Draft
Conversation
Co-authored-by: localai-bot <localai-bot@users.noreply.github.com>
Changed base image from Debian to Ubuntu and updated GitHub CLI installation method.
Removed 'software-properties-common' from the Dockerfile.
Removed specific Docker image entries and added placeholders for components.
A no-op tool that forces the model to think about a message. Takes a message string input and echoes it back, useful for debugging or forcing explicit reasoning steps in the model.
* feat: add think MCP server A no-op tool that forces the model to think about a message. Takes a message string input and echoes it back, useful for debugging or forcing explicit reasoning steps in the model. * feat(localrecall): gate all log messages under DEBUG flag - Add debugMode boolean that reads from DEBUG environment variable - Create debugLog() helper function that only prints when DEBUG=1 - Replace all log.Printf/log.Println calls with debugLog() - By default, no logs are emitted to preserve JSON-RPC stdio protocol Fixes: The LocalRecall MCP was corrupting JSON-RPC communication by emitting logs to stdout, causing the container to fail. Logs are now only shown when DEBUG=1 is set.
* feat: add codemogger MCP server - Add Dockerfile for codemogger (Node.js based MCP server) - Add codemogger to GitHub Actions CI pipeline * fix: remove redundant npm install -g npx (npx is included in node:20-slim) * docs: add codemogger to README
- Add getTimeout() function to read SHELL_TIMEOUT env var (default: 30s) - Update ExecuteCommand to use getTimeout() instead of hardcoded value - Update tool description to document the new env variable
- Implements sub_agent_chat tool for synchronous and asynchronous chat completions - Adds sub_agent_list tool to list active background tasks - Adds sub_agent_get_result tool to retrieve task results - Supports TTL-based cleanup for background tasks - Configurable via environment variables: - OPENAI_BASE_URL: Base URL for OpenAI API - OPENAI_MODEL: Model to use (default: gpt-4o-mini) - OPENAI_API_KEY: API key for authentication - SUB_AGENT_TTL: TTL in hours for task results (default: 4) Signed-off-by: localai-bot <localai-bot@users.noreply.github.com>
|
close this PR, you have to open it against github.com/mudler/MCPs |
Update root go.mod to reference sub-agent module via replace directive. This follows review feedback - we don't need separate go.mod/go.sum in the sub-agent directory as they already exist at the repository root. Signed-off-by: localai-bot <localai-bot@users.noreply.github.com>
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.
This PR removes the committed binary
sub-agent/sub-agentfrom the sub-agent MCP server PR.The binary was accidentally committed and should have been in .gitignore or built separately.
This PR cherry-picks all the legitimate code changes from PR mudler#16 (mudler#16) but excludes the binary file.
Files included:
Closes mudler#16