feat: support comma-separated AI_MODEL for quick multi-model setup (#870)

Users expected setting AI_MODEL to a comma-separated list to expose
multiple models in the picker, but the value was used verbatim as a
single model id, leaving the picker with only the "Server Default"
fallback.

Add a third-priority fallback in loadEnvServerModelsConfig: when
AI_MODELS_CONFIG and ai-models.json are both absent, AI_MODEL contains
a comma, and AI_PROVIDER is set to a known provider, synthesize an
equivalent ServerModelsConfig with the provider's models trimmed,
deduplicated, and the first marked as default.

Also makes getAIModel and getValidationModel pick the first comma-split
value when falling back to AI_MODEL, so requests started before the
client picker hydrates still resolve to a real model id.

Docs (en/cn/ja) and env.example updated; tests cover the new fallback
plus the no-comma / no-AI_PROVIDER negative cases.
This commit is contained in:
Dayuan Jiang
2026-06-15 14:27:55 +09:00
committed by GitHub
parent 0f9699843f
commit 8e42dd9da8
10 changed files with 140 additions and 12 deletions

View File

@@ -217,7 +217,7 @@ npm run dev
### 服务端多模型配置
管理员可以配置多个服务端模型,让所有用户无需提供个人 API Key 即可使用。通过 `AI_MODELS_CONFIG` 环境变量JSON 字符串)或 `ai-models.json` 文件配置。
管理员可以配置多个服务端模型,让所有用户无需提供个人 API Key 即可使用。通过 `AI_MODELS_CONFIG` 环境变量JSON 字符串)或 `ai-models.json` 文件配置。如果只需要单 provider 下的多个模型,也可以直接在 `AI_MODEL` 中用逗号分隔模型 ID。
**模型要求**此任务需要强大的模型能力因为它涉及生成具有严格格式约束的长文本draw.io XML。推荐使用 Claude Sonnet 4.5、GPT-5.1、Gemini 3 Pro 和 DeepSeek V3.2/R1。

View File

@@ -336,6 +336,17 @@ AI_MODELS_CONFIG='{"providers":[{"name":"OpenAI","provider":"openai","models":["
在项目根目录创建 `ai-models.json` 文件(或通过 `AI_MODELS_CONFIG_PATH` 指定路径)。
**方式三:`AI_MODEL` 用逗号分隔**(单 provider 的快速配置)
如果只需要暴露同一 provider 下的多个模型,可以直接在 `AI_MODEL` 里用逗号分隔。第一个模型会作为默认值。
```bash
AI_PROVIDER=doubao
AI_MODEL=doubao-seed-1-8-251215,doubao-seed-1-6-flash,doubao-seed-1-6-pro
```
这是等价 `ai-models.json` 的简写形式。如果需要配置多个 provider或自定义 `apiKeyEnv` / `baseUrlEnv`,请使用方式一或方式二。
### 配置示例
```json