Address 4 root causes of Windows + Claude Code reliability issues:
1. Workflow shell robustness: add || true guards to informational commands
(ls, grep, find, cat) that return non-zero on "no results", preventing
workflow step failures under strict execution models. Guard glob loops
with [ -e "$var" ] || continue to handle empty glob expansion.
2. Hook stdin handling: replace readFileSync('/dev/stdin') with async
process.stdin + timeout in agent templates (gsd-verifier.md). Existing
JS hooks already have timeout guards.
3. project_root detection: fix isInsideGitRepo() to check .git at the
candidate parent level (not just below it), enabling correct detection
when .git and .planning/ are siblings at the same directory level —
the common single-repo case from a subdirectory.
4. @file: handoff: add missing @file: handlers to autonomous.md and
manager.md workflows that call gsd-tools init but lacked the handler
for large output payloads.
Fixes#1343
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The map-codebase workflow was refactored to remove the explicit
"Runtimes with Task tool" line in favor of inline detection instructions.
Updated test to match the new workflow structure by checking the
"NOT available" condition line instead.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Worktree agents (gsd-executor, gsd-debugger) prompt for edit permissions
on every new directory they touch, even when the user has "accept edits"
enabled. This is caused by Claude Code's directory-scoped permission
model not propagating to worktree paths.
Setting permissionMode: acceptEdits in the agent frontmatter tells Claude
Code to auto-approve file edits for these agents, bypassing the per-
directory prompts. This is safe because these agents are already granted
Write/Edit in their tools list and are spawned in isolated worktrees.
- Add permissionMode: acceptEdits to gsd-executor.md frontmatter
- Add permissionMode: acceptEdits to gsd-debugger.md frontmatter
- Add regression tests verifying worktree agents have the field
- Add test ensuring all isolation="worktree" spawns are covered
Upstream: anthropics/claude-code#29110, anthropics/claude-code#28041
Fixes#1334
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Adds full Windsurf (by Codeium) runtime integration, following the same
pattern as the existing Cursor support. Windsurf uses .windsurf/ for
local config and ~/.windsurf/ for global config, with skills in
.windsurf/skills/ using the SKILL.md structure.
What:
- CLI flag --windsurf and interactive prompt option (8)
- Directory mapping (.windsurf local, ~/.windsurf global)
- Content converter functions (tool names, path replacements, brand refs)
- Skill copy function (copyCommandsAsWindsurfSkills)
- Agent conversion (convertClaudeAgentToWindsurfAgent)
- Install/uninstall branches
- Banner, help text, and issue template updates
- Windsurf conversion test suite (windsurf-conversion.test.cjs)
- Updated multi-runtime selection tests for 8 runtimes
Closes#1336
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The code/package detection in cmdInitNewProject only recognized 7 file
extensions and 5 package files, missing Android (Kotlin + Gradle), Flutter
(Dart + pubspec.yaml), C/C++, C#, Ruby, PHP, Scala, and others. This caused
new-project to treat brownfield projects in those ecosystems as greenfield,
skipping the codebase mapping step.
Added 18 code extensions and 11 package/build files to the detection lists.
Fixes#1325
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
OpenCode has a `task` tool that supports spawning subagents, but
map-codebase workflow incorrectly listed it under "Runtimes WITHOUT
Task tool". This caused the agent to skip parallel mapping and fall
back to sequential mode, wasting tokens when it self-corrected.
Move OpenCode to the "with Task tool" list and clarify that either
`Task` or `task` (case-insensitive) qualifies. Add regression test.
Fixes#1316
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
On Windows CI, os.tmpdir() returns 8.3 short paths (C:\Users\RUNNER~1)
while git returns long paths (C:\Users\runneradmin). fs.realpathSync()
doesn't resolve DOS 8.3 names on NTFS — fs.realpathSync.native() does.
Added normalizePath() helper using realpathSync.native with fallback,
applied to all temp dir creation and path comparisons in the linked
worktree test suite.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The test tried to fs.readFileSync on config.json which doesn't exist
in createTempProject() fixtures. Now gracefully creates the config
from scratch when the file is missing.
Co-Authored-By: GhadiSaab <GhadiSaab@users.noreply.github.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
`workflow.text_mode: true` (or `--text` flag) now applies to
plan-phase, not just discuss-phase. Fixes#1313.
Changes:
- `init plan-phase` now exposes `text_mode` from config in its JSON output
- plan-phase workflow parses `--text` flag and resolves TEXT_MODE from
init JSON or flag, whichever is set
- All four AskUserQuestion call sites (no-context gate, research prompt,
UI design contract gate, requirements coverage gap) now conditionally
present as plain-text numbered lists when TEXT_MODE is active
- `--text` added to plan-phase command argument-hint and flags docs
- Tests added for init output and workflow references
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
On Windows CI, fs.realpathSync returns the long path (runneradmin)
while git worktree list returns the 8.3 short path (RUNNER~1).
Apply fs.realpathSync to both sides of the assertion.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
resolveWorktreeRoot() unconditionally resolved linked worktrees to the main
repo root. When a linked worktree has its own independent .planning/ directory
(e.g., Conductor workspaces), all GSD commands read/wrote the wrong planning
state. Add an early return that checks for a local .planning/ before falling
through to main repo resolution.
The caller in gsd-tools.cjs already had this guard (added in #1283), but the
function itself should be correct regardless of call site. This is defense-in-
depth for any future callers.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The hardcoded EXPECTED_SKILLS and EXPECTED_AGENTS constants broke CI
on every PR that added or removed a command/agent, because the count
drifted from the source directories. Every open PR based on the old
count would fail until manually updated.
Now computed at test time by counting .md files in commands/gsd/ and
agents/ directories — the same source the installer reads from. Adding
a new command automatically updates the expected count.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Three non-blocking findings from the adversarial re-review of the
workstream namespacing PR, addressed as a follow-up:
1. setActiveWorkstream now validates names with the same regex used
at CLI entry and cmdWorkstreamSet — defense-in-depth so future
callers can't poison the active-workstream file
2. Replaced tautological test assertion (result.success || !result.success
was always true) with actual validation that cmdWorkstreamSet returns
invalid_name error for path traversal attempts. Added 8 new tests
for setActiveWorkstream's own validation.
3. Updated stale comment in copilot-install.test.cjs (said 31, actual 56)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Enable multiple Claude Code instances to work on the same codebase
simultaneously by scoping .planning/ state into workstreams.
Core changes:
- planningDir(cwd, ws?) and planningPaths(cwd, ws?) are now workstream-aware
via GSD_WORKSTREAM env var (auto-detected from --ws flag or active-workstream file)
- All bin/lib modules use planningDir(cwd) for scoped paths (STATE.md, ROADMAP.md,
phases/, REQUIREMENTS.md) and planningRoot(cwd) for shared paths (milestones/,
PROJECT.md, config.json, codebase/)
- New workstream.cjs module: create, list, status, complete, set, get, progress
- gsd-tools.cjs: --ws flag parsing with priority chain
(--ws > GSD_WORKSTREAM env > active-workstream file > flat mode)
- Collision detection: transition.md checks for other active workstreams before
suggesting next-milestone continuation (prevents WS A from trampling WS B)
- ${GSD_WS} routing propagation across all 9 workflow files ensures workstream
scope chains automatically through the workflow lifecycle
New files:
- get-shit-done/bin/lib/workstream.cjs (CRUD + collision detection)
- get-shit-done/commands/gsd/workstreams.md (slash command)
- get-shit-done/references/workstream-flag.md (documentation)
- tests/workstream.test.cjs (20 tests covering CRUD, env var routing, --ws flag)
All 1062 tests passing (1042 existing + 20 new workstream tests).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
When enabled, /gsd:autonomous chains directly from plan-phase to execute-phase,
skipping smart discuss. A minimal CONTEXT.md is auto-generated from the ROADMAP
phase goal so downstream agents have valid input. Manual /gsd:discuss-phase still
works regardless of the setting.
Changes:
- config.cjs: add workflow.skip_discuss to VALID_CONFIG_KEYS and hardcoded defaults (false)
- autonomous.md: check workflow.skip_discuss before smart_discuss, write minimal CONTEXT.md when skipping
- settings.md: add Skip Discuss toggle to interactive settings UI and global defaults
- config.test.cjs: 6 regression tests for the new config key
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add --pick flag to gsd-tools.cjs for extracting a single field from
JSON output, replacing all jq pipe usage across workflow and reference
files. Since Node.js is already a hard dependency, this eliminates the
need for jq on systems where it is not installed (notably Windows).
