MAJOR (security/correctness):
- commands/gsd/debug.md: add Write to allowed-tools (session file creation
requires it — workflow explicitly says 'use Write tool, never heredoc')
- workflows/debug.md: add SLUG sanitization guard to steps 1b+1c (status/
continue subcommands used raw user input in file paths — path traversal)
- workflows/thread.md: sanitize $ARGUMENTS in RESUME mode before file path
construction (was bypassing the sanitization guard in CLOSE/STATUS modes)
MINOR (consistency/correctness):
- docs/INVENTORY-MANIFEST.json: remove stale top-level 'workflows' array
(duplicate of families.workflows introduced in earlier update)
- commands/gsd/resume-work.md: normalize process to 'Execute end-to-end.'
- commands/gsd/settings.md: normalize process to 'Execute end-to-end.'
- commands/gsd/update.md: normalize otherwise branch to 'execute end-to-end.'
- docs/adr/0002: add Status: Accepted + Date header (ADR convention)
- workflows/extract-learnings.md: rename step extract_learnings → extract-learnings
- tests/extract-learnings.test.cjs: tighten step-name assertion to exact name
ARCHITECTURE:
- scripts/command-contract-helpers.cjs: extract CANONICAL_TOOLS, parseFrontmatter,
executionContextRefs as shared module — single source of truth consumed by
both lint script and test suite (prevents silent lint/test disagreement)
- scripts/lint-command-contract.cjs: require() helpers instead of duplicating
- tests/command-contract.test.cjs: require() helpers; move readFileSync calls
inside test() callbacks (registration-time throws surface as named failures)
After extracting debug.md and thread.md implementations to workflow files
and renaming extract_learnings.md, existing tests still referenced the
old locations:
- debug-session-management.test.cjs: commands/gsd/debug.md → workflows/debug.md
- thread-session-management.test.cjs: commands/gsd/thread.md → workflows/thread.md
- extract-learnings.test.cjs: extract_learnings.md → extract-learnings.md
- enh-2430-learnings-consumption.test.cjs: extract_learnings.md → extract-learnings.md
Also adds <available_agent_types> block and TEXT_MODE fallback note to
get-shit-done/workflows/debug.md to satisfy the spawn-type-consistency
(#1357) and AskUserQuestion text-mode fallback (#2012) contract tests
that scan all workflow files.
- Skill consolidation gap class: missing workflow files, detection via regression test
- CodeRabbit stale thread resolution pattern after allow-test-rule fixes
- PR discipline: split unrelated changes, one concern per PR
- INVENTORY.md must stay in sync with workflow filesystem on every add/remove
- README: storyline-only target, MD001/MD040 markdownlint rules to watch
- Issue triage: always check local branches for crash-recovery before re-implementing
- SDK-only verbs: golden-policy NO_CJS_SUBPROCESS_REASON exemption required
* fix(#3121): implement commands verb in SDK native registry
- Add commandsList handler — returns sorted JSON array of all registered
verb strings; satisfies workstream-flag.md + agent tooling discoverability
- Register ['commands', commandsList] in DECISION_ROUTING_STATIC_CATALOG
- Add golden-policy exemption (SDK-only, no CJS mirror needed)
- check.decision-coverage-plan/verify were already registered; commands was the remaining gap
Closes#3121
* fix(#3135): restore workflows/add-backlog.md — capture --backlog had no workflow to load
Root cause: PR #2824 consolidated add-backlog into gsd-capture --backlog and
wired capture.md to delegate to workflows/add-backlog.md via execution_context.
The workflow file was never created (same gap class as reapply-patches.md which
was caught and fixed in the same PR). With no file to load, the agent had no
implementation steps to follow when --backlog was invoked.
Fix:
- Restore get-shit-done/workflows/add-backlog.md with full process from deleted
commands/gsd/add-backlog.md (phase.next-decimal, ROADMAP write, mkdir, commit)
- Preserve #2280 ordering invariant: ROADMAP entry written before directory
- Fix docs/INVENTORY.md: remove incorrect attribution of --backlog to add-todo.md,
add add-backlog.md row, bump workflow count 84→85
- Update docs/INVENTORY-MANIFEST.json
- Add regression test: every execution_context @-reference in commands/gsd/*.md
must resolve to an existing workflow file on disk
Closes#3135
* fix(#3127): make state.begin-phase idempotent on mid-flight phases
Root cause: cmdStateBeginPhase() unconditionally overwrote execution-
progress fields regardless of current phase status. When execute-phase
called it on a phase already mid-flight (--wave N resume), it regressed:
- Current Plan to 1 (from e.g. 3)
- Last Activity Description to 'context gathered; ready for plan-phase'
- Plan: N of M body line to 'Plan: 1 of M'
- last_updated timestamp to an older value
- progress.percent could decrease
Fix: read Status field before writing. If phase is already executing
(Status: Executing Phase N), skip execution-progress fields and only
update fields safe on resume:
- Last Activity date (always safe)
- Resume-specific 'execution resumed (wave continue)' activity line
First-time execution (Status != Executing Phase N) writes all fields
as before -- no regression on the normal path.
Regression test: 4 real unit tests using synthetic STATE.md files:
- mid-flight phase does not reset Current Plan (was the bug)
- mid-flight phase does not overwrite stopped_at narrative
- fresh phase sets Current Plan to 1 (normal path, no regression)
- both paths update Last Activity date (safe field)
Suite: 6990/6990. Closes#3127.
* fix(lint+state): allow-test-rule, escapeRegex phaseNumber in idempotency guard
* fix(#3097, #3099): add cwd-drift + absolute-path guards to executor worktree protocol
#3097 — cwd-drift sentinel (gsd-executor.md task_commit_protocol step 0a):
A Bash cd out of the worktree makes [ -f .git ] false, silently skipping
all HEAD/branch safety guards. Commits land on main's branch.
Fix: on first commit, capture spawn-time toplevel into sentinel file at
.git/worktrees/<name>/gsd-spawn-toplevel. Before every subsequent commit,
verify ACTUAL_TL matches EXPECTED_TL. Exits 1 with recovery instructions
if drift detected.
#3099 — absolute-path guard (gsd-executor.md task_commit_protocol step 0b):
Absolute paths constructed from the orchestrator's pwd (main repo root)
resolve to the main repo inside worktrees. Edit/Write lands in wrong dir;
git commit sees a clean worktree tree; work silently lost or leaks to main.
Fix: before any absolute-path Edit/Write, verify path starts with
WT_ROOT=/Users/thbouc/projects/get-shit-done. Prefer relative paths.
Both guards are documented in references/worktree-path-safety.md, which
is now loaded into every executor spawn prompt via <execution_context>.
The <worktree_branch_check> footnote references all three steps (0/0a/0b).
execute-phase.md: extracted worktree bash commands to reference file
(safe embed — @ files are inlined before the executor processes the prompt).
The blank line in <required_reading> was removed to stay at the XL=1700 line
budget after adding the @ reference.
Suite: 6986/6986. Closes#3097. Closes#3099.
* fix(lint+executor+docs): allow-test-rule, fix [ -f .git ] guard, fail-closed abs-path check, fix INVENTORY count
* fix(#3096): enforce sequential Steps 7+8 + Edit-only discipline in ai-integration-phase
Root cause: Steps 7 (gsd-ai-researcher) and 8 (gsd-domain-researcher)
were listed without an explicit sequential constraint. An orchestrator
optimizing for speed could parallelize them since sections appeared
disjoint. gsd-domain-researcher's Write at finalization replaced the
full AI-SPEC.md with its in-memory copy (pre-researcher state), losing
Sections 3/4. Confirmed at 40% incidence (2/5 agents on a real run).
Recovery cost: one extra ai-researcher dispatch, ~18 min wall.
Fix:
- Explicit 'MUST run sequentially' note on Step 7 (ordering note)
- 'Wait for Step 7 to complete before spawning Step 8' on Step 8
- Edit-only tool discipline injected into both agent prompts:
'Use Edit exclusively - NEVER use Write on this file'
prevents the last-writer-wins overwrite regardless of dispatch order
Suite: 7043/7043. Closes#3096.
* fix(lint): allow-test-rule for ai-integration-phase structural contract test
* fix(#3120): add register_authored_at_plan_time guard to secure-phase
Root cause: Step 3 short-circuit used threats_open: 0 as the sole
condition to skip directly to Step 6 (write clean SECURITY.md). It
did not distinguish empty-by-all-mitigated from empty-by-no-planning.
Legacy phases authored before <threat_model> blocks were canonical
received a rubber-stamped clean SECURITY.md with no audit performed.
Fix:
Step 2c: track register_authored_at_plan_time (true iff >=1 PLAN
file contained a parseable <threat_model> block)
Step 3: two-condition short-circuit:
- threats_open:0 AND register_authored_at_plan_time:true
-> skip to Step 6 (legitimate, all mitigated)
- threats_open:0 AND register_authored_at_plan_time:false
-> retroactive-STRIDE mode in Step 5 (build register
from implementation, then verify)
Step 5: auditor constraint varies by mode:
planned -> Verify mitigations exist, do not scan
retroactive -> Build STRIDE register first, then verify
Suite: 7039/7039. Closes#3120.
* fix(lint+changeset): allow-test-rule, drop dead regex branches, fix pr field to 3142
* fix(#3129): replace bypassed bash regex with token-walk git-cmd.js classifier
Root cause: gsd-validate-commit.sh used:
if [[ "$CMD" =~ ^git[[:space:]]+commit ]]
This regex silently bypasses Conventional Commits enforcement for:
git -C /path commit -m ... (working-directory prefix)
GIT_AUTHOR_NAME=x git commit (env-var prefix)
/usr/bin/git commit -m ... (full-path executable)
Fix: introduces hooks/lib/git-cmd.js with isGitSubcommand(cmd, sub) —
a token-walk classifier that handles all four forms by:
1. Skipping leading VAR=VALUE env assignments
2. Validating the git executable (basename check for full-path support)
3. Consuming git global options (-C <path>, --git-dir=, -p, etc.)
4. Checking the subcommand token
The hook delegates to this classifier via node shell-out. node is
already called twice in this hook (config check + JSON parse), so no
new runtime dependency.
This becomes the single source of truth for all hooks that gate on
git subcommands (pre-commit-review-gate, post-push-verify, etc.).
Regression test: 27 assertions — tokenize correctness, 12 must-match
cases (including all 3 bypass forms), 8 must-not-match cases, 3 source
checks. All are real behavioral tests, not string comparisons.
Suite: 7035/7035. Closes#3129.
* fix(lint+hook+changeset): allow-test-rule, fix HOOK_DIR quote injection, fix changeset pr+typo
* fix(#3128): extend roadmap.cjs plan-count to match {N}-PLAN-{NN}-{slug}.md
Root cause: same regex flaw as #2893 (fixed in phase.cjs by #2896).
The manager-dashboard countPhasePlansAndSummaries() in roadmap.cjs was
not updated alongside the phase.cjs fix. Files like 5-PLAN-01-setup.md
end in -setup.md, not -PLAN.md, so plan_count returned 0.
Symptom: init manager returned plan_count=0 / disk_status=discussed for
fully-planned phases, triggering redundant background planner agents that
correctly detected existing plans and declined -- wasted runs.
Fix: apply the same looksLikePlanFile pattern from phase.cjs with
PLAN-OUTLINE and pre-bounce exclusions to countPhasePlansAndSummaries.
Regression test: tests/bug-3128-roadmap-plan-count-slug-layout.test.cjs
Suite: 6985/6985. Closes#3128.
* fix(lint): allow-test-rule for roadmap isPlanFile structural contract test
* fix(#3087): restore 10 demoted directive phrases in gsd-planner.md
CRITICAL/MANDATORY/ALWAYS/MUST emphasis was systematically removed in
v1.38.4 (PR #2489) without documentation. Conflicts with PR #2489's own
stated intent (sycophancy-hardening). Downstream effect: weaker adherence
to user decisions and requirement coverage in v1.38.4-v1.40.x.
Restored:
CRITICAL: User Decision Fidelity (heading)
CRITICAL: Never Simplify User Decisions (heading)
Multi-Source Coverage Audit (MANDATORY in every plan set)
Audit ALL four source types before finalizing
Discovery is MANDATORY unless you can prove...
ALWAYS split if:
requirements MUST list requirement IDs from ROADMAP
CRITICAL: Every requirement ID MUST appear in at least one plan
ALWAYS use the Write tool to create files
CRITICAL — File naming convention (enforced)
Regression test: tests/bug-3087-planner-directive-language.test.cjs
(10 assertions, one per restored directive — all pass).
Suite: 6983/6983. Closes#3087.
* fix(changeset+test): fix pr field to 3138, wrap readFileSync in try/catch
* fix(#3130): harden update.md npx invocations against cache-stale and token-routing
Two failure modes with the old form:
1. Cache-stale: npx serves a cached older version (no --package= flag)
2. Token-routing: Bash-tool wrapper misroutes @ token in package@tag spec
All three sibling invocations (local/global/unknown) now use:
npx -y --package=get-shit-done-cc@latest -- get-shit-done-cc $ARGS
--package= forces a fresh registry fetch; -- prevents token misrouting.
Also fixes the manual-update hint in the error-exit block.
Regression test: tests/bug-3130-update-npx-robust-invocation.test.cjs
Suite: 6973/6973 pass. Closes#3130.
* fix(lint): allow-test-rule for update.md structural contract test
Duplicate /gsd-help rows (caused by join-discord → help replacement
landing in tables that already had /gsd-help):
- Remove Discord-purpose duplicate row from README.md, README.ja-JP.md,
README.zh-CN.md, README.ko-KR.md, docs/zh-CN/README.md,
docs/zh-CN/USER-GUIDE.md, docs/ja-JP/USER-GUIDE.md,
docs/ko-KR/USER-GUIDE.md
- Remove orphaned Discord-only ### /gsd-help sections from
docs/ja-JP/COMMANDS.md and docs/ko-KR/COMMANDS.md
Gap-fix command precision (plan-milestone-gaps → audit-milestone --fix):
- README.ja-JP.md, README.ko-KR.md, README.zh-CN.md gap-fix rows
updated to /gsd-audit-milestone --fix
docs/COMMANDS.md: document --path <dir> for --from-gsd2 in table and
example block
docs/FEATURES.md:
- Add adaptive to /gsd-config --profile value set
- Add blank line before spike Produces table (MD058)
Suite: 6971/6971 pass
- discuss-phase --assumptions: add 'Stop here' + convert If→Otherwise
chain so the flag is an exclusive route (CodeRabbit major)
- import --from-gsd2: add 'Stop here' + convert final 'Execute...'
to 'Otherwise...' to prevent fall-through to standard import
(CodeRabbit major, inline comment)
- .changeset/rewire-orphaned-workflows-3131.md: add missing changeset
- discuss-phase --assumptions → list-phase-assumptions.md
- pause-work --report → session-report.md
- manager --analyze-deps → analyze-dependencies.md
- import --from-gsd2 → gsd-tools.cjs from-gsd2 CLI
TDD: 8 new assertions in enh-2790-skill-consolidation.test.cjs
(argument-hint presence + body dispatch reference per flag).
Confirmed RED before wiring, GREEN after. Full suite 6971/6971.
help.md updated with all four new flag forms to satisfy
bug-2954-help-md-slash-command-stubs parity test.
Closes#3131
* refactor(sdk): extract gsdtools transport seam with per-command policy
* fix(sdk): address CodeRabbit transport policy and timeout findings
* fix(sdk): harden raw transport formatting and raw-path coverage
* docs(en): update FEATURES/USER-GUIDE/COMMANDS for v1.40.0 surface
- FEATURES.md: append v1.40.0 section (#122 skill consolidation, #123
namespace meta-skills, #124 context-window guard, #125 phase-lifecycle
status-line read-side); add to TOC.
- USER-GUIDE.md: add slash-command form (hyphen vs colon) primer and
namespace routing primer; replace deleted slash forms in walkthroughs
(`/gsd-add-backlog`, `/gsd-plant-seed`, `/gsd-add-phase`,
`/gsd-set-profile`, `/gsd-list-workspaces`, etc.) with consolidated
forms (`/gsd-capture --backlog`, `/gsd-phase --insert`,
`/gsd-config --profile`, `/gsd-workspace --list`, etc.); fix
`/gsd-spike-wrap-up` and `/gsd-sketch-wrap-up` to flag form.
- COMMANDS.md: clarify Command Syntax (Gemini = colon form, others =
hyphen form); add Namespace Meta-Skills section with all six routers;
add `--context` to /gsd-health flag table.
Refs #3047
* docs(en): refresh INVENTORY/CLI-TOOLS/STATE-MD-LIFECYCLE for v1.40.0
- INVENTORY.md: workflow-row "Invoked by" column updated to point at
consolidated commands (`/gsd-phase` family, `/gsd-workspace --list`,
`/gsd-config --advanced/--integrations/--profile`,
`/gsd-sketch --wrap-up`, `/gsd-spike --wrap-up`); CLI-modules row for
`secrets.cjs` updated to `/gsd-config --integrations`. Command count
and namespace meta-skills section already reflect 65 shipped (= 59
consolidated sub-skills + 6 ns-* routers).
