fix: SDK bridge vision + docker timeout/env (containerised-api updates)#20
Closed
cfoucher wants to merge 6 commits into
Closed
fix: SDK bridge vision + docker timeout/env (containerised-api updates)#20cfoucher wants to merge 6 commits into
cfoucher wants to merge 6 commits into
Conversation
Add Docker Compose deployment with a Node API server and SDK bridge, route non-Composer models to SDK tool prompts, and parse legacy Kimi tool markers in the bridge so Gemini, Kimi, and Grok execute tools. Co-authored-by: Cursor <cursoragent@cursor.com>
Treat ConnectRPC abort errors as benign after capturing client tool calls, and add develop.watch rules to sync api and bridge code during development. Co-authored-by: Cursor <cursoragent@cursor.com>
Fetch Cursor's model catalog for authenticated /v1/models requests, rename default to auto in the list, and sort merged results by id. Co-authored-by: Cursor <cursoragent@cursor.com>
OpenClaw and other clients send base64 image payloads that exceeded the bridge JSON limit and never reached Agent.send as native vision input. Strip embedded images from the bridge prompt, pass them in a separate images field, enable streamEvents draining, and mark prompts as already prepared to avoid double-wrapping. Co-authored-by: Cursor <cursoragent@cursor.com>
Self-hosted OpenClaw vision runs need longer bridge timeouts and the api2 backend endpoints for direct chat transport. Also raise the bridge JSON body limit default for large agent contexts with images. Co-authored-by: Cursor <cursoragent@cursor.com>
Author
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
imagesarray (not base64 embedded in the prompt), enable NDJSON stream draining, setpromptAlreadyPrepared, and raise the bridge JSON body limit default — fixes OpenClaw/WhatsApp vision (Request body too large, "I don't see a photo").CURSOR_BACKEND_BASE_URL/ chat endpoints for direct vision transport (issue Documentation: how to obtain CURSOR_BACKEND_BASE_URL, CURSOR_CHAT_ENDPOINT, and CURSOR_LOCAL_AGENT_ENDPOINT values #13), and setCURSOR_SDK_BRIDGE_MAX_JSON_BYTES=16MBin compose.Commits
654b791fix: deliver SDK bridge vision via images array and streaming NDJSON28f3651fix: raise docker bridge timeouts and wire Cursor backend env varsNote
This extends the self-hosted/docker work in #17. If #17 merges first, these two commits can be cherry-picked onto that branch on
MRDGH2821/composer-api.Test plan
npm test(232 tests pass in docker)Made with Cursor