Changes:
- gsd-tools.cjs: add --pick <field> global flag with dot-notation and
bracket syntax support (e.g., --pick section, --pick directories[-1])
- Replace 15 jq pipe patterns across 6 workflow/reference files with
--pick flag or inline Node.js one-liner for variable extraction
- Add regression tests for --pick flag behavior
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Main already bumped 53→54 from merged PRs. Our new milestone-summary
command adds one more skill, making the total 55.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
New command that generates a comprehensive project summary from completed
milestone artifacts. Designed for team onboarding — new contributors can
run this against a completed project and understand what was built, how,
and why, with optional interactive Q&A grounded in build artifacts.
- commands/gsd/milestone-summary.md: command definition
- get-shit-done/workflows/milestone-summary.md: 9-step workflow
- tests/milestone-summary.test.cjs: 11 tests (command + workflow validation)
- tests/copilot-install.test.cjs: bump expected skill count 53→54
Reads: ROADMAP, REQUIREMENTS, PROJECT, CONTEXT, SUMMARY, VERIFICATION,
RETROSPECTIVE artifacts. Writes to .planning/reports/MILESTONE_SUMMARY-v{X}.md.
Closes#1298
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The discuss-phase command file contained a 93-line detailed <process>
block that competed with the actual workflow file. The agent treated
this summary as complete instructions and never read the execution_context
files (discuss-phase.md, discuss-phase-assumptions.md, context.md template).
Root cause: Unlike execute-phase and plan-phase commands (which have short
2-line process blocks deferring to the workflow file), discuss-phase had
inline step-by-step instructions detailed enough to act on without reading
the referenced workflow files.
Changes:
- Replace discuss-phase command's <process> block with a short directive
that forces reading the workflow file, matching execute-phase/plan-phase
pattern
- Add MANDATORY instruction that execution_context files ARE the
instructions, not optional reading
- Register workflow.research_before_questions and workflow.discuss_mode
as valid config keys (were missing from VALID_CONFIG_KEYS)
- Fix config key mismatch: workflows referenced "research_questions"
but documented key is "workflow.research_before_questions"
- Move research_before_questions from hooks section to workflow section
in settings workflow
- Add research_before_questions default to config template and builder
- Add suggestion mapping for deprecated hooks.research_questions key
- Add 6 regression tests covering config keys and process block guard
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Fixes from trek-e's review on PR #1282:
1. Add missing withProjectRoot() wrapper on output — all other cmdInit*
functions include project_root in JSON, manager was the only one without it.
2. Add getMilestonePhaseFilter() to directory scan — prevents stale phase
directories from prior milestones appearing as phantom dashboard entries.
3. Replace hardcoded .planning/ paths with planningPaths(cwd) — forward
compatibility with workstream scoping (#1268).
4. Add 3 new tests:
- Conflict filter blocks dependent phase execution when dep is active
- Conflict filter allows independent phase execution in parallel
- Output includes project_root field
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The interactive prompt now accepts comma-separated or space-separated
choices (e.g., "1,4,6" or "1 4 6") to install multiple runtimes in
one go, without needing --all or running the installer multiple times.
- Replaced if/else-if chain with runtimeMap lookup + split parser
- Added hint text: "Select multiple: 1,4,6 or 1 4 6"
- Invalid choices silently filtered, duplicates deduplicated
- Empty input still defaults to Claude Code
- Choice "8" still selects all runtimes
Tests: 10 new tests covering comma/space/mixed separators,
deduplication, invalid input filtering, order preservation,
and source-level assertions.
Closes#1281
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The installer pathPrefix for global installs replaced os.homedir()
with ~, which does NOT expand inside double-quoted shell commands
in POSIX shells. This caused MODULE_NOT_FOUND errors when executing
commands like: node "~/.claude/get-shit-done/bin/gsd-tools.cjs"
Changed pathPrefix to use $HOME instead of ~, which correctly expands
inside double quotes. Also fixed a quoted-tilde instance in do.md.
