feat(provider): add lmstudio and align local provider default auth/base handling (#2193)

* feat(provider): add lmstudio vendor and local no-key behavior * refactor(provider): consolidate protocol metadata and local tests * fix(provider): sync lmstudio probing and model normalization * test(web): format lmstudio model status cases for golines
2026-06-12 18:08:54 +00:00 · 2026-03-31 14:48:18 +08:00
parent d11f1bc064
commit ee02e30992
11 changed files with 307 additions and 72 deletions
@@ -563,6 +563,7 @@ For complete documentation, see [`security_configuration.md`](security_configura
 | **通义千问 (Qwen)**     | `qwen/`           | `https://dashscope.aliyuncs.com/compatible-mode/v1` | OpenAI    | [Get Key](https://dashscope.console.aliyun.com)                  |
 | **NVIDIA**              | `nvidia/`         | `https://integrate.api.nvidia.com/v1`               | OpenAI    | [Get Key](https://build.nvidia.com)                              |
 | **Ollama**              | `ollama/`         | `http://localhost:11434/v1`                         | OpenAI    | Local (no key needed)                                            |
+| **LM Studio**           | `lmstudio/`       | `http://localhost:1234/v1`                          | OpenAI    | Optional (local default: no key)                                 |
 | **OpenRouter**          | `openrouter/`     | `https://openrouter.ai/api/v1`                      | OpenAI    | [Get Key](https://openrouter.ai/keys)                            |
 | **LiteLLM Proxy**       | `litellm/`        | `http://localhost:4000/v1`                          | OpenAI    | Your LiteLLM proxy key                                           |
 | **VLLM**                | `vllm/`           | `http://localhost:8000/v1`                          | OpenAI    | Local                                                            |
@@ -710,6 +711,21 @@ For direct Anthropic API access or custom endpoints that only support Anthropic'

 </details>

+<details>
+<summary><b>LM Studio (local)</b></summary>
+
+```json
+{
+  "model_name": "lmstudio-local",
+  "model": "lmstudio/openai/gpt-oss-20b"
+}
+```
+
+`api_base` defaults to `http://localhost:1234/v1`. API key is optional unless your LM Studio server enables authentication.<br/>
+PicoClaw sends OpenAI-compatible requests to LM Studio, and strips the `lmstudio/` prefix before sending requests, so `lmstudio/openai/gpt-oss-20b` sends `openai/gpt-oss-20b` to the LM Studio server.
+
+</details>
+
 <details>
 <summary><b>Custom Proxy / LiteLLM</b></summary>

@@ -56,6 +56,7 @@ This design also enables **multi-agent support** with flexible provider selectio
 | **通义千问 (Qwen)** | `qwen/`           | `https://dashscope.aliyuncs.com/compatible-mode/v1` | OpenAI    | [Get Key](https://dashscope.console.aliyun.com)                  |
 | **NVIDIA**          | `nvidia/`         | `https://integrate.api.nvidia.com/v1`               | OpenAI    | [Get Key](https://build.nvidia.com)                              |
 | **Ollama**          | `ollama/`         | `http://localhost:11434/v1`                         | OpenAI    | Local (no key needed)                                            |
+| **LM Studio**       | `lmstudio/`       | `http://localhost:1234/v1`                          | OpenAI    | Optional (local default: no key)                                 |
 | **OpenRouter**      | `openrouter/`     | `https://openrouter.ai/api/v1`                      | OpenAI    | [Get Key](https://openrouter.ai/keys)                            |
 | **LiteLLM Proxy**   | `litellm/`        | `http://localhost:4000/v1`                          | OpenAI    | Your LiteLLM proxy key                                            |
 | **VLLM**            | `vllm/`           | `http://localhost:8000/v1`                          | OpenAI    | Local                                                            |
@@ -226,6 +227,18 @@ For direct Anthropic API access or custom endpoints that only support Anthropic'
 }
 ```

+**LM Studio (local)**
+
+```json
+{
+  "model_name": "lmstudio-local",
+  "model": "lmstudio/openai/gpt-oss-20b"
+}
+```
+
+`api_base` defaults to `http://localhost:1234/v1`. API key is optional unless your LM Studio server enables authentication.<br/>
+PicoClaw sends OpenAI-compatible requests to LM Studio, and strips the `lmstudio/` prefix before sending requests, so `lmstudio/openai/gpt-oss-20b` sends `openai/gpt-oss-20b` to the LM Studio server.
+
 **Custom Proxy/API**

