Two more diagnostic passes (clusters J: residuals in already-touched files,
K: 12 untouched files) plus a production-code path fix and a new
ratchet-style lint guard.
## Test-only fixes (14 files)
bug-1736, bug-2248, bug-2698 — replace inline 1s-budget rmSync with the
shared cleanup() helper (5s budget, 20×250ms retries). The earlier
inline maxRetries:10 / retryDelay:100 wasn't enough to absorb Windows
Defender's deferred-scan handle hold on cold runners.
bug-2256, skill-manifest — also override USERPROFILE alongside HOME in
beforeEach/runGsdTools calls. os.homedir() reads USERPROFILE on win32,
so HOME-only stubs leak the runner's real home into the SUT.
bug-2784, bug-3608, enh-2500, enh-2790, few-shot-calibration,
gsd-settings-advanced — CRLF tolerance: literal \n in regexes against
file content (frontmatter anchors, bash-fence regex, multi-line
numbered-list captures, awk-block extractors) becomes \r?\n; split('\n')
becomes split(/\r?\n/). Windows checkout with autocrlf=true puts \r
before every \n; .+ doesn't match \r in JS regex by default.
bug-2966 — three-part fix to extractStepRun (CRLF split), awk regex
(\r?\n), and conflict-marker parser (rawLine + \r$ strip).
bug-2969, config — normalize separators on test assertions where the
SUT correctly emits \ on win32 but the test compares against /.
prompt-injection-scan — normalize relPath via replace(/\\/g, '/') before
ALLOWLIST.has() lookup. ALLOWLIST keys are POSIX; path.relative returns
backslashes on win32 → falsely scans allowlisted security module → trips
the boundary-tag detector on its own legitimate detection code.
prune-orphaned-worktrees — use the existing canonicalPath +
listedWorktreePaths(repoDir).has(...) helpers instead of substring
matching the raw path. git stores long-form canonical paths
(runneradmin), but mkdtempSync returns 8.3 short-form (RUNNER~1) on
Windows runners; plain string compare misses every entry.
## Production-code fix (1 file)
get-shit-done/bin/lib/init.cjs — bug-3491 in_nested_subdir computation
canonicalizes both worktreeRoot and cwd via fs.realpathSync.native +
path.relative before declaring "nested." Windows runner cwd (8.3 short
name) vs git's --show-toplevel (long form, forward slashes) made the
raw string compare always say true even at the worktree root, breaking
the "init new-project at worktree root" subtest.
## New ratchet lint guard
tests/windows-test-parity-guard.test.cjs — scans tests/ for 7
anti-patterns that drove the Windows failure clusters. Each rule has a
baseline count snapshot from this PR; the test fails when a new
occurrence appears (count grows above baseline), ratcheting down as
existing offenders are fixed. Patterns covered:
G1 split('\n') after readFileSync (use /\r?\n/)
G2 ```bash\n fence regex (use ```bash\r?\n)
G3 ^---\n frontmatter anchor (use ^---\r?\n)
G4 hardcoded "/tmp/..." literal passed to fs.* (use os.tmpdir())
G5 bare 'npm' to execFileSync without {shell:true} on win32
G6 process.env.HOME stub with no USERPROFILE
G7 fs.rmSync({recursive,force}) without maxRetries
Future Windows-parity regressions get caught at PR time rather than
five iterations into a CI loop.
Validated: holodeck (ubuntu docker) 11232/0 pass (count +8 = the 7
new ratchet tests + parent describe).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Introduce `runtime-slash.cjs` as the single source of truth for emitting
GSD slash-command references in user-facing runtime output and persisted
artifacts. `formatGsdSlash(commandName, runtime)` produces `/gsd-<cmd>`
for skills-based runtimes (Claude/Cursor/OpenCode/Kilo/etc.) and
`$gsd-<cmd>` for Codex. The deprecated `/gsd:<cmd>` colon form is never
emitted — pasting a recommended-action command into Claude Code now
routes correctly instead of failing with `Unknown command`.
Wired into the high-impact emitters identified in #3584:
- `init.cjs` `cmdInitManager` recommended_actions[].command (the
original failure path in the bug report) plus the no-ROADMAP /
no-STATE error hints.
- `phase.cjs` `cmdPhaseAdd`, `cmdPhaseAddBatch`, `cmdPhaseInsert` —
ROADMAP.md `Plans:` references now persist the routable form
instead of the legacy colon form.
- `verify.cjs` `cmdValidateHealth` — every fix-hint addIssue() call
(E001/E002/E003/E004/E005, W002/W003/W008/W009/W011/W016/W018) and
the persisted STATE.md regenerate / MILESTONES.md backfill notes.
- `milestone.cjs` `cmdMilestoneComplete` — Operator Next Steps tail
rewrite.
- `validate-command-router.cjs` — `validate context` recommendation
strings for WARNING/CRITICAL utilization bands.
- `workstream.cjs` — missing .planning hint.
- `profile-output.cjs` — `generate-claude-md` workflow enforcement
block, project/skills fallbacks, profile placeholder, and the
dev-preferences refresh hints.
- `drift.cjs`, `gsd2-import.cjs`, `commands.cjs scaffold context` —
remaining one-off persisted references.
Runtime detection: `resolveRuntime(projectDir)` reads
`process.env.GSD_RUNTIME` first, then a side-effect-free direct read of
`.planning/config.json` (NOT `loadConfig`, which would normalize legacy
keys and re-write the file just to read the runtime name).
Tests:
- `tests/bug-3584-runtime-slash-formatter.test.cjs` — 22 unit tests
covering the pure formatter and resolver (hyphen vs codex, prefix
normalization, defensive returns, env/config/default chain).
- `tests/bug-3584-runtime-slash-emitters.test.cjs` — 6 integration
tests exercising `init manager`, `phase add` (via the structured
`roadmap get-phase` payload to avoid raw-text matching on the
on-disk artifact), `validate health`, `validate context`, and the
codex variant.
- Existing tests updated to assert the new contract: validate-context
recommendations, claude-md workflow block, milestone complete
Operator Next Steps. Copilot-install engine-conversion test now
asserts against a synthetic input since bin/lib/*.cjs no longer
contains literal `/gsd:` references for the install-time converter
to rewrite.
INVENTORY.md and INVENTORY-MANIFEST.json updated for the new module
(64 CLI modules shipped, +1).
Fixes#3584
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds a new `phase_status` field to the `init.plan-phase` SDK + CJS query
output and a §1.5 "Closed-Phase Gate" in workflows/plan-phase.md that
short-circuits on closed phases instead of silently replanning over
shipped code.
## What was broken
`gsd-sdk query init.plan-phase <N>` returned the same "ready to plan"
payload for a closed phase (REQUIREMENTS Met, VERIFICATION.md status:
passed, ROADMAP flipped) as for an open one. No field signaled closure,
so `/gsd:plan-phase --reviews` happily replanned over closed phases —
risking documentation drift on already-shipped code.
## Fix
- Export `determinePhaseStatus` from `commands.cjs` (already present, was
module-private).