- CLI-TOOLS.md: add `validate context` row under Validation Commands
with the 60 %/70 % threshold envelope used by `/gsd-health --context`.
- STATE-MD-LIFECYCLE.md: flip status header from "proposed" to
"shipped in v1.40.0" since `parseStateMd()` and `formatGsdState()`
now read and render `active_phase`, `next_action`, `next_phases`,
and `progress`.
`docs/AGENTS.md` audited and verified clean — `gsd-code-fixer` row
already lists the correct `/gsd-code-review --fix` spawner; no
deleted-skill references found. `docs/INVENTORY-MANIFEST.json`
audited and verified clean — already enumerates the 65 commands
(including six ns-* routers) and contains no deleted slash forms.
Refs #3047
* docs(en): cleanup ARCHITECTURE/CONFIGURATION for v1.40.0
- ARCHITECTURE.md: split Commands install-target list to call out the
Gemini colon form (`/gsd:command-name`) vs hyphen form for every
other runtime. Add a new subsection covering two-stage hierarchical
routing via the six namespace meta-skills (#2792) and a paired note
on the MCP token-budget interaction so readers see the two big
per-turn cost levers in one place.
- CONFIGURATION.md: rewrite three references to the deleted
`/gsd-settings-advanced` and `/gsd-settings-integrations` slash
forms to use the consolidated `/gsd-config --advanced` /
`/gsd-config --integrations` invocations. Add a new "STATE.md
Frontmatter (Phase Lifecycle)" section documenting the four
optional fields (`active_phase`, `next_action`, `next_phases`,
`progress`) read by the v1.40 status-line, with a pointer to
STATE-MD-LIFECYCLE.md for the full reference.
`docs/manual-update.md` audited and verified clean — already documents
`/gsd-update --reapply` (the consolidated form), no reference to the
deleted `/gsd-reapply-patches`.
Refs #3047
* docs(i18n): mirror v1.40.0 slash-command rename into ja-JP/ko-KR/zh-CN/pt-BR
Mechanical token-level renames only — every reference to a deleted
micro-skill slash form is rewritten to the consolidated form on the
matching parent skill. No prose was machine-translated; new prose
sections (slash-form primer, namespace routing primer, v1.40 feature
entries, STATE.md frontmatter) were left for human translator
follow-up.
Renames applied uniformly across all four trees:
/gsd-add-todo, /gsd-add-note, /gsd-add-backlog,
/gsd-plant-seed, /gsd-check-todos → /gsd-capture[ --note|
--backlog|--seed|--list]
/gsd-add-phase, /gsd-insert-phase,
/gsd-remove-phase, /gsd-edit-phase → /gsd-phase[ --insert|
--remove|--edit]
/gsd-new-workspace, /gsd-list-workspaces,
/gsd-remove-workspace → /gsd-workspace[ --new|
--list|--remove]
/gsd-settings-advanced,
/gsd-settings-integrations,
/gsd-set-profile → /gsd-config[ --advanced|
--integrations|--profile]
/gsd-sketch-wrap-up → /gsd-sketch --wrap-up
/gsd-spike-wrap-up → /gsd-spike --wrap-up
/gsd-reapply-patches → /gsd-update --reapply
/gsd-code-review-fix → /gsd-code-review --fix
/gsd-plan-milestone-gaps → /gsd-audit-milestone
Refs #3047
* docs(changelog): regroup [Unreleased] under Feature/Enhancement/Fix
Replace the existing Keep-a-Changelog \`Added\` / \`Changed\` /
\`Performance\` / \`Removed\` / \`Fixed\` sub-headers in the [Unreleased]
block with the issue/PR template taxonomy:
Added → Feature
Changed / Performance → Enhancement
Removed → Enhancement
Fixed → Fix
Order within the release: Feature → Enhancement → Fix. Every bullet
preserved verbatim — only headers and grouping changed; the awkward
inline-versioned headers (\`### Added — 1.40.0-rc.1\`,
\`### Changed — 1.40.0-rc.1\`, \`### Fixed — 1.40.0-rc.1\`) folded into
the same buckets with the \`— 1.40.0-rc.1\` suffix dropped, since the
[Unreleased] block IS 1.40.0-rc.1.
The [1.39.2] hotfix block called out in #3047's spec does not yet
exist in CHANGELOG.md (the previously released hotfix is [1.39.1]),
so this commit only regroups [Unreleased]. Older release blocks
([1.39.1] and earlier) are frozen and untouched.
Refs #3047
* docs(changeset): add fragment for v1.40.0 doc audit
Refs #3047
* docs(en): strip leading / from deleted slash-command tokens in FEATURES
REQ-CONSOLIDATE-03 and REQ-CONSOLIDATE-04 listed deleted commands by
their `/gsd-foo` form for the historical record. The docs-parity tests
in bug-3010, bug-3029-3034, and bug-3042-3044 use the regex
`/\/gsd-[a-z0-9][a-z0-9-]*/g` to scan user-facing surfaces for any
remaining mention of removed slash forms — they cannot tell prose
about a deleted command from a live recommendation.
Strip the leading slash from the bare-name references (preserve the
historical text otherwise). Tests now require a `/` prefix to match,
so `gsd-add-todo` reads identically to a human but no longer trips
the parser.
Verified locally: 65/65 tests pass across the three docs-parity
suites that were red on CI run 25270072600.
Refs #3047
* docs(en): fix CR feedback + drop literal /gsd:plan-phase from USER-GUIDE
CI: tests/bug-2543-gsd-slash-namespace.test.cjs flagged
docs/USER-GUIDE.md:35 for embedding the literal `/gsd:plan-phase`
token in the parenthetical Gemini-form example. The test scans every
.md under docs/ for `/gsd:<live-cmd>` because non-Gemini surfaces must
not advertise the colon form. Replaced the literal example with a
prose substitution rule.
CR: docs/ARCHITECTURE.md:125 — the namespace meta-skills were listed
by file-prefix (`gsd-ns-workflow`) but the invocable frontmatter `name:`
is the bare form (`gsd-workflow`). Verified against the six
`commands/gsd/ns-*.md` files. Replaced with the canonical names and
noted the file/name disagreement in-line.
CR: docs/COMMANDS.md:723 — `v1.40` aligned to canonical `v1.40.0`.
CR: docs/FEATURES.md:2679 — REQ-CTX-GUARD-02 advertised the wrong
invocation (`gsd-tools validate context`). The shipped handler is
exposed via `gsd-sdk query validate.context` and requires explicit
`--tokens-used <int>` + `--context-window <int>` flags (verified
against sdk/src/query/validate.ts:849-882 and
get-shit-done/bin/lib/validate-command-router.cjs:19-36).
CR: docs/zh-CN/README.md:533 — added `inherit` to the profile-options
parenthetical to match the canonical set (verified against
model-profiles.cjs:29 `VALID_PROFILES = […MODEL_PROFILES['gsd-planner'], 'inherit']`).
Verified locally: 74/74 tests pass across the four docs-parity suites
that were red on CI runs 25270072600 and 25270182903.
Refs #3047
* feat(plan-phase): --research-phase flag absorbs deleted /gsd-research-phase + scrub stale refs (#3042, #3044)
#3042 (orphaned research-phase): /gsd-research-phase had a workflow file
but no slash-command stub. Rather than restore the orphan, the research-
only capability is now a flag on /gsd-plan-phase:
/gsd-plan-phase --research-phase <N>
When set, the workflow scopes to phase N, runs the research step (Section
5 of the existing plan-phase workflow), then early-exits before the
planner/plan-checker/verifier chain.
Per RCA against the deleted standalone, the flag adds two modifiers to
fully cover the original surface (Option B from the RCA discussion):
- --view : print existing RESEARCH.md to stdout, no spawn. Cheapest mode
for the correction-without-replanning loop the issue reporter
explicitly called out. Errors with a clear hint if RESEARCH.md is
missing.
- --research : reuse the existing "force re-research" semantics. In
research-only mode this skips the existing-RESEARCH.md prompt and
re-spawns unconditionally.
- Neither flag, RESEARCH.md exists : prompt update/view/skip. Mirrors
the deleted standalone's existing-artifact menu (#3042 RCA).
#3044 (stale slash-command refs): scrubbed five deleted commands from
all user-facing surfaces, including English docs, 4 localized doc sets
(ja-JP, ko-KR, zh-CN, pt-BR), workflows, templates, and references.
/gsd-check-todos → /gsd-capture --list
/gsd-new-workspace → /gsd-workspace --new
/gsd-status → /gsd-progress
/gsd-plan-milestone-gaps → table rows / orphan sections removed
(PR #3038 only scrubbed workflows/agent;
missed the docs surfaces this PR covers)
/gsd-research-phase → /gsd-plan-phase --research-phase
Includes a fix to docs/issue-driven-orchestration.md (PR #3036)
which itself referenced /gsd-new-workspace 4 times — self-correction.
Removed:
- get-shit-done/workflows/research-phase.md (orphan, capability
absorbed into --research-phase flag)
Tests:
- tests/bug-3042-3044-research-flag-and-stale-refs.test.cjs — 46
structural-IR tests across both bugs:
- argument-hint advertises --research-phase + --view
- workflow parses --research-phase, sets RESEARCH_ONLY,
early-exits before planner
- --view prints RESEARCH.md without spawning
- --research forces refresh in research-only mode
- existing-RESEARCH.md prompt path with update/view/skip
- workflows/research-phase.md is removed
- 5 deleted slash-commands absent from 17 English user-facing
surfaces + 16 localized doc surfaces (4 locales × 4 docs each)
- replacement command tokens present where deleted ones lived
6950/6950 full suite pass. Lints clean.
Closes#3042Closes#3044
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* fix: address all 8 CR findings on PR #3045
Major (3):
- get-shit-done/workflows/plan-phase.md:344 — added explicit early-exit
guard at Section 5.1: "Skip if RESEARCH_ONLY=true". Without it, an LLM
could fall through "use existing, skip to step 6" → planner spawn,
violating the research-only contract. The guard makes the early-exit
unreachable from any non-research-only branch.
- get-shit-done/references/continuation-format.md (3 examples) +
zh-CN/.../continuation-format.md (3 examples) — pointed to
`/gsd-plan-phase --research-phase` but docs/COMMANDS.md didn't
document the flag. Added a full --research-phase + --view + --research
modifier section to the /gsd-plan-phase flag table in COMMANDS.md so
the canonical reference matches the continuation examples.
Minor (5):
- docs/FEATURES.md:1632 — `/gsd-plan-phase --research-phase` →
`/gsd-plan-phase --research-phase <N>` (include required arg).
- get-shit-done/templates/README.md:46 — NN-VALIDATION.md producer
reverted from `/gsd-plan-phase --research-phase` (Nyquist) to plain
`/gsd-plan-phase` (Nyquist). VALIDATION.md is created during normal
Nyquist flow, not research-only mode — the bulk replacement was
wrong for that line.
- get-shit-done/workflows/help.md:89 — signature line was missing
`--research`; added it alongside `--research-phase` and `--view`.
- tests/bug-3042-3044-...:197 — promptHasView/promptHasSkip were
tautological (matched anywhere in 1700-line workflow). Tightened
to a proximity check anchored on "RESEARCH.md already exists" prompt
header within a 600-char window. Updated workflow to emit that
literal phrase.
- tests/feat-2840-...:95 — workspace assertion used `/gsd-workspace`
but the documented replacement is `/gsd-workspace --new`. Tightened
to require both tokens (in 3 places: requiredCommands list, regex
in conceptPairs, error message).
6950/6950 full suite pass. Lint clean.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
* fix(install): skip Gemini local commands/gsd when global GSD present (#3037)
Reporter showed that running `npx get-shit-done-cc --gemini --global`
followed by `--gemini --local` in a project creates the same 65 GSD
command files in both Gemini scopes:
- ~/.gemini/commands/gsd/ (user scope)
- <project>/.gemini/commands/gsd/ (workspace scope)
Gemini conflict-detects by command name across scopes and renames every
overlapping /gsd:* command to /workspace.gsd:* and /user.gsd:*, breaking
the documented /gsd:* namespace.
Fix: in bin/install.js, when handling --gemini --local, detect whether
~/.gemini/commands/gsd/ already exists with managed-shape content. If
so, skip the local copy and print a clear three-line warning explaining
the conflict avoidance. The user-scope install already provides the
same /gsd:* commands in this project; the local copy adds zero value.
Sibling fixes (test isolation):
- tests/install-minimal-all-runtimes.test.cjs: pass HOME/USERPROFILE
through the spawned installer's env so the developer's real
~/.gemini/commands/gsd/ doesn't trigger the new skip path during
test runs that want to assert the local-install populates
commands/gsd/.
- tests/gemini-namespacing.test.cjs: the "Gemini Install (Behavioral)"
describe block now creates an isolated tmpHome and points
process.env.HOME at it before calling install(false, 'gemini'),
with proper restore in afterEach.
Test:
- tests/bug-3037-gemini-duplicate-commands.test.cjs — 4 structural
tests:
1. global install populates HOME/.gemini/commands/gsd
2. local install AFTER global skips the local copy
3. local install with NO existing global still populates locally
(no-regression)
4. local install when HOME has .gemini/ but no GSD-managed
commands/gsd/ still populates locally (non-GSD-Gemini-user
no-regression)
6909/6909 full suite pass. Lints clean.
Closes#3037
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* fix: address CR feedback on PR #3041 — narrower detection + USERPROFILE restore
CR findings:
1. **bin/install.js (Major)** — userScopeHasGsd used
`fs.readdirSync(homeGeminiGsd).length > 0` which would skip the
local install for any non-empty directory, including a user who
hand-dropped a single override at ~/.gemini/commands/gsd/<thing>
.toml without ever running --gemini --global. Narrowed the
detection to require at least 3 canonical GSD command files
(help.toml, progress.toml, new-project.toml) — a marker that
ships in every GSD Gemini install (minimal mode included) and is
structurally impossible to produce by accident.
2. **tests/bug-3037-...:59 (Minor)** — beforeEach overwrites
process.env.USERPROFILE but afterEach only restores HOME, leaking
the temp home into later tests on Windows or any code path that
reads USERPROFILE. Added save/restore symmetric with HOME.
Plus added a 5th regression test covering the narrowed detection:
"local install when HOME has hand-dropped overrides UNDER commands/gsd/
(but no full GSD) still populates locally" — directly exercises the
edge case CR identified.
5/5 targeted tests pass. 6910/6910 full suite pass.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
* fix(workflows,docs): scrub stale /gsd-code-review-fix and /gsd-plan-milestone-gaps refs (#3029, #3034)
#2790 consolidated /gsd-code-review-fix into /gsd-code-review --fix and
deleted /gsd-plan-milestone-gaps in favor of inline gap planning as part
of /gsd-audit-milestone's output. The deletion was propagated through
some surfaces (#2950 covered help/do/settings/discuss-phase/etc.) but
several user-facing surfaces still emitted the old forms:
#3029 — /gsd-code-review-fix references in:
- agents/gsd-code-fixer.md (description, "Spawned by", recovery prose)
- get-shit-done/workflows/code-review.md (offer text)
- get-shit-done/workflows/execute-phase.md (offer text)
- get-shit-done/workflows/code-review-fix.md (internal retry hints)
- docs/INVENTORY.md (agent + workflow rows)
- docs/CONFIGURATION.md (workflow.code_review row)
- docs/USER-GUIDE.md (3 occurrences in walkthrough)
- docs/AGENTS.md (gsd-code-fixer agent stub)
- docs/FEATURES.md (commands list + REQ-REVIEW-04)
All replaced with /gsd-code-review --fix. Internal retry hints in the
workflow file itself updated to point at the new form. Release notes
(docs/RELEASE-*.md) and gsd-ns-review's "absorbed by" deletion note
left unchanged — historical/explanatory content.
#3034 — /gsd-plan-milestone-gaps references in:
- get-shit-done/workflows/audit-milestone.md (<offer_next> blocks for
gaps_found and tech_debt: lines 281, 323)
- commands/gsd/complete-milestone.md (gaps_found pre-flight: lines 46, 57)
Replaced with inline closure path:
/gsd-phase --insert <N> "Close gap: <REQ-ID> ..."
/gsd-discuss-phase <N>
/gsd-plan-phase <N>
/gsd-execute-phase <N>
Plus a Nyquist-coverage hint pointing at /gsd-validate-phase /
/gsd-secure-phase for retroactive audit-chain hygiene gaps. The
gsd-ns-project SKILL.md "deleted by #2790" note is preserved
(it's the canonical pointer for future readers asking what
happened to the command).
Tests:
- tests/bug-3029-3034-stale-command-routes.test.cjs — parser-based
assertions per fixed surface, plus a structural cross-check that
gsd-ns-project keeps the deletion note. 15 tests, all green.
- 6905/6905 full suite passes.
Closes#3029Closes#3034
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* fix: address CR feedback on PR #3038 — argument order, structural tests, agent count
CR findings on PR #3038:
1. **docs/USER-GUIDE.md (Major)** — `--fix` examples used flag-first form
(`/gsd-code-review --fix 3`), but the supported CLI grammar is
phase-first (`/gsd-code-review 3 --fix`). The original sed-based
replacement preserved the position of the `gsd-code-review-fix`
token, producing the wrong order. Fixed in USER-GUIDE.md (3
occurrences) and the same drift in the workflow surfaces:
- get-shit-done/workflows/code-review-fix.md (2 retry hints)
- get-shit-done/workflows/code-review.md (offer text)
- get-shit-done/workflows/execute-phase.md (offer text)
2. **docs/AGENTS.md (Minor)** — internal count drift: line 483 said
"Ten additional agents" but line 725 said "12 advanced/specialized".
