Conversation
| if [[ ! "$WORKTREE_MODE" =~ ^(ask|bind|skip|error|create(:.+)?)$ ]]; then | ||
| echo "Error: Invalid --worktree value: $WORKTREE_MODE" >&2 | ||
| echo "Valid values are: ask, bind, skip, error" >&2 | ||
| echo "Valid values are: ask, bind, skip, error, create:<branch-name>" >&2 |
There was a problem hiding this comment.
what/how to just start/resume an existing? I wonder if overall it should be a separate option whenever this one in particular about binding -- so it could be (potentially) be used with "create" as "create but do not bind original" if I want to work in better isolation. So -- orthogonal features, and thus potentially orthogonal options desired IMHO.
Also as I have mentioned, might be worth right away to think about sub-agents and worktrees WITHIN claude session. If isolated, I guess we want to keep worktrees under .git/ of the main repo (where worktrees point to), but then since that one already has .git/worktrees/ (containing just .git/ level per each branch/worktree) -- we would need smth like .git/yolotrees or .git/yolo-worktrees?
Allows `yolo --worktree=create:fix-issue-99` to create a git worktree as a sibling directory, cd into it, and launch with bind mode — keeping the main working tree untouched while an agent works on an issue. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Redesign worktree creation per PR #57 review feedback: - Separate --create-worktree=BRANCH from --worktree=MODE (orthogonal) - Support base:branch syntax for specifying base ref - Resume existing worktrees if directory exists - Add WORKTREE_DIR config (default .git/my-worktrees, relative paths only) - Add CLAUDE.md formatting rule for human-readable tables Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
Marked as a draft because SPEC is not aligned with actual behavior. Based on @yarikoptic feedback I updated the spec for this PR to a quick and dirty draft of what it SHOULD be, NOT what it currently does. This was excellent test case for a POC project I was playing with, see below.EDIT: This is the intial test. Later wired into real CI, see bot comment below POC: Automated spec audit using local LLMI built a prototype that checks whether a PR's SPEC.md update matches its code changes, using qwen3:14b on Typhon via Ollama. It:
Verdict: FAIL Flag mismatch: The spec introduces a new flag ( Missing configuration: The spec adds a new config variable ( Contradictory behavior: The spec's POC lives in https://github.com/asmacdo/typhon-ai-experiments (private) under |
pr-scout: spec-audit❌ Spec update does not match code changesCode change summaryHere's a summary of the new or changed functionality:
VerdictFAIL Here's a breakdown of discrepancies and omissions:
|
Summary
--worktree=create:<branch-name>mode that creates a git worktree as a sibling directory, checks out a new branch from HEAD, and launches yolo with bind modeyolo --worktree=create:fix-issue-99🤖 Generated with Claude Code