- Both `cmdInitPlanPhase` (CJS) and `initPlanPhase` (TS SDK) now compute
`phase_status` from plan/summary counts + VERIFICATION.md status using
the existing `determinePhaseStatus` helper — the project-wide phase
lifecycle vocabulary (Pending | Planned | In Progress | Executed |
Complete | Needs Review). No directory yet → Pending.
- Workflow `plan-phase.md` adds §1.5 "Closed-Phase Gate":
- `phase_status == "Complete"` with `--reviews` → hard-stop, no
override (replanning a closed phase via review feedback is never
legitimate; concerns belong in a follow-up phase or new issue).
- `phase_status == "Complete"` without `--force` → exit with a clear
notice pointing at VERIFICATION.md.
- `phase_status == "Complete"` with `--force` → continue with a
transcript banner so the deliberate replan is visible.
`Executed` and `Needs Review` are intentionally not gated — those mean
planning finished but verification did not pass, and replanning is the
correct next step.
## Tests
- SDK: 4 new `phase_status` cases in init.test.ts covering Pending /
Planned / Executed / Complete transitions.
- Existing init.plan-phase golden parity test continues to pass (the
`researcher_model: '' vs sonnet` drift in that test predates this
change and is unrelated).
- Full Mac+Docker suite: 9323 / 9323 passed (Mac), 9318 / 9323 passed
(Docker, 5 skipped).
Fixes#3569
The `has_git` boolean returned by `init new-project` and `init ingest-docs`
was derived from a shallow `pathExists(cwd, '.git')` check, so a subdirectory
of an existing repo reported `has_git: false`. The workflow then ran
`git init`, creating a nested `.git` inside the outer worktree and silently
diverting subsequent `gsd-sdk commit` calls into the nested repo.
Replace the shallow check with `git rev-parse --is-inside-work-tree`
semantics in both CJS (`get-shit-done/bin/lib/init.cjs`) and TS
(`sdk/src/query/init.ts`, `sdk/src/query/init-complex.ts`) handlers via a new
shared `gitWorktreeInfoInternal` helper, and expose `git_worktree_root` +
`in_nested_subdir` so the workflows can refuse `git init` inside an existing
worktree and warn that planning files will track to the outer repo.
Regression test: `tests/bug-3491-nested-git-worktree.test.cjs`.
Fixes#3491
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* refactor(shell-projection): migrate roadmap.cjs writes to platformWriteSync (#3467)
2 atomicWriteFileSync calls → platformWriteSync. The seam owns markdown
normalization, so the explicit utf-8 encoding arg is no longer needed.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* refactor(shell-projection): migrate config.cjs writes to platformWriteSync (#3467)
- 3 atomicWriteFileSync calls → platformWriteSync
- 1 raw fs.writeFileSync (depth→granularity migration) → platformWriteSync
- 2 fs.mkdirSync(planningBase, { recursive: true }) → platformEnsureDir
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* refactor(shell-projection): migrate docs.cjs reads to platformReadSync (#3467)
6 try { fs.readFileSync } catch {} patterns → platformReadSync(path) with
explicit null guards. detectProjectType now reads package.json once and
shares it across has_cli_bin/is_monorepo/has_tests checks. JSON.parse is
still wrapped in a try (parsing is a separate failure mode from missing file).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* refactor(shell-projection): migrate audit.cjs reads to platformReadSync (#3467)
8 try { fs.readFileSync(safeFilePath, 'utf-8') } catch { continue } patterns
→ const content = platformReadSync(safeFilePath); if (content === null) continue;
The single safeSum case (where catch set status='unreadable' rather than
continue) maps to an if/else that preserves the same semantics.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* refactor(shell-projection): migrate planning-workspace.cjs to platform* seam (#3467)
- 2 try { fs.readFileSync } catch {} → platformReadSync (null on missing)
- 2 fs.writeFileSync (workstream pointer writes) → platformWriteSync
- 3 fs.mkdirSync(..., { recursive: true }) → platformEnsureDir
The .lock file write at withPlanningLock is intentionally NOT migrated.
That call uses { flag: 'wx' } for atomic exclusive-create, which is the
correct lock-acquisition primitive. platformWriteSync's atomic-rename
pattern would silently overwrite an existing lock file and break the
locking guarantee.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* refactor(shell-projection): migrate milestone.cjs writes to platform* seam (#3467)
- 5 atomicWriteFileSync calls → platformWriteSync (4 dropped normalizeMd
wrapper; seam handles .md normalization automatically)
- 2 raw fs.writeFileSync (archive ROADMAP.md / REQUIREMENTS.md) → platformWriteSync
- 2 fs.mkdirSync(..., { recursive: true }) → platformEnsureDir
- Dropped normalizeMd import (only used as write pre-call here)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* refactor(shell-projection): migrate intel.cjs to platform* seam (#3467)
- 7 fs.readFileSync (existsSync+readFileSync patterns and try/catch) → platformReadSync
- 2 fs.writeFileSync → platformWriteSync
- 1 fs.mkdirSync(intelPath, { recursive: true }) → platformEnsureDir
- Consolidated dual-check (existsSync + readFileSync) into single platformReadSync
call returning null on missing file
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* refactor(shell-projection): migrate workstream.cjs to platform* seam (#3467)
- 5 fs.mkdirSync(..., { recursive: true }) → platformEnsureDir
- 1 fs.writeFileSync (STATE.md initial scaffold) → platformWriteSync
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* refactor(shell-projection): migrate init.cjs reads/writes to platform* seam (#3467)
- 11 try/readFileSync and existsSync+readFileSync patterns → platformReadSync
- 1 fs.writeFileSync (skill-manifest.json) → platformWriteSync
Three bare fs.readFileSync calls remain (ROADMAP/STATE reads in code paths
where the file is required to exist) — these are not "Done when" violations
(no try/catch wrapping, no inline existsSync guard).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* refactor(shell-projection): migrate commands.cjs reads/writes to platform* seam (#3467)
- 6 try/readFileSync and existsSync+readFileSync patterns → platformReadSync
- 2 fs.writeFileSync → platformWriteSync
- 3 fs.mkdirSync(..., { recursive: true }) → platformEnsureDir
- Removed unused safeReadFile import (zero call sites in this file)
Three bare fs.readFileSync calls remain (sourcePath at line 752, fullPath at
443, roadmapPath in cmdAuditOpen) — preceded by existsSync guards or in code
paths where file presence is required; not "Done when" violations.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* refactor(shell-projection): migrate profile-output.cjs to platform* seam (#3467)
- 6 safeReadFile (from core.cjs) calls preserved by aliasing platformReadSync
as safeReadFile in the import — same semantics, zero call-site changes
- 3 try/JSON.parse(readFileSync) patterns → platformReadSync + try/JSON.parse
- 1 existsSync+readFileSync pattern (claude.md update) → platformReadSync
- 5 fs.writeFileSync → platformWriteSync
- 4 fs.mkdirSync(..., { recursive: true }) → platformEnsureDir
Two bare fs.readFileSync calls remain (template reads where file must exist
or fail loudly) — not "Done when" violations.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* refactor(shell-projection): migrate state.cjs to platform* seam (#3467)
- 4 atomicWriteFileSync calls → platformWriteSync (3 dropped normalizeMd
