `Migrating deprecated tools.experimental.skills setting from ${scope} settings...`,
+      );
+      loadedSettings.setValue(scope, 'experimental.skills', legacySkills);
+    }
   };
 
   processScope(SettingScope.User);

packages/cli/src/config/settingsSchema.ts

@@ -434,6 +434,16 @@ const SETTINGS_SCHEMA = {
           'Show welcome back dialog when returning to a project with conversation history.',
         showInDialog: true,
       },
+      enableUserFeedback: {
+        type: 'boolean',
+        label: 'Enable User Feedback',
+        category: 'UI',
+        requiresRestart: false,
+        default: true,
+        description:
+          'Show optional feedback dialog after conversations to help improve Qwen performance.',
+        showInDialog: true,
+      },
       accessibility: {
         type: 'object',
         label: 'Accessibility',
@@ -464,6 +474,15 @@ const SETTINGS_SCHEMA = {
           },
         },
       },
+      feedbackLastShownTimestamp: {
+        type: 'number',
+        label: 'Feedback Last Shown Timestamp',
+        category: 'UI',
+        requiresRestart: false,
+        default: 0,
+        description: 'The last time the feedback dialog was shown.',
+        showInDialog: false,
+      },
     },
   },
 
@@ -722,15 +741,6 @@ const SETTINGS_SCHEMA = {
         description: 'The format to use when importing memory.',
         showInDialog: false,
       },
-      discoveryMaxDirs: {
-        type: 'number',
-        label: 'Memory Discovery Max Dirs',
-        category: 'Context',
-        requiresRestart: false,
-        default: 200,
-        description: 'Maximum number of directories to search for memory.',
-        showInDialog: true,
-      },
       includeDirectories: {
         type: 'array',
         label: 'Include Directories',
@@ -1207,6 +1217,16 @@ const SETTINGS_SCHEMA = {
     description: 'Setting to enable experimental features',
     showInDialog: false,
     properties: {
+      skills: {
+        type: 'boolean',
+        label: 'Skills',
+        category: 'Experimental',
+        requiresRestart: true,
+        default: false,
+        description:
+          'Enable experimental Agent Skills feature. When enabled, Qwen Code can use Skills from .qwen/skills/ and ~/.qwen/skills/.',
+        showInDialog: true,
+      },
       extensionManagement: {
         type: 'boolean',
         label: 'Extension Management',

packages/cli/src/gemini.tsx

@@ -346,6 +346,7 @@ export async function main() {
       extensionEnablementManager,
       argv,
     );
+    registerCleanup(() => config.shutdown());
 
     if (config.getListExtensions()) {
       console.log('Installed extensions:');

packages/cli/src/i18n/locales/de.js

@@ -289,6 +289,13 @@ export default {
   'Show Citations': 'Quellenangaben anzeigen',
   'Custom Witty Phrases': 'Benutzerdefinierte Witzige Sprüche',
   'Enable Welcome Back': 'Willkommen-zurück aktivieren',
+  'Enable User Feedback': 'Benutzerfeedback aktivieren',
+  'How is Qwen doing this session? (optional)':
+    'Wie macht sich Qwen in dieser Sitzung? (optional)',
+  Bad: 'Schlecht',
+  Good: 'Gut',
+  'Not Sure Yet': 'Noch nicht sicher',
+  'Any other key': 'Beliebige andere Taste',
   'Disable Loading Phrases': 'Ladesprüche deaktivieren',
   'Screen Reader Mode': 'Bildschirmleser-Modus',
   'IDE Mode': 'IDE-Modus',

packages/cli/src/i18n/locales/en.js

@@ -286,6 +286,13 @@ export default {
   'Show Citations': 'Show Citations',
   'Custom Witty Phrases': 'Custom Witty Phrases',
   'Enable Welcome Back': 'Enable Welcome Back',
+  'Enable User Feedback': 'Enable User Feedback',
+  'How is Qwen doing this session? (optional)':
+    'How is Qwen doing this session? (optional)',
+  Bad: 'Bad',
+  Good: 'Good',
+  'Not Sure Yet': 'Not Sure Yet',
+  'Any other key': 'Any other key',
   'Disable Loading Phrases': 'Disable Loading Phrases',
   'Screen Reader Mode': 'Screen Reader Mode',
   'IDE Mode': 'IDE Mode',

packages/cli/src/i18n/locales/ru.js

@@ -289,6 +289,13 @@ export default {
   'Show Citations': 'Показывать цитаты',
   'Custom Witty Phrases': 'Пользовательские остроумные фразы',
   'Enable Welcome Back': 'Включить приветствие при возврате',
+  'Enable User Feedback': 'Включить отзывы пользователей',
+  'How is Qwen doing this session? (optional)':
+    'Как дела у Qwen в этой сессии? (необязательно)',
+  Bad: 'Плохо',
+  Good: 'Хорошо',
+  'Not Sure Yet': 'Пока не уверен',
+  'Any other key': 'Любая другая клавиша',
   'Disable Loading Phrases': 'Отключить фразы при загрузке',
   'Screen Reader Mode': 'Режим программы чтения с экрана',
   'IDE Mode': 'Режим IDE',

packages/cli/src/i18n/locales/zh.js

@@ -277,6 +277,12 @@ export default {
   'Show Citations': '显示引用',
   'Custom Witty Phrases': '自定义诙谐短语',
   'Enable Welcome Back': '启用欢迎回来',
+  'Enable User Feedback': '启用用户反馈',
+  'How is Qwen doing this session? (optional)': 'Qwen 这次表现如何？（可选）',
+  Bad: '不满意',
+  Good: '满意',
+  'Not Sure Yet': '暂不评价',
+  'Any other key': '任意其他键',
   'Disable Loading Phrases': '禁用加载短语',
   'Screen Reader Mode': '屏幕阅读器模式',
   'IDE Mode': 'IDE 模式',
@@ -873,11 +879,11 @@ export default {
   'Session Stats': '会话统计',
   'Model Usage': '模型使用情况',
   Reqs: '请求数',
-  'Input Tokens': '输入令牌',
-  'Output Tokens': '输出令牌',
+  'Input Tokens': '输入 token 数',
+  'Output Tokens': '输出 token 数',
   'Savings Highlight:': '节省亮点：',
   'of input tokens were served from the cache, reducing costs.':
-    '的输入令牌来自缓存，降低了成本',
+    '从缓存载入 token ，降低了成本',
   'Tip: For a full token breakdown, run `/stats model`.':
     '提示：要查看完整的令牌明细，请运行 `/stats model`',
   'Model Stats For Nerds': '模型统计（技术细节）',

packages/cli/src/services/BuiltinCommandLoader.ts

@@ -31,6 +31,7 @@ import { quitCommand } from '../ui/commands/quitCommand.js';
 import { restoreCommand } from '../ui/commands/restoreCommand.js';
 import { resumeCommand } from '../ui/commands/resumeCommand.js';
 import { settingsCommand } from '../ui/commands/settingsCommand.js';
+import { skillsCommand } from '../ui/commands/skillsCommand.js';
 import { statsCommand } from '../ui/commands/statsCommand.js';
 import { summaryCommand } from '../ui/commands/summaryCommand.js';
 import { terminalSetupCommand } from '../ui/commands/terminalSetupCommand.js';
@@ -78,6 +79,7 @@ export class BuiltinCommandLoader implements ICommandLoader {
       quitCommand,
       restoreCommand(this.config),
       resumeCommand,
+      ...(this.config?.getExperimentalSkills?.() ? [skillsCommand] : []),
       statsCommand,
       summaryCommand,
       themeCommand,

packages/cli/src/ui/AppContainer.tsx

@@ -45,6 +45,7 @@ import process from 'node:process';
 import { useHistory } from './hooks/useHistoryManager.js';
 import { useMemoryMonitor } from './hooks/useMemoryMonitor.js';
 import { useThemeCommand } from './hooks/useThemeCommand.js';
+import { useFeedbackDialog } from './hooks/useFeedbackDialog.js';
 import { useAuthCommand } from './auth/useAuth.js';
 import { useEditorSettings } from './hooks/useEditorSettings.js';
 import { useSettingsCommand } from './hooks/useSettingsCommand.js';
@@ -575,7 +576,6 @@ export const AppContainer = (props: AppContainerProps) => {
         config.getExtensionContextFilePaths(),
         config.isTrustedFolder(),
         settings.merged.context?.importFormat || 'tree', // Use setting or default to 'tree'
-        config.getFileFilteringOptions(),
       );
 
       config.setUserMemory(memoryContent);
@@ -1196,6 +1196,19 @@ export const AppContainer = (props: AppContainerProps) => {
     isApprovalModeDialogOpen ||
     isResumeDialogOpen;
 
+  const {
+    isFeedbackDialogOpen,
+    openFeedbackDialog,
+    closeFeedbackDialog,
+    submitFeedback,
+  } = useFeedbackDialog({
+    config,
+    settings,
+    streamingState,
+    history: historyManager.history,
+    sessionStats,
+  });
+
   const pendingHistoryItems = useMemo(
     () => [...pendingSlashCommandHistoryItems, ...pendingGeminiHistoryItems],
     [pendingSlashCommandHistoryItems, pendingGeminiHistoryItems],
@@ -1292,6 +1305,8 @@ export const AppContainer = (props: AppContainerProps) => {
       // Subagent dialogs
       isSubagentCreateDialogOpen,
       isAgentsManagerDialogOpen,
+      // Feedback dialog
+      isFeedbackDialogOpen,
     }),
     [
       isThemeDialogOpen,
@@ -1382,6 +1397,8 @@ export const AppContainer = (props: AppContainerProps) => {
       // Subagent dialogs
       isSubagentCreateDialogOpen,
       isAgentsManagerDialogOpen,
+      // Feedback dialog
+      isFeedbackDialogOpen,
     ],
   );
 
@@ -1422,6 +1439,10 @@ export const AppContainer = (props: AppContainerProps) => {
       openResumeDialog,
       closeResumeDialog,
       handleResume,
+      // Feedback dialog
+      openFeedbackDialog,
+      closeFeedbackDialog,
+      submitFeedback,
     }),
     [
       handleThemeSelect,
@@ -1457,6 +1478,10 @@ export const AppContainer = (props: AppContainerProps) => {
       openResumeDialog,
       closeResumeDialog,
       handleResume,
+      // Feedback dialog
+      openFeedbackDialog,
+      closeFeedbackDialog,
+      submitFeedback,
     ],
   );
 

packages/cli/src/ui/FeedbackDialog.tsx

@@ -0,0 +1,61 @@
+import { Box, Text } from 'ink';
+import type React from 'react';
+import { t } from '../i18n/index.js';
+import { useUIActions } from './contexts/UIActionsContext.js';
+import { useUIState } from './contexts/UIStateContext.js';
+import { useKeypress } from './hooks/useKeypress.js';
+
+const FEEDBACK_OPTIONS = {
+  GOOD: 1,
+  BAD: 2,
+  NOT_SURE: 3,
+} as const;
+
+const FEEDBACK_OPTION_KEYS = {
+  [FEEDBACK_OPTIONS.GOOD]: '1',
+  [FEEDBACK_OPTIONS.BAD]: '2',
+  [FEEDBACK_OPTIONS.NOT_SURE]: 'any',
+} as const;
+
+export const FEEDBACK_DIALOG_KEYS = ['1', '2'] as const;
+
+export const FeedbackDialog: React.FC = () => {
+  const uiState = useUIState();
+  const uiActions = useUIActions();
+
+  useKeypress(
+    (key) => {
+      if (key.name === FEEDBACK_OPTION_KEYS[FEEDBACK_OPTIONS.GOOD]) {
+        uiActions.submitFeedback(FEEDBACK_OPTIONS.GOOD);
+      } else if (key.name === FEEDBACK_OPTION_KEYS[FEEDBACK_OPTIONS.BAD]) {
+        uiActions.submitFeedback(FEEDBACK_OPTIONS.BAD);
+      } else {
+        uiActions.submitFeedback(FEEDBACK_OPTIONS.NOT_SURE);
+      }
+
+      uiActions.closeFeedbackDialog();
+    },
+    { isActive: uiState.isFeedbackDialogOpen },
+  );
+
+  return (
+    <Box flexDirection="column" marginY={1}>
+      <Box>
+        <Text color="cyan">● </Text>
+        <Text bold>{t('How is Qwen doing this session? (optional)')}</Text>
+      </Box>
+      <Box marginTop={1}>
+        <Text color="cyan">
+          {FEEDBACK_OPTION_KEYS[FEEDBACK_OPTIONS.GOOD]}:{' '}
+        </Text>
+        <Text>{t('Good')}</Text>
+        <Text> </Text>
+        <Text color="cyan">{FEEDBACK_OPTION_KEYS[FEEDBACK_OPTIONS.BAD]}: </Text>
+        <Text>{t('Bad')}</Text>
+        <Text> </Text>
+        <Text color="cyan">{t('Any other key')}: </Text>
+        <Text>{t('Not Sure Yet')}</Text>
+      </Box>
+    </Box>
+  );
+};

packages/cli/src/ui/auth/useAuth.ts

@@ -4,7 +4,11 @@
  * SPDX-License-Identifier: Apache-2.0
  */
 
-import type { Config, ModelProvidersConfig } from '@qwen-code/qwen-code-core';
+import type {
+  Config,
+  ContentGeneratorConfig,
+  ModelProvidersConfig,
+} from '@qwen-code/qwen-code-core';
 import {
   AuthEvent,
   AuthType,
@@ -83,12 +87,26 @@ export const useAuthCommand = (
     async (authType: AuthType, credentials?: OpenAICredentials) => {
       try {
         const authTypeScope = getPersistScopeForModelSelection(settings);
+
+        // Persist authType
         settings.setValue(
           authTypeScope,
           'security.auth.selectedType',
           authType,
         );
 
+        // Persist model from ContentGenerator config (handles fallback cases)
+        // This ensures that when syncAfterAuthRefresh falls back to default model,
+        // it gets persisted to settings.json
+        const contentGeneratorConfig = config.getContentGeneratorConfig();
+        if (contentGeneratorConfig?.model) {
+          settings.setValue(
+            authTypeScope,
+            'model.name',
+            contentGeneratorConfig.model,
+          );
+        }
+
         // Only update credentials if not switching to QWEN_OAUTH,
         // so that OpenAI credentials are preserved when switching to QWEN_OAUTH.
         if (authType !== AuthType.QWEN_OAUTH && credentials) {
@@ -106,9 +124,6 @@ export const useAuthCommand = (
               credentials.baseUrl,
             );
           }
-          if (credentials?.model != null) {
-            settings.setValue(authTypeScope, 'model.name', credentials.model);
-          }
         }
       } catch (error) {
         handleAuthFailure(error);
@@ -203,11 +218,19 @@ export const useAuthCommand = (
 
       if (authType === AuthType.USE_OPENAI) {
         if (credentials) {
-          config.updateCredentials({
-            apiKey: credentials.apiKey,
-            baseUrl: credentials.baseUrl,
-            model: credentials.model,
-          });
+          // Pass settings.model.generationConfig to updateCredentials so it can be merged
+          // after clearing provider-sourced config. This ensures settings.json generationConfig
+          // fields (e.g., samplingParams, timeout) are preserved.
+          const settingsGenerationConfig = settings.merged.model
+            ?.generationConfig as Partial<ContentGeneratorConfig> | undefined;
+          config.updateCredentials(
+            {
+              apiKey: credentials.apiKey,
+              baseUrl: credentials.baseUrl,
+              model: credentials.model,
+            },
+            settingsGenerationConfig,
+          );
           await performAuth(authType, credentials);
         }
         return;
@@ -215,7 +238,13 @@ export const useAuthCommand = (
 
       await performAuth(authType);
     },
-    [config, performAuth, isProviderManagedModel, onAuthError],
+    [
+      config,
+      performAuth,
+      isProviderManagedModel,
+      onAuthError,
+      settings.merged.model?.generationConfig,
+    ],
   );
 
   const openAuthDialog = useCallback(() => {

packages/cli/src/ui/commands/directoryCommand.test.tsx

@@ -54,9 +54,7 @@ describe('directoryCommand', () => {
       services: {
         config: mockConfig,
         settings: {
-          merged: {
-            memoryDiscoveryMaxDirs: 1000,
-          },
+          merged: {},
         },
       },
       ui: {

packages/cli/src/ui/commands/directoryCommand.tsx

@@ -119,8 +119,6 @@ export const directoryCommand: SlashCommand = {
                 config.getFolderTrust(),
                 context.services.settings.merged.context?.importFormat ||
                   'tree', // Use setting or default to 'tree'
-                config.getFileFilteringOptions(),
-                context.services.settings.merged.context?.discoveryMaxDirs,
               );
             config.setUserMemory(memoryContent);
             config.setGeminiMdFileCount(fileCount);

packages/cli/src/ui/commands/memoryCommand.test.ts

@@ -299,9 +299,7 @@ describe('memoryCommand', () => {
         services: {
           config: mockConfig,
           settings: {
-            merged: {
-              memoryDiscoveryMaxDirs: 1000,
-            },
+            merged: {},
           } as LoadedSettings,
         },
       });

packages/cli/src/ui/commands/memoryCommand.ts

@@ -315,8 +315,6 @@ export const memoryCommand: SlashCommand = {
                 config.getFolderTrust(),
                 context.services.settings.merged.context?.importFormat ||
                   'tree', // Use setting or default to 'tree'
-                config.getFileFilteringOptions(),
-                context.services.settings.merged.context?.discoveryMaxDirs,
               );
             config.setUserMemory(memoryContent);
             config.setGeminiMdFileCount(fileCount);

packages/cli/src/ui/commands/skillsCommand.ts

@@ -0,0 +1,132 @@
+/**
+ * @license
+ * Copyright 2025 Qwen
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import {
+  CommandKind,
+  type CommandCompletionItem,
+  type CommandContext,
+  type SlashCommand,
+} from './types.js';
+import { MessageType, type HistoryItemSkillsList } from '../types.js';
+import { t } from '../../i18n/index.js';
+import { AsyncFzf } from 'fzf';
+import type { SkillConfig } from '@qwen-code/qwen-code-core';
+
+export const skillsCommand: SlashCommand = {
+  name: 'skills',
+  get description() {
+    return t('List available skills.');
+  },
+  kind: CommandKind.BUILT_IN,
+  action: async (context: CommandContext, args?: string) => {
+    const rawArgs = args?.trim() ?? '';
+    const [skillName = ''] = rawArgs.split(/\s+/);
+
+    const skillManager = context.services.config?.getSkillManager();
+    if (!skillManager) {
+      context.ui.addItem(
+        {
+          type: MessageType.ERROR,
+          text: t('Could not retrieve skill manager.'),
+        },
+        Date.now(),
+      );
+      return;
+    }
+
+    const skills = await skillManager.listSkills();
+    if (skills.length === 0) {
+      context.ui.addItem(
+        {
+          type: MessageType.INFO,
+          text: t('No skills are currently available.'),
+        },
+        Date.now(),
+      );
+      return;
+    }
+
+    if (!skillName) {
+      const sortedSkills = [...skills].sort((left, right) =>
+        left.name.localeCompare(right.name),
+      );
+      const skillsListItem: HistoryItemSkillsList = {
+        type: MessageType.SKILLS_LIST,
+        skills: sortedSkills.map((skill) => ({ name: skill.name })),
+      };
+      context.ui.addItem(skillsListItem, Date.now());
+      return;
+    }
+    const normalizedName = skillName.toLowerCase();
+    const hasSkill = skills.some(
+      (skill) => skill.name.toLowerCase() === normalizedName,
+    );
+
+    if (!hasSkill) {
+      context.ui.addItem(
+        {
+          type: MessageType.ERROR,
+          text: t('Unknown skill: {{name}}', { name: skillName }),
+        },
+        Date.now(),
+      );
+      return;
+    }
+
+    const rawInput = context.invocation?.raw ?? `/skills ${rawArgs}`;
+    return {
+      type: 'submit_prompt',
+      content: [{ text: rawInput }],
+    };
+  },
+  completion: async (
+    context: CommandContext,
+    partialArg: string,
+  ): Promise<CommandCompletionItem[]> => {
+    const skillManager = context.services.config?.getSkillManager();
+    if (!skillManager) {
+      return [];
+    }
+
+    const skills = await skillManager.listSkills();
+    const normalizedPartial = partialArg.trim();
+    const matches = await getSkillMatches(skills, normalizedPartial);
+
+    return matches.map((skill) => ({
+      value: skill.name,
+      description: skill.description,
+    }));
+  },
+};
+
+async function getSkillMatches(
+  skills: SkillConfig[],
+  query: string,
+): Promise<SkillConfig[]> {
+  if (!query) {
+    return skills;
+  }
+
+  const names = skills.map((skill) => skill.name);
+  const skillMap = new Map(skills.map((skill) => [skill.name, skill]));
+
+  try {
+    const fzf = new AsyncFzf(names, {
+      fuzzy: 'v2',
+      casing: 'case-insensitive',
+    });
+    const results = (await fzf.find(query)) as Array<{ item: string }>;
+    return results
+      .map((result) => skillMap.get(result.item))
+      .filter((skill): skill is SkillConfig => !!skill);
+  } catch (error) {
+    console.error('[skillsCommand] Fuzzy match failed:', error);
+    const lowerQuery = query.toLowerCase();
+    return skills.filter((skill) =>
+      skill.name.toLowerCase().startsWith(lowerQuery),
+    );
+  }
+}

packages/cli/src/ui/commands/types.ts

@@ -209,6 +209,12 @@ export enum CommandKind {
   MCP_PROMPT = 'mcp-prompt',
 }
 
+export interface CommandCompletionItem {
+  value: string;
+  label?: string;
+  description?: string;
+}
+
 // The standardized contract for any command in the system.
 export interface SlashCommand {
   name: string;
@@ -234,7 +240,7 @@ export interface SlashCommand {
   completion?: (
     context: CommandContext,
     partialArg: string,
-  ) => Promise<string[]>;
+  ) => Promise<Array<string | CommandCompletionItem> | null>;
 
   subCommands?: SlashCommand[];
 }

packages/cli/src/ui/components/Composer.tsx

@@ -26,6 +26,7 @@ import { useSettings } from '../contexts/SettingsContext.js';
 import { ApprovalMode } from '@qwen-code/qwen-code-core';
 import { StreamingState } from '../types.js';
 import { ConfigInitDisplay } from '../components/ConfigInitDisplay.js';
+import { FeedbackDialog } from '../FeedbackDialog.js';
 import { t } from '../../i18n/index.js';
 
 export const Composer = () => {
@@ -134,6 +135,8 @@ export const Composer = () => {
         </OverflowProvider>
       )}
 