Filesystem reality: 33 agents total, 21 primary, 12 specialized
(count of `### ` stubs in the Advanced and Specialized section).
Updated lines 3, 13, 483 to use 12/33 and added the two missing
names (doc-classifier, doc-synthesizer) to the inline list at
line 13.
3. **tests:94 (Major refactor suggestion)** — `.includes()` token checks
were source-grep style. Refactored to a typed-IR pattern: extract
the SET of slash-command tokens via regex, assert membership on the
parsed Set instead of substring scanning the raw file text. Added
the `allow-test-rule` comment explaining the IR-build vs
IR-assertion split per scripts/lint-no-source-grep.cjs convention.
4. **tests:130 (Major)** — replacement-path assertion was file-wide and
could false-pass on generic mentions of "inline" elsewhere in the
file. Refactored: `extractOfferBlocks(content)` returns the typed
list of `<offer_next>` and "Pre-flight" blocks where the deleted
command previously lived, and the assertion runs against those
blocks specifically. Now requires `/gsd-phase --insert` or
inline-audit prose to appear in the same offer block, not just
somewhere in the file.
15/15 targeted tests pass. 6905/6905 full suite pass. Lints clean.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
* docs: add issue-driven orchestration guide (#2840)
Adds docs/issue-driven-orchestration.md — a recipe for driving GSD from a
GitHub / Linear / Jira issue using existing primitives. Maps Symphony-style
orchestration concepts onto GSD commands without vendoring code, adding a
daemon, or introducing tracker integration.
Concept mapping covers:
- WORKFLOW.md → ROADMAP.md / STATE.md / phase CONTEXT.md / phase PLAN.md
- isolated agent workspace → /gsd-new-workspace --strategy worktree
- agent dispatch → /gsd-manager (interactive), /gsd-autonomous (unattended)
- per-phase steps → /gsd-discuss-phase → /gsd-plan-phase → /gsd-execute-phase
- proof-of-work → /gsd-verify-work (UAT.md persists across /clear)
- adversarial review → /gsd-review (cross-AI peer review)
- human merge gate → /gsd-ship
- follow-up capture → /gsd-note, /gsd-plant-seed, /gsd-new-milestone
End-to-end flow walks through 7 numbered steps from picking the tracker
issue to capturing follow-ups. Safety boundaries (isolated worktrees,
explicit human review, no automatic public posting, verification before
ship) and non-goals (no vendoring, no daemon, no mandatory tracker, no
gate bypass, no command-surface expansion) are spelled out explicitly so
the doc cannot drift into "let's just add one more flag".
Cross-linked from docs/README.md (Documentation Index) and
docs/USER-GUIDE.md (Table of Contents preamble).
Tests: tests/feat-2840-issue-driven-orchestration-guide.test.cjs — 9
structural-IR tests parse the guide into a typed record and assert on
flags (commandsPresent, conceptPairs, nonGoalFlags, safetyFlags,
numberedSteps). Fence-language MD040 check enforced. Cross-link
presence enforced. No raw-text assertions on prose.
6890/6890 tests pass. Lint:tests clean (allow-test-rule comment justifies
the doc-shape parser per scripts/lint-no-source-grep.cjs escape hatch).
Lint:changeset clean.
Closes#2840
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* fix(test): guard USER-GUIDE.md existsSync before read (CR #3036)
CR Minor: cross-linked-from-USER-GUIDE.md test called fs.readFileSync
directly without first asserting fs.existsSync, asymmetric with the
README.md test above. A missing USER-GUIDE.md would throw ENOENT instead
of producing a meaningful assertion message. Mirror the null-guard
pattern.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
* feat(hooks): opt-in SessionStart update banner for non-statusline users (#2795)
When a user declines (or keeps a non-GSD) statusline at install time, the
installer now offers an opt-in SessionStart banner that surfaces GSD update
availability. The banner reads the existing
~/.cache/gsd/gsd-update-check.json cache (written by
gsd-check-update-worker.js) and emits a single systemMessage line only when
update_available is true:
GSD update available: <installed> → <latest>. Run /gsd-update.
It is silent when up-to-date and rate-limits "check failed" diagnostics to
once per 24h via a sentinel file so a corrupt cache doesn't nag every
session. Removed cleanly by `npx get-shit-done-cc --uninstall` which strips
both the script and the SessionStart entry. The banner is never offered when
GSD's statusline is being installed (statusline already surfaces update
info, so re-prompting would be noise).
Implementation:
- hooks/gsd-update-banner.js — pure functions buildBannerOutput,
shouldSuppressFailureWarning, readCache; thin main() wires them.
- bin/install.js — handleUpdateBanner() prompt, parseUpdateBannerInput(),
buildUpdateBannerHookEntry(), buildUpdateBannerPromptText(); chained into
installAllRuntimes() so finalize() receives both flags. updateBannerCommand
computed alongside the other JS-hook commands; finishInstall() registers
the SessionStart entry only when shouldInstallBanner === true and the
hook file is present at the target.
- Hook ships in scripts/build-hooks.js HOOKS_TO_COPY, listed in
MANAGED_HOOKS for stale-detection in gsd-check-update-worker.js, in the
uninstall hook-removal lists in install.js, and in the
rewriteLegacyManagedNodeHookCommands allowlist.
Tests:
- tests/feat-2795-update-banner.test.cjs — 22 tests, structural-IR
assertions on parsed JSON envelopes (no raw-text matching). Covers
pure-function branches (cache present/absent, parseError, rate-limit
suppression, missing version fields), end-to-end hook invocation against
fixture cache states, and install.js wiring (prompt text, input parsing,
hook entry shape).
- tests/trae-install.test.cjs — updated install() return-shape assertion to
include updateBannerCommand: null for the no-settings runtime.
- 6881/6881 tests pass.
Docs (bundled in same commit per the bundle-docs-with-code skill):
- docs/USER-GUIDE.md — new "Surface GSD Update Notifications Without GSD's
Statusline" task section with opt-in/opt-out instructions.
- docs/FEATURES.md — REQ-HOOK-08 added; "Update Banner" subsection under
the Hook System feature with cache flow + removal path.
- docs/INVENTORY.md — hook count 11 → 12, new row for gsd-update-banner.js.
- docs/INVENTORY-MANIFEST.json — regenerated.
Closes#2795
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* fix(install): gate banner prompt on actual installability (CR #3035)
CodeRabbit findings on PR #3035:
- bin/install.js (Major): continueAfterStatusline gated banner prompt on
the raw `shouldInstallStatusline` flag from handleStatusline. But
finishInstall later silently skips the statusline write on local
installs unless --force-statusline is set (#2248). Two consequences:
1. Interactive local Claude/Gemini installs got neither a statusline
nor a banner offer.
2. Codex/Cursor/Copilot/Windsurf/Trae/Cline-only installs (where
every result.updateBannerCommand is null) still got prompted even
though the choice was silently ignored.
Fix: derive willInstallStatusline = shouldInstallStatusline &&
(isGlobal || forceStatusline), and gate the banner prompt on a
canInstallBanner precondition computed from results[].updateBannerCommand.
Pass the raw shouldInstallStatusline through to finalize unchanged so
per-runtime statusline gating in finishInstall is unaffected.
- tests/feat-2795-update-banner.test.cjs (Minor): rate-limit suppression
test parsed r1.stdout without first asserting r1.status === 0. Other
e2e tests in this file (lines 210, 241) do this. A non-zero exit would
surface as a cryptic SyntaxError instead of a status assertion failure.
Fix applied verbatim.
6881/6881 tests pass.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
Closed on the technical merits: the determinism claim is theoretical (no
observed misinterpretation), token waste is small and unmeasured, and PR
#2279's orchestrator-embedding path already serves the deterministic-gating
need without a parallel templating subsystem.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Reporter did not return to clarify the actual ask after the narrowing-then-
retraction in the comment thread. Closing as wontfix per .out-of-scope/
temporal-context.md with re-open criteria spelled out.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* docs(#3025): MCP tool schema as a context-budget concern
Adds documentation covering the largest GSD cost lever that GSD
itself does not own: MCP tool schema injection. Every enabled MCP
server adds its schema to every turn (often 20k+ tokens for
heavyweight servers like browser/playwright, mac-tools, etc.),
which can dwarf whatever `model_profile` tuning saves.
Two doc surfaces (per the bundle-docs-with-code skill depth gradient):
1. get-shit-done/references/context-budget.md
- New "MCP Tool Schema Cost (Harness Concern)" section.
- Explains schemas-per-turn cost framing.
- Names enabledMcpjsonServers / disabledMcpjsonServers and
.claude/settings.json explicitly.
- Pre-phase audit checklist: browser/playwright, platform-specific,
cross-project/stale, duplicate/shadow.
- Explicit "GSD does not manage MCP enablement — harness concern"
statement so users don't hunt for a GSD setting.
- Links to Anthropic Claude Code MCP docs as canonical reference.
- Notes compounding interaction with model_profile (additive levers).
2. docs/USER-GUIDE.md
- New task-oriented "Trim MCP servers to reduce per-turn cost"
section above "Using Non-Claude Runtimes".
- Same checklist condensed.
- Cross-link to context-budget.md for the full reference.
Tests:
- tests/feat-3025-mcp-token-budget-docs.test.cjs (12 cases) parses
both docs into typed semantic-flag records and asserts behavioral
invariants (mentions key, includes audit, names harness, etc.)
rather than substring-matching prose. Adheres to CONTRIBUTING.md
no-source-grep — section can be reworded freely as long as the
required semantics survive.
- Markdownlint pre-flight tests (MD040 fence language, MD056 table
column count) per the bundle-docs-with-code skill so CR can't
ratchet on prose nitpicks across multiple review rounds.
Verification:
- 12/12 pass on regression test
- 6857/6857 full suite (12 net new)
- lint-no-source-grep clean (377 test files)
Companion to #3023 (per-phase-type model map) and #3024 (dynamic
routing). Together they cover the three biggest cost levers users
ask about; this issue covers the one GSD does not own.
Closes#3025
* docs(#3025): batch 3 CR fixes — pr id, relative link, named flag
CodeRabbit on PR #3032 (3 minor — 2 inline + 1 nitpick), all in one
push per the bundle-docs-with-code skill (avoid per-round nitpick
ratchet):
1. Inline (Minor) — .changeset/mcp-token-budget-docs.md:3
`pr: TBD` → `pr: 3032` so changeset tooling can link the entry.
2. Inline (Minor) — docs/USER-GUIDE.md:1101
Used a hardcoded `https://github.com/.../blob/main/...` URL for the
cross-link to `context-budget.md`. Rest of USER-GUIDE.md uses
relative links. Switched to `../get-shit-done/references/context-
budget.md#mcp-tool-schema-cost-harness-concern` so feature-branch
work shows the right content and rename-resilience is preserved.
3. Nitpick — tests/feat-3025-mcp-token-budget-docs.test.cjs:234
The cross-link assertion used an inline `/context-budget/i.test(...)`
while every other invariant in the file lived as a named flag in
`parseMcpBudgetSection`. Per CONTRIBUTING.md no-source-grep, added
`crossLinksContextBudget` to the parser and asserted on
`parsed.crossLinksContextBudget` so the cross-link rule sits next
to its siblings.
Verification:
- 12/12 pass on regression test (no count change; refactor only)
- No source code changes, only docs + tests
* test(#3025): strip inline markdown before phrase-match (CR nitpick)
CodeRabbit caught that the `explainsHarnessNotGsd` primary regex
branch couldn't match "GSD does **not** manage" in
context-budget.md because the markdown bold markers (`**`) sit
between contiguous words. The test passed today only via the
fallback `harness (concern|setting|controlled)` branch — the
primary branch was effectively dead code.
Fix: strip inline markdown emphasis (`**`, `*`, `~~`) and inline-
code backticks before any phrase-matching in `parseMcpBudgetSection`.
All seven flag computations now run against the stripped text so
markdown formatting can't silently invalidate any invariant.
Underscores are intentionally NOT stripped — `model_profile` and
other snake_case identifiers must survive intact for the
mentionsModelProfileInteraction check to find them.
Verification: 12/12 still pass; primary branches now fire on
real markdown content rather than relying on fallbacks.
* test(#3025): guard markdownlint tests against null section (CR nitpick)
CodeRabbit caught that the MD040 and MD056 markdownlint pre-flight
tests called `section.match(...)` and `section.split('\n')`
directly on the value returned by `extractSection`, which returns
null when no matching header is found. If the MCP section is ever
removed (regression), both tests would throw `TypeError: Cannot
read properties of null` instead of producing a clean assertion
failure naming the actual problem.
The semantic tests above are protected because parseMcpBudgetSection
short-circuits to a typed-falsy record on null input. The
markdownlint tests bypassed that guard since they need raw section
text, not parsed flags. Added `assert.ok(section, ...)` preconditions
to both so a missing section produces a meaningful failure message.
No content changes; defensive programming only.
Verification: 12/12 still pass.
* feat(#3024): dynamic routing with failure-tier escalation
Adds a `dynamic_routing` block to .planning/config.json that lets
the resolver start agents on a cheap tier and escalate one tier up
when the orchestrator detects a soft failure (verification
inconclusive, plan-check FLAG, etc.). Solves the "pay Opus rates as
insurance" anti-pattern by making escalation observed-quality-driven.
Architecture:
- AGENT_DEFAULT_TIERS map (light/standard/heavy) — every agent in
MODEL_PROFILES declares a default tier; tests assert coverage
so adding a new agent without updating the map fails CI.
- nextTier(currentTier) helper — light → standard → heavy → heavy
(heavy stays at heavy; can't go further).
- resolveModelForTier(cwd, agentType, attempt) — new resolver. The
orchestrator tracks the attempt counter and passes 0 for the
first spawn, 1+ on escalation. The resolver caps internally at
max_escalations so the orchestrator can blindly bump the counter.
- Schema validation: dynamic_routing.enabled / escalate_on_failure /
max_escalations / tier_models.<light|standard|heavy>. Unknown
tiers and unknown sub-keys rejected at config-set time.
- SDK schema mirror updated to keep CJS/SDK in lockstep (#2653).
Resolution precedence (highest → lowest):
1. model_overrides[<agent>] (full IDs accepted)
2. dynamic_routing.tier_models[<tier>] (NEW; escalation-aware)
3. models[<phase_type>] (#3023 phase-type map)
4. model_profile (per-agent column)
5. Runtime default
Backward compatibility: dynamic_routing is disabled by default
(enabled: false or block omitted). resolveModelForTier short-
circuits to resolveModelInternal in that case, so callers can
adopt unconditionally without breaking existing behavior.
This PR delivers the JS-layer infrastructure: schema + tier map +
resolver. Orchestrator adoption (workflow markdown updates that
detect soft failures and call resolveModelForTier with attempt+1)
is incremental follow-up — verifier / plan-checker / integration-
checker each adopt the protocol when ready.
Tests (23 cases, all structural-IR — no stdout grep):
- Schema invariants: AGENT_DEFAULT_TIERS coverage, VALID_AGENT_TIERS
exact match, every assignment uses a valid tier
- nextTier helper: light→standard→heavy→heavy, null on invalid input
- Disabled mode: no block + enabled:false both no-op (back-compat)
- Enabled mode: attempt=0 returns default tier model, attempt=1
escalates, beyond max_escalations caps, heavy agents stay heavy,
default max_escalations=1 when omitted
- Precedence: per-agent override beats dynamic_routing,
dynamic_routing beats phase-type models
- Validation: every settings key accepted, unknown tiers/sub-keys
rejected, bare `dynamic_routing` rejected as config-set target
Documentation:
- get-shit-done/references/model-profiles.md — full reference section
- docs/CONFIGURATION.md — full settings table + escalation flow
- docs/USER-GUIDE.md — task-oriented "Cheap-by-default" section
- docs/FEATURES.md — config row cross-link
Verification:
- 23/23 pass on regression test
- 6843/6843 full suite (23 net new from 6820)
- lint-no-source-grep clean (376 test files)
- SDK schema mirror keeps CJS/SDK in sync per #2653 parity test
Closes#3024
* fix(#3024): honor escalate_on_failure:false + 3 CR follow-ups
CodeRabbit on PR #3031 (4 findings — 1 Major + 2 Minor + 1 Nitpick):
1. **Major (inline)** — get-shit-done/bin/lib/core.cjs:1668
resolveModelForTier ignored dynamic_routing.escalate_on_failure.
When the user set it to false, escalation should be disabled, but
the resolver only checked attempt/max_escalations. An orchestrator
that always passes attempt+1 on retry would silently escalate
despite the user opting out.
Fix: gate effectiveAttempt on `dr.escalate_on_failure !== false`
so false short-circuits every attempt back to the default tier.
2. **Minor (inline)** — docs/CONFIGURATION.md:123-126
The dynamic_routing rows in the Core Settings table had 4 cells
instead of 5 (missing the Options column), breaking the table
structure. Added explicit Options values for enabled / escalate_on_failure
/ max_escalations rows.
3. **Minor (outside-diff)** — references/model-profiles.md:179-195
"Resolution Logic" sketch was pre-#3024 and didn't include
dynamic_routing in the precedence ladder. Updated to a 6-step
block with dynamic_routing at step 3 (between override and
phase-type).
4. **Nitpick** — tests/feat-3024-dynamic-routing.test.cjs:189+
Tests used `if (lightAgent) { ... }` guards that silent-pass
when AGENT_DEFAULT_TIERS drifts. Replaced all 5 conditional
skips with `assert.ok(lightAgent, '...')` preconditions so a
tier-mapping change surfaces as a test failure.
Plus: 2 new regression tests for the Major fix:
- escalate_on_failure:false caps every attempt at default tier
- escalate_on_failure:true (explicit) still escalates normally
Verification:
- 25/25 pass on regression test (23 prior + 2 escalate_on_failure)
- 6845/6845 full suite (2 net new)
- lint-no-source-grep clean
* docs(#3024): align precedence + add fence language tags (CR follow-up)
CodeRabbit (3 minor):
1. docs/CONFIGURATION.md:691 — "Per-Phase-Type Models → Resolution
precedence" was a 4-step block written pre-#3024; readers got
contradictory rules between the per-phase-type section and the
later dynamic_routing section. Updated to the same 5-step ladder
with dynamic_routing at step 2, and noted that dynamic_routing
is disabled by default so this section's behavior is unchanged
when the kill-switch is off.
2. docs/CONFIGURATION.md:770 — escalation-flow code fence missing
language tag (MD040). Added `text`.
3. references/model-profiles.md:184 — resolution-ladder code fence
missing language tag (MD040). Added `text`.
No code changes; docs only. Verification: regression test still 25/25.
* docs(#3024): clarify precedence prose — five layers, not four (CR nitpick)
CodeRabbit nitpick: the "Per-Phase-Type Models → Resolution
precedence" prose said "The four layers compose..." but the ladder
above lists five (including Runtime default). Also "dynamic_routing
escalates per-attempt above all of them" misreads as suggesting
dynamic_routing wins over model_overrides — actually overrides still
win at step 1.
Reworded top-down so the precedence direction is unambiguous:
- model_profile = base
- models = phase-level override
- dynamic_routing = per-attempt escalation
- model_overrides = per-agent exception (top)
- runtime default = fallback
No code changes; docs only.
* docs(#3024): note escalate_on_failure:false in escalation-flow diagram (CR)
CodeRabbit nitpick: the escalation-flow diagram in
docs/CONFIGURATION.md described the soft-failure → respawn →
tier_models[next_tier_up] path, but didn't surface the
`dynamic_routing.escalate_on_failure: false` kill-switch right next
to it. Users reading the flow diagram (which is the canonical place
to understand attempt behavior) wouldn't see that the kill-switch
overrides the soft-failure branch.
Added a one-paragraph note immediately after the flow listing,
before the tier-sequence example, so the kill-switch is visible
exactly where users decide whether escalation will happen.
No code changes; docs only.
* feat(#3023): per-phase-type model map in .planning/config.json
Adds a new `models` block to .planning/config.json with six phase-type
slots (planning / discuss / research / execution / verification /
completion). Lets users express coarse tuning ("Opus for planning,
Sonnet for the rest") without learning the agent taxonomy.
Resolution precedence (highest → lowest):
1. Per-agent `model_overrides[agent]` (full IDs; targeted exception)
2. Phase-type `models[phase_type]` (NEW; tier alias)
3. Profile table (`model_profile`) (per-agent column)
4. Runtime default
The three layers compose: `models` defaults a phase, `model_overrides`
carves an exception. Phase-type values are tier aliases (opus/sonnet/
haiku/inherit) so the runtime-resolution chain (#2517) stays correct
end-to-end without further branching.
Implementation:
- model-profiles.cjs: new AGENT_TO_PHASE_TYPE map + VALID_PHASE_TYPES
set. Each agent in MODEL_PROFILES gets one phase-type assignment;
tests assert coverage so adding a new agent without updating the
table fails CI.
- core.cjs (resolveModelInternal): inserts phase-type tier lookup
between per-agent override and profile-derived tier. Skips runtime
resolution when the resolved tier is 'inherit' (was previously gated
only on profile === 'inherit'; phase-type can now produce inherit
independently).
- core.cjs (loadConfig): pass `parsed.models` through both code paths
so resolveModelInternal can read it.
- config-schema.cjs + sdk/src/query/config-schema.ts: dynamic-pattern
validator accepts only the six known phase-types; unknown slots
rejected at config-set time.
Backward compat: configs without `models` behave exactly as today.
Tests (15 cases, all structural-IR — no stdout grep):
- Schema: AGENT_TO_PHASE_TYPE coverage, VALID_PHASE_TYPES exact match
- Resolver: phase-type alone; per-agent override beats phase-type;
phase-type beats profile; issue's full example; "inherit"; empty
block is no-op; no block is no-op
- Validation: each of the 6 slots accepted; unknown slot rejected;
bare `models` (no slot) rejected
Verification:
- 15/15 pass on new regression test
- 6808/6808 full suite (5 net new), 0 fail
- lint-no-source-grep clean across 375 test files
Closes#3023
* docs(#3023): document `models` per-phase-type config in user-facing docs
Adds `models` block coverage to the three user-facing docs that ship
with each release:
1. docs/CONFIGURATION.md
- New "Per-Phase-Type Models" section between "Per-Agent Overrides"
and "Non-Claude Runtimes" with:
* full example mixing models + model_overrides
* phase-type → agent mapping table
* resolution-precedence pseudocode
* accepted values (tier alias only)
* "When to use which" decision matrix
* validation behavior + example error
- Added `"models": {}` to the Full Schema snippet
- Added a row for `models.<phase_type>` to the config keys table
(next to model_profile_overrides for adjacency)
2. docs/FEATURES.md
- Added a row for models.<phase_type> in the Configurable Settings
table (right under model_profile)
- Cross-link to CONFIGURATION.md for the full surface
3. docs/USER-GUIDE.md
- New task-oriented "Tuning model cost by phase" section above
"Using Non-Claude Runtimes" — leads with the concrete config
and shows the override pattern (one-shot phase + targeted exception)
- Cross-link to CONFIGURATION.md
Verification:
- 29/29 pass on config-schema-docs-parity + docs-update + new feature
test (parity-check passes, so the config-schema entry I added in the
feature commit is now matched by a docs row)
- 6808/6808 full suite pass
- lint-no-source-grep clean
Doc style follows the same pattern used by the existing model_profile,
model_overrides, and model_profile_overrides sections — example-led,
table-backed, cross-referenced. Each doc surfaces the feature at the
right depth (reference / settings table / task guide).
* fix(#3023): mirror phase-type tier in resolveReasoningEffortInternal (CR Major)
CodeRabbit caught a real Codex correctness bug + 3 minor docs/test issues:
1. **Major (outside-diff)** — resolveReasoningEffortInternal in core.cjs
derived its tier exclusively from the profile table, ignoring the
models.<phase_type> override added in #3023. Failure mode on Codex:
Config: model_profile=balanced, models.execution=opus, agent=gsd-executor
resolveModelInternal: tier=opus → gpt-5.4
resolveReasoningEffortInternal: tier=sonnet → reasoning_effort=medium
↑
WRONG — should be xhigh
(opus tier on Codex)
The runtime received a mismatched (model, effort) pair. Mirrored the
phase-type lookup from resolveModelInternal so both functions derive
from the same tier source. 'inherit' phase-type returns null effort
(no runtime entry maps to 'inherit'; let runtime decide).
2. Minor — .changeset/per-phase-type-models.md `pr: TBD` → `pr: 3030`.
3. Minor (outside-diff) — model-profiles.md "Resolution Logic" section
omitted the new phase-type tier. Updated the 4-step block to a 5-step
block including `models[phase_type]` between override and profile,
plus a paragraph noting that `model` and `reasoning_effort` derive
from the same tier source.
4. Nitpick — added 2 typo-safety tests:
- models.research = "haiku3" (typo) → falls through to profile
- models.research = "openai/gpt-5" (full ID) → falls through to profile
Plus 5 new reasoning_effort tests covering the Major fix:
- exported correctly
- phase-type override flips both model AND effort to same tier
- inherit phase-type returns null effort
- per-agent override still bypasses phase-type for effort
- claude runtime ignores models.* (no effort propagation)
Verification:
- 24/24 pass on regression test (15 original + 2 typo-safety + 5 effort + 2 outside-diff related)
- 6815/6815 full suite (7 net new from 6808)
- lint-no-source-grep clean
The reasoning_effort tests are written semantically (phase-type override
must produce the SAME effort as a profile-only opus config) rather than
hard-coding tier-specific effort strings, so changes to the runtime tier
map don't break them.
* fix(#3023): phase-type override beats profile=inherit (CR Major round 2)
CodeRabbit caught another precedence inversion: when
{ model_profile: 'inherit', models: { execution: 'opus' } }
both resolvers short-circuited on `profile === 'inherit'` BEFORE the
phase-type override could be honored. Result: model returned 'inherit'
and reasoning_effort returned null — both contradicting the documented
precedence where models[phase_type] wins over model_profile.
Fix in resolveModelInternal:
- Compute tier from phase-type FIRST. If phase-type is a valid alias,
it wins. Otherwise, fall back to profile-derived tier OR 'inherit'
(when profile === 'inherit').
- Gate the runtime-resolution branch on `tier !== 'inherit'` (was
`profile !== 'inherit'`) so phase-type=opus can flip runtime mapping
on even when profile=inherit.
- Gate the inherit-return on `tier === 'inherit'` (was
`profile === 'inherit'`).
Fix in resolveReasoningEffortInternal:
- Remove the `if (profile === 'inherit') return null;` early-return.
- Compute tier from phase-type first, fall back to profile. If
phase-type is explicitly 'inherit' OR the resolved tier is 'inherit',
return null (no runtime entry maps to inherit).
Tests added (5 new):
- model: phase-type wins over profile=inherit (with explicit opus, with
haiku for one phase + planner-without-slot still inheriting)
- model: profile=inherit + no models block → all agents inherit (no
regression on existing inherit semantics)
- model: profile=inherit + models block but agent has no slot → that
agent inherits, agents with slots get phase-type tier
- effort: phase-type opus + profile=inherit → produces opus-tier
effort, NOT null (the original bug)
Verification:
- 27/27 pass on regression test (24 prior + 3 model + 1 effort)
- 6820/6820 full suite (5 net new)
- lint-no-source-grep clean
The effort test reads the expected value by running a profile-only opus
config and comparing — semantic check, not hard-coded effort string. So
runtime tier map changes don't break the test.
* fix(#3020): probe user shell PATH at install-time, not just process.env.PATH
The installer's "✓ GSD SDK ready" message was a false positive whenever
the install subprocess's process.env.PATH contained the gsd-sdk shim
but the user's later interactive shells did not. Three known sources
of mismatch on POSIX:
- ~/.local/bin: install subprocess inherits npm/npx-injected PATH;
user's login shell may not add ~/.local/bin if .profile/.bashrc/
.zshrc don't.
- nvm/fnm/volta: node version managers shim PATH per-shell, so
`npm prefix -g` from inside the install subprocess can resolve to
a different bin dir than the user's interactive shell sees.
- npm-prefix tooling: some installers inject extra PATH entries that
vanish in fresh sessions.
Result reported on #3011 by @x0rk and @stefanoginella: install prints
✓, but every workflow invocation later fails with
"bash: gsd-sdk: command not found".
Fix:
- isGsdSdkOnPath(pathString?) — now accepts an explicit PATH string.
Zero-arg form preserves existing behavior (reads process.env.PATH).
Pure walk, no spawn. Lets callers verify against any PATH source.
- getUserShellPath() — new helper. Probes the user's login shell via
`$SHELL -lc 'printf %s "$PATH"'` (POSIX). 2-second timeout so a
misconfigured rc file can't hang the install. Returns null on
Windows (cross-shell PATH probing requires a different strategy
per Git Bash / PowerShell / cmd.exe — tracked separately) or when
the probe fails; callers fall back to process.env.PATH in that case.
- installSdkIfNeeded() — after the existing isGsdSdkOnPath() check
passes, also verify the shim is reachable from getUserShellPath()
on POSIX. If install-PATH and user-shell-PATH disagree, downgrade
to the actionable ⚠ diagnostic from PR #3014 (which has the shim
location, shell-specific PATH-update commands, and an npx fallback
note). Routing affected users into PR #3014's diagnostic is the
point — not silently green-then-red.
Tests:
- bug-3020-install-shell-path-probe.test.cjs (10 tests, structural):
- isGsdSdkOnPath accepts an explicit PATH (true/false on fixture
PATH dirs with/without an executable shim)
- zero-arg form returns a boolean
- empty string PATH → false
- getUserShellPath returns string-or-null
- returns null on Windows
- returns null when $SHELL unset on POSIX
- cross-shell mismatch detection: install-PATH and user-PATH that
differ produce different isGsdSdkOnPath results — the invariant
the install-time check now exploits
- All assertions on structural records, not console output. Adheres
to typed-IR / CONTRIBUTING.md "Prohibited: Raw Text Matching".
Verification:
- 10/10 pass on new regression test
- 6768/6768 pass on full suite (5 net-new tests)
- lint-no-source-grep clean
Windows cross-shell coverage (gsd-sdk.cmd resolves under PowerShell
but not Git Bash without a no-extension sibling) is tracked separately
— this PR is the POSIX-side fix and the Windows scaffolding (the
optional pathString arg on isGsdSdkOnPath) that a Windows fix can
build on.
Closes#3020
* fix(#3020): type-guard pathString, last-line PATH parse (CR)
CodeRabbit on PR #3028 (4 findings — 3 actionable + 1 nitpick):
1. .changeset/install-shell-path-probe.md (2 findings):
- `pr: TBD` → `pr: 3028`
- Doc said `echo $PATH` but impl uses `printf %s "$PATH"` (chosen
to avoid shell-dependent echo behavior, e.g. interpreting `-n`).
Aligned changeset prose with implementation.
2. bin/install.js:9176 — isGsdSdkOnPath(pathString) used
`pathString !== undefined` to gate the explicit-PATH branch, but
getUserShellPath() can return null and `null.split()` throws.
Tightened to `typeof pathString === 'string'` so null / number /
object inputs fall back to process.env.PATH. Added 2 regression
tests covering the null and non-string cases.
3. bin/install.js:9232 — getUserShellPath trimmed entire stdout. A
misconfigured rc file that prints a banner / motd / log line
BEFORE the printf would pollute the result and incorrectly flip
the cross-shell check to false. Take the LAST non-empty line
(PATH itself is single-line) so noise can't hijack the probe.
4. Nitpick: the changeset PR placeholder — covered by (1).
Verification: 12/12 pass on regression test (10 original + 2 new
type-guard tests), 6770/6770 full suite, lint clean.
* docs(#3020): JSDoc references printf %s "$PATH", not echo $PATH (CR)
CodeRabbit caught two stale JSDoc references that still said
`$SHELL -lc 'echo $PATH'` while the implementation uses
`$SHELL -lc 'printf %s "$PATH"'`. echo is undesirable here because:
- POSIX echo's behavior with `-n` / backslash escapes varies across
shells (bash builtin vs /bin/echo vs zsh) and can introduce
trailing-newline pollution that the per-line trim now papers over.
- printf is portable and emits exactly the bytes given.
Synced both stale doc strings:
- bin/install.js:9211 (getUserShellPath JSDoc)
- tests/bug-3020-install-shell-path-probe.test.cjs:27 (header)
No behavior change — implementation already uses printf.
* fix(#3018): codex adapter must stop and ask, not silently default decisions
@jon-hendry: running `\$gsd-discuss-phase 81` in Codex Default mode
proceeded toward writing CONTEXT.md / DISCUSSION-LOG.md / checkpoint
artifacts without surfacing the discussion questions to the user. The
generated Codex skill adapter explicitly told it to do that:
Execute mode fallback:
- When `request_user_input` is rejected (Execute mode), present a
plain-text numbered list and pick a reasonable default.
That instruction is wrong for any workflow whose contract is to
discuss with the user (most prominently `$gsd-discuss-phase`). The
fallback now requires the agent to:
1. STOP. Present the questions as a plain-text numbered list, then
wait for the user's reply.
2. Only proceed without a user answer when one of these is true:
(a) invocation included --auto / --all,
(b) user explicitly approved a default for this question, or
(c) workflow's documented contract permits autonomous defaults.
3. Do NOT write CONTEXT.md, DISCUSSION-LOG.md, PLAN.md, or checkpoint
files until the user has answered or one of (a)-(c) above applies.
Tests:
- bug-3018-codex-discuss-fallback.test.cjs (5 tests, structural-IR):
parses the generated header into sections via regex, asserts on
the Execute-mode-fallback section's content (must contain stop/
wait + plain-text directives, must NOT contain "pick a reasonable
default", must name a permission path, must forbid artifact
writing). No raw text snapshot — the assertions describe the
behavioral invariant, so prose can be reworded without test churn.
- codex-config.test.cjs:128 still passes — section still mentions
"Execute mode" as required.
Verification:
- 5/5 pass on new regression test
- 116/116 pass on bug-3018 + codex-config combined
- 6763/6763 pass on full suite
- lint-no-source-grep clean
Closes#3018
* test(#3018): parse fallback into typed semantic-flag record (CR)
CodeRabbit nitpick on PR #3027: the regression tests grepped the
generated header prose with regex, which is brittle and tests wording
rather than semantics. Per CONTRIBUTING.md "no-source-grep" standard.
Refactored to a structural-IR shape:
- New `parseExecuteModeFallback(section)` walks the section text once
and returns a typed record:
{
ok, sectionLength,
instructsStop, // STOP/HALT/WAIT directive
presentsPlainTextQuestions, // plain-text / numbered list
namesPermissionPath, // --auto / --all / explicit approval
forbidsWritingArtifactsBeforeAnswer, // write-ban + named artifact class
silentlyPicksDefaults, // anti-pattern guard (must be false)
}
- Each positive invariant gets its own test asserting on the parsed
boolean, so a failure points at the exact invariant that broke.
- A final test does a single assert.deepStrictEqual against the full
expected contract — gives a structured diff when any flag flips.
- The artifact-write ban now requires BOTH a "do not write" intent
AND a named artifact class (was a single broad regex), so generic
"do not write" prose elsewhere in the section can't satisfy it.
Verification: 8/8 pass; lint-no-source-grep clean.
* fix(#3019): query --help reaches handler instead of short-circuiting to top-level usage
The query argv parser in sdk/src/cli.ts harvested -h/--help as a global
flag and main() short-circuited dispatch when args.help was true. Net
effect: every `gsd-sdk query <anything> --help` printed top-level USAGE
instead of contextual subcommand help. There was no path for users to
discover what arguments a query subcommand accepts — they had to trigger
"required" errors by trial and error.
Two-layer fix:
1. sdk/src/cli.ts (parseCliArgsQueryPermissive)
- Push -h / --help onto queryArgv instead of consuming them silently,
so the registered handler / gsd-tools.cjs fallback gets to interpret
the flag and render contextual help.
- Only honor the global help flag when there is NO real subcommand to
dispatch to (i.e. queryArgv contains only help flags). Preserves
`gsd-sdk query --help` → top-level USAGE while letting
`gsd-sdk query phase add --help` reach the handler.
2. get-shit-done/bin/gsd-tools.cjs
- Render top-level usage on --help / -h / -? / --usage instead of
erroring with "Unknown flag". The discovery hint in the usage text
points users at the working method (run without args → error names
required arguments) and references #3019 for tracking subcommand-
level help printers.
- --version remains rejected (no discovery use-case).
#1818 anti-hallucination invariant preserved: the destructive command
NEVER executes when --help is present. The new shape returns success:true
+ usage on stdout instead of the old success:false + error on stderr —
both satisfy "destructive command did not run", and the new shape also
restores discoverability.
Tests:
- sdk/src/cli.test.ts: 4 new vitest cases covering #3019 — query argv
parser keeps --help with subcommand, parses -h short flag, preserves
bare `query --help` top-level behavior, preserves --help position when
intermixed with other query flags.
- tests/bug-3019-help-passthrough.test.cjs: 5 node:test cases on the
fallback — bare gsd-tools (no args) errors with usage; --help renders
usage on stdout exit 0; -h same; subcommand --help renders usage; usage
hint mentions discovery method (without prose substring matching —
parses into typed sections).
- tests/bug-1818-unknown-flags.test.cjs: rewritten to assert the new
invariant ("destructive command did not run" + "usage was rendered")
instead of the old shape ("--help is rejected with non-zero exit").
Each destructive test seeds a sentinel artifact (phase dir, slug
output) and asserts it survives.
Verification:
- 47/47 vitest pass on sdk/src/cli.test.ts
- 5/5 pass on tests/bug-3019-help-passthrough.test.cjs
- 8/8 pass on tests/bug-1818-unknown-flags.test.cjs (rewritten)
- 6763/6763 pass on full node:test suite
- lint-no-source-grep clean (0 violations)
Closes#3019
* fix(#3019): SDK fallback forwards plain-text help, broader usage list (CR)
CodeRabbit on PR #3026 (4 findings — 1 Major outside-diff, 2 inline,
1 nitpick):
1. **Major outside-diff** — sdk/src/cli.ts:442-454. The fallback path
that delegates to gsd-tools.cjs called parseCliQueryJsonOutput
(JSON.parse) on stdout. Now that gsd-tools renders plain-text usage
on --help, JSON.parse threw "Unexpected token 'U'". Wrapped the
parse in try/catch — on parse failure, forward the plain stdout
verbatim so subcommand help reaches the user. Regression test:
tests/bug-3019-help-passthrough.test.cjs spawns the built SDK and
asserts `gsd-sdk query phase --help` exits 0, stdout contains the
gsd-tools usage, and stderr does NOT contain a JSON-parse error.
2. .changeset/help-passthrough.md:3 — `pr: TBD` → `pr: 3026`.
3. gsd-tools.cjs:346 (TOP_LEVEL_USAGE):
- Removed self-referencing `#3019` link (immediately stale after
this PR merges).
- Expanded Commands list from 17 → all 47 dispatcher cases:
agent-skills, audit-open, audit-uat, check-commit, commit, …
phase, phases, roadmap, milestone, validate, progress, intel,
graphify, learnings, etc. — the bulk of the surface that was
previously unreachable via --help discovery.
4. Nitpick: `isUsageOutput` was duplicated in bug-1818 and
bug-3019-help-passthrough tests. Moved to tests/helpers.cjs with
structural-comment, removed both duplicates.
Verification: 47/47 vitest pass, 14/14 regression tests pass,
6764/6764 full suite, lint clean.
* test(#3019): use t.skip() instead of bare return when SDK not built (CR)
CodeRabbit follow-up on PR #3026:
The integration test guarded against missing sdk/dist/cli.js with a
bare `return;` — node:test counts that as a passing test (0 assertions
exercised, 0 failures). On a CI checkout that hasn't run the SDK build,
the #3026 regression test silently green-lit and no signal ever
surfaced that the integration check was skipped.
Switched to `t.skip(...)` via the test context parameter so the
omission shows up in the test report. The unit-level fix
(sdk/src/cli.ts) is still covered by vitest, so the skip only affects
the end-to-end spawn-built-SDK check.
Verification: 6/6 pass when SDK is built; 5 pass + 1 skip when not.
* fix(#3017): codex SessionStart hook uses absolute node, not bare 'node'
PR #3002fixed#2979 for settings.json-based managed JS hooks (Claude
Code, Gemini, Antigravity) by routing through buildHookCommand() →
resolveNodeRunner(), emitting the absolute Node binary path so hooks
resolve under GUI/minimal-PATH runtimes (/usr/bin:/bin:/usr/sbin:/sbin)
where nvm/Homebrew/Volta-installed node is not on PATH.
The Codex install path bypassed both helpers — line 7935 of bin/install.js
wrote `command = "node ${path}"` directly into config.toml. So Codex
SessionStart hook still failed with exit 127 ("node: command not found")
under the same minimal-PATH conditions PR #3002 was meant to close.
Fix:
- Add buildCodexHookBlock(targetDir, { absoluteRunner, eol }) — a pure
helper that emits the toml hook block with the absolute runner. Returns
null when absoluteRunner is null so the caller skips registration with
a warning instead of writing a broken bare-node hook.
- Add rewriteLegacyCodexHookBlock(content, absoluteRunner) — mirror of
rewriteLegacyManagedNodeHookCommands for the toml surface, so
reinstall migrates a 1.39.x bare-node config.toml to the absolute form.
Uses basename equality (CODEX_MANAGED_HOOK_BASENAMES set) so user-
authored bare-node hooks are left alone.
- Replace the inline string-concat at line 7935 with a call to the new
helper, threaded with the detected line ending so CRLF files stay CRLF.
- On the codex reinstall path, call rewriteLegacyCodexHookBlock first so
existing bare-node entries get migrated before the new entry is added.
Tests:
- bug-3017-codex-hook-absolute-node.test.cjs (9 tests, all typed-IR):
- buildCodexHookBlock emits absolute runner, parses to expected fields
- returns null on missing runner (caller skips)
- integrates with resolveNodeRunner() in the live process
- rewriteLegacyCodexHookBlock migrates managed bare-node entries
- leaves user-authored bare-node hooks alone (basename allowlist)
- leaves entries with absolute runner unchanged (idempotent)
- returns content unchanged when absoluteRunner is null
- codex-config.test.cjs e2e expectation updated to match new shape:
parsed.hooks.SessionStart[0].hooks[0].command now equals
'"<process.execPath>" "<hookPath>"' instead of 'node <hookPath>'.
Verification:
- 9/9 pass on the new regression test
- 179/179 pass across all codex-touching test files
- 6767/6767 pass on full suite, lint-no-source-grep clean
- Adheres to typed-IR / CONTRIBUTING.md "Prohibited: Raw Text Matching":
parseCodexHookBlock returns a typed record; assertions are on
structured fields (runner, hookPath, type, hasMarker), not stdout regex.
Closes#3017
* test(#3017): tighten runner assertions to exact process.execPath (CR)
CodeRabbit on PR #3022 (3 findings, 2 actionable + 1 nitpick):
1. .changeset/codex-bare-node-fix.md:3 — replace `pr: TBD` with
`pr: 3022` so changeset metadata is traceable.
2. tests/bug-3017-codex-hook-absolute-node.test.cjs:81-146 — the test
asserted `parsed.runner !== 'node'` and `parsed.runner.includes('/node')`,
which would false-positive on any absolute path containing '/node'
(e.g. /Users/x/notnode/foo). Tightened to compare against the EXACT
absolute path supplied by the caller (after stripping toml + JSON
escape layers via a new unescapeRunner() helper). The live-process
integration test now compares against process.execPath exactly. The
rewriteLegacyCodexHookBlock test also uses exact-equality.
3. Nitpick (skipped): use repository's TOML parser for parsing instead
of bespoke regex. The hand-rolled parser is small, scoped, and
fully tested by these structural assertions; pulling in a TOML lib
for tests would create a circular dependency on the SUT (the
installer's own parser). Leaving as-is.
Verification: 9/9 pass on regression test, 6767/6767 full suite, lint clean.
* fix(#3010): post-install message and docs use /gsd-update --reapply
PR #2824 consolidated 86 skills into ~58, removing the standalone
/gsd-reapply-patches command and folding it into a flag on /gsd-update
(/gsd-update --reapply). The 1.39.1 hotfix (#2954) updated help.md
but missed three other surfaces that still recommended the dead form:
1. bin/install.js reportLocalPatches() — runtime emitter shown after
every install with backed-up patches. All branches updated:
- claude/opencode/kilo/copilot: /gsd-update --reapply
- gemini: /gsd:update --reapply
- codex: $gsd-update --reapply
- cursor: gsd-update --reapply (mention the skill name)
2. get-shit-done/workflows/update.md — Step 4 prose and the
check_local_patches block both referenced /gsd-reapply-patches.
Replaced with /gsd-update --reapply (with backticks around the
command per CR feedback for copy/paste UX).
3. Localized docs (en/ja-JP/ko-KR/zh-CN) — 14 files across
ARCHITECTURE.md / COMMANDS.md / FEATURES.md / INVENTORY.md /
USER-GUIDE.md / manual-update.md still listed the removed command.
Tests:
- bug-3010-reapply-patches-references.test.cjs (4 tests): scans
bin/install.js's reportLocalPatches body, every workflow file, and
every doc (excluding CHANGELOG history and help.md's deprecation
notice) for the removed command form, and verifies each runtime
branch emits the consolidated form via captured console output.
- tests/copilot-install.test.cjs:1081-1115 — stale assertions that
hard-coded the removed string updated to assert /gsd-update --reapply.
Verification: 115/115 pass across both files.
Co-authored-by: Patrick Clery <patrick@patrickclery.com>
Closes#3010
* test(#3010): broaden dead-command scan + tighten runtime exact-match
CodeRabbit follow-up findings on #3012:
1. Workflow + docs scans only matched "/gsd-reapply-patches", missing
the gemini ("/gsd:reapply-patches") and codex ("$gsd-reapply-patches")
spellings. A regression that re-introduced either form in localized
docs would have passed silently. Extracted a DEAD_COMMAND_PATTERNS
array + findDeadCommands() helper used by both scans, so all three
removed forms are checked uniformly. Match output also reports which
spellings hit, for faster diagnosis.
2. reportLocalPatches runtime test asserted output.includes('update --reapply'),
which is too loose — a malformed prefix like '/gsd:update --reapply' on
the claude branch would have passed. Replaced with an exact
{runtime → expected token} map covering all 7 branches:
claude/opencode/kilo/copilot → /gsd-update --reapply
gemini → /gsd:update --reapply
codex → $gsd-update --reapply
cursor → gsd-update --reapply
Negative assertion also runs DEAD_COMMAND_PATTERNS against output for
every runtime, so dead forms can't slip in regardless of branch.
Verification: 4/4 pass on bug-3010-reapply-patches-references.test.cjs.
* test(#3010): add prefix-absence guard for cursor runtime (CR follow-up)
CodeRabbit (Minor): the cursor expected token "gsd-update --reapply" is
a substring of every prefixed form ("/gsd-update --reapply" for claude/
opencode/kilo/copilot, "\$gsd-update --reapply" for codex). The positive
output.includes(expectedToken) check therefore can't distinguish correct
cursor output from a regression where the installer emits a prefixed
form for cursor — both pass the substring check.
Add an explicit prefix-absence assertion for cursor that fails if any
of /, \$, or : appears immediately before "gsd-update --reapply" in
output. The gemini form ("/gsd:update --reapply") doesn't share the
substring (gsd:update vs gsd-update) so it's already caught by the
positive includes failing on cursor's expected bare token.
Verification: 4/4 pass.
---------
Co-authored-by: Patrick Clery <patrick@patrickclery.com>
* fix(#3011): actionable SDK-not-on-PATH diagnostic with shim location and shell-specific commands
The previous diagnostic was a generic 'GSD SDK files are present but
gsd-sdk is not on your PATH' message with no concrete path or
shell-specific PATH-export command. Windows users reported that they
couldn't find where the shim was written and didn't know how to add
it to PATH for each shell (PowerShell vs cmd.exe vs Git Bash vs WSL
all read PATH from different sources).
New formatSdkPathDiagnostic({ shimDir, platform, runDir }) helper
returns a typed IR:
- shimLocationLine: explicit 'Shim written to: <path>'
- actionLines: platform-specific PATH-export commands
- Windows: 3 lines (PowerShell, cmd.exe, Git Bash with backslash->/
translation for bash compatibility)
- POSIX: 1 line (export PATH=...)
- npxNoteLines: 'you're running via npx ... npm install -g instead'
when runDir is under an _npx cache segment (where the shim may be
written to a temp dir that won't persist for the user's interactive
shell)
- isNpx, isWin32: structured booleans for assertions
Renderer in install.js just emits each line. Tests assert on the
typed IR fields directly (no source-grep, no console-output parsing).
Tests: 12 cases across 5 suites covering Windows shell flavors
(PowerShell preserves backslashes, Git Bash translates to forward),
POSIX exports, null-shimDir fallback to npm install -g advice, npx
detection on both path-separator conventions, and IR shape contract.
Closes#3011
* fix(#3011): cmd.exe guidance uses powershell -Command, not setx
CodeRabbit flagged the cmd.exe action line as a Major Windows
correctness bug:
setx PATH "${shimDir}; %PATH%"
Two failure modes:
1. setx silently truncates the registry value above 1024 chars,
permanently storing the truncated PATH and breaking applications
until restored from the registry backup or fixed manually.
2. %PATH% expands to its current literal value at the moment setx
runs, and the result is written as REG_SZ instead of REG_EXPAND_SZ.
Lazy references like %SystemRoot% are baked in as literals, so
future changes to those variables stop propagating.
Replace with the same SetEnvironmentVariable call already used for
the PowerShell line, invoked through `powershell -Command` so cmd.exe
users get a safe command without us recommending two different APIs.
* fix(#3011): escape shimDir for PowerShell, bash, and POSIX export
CodeRabbit (Minor): a Windows username with a single quote (e.g.
"C:\Users\O'Neil\AppData\Roaming\npm") would interpolate raw into the
suggested commands, producing unparseable shell input the user can't
fix without understanding the bug.
Each shell context needs a different escape:
- PowerShell single-quoted strings: '' is the literal-quote escape.
Apply to both the PowerShell line and the cmd.exe line (which
delegates to PowerShell).
- Git Bash, where the path lives inside an outer single-quoted echo:
'\'' (close-quote, escaped-quote, reopen-quote) embeds a literal
single quote. The slash-conversion (\\ → /) still applies first.
- POSIX export (Linux/macOS) inside double quotes: escape \, $, ",
and backtick so the path is copied verbatim. $PATH lives outside
the escape and still expands at paste time.
Regression test: bug-3011-sdk-path-diagnostic.test.cjs locks in the
expected escape sequence for all three shell flavors.
