feat: support --worktrees with MCP tasklist providers#46
Merged
Conversation
When a remote MCP provider is configured, ParallelOrchestrator now: - Fetches tasks from the MCP backend instead of reading local file - Fetches full task body via get_task() for each worker subprocess - Skips local tasklist mark-complete in MergePipeline (skip_tasklist_mark=True) - Marks the remote task done via update_task_status() after successful merge File-based behavior is completely unchanged. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This was referenced Mar 8, 2026
Merged
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
millstone --worktrees --concurrency Nwas previously incompatible with remote tasklist providers (GitHub Issues, Linear, Jira) —extract_all_task_ids()reads from a local file that doesn't exist for remote backends, resulting in zero tasks dispatched silently.This PR adds MCP-aware task fetching to
ParallelOrchestrator:_is_mcp_provider()/_fetch_tasks_from_provider()— lists tasks from the MCP backend in the scheduler-compatible format_fetch_task_body()— fetches full issue body viaget_task()so workers receive meaningful task descriptions_analyze_tasks_mcp()— builds the enriched task list without dependency graph (remote tasks have no local metadata)_mark_mcp_task_done()— marks task complete in the remote backend after successful mergeMergePipeline.skip_tasklist_mark— skips local tasklist checkbox update when using MCP backendsFile-based behavior is completely unchanged.
Test plan
test_parallel.pycovering MCP task fetch, body fetch, done-marking, and therun()dispatch pathCloses #45
🤖 Generated with Claude Code