+      {uiState.isFeedbackDialogOpen && <FeedbackDialog />}
+
       {uiState.isInputActive && (
         <InputPrompt
           buffer={uiState.buffer}

packages/cli/src/ui/components/HistoryItemDisplay.tsx

@@ -30,6 +30,7 @@ import { Help } from './Help.js';
 import type { SlashCommand } from '../commands/types.js';
 import { ExtensionsList } from './views/ExtensionsList.js';
 import { getMCPServerStatus } from '@qwen-code/qwen-code-core';
+import { SkillsList } from './views/SkillsList.js';
 import { ToolsList } from './views/ToolsList.js';
 import { McpStatus } from './views/McpStatus.js';
 
@@ -153,6 +154,9 @@ const HistoryItemDisplayComponent: React.FC<HistoryItemDisplayProps> = ({
           showDescriptions={itemForDisplay.showDescriptions}
         />
       )}
+      {itemForDisplay.type === 'skills_list' && (
+        <SkillsList skills={itemForDisplay.skills} />
+      )}
       {itemForDisplay.type === 'mcp_status' && (
         <McpStatus {...itemForDisplay} serverStatus={getMCPServerStatus} />
       )}

packages/cli/src/ui/components/InputPrompt.test.tsx

@@ -33,6 +33,9 @@ vi.mock('../hooks/useCommandCompletion.js');
 vi.mock('../hooks/useInputHistory.js');
 vi.mock('../hooks/useReverseSearchCompletion.js');
 vi.mock('../utils/clipboardUtils.js');
+vi.mock('../contexts/UIStateContext.js', () => ({
+  useUIState: vi.fn(() => ({ isFeedbackDialogOpen: false })),
+}));
 
 const mockSlashCommands: SlashCommand[] = [
   {
@@ -278,7 +281,7 @@ describe('InputPrompt', () => {
     unmount();
   });
 
-  it('should call completion.navigateUp for both up arrow and Ctrl+P when suggestions are showing', async () => {
+  it('should call completion.navigateUp for up arrow when suggestions are showing', async () => {
     mockedUseCommandCompletion.mockReturnValue({
       ...mockCommandCompletion,
       showSuggestions: true,
@@ -293,19 +296,22 @@ describe('InputPrompt', () => {
     const { stdin, unmount } = renderWithProviders(<InputPrompt {...props} />);
     await wait();
 
-    // Test up arrow
+    // Test up arrow for completion navigation
     stdin.write('\u001B[A'); // Up arrow
     await wait();
+    expect(mockCommandCompletion.navigateUp).toHaveBeenCalledTimes(1);
+    expect(mockCommandCompletion.navigateDown).not.toHaveBeenCalled();
 
+    // Ctrl+P should navigate history, not completion
     stdin.write('\u0010'); // Ctrl+P
     await wait();
-    expect(mockCommandCompletion.navigateUp).toHaveBeenCalledTimes(2);
-    expect(mockCommandCompletion.navigateDown).not.toHaveBeenCalled();
+    expect(mockCommandCompletion.navigateUp).toHaveBeenCalledTimes(1);
+    expect(mockInputHistory.navigateUp).toHaveBeenCalled();
 
     unmount();
   });
 
-  it('should call completion.navigateDown for both down arrow and Ctrl+N when suggestions are showing', async () => {
+  it('should call completion.navigateDown for down arrow when suggestions are showing', async () => {
     mockedUseCommandCompletion.mockReturnValue({
       ...mockCommandCompletion,
       showSuggestions: true,
@@ -319,14 +325,17 @@ describe('InputPrompt', () => {
     const { stdin, unmount } = renderWithProviders(<InputPrompt {...props} />);
     await wait();
 
-    // Test down arrow
+    // Test down arrow for completion navigation
     stdin.write('\u001B[B'); // Down arrow
     await wait();
+    expect(mockCommandCompletion.navigateDown).toHaveBeenCalledTimes(1);
+    expect(mockCommandCompletion.navigateUp).not.toHaveBeenCalled();
 
+    // Ctrl+N should navigate history, not completion
     stdin.write('\u000E'); // Ctrl+N
     await wait();
-    expect(mockCommandCompletion.navigateDown).toHaveBeenCalledTimes(2);
-    expect(mockCommandCompletion.navigateUp).not.toHaveBeenCalled();
+    expect(mockCommandCompletion.navigateDown).toHaveBeenCalledTimes(1);
+    expect(mockInputHistory.navigateDown).toHaveBeenCalled();
 
     unmount();
   });
@@ -764,6 +773,8 @@ describe('InputPrompt', () => {
         mockCommandContext,
         false,
         expect.any(Object),
+        // active parameter: completion enabled when not just navigated history
+        true,
       );
 
       unmount();
@@ -791,6 +802,8 @@ describe('InputPrompt', () => {
         mockCommandContext,
         false,
         expect.any(Object),
+        // active parameter: completion enabled when not just navigated history
+        true,
       );
 
       unmount();
@@ -818,6 +831,8 @@ describe('InputPrompt', () => {
         mockCommandContext,
         false,
         expect.any(Object),
+        // active parameter: completion enabled when not just navigated history
+        true,
       );
 
       unmount();
@@ -845,6 +860,8 @@ describe('InputPrompt', () => {
         mockCommandContext,
         false,
         expect.any(Object),
+        // active parameter: completion enabled when not just navigated history
+        true,
       );
 
       unmount();
@@ -872,6 +889,8 @@ describe('InputPrompt', () => {
         mockCommandContext,
         false,
         expect.any(Object),
+        // active parameter: completion enabled when not just navigated history
+        true,
       );
 
       unmount();
@@ -900,6 +919,8 @@ describe('InputPrompt', () => {
         mockCommandContext,
         false,
         expect.any(Object),
+        // active parameter: completion enabled when not just navigated history
+        true,
       );
 
       unmount();
@@ -927,6 +948,8 @@ describe('InputPrompt', () => {
         mockCommandContext,
         false,
         expect.any(Object),
+        // active parameter: completion enabled when not just navigated history
+        true,
       );
 
       unmount();
@@ -955,6 +978,8 @@ describe('InputPrompt', () => {
         mockCommandContext,
         false,
         expect.any(Object),
+        // active parameter: completion enabled when not just navigated history
+        true,
       );
 
       unmount();
@@ -983,6 +1008,8 @@ describe('InputPrompt', () => {
         mockCommandContext,
         false,
         expect.any(Object),
+        // active parameter: completion enabled when not just navigated history
+        true,
       );
 
       unmount();
@@ -1011,6 +1038,8 @@ describe('InputPrompt', () => {
         mockCommandContext,
         false,
         expect.any(Object),
+        // active parameter: completion enabled when not just navigated history
+        true,
       );
 
       unmount();
@@ -1039,6 +1068,8 @@ describe('InputPrompt', () => {
         mockCommandContext,
         false,
         expect.any(Object),
+        // active parameter: completion enabled when not just navigated history
+        true,
       );
 
       unmount();
@@ -1069,6 +1100,8 @@ describe('InputPrompt', () => {
         mockCommandContext,
         false,
         expect.any(Object),
+        // active parameter: completion enabled when not just navigated history
+        true,
       );
 
       unmount();
@@ -1097,6 +1130,8 @@ describe('InputPrompt', () => {
         mockCommandContext,
         false,
         expect.any(Object),
+        // active parameter: completion enabled when not just navigated history
+        true,
       );
 
       unmount();
@@ -1127,6 +1162,8 @@ describe('InputPrompt', () => {
         mockCommandContext,
         false,
         expect.any(Object),
+        // active parameter: completion enabled when not just navigated history
+        true,
       );
 
       unmount();

packages/cli/src/ui/components/InputPrompt.tsx

@@ -36,6 +36,8 @@ import {
 import * as path from 'node:path';
 import { SCREEN_READER_USER_PREFIX } from '../textConstants.js';
 import { useShellFocusState } from '../contexts/ShellFocusContext.js';
+import { useUIState } from '../contexts/UIStateContext.js';
+import { FEEDBACK_DIALOG_KEYS } from '../FeedbackDialog.js';
 export interface InputPromptProps {
   buffer: TextBuffer;
   onSubmit: (value: string) => void;
@@ -100,6 +102,7 @@ export const InputPrompt: React.FC<InputPromptProps> = ({
   isEmbeddedShellFocused,
 }) => {
   const isShellFocused = useShellFocusState();
+  const uiState = useUIState();
   const [justNavigatedHistory, setJustNavigatedHistory] = useState(false);
   const [escPressCount, setEscPressCount] = useState(0);
   const [showEscapePrompt, setShowEscapePrompt] = useState(false);
@@ -135,6 +138,8 @@ export const InputPrompt: React.FC<InputPromptProps> = ({
     commandContext,
     reverseSearchActive,
     config,
+    // Suppress completion when history navigation just occurred
+    !justNavigatedHistory,
   );
 
   const reverseSearchCompletion = useReverseSearchCompletion(
@@ -219,9 +224,9 @@ export const InputPrompt: React.FC<InputPromptProps> = ({
   const inputHistory = useInputHistory({
     userMessages,
     onSubmit: handleSubmitAndClear,
-    isActive:
-      (!completion.showSuggestions || completion.suggestions.length === 1) &&
-      !shellModeActive,
+    // History navigation (Ctrl+P/N) now always works since completion navigation
+    // only uses arrow keys. Only disable in shell mode.
+    isActive: !shellModeActive,
     currentQuery: buffer.text,
     onChange: customSetTextAndResetCompletionSignal,
   });
@@ -326,6 +331,14 @@ export const InputPrompt: React.FC<InputPromptProps> = ({
         return;
       }
 
+      // Intercept feedback dialog option keys (1, 2) when dialog is open
+      if (
+        uiState.isFeedbackDialogOpen &&
+        (FEEDBACK_DIALOG_KEYS as readonly string[]).includes(key.name)
+      ) {
+        return;
+      }
+
       // Reset ESC count and hide prompt on any non-ESC key
       if (key.name !== 'escape') {
         if (escPressCount > 0 || showEscapePrompt) {
@@ -670,6 +683,7 @@ export const InputPrompt: React.FC<InputPromptProps> = ({
       recentPasteTime,
       commandSearchActive,
       commandSearchCompletion,
+      uiState,
     ],
   );
 

packages/cli/src/ui/components/ModelDialog.tsx

@@ -275,7 +275,7 @@ export function ModelDialog({ onClose }: ModelDialogProps): React.JSX.Element {
         persistModelSelection(settings, effectiveModelId);
         persistAuthTypeSelection(settings, effectiveAuthType);
 
-        const baseUrl = after?.baseUrl ?? '(default)';
+        const baseUrl = after?.baseUrl ?? t('(default)');
         const maskedKey = maskApiKey(after?.apiKey);
         uiState?.historyManager.addItem(
           {
@@ -322,7 +322,7 @@ export function ModelDialog({ onClose }: ModelDialogProps): React.JSX.Element {
             <>
               <ConfigRow
                 label="Base URL"
-                value={effectiveConfig?.baseUrl ?? ''}
+                value={effectiveConfig?.baseUrl ?? t('(default)')}
                 badge={formatSourceBadge(sources['baseUrl'])}
               />
               <ConfigRow

packages/cli/src/ui/components/SettingsDialog.test.tsx

@@ -1331,9 +1331,7 @@ describe('SettingsDialog', () => {
           truncateToolOutputThreshold: 50000,
           truncateToolOutputLines: 1000,
         },
-        context: {
-          discoveryMaxDirs: 500,
-        },
+        context: {},
         model: {
           maxSessionTurns: 100,
           skipNextSpeakerCheck: false,
@@ -1466,7 +1464,6 @@ describe('SettingsDialog', () => {
             disableFuzzySearch: true,
           },
           loadMemoryFromIncludeDirectories: true,
-          discoveryMaxDirs: 100,
         },
       });
       const onSelect = vi.fn();

packages/cli/src/ui/components/SuggestionsDisplay.tsx

@@ -106,7 +106,7 @@ export function SuggestionsDisplay({
             </Box>
 
             {suggestion.description && (
-              <Box flexGrow={1} paddingLeft={3}>
+              <Box flexGrow={1} paddingLeft={2}>
                 <Text color={textColor} wrap="truncate">
                   {suggestion.description}
                 </Text>

packages/cli/src/ui/components/messages/InfoMessage.tsx

@@ -23,7 +23,7 @@ export const InfoMessage: React.FC<InfoMessageProps> = ({ text }) => {
   const prefixWidth = prefix.length;
 
   return (
-    <Box flexDirection="row" marginTop={1}>
+    <Box flexDirection="row" marginBottom={1}>
       <Box width={prefixWidth}>
         <Text color={theme.status.warning}>{prefix}</Text>
       </Box>

packages/cli/src/ui/components/messages/WarningMessage.tsx

@@ -18,7 +18,7 @@ export const WarningMessage: React.FC<WarningMessageProps> = ({ text }) => {
   const prefixWidth = 3;
 
   return (
-    <Box flexDirection="row" marginTop={1}>
+    <Box flexDirection="row" marginBottom={1}>
       <Box width={prefixWidth}>
         <Text color={Colors.AccentYellow}>{prefix}</Text>
       </Box>

packages/cli/src/ui/components/views/SkillsList.tsx

@@ -0,0 +1,36 @@
+/**
+ * @license
+ * Copyright 2025 Qwen
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import type React from 'react';
+import { Box, Text } from 'ink';
+import { theme } from '../../semantic-colors.js';
+import { type SkillDefinition } from '../../types.js';
+import { t } from '../../../i18n/index.js';
+
+interface SkillsListProps {
+  skills: readonly SkillDefinition[];
+}
+
+export const SkillsList: React.FC<SkillsListProps> = ({ skills }) => (
+  <Box flexDirection="column" marginBottom={1}>
+    <Text bold color={theme.text.primary}>
+      {t('Available skills:')}
+    </Text>
+    <Box height={1} />
+    {skills.length > 0 ? (
+      skills.map((skill) => (
+        <Box key={skill.name} flexDirection="row">
+          <Text color={theme.text.primary}>{'  '}- </Text>
+          <Text bold color={theme.text.accent}>
+            {skill.name}
+          </Text>
+        </Box>
+      ))
+    ) : (
+      <Text color={theme.text.primary}> {t('No skills available')}</Text>
+    )}
+  </Box>
+);

packages/cli/src/ui/contexts/UIActionsContext.tsx

@@ -66,6 +66,10 @@ export interface UIActions {
   openResumeDialog: () => void;
   closeResumeDialog: () => void;
   handleResume: (sessionId: string) => void;
+  // Feedback dialog
+  openFeedbackDialog: () => void;
+  closeFeedbackDialog: () => void;
+  submitFeedback: (rating: number) => void;
 }
 
 export const UIActionsContext = createContext<UIActions | null>(null);

packages/cli/src/ui/contexts/UIStateContext.tsx

@@ -126,6 +126,8 @@ export interface UIState {
   // Subagent dialogs
   isSubagentCreateDialogOpen: boolean;
   isAgentsManagerDialogOpen: boolean;
+  // Feedback dialog
+  isFeedbackDialogOpen: boolean;
 }
 
 export const UIStateContext = createContext<UIState | null>(null);

packages/cli/src/ui/hooks/useCommandCompletion.tsx

@@ -45,6 +45,8 @@ export function useCommandCompletion(
   commandContext: CommandContext,
   reverseSearchActive: boolean = false,
   config?: Config,
+  // When false, suppresses showing suggestions (e.g., after history navigation)
+  active: boolean = true,
 ): UseCommandCompletionReturn {
   const {
     suggestions,
@@ -152,7 +154,11 @@ export function useCommandCompletion(
   }, [suggestions, setActiveSuggestionIndex, setVisibleStartIndex]);
 
   useEffect(() => {
-    if (completionMode === CompletionMode.IDLE || reverseSearchActive) {
+    if (
+      completionMode === CompletionMode.IDLE ||
+      reverseSearchActive ||
+      !active
+    ) {
       resetCompletionState();
       return;
     }
@@ -163,6 +169,7 @@ export function useCommandCompletion(
     suggestions.length,
     isLoadingSuggestions,
     reverseSearchActive,
+    active,
     resetCompletionState,
     setShowSuggestions,
   ]);

