process.stdout.write() is async when stdout is a pipe. The
immediate process.exit(0) tears down the process before the
downstream reader (jq, python3, etc) consumes the buffer,
producing truncated JSON.
Replace with fs.writeSync(1, data) which blocks until the
kernel pipe buffer accepts the bytes, and drop process.exit(0)
on the success path so the event loop drains naturally.
Fixes#1275
Related: #493 (addressed >50KB case, this fixes <50KB)
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>
After gathering milestone goals and determining version, the workflow
now presents a summary and asks for confirmation before writing any
files. Users can adjust until satisfied, preventing the previous
behavior where GSD would immediately write PROJECT.md without verifying
its understanding of the milestone scope.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Test that has_reviews=true and reviews_path is set when REVIEWS.md exists
- Test that reviews_path is undefined and has_reviews=false when missing
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
On Windows, os.homedir() reads USERPROFILE, not HOME. Tests pass HOME
override for sandboxing. Use process.env.HOME with os.homedir() fallback
so tests work cross-platform.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Three new commands for managing isolated GSD workspaces:
- /gsd:new-workspace — create workspace with repo worktrees/clones
- /gsd:list-workspaces — scan ~/gsd-workspaces/ for active workspaces
- /gsd:remove-workspace — clean up workspace and git worktrees
Supports both multi-repo orchestration (subset of repos from a parent
directory) and feature branch isolation (worktree of current repo with
independent .planning/).
Includes init functions, command routing, workflows, 24 tests, and
user documentation.
Closes#1241
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Physical workspace model with three commands: new-workspace,
list-workspaces, remove-workspace. Supports both multi-repo
orchestration and same-repo feature branch isolation.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Teaches the debugger agent to trace path/URL/key construction across
producer and consumer code — prevents shallow investigation that misses
directory mismatches like the stale hooks bug (#1249).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
gsd-check-update.js looked for hooks in configDir/hooks/ (e.g.,
~/.claude/hooks/) but the installer writes hooks to
configDir/get-shit-done/hooks/. This mismatch caused false stale
hook warnings that persisted even after updating.
Also clears the update cache during install so the next session
re-evaluates hook versions with the correct path.
Closes#1249
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Wire the --reviews flag through the full stack so plan-phase can
replan incorporating cross-AI review feedback from REVIEWS.md:
- core.cjs: add has_reviews detection in searchPhaseInDir
- init.cjs: wire has_reviews and reviews_path through all init functions
- plan-phase.md command: add --reviews to argument-hint and flags
- plan-phase.md workflow: add step 2.5 validation, skip research,
skip existing plans prompt, pass reviews_path to planner
- gsd-planner.md: add reviews_mode section for consuming review feedback
- COMMANDS.md: add --reviews and missing flags to docs
Closes the gap where --reviews was referenced in 6 places (review
workflow, review command, help workflow, COMMANDS.md, FEATURES.md)
but never implemented.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
core.cjs output() created gsd-*.json files in /tmp for large payloads
but never cleaned them up, causing unbounded disk usage (800+ GB
reported in #1251). Similarly, profile-pipeline.cjs created
gsd-pipeline-* and gsd-profile-* temp directories without cleanup.
Adds reapStaleTempFiles() that removes gsd-prefixed temp files/dirs
older than 5 minutes. Called opportunistically before each new temp
file/dir creation. Non-critical — cleanup failures never break output.
Closes#1251
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add CLAUDE.md enforcement across the three core agents:
- gsd-plan-checker: new Dimension 10 verifies plans respect project
conventions, forbidden patterns, and required tools from CLAUDE.md
- gsd-phase-researcher: outputs Project Constraints section from
CLAUDE.md so planner can verify compliance
- gsd-executor: treats CLAUDE.md directives as hard constraints,
with precedence over plan instructions
Includes 4 regression tests validating the new dimension and
enforcement directives across all three agents.