wrapper; seam handles .md normalization)
- 4 try/readFileSync and existsSync+readFileSync patterns → platformReadSync
- 1 fs.writeFileSync (WAITING.json) → platformWriteSync
- 1 fs.mkdirSync(..., { recursive: true }) → platformEnsureDir
- Dropped normalizeMd and atomicWriteFileSync imports (only used as write
pre-calls here)
Bare fs.readFileSync calls remain in code paths where STATE.md is required
to exist (statePath reads in cmd handlers, dry-run prune) — not "Done when"
violations.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* refactor(shell-projection): migrate core.cjs to platform* seam (#3467)
- 7 try/readFileSync and existsSync+readFileSync patterns → platformReadSync
- 3 fs.writeFileSync (config writes + large-payload temp file) → platformWriteSync
- 1 fs.mkdirSync (GSD_TEMP_DIR) → platformEnsureDir
Three fs calls remain — they are the internal implementations of the
safeReadFile and atomicWriteFileSync wrappers that core.cjs exports for
backward compatibility. The wrappers are scheduled for removal in Phase 4
(#3468) and will not be migrated here.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* refactor(shell-projection): migrate phase.cjs writes to platform* seam (#3467)
- 6 atomicWriteFileSync calls → platformWriteSync
- 3 fs.writeFileSync(path.join(dirPath, '.gitkeep'), '') → platformWriteSync
- 3 fs.mkdirSync(..., { recursive: true }) → platformEnsureDir
Bare fs.readFileSync calls remain for roadmapPath/planPath reads where the
file is required to exist; these are not "Done when" violations.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* refactor(shell-projection): migrate verify.cjs to platform* seam (#3467)
- 8 safeReadFile (from core.cjs) calls preserved by aliasing platformReadSync
as safeReadFile in the import — same semantics, zero call-site changes
- 1 existsSync+readFileSync inline ternary → safeReadFile (returns null)
- 5 fs.writeFileSync (config writes + milestones writes) → platformWriteSync
Bare fs.readFileSync calls remain for code paths where the file is required
to exist (roadmap/state/config full reads); these are not "Done when"
violations.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* refactor(shell-projection): migrate frontmatter.cjs + update atomic-write test (#3467)
- frontmatter.cjs: 2 atomicWriteFileSync calls → platformWriteSync. The
legacy normalizeMd wrapper is dropped because the seam handles markdown
normalization. safeReadFile preserved by aliasing platformReadSync.
- atomic-write-coverage.test.cjs: update the #1972 structural invariant
to assert on platformWriteSync. platformWriteSync uses the same
tmp-file + atomic-rename primitive that atomicWriteFileSync did — the
no-partial-write guarantee is preserved across the migration.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* chore(changeset): add entry for shell-projection Phase 3 migration (#3467)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* chore(coderabbit): disable ESLint tool (repo uses custom lint scripts)
CodeRabbit's review surface emits a "skipped: no ESLint configuration"
warning because the repo doesn't ship ESLint config. The repo
intentionally does not use ESLint — it ships its own targeted lint
scripts (scripts/lint-no-source-grep.cjs, npm run lint:tests) that
enforce repo-specific test-quality invariants. Adding ESLint config
purely to satisfy CR would add an external dependency
(CONTRIBUTING.md: "No external dependencies in core") and overlap
with the existing custom lint surface.
Disable the ESLint tool in CR's tools config so the skip warning
stops appearing on every PR.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* refactor(shell-projection): migrate planning-workspace.cjs tty probe to probeTty seam (#3466)
Replaces direct execFileSync('tty') with probeTty() from the shell-projection
seam. Removes try/catch — probeTty() returns null on error/non-tty/win32.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* refactor(shell-projection): migrate commands.cjs to execGit seam (#3466)
- Replaces execSync('git diff --cached --name-only') with execGit array call
- Migrates 14 existing execGit(cwd, args) callers from core.cjs's local
wrapper to the seam's execGit(args, { cwd }) signature
- Drops execGit from the core.cjs destructure to resolve naming collision
Drops try/catch around git diff — execGit returns exitCode without throwing,
so the no-staged-files / not-a-git-repo case is detected by exitCode !== 0.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* refactor(shell-projection): migrate check-latest-version.cjs to execNpm seam (#3466)
Routes the default-spawn path through execNpm — execNpm owns the win32
shell-flag policy. The injection point remains spawnSync-shaped for test
compatibility; an internal adapter translates { exitCode } → { status }.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* refactor(shell-projection): migrate init.cjs git calls to execGit seam (#3466)
Replaces 3 execSync calls with execGit array-args:
- detectChildRepos: git status --porcelain
- cmdInitNewWorkspace: git --version (worktree availability probe)
- cmdRemoveWorkspace: git status --porcelain
Drops 3 try/catch blocks — execGit returns exitCode without throwing, so
best-effort handling becomes a clean exitCode === 0 check.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* refactor(shell-projection): migrate core.cjs to execGit seam delegation (#3466)
- Removes direct require('child_process') from core.cjs
- Replaces execFileSync('git check-ignore') with seam's execGit
- Local execGit wrapper now a thin adapter delegating to seam — keeps the
legacy (cwd, args) positional signature and derived timedOut field for
the verify.cjs and worktree-safety.cjs consumers that are out of Phase 2
scope (the wrapper proper would only be removed once those consumers
migrate, tracked separately)
Extends the seam's _spawnResult to expose signal and error fields so callers
can compute timedOut without bypassing the seam. The Phase 1 test suite
asserts on required field presence only, so the extension is
backward-compatible.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* refactor(shell-projection): migrate graphify.cjs to execTool seam (#3466)
- execGraphify: spawnSync('graphify', ...) → execTool with env passthrough,
preserving the ENOENT/TIMEOUT/EXIT_NONZERO typed reason mapping using the
seam's signal/error fields
- checkGraphifyInstalled: spawnSync('graphify', ['--help']) → execTool
- checkGraphifyVersion strategy 1: graphify --version via execTool
- checkGraphifyVersion strategy 2: python3 importlib.metadata via execTool
Adds env option to execTool — graphify needs PYTHONUNBUFFERED=1 to drain
buffered stdout on long-running operations.
Changes seam internals to access spawnSync/execFileSync via the non-destructured
childProcess module reference. Destructured imports capture references at load
time and are un-mockable by mock.method(childProcess, 'spawnSync', ...) — which
breaks all the graphify subprocess tests. Non-destructured access restores
mockability without changing public behavior.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat(shell-projection): execGit defaults to non-interactive git env (#3466)
Bakes GIT_TERMINAL_PROMPT=0 and GCM_INTERACTIVE=never into execGit's default
env. Without these, a credential prompt or terminal-input probe blocks the
git subprocess indefinitely until our 10s timeout kills it — surfacing as
a generic timeout instead of the actual auth-prompt cause.
