Merge pull request #1456 from Tibsfox/fix/worktree-disable-config-1451

feat(config): add workflow.use_worktrees toggle to disable worktree isolation
This commit is contained in:
Tom Boucher
2026-04-01 17:24:57 -04:00
committed by GitHub
8 changed files with 179 additions and 3 deletions

View File

@@ -55,6 +55,12 @@ gaps = [
</step>
<step name="report_plan">
**Read worktree config:**
```bash
USE_WORKTREES=$(node "$HOME/.claude/get-shit-done/bin/gsd-tools.cjs" config-get workflow.use_worktrees 2>/dev/null || echo "true")
```
**Report diagnosis plan to user:**
```
@@ -92,7 +98,7 @@ For each gap, fill the debug-subagent-prompt template and spawn:
Task(
prompt=filled_debug_subagent_prompt + "\n\n<files_to_read>\n- {phase_dir}/{phase_num}-UAT.md\n- .planning/STATE.md\n</files_to_read>\n${AGENT_SKILLS_DEBUGGER}",
subagent_type="gsd-debugger",
isolation="worktree",
${USE_WORKTREES !== "false" ? 'isolation="worktree",' : ''}
description="Debug: {truth_short}"
)
```

View File

@@ -68,6 +68,14 @@ AGENT_SKILLS=$(node "$HOME/.claude/get-shit-done/bin/gsd-tools.cjs" agent-skills
Parse JSON for: `executor_model`, `verifier_model`, `commit_docs`, `parallelization`, `branching_strategy`, `branch_name`, `phase_found`, `phase_dir`, `phase_number`, `phase_name`, `phase_slug`, `plans`, `incomplete_plans`, `plan_count`, `incomplete_count`, `state_exists`, `roadmap_exists`, `phase_req_ids`.
Read worktree config:
```bash
USE_WORKTREES=$(node "$HOME/.claude/get-shit-done/bin/gsd-tools.cjs" config-get workflow.use_worktrees 2>/dev/null || echo "true")
```
When `USE_WORKTREES` is `false`, all executor agents run without `isolation="worktree"` — they execute sequentially on the main working tree instead of in parallel worktrees.
**If `phase_found` is false:** Error — phase directory not found.
**If `plan_count` is 0:** Error — no plans found in phase.
**If `state_exists` is false but `.planning/` exists:** Offer reconstruct or continue.
@@ -223,6 +231,8 @@ Execute each selected wave in sequence. Within a wave: parallel if `PARALLELIZAT
For 200k models, this keeps orchestrator context lean (~10-15%).
For 1M+ models (Opus 4.6, Sonnet 4.6), richer context can be passed directly.
**Worktree mode** (`USE_WORKTREES` is not `false`):
```
Task(
subagent_type="gsd-executor",
@@ -279,6 +289,19 @@ Execute each selected wave in sequence. Within a wave: parallel if `PARALLELIZAT
)
```
**Sequential mode** (`USE_WORKTREES` is `false`):
Omit `isolation="worktree"` from the Task call. Replace the `<parallel_execution>` block with:
```
<sequential_execution>
You are running as a SEQUENTIAL executor agent on the main working tree.
Use normal git commits (with hooks). Do NOT use --no-verify.
</sequential_execution>
```
When worktrees are disabled, execute plans **one at a time within each wave** (sequential) regardless of the `PARALLELIZATION` setting — multiple agents writing to the same working tree concurrently would cause conflicts.
3. **Wait for all agents in wave to complete.**
**Completion signal fallback (Copilot and runtimes where Task() may not return):**

View File

@@ -72,7 +72,7 @@ grep -n "type=\"checkpoint" .planning/phases/XX-name/{phase}-{plan}-PLAN.md
| Verify-only | B (segmented) | Segments between checkpoints. After none/human-verify → SUBAGENT. After decision/human-action → MAIN |
| Decision | C (main) | Execute entirely in main context |
**Pattern A:** init_agent_tracking → spawn Task(subagent_type="gsd-executor", model=executor_model, isolation="worktree") with prompt: execute plan at [path], autonomous, all tasks + SUMMARY + commit, follow deviation/auth rules, report: plan name, tasks, SUMMARY path, commit hash → track agent_id → wait → update tracking → report.
**Pattern A:** init_agent_tracking → spawn Task(subagent_type="gsd-executor", model=executor_model) with prompt: execute plan at [path], autonomous, all tasks + SUMMARY + commit, follow deviation/auth rules, report: plan name, tasks, SUMMARY path, commit hash → track agent_id → wait → update tracking → report. **Include `isolation="worktree"` only if `workflow.use_worktrees` is not `false`** (read via `config-get workflow.use_worktrees`).
**Pattern B:** Execute segment-by-segment. Autonomous segments: spawn subagent for assigned tasks only (no SUMMARY/commit). Checkpoints: main context. After all segments: aggregate, create SUMMARY, commit. See segment_execution.

View File

@@ -138,6 +138,10 @@ AGENT_SKILLS_VERIFIER=$(node "$HOME/.claude/get-shit-done/bin/gsd-tools.cjs" age
Parse JSON for: `planner_model`, `executor_model`, `checker_model`, `verifier_model`, `commit_docs`, `branch_name`, `quick_id`, `slug`, `date`, `timestamp`, `quick_dir`, `task_dir`, `roadmap_exists`, `planning_exists`.
```bash
USE_WORKTREES=$(node "$HOME/.claude/get-shit-done/bin/gsd-tools.cjs" config-get workflow.use_worktrees 2>/dev/null || echo "true")
```
**If `roadmap_exists` is false:** Error — Quick mode requires an active project with ROADMAP.md. Run `/gsd:new-project` first.
Quick tasks can run mid-phase - validation only checks ROADMAP.md exists, not phase status.
@@ -571,7 +575,7 @@ ${AGENT_SKILLS_EXECUTOR}
",
subagent_type="gsd-executor",
model="{executor_model}",
isolation="worktree",
${USE_WORKTREES !== "false" ? 'isolation="worktree",' : ''}
description="Execute: ${DESCRIPTION}"
)
```