Nigel
/
opencode_offline
0
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity
opencode_offline/opencode-schema.json

377 lines
10 KiB
JSON
Raw Normal View History

config validation
2025-04-21 20:29:03 +08:00
{
"$schema": "http://json-schema.org/draft-07/schema#",
"definitions": {
"agent": {
"description": "Agent configuration",
"properties": {
"maxTokens": {
"description": "Maximum tokens for the agent",
"minimum": 1,
"type": "integer"
},
"model": {
"description": "Model ID for the agent",
"enum": [
feat: configure context paths (#86)
2025-04-28 02:11:09 +08:00
"bedrock.claude-3.7-sonnet",
"gpt-4o-mini",
feat: themes
2025-04-28 21:46:09 +08:00
"gemini-2.0-flash",
"openrouter.o3",
feat: add azure openai models (#74)
2025-04-28 21:42:57 +08:00
"azure.gpt-4o",
feat: themes
2025-04-28 21:46:09 +08:00
"azure.gpt-4.1",
"openrouter.gemini-2.5",
"meta-llama/llama-4-maverick-17b-128e-instruct",
"azure.o3-mini",
"azure.o1-mini",
"openrouter.gemini-2.5-flash",
"openrouter.gpt-4.1",
"claude-3.5-haiku",
feat: configure context paths (#86)
2025-04-28 02:11:09 +08:00
"gemini-2.0-flash-lite",
feat: themes
2025-04-28 21:46:09 +08:00
"azure.gpt-4.1-nano",
"openrouter.o1-pro",
"claude-3-haiku",
feat(groq): add support for Groq using the OpenAI provider
2025-04-25 13:48:48 +08:00
"deepseek-r1-distill-llama-70b",
feat: configure context paths (#86)
2025-04-28 02:11:09 +08:00
"gpt-4.1-mini",
feat: themes
2025-04-28 21:46:09 +08:00
"gpt-4.1",
"o3-mini",
"o1",
feat: configure context paths (#86)
2025-04-28 02:11:09 +08:00
"gemini-2.5",
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.
2025-04-29 19:56:49 +08:00
"openrouter.gpt-4.1-nano",
feat: themes
2025-04-28 21:46:09 +08:00
"azure.gpt-4.5-preview",
"gpt-4.5-preview",
"azure.o3",
"openrouter.o4-mini",
"openrouter.claude-3.7-sonnet",
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.
2025-04-29 19:56:49 +08:00
"openrouter.gpt-4.5-preview",
feat: themes
2025-04-28 21:46:09 +08:00
"claude-3-opus",
"o4-mini",
"o3",
"azure.o4-mini",
"azure.gpt-4.1-mini",
"gemini-2.5-flash",
"azure.gpt-4o-mini",
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.
2025-04-29 19:56:49 +08:00
"openrouter.gpt-4o-mini",
feat: themes
2025-04-28 21:46:09 +08:00
"openrouter.gpt-4.1-mini",
"openrouter.gpt-4o",
"claude-3.5-sonnet",
"o1-mini",
"openrouter.claude-3.5-haiku",
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.
2025-04-29 19:56:49 +08:00
"openrouter.o3-mini",
feat: themes
2025-04-28 21:46:09 +08:00
"openrouter.claude-3-opus",
"o1-pro",
"qwen-qwq",
"meta-llama/llama-4-scout-17b-16e-instruct",
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.
2025-04-29 19:56:49 +08:00
"openrouter.claude-3.5-sonnet",
feat: themes
2025-04-28 21:46:09 +08:00
"claude-3.7-sonnet",
"gpt-4o",
"openrouter.o1",
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.