These were previously set ad-hoc in worktree-safety.cjs's local execGitDefault
wrapper. Moving them to the seam makes them the consistent default for every
git call across the codebase. Callers can override via opts.env.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* refactor(shell-projection): remove core.cjs local execGit wrapper; migrate verify + worktree-safety (#3466)
Completes the Phase 2 "remove local execGit wrapper" criterion. All callers
now use the shell-projection seam's execGit(args, opts) signature directly.
- core.cjs: delete the local execGit wrapper and the execGit export. The
isGitIgnored seam check now calls execGit from the seam. Worktree-safety
function calls drop their execGit DI passthrough — worktree-safety's
internal execGitDefault now delegates to the seam and adds timedOut.
- verify.cjs: 6 callers migrate from execGit(cwd, args) to
execGit(args, { cwd }). Imports execGit from the seam directly. The
inspectWorktreeHealth DI passes the seam's execGit (worktree-safety now
matches that shape).
- worktree-safety.cjs: local execGitDefault becomes a thin adapter over
the seam — no more direct spawnSync. 11 internal callers migrate to the
new shape. DI contract for tests changes from (cwd, args) → (args, opts).
- graphify.cjs: 2 remaining execGit callers migrate from core.cjs (now
removed) to the seam directly.
- test mocks updated in 3 worktree-safety test files to match the new
(args, opts) DI shape — most mocks were shape-agnostic and required no
changes; only those that destructured cwd/args needed updates.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* chore(changeset): add entry for shell-projection Phase 2 migration (#3466)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(pr3476): address CodeRabbit review findings
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* refactor: tighten sdk-first architecture seams
Refs #3312
* refactor: finish state document seam cleanup
Refs #3312
* test: harden minimal install cleanup assertion
* ci: support sdk-scoped package lock
* fix(3316): restore root package-lock.json and align changeset pr ref
Reverts dec57a83 ("ci: support sdk-scoped package lock") and restores
the root package-lock.json that c249d34d deleted. The deletion was the
wrong direction:
- The root package.json declares its own runtime and dev deps
(@anthropic-ai/claude-agent-sdk, ws, c8). Without a root lockfile,
`npm install --no-package-lock` resolves whatever satisfies semver at
install time — CI today and CI in six months can install different
transitive trees, defeating reproducibility.
- The lockfile has been part of every release on this repo (long
history on main); removing it loses the npm audit / Dependabot
target without compensating benefit.
- The CI workaround pattern (cache-dependency-path: sdk/package-lock.json
+ `npm install --no-package-lock`) papered over the symptom rather
than fix the cause.
Also fix the changeset pr: from 3312 (issue) to 3316 (PR). CONTEXT.md
flags this exact failure mode as a recurring CodeRabbit finding.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix: address coderabbit review findings
* fix: close remaining coderabbit threads
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* test(phase-plans): red — shared scanPhasePlans contract + parity across call sites (#3262)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat(phase-plans): extract shared scanPhasePlans helper (k014) (#3262)
Eliminates four divergent copies of the plan-scan algorithm:
- roadmap.cjs:countPhasePlansAndSummaries (root call site)
- state.cjs:buildStateFrontmatter (1 of 3)
- state.cjs:cmdStateValidate (2 of 3)
- state.cjs:cmdStateSync (3 of 3)
- init.cjs:listPhasePlanFiles / listPhaseSummaryFiles
New bin/lib/plan-scan.cjs exports scanPhasePlans(phaseDir) → {
planCount, summaryCount, completed, hasNestedPlans,
planFiles, summaryFiles
}
Divergences resolved:
- roadmap.cjs used a broad isPlanFile (any .md containing PLAN in name,
matching the extended layout 5-PLAN-01-setup.md); canonical helper
adopts this wider pattern as the reference implementation.
- state.cjs used a strict endsWith(-PLAN.md) filter, missing extended-
layout root files; now unified with roadmap.cjs semantics.
- init.cjs listPhasePlanFiles used ^PLAN-\d+ for nested, missing
the -PLAN-\d+ variant state.cjs also matched; helper includes both.
- pre-bounce exclusion broadened to /.pre-bounce.md$/i (any pre-bounce
file), not just -PLAN.*\.pre-bounce\.md (roadmap form) or flat
.pre-bounce.md (state form).
- OUTLINE exclusion broadened to /-OUTLINE\.md$/i to catch both
flat (-PLAN-OUTLINE.md) and nested (PLAN-01-OUTLINE.md) forms.
Sibling audit: no 5th call site found. phase.cjs:looksLikePlanFile is
a diagnostic probe for non-canonical naming (not a counter) — left
in place per its distinct purpose.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* chore(changelog): add entry for #3262 scanPhasePlans extraction
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* chore(changeset): add changeset fragment for #3262
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* docs(inventory): add plan-scan.cjs row to INVENTORY.md CLI Modules table (#3262)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(3262): update bug-3128 test + INVENTORY counts for plan-scan.cjs
- Update tests/bug-3128-roadmap-plan-count-slug-layout.test.cjs to verify
that roadmap.cjs delegates to plan-scan.cjs (require check) and that the
extended filter lives in plan-scan.cjs as isRootPlanFile with /PLAN/i
- Bump docs/INVENTORY.md CLI Modules headline from 46 to 47 (plan-scan.cjs)
- Regenerate docs/INVENTORY-MANIFEST.json to include cli_modules/plan-scan.cjs
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(3262): migrate two missed call sites to scanPhasePlans (k014)
- init.cjs cmdInitExecutePhase: replace inline /-PLAN\.md$/i filter
with listPhasePlanFiles(path) to honour nested, extended-layout, OUTLINE
and pre-bounce exclusions (CR finding)
- state.cjs cmdStateUpdateProgress: replace dual /-PLAN\.md$/i and
/-SUMMARY\.md$/i filters with scanPhasePlans() so the progress-bar
body field uses the same counts as buildStateFrontmatter frontmatter
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(3262): correct INVENTORY-MANIFEST.json to tracked files only
Remove 3 untracked local entries from cli_modules so the manifest matches
what CI sees (47 tracked .cjs files, not 50 local). Previous regeneration
ran against the local filesystem which included cjs-command-router-adapter.cjs,
state-document.cjs, and workstream-inventory.cjs (all untracked on this branch).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* test: phase-dir prefix parity across creation paths (#3287 RED)
Add failing tests asserting that init.phase-op and init.plan-phase
expose expected_phase_dir with the project_code prefix when the phase
directory does not yet exist — matching the prefix applied by phase.add.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(phase): unify phase-dir naming via shared getPhaseDirName helper (#3287)
Both init.phase-op (discuss-phase workflow) and init.plan-phase
(plan-phase workflow) now compute expected_phase_dir — the canonical
directory name including the project_code prefix when set — and expose
it in their JSON bundle.
Workflow fallback mkdir calls are updated to use ${expected_phase_dir}
instead of constructing the path from padded_phase + phase_slug, which
was missing the project_code prefix.
This eliminates the two-headed naming convention where phase.add/insert
produced XR-01-foundation/ while the first-touch paths produced
01-foundation/ for the same project.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* refactor(phase): apply project_code prefix in scaffold phase-dir (#3287)
Audit finding: phase.scaffold (CJS commands.cjs + SDK phase-lifecycle.ts)
also constructed phase dir names without project_code prefix.
