Conversation
Co-authored-by: dadudekc <dadudekc@gmail.com>
|
Cursor Agent can help with this pull request. Just |
Co-authored-by: dadudekc <dadudekc@gmail.com>
Co-authored-by: dadudekc <dadudekc@gmail.com>
Co-authored-by: dadudekc <dadudekc@gmail.com>
Add .env to gitignore and update security scanner whitelist. Add new knowledge base entries and adjust verification script. Remove thea_cookies.json. Co-authored-by: dadudekc <dadudekc@gmail.com>
Co-authored-by: dadudekc <dadudekc@gmail.com>
Co-authored-by: dadudekc <dadudekc@gmail.com>
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| class MockQueue: | ||
| def send(self, *args, **kwargs): return True | ||
| def get_queue(): return MockQueue() |
There was a problem hiding this comment.
Fix MockQueue fallback interface mismatch
When swarm_mcp is not importable (the exact situation this fallback is meant to cover), the stubbed MockQueue.send() returns a boolean and exposes no territory/count_unheard attributes, but later code assumes a Howl object (howl.id) and accesses queue.territory/queue.count_unheard. That causes AttributeError and forces send_agent_message, broadcast_message, and get_agent_status to fail in verification environments without full setup, defeating the fallback’s purpose.
Useful? React with 👍 / 👎.
…st_toolbelt.py Add tools.cli package entry point
…ent-error-in-cli.py Add legacy tools/cli.py entrypoint to route flag-based toolbelt invocations
Add
examples/showcase_swarm_tools.pyto demonstrate and test the functionality of theswarm_mcptools.The
tools_v2module was found to be incomplete and non-functional due to missing dependencies. This PR focuses on providing practical examples for the fully operationalswarm_mcptools, serving as both a usage guide and a functional test suite.Note
Introduces a runnable example to demo and smoke-test
swarm_mcpCLI usage.examples/showcase_swarm_tools.pyto sequentially runstatus,profile,patterns,tasks --path tools/,conflict --list,vote --agent, andinboxwith clear success/error outputtools/agent_workspaces/Agent-5/COMPREHENSIVE_TOOLS_ANALYSIS_2025-12-06.jsonas a zeroed placeholder analysis artifactWritten by Cursor Bugbot for commit a85572a. Configure here.