mirror of
https://github.com/QwenLM/qwen-code.git
synced 2026-04-29 04:00:36 +00:00
Merge branch 'main' into feat/context-usage
This commit is contained in:
pomelo
GitHub
commit
d4379d6ee6
428 changed files with 36382 additions and 11297 deletions
|
|
@ -58,6 +58,40 @@ qwen --resume 123e4567-e89b-12d3-a456-426614174000 -p "Apply the follow-up refac
|
|||
> - Session data is project-scoped JSONL under `~/.qwen/projects/<sanitized-cwd>/chats`.
|
||||
> - Restores conversation history, tool outputs, and chat-compression checkpoints before sending the new prompt.
|
||||
|
||||
## Customize the Main Session Prompt
|
||||
|
||||
You can change the main session system prompt for a single CLI run without editing shared memory files.
|
||||
|
||||
### Override the Built-in System Prompt
|
||||
|
||||
Use `--system-prompt` to replace Qwen Code's built-in main-session prompt for the current run:
|
||||
|
||||
```bash
|
||||
qwen -p "Review this patch" --system-prompt "You are a terse release reviewer. Report only blocking issues."
|
||||
```
|
||||
|
||||
### Append Extra Instructions
|
||||
|
||||
Use `--append-system-prompt` to keep the built-in prompt and add extra instructions for this run:
|
||||
|
||||
```bash
|
||||
qwen -p "Review this patch" --append-system-prompt "Be terse and focus on concrete findings."
|
||||
```
|
||||
|
||||
You can combine both flags when you want a custom base prompt plus an extra run-specific instruction:
|
||||
|
||||
```bash
|
||||
qwen -p "Summarize this repository" \
|
||||
--system-prompt "You are a migration planner." \
|
||||
--append-system-prompt "Return exactly three bullets."
|
||||
```
|
||||
|
||||
> [!note]
|
||||
>
|
||||
> - `--system-prompt` applies only to the current run's main session.
|
||||
> - Loaded memory and context files such as `QWEN.md` are still appended after `--system-prompt`.
|
||||
> - `--append-system-prompt` is applied after the built-in prompt and loaded memory, and can be used together with `--system-prompt`.
|
||||
|
||||
## Output Formats
|
||||
|
||||
Qwen Code supports multiple output formats for different use cases:
|
||||
|
|
@ -189,19 +223,21 @@ qwen -p "Write code" --output-format stream-json --include-partial-messages | jq
|
|||
|
||||
Key command-line options for headless usage:
|
||||
|
||||
| Option | Description | Example |
|
||||
| ---------------------------- | --------------------------------------------------- | ------------------------------------------------------------------------ |
|
||||
| `--prompt`, `-p` | Run in headless mode | `qwen -p "query"` |
|
||||
| `--output-format`, `-o` | Specify output format (text, json, stream-json) | `qwen -p "query" --output-format json` |
|
||||
| `--input-format` | Specify input format (text, stream-json) | `qwen --input-format text --output-format stream-json` |
|
||||
| `--include-partial-messages` | Include partial messages in stream-json output | `qwen -p "query" --output-format stream-json --include-partial-messages` |
|
||||
| `--debug`, `-d` | Enable debug mode | `qwen -p "query" --debug` |
|
||||
| `--all-files`, `-a` | Include all files in context | `qwen -p "query" --all-files` |
|
||||
| `--include-directories` | Include additional directories | `qwen -p "query" --include-directories src,docs` |
|
||||
| `--yolo`, `-y` | Auto-approve all actions | `qwen -p "query" --yolo` |
|
||||
| `--approval-mode` | Set approval mode | `qwen -p "query" --approval-mode auto_edit` |
|
||||
| `--continue` | Resume the most recent session for this project | `qwen --continue -p "Pick up where we left off"` |
|
||||
| `--resume [sessionId]` | Resume a specific session (or choose interactively) | `qwen --resume 123e... -p "Finish the refactor"` |
|
||||
| Option | Description | Example |
|
||||
| ---------------------------- | ------------------------------------------------------------------------ | ------------------------------------------------------------------------ |
|
||||
| `--prompt`, `-p` | Run in headless mode | `qwen -p "query"` |
|
||||
| `--output-format`, `-o` | Specify output format (text, json, stream-json) | `qwen -p "query" --output-format json` |
|
||||
| `--input-format` | Specify input format (text, stream-json) | `qwen --input-format text --output-format stream-json` |
|
||||
| `--include-partial-messages` | Include partial messages in stream-json output | `qwen -p "query" --output-format stream-json --include-partial-messages` |
|
||||
| `--system-prompt` | Override the main session system prompt for this run | `qwen -p "query" --system-prompt "You are a terse reviewer."` |
|
||||
| `--append-system-prompt` | Append extra instructions to the main session system prompt for this run | `qwen -p "query" --append-system-prompt "Focus on concrete findings."` |
|
||||
| `--debug`, `-d` | Enable debug mode | `qwen -p "query" --debug` |
|
||||
| `--all-files`, `-a` | Include all files in context | `qwen -p "query" --all-files` |
|
||||
| `--include-directories` | Include additional directories | `qwen -p "query" --include-directories src,docs` |
|
||||
| `--yolo`, `-y` | Auto-approve all actions | `qwen -p "query" --yolo` |
|
||||
| `--approval-mode` | Set approval mode | `qwen -p "query" --approval-mode auto_edit` |
|
||||
| `--continue` | Resume the most recent session for this project | `qwen --continue -p "Pick up where we left off"` |
|
||||
| `--resume [sessionId]` | Resume a specific session (or choose interactively) | `qwen --resume 123e... -p "Finish the refactor"` |
|
||||
|
||||
For complete details on all available configuration options, settings files, and environment variables, see the [Configuration Guide](../configuration/settings).