Both implementations now read config.project_code and apply the same
prefix logic as phase.add/phase.insert.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* changeset: pr=3292 for #3287
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* docs(changelog): add entry for #3287 phase-dir prefix parity fix
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* Deepen SDK package seam and converge runtime skills policy
* fix(sdk): unified install-root resolution for workflows and agents (CR finding 1)
Use the already-resolved gsdInstallDir constant instead of calling
resolveLegacyInstallDir() again when computing agentsDir, ensuring
workflowsDir and agentsDir share the same install root.
* fix(sdk): tilde shortening requires path-boundary match (CR finding 2)
Both renderGlobalSkillsBaseDisplayPath and renderGlobalSkillDisplayPath
used startsWith(home) which could incorrectly shorten unrelated paths
sharing the same prefix. Now checks for home === base or
base.startsWith(home + sep) to ensure a real directory boundary.
* fix(sdk): validate loadConfig export before invocation (CR finding 3)
After requiring core.cjs, check typeof mod.loadConfig === 'function'
before calling it. Throws a classified GSDError with the module path
if the export is missing, rather than a generic TypeError.
* fix(test): guard root lookup before .path dereference (CR finding 4)
Added assert.ok() guards for claudeRoot and codexRoot after the .find()
calls so that a missing root produces an explicit assertion failure
rather than a TypeError on .path dereference.
* fix(ci): fail-safe on transient API errors in approval dismissal (CR finding 6)
resolveRole() returns 'unknown' for non-404 errors (rate limits, 5xx,
network blips). shouldDismissReviewer() now treats 'unknown' as
unresolvable and skips dismissal, preventing legitimate approvals from
being dismissed due to a transient API failure. Only 'none' (true 404)
is treated as a confirmed non-collaborator.
* changeset: pr=3238 SDK package seam and runtime skills convergence
* fix(sdk): harden resolveGlobalSkillDir against path traversal (CR finding 1)
Use resolve+relative to validate that skillName cannot escape the global
skills base directory. Values like "../../foo" or absolute paths now
return null instead of joining directly. All imports (resolve, relative,
isAbsolute) were already present in helpers.ts.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(sdk): split skill-dir-resolution and skill-not-found warnings (CR finding 2)
After resolveGlobalSkillDir's hardening can return null for traversal
attempts, the old single-branch warning "Global skill not found at ..."
was misleading. Split into two distinct cases:
- skillDir === null → "Could not resolve global skill directory for ..."
- skillMd missing → "Global skill not found at ..."
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* test: lock skill path-traversal rejection in resolveGlobalSkillDir
Regression test verifying that traversal segments (../../foo, ../escape),
empty string, and absolute paths are all rejected (return null), while
a legitimate skill name resolves correctly.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* test(sdk): align display-path contract + traversal coverage for resolveGlobalSkillMarkdownPath (CR nitpicks)
- renderGlobalSkillsBaseDisplayPath now returns a non-null string for
unsupported runtimes (e.g. cline → "(cline does not use a skills directory)")
matching the existing renderGlobalSkillDisplayPath contract; callers
of both helpers no longer need null-checks for unsupported runtimes.
- Remove now-redundant ! non-null assertion on renderGlobalSkillsBaseDisplayPath
calls in skill-manifest.ts (return type is string, not string | null).
- Extend the path-traversal test block to assert resolveGlobalSkillMarkdownPath
also propagates null for ../../foo, ../escape, empty, and /abs/path inputs,
locking the null-propagation contract against future refactors.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(#2997): mask SECRET_CONFIG_KEYS in SDK config-set/get and init responses
The CJS→TS port at sdk/src/query/config-mutation.ts:240,243 and
config-query.ts:122,128,132 dropped the masking layer that secrets.cjs
spec defines for brave_search/firecrawl/exa_search. Result: the SDK
echoed plaintext API keys into machine-readable JSON output (stdout,
transcripts, CI logs).
Adjacent leak in init.ts:673-675 / init.cjs:728-730: the init bundle
passed config.brave_search through raw, leaking the API key whenever
the user had stored one.
Fix:
- New sdk/src/query/secrets.ts ports SECRET_CONFIG_KEYS, isSecretKey,
maskSecret, maskIfSecret. Exact CJS parity (verified by 17 tests
in secrets.test.ts that import secrets.cjs and compare).
- config-set masks value + previousValue in response; on-disk plaintext
intact (key stays usable).
- config-get masks read response. --default flows through unmasked
(user's own input, not stored secret).
- init.ts/init.cjs mask string values only; booleans (availability
flags) pass through unchanged so the typed contract is preserved.
Tests: 17 in secrets.test.ts (including CJS parity), 5 in
config-mutation.test.ts (#2997 block — covers on-disk-preserved,
previousValue masking, short-value, unset, non-secret pass-through),
4 in config-query.test.ts.
Closes#2997
* chore(#2997): add changeset fragment for PR #2999
* chore(#2997): add changeset fragment for PR #2999
* chore(#2999): drop direct CHANGELOG.md edit; release entry now lives in .changeset/
The changeset-fragment workflow (#2975) renders fragments into
CHANGELOG.md at release time. Direct edits to [Unreleased] on
each PR caused merge conflicts on every concurrent PR. This commit
restores CHANGELOG.md to match origin/main; the release entry for
this fix is preserved in the .changeset/*.md fragment(s) on this
branch, which the release workflow consolidates.
* fix(#2801): add ingest-docs handler to gsd-tools init dispatch
The `/gsd-ingest-docs` workflow was broken because `workflows/ingest-docs.md`
called `gsd-sdk query init.ingest-docs` but the installed binary is `gsd-tools`,
and `gsd-tools init` had no `ingest-docs` case in its dispatch switch.
- Added `cmdInitIngestDocs` function to `init.cjs` and exported it; returns
`project_exists`, `planning_exists`, `has_git`, `project_path`, `commit_docs`
- Added `case 'ingest-docs'` to the `init` switch in `gsd-tools.cjs`
- Updated `workflows/ingest-docs.md` to call `gsd-tools init ingest-docs`
(line 55) and `gsd-tools commit` (line 292) instead of `gsd-sdk query ...`
- Regression test: `tests/bug-2801-ingest-docs-handler.test.cjs`
Closes#2801
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(#2801): address CodeRabbit — commit_docs assertion, broader gsd-sdk detection, bash fence
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(#2769): tolerate Requirements header with colon inside bold delimiters
extractReqIds in sdk/src/query/init.ts and the legacy init.cjs port only
matched `**Requirements**:` (colon outside bold), so phases declared with
the equally-valid markdown form `**Requirements:**` (colon inside bold,
which is what the project's own templates emit) returned phase_req_ids:
null for both `init plan-phase` and `init execute-phase`.