packages/cli/src/ui/hooks/useFeedbackDialog.ts

@@ -0,0 +1,178 @@
+import { useState, useCallback, useEffect } from 'react';
+import * as fs from 'node:fs';
+import {
+  type Config,
+  logUserFeedback,
+  UserFeedbackEvent,
+  type UserFeedbackRating,
+  isNodeError,
+  AuthType,
+} from '@qwen-code/qwen-code-core';
+import { StreamingState, MessageType, type HistoryItem } from '../types.js';
+import {
+  SettingScope,
+  type LoadedSettings,
+  USER_SETTINGS_PATH,
+} from '../../config/settings.js';
+import type { SessionStatsState } from '../contexts/SessionContext.js';
+import stripJsonComments from 'strip-json-comments';
+
+const FEEDBACK_SHOW_PROBABILITY = 0.25; // 25% probability of showing feedback dialog
+const MIN_TOOL_CALLS = 10; // Minimum tool calls to show feedback dialog
+const MIN_USER_MESSAGES = 5; // Minimum user messages to show feedback dialog
+
+// Fatigue mechanism constants
+const FEEDBACK_COOLDOWN_HOURS = 24; // Hours to wait before showing feedback dialog again
+
+/**
+ * Check if the last message in the conversation history is an AI response
+ */
+const lastMessageIsAIResponse = (history: HistoryItem[]): boolean =>
+  history.length > 0 && history[history.length - 1].type === MessageType.GEMINI;
+
+/**
+ * Read feedbackLastShownTimestamp directly from the user settings file
+ */
+const getFeedbackLastShownTimestampFromFile = (): number => {
+  try {
+    if (fs.existsSync(USER_SETTINGS_PATH)) {
+      const content = fs.readFileSync(USER_SETTINGS_PATH, 'utf-8');
+      const settings = JSON.parse(stripJsonComments(content));
+      return settings?.ui?.feedbackLastShownTimestamp ?? 0;
+    }
+  } catch (error) {
+    if (isNodeError(error) && error.code !== 'ENOENT') {
+      console.warn(
+        'Failed to read feedbackLastShownTimestamp from settings file:',
+        error,
+      );
+    }
+  }
+  return 0;
+};
+
+/**
+ * Check if we should show the feedback dialog based on fatigue mechanism
+ */
+const shouldShowFeedbackBasedOnFatigue = (): boolean => {
+  const feedbackLastShownTimestamp = getFeedbackLastShownTimestampFromFile();
+
+  const now = Date.now();
+  const timeSinceLastShown = now - feedbackLastShownTimestamp;
+  const cooldownMs = FEEDBACK_COOLDOWN_HOURS * 60 * 60 * 1000;
+
+  return timeSinceLastShown >= cooldownMs;
+};
+
+/**
+ * Check if the session meets the minimum requirements for showing feedback
+ * Either tool calls > 10 OR user messages > 5
+ */
+const meetsMinimumSessionRequirements = (
+  sessionStats: SessionStatsState,
+): boolean => {
+  const toolCallsCount = sessionStats.metrics.tools.totalCalls;
+  const userMessagesCount = sessionStats.promptCount;
+
+  return (
+    toolCallsCount > MIN_TOOL_CALLS || userMessagesCount > MIN_USER_MESSAGES
+  );
+};
+
+export interface UseFeedbackDialogProps {
+  config: Config;
+  settings: LoadedSettings;
+  streamingState: StreamingState;
+  history: HistoryItem[];
+  sessionStats: SessionStatsState;
+}
+
+export const useFeedbackDialog = ({
+  config,
+  settings,
+  streamingState,
+  history,
+  sessionStats,
+}: UseFeedbackDialogProps) => {
+  // Feedback dialog state
+  const [isFeedbackDialogOpen, setIsFeedbackDialogOpen] = useState(false);
+
+  const openFeedbackDialog = useCallback(() => {
+    setIsFeedbackDialogOpen(true);
+
+    // Record the timestamp when feedback dialog is shown (fire and forget)
+    settings.setValue(
+      SettingScope.User,
+      'ui.feedbackLastShownTimestamp',
+      Date.now(),
+    );
+  }, [settings]);
+
+  const closeFeedbackDialog = useCallback(
+    () => setIsFeedbackDialogOpen(false),
+    [],
+  );
+
+  const submitFeedback = useCallback(
+    (rating: number) => {
+      // Create and log the feedback event
+      const feedbackEvent = new UserFeedbackEvent(
+        sessionStats.sessionId,
+        rating as UserFeedbackRating,
+        config.getModel(),
+        config.getApprovalMode(),
+      );
+
+      logUserFeedback(config, feedbackEvent);
+      closeFeedbackDialog();
+    },
+    [config, sessionStats, closeFeedbackDialog],
+  );
+
+  useEffect(() => {
+    const checkAndShowFeedback = () => {
+      if (streamingState === StreamingState.Idle && history.length > 0) {
+        // Show feedback dialog if:
+        // 1. User is authenticated via QWEN_OAUTH
+        // 2. Qwen logger is enabled (required for feedback submission)
+        // 3. User feedback is enabled in settings
+        // 4. The last message is an AI response
+        // 5. Random chance (25% probability)
+        // 6. Meets minimum requirements (tool calls > 10 OR user messages > 5)
+        // 7. Fatigue mechanism allows showing (not shown recently across sessions)
+        if (
+          config.getAuthType() !== AuthType.QWEN_OAUTH ||
+          !config.getUsageStatisticsEnabled() ||
+          settings.merged.ui?.enableUserFeedback === false ||
+          !lastMessageIsAIResponse(history) ||
+          Math.random() > FEEDBACK_SHOW_PROBABILITY ||
+          !meetsMinimumSessionRequirements(sessionStats)
+        ) {
+          return;
+        }
+
+        // Check fatigue mechanism (synchronous)
+        if (shouldShowFeedbackBasedOnFatigue()) {
+          openFeedbackDialog();
+        }
+      }
+    };
+
+    checkAndShowFeedback();
+  }, [
+    streamingState,
+    history,
+    sessionStats,
+    isFeedbackDialogOpen,
+    openFeedbackDialog,
+    settings.merged.ui?.enableUserFeedback,
+    config,
+  ]);
+
+  return {
+    isFeedbackDialogOpen,
+    openFeedbackDialog,
+    closeFeedbackDialog,
+    submitFeedback,
+  };
+};

packages/cli/src/ui/hooks/useSlashCompletion.test.ts

@@ -573,6 +573,45 @@ describe('useSlashCompletion', () => {
       });
     });
 
+    it('should map completion items with descriptions for argument suggestions', async () => {
+      const mockCompletionFn = vi.fn().mockResolvedValue([
+        { value: 'pdf', description: 'Create PDF documents' },
+        { value: 'xlsx', description: 'Work with spreadsheets' },
+      ]);
+
+      const slashCommands = [
+        createTestCommand({
+          name: 'skills',
+          description: 'List available skills',
+          completion: mockCompletionFn,
+        }),
+      ];
+
+      const { result } = renderHook(() =>
+        useTestHarnessForSlashCompletion(
+          true,
+          '/skills ',
+          slashCommands,
+          mockCommandContext,
+        ),
+      );
+
+      await waitFor(() => {
+        expect(result.current.suggestions).toEqual([
+          {
+            label: 'pdf',
+            value: 'pdf',
+            description: 'Create PDF documents',
+          },
+          {
+            label: 'xlsx',
+            value: 'xlsx',
+            description: 'Work with spreadsheets',
+          },
+        ]);
+      });
+    });
+
     it('should call command.completion with an empty string when args start with a space', async () => {
       const mockCompletionFn = vi
         .fn()

packages/cli/src/ui/hooks/useSlashCompletion.ts

@@ -9,6 +9,7 @@ import { AsyncFzf } from 'fzf';
 import type { Suggestion } from '../components/SuggestionsDisplay.js';
 import {
   CommandKind,
+  type CommandCompletionItem,
   type CommandContext,
   type SlashCommand,
 } from '../commands/types.js';
@@ -215,10 +216,9 @@ function useCommandSuggestions(
             )) || [];
 
           if (!signal.aborted) {
-            const finalSuggestions = results.map((s) => ({
-              label: s,
-              value: s,
-            }));
+            const finalSuggestions = results
+              .map((item) => toSuggestion(item))
+              .filter((suggestion): suggestion is Suggestion => !!suggestion);
             setSuggestions(finalSuggestions);
             setIsLoading(false);
           }
@@ -310,6 +310,20 @@ function useCommandSuggestions(
   return { suggestions, isLoading };
 }
 
+function toSuggestion(item: string | CommandCompletionItem): Suggestion | null {
+  if (typeof item === 'string') {
+    return { label: item, value: item };
+  }
+  if (!item.value) {
+    return null;
+  }
+  return {
+    label: item.label ?? item.value,
+    value: item.value,
+    description: item.description,
+  };
+}
+
 function useCompletionPositions(
   query: string | null,
   parserResult: CommandParserResult,

packages/cli/src/ui/keyMatchers.test.ts

@@ -38,10 +38,10 @@ describe('keyMatchers', () => {
     [Command.NAVIGATION_DOWN]: (key: Key) => key.name === 'down',
     [Command.ACCEPT_SUGGESTION]: (key: Key) =>
       key.name === 'tab' || (key.name === 'return' && !key.ctrl),
-    [Command.COMPLETION_UP]: (key: Key) =>
-      key.name === 'up' || (key.ctrl && key.name === 'p'),
-    [Command.COMPLETION_DOWN]: (key: Key) =>
-      key.name === 'down' || (key.ctrl && key.name === 'n'),
+    // Completion navigation only uses arrow keys (not Ctrl+P/N)
+    // to allow Ctrl+P/N to always navigate history
+    [Command.COMPLETION_UP]: (key: Key) => key.name === 'up',
+    [Command.COMPLETION_DOWN]: (key: Key) => key.name === 'down',
     [Command.ESCAPE]: (key: Key) => key.name === 'escape',
     [Command.SUBMIT]: (key: Key) =>
       key.name === 'return' && !key.ctrl && !key.meta && !key.paste,
@@ -164,14 +164,26 @@ describe('keyMatchers', () => {
       negative: [createKey('return', { ctrl: true }), createKey('space')],
     },
     {
+      // Completion navigation only uses arrow keys (not Ctrl+P/N)
+      // to allow Ctrl+P/N to always navigate history
       command: Command.COMPLETION_UP,
-      positive: [createKey('up'), createKey('p', { ctrl: true })],
-      negative: [createKey('p'), createKey('down')],
+      positive: [createKey('up')],
+      negative: [
+        createKey('p'),
+        createKey('down'),
+        createKey('p', { ctrl: true }),
+      ],
     },
     {
+      // Completion navigation only uses arrow keys (not Ctrl+P/N)
+      // to allow Ctrl+P/N to always navigate history
       command: Command.COMPLETION_DOWN,
-      positive: [createKey('down'), createKey('n', { ctrl: true })],
-      negative: [createKey('n'), createKey('up')],
+      positive: [createKey('down')],
+      negative: [
+        createKey('n'),
+        createKey('up'),
+        createKey('n', { ctrl: true }),
+      ],
     },
 
     // Text input

packages/cli/src/ui/types.ts

@@ -201,12 +201,21 @@ export interface ToolDefinition {
   description?: string;
 }
 
+export interface SkillDefinition {
+  name: string;
+}
+
 export type HistoryItemToolsList = HistoryItemBase & {
   type: 'tools_list';
   tools: ToolDefinition[];
   showDescriptions: boolean;
 };
 
+export type HistoryItemSkillsList = HistoryItemBase & {
+  type: 'skills_list';
+  skills: SkillDefinition[];
+};
+
 // JSON-friendly types for using as a simple data model showing info about an
 // MCP Server.
 export interface JsonMcpTool {
@@ -268,6 +277,7 @@ export type HistoryItemWithoutId =
   | HistoryItemCompression
   | HistoryItemExtensionsList
   | HistoryItemToolsList
+  | HistoryItemSkillsList
   | HistoryItemMcpStatus;
 
 export type HistoryItem = HistoryItemWithoutId & { id: number };
@@ -289,6 +299,7 @@ export enum MessageType {
   SUMMARY = 'summary',
   EXTENSIONS_LIST = 'extensions_list',
   TOOLS_LIST = 'tools_list',
+  SKILLS_LIST = 'skills_list',
   MCP_STATUS = 'mcp_status',
 }
 

packages/cli/src/utils/commentJson.test.ts

@@ -8,7 +8,10 @@ import { describe, it, expect, beforeEach, afterEach, vi } from 'vitest';
 import * as fs from 'node:fs';
 import * as path from 'node:path';
 import * as os from 'node:os';
-import { updateSettingsFilePreservingFormat } from './commentJson.js';
+import {
+  updateSettingsFilePreservingFormat,
+  applyUpdates,
+} from './commentJson.js';
 
 describe('commentJson', () => {
   let tempDir: string;
@@ -180,3 +183,18 @@ describe('commentJson', () => {
     });
   });
 });
+
+describe('applyUpdates', () => {
+  it('should apply updates correctly', () => {
+    const original = { a: 1, b: { c: 2 } };
+    const updates = { b: { c: 3 } };
+    const result = applyUpdates(original, updates);
+    expect(result).toEqual({ a: 1, b: { c: 3 } });
+  });
+  it('should apply updates correctly when empty', () => {
+    const original = { a: 1, b: { c: 2 } };
+    const updates = { b: {} };
+    const result = applyUpdates(original, updates);
+    expect(result).toEqual({ a: 1, b: {} });
+  });
+});

packages/cli/src/utils/commentJson.ts

@@ -38,7 +38,7 @@ export function updateSettingsFilePreservingFormat(
   fs.writeFileSync(filePath, updatedContent, 'utf-8');
 }
 
-function applyUpdates(
+export function applyUpdates(
   current: Record<string, unknown>,
   updates: Record<string, unknown>,
 ): Record<string, unknown> {
@@ -50,6 +50,7 @@ function applyUpdates(
       typeof value === 'object' &&
       value !== null &&
       !Array.isArray(value) &&
+      Object.keys(value).length > 0 &&
       typeof result[key] === 'object' &&
       result[key] !== null &&
       !Array.isArray(result[key])

packages/cli/src/utils/errors.test.ts

@@ -117,8 +117,33 @@ describe('errors', () => {
       expect(getErrorMessage(undefined)).toBe('undefined');
     });
 
-    it('should handle objects', () => {
-      const obj = { message: 'test' };
+    it('should extract message from error-like objects', () => {
+      const obj = { message: 'test error message' };
+      expect(getErrorMessage(obj)).toBe('test error message');
+    });
+
+    it('should stringify plain objects without message property', () => {
+      const obj = { code: 500, details: 'internal error' };
+      expect(getErrorMessage(obj)).toBe(
+        '{"code":500,"details":"internal error"}',
+      );
+    });
+
+    it('should handle empty objects', () => {
+      expect(getErrorMessage({})).toBe('{}');
+    });
+
+    it('should handle objects with non-string message property', () => {
+      const obj = { message: 123 };
+      expect(getErrorMessage(obj)).toBe('{"message":123}');
+    });
+
+    it('should fallback to String() when toJSON returns undefined', () => {
+      const obj = {
+        toJSON() {
+          return undefined;
+        },
+      };
       expect(getErrorMessage(obj)).toBe('[object Object]');
     });
   });

packages/cli/src/utils/errors.ts

@@ -18,6 +18,29 @@ export function getErrorMessage(error: unknown): string {
   if (error instanceof Error) {
     return error.message;
   }
+
+  // Handle objects with message property (error-like objects)
+  if (
+    error !== null &&
+    typeof error === 'object' &&
+    'message' in error &&
+    typeof (error as { message: unknown }).message === 'string'
+  ) {
+    return (error as { message: string }).message;
+  }
+
+  // Handle plain objects by stringifying them
+  if (error !== null && typeof error === 'object') {
+    try {
+      const stringified = JSON.stringify(error);
+      // JSON.stringify can return undefined for objects with toJSON() returning undefined
+      return stringified ?? String(error);
+    } catch {
+      // If JSON.stringify fails (circular reference, etc.), fall back to String
+      return String(error);
+    }
+  }
+
   return String(error);
 }
 

