feat: Add support for OpenRouter (#92)

* Add support for OpenRouter as a new model provider

- Introduced `ProviderOpenRouter` in the `models` package.
- Added OpenRouter-specific models, including `GPT41`, `GPT41Mini`, `GPT4o`, and others, with their configurations and costs.
- Updated `generateSchema` to include OpenRouter as a provider.
- Added OpenRouter-specific environment variable handling (`OPENROUTER_API_KEY`) in `config.go`.
- Implemented default model settings for OpenRouter agents in `setDefaultModelForAgent`.
- Updated `getProviderAPIKey` to retrieve the OpenRouter API key.
- Extended `SupportedModels` to include OpenRouter models.
- Added OpenRouter client initialization in the `provider` package.
- Modified `processGeneration` to handle `FinishReasonUnknown` in addition to `FinishReasonToolUse`.

* [feature/openrouter-provider] Add new models and provider to schema

- Added "deepseek-chat-free" and "deepseek-r1-free" to the list of supported models in `opencode-schema.json`.

* [feature/openrouter-provider] Add OpenRouter provider support and integrate new models

- Updated README.md to include OpenRouter as a supported provider and its configuration details.
- Added `OPENROUTER_API_KEY` to environment variable configuration.
- Introduced OpenRouter-specific models in `internal/llm/models/openrouter.go` with mappings to existing cost and token configurations.
- Updated `internal/config/config.go` to set default models for OpenRouter agents.
- Extended `opencode-schema.json` to include OpenRouter models in the schema definitions.
- Refactored model IDs and names to align with OpenRouter naming conventions.

* [feature/openrouter-provider] Refactor finish reason handling and tool call logic in agent and OpenAI provider

- Simplified finish reason check in `agent.go` by removing redundant variable assignment.
- Updated `openai.go` to override the finish reason to `FinishReasonToolUse` when tool calls are present.
- Ensured consistent finish reason handling in both `send` and `stream` methods of the OpenAI provider.

[feature/openrouter-provider] Refactor finish reason handling and tool call logic in agent and OpenAI provider

- Simplified finish reason check in `agent.go` by removing redundant variable assignment.
- Updated `openai.go` to override the finish reason to `FinishReasonToolUse` when tool calls are present.
- Ensured consistent finish reason handling in both `send` and `stream` methods of the OpenAI provider.

* **[feature/openrouter-provider] Add support for custom headers in OpenAI client configuration**

- Introduced a new `extraHeaders` field in the `openaiOptions` struct to allow specifying additional HTTP headers.
- Added logic in `newOpenAIClient` to apply `extraHeaders` to the OpenAI client configuration.
- Implemented a new option function `WithOpenAIExtraHeaders` to set custom headers in `openaiOptions`.
- Updated the OpenRouter provider configuration in `NewProvider` to include default headers (`HTTP-Referer` and `X-Title`) for OpenRouter API requests.

* Update OpenRouter model config and remove unsupported models

* [feature/openrouter-provider] Update OpenRouter models and default configurations

- Added new OpenRouter models: `claude-3.5-sonnet`, `claude-3-haiku`, `claude-3.7-sonnet`, `claude-3.5-haiku`, and `claude-3-opus` in `openrouter.go`.
- Updated default agent models in `config.go`:
  - `agents.coder.model` now uses `claude-3.7-sonnet`.
  - `agents.task.model` now uses `claude-3.7-sonnet`.
  - `agents.title.model` now uses `claude-3.5-haiku`.
- Updated `opencode-schema.json` to include the new models in the allowed list for schema validation.
- Adjusted logic in `setDefaultModelForAgent` to reflect the new default models.

* [feature/openrouter-provider] Remove unused ProviderEvent emission in stream function

The changes remove the emission of a `ProviderEvent` with type `EventContentStop` in the `stream` function of the `openaiClient` implementation. This event was sent upon successful stream completion but is no longer used.