|
||||
|
||||
|
|
|
|||
|
|
@ -30,10 +30,10 @@ Qwen Code loads MCP servers from `mcpServers` in your `settings.json`. You can c
|
|||
qwen mcp add --transport http my-server http://localhost:3000/mcp
|
||||
```
|
||||
|
||||
2. Verify it shows up:
|
||||
2. Open MCP management dialog to view and manage servers:
|
||||
|
||||
```bash
|
||||
qwen mcp list
|
||||
qwen mcp
|
||||
```
|
||||
|
||||
3. Restart Qwen Code in the same project (or start it if it wasn’t running yet), then ask the model to use tools from that server.
|
||||
|
|
@ -274,12 +274,6 @@ qwen mcp add [options] <name> <commandOrUrl> [args...]
|
|||
| `--include-tools` | A comma-separated list of tools to include. | all tools included | `--include-tools mytool,othertool` |
|
||||
| `--exclude-tools` | A comma-separated list of tools to exclude. | none | `--exclude-tools mytool` |
|
||||
|
||||
#### Listing servers (`qwen mcp list`)
|
||||
|
||||
```bash
|
||||
qwen mcp list
|
||||
```
|
||||
|
||||
#### Removing a server (`qwen mcp remove`)
|
||||
|
||||
```bash
|
||||
|
|
|
|||
|
|
@ -29,7 +29,7 @@ The benefits of sandboxing include:
|
|||
|
||||
> [!note]
|
||||
>
|
||||
> **Naming note:** Some sandbox-related environment variables still use the `GEMINI_*` prefix for backwards compatibility.
|
||||
> **Naming note:** Some sandbox-related environment variables may have used the `GEMINI_*` prefix historically. All new environment variables use the `QWEN_*` prefix.
|
||||
|
||||
## Sandboxing methods
|
||||
|
||||
|
|
@ -68,7 +68,7 @@ The container sandbox mounts your workspace and your `~/.qwen` directory into th
|
|||
qwen -s -p "analyze the code structure"
|
||||
|
||||
# Or enable sandboxing for your shell session (recommended for CI / scripts)
|
||||
export GEMINI_SANDBOX=true # true auto-picks a provider (see notes below)
|
||||
export QWEN_SANDBOX=true # true auto-picks a provider (see notes below)
|
||||
qwen -p "run the test suite"
|
||||
|
||||
# Configure in settings.json
|
||||
|
|
@ -83,26 +83,26 @@ qwen -p "run the test suite"
|
|||
>
|
||||
> **Provider selection notes:**
|
||||
>
|
||||
> - On **macOS**, `GEMINI_SANDBOX=true` typically selects `sandbox-exec` (Seatbelt) if available.
|
||||
> - On **Linux/Windows**, `GEMINI_SANDBOX=true` requires `docker` or `podman` to be installed.
|
||||
> - To force a provider, set `GEMINI_SANDBOX=docker|podman|sandbox-exec`.
|
||||
> - On **macOS**, `QWEN_SANDBOX=true` typically selects `sandbox-exec` (Seatbelt) if available.
|
||||
> - On **Linux/Windows**, `QWEN_SANDBOX=true` requires `docker` or `podman` to be installed.