2025-04-29 19:56:49 +08:00
"openrouter.claude-3-haiku",
feat: themes
2025-04-28 21:46:09 +08:00
"azure.o1",
"llama-3.3-70b-versatile",
"gpt-4.1-nano",
"openrouter.o1-mini"
config validation
2025-04-21 20:29:03 +08:00
],
"type": "string"
},
"reasoningEffort": {
"description": "Reasoning effort for models that support it (OpenAI, Anthropic)",
feat: themes
2025-04-28 21:46:09 +08:00
"enum": [
"low",
"medium",
"high"
],
config validation
2025-04-21 20:29:03 +08:00
"type": "string"
}
},
feat: themes
2025-04-28 21:46:09 +08:00
"required": [
"model"
],
config validation
2025-04-21 20:29:03 +08:00
"type": "object"
}
},
"description": "Configuration schema for the OpenCode application",
"properties": {
"agents": {
"additionalProperties": {
"description": "Agent configuration",
"properties": {
"maxTokens": {
"description": "Maximum tokens for the agent",
"minimum": 1,
"type": "integer"
},
"model": {
"description": "Model ID for the agent",
"enum": [
feat: configure context paths (#86)
2025-04-28 02:11:09 +08:00
"bedrock.claude-3.7-sonnet",
"gpt-4o-mini",
feat: themes
2025-04-28 21:46:09 +08:00
"gemini-2.0-flash",
"openrouter.o3",
feat: add azure openai models (#74)
2025-04-28 21:42:57 +08:00
"azure.gpt-4o",
feat: themes
2025-04-28 21:46:09 +08:00
"azure.gpt-4.1",
"openrouter.gemini-2.5",
"meta-llama/llama-4-maverick-17b-128e-instruct",
"azure.o3-mini",
"azure.o1-mini",
"openrouter.gemini-2.5-flash",
"openrouter.gpt-4.1",
"claude-3.5-haiku",
feat: configure context paths (#86)
2025-04-28 02:11:09 +08:00
"gemini-2.0-flash-lite",
feat: themes
2025-04-28 21:46:09 +08:00
"azure.gpt-4.1-nano",
"openrouter.o1-pro",
"claude-3-haiku",
feat(groq): add support for Groq using the OpenAI provider
2025-04-25 13:48:48 +08:00
"deepseek-r1-distill-llama-70b",
feat: configure context paths (#86)
2025-04-28 02:11:09 +08:00
"gpt-4.1-mini",
feat: themes
2025-04-28 21:46:09 +08:00
"gpt-4.1",
"o3-mini",
"o1",
feat: configure context paths (#86)
2025-04-28 02:11:09 +08:00
"gemini-2.5",
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.
2025-04-29 19:56:49 +08:00
"openrouter.gpt-4.1-nano",
feat: themes
2025-04-28 21:46:09 +08:00
"azure.gpt-4.5-preview",
"gpt-4.5-preview",
"azure.o3",
"openrouter.o4-mini",
"openrouter.claude-3.7-sonnet",
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.
2025-04-29 19:56:49 +08:00
"openrouter.gpt-4.5-preview",
feat: themes
2025-04-28 21:46:09 +08:00
"claude-3-opus",
"o4-mini",
"o3",
"azure.o4-mini",
"azure.gpt-4.1-mini",
"gemini-2.5-flash",
"azure.gpt-4o-mini",
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.
2025-04-29 19:56:49 +08:00
"openrouter.gpt-4o-mini",
feat: themes
2025-04-28 21:46:09 +08:00
"openrouter.gpt-4.1-mini",
"openrouter.gpt-4o",
"claude-3.5-sonnet",
"o1-mini",
"openrouter.claude-3.5-haiku",
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.
2025-04-29 19:56:49 +08:00
"openrouter.o3-mini",
feat: themes
2025-04-28 21:46:09 +08:00
"openrouter.claude-3-opus",
"o1-pro",
"qwen-qwq",
"meta-llama/llama-4-scout-17b-16e-instruct",
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.
2025-04-29 19:56:49 +08:00
"openrouter.claude-3.5-sonnet",
feat: themes
2025-04-28 21:46:09 +08:00
"claude-3.7-sonnet",
"gpt-4o",
"openrouter.o1",
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.
