mirror of
https://github.com/QwenLM/qwen-code.git
synced 2026-04-28 11:41:04 +00:00
Merge branch 'main' into feat/sandbox-config-improvements
This commit is contained in:
tanzhenxin
commit
3a549419ba
363 changed files with 37015 additions and 6989 deletions
|
|
@ -2,7 +2,7 @@
|
|||
|
||||
> [!tip]
|
||||
>
|
||||
> **Authentication / API keys:** Authentication (Qwen OAuth vs OpenAI-compatible API) and auth-related environment variables (like `OPENAI_API_KEY`) are documented in **[Authentication](../configuration/auth)**.
|
||||
> **Authentication / API keys:** Authentication (Qwen OAuth, Alibaba Cloud Coding Plan, or API Key) and auth-related environment variables (like `OPENAI_API_KEY`) are documented in **[Authentication](../configuration/auth)**.
|
||||
|
||||
> [!note]
|
||||
>
|
||||
|
|
@ -125,18 +125,18 @@ Settings are organized into categories. All settings should be placed within the
|
|||
|
||||
#### model
|
||||
|
||||
| Setting | Type | Description | Default |
|
||||
| -------------------------------------------------- | ------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ----------- |
|
||||
| `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`, `enableCacheControl`, `contextWindowSize` (override model's context window size), `customHeaders` (custom HTTP headers for API requests), and `extra_body` (additional body parameters for OpenAI-compatible API requests only), 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` |
|
||||
| `model.skipStartupContext` | boolean | Skips sending the startup workspace context (environment summary and acknowledgement) at the beginning of each session. Enable this if you prefer to provide context manually or want to save tokens on startup. | `false` |
|
||||
| `model.enableOpenAILogging` | boolean | Enables logging of OpenAI API calls for debugging and analysis. When enabled, API requests and responses are logged to JSON files. | `false` |
|
||||
| `model.openAILoggingDir` | string | Custom directory path for OpenAI API logs. If not specified, defaults to `logs/openai` in the current working directory. Supports absolute paths, relative paths (resolved from current working directory), and `~` expansion (home directory). | `undefined` |
|
||||
| Setting | Type | Description | Default |
|
||||
| -------------------------------------------------- | ------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------- |
|
||||
| `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`, `enableCacheControl`, `contextWindowSize` (override model's context window size), `modalities` (override auto-detected input modalities), `customHeaders` (custom HTTP headers for API requests), and `extra_body` (additional body parameters for OpenAI-compatible API requests only), 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` |
|
||||
| `model.skipStartupContext` | boolean | Skips sending the startup workspace context (environment summary and acknowledgement) at the beginning of each session. Enable this if you prefer to provide context manually or want to save tokens on startup. | `false` |
|
||||
| `model.enableOpenAILogging` | boolean | Enables logging of OpenAI API calls for debugging and analysis. When enabled, API requests and responses are logged to JSON files. | `false` |
|
||||
| `model.openAILoggingDir` | string | Custom directory path for OpenAI API logs. If not specified, defaults to `logs/openai` in the current working directory. Supports absolute paths, relative paths (resolved from current working directory), and `~` expansion (home directory). | `undefined` |
|
||||
|
||||
**Example model.generationConfig:**
|
||||
|
||||
|
|
@ -146,10 +146,12 @@ Settings are organized into categories. All settings should be placed within the
|
|||
"generationConfig": {
|
||||
"timeout": 60000,
|
||||
"contextWindowSize": 128000,
|
||||
"modalities": {
|
||||
"image": true
|
||||
},
|
||||
"enableCacheControl": true,
|
||||
"customHeaders": {
|
||||
"X-Request-ID": "req-123",
|
||||
"X-User-ID": "user-456"
|
||||
"X-Client-Request-ID": "req-123"
|
||||
},
|
||||
"extra_body": {
|
||||
"enable_thinking": true
|
||||
|
|
@ -168,6 +170,10 @@ Settings are organized into categories. All settings should be placed within the
|
|||
|
||||
Overrides the default context window size for the selected model. Qwen Code determines the context window using built-in defaults based on model name matching, with a constant fallback value. Use this setting when a provider's effective context limit differs from Qwen Code's default. This value defines the model's assumed maximum context capacity, not a per-request token limit.
|
||||
|
||||
**modalities:**
|
||||
|
||||
Overrides the auto-detected input modalities for the selected model. Qwen Code automatically detects supported modalities (image, PDF, audio, video) based on model name pattern matching. Use this setting when the auto-detection is incorrect — for example, to enable `pdf` for a model that supports it but isn't recognized. Format: `{ "image": true, "pdf": true, "audio": true, "video": true }`. Omit a key or set it to `false` for unsupported types.
|
||||
|
||||
**customHeaders:**
|
||||
|
||||
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.
|
||||
|
|
@ -180,102 +186,6 @@ The `extra_body` field allows you to add custom parameters to the request body s
|
|||
- `"./custom-logs"` - Logs to `./custom-logs` relative to current directory
|
||||
- `"/tmp/openai-logs"` - Logs to absolute path `/tmp/openai-logs`
|
||||
|
||||
#### modelProviders
|
||||
|
||||
Use `modelProviders` to declare curated model lists per auth type that the `/model` picker can switch between. Keys must be valid auth types (`openai`, `anthropic`, `gemini`, `vertex-ai`, etc.). Each entry requires an `id` and **must include `envKey`**, with optional `name`, `description`, `baseUrl`, and `generationConfig`. Credentials are never persisted in settings; the runtime reads them from `process.env[envKey]`. Qwen OAuth models remain hard-coded and cannot be overridden.