|
||||
> - To force a provider, set `QWEN_SANDBOX=docker|podman|sandbox-exec`.
|
||||
|
||||
## Configuration
|
||||
|
||||
### Enable sandboxing (in order of precedence)
|
||||
|
||||
1. **Environment variable**: `GEMINI_SANDBOX=true|false|docker|podman|sandbox-exec`
|
||||
1. **Environment variable**: `QWEN_SANDBOX=true|false|docker|podman|sandbox-exec`
|
||||
2. **Command flag / argument**: `-s`, `--sandbox`, or `--sandbox=<provider>`
|
||||
3. **Settings file**: `tools.sandbox` in your `settings.json` (e.g., `{"tools": {"sandbox": true}}`).
|
||||
|
||||
> [!important]
|
||||
>
|
||||
> If `GEMINI_SANDBOX` is set, it **overrides** the CLI flag and `settings.json`.
|
||||
> If `QWEN_SANDBOX` is set, it **overrides** the CLI flag and `settings.json`.
|
||||
|
||||
### Configure the sandbox image (Docker/Podman)
|
||||
|
||||
- **CLI flag**: `--sandbox-image <image>`
|
||||
- **Environment variable**: `GEMINI_SANDBOX_IMAGE=<image>`
|
||||
- **Environment variable**: `QWEN_SANDBOX_IMAGE=<image>`
|
||||
|
||||
If you don’t set either, Qwen Code uses the default image configured in the CLI package (for example `ghcr.io/qwenlm/qwen-code:<version>`).
|
||||
|
||||
|
|
@ -150,7 +150,7 @@ export SANDBOX_FLAGS="--flag1 --flag2=value"
|
|||
|
||||
If you want to restrict outbound network access to an allowlist, you can run a local proxy alongside the sandbox:
|
||||
|
||||
- Set `GEMINI_SANDBOX_PROXY_COMMAND=<command>`
|
||||
- Set `QWEN_SANDBOX_PROXY_COMMAND=<command>`
|
||||
- The command must start a proxy server that listens on `:::8877`
|
||||
|
||||
This is especially useful with `*-proxied` Seatbelt profiles.
|
||||
|
|
@ -181,6 +181,29 @@ export SANDBOX_SET_UID_GID=false # Disable UID/GID mapping
|
|||
- Container sandbox: add them via `.qwen/sandbox.Dockerfile` or `.qwen/sandbox.bashrc`.
|
||||
- Seatbelt: your host binaries are used, but the sandbox may restrict access to some paths.
|
||||
|
||||
**Java not available in Docker sandbox**
|
||||
|
||||
The official Qwen Code Docker image is intentionally minimal to keep the image small, secure, and fast to pull. Different users require different language runtimes (Java, Python, Node.js, etc.), and bundling all environments into a single image is not practical. Therefore, Java is **not included by default** in the Docker sandbox.
|
||||
|
||||
If your workflow requires Java, you can extend the base image by creating a `.qwen/sandbox.Dockerfile` in your project:
|
||||
|
||||
```dockerfile
|
||||
FROM ghcr.io/qwenlm/qwen-code:latest
|
||||
|
||||
RUN apt-get update && \
|
||||
apt-get install -y openjdk-17-jre && \
|
||||
apt-get clean && \
|
||||
rm -rf /var/lib/apt/lists/*
|
||||
```
|
||||
|
||||
Then rebuild the sandbox image:
|
||||
|
||||
```bash
|
||||
QWEN_SANDBOX=docker BUILD_SANDBOX=1 qwen -s
|
||||
```
|
||||
|
||||
For more details on customizing the sandbox, see [Customizing the sandbox environment](/developers/tools/sandbox).
|
||||
|
||||
**Network issues**
|
||||
|
||||
- Check sandbox profile allows network.
|
||||
|
|
|
|||
|
|
@ -502,3 +502,10 @@ Always follow these standards:
|
|||
- **Access Control**: Project and user-level separation provides appropriate boundaries
|
||||
- **Sensitive Information**: Avoid including secrets or credentials in agent configurations
|
||||
- **Production Environments**: Consider separate agents for production vs development environments
|
||||
|
||||
## Limits
|
||||
|
||||
The following soft warnings apply to Subagent configurations (no hard limits are enforced):
|
||||
|
||||
- **Description Field**: A warning is shown for descriptions exceeding 1,000 characters
|
||||
- **System Prompt**: A warning is shown for system prompts exceeding 10,000 characters
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue