- core/agent_tool: recognize "cloud" model and append prompt positionally; honor per‑mode args
- core/codex(agent_run): include "cloud" in command resolution + PATH check
- core/slash_commands: default /plan,/solve models now include "cloud"; test asserts prompt includes it
- core/agent_defaults: add cloud case (no default flags); unit test ensures empty defaults
- docs: note default agent set includes "cloud"; add config example
Build passes via ./build-fast.sh. Full test suite currently fails on unrelated preexisting test drift (protocol/test-support imports, enum shapes).
- Add AgentConfig struct to define agent settings (name, command, args, read-only, enabled, env)
- Update Config and Session to include agent configurations
- Modify agent_tool.rs to use configured agents with their settings
- Update slash commands to dynamically use enabled agents from config
- Create comprehensive config.toml.example with agent examples
- Support both configured and unconfigured agents for backward compatibility
- Allow per-agent read-only override and environment variables
- Pass agent configuration through Session for proper access control
This allows users to:
- Define which AI agents are available
- Set custom commands and arguments for each agent
- Control read-only/write permissions per agent
- Enable/disable specific agents
- Configure environment variables for agents
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <[email protected]>
James Peter