* test(#2974): migrate 8 test files to typed-IR assertions
Replaces raw stdout/stderr substring matching with structured-field
assertions per CONTRIBUTING.md "Prohibited: Raw Text Matching on Test
Outputs". Adds shared infrastructure for typed error emission so this
pattern is the easy path going forward.
Shared infrastructure:
- core.cjs: ERROR_REASON frozen enum + setJsonErrorMode/getJsonErrorMode
- gsd-tools.cjs: --json-errors CLI flag, parsed before subcommand dispatch
- config.cjs: typed reasons at all 7 error sites
- graphify.cjs: GRAPHIFY_REASON enum + reason/timeout_ms in execGraphify result
- bin/install.js: pure buildSdkFailFastReport() IR builder + renderer
- hooks/gsd-session-state.sh, gsd-phase-boundary.sh: emit Claude Code
hookSpecificOutput JSON envelope with typed state_present/config_mode/
planning_modified/file_path fields (no-op when hooks.community is off)
Test migrations (all pass, 171 tests across the 8 files):
- bug-2649-sdk-fail-fast: assert on ir.reason / ir.context / ir.fix_command
- bug-2687-config-read-warning-parity: assert.equal stderr === ''
- bug-2796-arg-parsing-regression: assert on result.json.updated/.phase
- bug-2838-summary-rescue: parse rescue footer, assert mtime invariant
- bug-2943-config-get-context-window: parse JSON, assert ERROR_REASON.CONFIG_KEY_NOT_FOUND
- graphify: assert reason === GRAPHIFY_REASON.ENOENT/TIMEOUT
- hooks-opt-in: parse hookSpecificOutput, assert typed fields
- security-scan: reclassified as source-text-is-the-product (scan label
output and CI workflow YAML ARE the deployed contract)
Verification: lint-no-source-grep clean (0 violations), full suite
6741/6741 pass.
Closes#2974
* test(#2974): address CR feedback — typed code field, robust idempotency
Two CodeRabbit findings on #3016 addressed:
1. tests/hooks-opt-in.test.cjs:355 (Minor, inline) —
parsed.reason.includes('Conventional Commits') was still substring
matching after the typed-IR migration. Fixed at the source: the
gsd-validate-commit hook now emits a typed `code` field
('CONVENTIONAL_COMMITS_VIOLATION', 'COMMIT_SUBJECT_TOO_LONG')
alongside the human-readable `reason`. Test asserts strictEqual
on the code; the prose copy is no longer part of the test contract.
2. tests/bug-2838-summary-rescue-gitignored-planning.test.cjs:224-250
(Outside-diff) — mtimeMs alone can stay unchanged on coarse-grained
filesystems (HFS+, FAT) when two rewrites land within the same
timestamp tick, falsely passing the idempotency assertion.
Replaced with a full snapshot (mtimeMs, ctimeMs, size, ino, sha256
of contents) compared via assert.deepStrictEqual — the hash
catches any rewrite the timestamp would miss.
Verification: 30/30 pass on the two affected files; lint-no-source-grep
clean (0 violations across 368 test files).
* fix(#2979): emit absolute node path in managed hooks for GUI/minimal-PATH runtimes
Installer-emitted hook commands started with bare 'node' which works
under interactive shells (nvm/Homebrew/Volta on PATH) but fails in
GUI-launched runtimes that start with /usr/bin:/bin:/usr/sbin:/sbin.
Every managed JS hook (gsd-check-update, gsd-statusline, gsd-context-monitor,
gsd-prompt-guard, gsd-read-guard, gsd-read-injection-scanner,
gsd-workflow-guard) failed with /bin/sh: node: command not found —
silently disabling update checks, statusline, and security guards.
Fix: new resolveNodeRunner() helper returns process.execPath (the
absolute path of the Node binary running the installer) forward-slash-
normalized and double-quoted. Used in:
- buildHookCommand() for global installs (.js runner)
- local-install code paths for all 7 managed JS hooks
.sh hooks keep bare 'bash' — /bin/bash is in the POSIX standard PATH
and always resolves under minimal-PATH GUI launches.
Tests: bug-2979-hook-absolute-node.test.cjs parses emitted commands
into { runner, hookPath } records and asserts:
- resolveNodeRunner returns quoted absolute forward-slash node path
- .js hooks emit absolute runner (default and portableHooks modes)
- .sh hooks still emit bare 'bash'
Closes#2979
* chore(#2979): add changeset fragment for PR #3002
* chore(#2979): add changeset fragment for PR #3002
* fix(#2979): resolveNodeRunner returns null on missing execPath; rewrite legacy bare-node managed hooks (CR feedback)
CodeRabbit on PR #3002 caught two issues:
1. resolveNodeRunner fell back to bare 'node' when process.execPath was
empty -- recreating the exact #2979 bug. Now returns null. Callers
(buildHookCommand and the local-install code paths) check for null
and skip registration rather than emit a broken command.
2. The original #2979 fix only updated NEWLY registered hooks. Existing
bare-node managed hook entries from pre-#2979 installs stayed
broken across reinstalls. New rewriteLegacyManagedNodeHookCommands
walks settings.hooks and rewrites any managed-hook entry that starts
with bare 'node ' to use the absolute runner. Filename allowlist
(gsd-check-update.js, gsd-statusline.js, gsd-context-monitor.js,
gsd-prompt-guard.js, gsd-read-guard.js, gsd-read-injection-scanner.js,
gsd-workflow-guard.js) ensures user-authored bare-node hooks are
left untouched.
Tests: bug-2979-hook-absolute-node.test.cjs grows by 8 cases:
- 5 for the migration walker (rewrites managed entries, leaves quoted-
runner entries alone, leaves user-authored entries alone, leaves .sh
entries alone, no-ops on null runner).
- 2 for resolveNodeRunner returning null on empty execPath.
- 1 for buildHookCommand returning null when execPath unavailable.
* chore(#3002): 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(#2979): guard hook + statusline pushes against null commands (CR follow-up)
CodeRabbit on PR #3002 found an outside-diff issue: when
resolveNodeRunner() returns null, every dependent *Command becomes
null, but the registration sites still pushed { type: 'command',
command: null } entries onto settings.hooks. The runtime's hook
schema rejects null commands and the failure surfaces as a confusing
parse error.
Fix:
- One unified warning at the top of configureSettings when ANY JS-hook
command resolves null (operator sees the cause once instead of per-hook).
- Each of the 6 managed JS hook registration if-clauses now guards on
the *Command variable being truthy: && updateCheckCommand,
&& contextMonitorCommand, && promptGuardCommand, && readGuardCommand,
&& readInjectionScannerCommand, && workflowGuardCommand.
- Statusline registration adds an else-if (!statuslineCommand) clause
with its own warn before the settings.statusLine write site.
Tests: bug-2979-hook-absolute-node.test.cjs grows by 7 cases
(6 per-hook structural assertions parsing install.js for the
`fs.existsSync(<file>) && <command>` shape, plus 1 statusline
guard-precedes-write test).
* fix(#2979): defense-in-depth validateHookFields before writeSettings (CR)
CodeRabbit on PR #3002 (post-fix-up review): replace source-grep
structural tests with behavioral assertions on the settings object.
The push-site `&& <command>` guards (commit ce696c64) prevent null
commands from being pushed in the first place. As a defense-in-depth
backstop, install.js now runs validateHookFields(settings) right
before writeSettings(); validateHookFields already filters
{type:'command', command: null} entries (line 5884), so even if my
push-site guards ever regress, no null-command entries reach disk.
Tests: replaced the 7 install.js source-grep tests with 8 truly
behavioral tests:
- validateHookFields strips null-command entries for each of the 6
managed JS hook shapes (parameterized by event + matcher)
- validateHookFields drops the entry entirely when all its hooks are
null-command
- validateHookFields preserves agent-type hooks while stripping
null-command sibling hooks in the same entry
These tests exercise the actual function the production code uses,
not its source representation. They survive future refactors of the
registration call sites.
* fix(#2979): tighten managed-hook migration to basename equality (CR)
CodeRabbit on PR #3002 (post-fix-up review): the previous
`trimmed.includes(name)` matcher had a false-positive vector. A
user-authored hook whose path contained a managed filename as a
substring (e.g. /home/me/scripts/wraps-gsd-check-update.js-helper.js)
would be unconditionally rewritten with the GSD runner, replacing
the user's bare `node` with our absolute path -- silently mutating
their hook configuration.
Fix: parse the command into <runner> <script-token> with the
script-token allowed to be quoted (single or double) or bareword.
Extract the path inside quotes, take the basename (handles both
forward and backslash separators on Windows), and match against
MANAGED_HOOK_FILES via Set.has() — exact equality, not substring.
Tests: bug-2979 grows by 4 cases:
- user hook with managed-filename-as-substring is NOT rewritten
- single-quoted path: rewritten correctly
- bareword path: rewritten correctly
- Windows backslash path: basename extraction works
* fix(#2973): /gsd-profile-user writes dev-preferences.md to skills/ not legacy commands/gsd/
v1.39.0's install summary claimed the legacy ~/.claude/commands/gsd/
directory had been removed in favor of skills-only architecture, but
the cmdGenerateDevPreferences writer at profile-output.cjs:781 still
defaulted to the legacy path. Every /gsd-profile-user --refresh
deterministically re-created the legacy directory.
Missed in PR #1540's migration because dev-preferences is a
runtime-generated user artifact, not a GSD-shipped command file.
Fix:
- Writer default: ~/.claude/skills/gsd-dev-preferences/SKILL.md
- profile-user.md Display message + artifact list reference new path
- New migrateLegacyDevPreferencesToSkill(targetDir, saved) installer
helper. Called at all 5 skills-aware install branches. Copies
preserved legacy dev-preferences.md into skills/gsd-dev-preferences/
SKILL.md, but ONLY if no SKILL.md already exists -- never clobbers
user-customized skill content.
Tests: bug-2973-profile-user-skills-path.test.cjs runs the writer in
a subprocess (core.cjs:output uses fs.writeSync(1, ...) which bypasses
in-process stubbing), asserts the writer's command_path field is the
skills location, the file is on disk at that path, the legacy path is
NOT created. Tests for migration helper assert it writes when no skill
exists and skips when one does.
Closes#2973
* chore(#2973): add changeset fragment for PR #3003
* fix(#2973): rephrase comment to avoid cline-install leaked-path lint
The new comment at line 780 of profile-output.cjs literally contained
the string '~/.claude/commands/gsd/' which the cline-install
leaked-path regression test (tests/cline-install.test.cjs:175)
correctly flagged.
Cline transforms .claude/skills/ -> .cline/skills/ in installed .cjs
files but does not transform .claude/commands/. The new comment talks
about the legacy 'commands/gsd' subdirectory without the ~/.claude/
prefix, so the lint passes. The path semantics are unchanged -- the
runtime construction at line 787 still uses path.join(os.homedir(),
'.claude', 'skills', ...) which the lint regex does not match.
* test(#2973): add timeout to spawnSync to prevent CI hangs (CR feedback)
CodeRabbit on PR #3003: without a timeout, a regression that hangs the
writer or dispatcher would block CI indefinitely. Added a 30s timeout
(generous for what should complete in <1s) and an explicit signal
assertion so a timeout trip surfaces as a clear test failure with
context rather than a hung worker.
* test(#2973): add allow-test-rule annotation for legitimate product-text parsing
The new var-binding lint from #2982/#2985 caught readFileSync(...).match()
and readFileSync(...).includes() calls in this test. Both are legitimate
structural assertions against the product workflow markdown, not source-grep:
- match() extracts the path from a structured Display: "..." line and
asserts on the typed path value (same pattern as bug-2470's installer
scanForLeakedPaths regex test).
- includes() asserts the absence of a legacy path literal.
profile-user.md IS the shipped workflow artifact, and its Display: line
IS what the user sees. Per the existing test-rigor convention, this is
the source-text-is-the-product justification category.
Annotated with allow-test-rule citing that category.
* chore(#3003): 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(#2973): preserve user-owned gsd-dev-preferences skill across wipe (CR)
CodeRabbit on PR #3003 caught a real bug: copyCommandsAsClaudeSkills()
wipes ALL gsd-* skill directories at the top of every install, then
reinstalls from the package source. Since gsd-dev-preferences is
user-generated (written by /gsd-profile-user --refresh) and NOT
shipped by the npm package, the wipe deletes the user's customized
SKILL.md with nothing to restore from.
Fix: USER_OWNED_SKILLS allow-list in copyCommandsAsClaudeSkills.
Snapshot files under skills/gsd-dev-preferences/ before the wipe,
restore after. Same preserve/restore pattern as PR #1924.
Tests: bug-2973 grows by 2 cases:
- user-customized SKILL.md survives the wipe
- non-user-owned gsd-* skills are still wiped (preservation is opt-in)
* fix(#2990): gsd-code-fixer worktree attaches to a new branch, not the user-checked-out one
The agent's setup_worktree step ran 'git worktree add "$wt" "$branch"'
where $branch was the user's currently-checked-out branch in the main
repo. Git refuses to check out the same branch in two worktrees by
default, so the call failed before any review fix could be applied.
This is the next-layer failure after #2686 (foreground/background race)
and #2839 (transactional cleanup): the isolation strategy was correct
in design, blocked only by git's same-branch protection.
Fix:
- Create a new branch 'gsd-reviewfix/${padded_phase}-$$' from the
current branch tip and attach the worktree to it via
'git worktree add -b "$reviewfix_branch" "$wt" "$branch"'.
- Cleanup tail is now four steps:
1. 'git -C "$main_repo" merge --ff-only "$reviewfix_branch"'
-- captures the agent's commits on the user's branch. --ff-only
fails loudly on divergence (concurrent commits to $branch); the
temp branch is preserved for manual merge.
2. 'git worktree remove "$wt" --force'.
3. 'git -C "$main_repo" branch -D "$reviewfix_branch"' ONLY if
ff-only succeeded.
4. 'rm -f "$sentinel"' last (preserves #2839 transactional ordering).
- Recovery sentinel JSON now records reviewfix_branch alongside
worktree_path so a re-run after interruption cleans both the orphan
worktree and the orphan temp branch.
Regression test: tests/bug-2990-code-fixer-worktree-branch.test.cjs
parses the agent .md into structured 'git worktree add' invocation
records (skipping occurrences inside markdown inline-code or bash
comments -- those are citations of the OLD pattern, not executable)
and asserts the structural invariants on the new pattern.
Closes#2990
* chore(#2990): add changeset fragment for PR #3001
* chore(#2990): add changeset fragment for PR #3001
* fix(#2990): correct main_repo parsing and ff_status capture (CR feedback)
CodeRabbit on PR #3001 caught two real bugs in the cleanup tail:
1. `awk '/^worktree / { print $2 }'` truncates paths containing
spaces. /path/with spaces/repo becomes /path/with. Replaced with
`sub(/^worktree /, ''); print` which strips the prefix and
preserves the full path.
2. `if ! git merge ...; then ff_status=$?` captures the exit of the
`!` operator (always 1 on failure), not the merge command's exit
code. Restructured to `if cmd; then ff_status=0; else ff_status=$?`
so the else-branch captures the real merge exit code.
Tests still pass: bug-2990 structural assertions on the agent .md
content unchanged.
* fix(#2990): recovery extracts reviewfix_branch and deletes orphan branch (CR)
CodeRabbit on PR #3001 found two issues:
1. (Major) Recovery code only extracted worktree_path from the sentinel.
If a prior run died after `git worktree remove` but before
`git branch -D`, the orphan reviewfix branch survived forever. The
sentinel records reviewfix_branch (line 272) and the docs claim
recovery deletes it, but the code didn't.
Fixed: emit BOTH worktree_path and reviewfix_branch from the parser
(newline-separated), capture each into shell vars, and call
`git branch -D "$prior_branch" 2>/dev/null || true` after worktree
removal but before sentinel deletion.
2. (Quick win) The bug-2990 test used regex .test() against the raw
markdown, which would have been satisfied by prose mentioning the
token. Restructured to:
- parseCleanupGitInvocations() returns ordered records with structured
fields (verb, targetsReviewfixBranch, isMergeFfOnly, isBranchDelete)
- assert exactly-one merge --ff-only AND exactly-one branch -D
- assert merge precedes branch-delete in execution order
- parse the sentinel JSON.stringify call to extract field names and
assert reviewfix_branch is among them
Added 2 new tests for the recovery-block invariant: parses the recovery
node -e block and asserts it extracts parsed.reviewfix_branch alongside
parsed.worktree_path; and asserts the recovery shell calls
`git branch -D "$prior_branch"`.
* test(#2990): add allow-test-rule annotation for product-text parsing (CR follow-up)
The lint-tests CI catch flagged md.match() in the new structural-IR
test suite. The .match() calls extract typed fields (cleanup-tail
git invocation records, sentinel JSON field names, recovery-block
node script content) from agents/gsd-code-fixer.md — which IS the
deployed agent product. Asserting on those typed fields tests the
runtime contract, not source code internals.
source-text-is-the-product is the correct classification per the
existing convention (matches thread-session-management.test.cjs and
the others reclassified in PR #2985's CR follow-up).