 ```json
@@ -365,6 +365,7 @@ Agent 读取 HEARTBEAT.md
 | **通义千问 (Qwen)**     | `qwen/`           | `https://dashscope.aliyuncs.com/compatible-mode/v1` | OpenAI    | [获取](https://dashscope.console.aliyun.com)                     |
 | **NVIDIA**              | `nvidia/`         | `https://integrate.api.nvidia.com/v1`               | OpenAI    | [获取](https://build.nvidia.com)                                 |
 | **Ollama**              | `ollama/`         | `http://localhost:11434/v1`                         | OpenAI    | 本地（无需 Key）                                                 |
+| **LM Studio**           | `lmstudio/`       | `http://localhost:1234/v1`                          | OpenAI    | 可选（本地默认无需密钥）                                         |
 | **OpenRouter**          | `openrouter/`     | `https://openrouter.ai/api/v1`                      | OpenAI    | [获取](https://openrouter.ai/keys)                               |
 | **LiteLLM Proxy**       | `litellm/`        | `http://localhost:4000/v1`                          | OpenAI    | 你的 LiteLLM 代理 Key                                            |
 | **VLLM**                | `vllm/`           | `http://localhost:8000/v1`                          | OpenAI    | 本地                                                             |
@@ -506,6 +507,21 @@ Agent 读取 HEARTBEAT.md

 </details>

+<details>
+<summary><b>LM Studio（本地）</b></summary>
+
+```json
+{
+  "model_name": "lmstudio-local",
+  "model": "lmstudio/openai/gpt-oss-20b"
+}
+```
+
+`api_base` 默认是 `http://localhost:1234/v1`。除非你在 LM Studio 侧启用了认证，否则不需要配置 API Key。
+PicoClaw 向 LM Studio 的 OpenAI 兼容终结点发送请求，且将移除首个 `lmstudio/` 前缀，因此 `lmstudio/openai/gpt-oss-20b` 会发送 `openai/gpt-oss-20b`。
+
+</details>
+
 <details>
 <summary><b>自定义代理 / LiteLLM</b></summary>

@@ -53,6 +53,7 @@
 | **通义千问 (Qwen)** | `qwen/`           | `https://dashscope.aliyuncs.com/compatible-mode/v1` | OpenAI    | [获取密钥](https://dashscope.console.aliyun.com)                  |
 | **NVIDIA**          | `nvidia/`         | `https://integrate.api.nvidia.com/v1`               | OpenAI    | [获取密钥](https://build.nvidia.com)                              |
 | **Ollama**          | `ollama/`         | `http://localhost:11434/v1`                         | OpenAI    | 本地（无需密钥）                                                  |
+| **LM Studio**       | `lmstudio/`       | `http://localhost:1234/v1`                          | OpenAI    | 可选（本地默认无需密钥）                                          |
 | **OpenRouter**      | `openrouter/`     | `https://openrouter.ai/api/v1`                      | OpenAI    | [获取密钥](https://openrouter.ai/keys)                            |
 | **LiteLLM Proxy**   | `litellm/`        | `http://localhost:4000/v1`                          | OpenAI    | 你的 LiteLLM 代理密钥                                             |
 | **VLLM**            | `vllm/`           | `http://localhost:8000/v1`                          | OpenAI    | 本地                                                              |
@@ -211,6 +212,18 @@
 }
 ```

+**LM Studio（本地）**
+
+```json
+{
+  "model_name": "lmstudio-local",
+  "model": "lmstudio/openai/gpt-oss-20b"
+}
+```
+
+`api_base` 默认是 `http://localhost:1234/v1`。除非你在 LM Studio 侧启用了认证，否则不需要配置 API Key。
+PicoClaw 向 LM Studio 的 OpenAI 兼容终结点发送请求，且将移除首个 `lmstudio/` 前缀，因此 `lmstudio/openai/gpt-oss-20b` 会发送 `openai/gpt-oss-20b`。
+
 **自定义代理/API**

 ```json