agent: Allow customizing temperature by provider/model (#30033)

Adds a new `agent.model_parameters` setting that allows the user to
specify a custom temperature for a provider AND/OR model:

```json5
    "model_parameters": [
      // To set parameters for all requests to OpenAI models:
      {
        "provider": "openai",
        "temperature": 0.5
      },
      // To set parameters for all requests in general:
      {
        "temperature": 0
      },
      // To set parameters for a specific provider and model:
      {
        "provider": "zed.dev",
        "model": "claude-3-7-sonnet-latest",
        "temperature": 1.0
      }
    ],
```

Release Notes:

- agent: Allow customizing temperature by provider/model

---------

Co-authored-by: Max Brunsfeld <maxbrunsfeld@gmail.com>
Co-authored-by: Marshall Bowers <git@maxdeviant.com>

crates/agent/src/message_editor.rs

@@ -8,7 +8,7 @@ use crate::ui::{
     AnimatedLabel, MaxModeTooltip,
     preview::{AgentPreview, UsageCallout},
 };
-use assistant_settings::CompletionMode;
+use assistant_settings::{AssistantSettings, CompletionMode};
 use buffer_diff::BufferDiff;
 use client::UserStore;
 use collections::{HashMap, HashSet};
@@ -1273,7 +1273,7 @@ impl MessageEditor {
                         messages: vec![request_message],
                         tools: vec![],
                         stop: vec![],
-                        temperature: None,
+                        temperature: AssistantSettings::temperature_for_model(&model.model, cx),
                     };
 
                     Some(model.model.count_tokens(request, cx))