packages/cli/src/utils/modelConfigUtils.test.ts

@@ -0,0 +1,722 @@
+/**
+ * @license
+ * Copyright 2025 Qwen Team
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { describe, it, expect, beforeEach, afterEach, vi } from 'vitest';
+import {
+  AuthType,
+  resolveModelConfig,
+  type ProviderModelConfig,
+} from '@qwen-code/qwen-code-core';
+import {
+  getAuthTypeFromEnv,
+  resolveCliGenerationConfig,
+} from './modelConfigUtils.js';
+import type { Settings } from '../config/settings.js';
+
+vi.mock('@qwen-code/qwen-code-core', async (importOriginal) => {
+  const original =
+    await importOriginal<typeof import('@qwen-code/qwen-code-core')>();
+  return {
+    ...original,
+    resolveModelConfig: vi.fn(),
+  };
+});
+
+describe('modelConfigUtils', () => {
+  describe('getAuthTypeFromEnv', () => {
+    const originalEnv = process.env;
+
+    beforeEach(() => {
+      vi.resetModules();
+      // Start with a clean env - getAuthTypeFromEnv only checks auth-related vars
+      process.env = {};
+    });
+
+    afterEach(() => {
+      process.env = originalEnv;
+    });
+
+    it('should return USE_OPENAI when all OpenAI env vars are set', () => {
+      process.env['OPENAI_API_KEY'] = 'test-key';
+      process.env['OPENAI_MODEL'] = 'gpt-4';
+      process.env['OPENAI_BASE_URL'] = 'https://api.openai.com';
+
+      expect(getAuthTypeFromEnv()).toBe(AuthType.USE_OPENAI);
+    });
+
+    it('should return undefined when OpenAI env vars are incomplete', () => {
+      process.env['OPENAI_API_KEY'] = 'test-key';
+      process.env['OPENAI_MODEL'] = 'gpt-4';
+      // Missing OPENAI_BASE_URL
+
+      expect(getAuthTypeFromEnv()).toBeUndefined();
+    });
+
+    it('should return QWEN_OAUTH when QWEN_OAUTH is set', () => {
+      process.env['QWEN_OAUTH'] = 'true';
+
+      expect(getAuthTypeFromEnv()).toBe(AuthType.QWEN_OAUTH);
+    });
+
+    it('should return USE_GEMINI when Gemini env vars are set', () => {
+      process.env['GEMINI_API_KEY'] = 'test-key';
+      process.env['GEMINI_MODEL'] = 'gemini-pro';
+
+      expect(getAuthTypeFromEnv()).toBe(AuthType.USE_GEMINI);
+    });
+
+    it('should return undefined when Gemini env vars are incomplete', () => {
+      process.env['GEMINI_API_KEY'] = 'test-key';
+      // Missing GEMINI_MODEL
+
+      expect(getAuthTypeFromEnv()).toBeUndefined();
+    });
+
+    it('should return USE_VERTEX_AI when Google env vars are set', () => {
+      process.env['GOOGLE_API_KEY'] = 'test-key';
+      process.env['GOOGLE_MODEL'] = 'vertex-model';
+
+      expect(getAuthTypeFromEnv()).toBe(AuthType.USE_VERTEX_AI);
+    });
+
+    it('should return undefined when Google env vars are incomplete', () => {
+      process.env['GOOGLE_API_KEY'] = 'test-key';
+      // Missing GOOGLE_MODEL
+
+      expect(getAuthTypeFromEnv()).toBeUndefined();
+    });
+
+    it('should return USE_ANTHROPIC when Anthropic env vars are set', () => {
+      process.env['ANTHROPIC_API_KEY'] = 'test-key';
+      process.env['ANTHROPIC_MODEL'] = 'claude-3';
+      process.env['ANTHROPIC_BASE_URL'] = 'https://api.anthropic.com';
+
+      expect(getAuthTypeFromEnv()).toBe(AuthType.USE_ANTHROPIC);
+    });
+
+    it('should return undefined when Anthropic env vars are incomplete', () => {
+      process.env['ANTHROPIC_API_KEY'] = 'test-key';
+      process.env['ANTHROPIC_MODEL'] = 'claude-3';
+      // Missing ANTHROPIC_BASE_URL
+
+      expect(getAuthTypeFromEnv()).toBeUndefined();
+    });
+
+    it('should prioritize QWEN_OAUTH over other auth types when explicitly set', () => {
+      process.env['QWEN_OAUTH'] = 'true';
+      process.env['OPENAI_API_KEY'] = 'test-key';
+      process.env['OPENAI_MODEL'] = 'gpt-4';
+      process.env['OPENAI_BASE_URL'] = 'https://api.openai.com';
+
+      // QWEN_OAUTH is checked first, so it should be returned even when other auth vars are set
+      expect(getAuthTypeFromEnv()).toBe(AuthType.QWEN_OAUTH);
+    });
+
+    it('should return undefined when no auth env vars are set', () => {
+      expect(getAuthTypeFromEnv()).toBeUndefined();
+    });
+  });
+
+  describe('resolveCliGenerationConfig', () => {
+    const originalEnv = process.env;
+    const originalConsoleWarn = console.warn;
+
+    beforeEach(() => {
+      vi.resetModules();
+      process.env = { ...originalEnv };
+      console.warn = vi.fn();
+    });
+
+    afterEach(() => {
+      process.env = originalEnv;
+      console.warn = originalConsoleWarn;
+      vi.clearAllMocks();
+    });
+
+    function makeMockSettings(overrides?: Partial<Settings>): Settings {
+      return {
+        model: { name: 'default-model' },
+        security: {
+          auth: {
+            apiKey: 'settings-api-key',
+            baseUrl: 'https://settings.example.com',
+          },
+        },
+        ...overrides,
+      } as Settings;
+    }
+
+    it('should resolve config from argv with highest precedence', () => {
+      const argv = {
+        model: 'argv-model',
+        openaiApiKey: 'argv-key',
+        openaiBaseUrl: 'https://argv.example.com',
+      };
+      const settings = makeMockSettings();
+      const selectedAuthType = AuthType.USE_OPENAI;
+
+      vi.mocked(resolveModelConfig).mockReturnValue({
+        config: {
+          model: 'argv-model',
+          apiKey: 'argv-key',
+          baseUrl: 'https://argv.example.com',
+        },
+        sources: {
+          model: { kind: 'cli', detail: '--model' },
+          apiKey: { kind: 'cli', detail: '--openaiApiKey' },
+          baseUrl: { kind: 'cli', detail: '--openaiBaseUrl' },
+        },
+        warnings: [],
+      });
+
+      const result = resolveCliGenerationConfig({
+        argv,
+        settings,
+        selectedAuthType,
+      });
+
+      expect(result.model).toBe('argv-model');
+      expect(result.apiKey).toBe('argv-key');
+      expect(result.baseUrl).toBe('https://argv.example.com');
+      expect(vi.mocked(resolveModelConfig)).toHaveBeenCalledWith(
+        expect.objectContaining({
+          cli: {
+            model: 'argv-model',
+            apiKey: 'argv-key',
+            baseUrl: 'https://argv.example.com',
+          },
+        }),
+      );
+    });
+
+    it('should resolve config from settings when argv is not provided', () => {
+      const argv = {};
+      const settings = makeMockSettings({
+        model: { name: 'settings-model' },
+        security: {
+          auth: {
+            apiKey: 'settings-key',
+            baseUrl: 'https://settings.example.com',
+          },
+        },
+      });
+      const selectedAuthType = AuthType.USE_OPENAI;
+
+      vi.mocked(resolveModelConfig).mockReturnValue({
+        config: {
+          model: 'settings-model',
+          apiKey: 'settings-key',
+          baseUrl: 'https://settings.example.com',
+        },
+        sources: {
+          model: { kind: 'settings', detail: 'model.name' },
+          apiKey: { kind: 'settings', detail: 'security.auth.apiKey' },
+          baseUrl: { kind: 'settings', detail: 'security.auth.baseUrl' },
+        },
+        warnings: [],
+      });
+
+      const result = resolveCliGenerationConfig({
+        argv,
+        settings,
+        selectedAuthType,
+      });
+
+      expect(result.model).toBe('settings-model');
+      expect(result.apiKey).toBe('settings-key');
+      expect(result.baseUrl).toBe('https://settings.example.com');
+    });
+
+    it('should merge generationConfig from settings', () => {
+      const argv = {};
+      const settings = makeMockSettings({
+        model: {
+          name: 'test-model',
+          generationConfig: {
+            samplingParams: {
+              temperature: 0.7,
+              max_tokens: 1000,
+            },
+            timeout: 5000,
+          } as Record<string, unknown>,
+        },
+      });
+      const selectedAuthType = AuthType.USE_OPENAI;
+
+      vi.mocked(resolveModelConfig).mockReturnValue({
+        config: {
+          model: 'test-model',
+          apiKey: '',
+          baseUrl: '',
+          samplingParams: {
+            temperature: 0.7,
+            max_tokens: 1000,
+          },
+          timeout: 5000,
+        },
+        sources: {},
+        warnings: [],
+      });
+
+      const result = resolveCliGenerationConfig({
+        argv,
+        settings,
+        selectedAuthType,
+      });
+
+      expect(result.generationConfig.samplingParams?.temperature).toBe(0.7);
+      expect(result.generationConfig.samplingParams?.max_tokens).toBe(1000);
+      expect(result.generationConfig.timeout).toBe(5000);
+    });
+
+    it('should resolve OpenAI logging from argv', () => {
+      const argv = {
+        openaiLogging: true,
+        openaiLoggingDir: '/custom/log/dir',
+      };
+      const settings = makeMockSettings();
+      const selectedAuthType = AuthType.USE_OPENAI;
+
+      vi.mocked(resolveModelConfig).mockReturnValue({
+        config: {
+          model: 'test-model',
+          apiKey: '',
+          baseUrl: '',
+        },
+        sources: {},
+        warnings: [],
+      });
+
+      const result = resolveCliGenerationConfig({
+        argv,
+        settings,
+        selectedAuthType,
+      });
+
+      expect(result.generationConfig.enableOpenAILogging).toBe(true);
+      expect(result.generationConfig.openAILoggingDir).toBe('/custom/log/dir');
+    });
+
+    it('should resolve OpenAI logging from settings when argv is undefined', () => {
+      const argv = {};
+      const settings = makeMockSettings({
+        model: {
+          name: 'test-model',
+          enableOpenAILogging: true,
+          openAILoggingDir: '/settings/log/dir',
+        },
+      });
+      const selectedAuthType = AuthType.USE_OPENAI;
+
+      vi.mocked(resolveModelConfig).mockReturnValue({
+        config: {
+          model: 'test-model',
+          apiKey: '',
+          baseUrl: '',
+        },
+        sources: {},
+        warnings: [],
+      });
+
+      const result = resolveCliGenerationConfig({
+        argv,
+        settings,
+        selectedAuthType,
+      });
+
+      expect(result.generationConfig.enableOpenAILogging).toBe(true);
+      expect(result.generationConfig.openAILoggingDir).toBe(
+        '/settings/log/dir',
+      );
+    });
+
+    it('should default OpenAI logging to false when not provided', () => {
+      const argv = {};
+      const settings = makeMockSettings();
+      const selectedAuthType = AuthType.USE_OPENAI;
+
+      vi.mocked(resolveModelConfig).mockReturnValue({
+        config: {
+          model: 'test-model',
+          apiKey: '',
+          baseUrl: '',
+        },
+        sources: {},
+        warnings: [],
+      });
+
+      const result = resolveCliGenerationConfig({
+        argv,
+        settings,
+        selectedAuthType,
+      });
+
+      expect(result.generationConfig.enableOpenAILogging).toBe(false);
+    });
+
+    it('should find modelProvider from settings when authType and model match', () => {
+      const argv = { model: 'provider-model' };
+      const modelProvider: ProviderModelConfig = {
+        id: 'provider-model',
+        name: 'Provider Model',
+        generationConfig: {
+          samplingParams: { temperature: 0.8 },
+        },
+      };
+      const settings = makeMockSettings({
+        modelProviders: {
+          [AuthType.USE_OPENAI]: [modelProvider],
+        },
+      });
+      const selectedAuthType = AuthType.USE_OPENAI;
+
+      vi.mocked(resolveModelConfig).mockReturnValue({
+        config: {
+          model: 'provider-model',
+          apiKey: '',
+          baseUrl: '',
+        },
+        sources: {},
+        warnings: [],
+      });
+
+      resolveCliGenerationConfig({
+        argv,
+        settings,
+        selectedAuthType,
+      });
+
+      expect(vi.mocked(resolveModelConfig)).toHaveBeenCalledWith(
+        expect.objectContaining({
+          modelProvider,
+        }),
+      );
+    });
+
+    it('should find modelProvider from settings.model.name when argv.model is not provided', () => {
+      const argv = {};
+      const modelProvider: ProviderModelConfig = {
+        id: 'settings-model',
+        name: 'Settings Model',
+        generationConfig: {
+          samplingParams: { temperature: 0.9 },
+        },
+      };
+      const settings = makeMockSettings({
+        model: { name: 'settings-model' },
+        modelProviders: {
+          [AuthType.USE_OPENAI]: [modelProvider],
+        },
+      });
+      const selectedAuthType = AuthType.USE_OPENAI;
+
+      vi.mocked(resolveModelConfig).mockReturnValue({
+        config: {
+          model: 'settings-model',
+          apiKey: '',
+          baseUrl: '',
+        },
+        sources: {},
+        warnings: [],
+      });
+
+      resolveCliGenerationConfig({
+        argv,
+        settings,
+        selectedAuthType,
+      });
+
+      expect(vi.mocked(resolveModelConfig)).toHaveBeenCalledWith(
+        expect.objectContaining({
+          modelProvider,
+        }),
+      );
+    });
+
+    it('should not find modelProvider when authType is undefined', () => {
+      const argv = { model: 'test-model' };
+      const settings = makeMockSettings({
+        modelProviders: {
+          [AuthType.USE_OPENAI]: [{ id: 'test-model', name: 'Test Model' }],
+        },
+      });
+      const selectedAuthType = undefined;
+
+      vi.mocked(resolveModelConfig).mockReturnValue({
+        config: {
+          model: 'test-model',
+          apiKey: '',
+          baseUrl: '',
+        },
+        sources: {},
+        warnings: [],
+      });
+
+      resolveCliGenerationConfig({
+        argv,
+        settings,
+        selectedAuthType,
+      });
+
+      expect(vi.mocked(resolveModelConfig)).toHaveBeenCalledWith(
+        expect.objectContaining({
+          modelProvider: undefined,
+        }),
+      );
+    });
+
+    it('should not find modelProvider when modelProviders is not an array', () => {
+      const argv = { model: 'test-model' };
+      const settings = makeMockSettings({
+        modelProviders: {
+          [AuthType.USE_OPENAI]: null as unknown as ProviderModelConfig[],
+        },
+      });
+      const selectedAuthType = AuthType.USE_OPENAI;
+
+      vi.mocked(resolveModelConfig).mockReturnValue({
+        config: {
+          model: 'test-model',
+          apiKey: '',
+          baseUrl: '',
+        },
+        sources: {},
+        warnings: [],
+      });
+
+      resolveCliGenerationConfig({
+        argv,
+        settings,
+        selectedAuthType,
+      });
+
+      expect(vi.mocked(resolveModelConfig)).toHaveBeenCalledWith(
+        expect.objectContaining({
+          modelProvider: undefined,
+        }),
+      );
+    });
+
+    it('should log warnings from resolveModelConfig', () => {
+      const argv = {};
+      const settings = makeMockSettings();
+      const selectedAuthType = AuthType.USE_OPENAI;
+
+      vi.mocked(resolveModelConfig).mockReturnValue({
+        config: {
+          model: 'test-model',
+          apiKey: '',
+          baseUrl: '',
+        },
+        sources: {},
+        warnings: ['Warning 1', 'Warning 2'],
+      });
+
+      resolveCliGenerationConfig({
+        argv,
+        settings,
+        selectedAuthType,
+      });
+
+      expect(console.warn).toHaveBeenCalledWith('Warning 1');
+      expect(console.warn).toHaveBeenCalledWith('Warning 2');
+    });
+
+    it('should use custom env when provided', () => {
+      const argv = {};
+      const settings = makeMockSettings();
+      const selectedAuthType = AuthType.USE_OPENAI;
+      const customEnv = {
+        OPENAI_API_KEY: 'custom-key',
+        OPENAI_MODEL: 'custom-model',
+      };
+
+      vi.mocked(resolveModelConfig).mockReturnValue({
+        config: {
+          model: 'custom-model',
+          apiKey: 'custom-key',
+          baseUrl: '',
+        },
+        sources: {},
+        warnings: [],
+      });
+
+      resolveCliGenerationConfig({
+        argv,
+        settings,
+        selectedAuthType,
+        env: customEnv,
+      });
+
+      expect(vi.mocked(resolveModelConfig)).toHaveBeenCalledWith(
+        expect.objectContaining({
+          env: customEnv,
+        }),
+      );
+    });
+
+    it('should use process.env when env is not provided', () => {
+      const argv = {};
+      const settings = makeMockSettings();
+      const selectedAuthType = AuthType.USE_OPENAI;
+
+      vi.mocked(resolveModelConfig).mockReturnValue({
+        config: {
+          model: 'test-model',
+          apiKey: '',
+          baseUrl: '',
+        },
+        sources: {},
+        warnings: [],
+      });
+
+      resolveCliGenerationConfig({
+        argv,
+        settings,
+        selectedAuthType,
+      });
+
+      expect(vi.mocked(resolveModelConfig)).toHaveBeenCalledWith(
+        expect.objectContaining({
+          env: process.env,
+        }),
+      );
+    });
+
+    it('should return empty strings for missing model, apiKey, and baseUrl', () => {
+      const argv = {};
+      const settings = makeMockSettings();
+      const selectedAuthType = AuthType.USE_OPENAI;
+
+      vi.mocked(resolveModelConfig).mockReturnValue({
+        config: {
+          model: '',
+          apiKey: '',
+          baseUrl: '',
+        },
+        sources: {},
+        warnings: [],
+      });
+
+      const result = resolveCliGenerationConfig({
+        argv,
+        settings,
+        selectedAuthType,
+      });
+
+      expect(result.model).toBe('');
+      expect(result.apiKey).toBe('');
+      expect(result.baseUrl).toBe('');
+    });
+
+    it('should merge resolved config with logging settings', () => {
+      const argv = {
+        openaiLogging: true,
+      };
+      const settings = makeMockSettings({
+        model: {
+          name: 'test-model',
+          generationConfig: {
+            timeout: 5000,
+          } as Record<string, unknown>,
+        },
+      });
+      const selectedAuthType = AuthType.USE_OPENAI;
+
+      vi.mocked(resolveModelConfig).mockReturnValue({
+        config: {
+          model: 'test-model',
+          apiKey: 'test-key',
+          baseUrl: 'https://test.com',
+          samplingParams: { temperature: 0.5 },
+        },
+        sources: {},
+        warnings: [],
+      });
+
+      const result = resolveCliGenerationConfig({
+        argv,
+        settings,
+        selectedAuthType,
+      });
+
+      expect(result.generationConfig).toEqual({
+        model: 'test-model',
+        apiKey: 'test-key',
+        baseUrl: 'https://test.com',
+        samplingParams: { temperature: 0.5 },
+        enableOpenAILogging: true,
+        openAILoggingDir: undefined,
+      });
+    });
+
+    it('should handle settings without model property', () => {
+      const argv = {};
+      const settings = makeMockSettings({
+        model: undefined as unknown as Settings['model'],
+      });
+      const selectedAuthType = AuthType.USE_OPENAI;
+
+      vi.mocked(resolveModelConfig).mockReturnValue({
+        config: {
+          model: '',
+          apiKey: '',
+          baseUrl: '',
+        },
+        sources: {},
+        warnings: [],
+      });
+
+      const result = resolveCliGenerationConfig({
+        argv,
+        settings,
+        selectedAuthType,
+      });
+
+      expect(result.model).toBe('');
+      expect(vi.mocked(resolveModelConfig)).toHaveBeenCalledWith(
+        expect.objectContaining({
+          settings: expect.objectContaining({
+            model: undefined,
+          }),
+        }),
+      );
+    });
+
+    it('should handle settings without security.auth property', () => {
+      const argv = {};
+      const settings = makeMockSettings({
+        security: undefined,
+      });
+      const selectedAuthType = AuthType.USE_OPENAI;
+
+      vi.mocked(resolveModelConfig).mockReturnValue({
+        config: {
+          model: '',
+          apiKey: '',
+          baseUrl: '',
+        },
+        sources: {},
+        warnings: [],
+      });
+
+      resolveCliGenerationConfig({
+        argv,
+        settings,
+        selectedAuthType,
+      });
+
+      expect(vi.mocked(resolveModelConfig)).toHaveBeenCalledWith(
+        expect.objectContaining({
+          settings: expect.objectContaining({
+            apiKey: undefined,
+            baseUrl: undefined,
+          }),
+        }),
+      );
+    });
+  });
+});

packages/cli/src/utils/modelConfigUtils.ts

@@ -10,6 +10,7 @@ import {
   type ContentGeneratorConfigSources,
   resolveModelConfig,
   type ModelConfigSourcesInput,
+  type ProviderModelConfig,
 } from '@qwen-code/qwen-code-core';
 import type { Settings } from '../config/settings.js';
 
@@ -43,20 +44,31 @@ export interface ResolvedCliGenerationConfig {
 }
 
 export function getAuthTypeFromEnv(): AuthType | undefined {
-  if (process.env['OPENAI_API_KEY']) {
-    return AuthType.USE_OPENAI;
-  }
   if (process.env['QWEN_OAUTH']) {
     return AuthType.QWEN_OAUTH;
   }
 
-  if (process.env['GEMINI_API_KEY']) {
+  if (
+    process.env['OPENAI_API_KEY'] &&
+    process.env['OPENAI_MODEL'] &&
+    process.env['OPENAI_BASE_URL']
+  ) {
+    return AuthType.USE_OPENAI;
+  }
+
+  if (process.env['GEMINI_API_KEY'] && process.env['GEMINI_MODEL']) {
     return AuthType.USE_GEMINI;
   }
-  if (process.env['GOOGLE_API_KEY']) {
+
+  if (process.env['GOOGLE_API_KEY'] && process.env['GOOGLE_MODEL']) {
     return AuthType.USE_VERTEX_AI;
   }
-  if (process.env['ANTHROPIC_API_KEY']) {
+
+  if (
+    process.env['ANTHROPIC_API_KEY'] &&
+    process.env['ANTHROPIC_MODEL'] &&
+    process.env['ANTHROPIC_BASE_URL']
+  ) {
     return AuthType.USE_ANTHROPIC;
   }
 
@@ -81,6 +93,21 @@ export function resolveCliGenerationConfig(
 
   const authType = selectedAuthType;
 
+  // Find modelProvider from settings.modelProviders based on authType and model
+  let modelProvider: ProviderModelConfig | undefined;
+  if (authType && settings.modelProviders) {
+    const providers = settings.modelProviders[authType];
+    if (providers && Array.isArray(providers)) {
+      // Try to find by requested model (from CLI or settings)
+      const requestedModel = argv.model || settings.model?.name;
+      if (requestedModel) {
+        modelProvider = providers.find((p) => p.id === requestedModel) as
+          | ProviderModelConfig
+          | undefined;
+      }
+    }
+  }
+
   const configSources: ModelConfigSourcesInput = {
     authType,
     cli: {
@@ -96,6 +123,7 @@ export function resolveCliGenerationConfig(
         | Partial<ContentGeneratorConfig>
         | undefined,
     },
+    modelProvider,
     env,
   };
 
@@ -103,7 +131,7 @@ export function resolveCliGenerationConfig(
 
   // Log warnings if any
   for (const warning of resolved.warnings) {
-    console.warn(`[modelProviderUtils] ${warning}`);
+    console.warn(warning);
   }
 
   // Resolve OpenAI logging config (CLI-specific, not part of core resolver)

packages/cli/src/utils/sandbox.ts

@@ -360,10 +360,10 @@ export async function start_sandbox(
     //
     // note this can only be done with binary linked from gemini-cli repo
     if (process.env['BUILD_SANDBOX']) {
-      if (!gcPath.includes('gemini-cli/packages/')) {
+      if (!gcPath.includes('qwen-code/packages/')) {
         throw new FatalSandboxError(
-          'Cannot build sandbox using installed gemini binary; ' +
-            'run `npm link ./packages/cli` under gemini-cli repo to switch to linked binary.',
+          'Cannot build sandbox using installed Qwen Code binary; ' +
+            'run `npm link ./packages/cli` under QwenCode-cli repo to switch to linked binary.',
         );
       } else {
         console.error('building sandbox ...');

packages/core/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@qwen-code/qwen-code-core",
-  "version": "0.7.0",
+  "version": "0.7.1",
   "description": "Qwen Code Core",
   "repository": {
     "type": "git",
@@ -27,7 +27,6 @@
     "@google/genai": "1.30.0",
     "@modelcontextprotocol/sdk": "^1.25.1",
     "@opentelemetry/api": "^1.9.0",
-    "async-mutex": "^0.5.0",
     "@opentelemetry/exporter-logs-otlp-grpc": "^0.203.0",
     "@opentelemetry/exporter-logs-otlp-http": "^0.203.0",
     "@opentelemetry/exporter-metrics-otlp-grpc": "^0.203.0",
@@ -40,7 +39,9 @@
     "@xterm/headless": "5.5.0",
     "ajv": "^8.17.1",
     "ajv-formats": "^3.0.0",
+    "async-mutex": "^0.5.0",
     "chardet": "^2.1.0",
+    "chokidar": "^4.0.3",
     "diff": "^7.0.0",
     "dotenv": "^17.1.0",
     "fast-levenshtein": "^2.0.6",

packages/core/src/config/config.ts

@@ -404,7 +404,7 @@ export class Config {
   private toolRegistry!: ToolRegistry;
   private promptRegistry!: PromptRegistry;
   private subagentManager!: SubagentManager;
-  private skillManager!: SkillManager;
+  private skillManager: SkillManager | null = null;
   private fileSystemService: FileSystemService;
   private contentGeneratorConfig!: ContentGeneratorConfig;
   private contentGeneratorConfigSources: ContentGeneratorConfigSources = {};
@@ -672,7 +672,10 @@ export class Config {
     }
     this.promptRegistry = new PromptRegistry();
     this.subagentManager = new SubagentManager(this);
-    this.skillManager = new SkillManager(this);
+    if (this.getExperimentalSkills()) {
+      this.skillManager = new SkillManager(this);
+      await this.skillManager.startWatching();
+    }
 
     // Load session subagents if they were provided before initialization
     if (this.sessionSubagents.length > 0) {
@@ -705,12 +708,15 @@ export class Config {
    * Exclusive for `OpenAIKeyPrompt` to update credentials via `/auth`
    * Delegates to ModelsConfig.
    */
-  updateCredentials(credentials: {
-    apiKey?: string;
-    baseUrl?: string;
-    model?: string;
-  }): void {
-    this._modelsConfig.updateCredentials(credentials);
+  updateCredentials(
+    credentials: {
+      apiKey?: string;
+      baseUrl?: string;
+      model?: string;
+    },
+    settingsGenerationConfig?: Partial<ContentGeneratorConfig>,
+  ): void {
+    this._modelsConfig.updateCredentials(credentials, settingsGenerationConfig);
   }
 
