mirrors/opencode
1
0
Fork 0
mirror of https://github.com/anomalyco/opencode.git synced 2026-11-10 07:11:25 +03:00
Code Issues Packages Projects Releases Wiki Activity
143 Commits 2,608 Branches 1,168 Tags
v0.0.36
Commit Graph

30 Commits

  • 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.
    Isaac Scarrott · 2025-04-29 13:56:49 +02:00
    98e2910e82
  • feat: add azure openai models (#74)
    YJG · 2025-04-28 15:42:57 +02:00
    805aeff83c
  • feat: configure context paths (#86)
    Garrett Ladley · 2025-04-27 20:11:09 +02:00
    8f3a94df92
  • change package name
    Kujtim Hoxha · 2025-04-24 18:26:16 +02:00
    b106787a50
  • update mainter email
    Kujtim Hoxha · 2025-04-24 16:40:36 +02:00
    f879a94c95
  • small things
    Kujtim Hoxha · 2025-04-21 16:24:38 +02:00
    ed3518d075
  • add description
    Kujtim Hoxha · 2025-04-21 15:52:32 +02:00
    1e11805efc
  • config validation
    Kujtim Hoxha · 2025-04-21 14:29:28 +02:00
    a8d5787e8e
  • fix the memory bug
    Kujtim Hoxha · 2025-04-21 13:42:29 +02:00
    e7bb99baab
  • rename to opencode
    Kujtim Hoxha · 2025-04-21 13:42:02 +02:00
    cc07f7a186
  • reimplement agent,provider and add file history
    Kujtim Hoxha · 2025-04-21 13:42:00 +02:00
    bbfa60c787
  • cleanup diff, cleanup agent
    Kujtim Hoxha · 2025-04-21 13:41:27 +02:00
    cdc5f209dc
  • cleanup app, config and root
    Kujtim Hoxha · 2025-04-21 13:41:25 +02:00
    3ad983db0f
  • add initial git support
    Kujtim Hoxha · 2025-04-21 13:38:42 +02:00
    bd2ec29b65
  • refactor: use context for automatic lsp process cleanup
    Nacho Vazquez · 2025-04-12 12:43:23 -03:00
    bd2cb4b5b9
  • fix logs and add cancellation
    Kujtim Hoxha · 2025-04-10 13:29:44 +02:00
    36f201d5d3
  • finish logs page
    Kujtim Hoxha · 2025-04-09 19:07:39 +02:00
    d39d52d95d
  • Merge pull request #22 from adamdottv/adam/retries 
    fix(anthropic): better 429/529 handling
    Kujtim Hoxha · 2025-04-08 20:32:57 +02:00
    fde04bbf85
  • structure tools the same 
    - add some tests
- fix some tests
- change how we handle permissions
    Kujtim Hoxha · 2025-04-08 19:15:23 +02:00
    94923948e1
  • improve status message handling
    Kujtim Hoxha · 2025-04-07 19:43:31 +02:00
    f463ce6694
  • remove test code
    Kujtim Hoxha · 2025-04-07 12:56:54 +02:00
    a6db4f652c
  • Improve Sourcegraph tool with context window and fix diagnostics 
    - Add context_window parameter to control code context display
- Fix LSP diagnostics notification handling with proper async waiting
- Switch to keyword search pattern for better results
- Add Sourcegraph tool to task agent

🤖 Generated with termai
Co-Authored-By: termai <noreply@termai.io>
    Kujtim Hoxha · 2025-04-04 14:23:08 +02:00
    6bb1c84f7f
  • add initial lsp support
    Kujtim Hoxha · 2025-04-03 17:23:41 +02:00
    cfdd687216
  • rework llm
    Kujtim Hoxha · 2025-04-01 13:38:54 +02:00
    afd9ad0560
  • additional tools
    Kujtim Hoxha · 2025-03-26 01:12:30 +01:00
    904061c243
  • initial working agent
    Kujtim Hoxha · 2025-03-24 11:47:39 +01:00
    005b8ac167
  • initial agent setup
    Kujtim Hoxha · 2025-03-23 22:25:31 +01:00
    e7258e38ae
  • add initial stuff
    Kujtim Hoxha · 2025-03-23 19:19:08 +01:00
    8daa6e774a
  • add help
    Kujtim Hoxha · 2025-03-23 15:00:12 +01:00
    7844cacb25
  • initial
    Kujtim Hoxha · 2025-03-21 18:20:28 +01:00
    4b0ea68d7a