Files
msd-core/get-shit-done/workflows/new-workspace.md
Rezolv d3a79917fa feat: Phase 2 caller migration — gsd-sdk query in workflows, agents, commands (#2179)
* feat: Phase 2 caller migration — gsd-sdk query in workflows (#2122)

Cherry-picked orchestration rewrites from feat/sdk-foundation (#2008, 4018fee) onto current main, resolving conflicts to keep upstream worktree guards and post-merge test gate. SDK stub registry omitted (out of Phase 2 scope per #2122).

Refs: #2122 #2008
Made-with: Cursor

* docs: add gsd-sdk query migration blurb

Made-with: Cursor

* docs(workflows): extend Phase 2 gsd-sdk query caller migration

- Swap node gsd-tools.cjs for gsd-sdk query in review, plan-phase, execute-plan,
  ship, extract_learnings, ai-integration-phase, eval-review, next, thread
- Document graphify CJS-only in gsd-planner; dual-path in CLI-TOOLS and ARCHITECTURE
- Update tests: workstreams gsd-sdk path, thread frontmatter.get, workspace init.*,
  CRLF-safe autonomous frontmatter parse
- CHANGELOG: Phase 2 caller migration scope

Made-with: Cursor

* docs(phase2): USER-GUIDE + remaining gsd-sdk query call sites

- USER-GUIDE: dual-path CLI section; state validate/sync use full CJS path
- Commands: debug (config-get+tdd), quick (security note), intel Task prompt
- Agent: gsd-debug-session-manager resolve-model via jq
- Workflows: milestone-summary, forensics, next, complete-milestone/verify-work
  (audit-open CJS notes), discuss-phase, progress, verify-phase, add/insert/remove
  phase, transition, manager, quick workflow; remove-phase commit without --files
- Test: quick-session-management accepts frontmatter.get
- CHANGELOG: Phase 2 follow-up bullet

Made-with: Cursor

* docs(phase2): align gsd-sdk query examples in commands and agents

- init.* query names; frontmatter.get uses positional field name
- state.* handlers use positional args; commit uses positional paths
- CJS-only notes for from-gsd2 and graphify; learnings.query wording
- CHANGELOG: Phase 2 orchestration doc pass

Made-with: Cursor

* docs(phase2): normalize gsd-sdk query commit to positional file paths

- Strip --files from commit examples in workflows, references, commands
- Keep commit-to-subrepo ... --files (separate handler)
- git-planning-commit.md: document positional args
- Tests: new-project commit line, state.record-session, gates CRLF, roadmap.analyze
- CHANGELOG [Unreleased]

Made-with: Cursor

* feat(sdk): gsd-sdk query parity with gsd-tools and PR 2179 registry fixes

- Route query via longest-prefix match and dotted single-token expansion; fall back
  to runGsdToolsQuery (same argv as node gsd-tools.cjs) for full CLI coverage.
- Parse gsd-sdk query permissively so gsd-tools flags (--json, --verify, etc.) are
  not rejected by strict parseArgs.
- resolveGsdToolsPath: honor GSD_TOOLS_PATH; prefer bundled get-shit-done copy
  over project .claude installs; export runGsdToolsQuery from the SDK.
- Fix gsd-tools audit-open (core.output; pass object for --json JSON).
- Register summary-extract as alias of summary.extract; fix audit-fix workflow to
  call audit-uat instead of invalid init.audit-uat (PR review).

Updates QUERY-HANDLERS.md and CHANGELOG [Unreleased].

Made-with: Cursor

* fix(sdk): Phase 2 scope — Trek-e review (#2179, #2122)

- Remove gsd-sdk query passthrough to gsd-tools.cjs; drop GSD_TOOLS_PATH
- Consolidate argv routing in resolveQueryArgv(); update USAGE and QUERY-HANDLERS
- Surface @file: read failures in GSDTools.parseOutput
- execute-plan: defer Task Commit Protocol to gsd-executor
- stale-colon-refs: skip .planning/ and root CLAUDE.md (gitignored overlays)
- CHANGELOG [Unreleased]: maintainer review and routing notes

Made-with: Cursor
2026-04-15 22:46:31 -04:00

6.6 KiB

Create an isolated workspace directory with git repo copies (worktrees or clones) and an independent `.planning/` directory. Supports multi-repo orchestration and single-repo feature branch isolation.

<required_reading> Read all files referenced by the invoking prompt's execution_context before starting. </required_reading>

1. Setup

MANDATORY FIRST STEP — Execute init command:

INIT=$(gsd-sdk query init.new-workspace)
if [[ "$INIT" == @file:* ]]; then INIT=$(cat "${INIT#@file:}"); fi

Parse JSON for: default_workspace_base, child_repos, child_repo_count, worktree_available, is_git_repo, cwd_repo_name, project_root.

