Add RubyLLM::Chat#with_params to add custom parameters to the underlying API payload (#265)

## What this does

Implements `with_request_options` (renamed from `with_options` due to
ActiveRecord conflict -- see conversation) with @crmne's suggestions
from comment
#130 (review)
and tested against all providers.

This allows users to set arbitrary options on the payload before it's
sent to the provider's API endpoint. The render_payload takes
precedence.

Demo:

```ruby
chat = RubyLLM
  .chat(model: "qwen3", provider: :ollama)
  .with_request_options(response_format: {type: "json_object"})
  .with_instructions("Answer with a JSON object with the key `result` and a numerical value.")
response = chat.ask("What is the square root of 64?")
response.content
=> "{\n  \"result\": 8\n}"
```

This is a power-user feature, and is specific to each provider (and
model, to a lesser extent). I added a brief section to the docs.

For tests: different providers supported different options, so tests are
divided by provider.

(Note that `deep_merge` is required for Gemini in particular because it
relies on a top-level `generationConfig` object.)

## Type of change

- [ ] Bug fix
- [X] New feature
- [ ] Breaking change
- [ ] Documentation
- [ ] Performance improvement

## Scope check

- [X] I read the [Contributing
Guide](https://github.com/crmne/ruby_llm/blob/main/CONTRIBUTING.md)
- [X] This aligns with RubyLLM's focus on **LLM communication**
- [X] This isn't application-specific logic that belongs in user code
- [X] This benefits most users, not just my specific use case

## Quality check

- [ ] I ran `overcommit --install` and all hooks pass
- [X] I tested my changes thoroughly
- [X] I updated documentation if needed
- [X] I didn't modify auto-generated files manually (`models.json`,
`aliases.json`)

## API changes

- [ ] Breaking change
- [X] New public methods/classes
- [ ] Changed method signatures
- [ ] No API changes

## Related issues

- #130
- #131
- #221

---------

Co-authored-by: Carmine Paolino <[email protected]>

Author: compumike

docs/guides/chat.md

@@ -246,6 +246,19 @@ puts response2.content
 
 You can set the temperature using `with_temperature`, which returns the `Chat` instance for chaining.
 
+## Custom Request Parameters
+
+You can configure additional provider-specific features by adding custom fields to each API request. Use the `with_params` method.
+
+```ruby
+# response_format parameter is supported by :openai, :ollama, :deepseek
+chat = RubyLLM.chat.with_params(response_format: { type: 'json_object' })
+response = chat.ask "What is the square root of 64? Answer with a JSON object with the key `result`."
+puts JSON.parse(response.content)
+```
+
+Allowed parameters vary widely by provider and model.
+
 ## Tracking Token Usage
 
 Understanding token usage is important for managing costs and staying within context limits. Each `RubyLLM::Message` returned by `ask` includes token counts.
@@ -311,4 +324,4 @@ This guide covered the core `Chat` interface. Now you might want to explore:
 *   [Using Tools]({% link guides/tools.md %}): Enable the AI to call your Ruby code.
 *   [Streaming Responses]({% link guides/streaming.md %}): Get real-time feedback from the AI.
 *   [Rails Integration]({% link guides/rails.md %}): Persist your chat conversations easily.
-*   [Error Handling]({% link guides/error-handling.md %}): Build robust applications that handle API issues.
+*   [Error Handling]({% link guides/error-handling.md %}): Build robust applications that handle API issues.

lib/ruby_llm/active_record/acts_as.rb

@@ -130,6 +130,11 @@ def with_context(...)
         self
       end
 
+      def with_params(...)
+        to_llm.with_params(...)
+        self
+      end
+
       def on_new_message(...)
         to_llm.on_new_message(...)
         self

lib/ruby_llm/chat.rb

@@ -11,7 +11,7 @@ module RubyLLM
   class Chat
     include Enumerable
 
-    attr_reader :model, :messages, :tools
+    attr_reader :model, :messages, :tools, :params
 
     def initialize(model: nil, provider: nil, assume_model_exists: false, context: nil)
       if assume_model_exists && !provider
@@ -25,6 +25,7 @@ def initialize(model: nil, provider: nil, assume_model_exists: false, context: n
       @temperature = 0.7
       @messages = []
       @tools = {}
+      @params = {}
       @on = {
         new_message: nil,
         end_message: nil
@@ -78,6 +79,11 @@ def with_context(context)
       self
     end
 
+    def with_params(**params)
+      @params = params
+      self
+    end
+
     def on_new_message(&block)
       @on[:new_message] = block
       self
@@ -99,6 +105,7 @@ def complete(&)
         temperature: @temperature,
         model: @model.id,
         connection: @connection,
+        params: @params,
         &wrap_streaming_block(&)
       )
 

lib/ruby_llm/provider.rb

@@ -10,14 +10,19 @@ module Provider
     module Methods
       extend Streaming
 
-      def complete(messages, tools:, temperature:, model:, connection:, &)
+      def complete(messages, tools:, temperature:, model:, connection:, params: {}, &) # rubocop:disable Metrics/ParameterLists
         normalized_temperature = maybe_normalize_temperature(temperature, model)
 
-        payload = render_payload(messages,
-                                 tools: tools,
-                                 temperature: normalized_temperature,
-                                 model: model,
-                                 stream: block_given?)
+        payload = deep_merge(
+          params,
+          render_payload(
+            messages,
+            tools: tools,
+            temperature: normalized_temperature,
+            model: model,
+            stream: block_given?
+          )
+        )
 
         if block_given?
           stream_response connection, payload, &
@@ -26,6 +31,16 @@ def complete(messages, tools:, temperature:, model:, connection:, &)
         end
       end
 
+      def deep_merge(params, payload)
+        params.merge(payload) do |_key, params_value, payload_value|
+          if params_value.is_a?(Hash) && payload_value.is_a?(Hash)
+            deep_merge(params_value, payload_value)
+          else
+            payload_value
+          end
+        end
+      end
+
       def list_models(connection:)
         response = connection.get models_url
         parse_list_models_response response, slug, capabilities