Add capabilities to OpenAI-compatible model settings (#36370)

### TL;DR
* Adds `capabilities` configuration for OpenAI-compatible models
* Relates to
https://github.com/zed-industries/zed/issues/36215#issuecomment-3193920491

### Summary
This PR introduces support for configuring model capabilities for
OpenAI-compatible language models. The implementation addresses the
issue that not all OpenAI-compatible APIs support the same features -
for example, Cerebras' API explicitly does not support
`parallel_tool_calls` as documented in their [OpenAI compatibility
guide](https://inference-docs.cerebras.ai/resources/openai#currently-unsupported-openai-features).

### Changes

1. **Model Capabilities Structure**:
- Added `ModelCapabilityToggles` struct for UI representation with
boolean toggle states
- Implemented proper parsing of capability toggles into
`ModelCapabilities`

2. **UI Updates**:
- Modified the "Add LLM Provider" modal to include checkboxes for each
capability
- Each OpenAI-compatible model can now be configured with its specific
capabilities through the UI

3. **Configuration File Structure**:
- Updated the settings schema to support a `capabilities` object for
each `openai_compatible` model
- Each capability (`tools`, `images`, `parallel_tool_calls`,
`prompt_cache_key`) can be individually specified per model

### Example Configuration

```json
{
  "openai_compatible": {
    "Cerebras": {
      "api_url": "https://api.cerebras.ai/v1",
      "available_models": [
        {
          "name": "gpt-oss-120b",
          "max_tokens": 131000,
          "capabilities": {
            "tools": true,
            "images": false,
            "parallel_tool_calls": false,
            "prompt_cache_key": false
          }
        }
      ]
    }
  }
}
```

### Tests Added

- Added tests to verify default capability values are correctly applied
- Added tests to verify that deselected toggles are properly parsed as
`false`
- Added tests to verify that mixed capability selections work correctly

Thanks to @osyvokon for the desired `capabilities` configuration
structure!


Release Notes:

- OpenAI-compatible models now have configurable capabilities (#36370;
thanks @calesennett)

---------

Co-authored-by: Oleksiy Syvokon <oleksiy@zed.dev>

crates/language_models/src/provider/open_ai_compatible.rs

@@ -38,6 +38,27 @@ pub struct AvailableModel {
     pub max_tokens: u64,
     pub max_output_tokens: Option<u64>,
     pub max_completion_tokens: Option<u64>,
+    #[serde(default)]
+    pub capabilities: ModelCapabilities,
+}
+
+#[derive(Clone, Debug, PartialEq, Serialize, Deserialize, JsonSchema)]
+pub struct ModelCapabilities {
+    pub tools: bool,
+    pub images: bool,
+    pub parallel_tool_calls: bool,
+    pub prompt_cache_key: bool,
+}
+
+impl Default for ModelCapabilities {
+    fn default() -> Self {
+        Self {
+            tools: true,
+            images: false,
+            parallel_tool_calls: false,
+            prompt_cache_key: false,
+        }
+    }
 }
 
 pub struct OpenAiCompatibleLanguageModelProvider {
@@ -293,17 +314,17 @@ impl LanguageModel for OpenAiCompatibleLanguageModel {
     }
 
     fn supports_tools(&self) -> bool {
-        true
+        self.model.capabilities.tools
     }
 
     fn supports_images(&self) -> bool {
-        false
+        self.model.capabilities.images
     }
 
     fn supports_tool_choice(&self, choice: LanguageModelToolChoice) -> bool {
         match choice {
-            LanguageModelToolChoice::Auto => true,
-            LanguageModelToolChoice::Any => true,
+            LanguageModelToolChoice::Auto => self.model.capabilities.tools,
+            LanguageModelToolChoice::Any => self.model.capabilities.tools,
             LanguageModelToolChoice::None => true,
         }
     }
@@ -355,13 +376,11 @@ impl LanguageModel for OpenAiCompatibleLanguageModel {
             LanguageModelCompletionError,
         >,
     > {
-        let supports_parallel_tool_call = true;
-        let supports_prompt_cache_key = false;
         let request = into_open_ai(
             request,
             &self.model.name,
-            supports_parallel_tool_call,
-            supports_prompt_cache_key,
+            self.model.capabilities.parallel_tool_calls,
+            self.model.capabilities.prompt_cache_key,
             self.max_output_tokens(),
             None,
         );