|
||||
|
||||
##### Example
|
||||
|
||||
```json
|
||||
{
|
||||
"modelProviders": {
|
||||
"openai": [
|
||||
{
|
||||
"id": "gpt-4o",
|
||||
"name": "GPT-4o",
|
||||
"envKey": "OPENAI_API_KEY",
|
||||
"baseUrl": "https://api.openai.com/v1",
|
||||
"generationConfig": {
|
||||
"timeout": 60000,
|
||||
"maxRetries": 3,
|
||||
"customHeaders": {
|
||||
"X-Model-Version": "v1.0",
|
||||
"X-Request-Priority": "high"
|
||||
},
|
||||
"extra_body": {
|
||||
"enable_thinking": true
|
||||
},
|
||||
"samplingParams": { "temperature": 0.2 }
|
||||
}
|
||||
}
|
||||
],
|
||||
"anthropic": [
|
||||
{
|
||||
"id": "claude-3-5-sonnet",
|
||||
"envKey": "ANTHROPIC_API_KEY",
|
||||
"baseUrl": "https://api.anthropic.com/v1"
|
||||
}
|
||||
],
|
||||
"gemini": [
|
||||
{
|
||||
"id": "gemini-2.0-flash",
|
||||
"name": "Gemini 2.0 Flash",
|
||||
"envKey": "GEMINI_API_KEY",
|
||||
"baseUrl": "https://generativelanguage.googleapis.com"
|
||||
}
|
||||
],
|
||||
"vertex-ai": [
|
||||
{
|
||||
"id": "gemini-1.5-pro-vertex",
|
||||
"envKey": "GOOGLE_API_KEY",
|
||||
"baseUrl": "https://generativelanguage.googleapis.com"
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
> [!note]
|
||||
> Only the `/model` command exposes non-default auth types. Anthropic, Gemini, Vertex AI, etc., must be defined via `modelProviders`. The `/auth` command intentionally lists only the built-in Qwen OAuth and OpenAI flows.
|
||||
|
||||
##### Resolution layers and atomicity
|
||||
|
||||
The effective auth/model/credential values are chosen per field using the following precedence (first present wins). You can combine `--auth-type` with `--model` to point directly at a provider entry; these CLI flags run before other layers.
|
||||
|
||||
| Layer (highest → lowest) | authType | model | apiKey | baseUrl | apiKeyEnvKey | proxy |
|
||||
| -------------------------- | ----------------------------------- | ----------------------------------------------- | --------------------------------------------------- | ---------------------------------------------------- | ---------------------- | --------------------------------- |
|
||||
| Programmatic overrides | `/auth ` | `/auth` input | `/auth` input | `/auth` input | — | — |
|
||||
| Model provider selection | — | `modelProvider.id` | `env[modelProvider.envKey]` | `modelProvider.baseUrl` | `modelProvider.envKey` | — |
|
||||
| CLI arguments | `--auth-type` | `--model` | `--openaiApiKey` (or provider-specific equivalents) | `--openaiBaseUrl` (or provider-specific equivalents) | — | — |
|
||||
| Environment variables | — | Provider-specific mapping (e.g. `OPENAI_MODEL`) | Provider-specific mapping (e.g. `OPENAI_API_KEY`) | Provider-specific mapping (e.g. `OPENAI_BASE_URL`) | — | — |
|
||||
| Settings (`settings.json`) | `security.auth.selectedType` | `model.name` | `security.auth.apiKey` | `security.auth.baseUrl` | — | — |
|
||||
| Default / computed | Falls back to `AuthType.QWEN_OAUTH` | Built-in default (OpenAI ⇒ `qwen3-coder-plus`) | — | — | — | `Config.getProxy()` if configured |
|
||||
|
||||
\*When present, CLI auth flags override settings. Otherwise, `security.auth.selectedType` or the implicit default determine the auth type. Qwen OAuth and OpenAI are the only auth types surfaced without extra configuration.
|
||||
|
||||
Model-provider sourced values are applied atomically: once a provider model is active, every field it defines is protected from lower layers until you manually clear credentials via `/auth`. The final `generationConfig` is the projection across all layers—lower layers only fill gaps left by higher ones, and the provider layer remains impenetrable.
|
||||
|
||||
The merge strategy for `modelProviders` is REPLACE: the entire `modelProviders` from project settings will override the corresponding section in user settings, rather than merging the two.
|
||||
|
||||
##### Generation config layering
|
||||
|
||||
Per-field precedence for `generationConfig`:
|
||||
|
||||
1. Programmatic overrides (e.g. runtime `/model`, `/auth` changes)
|
||||
2. `modelProviders[authType][].generationConfig`
|
||||
3. `settings.model.generationConfig`
|
||||
4. Content-generator defaults (`getDefaultGenerationConfig` for OpenAI, `getParameterValue` for Gemini, etc.)
|
||||
|
||||
`samplingParams`, `customHeaders`, and `extra_body` are all 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
|
||||
|
||||
> [!important]
|
||||
> Define `modelProviders` in the user-scope `~/.qwen/settings.json` whenever possible and avoid persisting credential overrides in any scope. Keeping the provider catalog in user settings prevents merge/override conflicts between project and user scopes and ensures `/auth` and `/model` updates always write back to a consistent scope.
|
||||
|
||||
- `/model` and `/auth` persist `model.name` (where applicable) and `security.auth.selectedType` to the closest writable scope that already defines `modelProviders`; otherwise they fall back to the user scope. This keeps workspace/user files in sync with the active provider catalog.
|
||||
- Without `modelProviders`, the resolver mixes CLI/env/settings layers, which is fine for single-provider setups but cumbersome when frequently switching. Define provider catalogs whenever multi-model workflows are common so that switches stay atomic, source-attributed, and debuggable.
|
||||
|
||||
#### context
|
||||
|
||||
| Setting | Type | Description | Default |
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue