docs: propose agent provider abstraction#322
Open
qian-le wants to merge 2 commits into
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
This PR adds a design proposal for an Agent Provider abstraction layer.
The goal is to explore how Edict could support multiple execution backends in the future while keeping the existing OpenClaw-based workflow unchanged.
Motivation
Edict already provides a strong multi-agent workflow console. Introducing a provider abstraction may make it easier to integrate with other local workflow tools, shell-based executors, Codex, Claude Code, CI jobs, or downstream personal workflow systems.
Scope
This PR only adds documentation.
It does not:
Proposed Direction
The document suggests a possible AgentProvider interface and a phased migration path, starting with a minimal ShellProvider.
Notes
This is intended as a discussion-friendly proposal. I’m happy to adjust the direction based on maintainer feedback.
中文说明
这个 PR 新增了一份关于 Agent Provider 抽象层的设计提案。
目标是在不改变现有 OpenClaw 工作流的前提下,讨论 Edict 未来是否可以支持更多执行后端,例如本地 shell 脚本、Codex、Claude Code、CI 任务,或下游个人工作流系统。
本 PR 仅包含文档,不会:
文档中提出了一个可能的
AgentProvider接口和分阶段迁移路径,并建议从最小的ShellProvider原型开始探索。另外,文档也补充了
ClaudeCodeProvider的受控代码修改思路:Claude Code 可以在隔离 workspace 或贡献分支中生成 patch、测试输出和变更摘要,但 commit、push 或 merge 仍应经过 Edict 的审核门禁。这份提案主要用于开启讨论,我愿意根据维护者反馈调整方向。