   /**
@@ -773,6 +779,13 @@ export class Config {
     return this.sessionId;
   }
 
+  /**
+   * Releases resources owned by the config instance.
+   */
+  async shutdown(): Promise<void> {
+    this.skillManager?.stopWatching();
+  }
+
   /**
    * Starts a new session and resets session-scoped services.
    */
@@ -1431,7 +1444,7 @@ export class Config {
     return this.subagentManager;
   }
 
-  getSkillManager(): SkillManager {
+  getSkillManager(): SkillManager | null {
     return this.skillManager;
   }
 

packages/core/src/core/anthropicContentGenerator/anthropicContentGenerator.test.ts

@@ -10,6 +10,7 @@ import type {
   GenerateContentParameters,
 } from '@google/genai';
 import { FinishReason, GenerateContentResponse } from '@google/genai';
+import type { ContentGeneratorConfig } from '../contentGenerator.js';
 
 // Mock the request tokenizer module BEFORE importing the class that uses it.
 const mockTokenizer = {
@@ -127,6 +128,32 @@ describe('AnthropicContentGenerator', () => {
     );
   });
 
+  it('merges customHeaders into defaultHeaders (does not replace defaults)', async () => {
+    const { AnthropicContentGenerator } = await importGenerator();
+    void new AnthropicContentGenerator(
+      {
+        model: 'claude-test',
+        apiKey: 'test-key',
+        baseUrl: 'https://example.invalid',
+        timeout: 10_000,
+        maxRetries: 2,
+        samplingParams: {},
+        schemaCompliance: 'auto',
+        reasoning: { effort: 'medium' },
+        customHeaders: {
+          'X-Custom': '1',
+        },
+      } as unknown as Record<string, unknown> as ContentGeneratorConfig,
+      mockConfig,
+    );
+
+    const headers = (anthropicState.constructorOptions?.['defaultHeaders'] ||
+      {}) as Record<string, string>;
+    expect(headers['User-Agent']).toContain('QwenCode/1.2.3');
+    expect(headers['anthropic-beta']).toContain('effort-2025-11-24');
+    expect(headers['X-Custom']).toBe('1');
+  });
+
   it('adds the effort beta header when reasoning.effort is set', async () => {
     const { AnthropicContentGenerator } = await importGenerator();
     void new AnthropicContentGenerator(

packages/core/src/core/anthropicContentGenerator/anthropicContentGenerator.ts

@@ -141,6 +141,7 @@ export class AnthropicContentGenerator implements ContentGenerator {
   private buildHeaders(): Record<string, string> {
     const version = this.cliConfig.getCliVersion() || 'unknown';
     const userAgent = `QwenCode/${version} (${process.platform}; ${process.arch})`;
+    const { customHeaders } = this.contentGeneratorConfig;
 
     const betas: string[] = [];
     const reasoning = this.contentGeneratorConfig.reasoning;
@@ -163,7 +164,7 @@ export class AnthropicContentGenerator implements ContentGenerator {
       headers['anthropic-beta'] = betas.join(',');
     }
 
-    return headers;
+    return customHeaders ? { ...headers, ...customHeaders } : headers;
   }
 
   private async buildRequest(

packages/core/src/core/contentGenerator.ts

@@ -91,6 +91,8 @@ export type ContentGeneratorConfig = {
   userAgent?: string;
   // Schema compliance mode for tool definitions
   schemaCompliance?: 'auto' | 'openapi_30';
+  // Custom HTTP headers to be sent with requests
+  customHeaders?: Record<string, string>;
 };
 
 // Keep the public ContentGeneratorConfigSources API, but reuse the generic
@@ -268,28 +270,28 @@ export function createContentGeneratorConfig(
 }
 
 export async function createContentGenerator(
-  config: ContentGeneratorConfig,
-  gcConfig: Config,
+  generatorConfig: ContentGeneratorConfig,
+  config: Config,
   isInitialAuth?: boolean,
 ): Promise<ContentGenerator> {
-  const validation = validateModelConfig(config, false);
+  const validation = validateModelConfig(generatorConfig, false);
   if (!validation.valid) {
     throw new Error(validation.errors.map((e) => e.message).join('\n'));
   }
 
-  if (config.authType === AuthType.USE_OPENAI) {
-    // Import OpenAIContentGenerator dynamically to avoid circular dependencies
+  const authType = generatorConfig.authType;
+  if (!authType) {
+    throw new Error('ContentGeneratorConfig must have an authType');
+  }
+
+  let baseGenerator: ContentGenerator;
+
+  if (authType === AuthType.USE_OPENAI) {
     const { createOpenAIContentGenerator } = await import(
       './openaiContentGenerator/index.js'
     );
-
-    // Always use OpenAIContentGenerator, logging is controlled by enableOpenAILogging flag
-    const generator = createOpenAIContentGenerator(config, gcConfig);
-    return new LoggingContentGenerator(generator, gcConfig);
-  }
-
-  if (config.authType === AuthType.QWEN_OAUTH) {
-    // Import required classes dynamically
+    baseGenerator = createOpenAIContentGenerator(generatorConfig, config);
+  } else if (authType === AuthType.QWEN_OAUTH) {
     const { getQwenOAuthClient: getQwenOauthClient } = await import(
       '../qwen/qwenOAuth2.js'
     );
@@ -298,44 +300,38 @@ export async function createContentGenerator(
     );
 
     try {
-      // Get the Qwen OAuth client (now includes integrated token management)
-      // If this is initial auth, require cached credentials to detect missing credentials
       const qwenClient = await getQwenOauthClient(
-        gcConfig,
+        config,
         isInitialAuth ? { requireCachedCredentials: true } : undefined,
       );
-
-      // Create the content generator with dynamic token management
-      const generator = new QwenContentGenerator(qwenClient, config, gcConfig);
-      return new LoggingContentGenerator(generator, gcConfig);
+      baseGenerator = new QwenContentGenerator(
+        qwenClient,
+        generatorConfig,
+        config,
+      );
     } catch (error) {
       throw new Error(
         `${error instanceof Error ? error.message : String(error)}`,
       );
     }
-  }
-
-  if (config.authType === AuthType.USE_ANTHROPIC) {
+  } else if (authType === AuthType.USE_ANTHROPIC) {
     const { createAnthropicContentGenerator } = await import(
       './anthropicContentGenerator/index.js'
     );
-
-    const generator = createAnthropicContentGenerator(config, gcConfig);
-    return new LoggingContentGenerator(generator, gcConfig);
-  }
-
-  if (
-    config.authType === AuthType.USE_GEMINI ||
-    config.authType === AuthType.USE_VERTEX_AI
+    baseGenerator = createAnthropicContentGenerator(generatorConfig, config);
+  } else if (
+    authType === AuthType.USE_GEMINI ||
+    authType === AuthType.USE_VERTEX_AI
   ) {
     const { createGeminiContentGenerator } = await import(
       './geminiContentGenerator/index.js'
     );
-    const generator = createGeminiContentGenerator(config, gcConfig);
-    return new LoggingContentGenerator(generator, gcConfig);
+    baseGenerator = createGeminiContentGenerator(generatorConfig, config);
+  } else {
+    throw new Error(
+      `Error creating contentGenerator: Unsupported authType: ${authType}`,
+    );
   }
 
-  throw new Error(
-    `Error creating contentGenerator: Unsupported authType: ${config.authType}`,
-  );
+  return new LoggingContentGenerator(baseGenerator, config, generatorConfig);
 }

packages/core/src/core/geminiContentGenerator/geminiContentGenerator.test.ts

@@ -39,6 +39,41 @@ describe('GeminiContentGenerator', () => {
     mockGoogleGenAI = vi.mocked(GoogleGenAI).mock.results[0].value;
   });
 
+  it('should merge customHeaders into existing httpOptions.headers', async () => {
+    vi.mocked(GoogleGenAI).mockClear();
+
+    void new GeminiContentGenerator(
+      {
+        apiKey: 'test-api-key',
+        httpOptions: {
+          headers: {
+            'X-Base': 'base',
+            'X-Override': 'base',
+          },
+        },
+      },
+      {
+        customHeaders: {
+          'X-Custom': 'custom',
+          'X-Override': 'custom',
+        },
+        // eslint-disable-next-line @typescript-eslint/no-explicit-any
+      } as any,
+    );
+
+    expect(vi.mocked(GoogleGenAI)).toHaveBeenCalledTimes(1);
+    expect(vi.mocked(GoogleGenAI)).toHaveBeenCalledWith({
+      apiKey: 'test-api-key',
+      httpOptions: {
+        headers: {
+          'X-Base': 'base',
+          'X-Custom': 'custom',
+          'X-Override': 'custom',
+        },
+      },
+    });
+  });
+
   it('should call generateContent on the underlying model', async () => {
     const request = { model: 'gemini-1.5-flash', contents: [] };
     const expectedResponse = { responseId: 'test-id' };

packages/core/src/core/geminiContentGenerator/geminiContentGenerator.ts

@@ -35,7 +35,26 @@ export class GeminiContentGenerator implements ContentGenerator {
     },
     contentGeneratorConfig?: ContentGeneratorConfig,
   ) {
-    this.googleGenAI = new GoogleGenAI(options);
+    const customHeaders = contentGeneratorConfig?.customHeaders;
+    const finalOptions = customHeaders
+      ? (() => {
+          const baseHttpOptions = options.httpOptions;
+          const baseHeaders = baseHttpOptions?.headers ?? {};
+
+          return {
+            ...options,
+            httpOptions: {
+              ...(baseHttpOptions ?? {}),
+              headers: {
+                ...baseHeaders,
+                ...customHeaders,
+              },
+            },
+          };
+        })()
+      : options;
+
+    this.googleGenAI = new GoogleGenAI(finalOptions);
     this.contentGeneratorConfig = contentGeneratorConfig;
   }
 

packages/core/src/core/loggingContentGenerator/loggingContentGenerator.test.ts

@@ -12,6 +12,7 @@ import type {
 import { GenerateContentResponse } from '@google/genai';
 import type { Config } from '../../config/config.js';
 import type { ContentGenerator } from '../contentGenerator.js';
+import { AuthType } from '../contentGenerator.js';
 import { LoggingContentGenerator } from './index.js';
 import { OpenAIContentConverter } from '../openaiContentGenerator/converter.js';
 import {
@@ -50,14 +51,17 @@ const convertGeminiResponseToOpenAISpy = vi
     choices: [],
   } as OpenAI.Chat.ChatCompletion);
 
-const createConfig = (overrides: Record<string, unknown> = {}): Config =>
-  ({
-    getContentGeneratorConfig: () => ({
-      authType: 'openai',
-      enableOpenAILogging: false,
-      ...overrides,
-    }),
-  }) as Config;
+const createConfig = (overrides: Record<string, unknown> = {}): Config => {
+  const configContent = {
+    authType: 'openai',
+    enableOpenAILogging: false,
+    ...overrides,
+  };
+  return {
+    getContentGeneratorConfig: () => configContent,
+    getAuthType: () => configContent.authType as AuthType | undefined,
+  } as Config;
+};
 
 const createWrappedGenerator = (
   generateContent: ContentGenerator['generateContent'],
@@ -124,13 +128,17 @@ describe('LoggingContentGenerator', () => {
       ),
       vi.fn(),
     );
+    const generatorConfig = {
+      model: 'test-model',
+      authType: AuthType.USE_OPENAI,
+      enableOpenAILogging: true,
+      openAILoggingDir: 'logs',
+      schemaCompliance: 'openapi_30' as const,
+    };
     const generator = new LoggingContentGenerator(
       wrapped,
-      createConfig({
-        enableOpenAILogging: true,
-        openAILoggingDir: 'logs',
-        schemaCompliance: 'openapi_30',
-      }),
+      createConfig(),
+      generatorConfig,
     );
 
     const request = {
@@ -225,9 +233,15 @@ describe('LoggingContentGenerator', () => {
       vi.fn().mockRejectedValue(error),
       vi.fn(),
     );
+    const generatorConfig = {
+      model: 'test-model',
+      authType: AuthType.USE_OPENAI,
+      enableOpenAILogging: true,
+    };
     const generator = new LoggingContentGenerator(
       wrapped,
-      createConfig({ enableOpenAILogging: true }),
+      createConfig(),
+      generatorConfig,
     );
 
     const request = {
@@ -293,9 +307,15 @@ describe('LoggingContentGenerator', () => {
         })(),
       ),
     );
+    const generatorConfig = {
+      model: 'test-model',
+      authType: AuthType.USE_OPENAI,
+      enableOpenAILogging: true,
+    };
     const generator = new LoggingContentGenerator(
       wrapped,
-      createConfig({ enableOpenAILogging: true }),
+      createConfig(),
+      generatorConfig,
     );
 
     const request = {
@@ -345,9 +365,15 @@ describe('LoggingContentGenerator', () => {
         })(),
       ),
     );
+    const generatorConfig = {
+      model: 'test-model',
+      authType: AuthType.USE_OPENAI,
+      enableOpenAILogging: true,
+    };
     const generator = new LoggingContentGenerator(
       wrapped,
-      createConfig({ enableOpenAILogging: true }),
+      createConfig(),
+      generatorConfig,
     );
 
     const request = {

packages/core/src/core/loggingContentGenerator/loggingContentGenerator.ts

@@ -31,7 +31,10 @@ import {
   logApiRequest,
   logApiResponse,
 } from '../../telemetry/loggers.js';
-import type { ContentGenerator } from '../contentGenerator.js';
+import type {
+  ContentGenerator,
+  ContentGeneratorConfig,
+} from '../contentGenerator.js';
 import { isStructuredError } from '../../utils/quotaErrorDetection.js';
 import { OpenAIContentConverter } from '../openaiContentGenerator/converter.js';
 import { OpenAILogger } from '../../utils/openaiLogger.js';
@@ -50,9 +53,11 @@ export class LoggingContentGenerator implements ContentGenerator {
   constructor(
     private readonly wrapped: ContentGenerator,
     private readonly config: Config,
+    generatorConfig: ContentGeneratorConfig,
   ) {
-    const generatorConfig = this.config.getContentGeneratorConfig();
-    if (generatorConfig?.enableOpenAILogging) {
+    // Extract fields needed for initialization from passed config
+    // (config.getContentGeneratorConfig() may not be available yet during refreshAuth)
+    if (generatorConfig.enableOpenAILogging) {
       this.openaiLogger = new OpenAILogger(generatorConfig.openAILoggingDir);
       this.schemaCompliance = generatorConfig.schemaCompliance;
     }
@@ -89,7 +94,7 @@ export class LoggingContentGenerator implements ContentGenerator {
         model,
         durationMs,
         prompt_id,
-        this.config.getContentGeneratorConfig()?.authType,
+        this.config.getAuthType(),
         usageMetadata,
         responseText,
       ),
@@ -126,7 +131,7 @@ export class LoggingContentGenerator implements ContentGenerator {
         errorMessage,
         durationMs,
         prompt_id,
-        this.config.getContentGeneratorConfig()?.authType,
+        this.config.getAuthType(),
         errorType,
         errorStatus,
       ),

packages/core/src/core/openaiContentGenerator/provider/dashscope.test.ts

@@ -142,6 +142,27 @@ describe('DashScopeOpenAICompatibleProvider', () => {
       });
     });
 
+    it('should merge custom headers with DashScope defaults', () => {
+      const providerWithCustomHeaders = new DashScopeOpenAICompatibleProvider(
+        {
+          ...mockContentGeneratorConfig,
+          customHeaders: {
+            'X-Custom': '1',
+            'X-DashScope-CacheControl': 'disable',
+          },
+        } as ContentGeneratorConfig,
+        mockCliConfig,
+      );
+
+      const headers = providerWithCustomHeaders.buildHeaders();
+
+      expect(headers['User-Agent']).toContain('QwenCode/1.0.0');
+      expect(headers['X-DashScope-UserAgent']).toContain('QwenCode/1.0.0');
+      expect(headers['X-DashScope-AuthType']).toBe(AuthType.QWEN_OAUTH);
+      expect(headers['X-Custom']).toBe('1');
+      expect(headers['X-DashScope-CacheControl']).toBe('disable');
+    });
+
     it('should handle unknown CLI version', () => {
       (
         mockCliConfig.getCliVersion as MockedFunction<

packages/core/src/core/openaiContentGenerator/provider/dashscope.ts

@@ -47,13 +47,17 @@ export class DashScopeOpenAICompatibleProvider
   buildHeaders(): Record<string, string | undefined> {
     const version = this.cliConfig.getCliVersion() || 'unknown';
     const userAgent = `QwenCode/${version} (${process.platform}; ${process.arch})`;
-    const { authType } = this.contentGeneratorConfig;
-    return {
+    const { authType, customHeaders } = this.contentGeneratorConfig;
+    const defaultHeaders = {
       'User-Agent': userAgent,
       'X-DashScope-CacheControl': 'enable',
       'X-DashScope-UserAgent': userAgent,
       'X-DashScope-AuthType': authType,
     };
+
+    return customHeaders
+      ? { ...defaultHeaders, ...customHeaders }
+      : defaultHeaders;
   }
 
   buildClient(): OpenAI {

packages/core/src/core/openaiContentGenerator/provider/default.test.ts

@@ -73,6 +73,26 @@ describe('DefaultOpenAICompatibleProvider', () => {
       });
     });
 
+    it('should merge customHeaders with defaults (and allow overrides)', () => {
+      const providerWithCustomHeaders = new DefaultOpenAICompatibleProvider(
+        {
+          ...mockContentGeneratorConfig,
+          customHeaders: {
+            'X-Custom': '1',
+            'User-Agent': 'custom-agent',
+          },
+        } as ContentGeneratorConfig,
+        mockCliConfig,
+      );
+
+      const headers = providerWithCustomHeaders.buildHeaders();
+
+      expect(headers).toEqual({
+        'User-Agent': 'custom-agent',
+        'X-Custom': '1',
+      });
+    });
+
     it('should handle unknown CLI version', () => {
       (
         mockCliConfig.getCliVersion as MockedFunction<

packages/core/src/core/openaiContentGenerator/provider/default.ts

@@ -25,9 +25,14 @@ export class DefaultOpenAICompatibleProvider
   buildHeaders(): Record<string, string | undefined> {
     const version = this.cliConfig.getCliVersion() || 'unknown';
     const userAgent = `QwenCode/${version} (${process.platform}; ${process.arch})`;
-    return {
+    const { customHeaders } = this.contentGeneratorConfig;
+    const defaultHeaders = {
       'User-Agent': userAgent,
     };
+
+    return customHeaders
+      ? { ...defaultHeaders, ...customHeaders }
+      : defaultHeaders;
   }
 
   buildClient(): OpenAI {

packages/core/src/models/constants.ts

@@ -25,6 +25,7 @@ export const MODEL_GENERATION_CONFIG_FIELDS = [
   'disableCacheControl',
   'schemaCompliance',
   'reasoning',
+  'customHeaders',
 ] as const satisfies ReadonlyArray<keyof ContentGeneratorConfig>;
 
 /**
@@ -105,15 +106,6 @@ export const QWEN_OAUTH_MODELS: ModelConfig[] = [
     description:
       'The latest Qwen Coder model from Alibaba Cloud ModelStudio (version: qwen3-coder-plus-2025-09-23)',
     capabilities: { vision: false },
-    generationConfig: {
-      samplingParams: {
-        temperature: 0.7,
-        top_p: 0.9,
-        max_tokens: 8192,
-      },
-      timeout: 60000,
-      maxRetries: 3,
-    },
   },
   {
     id: 'vision-model',
@@ -121,14 +113,5 @@ export const QWEN_OAUTH_MODELS: ModelConfig[] = [
     description:
       'The latest Qwen Vision model from Alibaba Cloud ModelStudio (version: qwen3-vl-plus-2025-09-23)',
     capabilities: { vision: true },
-    generationConfig: {
-      samplingParams: {
-        temperature: 0.7,
-        top_p: 0.9,
-        max_tokens: 8192,
-      },
-      timeout: 60000,
-      maxRetries: 3,
-    },
   },
 ];

packages/core/src/models/modelConfigResolver.test.ts

@@ -112,11 +112,9 @@ describe('modelConfigResolver', () => {
           modelProvider: {
             id: 'provider-model',
             name: 'Provider Model',
-            authType: AuthType.USE_OPENAI,
             envKey: 'MY_CUSTOM_KEY',
             baseUrl: 'https://provider.example.com',
             generationConfig: {},
-            capabilities: {},
           },
         });
 
