Open
Conversation
Extend the API proxy to route requests to three CLI backends (Claude, Cursor agent, Gemini) based on model name prefix, so openclaw bot can use any of them via the same OpenAI-compatible endpoint. New files: - src/subprocess/cursor.ts – CursorSubprocess (agent -p, stdin prompt) - src/subprocess/gemini.ts – GeminiSubprocess (gemini -p) - src/subprocess/factory.ts – resolveBackend() + createSubprocess() - src/types/common.ts – shared ContentDeltaEvent / ResultEvent Modified: - ClaudeSubprocess now emits standardised events - routes.ts is backend-agnostic (uses factory + common events) - /v1/models lists all three backends - standalone.ts verifies & reports all available CLIs on startup - Plugin entry point registers all backends for Clawdbot Co-authored-by: Cursor <cursoragent@cursor.com>
- Handle array-format message content (e.g. [{type:"text", text:"..."}])
that OpenClaw and other clients send, instead of only plain strings
- Add gemini/ prefix routing in factory (alongside gemini-cli/)
- Update OpenAIChatMessage type to accept string | content-part array
Co-authored-by: Cursor <cursoragent@cursor.com>
Rewrite documentation to cover all three backends, model routing, OpenClaw configuration, and updated architecture diagram. Co-authored-by: Cursor <cursoragent@cursor.com>
OpenClaw custom providers can't use "/" in model IDs, so add dash-format aliases (e.g. cursor-opus-4.6, gemini-cli-gemini-2.5-pro) alongside the existing slash-format. Both the /v1/models endpoint and the backend resolver now handle either convention. Co-authored-by: Cursor <cursoragent@cursor.com>
Document both the simpler openai-provider setup (slash-format IDs) and the custom cli-proxy provider (dash-format IDs). Add verification steps, per-agent config, rate-limit fallback tips, and troubleshooting for the [object Object] content issue. Co-authored-by: Cursor <cursoragent@cursor.com>
Without this flag, Cursor agent in headless (-p) mode cannot execute shell commands (e.g. python) because it waits for user confirmation that never comes. The --yolo flag (alias for --force) auto-approves all tool executions, matching Gemini CLI's -y behavior. Co-authored-by: Cursor <cursoragent@cursor.com>
3 tasks
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
1 participant
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.
No description provided.