Conversation
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
v0.3.0 — Multi-agent, MCP control, CLI improvements
New features
agent tool — parent LLM can spawn focused sub-agents for isolated sub-tasks (code review, research, test runs).
Sub-agents run in AUTO mode with their own history, capped at 10 iterations, no recursion
/mcp add, /mcp stop, /mcp start commands in interactive chat for runtime MCP server control
--mcp, --no-mcp flags on
devorch ask,devorch run,devorch editfor per-command MCP filtering--skill, --mode flags on non-interactive commands matching interactive chat parity
Improvements
CLI modularized — commands moved to
cli/commands/(ask.py,run.py,edit.py,_shared.py)Constants extracted to
cli/constants.py(version, banners, slash commands, completers)Permission prompt for agent tool shows clean task preview instead of raw JSON dump
Planner wired to ModeManager properly — plan approval state now tracked correctly
AgentTool available in both interactive chat and non-interactive commands
Internal
build_agent()helper centralizes agent construction with post-construction tool injectionSimplePlanner is now tool-aware, keeps system prompt in sync after MCP changes