2 files changed, 41 insertions, 3 deletions

diff --git a/internal/llm/provider/openai.go b/internal/llm/provider/openai.go
index 4d45aebfa..b557df535 100644
--- a/internal/llm/provider/openai.go
+++ b/internal/llm/provider/openai.go
@@ -21,6 +21,7 @@ type openaiOptions struct {
 	baseURL         string
 	disableCache    bool
 	reasoningEffort string
+	extraHeaders    map[string]string
 }
 
 type OpenAIOption func(*openaiOptions)
@@ -49,6 +50,12 @@ func newOpenAIClient(opts providerClientOptions) OpenAIClient {
 		openaiClientOptions = append(openaiClientOptions, option.WithBaseURL(openaiOpts.baseURL))
 	}
 
+	if openaiOpts.extraHeaders != nil {
+		for key, value := range openaiOpts.extraHeaders {
+			openaiClientOptions = append(openaiClientOptions, option.WithHeader(key, value))
+		}
+	}
+
 	client := openai.NewClient(openaiClientOptions...)
 	return &openaiClient{
 		providerOptions: opts,
@@ -204,11 +211,18 @@ func (o *openaiClient) send(ctx context.Context, messages []message.Message, too
 			content = openaiResponse.Choices[0].Message.Content
 		}
 
+		toolCalls := o.toolCalls(*openaiResponse)
+		finishReason := o.finishReason(string(openaiResponse.Choices[0].FinishReason))
+
+		if len(toolCalls) > 0 {
+			finishReason = message.FinishReasonToolUse
+		}
+
 		return &ProviderResponse{
 			Content:      content,
-			ToolCalls:    o.toolCalls(*openaiResponse),
+			ToolCalls:    toolCalls,
 			Usage:        o.usage(*openaiResponse),
-			FinishReason: o.finishReason(string(openaiResponse.Choices[0].FinishReason)),
+			FinishReason: finishReason,
 		}, nil
 	}
 }
@@ -267,13 +281,19 @@ func (o *openaiClient) stream(ctx context.Context, messages []message.Message, t
 			err := openaiStream.Err()
 			if err == nil || errors.Is(err, io.EOF) {
 				// Stream completed successfully
+				finishReason := o.finishReason(string(acc.ChatCompletion.Choices[0].FinishReason))
+
+				if len(toolCalls) > 0 {
+					finishReason = message.FinishReasonToolUse
+				}
+
 				eventChan <- ProviderEvent{
 					Type: EventComplete,
 					Response: &ProviderResponse{
 						Content:      currentContent,
 						ToolCalls:    toolCalls,
 						Usage:        o.usage(acc.ChatCompletion),
-						FinishReason: o.finishReason(string(acc.ChatCompletion.Choices[0].FinishReason)),
+						FinishReason: finishReason,
 					},
 				}
 				close(eventChan)
@@ -375,6 +395,12 @@ func WithOpenAIBaseURL(baseURL string) OpenAIOption {
 	}
 }
 
+func WithOpenAIExtraHeaders(headers map[string]string) OpenAIOption {
+	return func(options *openaiOptions) {
+		options.extraHeaders = headers
+	}
+}
+
 func WithOpenAIDisableCache() OpenAIOption {
 	return func(options *openaiOptions) {
 		options.disableCache = true
diff --git a/internal/llm/provider/provider.go b/internal/llm/provider/provider.go
index 737b6fb00..1545bc27a 100644
--- a/internal/llm/provider/provider.go
+++ b/internal/llm/provider/provider.go
@@ -120,6 +120,18 @@ func NewProvider(providerName models.ModelProvider, opts ...ProviderClientOption
 			options: clientOptions,
 			client:  newAzureClient(clientOptions),
 		}, nil
+	case models.ProviderOpenRouter:
+		clientOptions.openaiOptions = append(clientOptions.openaiOptions,
+			WithOpenAIBaseURL("https://openrouter.ai/api/v1"),
+			WithOpenAIExtraHeaders(map[string]string{
+				"HTTP-Referer": "opencode.ai",
+				"X-Title":      "OpenCode",
+			}),
+		)
+		return &baseProvider[OpenAIClient]{
+			options: clientOptions,
+			client:  newOpenAIClient(clientOptions),
+		}, nil
 	case models.ProviderMock:
 		// TODO: implement mock client for test
 		panic("not implemented")