@@ -249,13 +247,11 @@ describe('modelConfigResolver', () => {
           modelProvider: {
             id: 'model',
             name: 'Model',
-            authType: AuthType.USE_OPENAI,
             envKey: 'MY_KEY',
             baseUrl: 'https://api.example.com',
             generationConfig: {
               timeout: 60000,
             },
-            capabilities: {},
           },
         });
 

packages/core/src/models/modelConfigResolver.ts

@@ -41,7 +41,7 @@ import {
   QWEN_OAUTH_ALLOWED_MODELS,
   MODEL_GENERATION_CONFIG_FIELDS,
 } from './constants.js';
-import type { ResolvedModelConfig } from './types.js';
+import type { ModelConfig as ModelProviderConfig } from './types.js';
 export {
   validateModelConfig,
   type ModelConfigValidationResult,
@@ -86,8 +86,8 @@ export interface ModelConfigSourcesInput {
   /** Environment variables (injected for testability) */
   env: Record<string, string | undefined>;
 
-  /** Resolved model from ModelProviders (explicit selection, highest priority) */
-  modelProvider?: ResolvedModelConfig;
+  /** Model from ModelProviders (explicit selection, highest priority) */
+  modelProvider?: ModelProviderConfig;
 
   /** Proxy URL (computed from Config) */
   proxy?: string;
@@ -277,7 +277,7 @@ function resolveQwenOAuthConfig(
   input: ModelConfigSourcesInput,
   warnings: string[],
 ): ModelConfigResolutionResult {
-  const { cli, settings, proxy } = input;
+  const { cli, settings, proxy, modelProvider } = input;
   const sources: ConfigSources = {};
 
   // Qwen OAuth only allows specific models
@@ -311,10 +311,10 @@ function resolveQwenOAuthConfig(
     sources['proxy'] = computedSource('Config.getProxy()');
   }
 
-  // Resolve generation config from settings
+  // Resolve generation config from settings and modelProvider
   const generationConfig = resolveGenerationConfig(
     settings?.generationConfig,
-    undefined,
+    modelProvider?.generationConfig,
     AuthType.QWEN_OAUTH,
     resolvedModel,
     sources,
@@ -344,7 +344,7 @@ function resolveGenerationConfig(
   const result: Partial<ContentGeneratorConfig> = {};
 
   for (const field of MODEL_GENERATION_CONFIG_FIELDS) {
-    // ModelProvider config takes priority
+    // ModelProvider config takes priority over settings config
     if (authType && modelProviderConfig && field in modelProviderConfig) {
       // eslint-disable-next-line @typescript-eslint/no-explicit-any
       (result as any)[field] = modelProviderConfig[field];

packages/core/src/models/modelsConfig.test.ts

@@ -191,7 +191,7 @@ describe('ModelsConfig', () => {
     expect(gc.apiKeyEnvKey).toBe('API_KEY_SHARED');
   });
 
-  it('should preserve settings generationConfig when model is updated via updateCredentials even if it matches modelProviders', () => {
+  it('should use provider config when modelId exists in registry even after updateCredentials', () => {
     const modelProvidersConfig: ModelProvidersConfig = {
       openai: [
         {
@@ -213,7 +213,7 @@ describe('ModelsConfig', () => {
       initialAuthType: AuthType.USE_OPENAI,
       modelProvidersConfig,
       generationConfig: {
-        model: 'model-a',
+        model: 'custom-model',
         samplingParams: { temperature: 0.9, max_tokens: 999 },
         timeout: 9999,
         maxRetries: 9,
@@ -235,30 +235,30 @@ describe('ModelsConfig', () => {
       },
     });
 
-    // User manually updates the model via updateCredentials (e.g. key prompt flow).
-    // Even if the model ID matches a modelProviders entry, we must not apply provider defaults
-    // that would overwrite settings.model.generationConfig.
-    modelsConfig.updateCredentials({ model: 'model-a' });
+    // User manually updates credentials via updateCredentials.
+    // Note: In practice, handleAuthSelect prevents using a modelId that matches a provider model,
+    // but if syncAfterAuthRefresh is called with a modelId that exists in registry,
+    // we should use provider config.
+    modelsConfig.updateCredentials({ apiKey: 'manual-key' });
 
-    modelsConfig.syncAfterAuthRefresh(
-      AuthType.USE_OPENAI,
-      modelsConfig.getModel(),
-    );
+    // syncAfterAuthRefresh with a modelId that exists in registry should use provider config
+    modelsConfig.syncAfterAuthRefresh(AuthType.USE_OPENAI, 'model-a');
 
     const gc = currentGenerationConfig(modelsConfig);
     expect(gc.model).toBe('model-a');
-    expect(gc.samplingParams?.temperature).toBe(0.9);
-    expect(gc.samplingParams?.max_tokens).toBe(999);
-    expect(gc.timeout).toBe(9999);
-    expect(gc.maxRetries).toBe(9);
+    // Provider config should be applied
+    expect(gc.samplingParams?.temperature).toBe(0.1);
+    expect(gc.samplingParams?.max_tokens).toBe(123);
+    expect(gc.timeout).toBe(111);
+    expect(gc.maxRetries).toBe(1);
   });
 
-  it('should preserve settings generationConfig across multiple auth refreshes after updateCredentials', () => {
+  it('should preserve settings generationConfig when modelId does not exist in registry', () => {
     const modelProvidersConfig: ModelProvidersConfig = {
       openai: [
         {
-          id: 'model-a',
-          name: 'Model A',
+          id: 'provider-model',
+          name: 'Provider Model',
           baseUrl: 'https://api.example.com/v1',
           envKey: 'API_KEY_A',
           generationConfig: {
@@ -270,11 +270,12 @@ describe('ModelsConfig', () => {
       ],
     };
 
+    // Simulate settings with a custom model (not in registry)
     const modelsConfig = new ModelsConfig({
       initialAuthType: AuthType.USE_OPENAI,
       modelProvidersConfig,
       generationConfig: {
-        model: 'model-a',
+        model: 'custom-model',
         samplingParams: { temperature: 0.9, max_tokens: 999 },
         timeout: 9999,
         maxRetries: 9,
@@ -296,25 +297,21 @@ describe('ModelsConfig', () => {
       },
     });
 
+    // User manually sets credentials for a custom model (not in registry)
     modelsConfig.updateCredentials({
       apiKey: 'manual-key',
       baseUrl: 'https://manual.example.com/v1',
-      model: 'model-a',
+      model: 'custom-model',
     });
 
-    // First auth refresh
-    modelsConfig.syncAfterAuthRefresh(
-      AuthType.USE_OPENAI,
-      modelsConfig.getModel(),
-    );
+    // First auth refresh - modelId doesn't exist in registry, so credentials should be preserved
+    modelsConfig.syncAfterAuthRefresh(AuthType.USE_OPENAI, 'custom-model');
     // Second auth refresh should still preserve settings generationConfig
-    modelsConfig.syncAfterAuthRefresh(
-      AuthType.USE_OPENAI,
-      modelsConfig.getModel(),
-    );
+    modelsConfig.syncAfterAuthRefresh(AuthType.USE_OPENAI, 'custom-model');
 
     const gc = currentGenerationConfig(modelsConfig);
-    expect(gc.model).toBe('model-a');
+    expect(gc.model).toBe('custom-model');
+    // Settings-sourced generation config should be preserved since modelId doesn't exist in registry
     expect(gc.samplingParams?.temperature).toBe(0.9);
     expect(gc.samplingParams?.max_tokens).toBe(999);
     expect(gc.timeout).toBe(9999);
@@ -480,6 +477,91 @@ describe('ModelsConfig', () => {
     expect(gc.apiKeyEnvKey).toBeUndefined();
   });
 
+  it('should use default model for new authType when switching from different authType with env vars', () => {
+    // Simulate cold start with OPENAI env vars (OPENAI_MODEL and OPENAI_API_KEY)
+    // This sets the model in generationConfig but no authType is selected yet
+    const modelsConfig = new ModelsConfig({
+      generationConfig: {
+        model: 'gpt-4o', // From OPENAI_MODEL env var
+        apiKey: 'openai-key-from-env',
+      },
+    });
+
+    // User switches to qwen-oauth via AuthDialog
+    // refreshAuth calls syncAfterAuthRefresh with the current model (gpt-4o)
+    // which doesn't exist in qwen-oauth registry, so it should use default
+    modelsConfig.syncAfterAuthRefresh(AuthType.QWEN_OAUTH, 'gpt-4o');
+
+    const gc = currentGenerationConfig(modelsConfig);
+    // Should use default qwen-oauth model (coder-model), not the OPENAI model
+    expect(gc.model).toBe('coder-model');
+    expect(gc.apiKey).toBe('QWEN_OAUTH_DYNAMIC_TOKEN');
+    expect(gc.apiKeyEnvKey).toBeUndefined();
+  });
+
+  it('should clear manual credentials when switching from USE_OPENAI to QWEN_OAUTH', () => {
+    // User manually set credentials for OpenAI
+    const modelsConfig = new ModelsConfig({
+      initialAuthType: AuthType.USE_OPENAI,
+      generationConfig: {
+        model: 'gpt-4o',
+        apiKey: 'manual-openai-key',
+        baseUrl: 'https://manual.example.com/v1',
+      },
+    });
+
+    // Manually set credentials via updateCredentials
+    modelsConfig.updateCredentials({
+      apiKey: 'manual-openai-key',
+      baseUrl: 'https://manual.example.com/v1',
+      model: 'gpt-4o',
+    });
+
+    // User switches to qwen-oauth
+    // Since authType is not USE_OPENAI, manual credentials should be cleared
+    // and default qwen-oauth model should be applied
+    modelsConfig.syncAfterAuthRefresh(AuthType.QWEN_OAUTH, 'gpt-4o');
+
+    const gc = currentGenerationConfig(modelsConfig);
+    // Should use default qwen-oauth model, not preserve manual OpenAI credentials
+    expect(gc.model).toBe('coder-model');
+    expect(gc.apiKey).toBe('QWEN_OAUTH_DYNAMIC_TOKEN');
+    // baseUrl should be set to qwen-oauth default, not preserved from manual OpenAI config
+    expect(gc.baseUrl).toBe('DYNAMIC_QWEN_OAUTH_BASE_URL');
+    expect(gc.apiKeyEnvKey).toBeUndefined();
+  });
+
+  it('should preserve manual credentials when switching to USE_OPENAI', () => {
+    // User manually set credentials
+    const modelsConfig = new ModelsConfig({
+      initialAuthType: AuthType.USE_OPENAI,
+      generationConfig: {
+        model: 'gpt-4o',
+        apiKey: 'manual-openai-key',
+        baseUrl: 'https://manual.example.com/v1',
+        samplingParams: { temperature: 0.9 },
+      },
+    });
+
+    // Manually set credentials via updateCredentials
+    modelsConfig.updateCredentials({
+      apiKey: 'manual-openai-key',
+      baseUrl: 'https://manual.example.com/v1',
+      model: 'gpt-4o',
+    });
+
+    // User switches to USE_OPENAI (same or different model)
+    // Since authType is USE_OPENAI, manual credentials should be preserved
+    modelsConfig.syncAfterAuthRefresh(AuthType.USE_OPENAI, 'gpt-4o');
+
+    const gc = currentGenerationConfig(modelsConfig);
+    // Should preserve manual credentials
+    expect(gc.model).toBe('gpt-4o');
+    expect(gc.apiKey).toBe('manual-openai-key');
+    expect(gc.baseUrl).toBe('https://manual.example.com/v1');
+    expect(gc.samplingParams?.temperature).toBe(0.9); // Preserved from initial config
+  });
+
   it('should maintain consistency between currentModelId and _generationConfig.model after initialization', () => {
     const modelProvidersConfig: ModelProvidersConfig = {
       openai: [
@@ -596,4 +678,120 @@ describe('ModelsConfig', () => {
     expect(modelsConfig.getModel()).toBe('updated-model');
     expect(modelsConfig.getGenerationConfig().model).toBe('updated-model');
   });
+
+  describe('getAllAvailableModels', () => {
+    it('should return all models across all authTypes', () => {
+      const modelProvidersConfig: ModelProvidersConfig = {
+        openai: [
+          {
+            id: 'openai-model-1',
+            name: 'OpenAI Model 1',
+            baseUrl: 'https://api.openai.com/v1',
+            envKey: 'OPENAI_API_KEY',
+          },
+          {
+            id: 'openai-model-2',
+            name: 'OpenAI Model 2',
+            baseUrl: 'https://api.openai.com/v1',
+            envKey: 'OPENAI_API_KEY',
+          },
+        ],
+        anthropic: [
+          {
+            id: 'anthropic-model-1',
+            name: 'Anthropic Model 1',
+            baseUrl: 'https://api.anthropic.com/v1',
+            envKey: 'ANTHROPIC_API_KEY',
+          },
+        ],
+        gemini: [
+          {
+            id: 'gemini-model-1',
+            name: 'Gemini Model 1',
+            baseUrl: 'https://generativelanguage.googleapis.com/v1',
+            envKey: 'GEMINI_API_KEY',
+          },
+        ],
+      };
+
+      const modelsConfig = new ModelsConfig({
+        modelProvidersConfig,
+      });
+
+      const allModels = modelsConfig.getAllAvailableModels();
+
+      // Should include qwen-oauth models (hard-coded)
+      const qwenModels = allModels.filter(
+        (m) => m.authType === AuthType.QWEN_OAUTH,
+      );
+      expect(qwenModels.length).toBeGreaterThan(0);
+
+      // Should include openai models
+      const openaiModels = allModels.filter(
+        (m) => m.authType === AuthType.USE_OPENAI,
+      );
+      expect(openaiModels.length).toBe(2);
+      expect(openaiModels.map((m) => m.id)).toContain('openai-model-1');
+      expect(openaiModels.map((m) => m.id)).toContain('openai-model-2');
+
+      // Should include anthropic models
+      const anthropicModels = allModels.filter(
+        (m) => m.authType === AuthType.USE_ANTHROPIC,
+      );
+      expect(anthropicModels.length).toBe(1);
+      expect(anthropicModels[0].id).toBe('anthropic-model-1');
+
+      // Should include gemini models
+      const geminiModels = allModels.filter(
+        (m) => m.authType === AuthType.USE_GEMINI,
+      );
+      expect(geminiModels.length).toBe(1);
+      expect(geminiModels[0].id).toBe('gemini-model-1');
+    });
+
+    it('should return empty array when no models are registered', () => {
+      const modelsConfig = new ModelsConfig();
+
+      const allModels = modelsConfig.getAllAvailableModels();
+
+      // Should still include qwen-oauth models (hard-coded)
+      expect(allModels.length).toBeGreaterThan(0);
+      const qwenModels = allModels.filter(
+        (m) => m.authType === AuthType.QWEN_OAUTH,
+      );
+      expect(qwenModels.length).toBeGreaterThan(0);
+    });
+
+    it('should return models with correct structure', () => {
+      const modelProvidersConfig: ModelProvidersConfig = {
+        openai: [
+          {
+            id: 'test-model',
+            name: 'Test Model',
+            description: 'A test model',
+            baseUrl: 'https://api.example.com/v1',
+            envKey: 'TEST_API_KEY',
+            capabilities: {
+              vision: true,
+            },
+          },
+        ],
+      };
+
+      const modelsConfig = new ModelsConfig({
+        modelProvidersConfig,
+      });
+
+      const allModels = modelsConfig.getAllAvailableModels();
+      const testModel = allModels.find((m) => m.id === 'test-model');
+
+      expect(testModel).toBeDefined();
+      expect(testModel?.id).toBe('test-model');
+      expect(testModel?.label).toBe('Test Model');
+      expect(testModel?.description).toBe('A test model');
+      expect(testModel?.authType).toBe(AuthType.USE_OPENAI);
+      expect(testModel?.isVision).toBe(true);
+      expect(testModel?.capabilities?.vision).toBe(true);
+    });
+  });
 });

packages/core/src/models/modelsConfig.ts

@@ -203,6 +203,18 @@ export class ModelsConfig {
     return this.modelRegistry.getModelsForAuthType(authType);
   }
 
+  /**
+   * Get all available models across all authTypes
+   */
+  getAllAvailableModels(): AvailableModel[] {
+    const allModels: AvailableModel[] = [];
+    for (const authType of Object.values(AuthType)) {
+      const models = this.modelRegistry.getModelsForAuthType(authType);
+      allModels.push(...models);
+    }
+    return allModels;
+  }
+
   /**
    * Check if a model exists for the given authType
    */
@@ -307,6 +319,33 @@ export class ModelsConfig {
     return this.generationConfigSources;
   }
 
+  /**
+   * Merge settings generation config, preserving existing values.
+   * Used when provider-sourced config is cleared but settings should still apply.
+   */
+  mergeSettingsGenerationConfig(
+    settingsGenerationConfig?: Partial<ContentGeneratorConfig>,
+  ): void {
+    if (!settingsGenerationConfig) {
+      return;
+    }
+
+    for (const field of MODEL_GENERATION_CONFIG_FIELDS) {
+      if (
+        !(field in this._generationConfig) &&
+        field in settingsGenerationConfig
+      ) {
+        // eslint-disable-next-line @typescript-eslint/no-explicit-any
+        (this._generationConfig as any)[field] =
+          settingsGenerationConfig[field];
+        this.generationConfigSources[field] = {
+          kind: 'settings',
+          detail: `model.generationConfig.${field}`,
+        };
+      }
+    }
+  }
+
   /**
    * Update credentials in generation config.
    * Sets a flag to prevent syncAfterAuthRefresh from overriding these credentials.
@@ -314,12 +353,20 @@ export class ModelsConfig {
    * When credentials are manually set, we clear all provider-sourced configuration
    * to maintain provider atomicity (either fully applied or not at all).
    * Other layers (CLI, env, settings, defaults) will participate in resolve.
+   *
+   * @param settingsGenerationConfig Optional generation config from settings.json
+   *                                  to merge after clearing provider-sourced config.
+   *                                  This ensures settings.model.generationConfig fields
+   *                                  (e.g., samplingParams, timeout) are preserved.
    */
-  updateCredentials(credentials: {
-    apiKey?: string;
-    baseUrl?: string;
-    model?: string;
-  }): void {
+  updateCredentials(
+    credentials: {
+      apiKey?: string;
+      baseUrl?: string;
+      model?: string;
+    },
+    settingsGenerationConfig?: Partial<ContentGeneratorConfig>,
+  ): void {
     /**
      * If any fields are updated here, we treat the resulting config as manually overridden
      * and avoid applying modelProvider defaults during the next auth refresh.
@@ -359,6 +406,14 @@ export class ModelsConfig {
     this.strictModelProviderSelection = false;
     // Clear apiKeyEnvKey to prevent validation from requiring environment variable
     this._generationConfig.apiKeyEnvKey = undefined;
+
+    // After clearing provider-sourced config, merge settings.model.generationConfig
+    // to ensure fields like samplingParams, timeout, etc. are preserved.
+    // This follows the resolution strategy where settings.model.generationConfig
+    // has lower priority than programmatic overrides but should still be applied.
+    if (settingsGenerationConfig) {
+      this.mergeSettingsGenerationConfig(settingsGenerationConfig);
+    }
   }
 
   /**
@@ -587,41 +642,89 @@ export class ModelsConfig {
   }
 
   /**
-   * Called by Config.refreshAuth to sync state after auth refresh.
-   *
-   * IMPORTANT: If credentials were manually set via updateCredentials(),
-   * we should NOT override them with modelProvider defaults.
-   * This handles the case where user inputs credentials via OpenAIKeyPrompt
-   * after removing environment variables for a previously selected model.
+   * Sync state after auth refresh with fallback strategy:
+   * 1. If modelId can be found in modelRegistry, use the config from modelRegistry.
+   * 2. Otherwise, if existing credentials exist in resolved generationConfig from other sources
+   *    (not modelProviders), preserve them and update authType/modelId only.
+   * 3. Otherwise, fall back to default model for the authType.
+   * 4. If no default is available, leave the generationConfig incomplete and let
+   *    resolveContentGeneratorConfigWithSources throw exceptions as expected.
    */
   syncAfterAuthRefresh(authType: AuthType, modelId?: string): void {
-    // Check if we have manually set credentials that should be preserved
-    const preserveManualCredentials = this.hasManualCredentials;
+    this.strictModelProviderSelection = false;
+    const previousAuthType = this.currentAuthType;
+    this.currentAuthType = authType;
 
