feat: add LM Studio provider for local Qwen model support (#340)

* feat: add LM Studio provider for local Qwen model support

Register `lmstudio` as an OpenAI-compatible provider in
`opencode.jsonc`, pointing at the default LM Studio local
server (`localhost:1234`).

* fix: correct LM Studio port and model IDs to match actual server

- Port: 11434 (not default 1234)
- Models: `gpt-oss:20b` and `deepseek-r1:70b` (actual loaded models)

* fix: address PR review — generic config, correct port, add docs

- Use LM Studio default port 1234 (not Ollama's 11434)
- Replace hardcoded model IDs with commented examples users fill in
- Add `LMSTUDIO_API_KEY` env var support
- Add LM Studio section to providers.md docs
- Add LM Studio tab to quickstart.md provider examples

Author: anandgupta42

.opencode/opencode.jsonc

@@ -4,6 +4,35 @@
     "opencode": {
       "options": {},
     },
+    // LM Studio — local inference via OpenAI-compatible API
+    // 1. Open LM Studio → Developer tab → Start Server (default port: 1234)
+    // 2. Load a model in LM Studio
+    // 3. Run: curl http://localhost:1234/v1/models   to find the model ID
+    // 4. Add the model ID to the "models" section below
+    // 5. Use as: altimate-code run -m lmstudio/<model-id>
+    "lmstudio": {
+      "name": "LM Studio",
+      "npm": "@ai-sdk/openai-compatible",
+      "env": ["LMSTUDIO_API_KEY"],
+      "options": {
+        "apiKey": "lm-studio",
+        "baseURL": "http://localhost:1234/v1",
+      },
+      "models": {
+        // Add your loaded models here. The key must match the model ID from LM Studio.
+        // Examples:
+        // "qwen2.5-7b-instruct": {
+        //   "name": "Qwen 2.5 7B Instruct",
+        //   "tool_call": true,
+        //   "limit": { "context": 131072, "output": 8192 }
+        // },
+        // "deepseek-r1:70b": {
+        //   "name": "DeepSeek R1 70B",
+        //   "tool_call": true,
+        //   "limit": { "context": 65536, "output": 8192 }
+        // }
+      },
+    },
   },
   "permission": {
     "edit": {

docs/docs/configure/providers.md

@@ -148,6 +148,48 @@ No API key needed. Runs entirely on your local machine.
 !!! info
     Make sure Ollama is running before starting altimate. Install it from [ollama.com](https://ollama.com) and pull your desired model with `ollama pull llama3.1`.
 
+## LM Studio (Local)
+
+Run local models through [LM Studio](https://lmstudio.ai)'s OpenAI-compatible server:
+
+```json
+{
+  "provider": {
+    "lmstudio": {
+      "name": "LM Studio",
+      "npm": "@ai-sdk/openai-compatible",
+      "env": ["LMSTUDIO_API_KEY"],
+      "options": {
+        "apiKey": "lm-studio",
+        "baseURL": "http://localhost:1234/v1"
+      },
+      "models": {
+        "qwen2.5-7b-instruct": {
+          "name": "Qwen 2.5 7B Instruct",
+          "tool_call": true,
+          "limit": { "context": 131072, "output": 8192 }
+        }
+      }
+    }
+  },
+  "model": "lmstudio/qwen2.5-7b-instruct"
+}
+```
+
+**Setup:**
+
+1. Open LM Studio → **Developer** tab → **Start Server** (default port: 1234)
+2. Load a model in LM Studio
+3. Find your model ID: `curl http://localhost:1234/v1/models`
+4. Add the model ID to the `models` section in your config
+5. Use it: `altimate-code run -m lmstudio/<model-id>`
+
+!!! tip
+    The model key in your config must match the model ID returned by LM Studio's `/v1/models` endpoint. If you change models in LM Studio, update the config to match.
+
+!!! note
+    If you changed LM Studio's default port, update the `baseURL` accordingly. No real API key is needed — the `"lm-studio"` placeholder satisfies the SDK requirement.
+
 ## OpenRouter
 
 ```json

docs/docs/getting-started/quickstart.md

@@ -130,6 +130,31 @@ Switch providers at any time by updating the `provider` and `model` fields in `a
     }
     ```
 
+=== "LM Studio (Local)"
+
+    ```json
+    {
+      "provider": {
+        "lmstudio": {
+          "name": "LM Studio",
+          "npm": "@ai-sdk/openai-compatible",
+          "options": {
+            "apiKey": "lm-studio",
+            "baseURL": "http://localhost:1234/v1"
+          },
+          "models": {
+            "qwen2.5-7b-instruct": {
+              "name": "Qwen 2.5 7B Instruct",
+              "tool_call": true,
+              "limit": { "context": 131072, "output": 8192 }
+            }
+          }
+        }
+      },
+      "model": "lmstudio/qwen2.5-7b-instruct"
+    }
+    ```
+
 === "OpenRouter"
 
     ```json