2025-04-29 19:56:49 +08:00
"openrouter.claude-3-haiku",
feat: themes
2025-04-28 21:46:09 +08:00
"azure.o1",
"llama-3.3-70b-versatile",
"gpt-4.1-nano",
"openrouter.o1-mini"
config validation
2025-04-21 20:29:03 +08:00
],
"type": "string"
},
"reasoningEffort": {
"description": "Reasoning effort for models that support it (OpenAI, Anthropic)",
feat: themes
2025-04-28 21:46:09 +08:00
"enum": [
"low",
"medium",
"high"
],
config validation
2025-04-21 20:29:03 +08:00
"type": "string"
}
},
feat: themes
2025-04-28 21:46:09 +08:00
"required": [
"model"
],
config validation
2025-04-21 20:29:03 +08:00
"type": "object"
},
"description": "Agent configurations",
"properties": {
"coder": {
"$ref": "#/definitions/agent"
},
"task": {
"$ref": "#/definitions/agent"
},
"title": {
"$ref": "#/definitions/agent"
}
},
"type": "object"
},
feat: configure context paths (#86)
2025-04-28 02:11:09 +08:00
"contextPaths": {
"default": [
".github/copilot-instructions.md",
".cursorrules",
".cursor/rules/",
"CLAUDE.md",
"CLAUDE.local.md",
"opencode.md",
"opencode.local.md",
"OpenCode.md",
"OpenCode.local.md",
"OPENCODE.md",
"OPENCODE.local.md"
],
"description": "Context paths for the application",
"items": {
"type": "string"
},
"type": "array"
},
config validation
2025-04-21 20:29:03 +08:00
"data": {
"description": "Storage configuration",
"properties": {
"directory": {
"default": ".opencode",
"description": "Directory where application data is stored",
"type": "string"
}
},
feat: themes
2025-04-28 21:46:09 +08:00
"required": [
"directory"
],
config validation
2025-04-21 20:29:03 +08:00
"type": "object"
},
"debug": {
"default": false,
"description": "Enable debug mode",
"type": "boolean"
},
"debugLSP": {
"default": false,
"description": "Enable LSP debug mode",
"type": "boolean"
},
"lsp": {
"additionalProperties": {
"description": "LSP configuration for a language",
"properties": {
"args": {
"description": "Command arguments for the LSP server",
"items": {
"type": "string"
},
"type": "array"
},
"command": {
"description": "Command to execute for the LSP server",
"type": "string"
},
"disabled": {
"default": false,
"description": "Whether the LSP is disabled",
"type": "boolean"
},
"options": {
"description": "Additional options for the LSP server",
"type": "object"
}
},
feat: themes
2025-04-28 21:46:09 +08:00
"required": [
"command"
],
config validation
2025-04-21 20:29:03 +08:00
"type": "object"
},
"description": "Language Server Protocol configurations",
"type": "object"
},
"mcpServers": {
"additionalProperties": {
"description": "MCP server configuration",
"properties": {
"args": {
"description": "Command arguments for the MCP server",
"items": {
"type": "string"
},
"type": "array"
},
"command": {
"description": "Command to execute for the MCP server",
"type": "string"
},
"env": {
"description": "Environment variables for the MCP server",
"items": {
"type": "string"
},
"type": "array"
},
"headers": {
"additionalProperties": {
"type": "string"
},
"description": "HTTP headers for SSE type MCP servers",
"type": "object"
},
"type": {
"default": "stdio",
"description": "Type of MCP server",
feat: themes
2025-04-28 21:46:09 +08:00
"enum": [
"stdio",
"sse"
],
config validation
2025-04-21 20:29:03 +08:00
"type": "string"
},
"url": {
"description": "URL for SSE type MCP servers",
"type": "string"
}
},
feat: themes
2025-04-28 21:46:09 +08:00
"required": [
"command"
],
config validation
2025-04-21 20:29:03 +08:00
"type": "object"
},
"description": "Model Control Protocol server configurations",
"type": "object"
},
"providers": {
"additionalProperties": {
"description": "Provider configuration",
"properties": {
"apiKey": {
"description": "API key for the provider",
"type": "string"
},
"disabled": {
"default": false,
"description": "Whether the provider is disabled",
"type": "boolean"
},
"provider": {
"description": "Provider type",
"enum": [
"anthropic",
"openai",
"gemini",
"groq",
feat: themes
2025-04-28 21:46:09 +08:00
"openrouter",
feat: add azure openai models (#74)
2025-04-28 21:42:57 +08:00
"bedrock",
feat: themes
2025-04-28 21:46:09 +08:00
"azure"
config validation
2025-04-21 20:29:03 +08:00
],
"type": "string"
}
},
"type": "object"
},
"description": "LLM provider configurations",
"type": "object"
},
feat: themes
2025-04-28 21:46:09 +08:00
"tui": {
"description": "Terminal User Interface configuration",
"properties": {
"theme": {
"default": "catppuccin",
"description": "TUI theme name",
"enum": [
"catppuccin",
"gruvbox"
],
"type": "string"
}
},
"type": "object"
},
config validation
2025-04-21 20:29:03 +08:00
"wd": {
"description": "Working directory for the application",
"type": "string"
}
},
"title": "OpenCode Configuration",
"type": "object"
}