The mirror-image bug in `phase complete`'s REQUIREMENTS.md traceability
sweep at get-shit-done/bin/lib/phase.cjs:871 only matched the inside-bold
form, silently skipping the REQ-ID checkbox flips for any roadmap that
used the outside-bold form. Both parsers now share the same canonical
regex that accepts all three rendered-identical variants:
**Requirements:** (colon inside bold)
**Requirements**: (colon outside bold)
**Requirements** : (space before outside colon)
Tests:
- tests/init.test.cjs — parameterized over the three header variants for
both init plan-phase and init execute-phase (6 new behavioral cases).
- sdk/src/query/init.test.ts — describe.each over the same variants
exercising initPlanPhase through the SDK.
- tests/bug-2769-requirements-header-variants.test.cjs — phase complete
flips REQ-001 in REQUIREMENTS.md across all three header variants.
Closes#2769
* refactor(#2769): centralize REQUIREMENTS_HEADER_RE constant per CodeRabbit
All workflow, command, reference, template, and tool-output files that
surfaced /gsd:<cmd> as a user-typed slash command have been updated to
use /gsd-<cmd>, matching the Claude Code skill directory name.
Closes#2697
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(#2633): use ROADMAP.md as authority for current-milestone phase counts
initMilestoneOp (SDK + CJS) derives phase_count and completed_phases from
the current milestone section of ROADMAP.md instead of counting on-disk
`.planning/phases/` directories. After `phases clear` at the start of a new
milestone the on-disk set is a subset of the roadmap, causing premature
`all_phases_complete: true`.
validateHealth W002 now unions ROADMAP.md phase declarations (all milestones
— current, shipped, backlog) with on-disk dirs when checking STATE.md phase
refs. Eliminates false positives for future-phase refs in the current
milestone and history-phase refs from shipped milestones.
Falls back to legacy on-disk counting when ROADMAP.md is missing or
unparseable so no-roadmap fixtures still work.
Adds vitest regressions for both handlers; all 66 SDK + 118 CJS tests pass.
* fix(#2633): preserve full phase tokens in W002 + completion lookup
CodeRabbit flagged that the parseInt-based normalization collapses distinct
phase IDs (3, 3A, 3.1) into the same integer bucket, masking real
STATE/ROADMAP mismatches and miscounting completions in milestones with
inserted/sub-phases.
Index disk dirs and validate STATE.md refs by canonical full phase token —
strip leading zeros from the integer head only, preserve [A-Z] suffix and
dotted segments, and accept just the leading-zero variant of the integer
prefix as a tolerated alias. 3A and 3 never share a bucket.
Also widens the disk and STATE.md regexes to accept [A-Z]? suffix tokens.
initProgress (and its CJS twin) hardcoded `not_started` for ROADMAP-only
phases, so `completed_count` stayed at 0 even when the ROADMAP showed
`- [x] Phase N`. Extract ROADMAP checkbox states into a shared helper
and use `- [x]` as the completion signal when no phase directory is
present. Disk status continues to win when both exist.
Adds a regression test that reproduces the bug with no phases/ dir and
one `[x]` / one `[ ]` phase, asserting completed_count===1.
Fixes#2646
Commands are now installed as commands/gsd/<name>.md and invoked as
/gsd:<name> in Claude Code. The old hyphen form /gsd-<name> was still
hardcoded in hundreds of places across workflows, references, templates,
lib modules, and command files — causing "Unknown command" errors
whenever GSD suggested a command to the user.
Replace all /gsd-<cmd> occurrences where <cmd> is a known command name
(derived at runtime from commands/gsd/*.md) using a targeted Node.js
script. Agent names, tool names (gsd-sdk, gsd-tools), directory names,
and path fragments are not touched.
Adds regression test tests/bug-2543-gsd-slash-namespace.test.cjs that
enforces zero legacy occurrences going forward. Removes inverted
tests/stale-colon-refs.test.cjs (bug #1748) which enforced the now-obsolete
hyphen form; the new bug-2543 test supersedes it. Updates 5 assertion
tests that hardcoded the old hyphen form to accept the new colon form.
Closes#2543
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(sdk): extractCurrentMilestone Backlog leak + state.begin-phase flag parsing
Closes#2422Closes#2420
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(#2444,#2445): scope stopped_at extraction to Session section; filter stale phase dirs
- buildStateFrontmatter now extracts stopped_at only from the ## Session
section when one exists, preventing historical prose elsewhere in the
body (e.g. "Stopped at: Phase 5 complete" in old notes) from overwriting
the current value in frontmatter (bug #2444)
- buildStateFrontmatter de-duplicates phase dirs by normalized phase number
before computing plan/phase counts, so stale phase dirs from a prior
milestone with the same phase numbers as the new milestone don't inflate
totals (bug #2445)
- cmdInitNewMilestone now filters phase dirs through getMilestonePhaseFilter
so phase_dir_count excludes stale prior-milestone dirs (bug #2445)
- Tests: 4 tests in state.test.cjs covering both bugs
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat: add /gsd-spec-phase — Socratic spec refinement with ambiguity scoring (#2213)
Introduces `/gsd-spec-phase <phase>` as an optional pre-step before discuss-phase.
Clarifies WHAT a phase delivers (requirements, boundaries, acceptance criteria) with
quantitative ambiguity scoring before discuss-phase handles HOW to implement.
- `commands/gsd/spec-phase.md` — slash command routing to workflow
- `get-shit-done/workflows/spec-phase.md` — full Socratic interview loop (up to 6
rounds, 5 rotating perspectives: Researcher, Simplifier, Boundary Keeper, Failure
Analyst, Seed Closer) with weighted 4-dimension ambiguity gate (≤ 0.20 to write SPEC.md)
- `get-shit-done/templates/spec.md` — SPEC.md template with falsifiable requirements
(Current/Target/Acceptance per requirement), Boundaries, Acceptance Criteria,
Ambiguity Report, and Interview Log; includes two full worked examples
- `get-shit-done/workflows/discuss-phase.md` — new `check_spec` step detects
`{padded_phase}-SPEC.md` at startup; displays "Found SPEC.md — N requirements
locked. Focusing on implementation decisions."; `analyze_phase` respects `spec_loaded`
flag to skip "what/why" gray areas; `write_context` emits `<spec_lock>` section
with boundary summary and canonical ref to SPEC.md
- `docs/ARCHITECTURE.md` — update command/workflow counts (74→75, 71→72)
Closes#2213
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat(worktrees): auto-prune merged worktrees in code, not prose
Adds pruneOrphanedWorktrees(repoRoot) to core.cjs. It runs on every
cmdInitProgress call (the entry point for most GSD commands) and removes
linked worktrees whose branch is fully merged into main, then runs
git worktree prune to clear stale references. Guards prevent removal of
the main worktree, the current process.cwd(), or any unmerged branch.
Covered by 4 new real-git integration tests in
tests/prune-orphaned-worktrees.test.cjs (TDD red→green).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
The sliding-window pattern serialized discuss to one phase at a time
even when phases had no dependency relationship. Replaced it with a
simple predicate: every undiscussed phase whose dependencies are
satisfied is marked is_next_to_discuss, letting the user pick any of
them from the manager's recommended_actions list.
Closes#2268
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
The `cmdInitMapCodebase` / `initMapCodebase` init handlers did not
include `date` or `timestamp` fields in their JSON output, unlike
`init quick` and `init todo` which both provide them.