Closes#1260
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
syncStateFrontmatter() rebuilds YAML frontmatter from the body on every
writeStateMd() call. If an agent removes or omits the Status: field from
the body, buildStateFrontmatter() defaults to 'unknown', overwriting a
previously valid status (e.g., 'executing').
Fix: read existing frontmatter before stripping, and preserve its status
value when the body-derived status would be 'unknown'. This makes
frontmatter self-healing — once a status is set, it persists even if the
body loses the field.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
ensureConfigFile(): keep our refactored version that delegates to
buildNewProjectConfig({}) instead of upstream's duplicated logic.
buildNewProjectConfig(): add firecrawl and exa_search API key
detection alongside existing brave_search, matching upstream's
new integrations.
Decisions in CONTEXT.md are now numbered (D-01, D-02, etc.) so
downstream agents can reference them and the plan-checker can verify
100% coverage.
Changes:
- templates/context.md: Decisions use **D-XX:** prefix format
- workflows/discuss-phase.md: write_context step numbers decisions
- agents/gsd-planner.md: Self-check verifies decision ID references
in task actions; tasks reference D-XX IDs for traceability
- agents/gsd-plan-checker.md: Dimension 7 (Context Compliance)
extracts D-XX IDs and verifies every decision has a task
Enhanced gsd-verifier's anti-pattern detection to catch:
- Hardcoded empty data props (={[]}, ={{}}, ={null})
- 'not available' and 'not yet implemented' placeholder text
- Data stub classification guidance (only flag when value flows
to rendering without a data-fetching path)
Added stub tracking to gsd-executor's summary creation:
- Before writing SUMMARY, scan files for stub patterns
- Document stubs in a '## Known Stubs' section
- Block plan completion if stubs prevent the plan's goal
The gsd-context-monitor PostToolUse hook was configured without a
matcher or timeout, causing it to fire on every tool use including
Read, Glob, and Grep. When multiple Read calls happen in parallel,
some hook processes failed with errors.
Added matcher: 'Bash|Edit|Write|MultiEdit|Agent|Task' to limit the
hook to tools that actually modify context significantly. Added
timeout: 10 to prevent hangs.
Includes migration logic: existing installations without matcher/timeout
get them added on next /gsd:update.
gsd-workflow-guard.js was missing the // gsd-hook-version: {{GSD_VERSION}}
header that all other hook files have. The stale hook detection in
gsd-check-update.js scans all gsd-*.js files for this header and flags
any without it as stale (hookVersion: 'unknown'). This caused a
persistent '⚠ stale hooks — run /gsd:update' warning in the statusline
even on the latest version.
Added the version header to gsd-workflow-guard.js. Running /gsd:update
will reinstall the hook with the correct version stamp.
loadConfig() defaulted commit_docs to true regardless of whether
.planning/ was gitignored. The documented auto-detection only existed
inside cmdCommit, so init commands returned commit_docs: true even
when .planning/ was in .gitignore. This caused LLM executors to
bypass the cmdCommit gate and re-commit planning files with raw git.
Now loadConfig() checks isGitIgnored(cwd, '.planning/') when no
explicit commit_docs value is set in config.json. If .planning/ is
gitignored, commit_docs defaults to false. An explicit commit_docs
value in config.json is always respected.
Added 5 regression tests covering auto-detection, explicit overrides,
and the no-config-file edge case.
cmdInitPlanPhase, cmdInitExecutePhase, and cmdInitVerifyWork returned
phase_found: false when the phase existed in ROADMAP.md but no phase
directory had been created yet. This caused workflows to fail silently
after /gsd:new-project, producing directories named null-null.
cmdInitPhaseOp (used by discuss-phase) already had a ROADMAP fallback.
Applied the same pattern to the three missing commands: when
findPhaseInternal returns null, fall back to getRoadmapPhaseInternal
and construct phaseInfo from the ROADMAP entry.
Added 5 regression tests covering:
- plan-phase ROADMAP fallback
- execute-phase ROADMAP fallback
- verify-work ROADMAP fallback
- phase_found false when neither directory nor ROADMAP entry exists
- disk directory preferred over ROADMAP fallback
