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>
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)
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>
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>
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>
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
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
Integrate Exa (semantic search) and Firecrawl (deep web scraping) as
MCP-based research tools, following the existing Brave Search pattern.
- Add tool declarations to all 3 researcher agents
- Add tool strategy sections with usage guidance and priority
- Add config detection for FIRECRAWL_API_KEY and EXA_API_KEY env vars
- Add firecrawl/exa_search config keys to core defaults and init output
- Update source priority hierarchy across all researchers
The stats workflow was the only file using $GSD_TOOLS, which is never
defined anywhere. This caused the LLM to improvise the path at runtime,
producing the wrong directory (tools/) and extension (.mjs) instead of
the correct bin/gsd-tools.cjs used by all other workflows.
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Adds an optional advisor mode to discuss-phase that provides research-backed
comparison tables before asking users to make decisions. Activates when
USER-PROFILE.md exists, degrades gracefully otherwise.
New agent: gsd-advisor-researcher -- spawned in parallel per gray area,
returns structured 5-column comparison tables calibrated to the user vendor
philosophy preference (full_maturity/standard/minimal_decisive).
Workflow changes (discuss-phase.md):
- Advisor mode detection in analyze_phase step
- New advisor_research step spawns parallel research agents
- Table-first discussion flow in discuss_areas when advisor mode active
- Standard conversational flow unchanged when advisor mode inactive
VALID_CONFIG_KEYS: merge our additions (workflow.auto_advance,
workflow.node_repair, workflow.node_repair_budget, hooks.context_warnings)
with upstream's additions (workflow.text_mode, git.quick_branch_template).
ensureConfigFile(): keep our refactored version that delegates to
buildNewProjectConfig({}) instead of upstream's duplicated logic.
buildNewProjectConfig(): add git.quick_branch_template: null and
workflow.text_mode: false to match upstream's new keys.
new-project.md: integrate upstream's Step 5.1 Sub-Repo Detection
after our commit block; drop upstream's duplicate Note (ours at
line 493 is more detailed).
1. Gate findProjectRoot to commands that access .planning/ — skip for
pure-utility commands (generate-slug, current-timestamp, template,
frontmatter, verify-path-exists, verify-summary) to avoid unnecessary
filesystem traversal on every invocation.
2. Warn to stderr when commit-to-subrepo encounters files that don't
match any configured sub-repo prefix.
3. Document that loadConfig auto-syncs sub_repos with the filesystem,
so config.json may be rewritten when repos are added or removed.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The workflow set commit_docs to false for multi-repo workspaces then
immediately ran gsd-tools commit on config.json, which would be
skipped. Replace with a note that config changes are local-only.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- findProjectRoot: use isInsideGitRepo() to walk up and find .git in
ancestor dirs, fixing nested paths like backend/src/modules/
- Add sub_repos to cmdInitExecutePhase output so execute-plan.md and
gsd-executor.md can route commits correctly
- Align new-project.md sub-repo detection to maxdepth 1 matching
detectSubRepos() behavior
- Add 3 nested path tests for .git heuristic, sub_repos, and multiRepo
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add support for workspaces with multiple independent git repositories.
When configured, GSD routes commits to the correct sub-repo and ensures
.planning/ stays at the project root.
Core features:
- detectSubRepos(): scans child directories for .git to discover repos
- findProjectRoot(): walks up from CWD to find the project root that
owns .planning/, preventing orphaned .planning/ in sub-repos
- loadConfig auto-syncs sub_repos when repos are added or removed
- Migrates legacy "multiRepo: true" to sub_repos array automatically
- All init commands include project_root in output
- cmdCommitToSubrepo: groups files by sub-repo prefix, commits independently
Zero impact on single-repo workflows — sub_repos defaults to empty array.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Refactoring:
- Extract stateReplaceFieldWithFallback() to state.cjs as single source of truth
for the try-primary-then-fallback pattern that was duplicated inline across
phase.cjs, milestone.cjs, and state.cjs
- Replace all inline bold-only regex patterns in cmdPhaseComplete with shared
stateReplaceField/stateExtractField helpers — now supports both **Bold:**
and plain Field: STATE.md formats (fixes the same bug as #924)
- Replace inline bold-only regex patterns in cmdMilestoneComplete with shared helpers
- Replace inline bold-only regex for Completed Phases/Total Phases/Progress
counters in cmdPhaseComplete with stateExtractField/stateReplaceField
- Replace inline bold-only Total Phases regex in cmdPhaseRemove with shared helpers
Security:
- Fix command injection surface in isGitIgnored (core.cjs): replace execSync with
string concatenation with execFileSync using array arguments — prevents shell
interpretation of special characters in file paths
Tests (7 new):
- 5 tests for stateReplaceFieldWithFallback: primary field, fallback, neither,
preference, and plain format
- 1 regression test: phase complete with plain-format STATE.md fields
- 1 regression test: milestone complete with plain-format STATE.md fields
854 tests pass (was 847). No behavioral regressions.
- Add resolveWorktreeRoot() that detects linked worktrees via
git rev-parse --git-common-dir and resolves to the main worktree
where .planning/ lives
- Add withPlanningLock() file-based locking mechanism to prevent
concurrent worktrees from corrupting shared planning files
- Wire worktree root resolution into gsd-tools.cjs main entry point
- Add regression tests for resolveWorktreeRoot (non-git, normal repo)
and withPlanningLock (normal execution, error cleanup, stale lock
recovery)
When check-todos moves a file from pending/ to done/, the commit only
staged the new destination. The deletion of the source was never staged
because `git add` on a non-existent path is a no-op. Now we detect
missing files and use `git rm --cached` to stage the deletion.
Closes#1228
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The regex-based table parser captured a fixed number of columns,
so 5-column tables (Phase | Milestone | Plans | Status | Completed)
had the Milestone column eaten and Status/Date written to wrong cells.
Replaced regex with cell-based `split('|')` parsing that detects
column count (4 or 5) and updates the correct cells by index.
Affects both `cmdRoadmapUpdatePlanProgress` and `cmdPhaseComplete`.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The summary template puts the one-liner as a `**bold**` line after the
`# Phase N` heading, but `cmdSummaryExtract` and `cmdMilestoneComplete`
only checked frontmatter `one-liner` field — which is often empty.
Adds `extractOneLinerFromBody()` to core.cjs as a fallback that parses
the first `**...**` line after the heading.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
`cmdStateAdvancePlan` expected separate `Current Plan` and
`Total Plans in Phase` fields, but the current STATE.md template
uses a single compound field: `Plan: X of Y in current phase`.
Now tries legacy separate fields first, then falls back to parsing
the compound format. Preserves the compound format when writing back
(replaces only the plan number). Also handles `Last activity`
(lowercase) field name from current template.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Generate {phase_num}-DISCUSSION-LOG.md alongside CONTEXT.md during
discuss-phase sessions
- Log captures all options presented per gray area (not just the
selected one), user's choice, notes, Claude's discretion items,
and deferred ideas
- File is explicitly marked as audit-only — not for agent consumption
- Add discussion-log.md template with format specification
- Track Q&A data accumulation instruction in discuss_areas step
- Commit discussion log alongside CONTEXT.md in same git commit
- Add regression tests for workflow reference and template existence
