wt-switch-create

Arguments: `$ARGUMENTS`. Grammar: `[<branch>] [<repo>] [-- <task>]`. - **branch** — optional; the branch name for the new worktree. When omitted, pick one (step 1 below). - **repo** — optional path or name; create the worktree in this repo instead of the session's current one. - **task** — optional; what to do inside the new worktree. No task means enter the worktree and wait. Tokens before the `--` are the branch and/or repo. A path-shaped token (starting with `/`, `~`, `./`, or `../`) is the repo. A bare name can be either, so make an informed guess. It is the branch when the current repo already has a branch by that name, as it is for `wt switch` itself. Otherwise it is the repo when a git repository by that name exists where the user keeps repos (beside the current repo, or in a workspace directory like `~/workspace`), and the branch when none does (`docs` is a branch, not the current repo's `docs/` directory). A name read as the repo carries its absolute path forward: that path, not the bare token, is the `<repo>` in step 3. Two tokens that both read as branches don't fit the grammar — ask. Without a `--`, judge where the task starts: leading tokens that read as a branch name (`fix-auth`) or a repo are consumed as such, and the rest is the task; otherwise the whole input is the task (`fix the parser bug` has no branch-shaped lead — all task). ``` /wt-switch-create my-feature -- fix the parser bug /wt-switch-create -- fix the parser bug /wt-switch-create my-feature ~/workspace/other-repo -- fix the parser bug /wt-switch-create my-feature ``` ## What to do Creating the worktree comes first on every invocation, before any other work. The invocation is itself the explicit request to create it; a research or read-only task gets one all the same. <!-- Maintainers: rationale.md (same directory) covers the harness rules and design choices behind this — read it before re-adding guards or routes. --> 1. **Pick a new branch name** if none was given: short, from the task and consistent with existing worktree names, or, mid-session, from the work being moved; with nothing to derive from, ask. 2. **With no repo argument, create and enter in one call:** `EnterWorktree({name: "<branch>"})`. Worktrunk's `WorktreeCreate` hook runs `wt switch --create` for a new branch or `wt switch` for an existing one, creating its checkout if needed. The result is an ordinary `wt` worktree, and the user sees no confirmation prompt. On success, do the task (or, with no task text, confirm it's ready and wait). Mid-session, carry uncommitted work across: `git stash push -u` before the `EnterWorktree` call, then `git stash pop` once the session is in the new worktree, which is after step 3 if this call fails. Entering re-roots the session into the new worktree, and the stash is shared across worktrees. If step 3 hands back without the session in the new worktree, restore the work where it came from first (`git -C <that worktree> stash pop`). 3. **Otherwise create it with `wt` and enter by path.** Two cases reach here: a repo argument, which step 2 can't target, and a failed step 2, whose error says `Already in a worktree session`. Create with a `Bash` call (omit `-C <repo>` for this repo): ``` wt -C <repo> switch --create <branch> --no-cd --format=json ``` Stdout is JSON whose `path` field is the worktree's absolute path (status lines go to stderr). On `Branch <branch> already exists`: if the user named the branch, rerun without `--create` (it enters the branch, creating its worktree if missing); if step 1 picked the name, pick another and rerun. Any other failure (not a git repo, invalid name): report it and stop. Next, call `ExitWorktree({action: "keep"})`. This invocation is the user asking to move the session, which includes leaving the worktree it is in, so make the call even when you're unsure the session is in one. A session in a worktree can enter only one under its repository's `.claude/worktrees/`; leaving lifts that limit, keeps the old worktree and its branch on disk, and returns the session to the directory it was in before it entered. Where there is nothing to leave (no worktree session, or an agent pinned to its own worktree), the call returns an error and changes nothing; carry on. If the session did leave a worktree and the entry below doesn't happen, say so when you hand back: name the worktree it left, still on disk, and where the session is now. With a repo argument, `cd <repo>` next, in its own `Bash` call: `EnterWorktree` re-roots only within the repository the cwd is in, and worktrunk's `PermissionRequest` hook answers the confirmation that call asks for only for a `wt` worktree of that same repository. If that `cd` reports `Shell cwd was reset`, the repo is unreachable: skip the entry and hand back as in **Unreachable** below. With no repo argument, don't `cd`: leaving put the session back in this repository, and a `cd` into the worktree it left can reset. Then call `EnterWorktree({path: "<path from the JSON>"})`. With a repo argument, once the session works in the new worktree (entered, or reached by `cd` in the recovery below), read whichever of its root `CLAUDE.md` and `AGENTS.md` exist before the task. Claude Code keeps the launch repo's root instructions in context and loads only the new repo's nested ones, so the new repo's root files supersede the launch repo's for the rest of the session. - **Accepted** → the session is re-rooted in the worktree. Do the task (or, with no task text, confirm it's ready and wait). - **Tool error** — the tool ran and returned an error (`Cannot enter worktree: …`) → graceful; nothing moved, and one recovery covers them all. One cause is an agent pinned to its own worktree, which can enter only under its repo's `.claude/worktrees/`, excluding even a same-repo `wt` sibling. The recovery test is whether you can `cd` into the worktree, which works when it's inside an allowed directory. So `cd <path>` and read the result: - no `Shell cwd was reset` notice → it stuck; the worktree is reachable. Work there, but a bare `cd` is not a tracked re-root, so the cwd can revert to the session's launch worktree across turns (and in spawned subagents); pin commands with `git -C <path>` / `wt -C <path>` rather than trusting the `cd` to persist. - `Shell cwd was reset` → **Unreachable.** Stop and ask the user to make the directory whose `cd` reset reachable: add a parent that holds both the repo and its worktrees, like `~/workspace`, to `permissions.additionalDirectories` (durable, every session), or run `/add-dir` on it (this session). Then continue from that `cd`. Don't grind through absolute paths with `cd` resetting on every command. - **Denied** — the call itself was refused, with no tool error → however the denial is worded, it is the user's answer to the confirmation Claude Code shows for entering a worktree outside `.claude/worktrees/`, unless there was no user to ask (the denial says the session couldn't prompt), which decides nothing — take the recovery above. On the user's answer: the worktree `wt` just created still exists; only the entry didn't happen. `cd` back out of the repo you moved into, if any, then report the worktree's path and ask how to proceed, since reaching it through `cd` would override that answer. ## Cleanup The worktree is a normal worktrunk worktree: it shows up in `wt list` and is merged or removed with `wt merge` / `wt remove <branch>` like any other. Don't remove it unprompted. A worktree from step 2 that the session never touched — no changed files, no commits — is cleaned up when the session ends, branch included; anything written into it keeps it. A worktree from step 3 always stays, as does a worktree the session left in step 3. If the user asks to leave mid-session, `ExitWorktree({action: "keep"})` returns the session to its original directory; `ExitWorktree` cannot remove a worktree entered by `path`, so removing one of those is always `wt remove <branch>`. ## Scope The command's mandate is ONE worktree (in the named repo, if one was given) and the requested task inside it. Commits, pushes, and merges still each require explicit user permission.