用程式碼修復 CI
一段簡短的腳本請 OpenCode 修復失敗的測試,然後重新執行。
從你自己的腳本、CI 工作和工具驅動 OpenCode。SDK 在你的處理程序內執行 OpenCode,使用你的設定和模型,其具型別的用戶端可以建立工作階段、傳送提示詞並串流每個事件。
一段簡短的腳本請 OpenCode 修復失敗的測試,然後重新執行。
串流事件,即時查看代理呼叫的每個工具。
只要幾行程式碼,就能把 OpenCode 接入機器人、儀表板和工作流程。
在你的處理程序內執行 OpenCode,使用你的設定和模型。
client.experimental.job.list() and its Effect equivalent for listing background shell, subagent, and image jobs, with session, descendant, kind, and status filters.#60698fetch implementation for OpenCode HTTP, model, web, and remote MCP traffic.#61582Enable "experimental": { "artifacts": true } in opencode.json to let agents publish, update, and serve HTML or static artifacts through the built-in local provider or plugin-provided storage.#60351
client.experimental.persistentPty.update to rename terminals or clear a user title, and exposed userTitle plus persistent-pty.updated events.#60329experimental.media_blob is enabledAdded lazy loading for stored image references when experimental.media_blob is enabled. Images are downloaded only for previews, while undo, revert, fork, and prompt recall restore referenced attachments safely.#60116
LLMResponse output on AIError.partial when generation, object generation, or a tool loop fails.#60477tool(...), with optional output schemas and executable or declaration-only tools.#60407debug, models, plugins, provider, and user options to the Responses route.#60044execute handler can throw available to the AI client.#60431filename alongside file_url on OpenAI Responses requests.#60382