* chore(#3001): 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(#2994): move verify-reapply-patches.cjs to get-shit-done/bin/ so installer ships it
scripts/verify-reapply-patches.cjs (added in #2972 to close the
verified-yes-without-checking gap from #2969) shipped in the npm tarball
but never reached user installs: bin/install.js copies get-shit-done/
recursively but does not copy the top-level scripts/ directory.
Effect: every fresh install hit `Cannot find module …/scripts/verify-reapply-patches.cjs`
on Step 5 of /gsd-reapply-patches. The whole point of moving
verification out of LLM-driven prose into a deterministic script is
undone if the script does not resolve at runtime.
Fix: move the script to get-shit-done/bin/verify-reapply-patches.cjs
(same pattern as gsd-tools.cjs and other runtime bin scripts that the
installer ships) and update reapply-patches.md Step 5 to invoke
${GSD_HOME}/get-shit-done/bin/verify-reapply-patches.cjs.
Tests:
- bug-2969 SCRIPT path updated to the new location
- New bug-2994-verify-reapply-patches-installed-path.test.cjs parses
reapply-patches.md into structured invocation records and asserts
every node ${GSD_HOME}/... reference lives under get-shit-done/
(the installed tree). Catches future regressions where someone moves
a runtime-needed script back to scripts/.
Closes#2994
* chore(#2994): add changeset fragment for PR #3000
* chore(#2994): add changeset fragment for PR #3000
* docs(#2994): update verifier-script-location comment to reflect new path (CR)
CodeRabbit on PR #3000: the parenthetical at line 278 still said the
script ships under scripts/, but this PR moved it to get-shit-done/bin/.
Updated the prose to reference the new location and the installer
target path.
* chore(#3000): 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(#2992): deterministic latest-version check — package name is a constant, not LLM choice
The /gsd-update workflow's check_latest_version step was prescribed in
LLM-driven prose: "run `npm view get-shit-done-cc version`". The
executing model could and did shortcut the prescription and invent
npm queries against name-shaped guesses — `@get-shit-done/cli`,
`get-shit-done-cli`, `gsd` — all of which 404 or, worse, return an
unrelated typosquat (the 2016 `get-shit-done` timer package). Same
architectural anti-pattern as #2969 (Hunk Verification Gate where
the LLM filled `verified: yes` without checking).
Implementation built TDD per #2992:
get-shit-done/bin/check-latest-version.cjs
- PACKAGE_NAME = 'get-shit-done-cc' as a module constant; not
parameterised, not exposed for override.
- checkLatestVersion({ spawn? }) returns
{ ok: bool, version?: string, reason: CHECK_REASON.X, detail? }
via a frozen enum: OK / FAIL_NPM_FAILED / FAIL_INVALID_OUTPUT.
- --json mode emits the structured record on stdout for the
workflow to parse via jq.
- Windows-aware: uses { shell: process.platform === 'win32' }
since npm is npm.cmd on Windows (same lesson as #2962).
- Stored under get-shit-done/bin/ (not top-level scripts/) because
that path IS in the user's installed config dir; top-level
scripts/ ships in the npm tarball but is not copied into
~/.claude/ at install time.
tests/bug-2992-check-latest-version.test.cjs
- 7 tests, all assertions on the typed CHECK_REASON enum + the
structured record. Injectable spawn function so no real npm
process is invoked. Covers OK, npm-non-zero, invalid-output,
empty-output, pre-release semver, PACKAGE_NAME constant lock,
enum-shape lock.
get-shit-done/workflows/update.md
- check_latest_version step rewritten to call the script via
`node "${GSD_HOME}/get-shit-done/bin/check-latest-version.cjs"
--json` and parse the structured response with jq. Explicit
"Do NOT run `npm view` or `npm search` directly" guidance
cites #2992 so future contributors understand why.
Closes#2992
* fix(#2992): trailing slash on GSD_HOME default to satisfy bare-path lint
The bug-2470 regression test scans update.md for bare `$HOME/.claude`
references (no trailing slash). The PR added one in the new
check_latest_version step. Fix: trailing slash on the default value
(`${GSD_HOME:-$HOME/.claude/}`). Bash POSIX collapses the resulting
double slash; the lint pattern's negative lookahead is now satisfied.
* fix(#2992): emit GSD_DIR from get_installed_version, use it in check_latest_version
Addresses CodeRabbit feedback: the previous `${GSD_HOME:-$HOME/.claude/}`
fallback hardcoded the Claude runtime path, which silently breaks for
non-Claude runtimes (gemini, codex, opencode, kilo).
Fix:
- get_installed_version now emits a 4th line with the resolved config
dir ($LOCAL_DIR or $GLOBAL_DIR), captured by callers as GSD_DIR.
- check_latest_version uses $GSD_DIR/get-shit-done/bin/check-latest-version.cjs.
Empty GSD_DIR (UNKNOWN scope) skips the version check and falls
through to fresh-install path.
This keeps the package name deterministic (#2992) AND respects the
detected runtime, instead of assuming Claude.
* chore(#2992): add changeset fragment for PR #2993
* chore(#2992): add changeset fragment for PR #2993
* fix(#2992): consolidate LATEST_RESULT parsing inside the GSD_DIR guard
CodeRabbit on PR #2993: the previous structure separated the GSD_DIR
guard from the jq parsing, so when GSD_DIR was empty the parsing block
ran against an unset LATEST_RESULT and produced misleading 'couldn't
check for updates' diagnostics instead of clean 'no_install_detected'.
Move all field assignments inside the conditional so the skip path
seeds LATEST_OK=false, LATEST_VERSION='', LATEST_REASON='no_install_detected',
and LATEST_STATUS=0 atomically.
* fix(#2992): emit GSD_DIR in early-return; add code-block lang and spawnSync timeout (CR)
CodeRabbit on PR #2993 caught three issues:
1. (Major) The early-return path in get_installed_version (PREFERRED_CONFIG_DIR
fast path) only echoed 3 lines, but PR #2993 changed the contract to 4
(GSD_DIR is now line 4). Downstream check_latest_version misread valid
installs as UNKNOWN. Added `echo "$PREFERRED_CONFIG_DIR"` before exit 0.
2. (Minor) Markdown MD040: fenced code block at line 310 was missing a
language identifier. Added ```text.
3. (Quick win) spawnSync('npm view ...') had no timeout, so a hung network
could block /gsd-update indefinitely. Added 15s timeout; on timeout
spawnSync returns with signal !== null and the existing failure path
emits FAIL_NPM_FAILED.
* fix(#3008): kill cross-process race in install-minimal:307 mid-copy test
Old shape compared listTmpStageDirs() snapshots before/after the
mid-copy throw. Under scripts/run-tests.cjs --test-concurrency=4,
tests/install-minimal-all-runtimes.test.cjs runs in a parallel
subprocess and also creates gsd-minimal-skills-* dirs in shared
os.tmpdir(). The parallel process's create/remove activity between
this test's two snapshots caused deterministic failure when timing
aligned -- presented as 'flaky' but is a real race.
CI failure data (PR #2993 run 25238555786):
expected (before): ['gsd-minimal-skills-km1O1O']
actual (after): []
Both processes behaved correctly in isolation. The test was wrong:
it observed a shared filesystem state across processes.
Fix: stub fs.mkdtempSync inside this test to record THIS call's
stage dir path. After the throw, assert fs.existsSync(stagedDir)
=== false. Direct observation of the function's own behavior; no
global tmpdir scan; no parallel-process interference.
Closes#3008
* fix(#2992): distinguish timeout from npm failure; guard empty LATEST_RESULT (CR)
CodeRabbit on PR #2993 (post-fix-up review) caught two improvements:
1. (Low value) check-latest-version.cjs:55-61 — when spawnSync times
out, r.status is null and r.signal is set (e.g. 'SIGTERM'), but
r.stderr is empty. Without the signal-first branch, both timeouts
and genuine npm failures shaped as 'npm exited non-zero' in detail,
making logs ambiguous. Added explicit signal-first branch:
'npm timed out (signal: SIGTERM)'.
2. (Quick win) update.md:284-315 — when node is missing or the script
doesn't exist, LATEST_RESULT is empty. Piping empty to jq parses
without error but leaves LATEST_OK / LATEST_REASON as empty
strings, producing the user-visible diagnostic
'Couldn\'t check for updates (reason: , exit: N)' with a blank
reason. Added an explicit guard that sets LATEST_REASON to
'script_not_found_or_node_unavailable' when LATEST_RESULT is empty,
so operators see a meaningful failure message.
Tests: bug-2992 grows by 2 cases (timeout signal detail + empty
stderr fallback).
* 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.
Old shape compared listTmpStageDirs() snapshots before/after the
mid-copy throw. Under scripts/run-tests.cjs --test-concurrency=4,
tests/install-minimal-all-runtimes.test.cjs runs in a parallel
subprocess and also creates gsd-minimal-skills-* dirs in shared
os.tmpdir(). The parallel process's create/remove activity between
this test's two snapshots caused deterministic failure when timing
aligned -- presented as 'flaky' but is a real race.
CI failure data (PR #2993 run 25238555786):
expected (before): ['gsd-minimal-skills-km1O1O']
actual (after): []
Both processes behaved correctly in isolation. The test was wrong:
it observed a shared filesystem state across processes.
Fix: stub fs.mkdtempSync inside this test to record THIS call's
stage dir path. After the throw, assert fs.existsSync(stagedDir)
=== false. Direct observation of the function's own behavior; no
global tmpdir scan; no parallel-process interference.
Closes#3008
* fix(#2998): populate gsd-pristine/ from install transform pipeline so verifier has a real baseline
saveLocalPatches declared a pristineDir variable and JSDoc'd 'saves
pristine copies to gsd-pristine/' but no code ever wrote there. Effect:
/gsd-reapply-patches Step 5 verifier (#2972) silently fell back to its
over-broad heuristic ('every significant backup line') -- exactly the
silent-success-on-lost-content failure mode #2969 was designed to
prevent.
Fix: new populatePristineDir({...}) helper runs copyWithPathReplacement
(the install transform pipeline) into a tmp staging dir, then copies out
only the modified-file paths into gsd-pristine/. saveLocalPatches now
accepts a pristineCtx and calls the helper when local patches are
detected. Soft-fails on transform errors (logs warning, continues with
empty pristine -- no worse than pre-fix).
Pristine reflects the about-to-install version's content, which is the
right baseline for 'what would survive without the user's modifications'.
Tests: bug-2998-pristine-dir-populated.test.cjs asserts the helper is
exported, no-ops on empty input, writes one pristine file per source-
existing path, skips ghost paths, and produces deterministic output
(byte-identical across runs -- the property pristine_hashes depends on).
Closes#2998
* chore(#2998): add changeset fragment for PR #3004
* fix(#2998): expand pristine to all manifest install roots; clear stale pristine on populate (CR)
CodeRabbit on PR #3004 caught two issues:
1. populatePristineDir only staged packageSrc/get-shit-done/ but
manifest.files records edits under several install roots (commands/,
agents/, hooks/, skills/, root files like .clinerules). Modified
paths outside get-shit-done/ were silently skipped, leaving the
verifier with no baseline for those edits. Fixed by computing the
set of top-level dirs from the modified set and staging each one
that exists in source. Root-level files (no slash) bypass the
transform pipeline and are copied directly.
2. populatePristineDir did not wipe pre-existing gsd-pristine/ before
populating. A previous run's stale pristine could survive into the
current run's diff baseline. Now wipe before populate AND in the
catch path so soft-failures don't leave half-populated data on disk.
Tests: bug-2998-pristine-dir-populated.test.cjs grows by 2 cases:
- agents/ paths are staged and copied (was silently skipped pre-fix)
- mixed get-shit-done/ + agents/ in same modified list both stage
* feat(#2995): post-install path audit for workflow-invoked scripts
Catches the gap class surfaced by #2994: a workflow references a script
via ${GSD_HOME}/<path> that ships in the npm tarball but is not copied
to the user's config dir at install time. Unit tests don't catch it
because they resolve the script via path.join(__dirname, '..', 'scripts',
…) — the source layout, not the deployed layout.
Implementation built TDD per #2995, vertical slices with structured-IR
assertions:
scripts/audit-workflow-script-paths.cjs
- Pure auditWorkflowScriptPaths({ workflowsDir, repoRoot,
installedPrefixes }) returns { ok, findings: [{ workflow, path,
kind }] } via the AUDIT_FINDING enum.
- Two finding kinds: MISSING_FROM_REPO (typo / file deleted) and
NOT_INSTALLED (#2994 class — first segment outside installed
prefixes).
- Tolerates ${GSD_HOME:-...} default-fallback syntax.
tests/bug-2995-post-install-script-paths.test.cjs
- 9 tests across 3 suites:
• Pure-function pass and per-finding-kind detection (5 tests on
synthetic fixtures).
• Real workflow audit (2 tests asserting the actual repo's
get-shit-done/workflows/ has no NEW gaps and KNOWN_GAPS stays
consistent with audit findings).
• Enum shape lock + extractReferences edge cases.
- All assertions on typed AUDIT_FINDING enum / structured records;
zero raw text matching.
- KNOWN_GAPS is a Set keyed on `workflow|path|kind` strings;
currently contains the #2994 entry. The companion test fails if
a KNOWN_GAPS entry no longer matches a real finding (forces the
allow-list to shrink as gaps fix).
The audit immediately catches #2994's gap on `reapply-patches.md`. The
allow-list contains exactly that entry; new gaps fail CI; #2994's fix
will remove the entry as part of the same PR.
Closes#2995
Refs #2994
* chore(#2995): add changeset fragment for PR #2996
* chore(#2995): add changeset fragment for PR #2996
* fix(#2995): emit both NOT_INSTALLED + MISSING_FROM_REPO; clean up fixture leak (CR)
CodeRabbit on PR #2996 found two issues:
1. (Low value) auditWorkflowScriptPaths short-circuited on NOT_INSTALLED,
masking MISSING_FROM_REPO for the same ref. Removed the `continue` so
both findings emit in one run; added a regression test.
2. (Low value) bug-2995 test created tmpRoot in before() but never wrote
into it; per-fixture mkdtempSync dirs leaked. Rooted fixture repos
under tmpRoot so the after() cleanup actually frees them.
* test(#2986): mutation-killer suite for config-schema.cjs (95 typed assertions)
Stryker measured 4.62% mutation score on config-schema.cjs (6 killed,
124 survived). Surviving mutants documented that existing tests were
exercising paths without verifying outputs.
Adds tests/bug-2986-config-schema-mutation-killers.test.cjs (95 tests,
4 suites) targeting each surviving mutant class:
- M1/M4: parameterized isValidConfigKey(key) === true for every member
of VALID_CONFIG_KEYS. Kills static-key-fast-path mutations
(if (VALID_CONFIG_KEYS.has(...)) return true; -> if (false) return true;)
because no static key matches any DYNAMIC_KEY_PATTERN by design.
- M2: representative dynamic-pattern keys (one per pattern). Each matches
exactly one pattern. Kills .some -> .every mutation: with .every, no
single key matches all patterns -> all dynamic keys would be rejected.
- M3: strictEqual against the literal boolean true/false (not assert.ok
truthy checks). Kills polarity-flip mutations.
- Anchor-tightening: keys that differ from valid by one char beyond the
documented shape (trailing dot-segment, empty agent name, non-enum tier,
etc.). Kills regex-loosening mutations on ^, $, charset boundaries.
Tests assert on typed boolean return values from the lib's public surface.
Zero source-grep, zero raw-text matching.
* chore(#2986): add changeset fragment for PR #3005
* test(#2986): use dynamic-only rep key for features pattern (CR feedback)
CodeRabbit on PR #3005: features.thinking_partner is in the static
VALID_CONFIG_KEYS set, so the static fast-path returns true before
DYNAMIC_KEY_PATTERNS.some() is ever called. A Stryker mutant that
removed only the features entry from DYNAMIC_KEY_PATTERNS would
survive because the test only ever exercised the static path for
that key.
Replaced features.thinking_partner with features.some_dynamic_feature
which is NOT in static keys, so isValidConfigKey must reach the
dynamic path to return true. Added a per-rep invariant that asserts
each representative key is NOT a member of VALID_CONFIG_KEYS,
catching this class of mistake at test time on any future
representative-key change.
The three PR templates still asked contributors to tick `CHANGELOG.md
updated`, contradicting the post-#2978 rule (documented in
CONTRIBUTING.md and enforced by scripts/changeset/lint.cjs) that
`CHANGELOG.md` must not be edited directly.
Each checkbox now references `npm run changeset` with the appropriate
`--type` (Fixed/Changed/Added) and notes the `no-changelog` opt-out
label where applicable, so `gh pr create` users land in the correct
workflow by copy-paste.
Closes#3006
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
* feat(#2982): extend no-source-grep lint to catch var-binding readFileSync.includes()
The base lint (scripts/lint-no-source-grep.cjs) only catches
readFileSync(...).<text-method>() chained directly. The much more
common var-binding form escapes it:
const src = fs.readFileSync(p, 'utf8');
// 50 lines later
if (src.includes('foo')) {} // ← still grep, lint missed it
Scan of the test suite found ~141 files using this pattern.
Implementation built TDD per #2982 with structured-IR assertions:
scripts/lint-no-source-grep-extras.cjs
- detectVarBindingViolations(src) — pure detector, two passes:
pass 1 collects vars bound from readFileSync, pass 2 finds any
<var>.<includes|startsWith|endsWith|match|search>( on those vars.