2. Parse Arguments

Extract from $ARGUMENTS:

  • --name → WORKSPACE_NAME (required)
  • --repos → REPO_LIST (comma-separated paths or names)
  • --path → TARGET_PATH (defaults to $default_workspace_base/$WORKSPACE_NAME)
  • --strategy → STRATEGY (defaults to worktree)
  • --branch → BRANCH_NAME (defaults to workspace/$WORKSPACE_NAME)
  • --auto → skip interactive questions

If --name is missing and not --auto:

Text mode (workflow.text_mode: true in config or --text flag): Set TEXT_MODE=true if --text is present in $ARGUMENTS OR text_mode from init JSON is true. When TEXT_MODE is active, replace every AskUserQuestion call with a plain-text numbered list and ask the user to type their choice number. This is required for non-Claude runtimes (OpenAI Codex, Gemini CLI, etc.) where AskUserQuestion is not available. Use AskUserQuestion:

  • header: "Workspace Name"
  • question: "What should this workspace be called?"
  • requireAnswer: true

3. Select Repos

If --repos is provided: Parse comma-separated values. For each value:

  • If it's an absolute path, use it directly
  • If it's a relative path or name, resolve against $project_root
  • Special case: . means current repo (use $project_root, name it $cwd_repo_name)

If --repos is NOT provided and not --auto:

If child_repo_count > 0:

Present child repos for selection:

Use AskUserQuestion:

  • header: "Select Repos"
  • question: "Which repos should be included in the workspace?"
  • options: List each child repo from child_repos array by name
  • multiSelect: true

If child_repo_count is 0 and is_git_repo is true:

Use AskUserQuestion:

  • header: "Current Repo"
  • question: "No child repos found. Create a workspace with the current repo?"
  • options:
    • "Yes — create workspace with current repo" → use current repo
    • "Cancel" → exit

If child_repo_count is 0 and is_git_repo is false:

Error:

No git repos found in the current directory and this is not a git repo.

Run this command from a directory containing git repos, or specify repos explicitly:
  /gsd-new-workspace --name my-workspace --repos /path/to/repo1,/path/to/repo2

Exit.

If --auto and --repos is NOT provided:

Error:

Error: --auto requires --repos to specify which repos to include.

Usage:
  /gsd-new-workspace --name my-workspace --repos repo1,repo2 --auto

Exit.

4. Select Strategy

If --strategy is provided: Use it (validate: must be worktree or clone).

If --strategy is NOT provided and not --auto:

Use AskUserQuestion:

  • header: "Strategy"
  • question: "How should repos be copied into the workspace?"
  • options:
    • "Worktree (recommended) — lightweight, shares .git objects with source repo" → worktree
    • "Clone — fully independent copy, no connection to source repo" → clone

If --auto: Default to worktree.

5. Validate

Before creating anything, validate:

  1. Target path — must not exist or must be empty:
if [ -d "$TARGET_PATH" ] && [ "$(ls -A "$TARGET_PATH" 2>/dev/null)" ]; then
  echo "Error: Target path already exists and is not empty: $TARGET_PATH"
  echo "Choose a different --name or --path."
  exit 1
fi
  1. Source repos exist and are git repos — for each repo path:
if [ ! -d "$REPO_PATH/.git" ]; then
  echo "Error: Not a git repo: $REPO_PATH"
  exit 1
fi
  1. Worktree availability — if strategy is worktree and worktree_available is false:
Error: git is not available. Install git or use --strategy clone.

Report all validation errors at once, not one at a time.

6. Create Workspace

mkdir -p "$TARGET_PATH"

For each repo:

Worktree strategy:

cd "$SOURCE_REPO_PATH"
git worktree add "$TARGET_PATH/$REPO_NAME" -b "$BRANCH_NAME" 2>&1

If git worktree add fails because the branch already exists, try with a timestamped branch:

TIMESTAMP=$(date +%Y%m%d%H%M%S)
git worktree add "$TARGET_PATH/$REPO_NAME" -b "${BRANCH_NAME}-${TIMESTAMP}" 2>&1

If that also fails, report the error and continue with remaining repos.

Clone strategy:

git clone "$SOURCE_REPO_PATH" "$TARGET_PATH/$REPO_NAME" 2>&1
cd "$TARGET_PATH/$REPO_NAME"
git checkout -b "$BRANCH_NAME" 2>&1

Track results: which repos succeeded, which failed, what branch was used.

7. Write WORKSPACE.md

Write the workspace manifest at $TARGET_PATH/WORKSPACE.md:

# Workspace: $WORKSPACE_NAME

Created: $DATE
Strategy: $STRATEGY

## Member Repos

| Repo | Source | Branch | Strategy |
|------|--------|--------|----------|
| $REPO_NAME | $SOURCE_PATH | $BRANCH | $STRATEGY |
...for each repo...

## Notes

[Add context about what this workspace is for]

8. Initialize .planning/

mkdir -p "$TARGET_PATH/.planning"

9. Report and Next Steps

If all repos succeeded:

Workspace created: $TARGET_PATH

  Repos: $REPO_COUNT
  Strategy: $STRATEGY
  Branch: $BRANCH_NAME

Next steps:
  cd "$TARGET_PATH"
  /gsd-new-project    # Initialize GSD in the workspace

If some repos failed:

Workspace created with $SUCCESS_COUNT of $TOTAL_COUNT repos: $TARGET_PATH

  Succeeded: repo1, repo2
  Failed: repo3 (branch already exists), repo4 (not a git repo)

Next steps:
  cd "$TARGET_PATH"
  /gsd-new-project    # Initialize GSD in the workspace

Offer to initialize GSD (if not --auto):

Use AskUserQuestion:

  • header: "Initialize GSD"
  • question: "Would you like to initialize a GSD project in the new workspace?"
  • options:
    • "Yes — run /gsd-new-project" → tell user to cd "$TARGET_PATH" first, then run /gsd-new-project
    • "No — I'll set it up later" → done

<success_criteria>

  • Workspace directory created at target path
  • All specified repos copied (worktree or clone) into workspace
  • WORKSPACE.md manifest written with correct repo table
  • .planning/ directory initialized at workspace root
  • User informed of workspace path and next steps </success_criteria>