-    // If credentials were manually set, don't apply modelProvider defaults
-    // Just update the authType and preserve the manually set credentials
-    if (preserveManualCredentials) {
-      this.strictModelProviderSelection = false;
-      this.currentAuthType = authType;
+    // Step 1: If modelId exists in registry, always use config from modelRegistry
+    // Manual credentials won't have a modelId that matches a provider model (handleAuthSelect prevents it),
+    // so if modelId exists in registry, we should always use provider config.
+    // This handles provider switching even within the same authType.
+    if (modelId && this.modelRegistry.hasModel(authType, modelId)) {
+      const resolved = this.modelRegistry.getModel(authType, modelId);
+      if (resolved) {
+        this.applyResolvedModelDefaults(resolved);
+        this.strictModelProviderSelection = true;
+        return;
+      }
+    }
+
+    // Step 2: Check if there are existing credentials from other sources (not modelProviders)
+    const apiKeySource = this.generationConfigSources['apiKey'];
+    const baseUrlSource = this.generationConfigSources['baseUrl'];
+    const hasExistingCredentials =
+      (this._generationConfig.apiKey &&
+        apiKeySource?.kind !== 'modelProviders') ||
+      (this._generationConfig.baseUrl &&
+        baseUrlSource?.kind !== 'modelProviders');
+
+    // Only preserve credentials if:
+    // 1. AuthType hasn't changed (credentials are authType-specific), AND
+    // 2. The modelId doesn't exist in the registry (if it did, we would have used provider config in Step 1), AND
+    // 3. Either:
+    //    a. We have manual credentials (set via updateCredentials), OR
+    //    b. We have existing credentials
+    // Note: Even if authType hasn't changed, switching to a different provider model (that exists in registry)
+    // will use provider config (Step 1), not preserve old credentials. This ensures credentials change when
+    // switching providers, independent of authType changes.
+    const isAuthTypeChange = previousAuthType !== authType;
+    const shouldPreserveCredentials =
+      !isAuthTypeChange &&
+      (modelId === undefined ||
+        !this.modelRegistry.hasModel(authType, modelId)) &&
+      (this.hasManualCredentials || hasExistingCredentials);
+
+    if (shouldPreserveCredentials) {
+      // Preserve existing credentials, just update authType and modelId if provided
       if (modelId) {
         this._generationConfig.model = modelId;
+        if (!this.generationConfigSources['model']) {
+          this.generationConfigSources['model'] = {
+            kind: 'programmatic',
+            detail: 'auth refresh (preserved credentials)',
+          };
+        }
       }
       return;
     }
 
-    this.strictModelProviderSelection = false;
+    // Step 3: Fall back to default model for the authType
+    const defaultModel =
+      this.modelRegistry.getDefaultModelForAuthType(authType);
+    if (defaultModel) {
+      this.applyResolvedModelDefaults(defaultModel);
+      return;
+    }
 
-    if (modelId && this.modelRegistry.hasModel(authType, modelId)) {
-      const resolved = this.modelRegistry.getModel(authType, modelId);
-      if (resolved) {
-        // Ensure applyResolvedModelDefaults can correctly apply authType-specific
-        // behavior (e.g., Qwen OAuth placeholder token) by setting currentAuthType
-        // before applying defaults.
-        this.currentAuthType = authType;
-        this.applyResolvedModelDefaults(resolved);
+    // Step 4: No default available - leave generationConfig incomplete
+    // resolveContentGeneratorConfigWithSources will throw exceptions as expected
+    if (modelId) {
+      this._generationConfig.model = modelId;
+      if (!this.generationConfigSources['model']) {
+        this.generationConfigSources['model'] = {
+          kind: 'programmatic',
+          detail: 'auth refresh (no default model)',
+        };
       }
-    } else {
-      this.currentAuthType = authType;
     }
   }
 

packages/core/src/models/types.ts

@@ -31,6 +31,7 @@ export type ModelGenerationConfig = Pick<
   | 'disableCacheControl'
   | 'schemaCompliance'
   | 'reasoning'
+  | 'customHeaders'
 >;
 
 /**

packages/core/src/qwen/qwenOAuth2.test.ts

@@ -751,6 +751,7 @@ describe('getQwenOAuthClient', () => {
   beforeEach(() => {
     mockConfig = {
       isBrowserLaunchSuppressed: vi.fn().mockReturnValue(false),
+      isInteractive: vi.fn().mockReturnValue(true),
     } as unknown as Config;
 
     originalFetch = global.fetch;
@@ -839,9 +840,7 @@ describe('getQwenOAuthClient', () => {
           requireCachedCredentials: true,
         }),
       ),
-    ).rejects.toThrow(
-      'No cached Qwen-OAuth credentials found. Please re-authenticate.',
-    );
+    ).rejects.toThrow('Please use /auth to re-authenticate.');
 
     expect(global.fetch).not.toHaveBeenCalled();
 
@@ -1007,6 +1006,7 @@ describe('getQwenOAuthClient - Enhanced Error Scenarios', () => {
   beforeEach(() => {
     mockConfig = {
       isBrowserLaunchSuppressed: vi.fn().mockReturnValue(false),
+      isInteractive: vi.fn().mockReturnValue(true),
     } as unknown as Config;
 
     originalFetch = global.fetch;
@@ -1202,6 +1202,7 @@ describe('authWithQwenDeviceFlow - Comprehensive Testing', () => {
   beforeEach(() => {
     mockConfig = {
       isBrowserLaunchSuppressed: vi.fn().mockReturnValue(false),
+      isInteractive: vi.fn().mockReturnValue(true),
     } as unknown as Config;
 
     originalFetch = global.fetch;
@@ -1405,6 +1406,7 @@ describe('Browser Launch and Error Handling', () => {
   beforeEach(() => {
     mockConfig = {
       isBrowserLaunchSuppressed: vi.fn().mockReturnValue(false),
+      isInteractive: vi.fn().mockReturnValue(true),
     } as unknown as Config;
 
     originalFetch = global.fetch;
@@ -2043,6 +2045,7 @@ describe('SharedTokenManager Integration in QwenOAuth2Client', () => {
   it('should handle TokenManagerError types correctly in getQwenOAuthClient', async () => {
     const mockConfig = {
       isBrowserLaunchSuppressed: vi.fn().mockReturnValue(true),
+      isInteractive: vi.fn().mockReturnValue(true),
     } as unknown as Config;
 
     // Test different TokenManagerError types

packages/core/src/qwen/qwenOAuth2.ts

@@ -516,9 +516,7 @@ export async function getQwenOAuthClient(
     }
 
     if (options?.requireCachedCredentials) {
-      throw new Error(
-        'No cached Qwen-OAuth credentials found. Please re-authenticate.',
-      );
+      throw new Error('Please use /auth to re-authenticate.');
     }
 
     // If we couldn't obtain valid credentials via SharedTokenManager, fall back to
@@ -559,6 +557,109 @@ export async function getQwenOAuthClient(
   }
 }
 
+/**
+ * Displays a formatted box with OAuth device authorization URL.
+ * Uses process.stderr.write() to bypass ConsolePatcher and ensure the auth URL
+ * is always visible to users, especially in non-interactive mode.
+ * Using stderr prevents corruption of structured JSON output (which goes to stdout)
+ * and follows the standard Unix convention of user-facing messages to stderr.
+ */
+function showFallbackMessage(verificationUriComplete: string): void {
+  const title = 'Qwen OAuth Device Authorization';
+  const url = verificationUriComplete;
+  const minWidth = 70;
+  const maxWidth = 80;
+  const boxWidth = Math.min(Math.max(title.length + 4, minWidth), maxWidth);
+
+  // Calculate the width needed for the box (account for padding)
+  const contentWidth = boxWidth - 4; // Subtract 2 spaces and 2 border chars
+
+  // Helper to wrap text to fit within box width
+  const wrapText = (text: string, width: number): string[] => {
+    // For URLs, break at any character if too long
+    if (text.startsWith('http://') || text.startsWith('https://')) {
+      const lines: string[] = [];
+      for (let i = 0; i < text.length; i += width) {
+        lines.push(text.substring(i, i + width));
+      }
+      return lines;
+    }
+
+    // For regular text, break at word boundaries
+    const words = text.split(' ');
+    const lines: string[] = [];
+    let currentLine = '';
+
+    for (const word of words) {
+      if (currentLine.length + word.length + 1 <= width) {
+        currentLine += (currentLine ? ' ' : '') + word;
+      } else {
+        if (currentLine) {
+          lines.push(currentLine);
+        }
+        currentLine = word.length > width ? word.substring(0, width) : word;
+      }
+    }
+    if (currentLine) {
+      lines.push(currentLine);
+    }
+    return lines;
+  };
+
+  // Build the box borders with title centered in top border
+  // Format: +--- Title ---+
+  const titleWithSpaces = ' ' + title + ' ';
+  const totalDashes = boxWidth - 2 - titleWithSpaces.length; // Subtract corners and title
+  const leftDashes = Math.floor(totalDashes / 2);
+  const rightDashes = totalDashes - leftDashes;
+  const topBorder =
+    '+' +
+    '-'.repeat(leftDashes) +
+    titleWithSpaces +
+    '-'.repeat(rightDashes) +
+    '+';
+  const emptyLine = '|' + ' '.repeat(boxWidth - 2) + '|';
+  const bottomBorder = '+' + '-'.repeat(boxWidth - 2) + '+';
+
+  // Build content lines
+  const instructionLines = wrapText(
+    'Please visit the following URL in your browser to authorize:',
+    contentWidth,
+  );
+  const urlLines = wrapText(url, contentWidth);
+  const waitingLine = 'Waiting for authorization to complete...';
+
+  // Write the box
+  process.stderr.write('\n' + topBorder + '\n');
+  process.stderr.write(emptyLine + '\n');
+
+  // Write instructions
+  for (const line of instructionLines) {
+    process.stderr.write(
+      '| ' + line + ' '.repeat(contentWidth - line.length) + ' |\n',
+    );
+  }
+
+  process.stderr.write(emptyLine + '\n');
+
+  // Write URL
+  for (const line of urlLines) {
+    process.stderr.write(
+      '| ' + line + ' '.repeat(contentWidth - line.length) + ' |\n',
+    );
+  }
+
+  process.stderr.write(emptyLine + '\n');
+
+  // Write waiting message
+  process.stderr.write(
+    '| ' + waitingLine + ' '.repeat(contentWidth - waitingLine.length) + ' |\n',
+  );
+
+  process.stderr.write(emptyLine + '\n');
+  process.stderr.write(bottomBorder + '\n\n');
+}
+
 async function authWithQwenDeviceFlow(
   client: QwenOAuth2Client,
   config: Config,
@@ -571,6 +672,50 @@ async function authWithQwenDeviceFlow(
   };
   qwenOAuth2Events.once(QwenOAuth2Event.AuthCancel, cancelHandler);
 
+  // Helper to check cancellation and return appropriate result
+  const checkCancellation = (): AuthResult | null => {
+    if (!isCancelled) {
+      return null;
+    }
+    const message = 'Authentication cancelled by user.';
+    console.debug('\n' + message);
+    qwenOAuth2Events.emit(QwenOAuth2Event.AuthProgress, 'error', message);
+    return { success: false, reason: 'cancelled', message };
+  };
+
+  // Helper to emit auth progress events
+  const emitAuthProgress = (
+    status: 'polling' | 'success' | 'error' | 'timeout' | 'rate_limit',
+    message: string,
+  ): void => {
+    qwenOAuth2Events.emit(QwenOAuth2Event.AuthProgress, status, message);
+  };
+
+  // Helper to handle browser launch with error handling
+  const launchBrowser = async (url: string): Promise<void> => {
+    try {
+      const childProcess = await open(url);
+
+      // IMPORTANT: Attach an error handler to the returned child process.
+      // Without this, if `open` fails to spawn a process (e.g., `xdg-open` is not found
+      // in a minimal Docker container), it will emit an unhandled 'error' event,
+      // causing the entire Node.js process to crash.
+      if (childProcess) {
+        childProcess.on('error', (err) => {
+          console.debug(
+            'Browser launch failed:',
+            err.message || 'Unknown error',
+          );
+        });
+      }
+    } catch (err) {
+      console.debug(
+        'Failed to open browser:',
+        err instanceof Error ? err.message : 'Unknown error',
+      );
+    }
+  };
+
   try {
     // Generate PKCE code verifier and challenge
     const { code_verifier, code_challenge } = generatePKCEPair();
@@ -593,56 +738,16 @@ async function authWithQwenDeviceFlow(
     // Emit device authorization event for UI integration immediately
     qwenOAuth2Events.emit(QwenOAuth2Event.AuthUri, deviceAuth);
 
-    const showFallbackMessage = () => {
-      console.log('\n=== Qwen OAuth Device Authorization ===');
-      console.log(
-        'Please visit the following URL in your browser to authorize:',
-      );
-      console.log(`\n${deviceAuth.verification_uri_complete}\n`);
-      console.log('Waiting for authorization to complete...\n');
-    };
-
-    // Always show the fallback message in non-interactive environments to ensure
-    // users can see the authorization URL even if browser launching is attempted.
-    // This is critical for headless/remote environments where browser launching
-    // may silently fail without throwing an error.
-    if (config.isBrowserLaunchSuppressed()) {
-      // Browser launch is suppressed, show fallback message
-      showFallbackMessage();
-    } else {
-      // Try to open the URL in browser, but always show the URL as fallback
-      // to handle cases where browser launch silently fails (e.g., headless servers)
-      showFallbackMessage();
-      try {
-        const childProcess = await open(deviceAuth.verification_uri_complete);
-
-        // IMPORTANT: Attach an error handler to the returned child process.
-        // Without this, if `open` fails to spawn a process (e.g., `xdg-open` is not found
-        // in a minimal Docker container), it will emit an unhandled 'error' event,
-        // causing the entire Node.js process to crash.
-        if (childProcess) {
-          childProcess.on('error', (err) => {
-            console.debug(
-              'Browser launch failed:',
-              err.message || 'Unknown error',
-            );
-          });
-        }
-      } catch (err) {
-        console.debug(
-          'Failed to open browser:',
-          err instanceof Error ? err.message : 'Unknown error',
-        );
-      }
+    if (config.isBrowserLaunchSuppressed() || !config.isInteractive()) {
+      showFallbackMessage(deviceAuth.verification_uri_complete);
     }
 
-    // Emit auth progress event
-    qwenOAuth2Events.emit(
-      QwenOAuth2Event.AuthProgress,
-      'polling',
-      'Waiting for authorization...',
-    );
+    // Try to open browser if not suppressed
+    if (!config.isBrowserLaunchSuppressed()) {
+      await launchBrowser(deviceAuth.verification_uri_complete);
+    }
 
+    emitAuthProgress('polling', 'Waiting for authorization...');
     console.debug('Waiting for authorization...\n');
 
     // Poll for the token
@@ -653,11 +758,9 @@ async function authWithQwenDeviceFlow(
 
     for (let attempt = 0; attempt < maxAttempts; attempt++) {
       // Check if authentication was cancelled
-      if (isCancelled) {
-        const message = 'Authentication cancelled by user.';
-        console.debug('\n' + message);
-        qwenOAuth2Events.emit(QwenOAuth2Event.AuthProgress, 'error', message);
-        return { success: false, reason: 'cancelled', message };
+      const cancellationResult = checkCancellation();
+      if (cancellationResult) {
+        return cancellationResult;
       }
 
       try {
@@ -700,9 +803,7 @@ async function authWithQwenDeviceFlow(
             // minimal stub; cache invalidation is best-effort and should not break auth.
           }
 
-          // Emit auth progress success event
-          qwenOAuth2Events.emit(
-            QwenOAuth2Event.AuthProgress,
+          emitAuthProgress(
             'success',
             'Authentication successful! Access token obtained.',
           );
@@ -725,9 +826,7 @@ async function authWithQwenDeviceFlow(
             pollInterval = 2000; // Reset to default interval
           }
 
-          // Emit polling progress event
-          qwenOAuth2Events.emit(
-            QwenOAuth2Event.AuthProgress,
+          emitAuthProgress(
             'polling',
             `Polling... (attempt ${attempt + 1}/${maxAttempts})`,
           );
@@ -757,15 +856,9 @@ async function authWithQwenDeviceFlow(
           });
 
           // Check for cancellation after waiting
-          if (isCancelled) {
-            const message = 'Authentication cancelled by user.';
-            console.debug('\n' + message);
-            qwenOAuth2Events.emit(
-              QwenOAuth2Event.AuthProgress,
-              'error',
-              message,
-            );
-            return { success: false, reason: 'cancelled', message };
+          const cancellationResult = checkCancellation();
+          if (cancellationResult) {
+            return cancellationResult;
           }
 
           continue;
@@ -793,15 +886,17 @@ async function authWithQwenDeviceFlow(
           message: string,
           eventType: 'error' | 'rate_limit' = 'error',
         ): AuthResult => {
-          qwenOAuth2Events.emit(
-            QwenOAuth2Event.AuthProgress,
-            eventType,
-            message,
-          );
+          emitAuthProgress(eventType, message);
           console.error('\n' + message);
           return { success: false, reason, message };
         };
 
+        // Check for cancellation first
+        const cancellationResult = checkCancellation();
+        if (cancellationResult) {
+          return cancellationResult;
+        }
+
         // Handle credential caching failures - stop polling immediately
         if (errorMessage.includes('Failed to cache credentials')) {
           return handleError('error', errorMessage);
@@ -825,26 +920,14 @@ async function authWithQwenDeviceFlow(
         }
 
         const message = `Error polling for token: ${errorMessage}`;
-        qwenOAuth2Events.emit(QwenOAuth2Event.AuthProgress, 'error', message);
-
-        if (isCancelled) {
-          const message = 'Authentication cancelled by user.';
-          return { success: false, reason: 'cancelled', message };
-        }
+        emitAuthProgress('error', message);
 
         await new Promise((resolve) => setTimeout(resolve, pollInterval));
       }
     }
 
     const timeoutMessage = 'Authorization timeout, please restart the process.';
-
-    // Emit timeout error event
-    qwenOAuth2Events.emit(
-      QwenOAuth2Event.AuthProgress,
-      'timeout',
-      timeoutMessage,
-    );
-
+    emitAuthProgress('timeout', timeoutMessage);
     console.error('\n' + timeoutMessage);
     return { success: false, reason: 'timeout', message: timeoutMessage };
   } catch (error: unknown) {
@@ -853,7 +936,7 @@ async function authWithQwenDeviceFlow(
     });
     const message = `Device authorization flow failed: ${fullErrorMessage}`;
 
-    qwenOAuth2Events.emit(QwenOAuth2Event.AuthProgress, 'error', message);
+    emitAuthProgress('error', message);
     console.error(message);
     return { success: false, reason: 'error', message };
   } finally {

packages/core/src/skills/skill-manager.test.ts

@@ -112,6 +112,62 @@ You are a helpful assistant with this skill.
       expect(config.filePath).toBe(validSkillConfig.filePath);
     });
 
+    it('should parse markdown with CRLF line endings', () => {
+      const markdownCrlf = `---\r
+name: test-skill\r
+description: A test skill\r
+---\r
+\r
+You are a helpful assistant with this skill.\r
+`;
+
+      const config = manager.parseSkillContent(
+        markdownCrlf,
+        validSkillConfig.filePath,
+        'project',
+      );
+
+      expect(config.name).toBe('test-skill');
+      expect(config.description).toBe('A test skill');
+      expect(config.body).toBe('You are a helpful assistant with this skill.');
+    });
+
+    it('should parse markdown with UTF-8 BOM', () => {
+      const markdownWithBom = `\uFEFF---
+name: test-skill
+description: A test skill
+---
+
+You are a helpful assistant with this skill.
+`;
+
+      const config = manager.parseSkillContent(
+        markdownWithBom,
+        validSkillConfig.filePath,
+        'project',
+      );
+
+      expect(config.name).toBe('test-skill');
+      expect(config.description).toBe('A test skill');
+    });
+
+    it('should parse markdown when body is empty and file ends after frontmatter', () => {
+      const frontmatterOnly = `---
+name: test-skill
+description: A test skill
+---`;
+
+      const config = manager.parseSkillContent(
+        frontmatterOnly,
+        validSkillConfig.filePath,
+        'project',
+      );
+
+      expect(config.name).toBe('test-skill');
+      expect(config.description).toBe('A test skill');
+      expect(config.body).toBe('');
+    });
+
     it('should parse content with allowedTools', () => {
       const markdownWithTools = `---
 name: test-skill

packages/core/src/skills/skill-manager.ts

@@ -5,8 +5,10 @@
  */
 
 import * as fs from 'fs/promises';
+import * as fsSync from 'fs';
 import * as path from 'path';
 import * as os from 'os';
+import { watch as watchFs, type FSWatcher } from 'chokidar';
 import { parse as parseYaml } from '../utils/yaml-parser.js';
 import type {
   SkillConfig,
@@ -29,6 +31,9 @@ export class SkillManager {
   private skillsCache: Map<SkillLevel, SkillConfig[]> | null = null;
   private readonly changeListeners: Set<() => void> = new Set();
   private parseErrors: Map<string, SkillError> = new Map();
+  private readonly watchers: Map<string, FSWatcher> = new Map();
+  private watchStarted = false;
+  private refreshTimer: NodeJS.Timeout | null = null;
 
   constructor(private readonly config: Config) {}
 
@@ -221,6 +226,37 @@ export class SkillManager {
     this.notifyChangeListeners();
   }
 
