Add docker container release workflow + enhancements#17
Open
MRDGH2821 wants to merge 6 commits into
Open
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>
|
While running this branch with OpenClaw, we hit a couple of issues and put together a small follow-up that might be useful:
Branch: No pressure to merge — happy to adjust or fold in however works best for #17. |
cfoucher
added a commit
to cfoucher/composer-api
that referenced
this pull request
Jun 12, 2026
Pass vision inputs via a separate images[] array instead of embedding large base64 blobs in the bridge JSON body, drain NDJSON stream events reliably, and raise bridge timeout/JSON limits for vision workloads. Stacked on containerised-api (standardagents#17): docker-compose timeout wiring, optional backend env passthrough in api-server.ts, and tests for the new bridge vision extraction path. Co-authored-by: Cursor <cursoragent@cursor.com>
Pass vision inputs through a separate images[] array instead of embedding large base64 blobs in the bridge JSON body, and drain NDJSON stream events reliably. Raise bridge JSON size limit for image payloads. Stacked on containerised-api (standardagents#17): docker-compose env wiring for bridge run timeout and max JSON bytes, optional backend env passthrough in api-server.ts, and tests for the bridge vision extraction path. Co-authored-by: Cursor <cursoragent@cursor.com>
fix: SDK bridge vision + docker bridge timeouts (stacked on standardagents#17)
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.
Fixed tool calls done by Gemini, Groq & Kimi models
And this now returns complete model list.
Renamed
defaulttoautoto mirror how it is in Cursor IDE