- bin/install.js: $HOME prefix instead of ~ for global installs
- get-shit-done/workflows/do.md: node "$HOME/..." instead of "~/"
- tests/path-replacement.test.cjs: updated + 3 new regression tests
Closes#1284
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
When running GSD from a monorepo subdirectory inside a git worktree,
resolveWorktreeRoot() resolved to the worktree root, discarding the
subdirectory where .planning/ lives. All commands failed with
"No ROADMAP.md found" even though the planning structure existed.
Now check if CWD already contains .planning/ before worktree
resolution. If it does, the CWD is already the correct project root
and worktree resolution is skipped.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Integrate upstream workspace features (new-workspace, list-workspaces,
remove-workspace) alongside manager feature. Bump copilot skill count
53 → 54 and agent count to 18 to account for both upstream additions
and the new manager skill.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add /gsd:manager — a single-terminal dashboard for managing milestones.
Shows all phases with visual status indicators (D/P/E columns), computes
recommended next actions, and dispatches discuss inline while plan/execute
run as background agents.
Key behaviors:
- Recommendation engine prioritizes execute > plan > discuss
- Filters parallel execute/plan when phases share dependency chains
- Independent phases (no direct or transitive dep relationship) CAN
run in parallel — dependent phases are serialized
- Dashboard shows compact Deps column for at-a-glance dependency view
- Sliding window limits discuss to one phase at a time
- Activity detection via file mtime (5-min window) for is_active flag
New files:
- commands/gsd/manager.md — skill definition
- get-shit-done/workflows/manager.md — full workflow spec
- get-shit-done/bin/lib/init.cjs — cmdInitManager() with phase parsing,
dependency graph traversal, and recommendation filtering
- get-shit-done/bin/gsd-tools.cjs — route 'init manager' to new command
- tests/init-manager.test.cjs — 16 tests covering status detection,
deps, sliding window, recommendations, and edge cases
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
When branching_strategy is "phase" or "milestone", the branch was only
created during execute-phase — but discuss-phase, plan-phase, and
new-milestone all commit artifacts before that, landing them on main.
Move branch creation into cmdCommit() so the strategy branch is created
at the first commit point in any workflow. execute-phase's existing
handle_branching step becomes a harmless no-op (checkout existing branch).
Also fixes websearch test mocks broken by #1276 (fs.writeSync change).
Closes#1278
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Extend resolve_model_ids to accept "omit" value: returns empty string
so non-Claude runtimes (OpenCode, Codex, Gemini, etc.) use their
configured default model instead of unresolvable Claude aliases.
- resolve_model_ids: "omit" short-circuits before alias resolution
- model_overrides still respected (checked first) for explicit IDs
- Installer sets resolve_model_ids: "omit" in ~/.gsd/defaults.json
for non-Claude runtimes during install
- 4 new tests covering omit behavior and override passthrough
- Fix websearch test mocks for fs.writeSync output change (#1276)
Closes#1156
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add codebase-first assumption-driven alternative to the interview-style
discuss-phase. New `workflow.discuss_mode: "assumptions"` config routes
to a separate workflow that spawns a gsd-assumptions-analyzer agent to
read 5-15 codebase files, surface assumptions with evidence, and ask
only for corrections (~2-4 interactions vs ~15-20).
- New gsd-assumptions-analyzer agent for deep codebase analysis
- New discuss-phase-assumptions.md workflow (15 steps)
- Command-level routing via dual @reference + process gate
- Identical CONTEXT.md output — downstream agents unaffected
- Existing discuss-phase.md workflow untouched (zero diff)
- Mode-aware plan-phase gate and progress display
- User documentation and integration tests
- Update agent count and list in copilot-install tests (17 → 18)
Closes#637
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Verification checked structure but not whether data actually flows
end-to-end or whether external dependencies are available. Adds:
- Step 4b (Data-Flow Trace): Level 4 verification traces upstream from
wired artifacts to verify data sources produce real data, catching
hollow components that render empty/hardcoded values
- Step 7b (Behavioral Spot-Checks): lightweight smoke tests that verify
runnable code produces expected output, not just that it exists
- Step 2.6 (Environment Audit): researcher probes target machine for
external tools/services/runtimes before planning, so plans include
fallback strategies for missing dependencies
Closes#1245
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