+  /**
+   * Starts watching skill directories for changes.
+   */
+  async startWatching(): Promise<void> {
+    if (this.watchStarted) {
+      return;
+    }
+
+    this.watchStarted = true;
+    await this.ensureUserSkillsDir();
+    await this.refreshCache();
+    this.updateWatchersFromCache();
+  }
+
+  /**
+   * Stops watching skill directories for changes.
+   */
+  stopWatching(): void {
+    for (const watcher of this.watchers.values()) {
+      void watcher.close().catch((error) => {
+        console.warn('Failed to close skills watcher:', error);
+      });
+    }
+    this.watchers.clear();
+    this.watchStarted = false;
+    if (this.refreshTimer) {
+      clearTimeout(this.refreshTimer);
+      this.refreshTimer = null;
+    }
+  }
+
   /**
    * Parses a SKILL.md file and returns the configuration.
    *
@@ -271,9 +307,11 @@ export class SkillManager {
     level: SkillLevel,
   ): SkillConfig {
     try {
+      const normalizedContent = normalizeSkillFileContent(content);
+
       // Split frontmatter and content
-      const frontmatterRegex = /^---\n([\s\S]*?)\n---\n([\s\S]*)$/;
-      const match = content.match(frontmatterRegex);
+      const frontmatterRegex = /^---\n([\s\S]*?)\n---(?:\n|$)([\s\S]*)$/;
+      const match = normalizedContent.match(frontmatterRegex);
 
       if (!match) {
         throw new Error('Invalid format: missing YAML frontmatter');
@@ -449,4 +487,84 @@ export class SkillManager {
       this.skillsCache.set(level, levelSkills);
     }
   }
+
+  private updateWatchersFromCache(): void {
+    const watchTargets = new Set<string>(
+      (['project', 'user'] as const)
+        .map((level) => this.getSkillsBaseDir(level))
+        .filter((baseDir) => fsSync.existsSync(baseDir)),
+    );
+
+    for (const existingPath of this.watchers.keys()) {
+      if (!watchTargets.has(existingPath)) {
+        void this.watchers
+          .get(existingPath)
+          ?.close()
+          .catch((error) => {
+            console.warn(
+              `Failed to close skills watcher for ${existingPath}:`,
+              error,
+            );
+          });
+        this.watchers.delete(existingPath);
+      }
+    }
+
+    for (const watchPath of watchTargets) {
+      if (this.watchers.has(watchPath)) {
+        continue;
+      }
+
+      try {
+        const watcher = watchFs(watchPath, {
+          ignoreInitial: true,
+        })
+          .on('all', () => {
+            this.scheduleRefresh();
+          })
+          .on('error', (error) => {
+            console.warn(`Skills watcher error for ${watchPath}:`, error);
+          });
+        this.watchers.set(watchPath, watcher);
+      } catch (error) {
+        console.warn(
+          `Failed to watch skills directory at ${watchPath}:`,
+          error,
+        );
+      }
+    }
+  }
+
+  private scheduleRefresh(): void {
+    if (this.refreshTimer) {
+      clearTimeout(this.refreshTimer);
+    }
+
+    this.refreshTimer = setTimeout(() => {
+      this.refreshTimer = null;
+      void this.refreshCache().then(() => this.updateWatchersFromCache());
+    }, 150);
+  }
+
+  private async ensureUserSkillsDir(): Promise<void> {
+    const baseDir = this.getSkillsBaseDir('user');
+    try {
+      await fs.mkdir(baseDir, { recursive: true });
+    } catch (error) {
+      console.warn(
+        `Failed to create user skills directory at ${baseDir}:`,
+        error,
+      );
+    }
+  }
+}
+
+function normalizeSkillFileContent(content: string): string {
+  // Strip UTF-8 BOM to ensure frontmatter starts at the first character.
+  let normalized = content.replace(/^\uFEFF/, '');
+
+  // Normalize line endings so skills authored on Windows (CRLF) parse correctly.
+  normalized = normalized.replace(/\r\n/g, '\n').replace(/\r/g, '\n');
+
+  return normalized;
 }

packages/core/src/telemetry/constants.ts

@@ -35,6 +35,7 @@ export const EVENT_MODEL_SLASH_COMMAND = 'qwen-code.slash_command.model';
 export const EVENT_SUBAGENT_EXECUTION = 'qwen-code.subagent_execution';
 export const EVENT_SKILL_LAUNCH = 'qwen-code.skill_launch';
 export const EVENT_AUTH = 'qwen-code.auth';
+export const EVENT_USER_FEEDBACK = 'qwen-code.user_feedback';
 
 // Performance Events
 export const EVENT_STARTUP_PERFORMANCE = 'qwen-code.startup.performance';

packages/core/src/telemetry/index.ts

@@ -45,6 +45,7 @@ export {
   logNextSpeakerCheck,
   logAuth,
   logSkillLaunch,
+  logUserFeedback,
 } from './loggers.js';
 export type { SlashCommandEvent, ChatCompressionEvent } from './types.js';
 export {
@@ -65,6 +66,8 @@ export {
   NextSpeakerCheckEvent,
   AuthEvent,
   SkillLaunchEvent,
+  UserFeedbackEvent,
+  UserFeedbackRating,
 } from './types.js';
 export { makeSlashCommandEvent, makeChatCompressionEvent } from './types.js';
 export type { TelemetryEvent } from './types.js';

packages/core/src/telemetry/loggers.ts

@@ -38,6 +38,7 @@ import {
   EVENT_INVALID_CHUNK,
   EVENT_AUTH,
   EVENT_SKILL_LAUNCH,
+  EVENT_USER_FEEDBACK,
 } from './constants.js';
 import {
   recordApiErrorMetrics,
@@ -86,6 +87,7 @@ import type {
   InvalidChunkEvent,
   AuthEvent,
   SkillLaunchEvent,
+  UserFeedbackEvent,
 } from './types.js';
 import type { UiEvent } from './uiTelemetry.js';
 import { uiTelemetryService } from './uiTelemetry.js';
@@ -887,3 +889,32 @@ export function logSkillLaunch(config: Config, event: SkillLaunchEvent): void {
   };
   logger.emit(logRecord);
 }
+
+export function logUserFeedback(
+  config: Config,
+  event: UserFeedbackEvent,
+): void {
+  const uiEvent = {
+    ...event,
+    'event.name': EVENT_USER_FEEDBACK,
+    'event.timestamp': new Date().toISOString(),
+  } as UiEvent;
+  uiTelemetryService.addEvent(uiEvent);
+  config.getChatRecordingService()?.recordUiTelemetryEvent(uiEvent);
+  QwenLogger.getInstance(config)?.logUserFeedbackEvent(event);
+  if (!isTelemetrySdkInitialized()) return;
+
+  const attributes: LogAttributes = {
+    ...getCommonAttributes(config),
+    ...event,
+    'event.name': EVENT_USER_FEEDBACK,
+    'event.timestamp': new Date().toISOString(),
+  };
+
+  const logger = logs.getLogger(SERVICE_NAME);
+  const logRecord: LogRecord = {
+    body: `User feedback: Rating ${event.rating} for session ${event.session_id}.`,
+    attributes,
+  };
+  logger.emit(logRecord);
+}

packages/core/src/telemetry/qwen-logger/qwen-logger.ts

@@ -39,6 +39,7 @@ import type {
   ExtensionDisableEvent,
   AuthEvent,
   SkillLaunchEvent,
+  UserFeedbackEvent,
   RipgrepFallbackEvent,
   EndSessionEvent,
 } from '../types.js';
@@ -842,6 +843,21 @@ export class QwenLogger {
     this.flushIfNeeded();
   }
 
+  logUserFeedbackEvent(event: UserFeedbackEvent): void {
+    const rumEvent = this.createActionEvent('user', 'user_feedback', {
+      properties: {
+        session_id: event.session_id,
+        rating: event.rating,
+        model: event.model,
+        approval_mode: event.approval_mode,
+        prompt_id: event.prompt_id || '',
+      },
+    });
+
+    this.enqueueLogEvent(rumEvent);
+    this.flushIfNeeded();
+  }
+
   logChatCompressionEvent(event: ChatCompressionEvent): void {
     const rumEvent = this.createActionEvent('misc', 'chat_compression', {
       properties: {

packages/core/src/telemetry/types.ts

@@ -757,6 +757,38 @@ export class SkillLaunchEvent implements BaseTelemetryEvent {
   }
 }
 
+export enum UserFeedbackRating {
+  BAD = 1,
+  FINE = 2,
+  GOOD = 3,
+}
+
+export class UserFeedbackEvent implements BaseTelemetryEvent {
+  'event.name': 'user_feedback';
+  'event.timestamp': string;
+  session_id: string;
+  rating: UserFeedbackRating;
+  model: string;
+  approval_mode: string;
+  prompt_id?: string;
+
+  constructor(
+    session_id: string,
+    rating: UserFeedbackRating,
+    model: string,
+    approval_mode: string,
+    prompt_id?: string,
+  ) {
+    this['event.name'] = 'user_feedback';
+    this['event.timestamp'] = new Date().toISOString();
+    this.session_id = session_id;
+    this.rating = rating;
+    this.model = model;
+    this.approval_mode = approval_mode;
+    this.prompt_id = prompt_id;
+  }
+}
+
 export type TelemetryEvent =
   | StartSessionEvent
   | EndSessionEvent
@@ -786,7 +818,8 @@ export type TelemetryEvent =
   | ToolOutputTruncatedEvent
   | ModelSlashCommandEvent
   | AuthEvent
-  | SkillLaunchEvent;
+  | SkillLaunchEvent
+  | UserFeedbackEvent;
 
 export class ExtensionDisableEvent implements BaseTelemetryEvent {
   'event.name': 'extension_disable';

packages/core/src/tools/__snapshots__/shell.test.ts.snap

@@ -1,67 +1,98 @@
 // Vitest Snapshot v1, https://vitest.dev/guide/snapshot.html
 
 exports[`ShellTool > getDescription > should return the non-windows description when not on windows 1`] = `
-"This tool executes a given shell command as \`bash -c <command>\`. Command can start background processes using \`&\`. Command is executed as a subprocess that leads its own process group. Command process group can be terminated as \`kill -- -PGID\` or signaled as \`kill -s SIGNAL -- -PGID\`.
+"Executes a given shell command (as \`bash -c <command>\`) in a persistent shell session with optional timeout, ensuring proper handling and security measures.
 
-      **Background vs Foreground Execution:**
-      You should decide whether commands should run in background or foreground based on their nature:
-      
-      **Use background execution (is_background: true) for:**
-      - Long-running development servers: \`npm run start\`, \`npm run dev\`, \`yarn dev\`, \`bun run start\`
-      - Build watchers: \`npm run watch\`, \`webpack --watch\`
-      - Database servers: \`mongod\`, \`mysql\`, \`redis-server\`
-      - Web servers: \`python -m http.server\`, \`php -S localhost:8000\`
-      - Any command expected to run indefinitely until manually stopped
-      
-      **Use foreground execution (is_background: false) for:**
-      - One-time commands: \`ls\`, \`cat\`, \`grep\`
-      - Build commands: \`npm run build\`, \`make\`
-      - Installation commands: \`npm install\`, \`pip install\`
-      - Git operations: \`git commit\`, \`git push\`
-      - Test runs: \`npm test\`, \`pytest\`
-      
-      The following information is returned:
+IMPORTANT: This tool is for terminal operations like git, npm, docker, etc. DO NOT use it for file operations (reading, writing, editing, searching, finding files) - use the specialized tools for this instead.
 
-      Command: Executed command.
-      Directory: Directory where command was executed, or \`(root)\`.
-      Stdout: Output on stdout stream. Can be \`(empty)\` or partial on error and for any unwaited background processes.
-      Stderr: Output on stderr stream. Can be \`(empty)\` or partial on error and for any unwaited background processes.
-      Error: Error or \`(none)\` if no error was reported for the subprocess.
-      Exit Code: Exit code or \`(none)\` if terminated by signal.
-      Signal: Signal number or \`(none)\` if no signal was received.
-      Background PIDs: List of background processes started or \`(none)\`.
-      Process Group PGID: Process group started or \`(none)\`"
+**Usage notes**:
+- The command argument is required.
+- You can specify an optional timeout in milliseconds (up to 600000ms / 10 minutes). If not specified, commands will timeout after 120000ms (2 minutes).
+- It is very helpful if you write a clear, concise description of what this command does in 5-10 words.
+
+- Avoid using run_shell_command with the \`find\`, \`grep\`, \`cat\`, \`head\`, \`tail\`, \`sed\`, \`awk\`, or \`echo\` commands, unless explicitly instructed or when these commands are truly necessary for the task. Instead, always prefer using the dedicated tools for these commands:
+  - File search: Use glob (NOT find or ls)
+  - Content search: Use grep_search (NOT grep or rg)
+  - Read files: Use read_file (NOT cat/head/tail)
+  - Edit files: Use edit (NOT sed/awk)
+  - Write files: Use write_file (NOT echo >/cat <<EOF)
+  - Communication: Output text directly (NOT echo/printf)
+- When issuing multiple commands:
+  - If the commands are independent and can run in parallel, make multiple run_shell_command tool calls in a single message. For example, if you need to run "git status" and "git diff", send a single message with two run_shell_command tool calls in parallel.
+  - If the commands depend on each other and must run sequentially, use a single run_shell_command call with '&&' to chain them together (e.g., \`git add . && git commit -m "message" && git push\`). For instance, if one operation must complete before another starts (like mkdir before cp, Write before run_shell_command for git operations, or git add before git commit), run these operations sequentially instead.
+  - Use ';' only when you need to run commands sequentially but don't care if earlier commands fail
+  - DO NOT use newlines to separate commands (newlines are ok in quoted strings)
+- Try to maintain your current working directory throughout the session by using absolute paths and avoiding usage of \`cd\`. You may use \`cd\` if the User explicitly requests it.
+  <good-example>
+  pytest /foo/bar/tests
+  </good-example>
+  <bad-example>
+  cd /foo/bar && pytest tests
+  </bad-example>
+
+**Background vs Foreground Execution:**
+- You should decide whether commands should run in background or foreground based on their nature:
+- Use background execution (is_background: true) for:
+  - Long-running development servers: \`npm run start\`, \`npm run dev\`, \`yarn dev\`, \`bun run start\`
+  - Build watchers: \`npm run watch\`, \`webpack --watch\`
+  - Database servers: \`mongod\`, \`mysql\`, \`redis-server\`
+  - Web servers: \`python -m http.server\`, \`php -S localhost:8000\`
+  - Any command expected to run indefinitely until manually stopped
+
+  - Command is executed as a subprocess that leads its own process group. Command process group can be terminated as \`kill -- -PGID\` or signaled as \`kill -s SIGNAL -- -PGID\`.
+- Use foreground execution (is_background: false) for:
+  - One-time commands: \`ls\`, \`cat\`, \`grep\`
+  - Build commands: \`npm run build\`, \`make\`
+  - Installation commands: \`npm install\`, \`pip install\`
+  - Git operations: \`git commit\`, \`git push\`
+  - Test runs: \`npm test\`, \`pytest\`
+"
 `;
 
 exports[`ShellTool > getDescription > should return the windows description when on windows 1`] = `
-"This tool executes a given shell command as \`cmd.exe /c <command>\`. Command can start background processes using \`start /b\`.
+"Executes a given shell command (as \`cmd.exe /c <command>\`) in a persistent shell session with optional timeout, ensuring proper handling and security measures.
 
-      **Background vs Foreground Execution:**
-      You should decide whether commands should run in background or foreground based on their nature:
-      
-      **Use background execution (is_background: true) for:**
-      - Long-running development servers: \`npm run start\`, \`npm run dev\`, \`yarn dev\`, \`bun run start\`
-      - Build watchers: \`npm run watch\`, \`webpack --watch\`
-      - Database servers: \`mongod\`, \`mysql\`, \`redis-server\`
-      - Web servers: \`python -m http.server\`, \`php -S localhost:8000\`
-      - Any command expected to run indefinitely until manually stopped
-      
-      **Use foreground execution (is_background: false) for:**
-      - One-time commands: \`ls\`, \`cat\`, \`grep\`
-      - Build commands: \`npm run build\`, \`make\`
-      - Installation commands: \`npm install\`, \`pip install\`
-      - Git operations: \`git commit\`, \`git push\`
-      - Test runs: \`npm test\`, \`pytest\`
-      
-      The following information is returned:
+IMPORTANT: This tool is for terminal operations like git, npm, docker, etc. DO NOT use it for file operations (reading, writing, editing, searching, finding files) - use the specialized tools for this instead.
 
-      Command: Executed command.
-      Directory: Directory where command was executed, or \`(root)\`.
-      Stdout: Output on stdout stream. Can be \`(empty)\` or partial on error and for any unwaited background processes.
-      Stderr: Output on stderr stream. Can be \`(empty)\` or partial on error and for any unwaited background processes.
-      Error: Error or \`(none)\` if no error was reported for the subprocess.
-      Exit Code: Exit code or \`(none)\` if terminated by signal.
-      Signal: Signal number or \`(none)\` if no signal was received.
-      Background PIDs: List of background processes started or \`(none)\`.
-      Process Group PGID: Process group started or \`(none)\`"
+**Usage notes**:
+- The command argument is required.
+- You can specify an optional timeout in milliseconds (up to 600000ms / 10 minutes). If not specified, commands will timeout after 120000ms (2 minutes).
+- It is very helpful if you write a clear, concise description of what this command does in 5-10 words.
+
+- Avoid using run_shell_command with the \`find\`, \`grep\`, \`cat\`, \`head\`, \`tail\`, \`sed\`, \`awk\`, or \`echo\` commands, unless explicitly instructed or when these commands are truly necessary for the task. Instead, always prefer using the dedicated tools for these commands:
+  - File search: Use glob (NOT find or ls)
+  - Content search: Use grep_search (NOT grep or rg)
+  - Read files: Use read_file (NOT cat/head/tail)
+  - Edit files: Use edit (NOT sed/awk)
+  - Write files: Use write_file (NOT echo >/cat <<EOF)
+  - Communication: Output text directly (NOT echo/printf)
+- When issuing multiple commands:
+  - If the commands are independent and can run in parallel, make multiple run_shell_command tool calls in a single message. For example, if you need to run "git status" and "git diff", send a single message with two run_shell_command tool calls in parallel.
+  - If the commands depend on each other and must run sequentially, use a single run_shell_command call with '&&' to chain them together (e.g., \`git add . && git commit -m "message" && git push\`). For instance, if one operation must complete before another starts (like mkdir before cp, Write before run_shell_command for git operations, or git add before git commit), run these operations sequentially instead.
+  - Use ';' only when you need to run commands sequentially but don't care if earlier commands fail
+  - DO NOT use newlines to separate commands (newlines are ok in quoted strings)
+- Try to maintain your current working directory throughout the session by using absolute paths and avoiding usage of \`cd\`. You may use \`cd\` if the User explicitly requests it.
+  <good-example>
+  pytest /foo/bar/tests
+  </good-example>
+  <bad-example>
+  cd /foo/bar && pytest tests
+  </bad-example>
+
+**Background vs Foreground Execution:**
+- You should decide whether commands should run in background or foreground based on their nature:
+- Use background execution (is_background: true) for:
+  - Long-running development servers: \`npm run start\`, \`npm run dev\`, \`yarn dev\`, \`bun run start\`
+  - Build watchers: \`npm run watch\`, \`webpack --watch\`
+  - Database servers: \`mongod\`, \`mysql\`, \`redis-server\`
+  - Web servers: \`python -m http.server\`, \`php -S localhost:8000\`
+  - Any command expected to run indefinitely until manually stopped
+
+- Use foreground execution (is_background: false) for:
+  - One-time commands: \`ls\`, \`cat\`, \`grep\`
+  - Build commands: \`npm run build\`, \`make\`
+  - Installation commands: \`npm install\`, \`pip install\`
+  - Git operations: \`git commit\`, \`git push\`
+  - Test runs: \`npm test\`, \`pytest\`
+"
 `;