Because the mapper agents had no reliable date source, they were forced
to guess the date from model training data, producing incorrect
Analysis Date values (e.g. 2025-07-15 instead of the actual date) in
all seven `.planning/codebase/*.md` documents.
Changes:
- Add `date` and `timestamp` to `cmdInitMapCodebase` (init.cjs) and
`initMapCodebase` (init.ts)
- Pass `{date}` into each mapper agent prompt via the workflow
- Update agent definition to use the prompt-provided date instead of
guessing
- Cover sequential_mapping fallback path as well
* feat(handoffs): include project identity in all Next Up blocks
Adds project_code and project_title to withProjectRoot() and updates
all 30 Next Up headings across 18 workflow files to include
[PROJECT_CODE] PROJECT_TITLE suffix for multi-project clarity.
Closes#1948
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(review): add withProjectRoot tests and fix placeholder syntax (#1951)
Address code review feedback:
- Add 4 tests for project_code/project_title injection in withProjectRoot()
- Fix inconsistent placeholder syntax in continuation-format.md canonical
template (bare-brace → shell-dollar to match variant examples)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(phase): preserve zero-padded prefix in renameDecimalPhases
Captures the zero-padded prefix (e.g. "06" from "06.3-slug") with
(0*${baseInt}) so renamed directories keep their original format
(06.2-slug) instead of stripping padding (6.2-slug).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Brandon Higgins <brandonscotthiggins@gmail.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Prevents infinite config-get loops on Kimi K2.5 and other models that
re-execute bash tool calls when they encounter config-get subshell patterns.
Values are now bundled into the init plan-phase JSON so step 15 of
plan-phase.md can read them directly without separate shell calls.
Closes#2192
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
- Build completedNums from current milestone phases as before
- Also scan full rawContent for [x]-checked Phase lines across all
milestone sections (including <details>-wrapped shipped milestones)
- Phases from prior milestones are complete by definition, so any
dep on them should always resolve to deps_satisfied: true
- Add regression tests in tests/init-manager-deps.test.cjs
Closes#2267
* test: guard ARCHITECTURE.md component counts against drift (#2258)
Add tests/architecture-counts.test.cjs — 3 tests that dynamically
verify the "Total commands/workflows/agents" counts in
docs/ARCHITECTURE.md match the actual *.md file counts on disk.
Both sides computed at runtime; zero hardcoded numbers.
Also corrects the stale counts in ARCHITECTURE.md:
- commands: 69 → 74
- workflows: 68 → 71
- agents: 24 → 31
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(init): remove literal ~/.claude/ from deprecated root identifiers to pass Cline path-leak test
The cline-install.test.cjs scans installed engine files for literal
~/.claude/(get-shit-done|commands|...) strings that should have been
substituted during install. Two deprecated-legacy entries added by #2261
used tilde-notation string literals for their root identifier, which
triggered this scan.
root is only a display/sort key — filesystem scanning always uses the
path property (already dynamic via path.join). Switching root to the
relative form '.claude/get-shit-done/skills' and '.claude/commands/gsd'
satisfies the Cline path-leak guard without changing runtime behaviour.
Update skill-manifest.test.cjs assertion to match the new root format.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
When a new milestone reuses a phase number that exists in an archived
milestone (e.g., v2.0 Phase 2 while v1.0-phases/02-old-feature exists),
findPhaseInternal falls through to the archive and returns the old
phase. init plan-phase and init execute-phase then emitted archived
values for phase_dir, phase_slug, has_context, has_research, and
*_path fields, while phase_req_ids came from the current ROADMAP —
producing a silent inconsistency that pointed downstream agents at a
shipped phase from a previous milestone.
cmdInitPhaseOp already guarded against this (see lines 617-642);
apply the same guard in cmdInitPlanPhase, cmdInitExecutePhase, and
cmdInitVerifyWork: if findPhaseInternal returns an archived match
and the current ROADMAP.md has the phase, discard the archived
phaseInfo so the ROADMAP fallback path produces clean values.
Adds three regression tests covering plan-phase, execute-phase, and
verify-work under the shared-number scenario.
* test(2129): add failing tests for 999.x backlog phase exclusion
Bug A: phase complete reports 999.1 as next phase instead of 3
Bug B: init manager returns all_complete:false when only 999.x is incomplete
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(2129): exclude 999.x backlog phases from next-phase scan and all_complete check
In cmdPhaseComplete, backlog phases (999.x) on disk were picked as the
next phase when intervening milestone phases had no directory yet. Now
the filesystem scan skips any directory whose phase number starts with 999.
In cmdInitManager, all_complete compared completed count against the full
phase list including 999.x stubs, making it impossible to reach true when
backlog items existed. Now the check uses only non-backlog phases.
Closes#2129
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* test(2123): add failing tests for TDD init JSON exposure and --tdd flag
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat(2123): expose tdd_mode in init JSON and add --tdd flag override
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Add a new pattern mapper agent that analyzes the codebase for existing
patterns before planning, producing PATTERNS.md with per-file analog
assignments and code excerpts. Integrated into plan-phase workflow as
Step 7.8 (between research and planning), controlled by the
workflow.pattern_mapper config key (default: true).
Changes:
- New agent: agents/gsd-pattern-mapper.md
- New config key: workflow.pattern_mapper in VALID_CONFIG_KEYS and CONFIG_DEFAULTS
- init plan-phase: patterns_path field in JSON output
- plan-phase.md: Step 7.8 spawns pattern mapper, PATTERNS_PATH in planner files_to_read
- gsd-plan-checker.md: Dimension 12 (Pattern Compliance)
- model-profiles.cjs: gsd-pattern-mapper profile entry
- Tests: tests/pattern-mapper.test.cjs (5 tests)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Adds `skill-manifest` command that scans a skills directory, extracts
frontmatter and trigger conditions from each SKILL.md, and outputs a
compact JSON manifest. This reduces per-agent skill discovery from 36
Read operations (~6,000 tokens) to a single manifest read (~1,000 tokens).
Closes#1976
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Review feedback from @trek-e — three blocking issues and one style fix:
1. **Symlink escape guard** — Added validatePath() call on the resolved
global skill path with allowAbsolute: true. This routes the path
through the existing symlink-resolution and containment logic in
security.cjs, preventing a skill directory symlinked to an arbitrary
location from being injected. The name regex alone prevented
traversal in the literal name but not in the underlying directory.
2. **5 new tests** covering the global: code path:
- global:valid-skill resolves and appears in output
- global:invalid!name rejected by regex, skipped without crash
- global:missing-skill (directory absent) skipped gracefully
- Mix of global: and project-relative paths both resolve
- global: with empty name produces clear warning and skips
3. **Explicit empty-name guard** — Added before the regex check so
"global:" produces "empty skill name" instead of the confusing
'Invalid global skill name ""'.
4. **Style fix** — Hoisted require('os') and globalSkillsBase
calculation out of the loop, alongside the existing validatePath
import at the top of buildAgentSkillsBlock.
All 16 agent-skills tests pass.
Add global: prefix for agent_skills config entries that resolve to
~/.claude/skills/<name>/SKILL.md instead of the project root. This
allows injecting globally-installed skills (e.g., shadcn, supabase)
into GSD sub-agents without duplicating them into every project.
Example config:
"agent_skills": {
"gsd-executor": ["global:shadcn", "global:supabase-postgres"]
}
Security: skill names are validated against /^[a-zA-Z0-9_-]+$/ to
prevent path traversal. The ~/.claude/skills/ directory is a trusted
runtime-controlled location. Project-relative paths continue to use
validatePath() containment checks as before.
Closes#1992
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
cmdInitManager called fs.readdirSync(phasesDir) and compiled a new
RegExp inside the per-phase while loop. At 50 phases this produced
50 redundant directory scans and 50 regex compilations with full
ROADMAP content scans.
Move the directory listing before the loop and pre-extract all
checkbox states via a single matchAll pass. This reduces both
patterns from O(N^2) to O(N).
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat(state): add programmatic gates for STATE.md consistency
Adds four enforcement gates to prevent STATE.md drift:
- `state validate`: detects drift between STATE.md and filesystem
- `state sync`: reconstructs STATE.md from actual project state
- `state planned-phase`: records state after plan-phase completes
- Performance Metrics update in `phase complete`
Also fixes ghost `state update-position` command reference in
execute-phase.md (command didn't exist in CLI dispatcher).
Closes#1627
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(state): By Phase table regex ate next section when table body was empty
The lazy [\s\S]*? with a $ lookahead in byPhaseTablePattern would
match past blank lines and capture the next ## section header as table
body when no data rows existed. Replaced with a precise row-matching
pattern ((?:[ \t]*\|[^\n]*\n)*) that only captures pipe-delimited
lines. Added regression assertion to verify row placement.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat(i18n): add response_language config for cross-phase language consistency
Adds `response_language` config key that propagates through all init
outputs via withProjectRoot(). Workflows read this field and instruct
agents to present user-facing questions in the configured language,
solving the problem of language preference resetting at phase boundaries.
Usage: gsd-tools config-set response_language "Portuguese"
Closes#1399
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* test(security): allowlist discuss-phase.md for size threshold
discuss-phase.md legitimately exceeds 50K chars due to power mode
and i18n directives — not prompt stuffing.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: replace /gsd: command format with /gsd- skill format in all suggestions
All next-step suggestions shown to users were still using the old colon
format (/gsd:xxx) which cannot be copy-pasted as skills. Migrated all
occurrences across agents/, commands/, get-shit-done/, docs/, README files,
bin/install.js (hardcoded defaults for claude runtime), and
get-shit-done/bin/lib/*.cjs (generate-claude-md templates and error messages).
Updated tests to assert new hyphen format instead of old colon format.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: migrate remaining /gsd: format to /gsd- in hooks, workflows, and sdk
Addresses remaining user-facing occurrences missed in the initial migration:
- hooks/: fix 4 user-facing messages (pause-work, update, fast, quick)
and 2 comments in gsd-workflow-guard.js
- get-shit-done/workflows/: fix 21 Skill() literal calls that Claude
executes directly (installer does not transform workflow content)
- sdk/prompt-sanitizer.ts: update regex to strip /gsd- format in addition
to legacy /gsd: format; update JSDoc comment
- tests/: update autonomous-ui-steps, prompt-sanitizer to assert new format
Note: commands/gsd/*.md frontmatter (name: gsd:xxx) intentionally unchanged
— installer derives skillName from directory path, not the name field.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(plan-phase): preserve --chain flag in auto-advance sync and handle ui-phase gate in chain mode
Bug 1: step 15 sync-flag check only guarded against --auto, causing
_auto_chain_active to be cleared when plan-phase is invoked without
--auto in ARGUMENTS even though a --chain pipeline was active. Added
--chain to the guard condition, matching discuss-phase behaviour.
Bug 2: UI Design Contract gate (step 5.6) always exited the workflow
when UI-SPEC was missing, breaking the discuss --chain pipeline
silently. When _auto_chain_active is true, the gate now auto-invokes
gsd-ui-phase --auto via Skill() and continues to step 6 without
prompting. Manual invocations retain the existing AskUserQuestion flow.
* fix: remove <sub>/clear</sub> pattern and duplicate old-format command in discuss-phase.md
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* fix(phase-resolution): use exact token matching instead of prefix matches
Closes#1635
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(phase-resolution): add case-insensitive flag to project-code strip regex
The strip regex in phaseTokenMatches lacked the `i` flag, so lowercase
project-code prefixes (e.g. `ck-01-name`) were not stripped during the
fallback comparison. This made `phaseTokenMatches('ck-01-name', '01')`
return false when it should return true.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
- fix(#1572): phase complete now marks bold-wrapped plan checkboxes in ROADMAP.md
(`- [ ] **01-01**` format) by allowing optional `**` around plan IDs in the
planCheckboxPattern regex in both phase.cjs and roadmap.cjs
- fix(#1569): manager init no longer recommends 999.x (BACKLOG) phases as next
actions; add guard in cmdManagerInit that skips phases matching /^999(?:\.|$)/
- fix(#1568): add regression tests confirming init execute-phase respects
model_overrides for executor_model, including when resolve_model_ids is 'omit'
- fix(#1533): reject session_id values containing path traversal sequences
(../, /, \) in gsd-context-monitor and gsd-statusline before constructing
/tmp file paths; add security tests covering both hooks
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Detect runtime from execution_context path or env vars at workflow start,
then set INSTRUCTION_FILE (AGENTS.md for Codex, CLAUDE.md for all others).
Pass --output $INSTRUCTION_FILE to generate-claude-md so the helper writes
to the correct file instead of always defaulting to CLAUDE.md.
Also add .codex to skipDirs in init.cjs so Codex runtime directories are
not mistaken for project content during brownfield codebase analysis.
Closes#1521
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Address review feedback: sanitize manager.flags values to allow only
CLI-safe tokens (--flag patterns and alphanumeric values). Invalid
tokens are dropped with a stderr warning. Prevents prompt injection
via compromised config.json.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Adds `manager.flags.{discuss,plan,execute}` config keys so users can
configure flags that /gsd:manager passes to each step when dispatching.
For example, `manager.flags.discuss: "--auto --analyze"` makes every
discuss dispatched from the manager include those flags.
Closes#1400
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The map-codebase workflow had a hardcoded 300000ms (5 minute) timeout
for parallel subagent tasks. On large codebases or with slower models
(e.g. GPT via Codex), subagents can need 10-20+ minutes, causing the
parent to kill still-working agents and fall back to sequential mode.
Changes:
- Add workflow.subagent_timeout config key (default: 300000ms)
- Register in VALID_CONFIG_KEYS (config.cjs)
- Add to loadConfig() defaults and return object (core.cjs)
- Emit in map-codebase init context (init.cjs)
- Update map-codebase.md to use config value instead of hardcoded 300000
- Document in planning-config.md reference
Users can now increase the timeout via:
/gsd:settings workflow.subagent_timeout 900000
Closes#1472
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