- detectWrappedAssertOkMatch(src) — flags
assert.ok(<expr>.match(...)) which escapes the assert.match rule.
- VIOLATION enum exposes stable codes for tests to assert on.
scripts/lint-no-source-grep.cjs
- Wires the new detectors into the existing per-file check; one
additional violation row per file with the first 3 sample tokens.
tests/bug-2982-lint-var-binding.test.cjs
- 13 tests, all assertions on typed VIOLATION enum / structured
records. Covers all 5 text-match methods, multi-var, no-bind,
string literal (must NOT trigger), wrapped assert.ok(.match),
and assert.match (must NOT double-flag).
Migration backlog (#2974 expanded scope):
- 42 files annotated `// allow-test-rule: source-text-is-the-product`
(legitimate — they read .md/.json/.yml files whose deployed text
IS the product)
- 3 files annotated `// allow-test-rule: pending-migration-to-typed-ir [#2974]`
(read .cjs/.js source — clear migration debt)
- 95 files annotated `pending-migration-to-typed-ir [#2974]` with
`Per-file review may reclassify as source-text-is-the-product
during migration` (mixed — manual review under #2974)
After this lands the lint reports 0 violations on main; new
violations in PRs surface immediately.
Closes#2982
Refs #2974
* test(#2982): fix truncated test name per CR
The label ended with a bare '(' from a copy-paste mishap. Now reads
'does NOT flag .matchAll(...) — matchAll is not match, so
assert.ok(.matchAll(...)) is not flagged'.
* chore(#2982): add changeset fragment for PR #2985
* chore(#2982): add changeset fragment for PR #2985
Both v1.39.0 (stable, tagged 2026-05-01T03:05:33Z) and v1.39.1
(hotfix, tagged 2026-05-01T21:03:54Z) shipped to npm but the
CHANGELOG `[Unreleased]` link still pointed at `v1.38.5...HEAD` and
the entries that landed in v1.39.1 were still un-promoted.
Move the five v1.39.1 hotfix entries (#2917, #2949, #2954, #2962,
#2969) into a new `## [1.39.1] - 2026-05-01` section above
`## [1.38.5]`, with a one-line intro and install snippet matching
the conventions used in earlier dated sections.
Update the `[Unreleased]` link to point at `v1.39.1...HEAD`.
Out of scope (separate cleanup):
- Backfilling a `## [1.39.0]` section. The CHANGELOG never had one;
this PR doesn't make that worse but also doesn't try to invent
release-note text from commit messages.
- The eight v1.39.1 commits without `[Unreleased]` entries
(#2942, #2944, #2924/#2941, #2940, #2947, #2950, #2948, #2957).
These weren't in `[Unreleased]` to begin with; faithful
promotion only moves what was already documented.
- Adding a `docs/RELEASE-v1.39.1.md` file. The `docs/RELEASE-*.md`
pattern in this repo is RC-only; stable patches historically
don't have a counterpart.
The post-v1.39.1 hardening entries (#2980, #2983, #2987 from this
session, plus #2976 which was pre-skipped from the v1.39.1
cherry-pick set after #2980 landed) remain in the new
`[Unreleased]` section — they ship in the next release.
Closes#2989
* feat(#2975): adopt changeset-fragment workflow to eliminate CHANGELOG conflicts
Two PRs that both edit `### Fixed` in CHANGELOG.md always conflict on merge.
Recently bit on #2960/#2972 in the same session — fix-the-conflict-and-rebase
tax. Replace the shared-file model with per-PR fragment files that never
share lines.
Implementation built TDD per #2975, vertical slices with structured-IR
assertions throughout:
scripts/changeset/parse.cjs - fragment text → typed record + frozen
FRAGMENT_ERROR enum (8 tests)
scripts/changeset/render.cjs - fragments → structured IR with
Keep-a-Changelog section ordering
(2 tests)
scripts/changeset/serialize.cjs - IR ↔ markdown round-trip pair
(parse(serialize(ir)) === ir,
3 tests)
scripts/changeset/cli.cjs - file-I/O wrapper with --json mode;
reads .changeset/, folds into
CHANGELOG.md, deletes consumed
fragments. Idempotent. (1 test)
scripts/changeset/lint.cjs - pure verdict (changedFiles, labels)
→ { ok, reason } via LINT_REASON
enum. Honors `no-changelog` label.
(5 tests)
scripts/changeset/new.cjs - fragment scaffolder with random
adjective-noun-noun filename. Tests
assert via parseFragment round-trip.
(3 tests)
Total: 22 tests, all assertions on typed structured fields. No regex on
text, no String#includes on file content. Lint clean across 356 test files.
Supporting:
.changeset/README.md - format spec + workflow docs
.changeset/eager-hawks-rally.md - dogfood fragment for THIS PR (will
be the first thing the new release
tool consumes)
.github/workflows/changeset-required.yml
- CI: every PR runs lint.cjs
package.json - npm run changeset, changelog:render,
lint:changeset
CONTRIBUTING.md - new "CHANGELOG Entries — Drop a
Fragment" section between PR
Guidelines and Testing Standards
Closes#2975
* fix(#2975): address CodeRabbit findings on changeset workflow
7 valid findings (4 Major, 3 Minor); all addressed:
scripts/changeset/parse.cjs
- Preserve fragment body verbatim. Previously body.trim() ate
intentional leading whitespace (code blocks, etc.); now trim() is
used only for the emptiness check, and a single trailing newline
is stripped (the editor-added one) so well-formed fragments
round-trip byte-for-byte. Added a regression test asserting a
code-block-leading body is preserved.
scripts/changeset/cli.cjs
- Validate flag values during argument parsing. parseArgs now returns
{ ok, opts | error }; rejects `--repo` etc. with no following value
or with another flag as the value. main() surfaces the error
message before exiting 2.
- Handle post-write fragment-deletion failures. After CHANGELOG.md
is written, any unlink failure is captured into a structured
deleteFailures list with reason 'fail_fragment_delete'; cmdRender
returns exitCode=1 with the partial-failure detail instead of
leaving the changelog updated and fragments behind (which would
cause double-consumption on rerun).
scripts/changeset/lint.cjs
- Treat CHANGELOG.md as a linted user-facing path. Direct edits to
CHANGELOG.md (the bypass route around the new workflow) now fail
the lint with FAIL_MISSING_FRAGMENT. Added a regression test for
that case.
- Use cp.execFileSync instead of cp.execSync for the git diff call.
Eliminates the shell-interpolation surface on GITHUB_BASE_REF;
git's own arg parser remains the validator.
scripts/changeset/new.cjs
- Atomic fragment creation. existsSync() + writeFileSync was racy
under concurrent invocations. Now writeFileSync uses { flag: 'wx' }
which fails EEXIST on collision; the random-name retry loop
catches EEXIST and re-rolls. Throws explicitly after 16 attempts
rather than silently overwriting.
.changeset/README.md
- Add language tag `md` to the format example fence (markdownlint
MD040).
All 25 changeset tests pass; lint clean (356 test files, 0 violations).
* fix(#2975): sanitize --type and validate flag values in new.cjs (CR fixes)
Two CR findings on scripts/changeset/new.cjs:
1. (Minor) `type` was embedded in frontmatter without sanitization. A
newline in the value (e.g. `--type 'Fixed\ntype: Added'`) would
corrupt the fragment. scaffoldFragment now validates `type` against
the Keep-a-Changelog ALLOWED_TYPES set BEFORE writing — same set
parse.cjs uses on consume. Throws with a typed error referencing
the allowed values; tests cover the newline case + 4 other
non-allowed values.
2. (Minor) `--repo` (and other value-taking flags) without a value
silently set opts.repo to undefined, which produced a cryptic
ERR_INVALID_ARG_TYPE deep inside path.join. parseArgs now mirrors
the cli.cjs convention: returns { ok, opts | error }, validates
that the next token exists and is not itself another flag, and
surfaces a precise "missing value for --repo" message before exit.
Added 3 tests: missing-trailing-value, flag-as-value, well-formed.
29 tests pass across the changeset suite (4 new regression tests).
2026-05-01 18:12:20 -04:00
587 changed files with 20817 additions and 4195 deletions
This directory holds **per-PR CHANGELOG fragments**. Every PR with user-facing changes drops one (or more) `<random-name>.md` files here describing its CHANGELOG entry. Fragments are consolidated into the top-level `CHANGELOG.md` at release time.
## Why
Two PRs that both edit the `### Fixed` block of `CHANGELOG.md` always conflict on merge — git can't pick a serialization order without human input. Two PRs that each add a fresh `.changeset/<unique-name>.md` never conflict because they don't share lines.
See [#2975](https://github.com/gsd-build/get-shit-done/issues/2975) for the full rationale.
## Adding a fragment
```bash
node scripts/changeset/new.cjs \
--type Fixed \
--pr 1234\
--body "fix the thing — explain the user-visible change in one sentence"
```
This writes `.changeset/<adjective>-<noun>-<noun>.md` with frontmatter and a body. Three random words → concurrent PRs don't collide.
## Format
```md
---
type: Fixed
pr: 1234
---
**`/gsd-foo` no longer drops trailing slashes** — explain the user-visible change.
Reads every fragment, groups bullets by `type:`, replaces `## [Unreleased]` with a new `## [vX.Y.Z] - YYYY-MM-DD` block, opens a fresh `## [Unreleased]` above, deletes consumed fragments. Idempotent.
**Command contract validation now enforced in CI (ADR-0002)** — \`scripts/lint-command-contract.cjs\` runs as a pre-test step and validates every \`commands/gsd/*.md\` file against five rules: \`name:\` present + \`gsd:\` prefix, \`description:\` non-empty, \`allowed-tools:\` entries canonical, \`execution_context\` @-refs resolve on disk, @-refs on their own line. Prevents the \`add-backlog.md\`-class gap from silently reappearing on consolidation PRs.
**~900 tokens/invocation recovered** — prose \`@~/.claude/get-shit-done/...\` path tokens removed from \`<process>\` blocks in 39 command files. The \`<execution_context>\` block is now the single authoritative load declaration; the duplicate prose copies were inert but consumed context on every command invocation.
**~3,750 tokens removed from eager session load** — \`/gsd-debug\` (9,603 → 1,703 chars) and \`/gsd-thread\` (7,868 → 585 chars) now follow the workflow-delegation pattern used by all other commands. Their implementations moved to \`get-shit-done/workflows/debug.md\` and \`get-shit-done/workflows/thread.md\`. Behavior is unchanged.
\`get-shit-done/workflows/extract_learnings.md\` renamed to \`extract-learnings.md\` to match the hyphen convention of all other workflow files. Closes #3151.
**GSD transport raw-mode handling and timeout fallback hardened** — fixes undefined raw formatting edge case and adds raw-path coverage to prevent regressions.
**query command metadata now flows through a canonical Command Definition Module seam** — registry assembly, mutation semantics, and alias generation consume one Interface (`family`, `canonical`, `aliases`, `mutation`, `output_mode`, `handler_key`) to improve locality and reduce drift.
**query fallback error mapping cleanup** — the CJS fallback catch path now passes original `err` to `mapFallbackDispatchError` (follow-up to prior review feedback missed in PR #3066).
gsd-code-fixer worktree no longer fails on the same-branch checkout — the agent now creates a new gsd-reviewfix/ branch via git worktree add -b and fast-forwards the user's branch on cleanup. See #2990.
Test suite for config-schema.cjs is now mutation-resistant — 95 typed assertions kill the 124 surviving Stryker mutants from the 4.62% baseline. Tests target static-key fast path, dynamic-pattern .some semantics, polarity, and regex-anchor tightening. See #2986.
**`tests/install-minimal.test.cjs:307` no longer races on shared `os.tmpdir()` under parallel CI** — the previous shape compared `listTmpStageDirs()` snapshots before and after the throw. Under `scripts/run-tests.cjs --test-concurrency=4`, `tests/install-minimal-all-runtimes.test.cjs` runs in a parallel process and creates/removes `gsd-minimal-skills-*` dirs in the shared OS tmpdir between snapshots, so `deepStrictEqual` failed deterministically when the parallel process happened to have a live stage dir during the snapshot window. Fix: stub `fs.mkdtempSync` to record THIS call's stage dir, then assert that exact path no longer exists after the throw — no global filesystem snapshot, no race. (#3008)
**Codex SessionStart hook now uses absolute Node binary path** — closes the gap left after #3002. The Codex install path wrote `command = "node ${path}"` directly into config.toml, bypassing `resolveNodeRunner()`. Under GUI/minimal-PATH runtimes (`/usr/bin:/bin:/usr/sbin:/sbin`), bare `node` failed to resolve, exit 127. Now routed through new `buildCodexHookBlock()` helper. Reinstall path migrates legacy bare-node entries via new `rewriteLegacyCodexHookBlock()`. See #3017.
**Codex skill adapter no longer instructs the agent to silently default discuss-phase decisions.** When `request_user_input` was rejected (Default mode), the generated adapter said "pick a reasonable default" — so `$gsd-discuss-phase` proceeded toward writing CONTEXT.md / DISCUSSION-LOG.md / checkpoints without ever asking the user. Adapter prose now requires the agent to STOP, present plain-text questions, and wait, with explicit named exceptions (`--auto`/`--all`/explicit user approval). See #3018.
**query CLI path extracted into a dedicated Query CLI Adapter Module** — `sdk/src/cli.ts` now delegates query-specific dispatch, error mapping, and output/exit handling to `sdk/src/query/query-cli-adapter.ts` for better locality and testability.
**Post-install message and update.md no longer recommend the removed `/gsd-reapply-patches` command** — after PR #2824 consolidated 86 skills into ~58, `/gsd-reapply-patches` was folded into a flag (`/gsd-update --reapply`). The 1.39.1 hotfix (#2954) updated `help.md` but missed `bin/install.js`'s `reportLocalPatches` runtime emitter, `get-shit-done/workflows/update.md` Step 4, and the English + zh-CN/ja-JP/ko-KR doc set. Users hit "Unknown command" after every install with backed-up patches. All five runtime branches in `reportLocalPatches` (claude, opencode, kilo, copilot, gemini, codex, cursor) now emit the consolidated form. Regression: `tests/bug-3010-reapply-patches-references.test.cjs` scans `bin/install.js`, every workflow file, and every doc (excluding CHANGELOG history and help.md's deprecation notice) for stale recommendations. See #3010.
**Documentation refreshed for v1.40.0** — full audit of `docs/` against the 1.40.0-rc.1 release surface. Updates command lists, walkthroughs, and inventory rows for the 86→59 skill consolidation (#2790), the six namespace meta-skills with two-stage routing (#2792), the `/gsd-health --context` guard, the phase-lifecycle status-line read-side (#2833), and the Gemini colon-form / non-Gemini hyphen-form slash-command split. Translations in ja-JP/ko-KR/zh-CN/pt-BR mirror the structural changes; new English prose is marked with `<!-- TODO i18n -->` for human translator follow-up. CHANGELOG.md `[Unreleased]` section regrouped under Feature/Enhancement/Fix headers.
**`dynamic_routing` block in `.planning/config.json` for failure-tier escalation (#3024).** Each agent declares a default tier (`light` / `standard` / `heavy`); when `dynamic_routing.enabled: true`, the resolver picks `tier_models[default_tier]` for the first spawn and escalates one tier up on orchestrator-detected soft failure (capped by `max_escalations`). Disabled by default — fully backward compatible. Composes with `model_overrides` (higher precedence) and `models.<phase_type>` (lower) for full cost-control flexibility. Adds new resolver `resolveModelForTier(cwd, agent, attempt)` to `core.cjs` for orchestrator integration.
**Changeset-fragment workflow** — eliminates CHANGELOG.md merge conflicts. Each PR drops `.changeset/<random-name>.md` with frontmatter (`type:`, `pr:`) plus a markdown body; the release-time `npm run changelog:render` consolidates fragments into `CHANGELOG.md` and deletes them. CI lint (`npm run lint:changeset`) requires a fragment on any PR touching user-facing files (`bin/`, `get-shit-done/`, `agents/`, `commands/`, `hooks/`, `sdk/src/`); contributors can opt out via the `no-changelog` label for purely internal changes. See [.changeset/README.md](.changeset/README.md) and CONTRIBUTING.md for the workflow.
**`/gsd-progress --next` doc migration is fully consistent** — command docs now use clear `--next` wording, FEATURES TOC anchors match renamed headings, and regression tests enforce stale-command detection via structured slash-command token checks.
**Worktree prune regression checks are now path-normalized** — pruning safety tests now parse `git worktree list --porcelain` and assert structured normalized paths, preventing path-separator false negatives across platforms while preserving non-destructive prune guarantees.
**Optional findings probe guard checks now use structured parsing** — regression tests now parse fenced bash blocks and validate sketch/spike findings probes as structured command records, ensuring non-fatal `|| true` guards are enforced without raw source grep assertions.
**`gsd-planner.md` directive language restored** — 10 instances of `CRITICAL`/`MANDATORY`/`ALWAYS`/`MUST` emphasis were silently removed in v1.38.4 (PR #2489) without documentation, conflicting with that release's stated sycophancy-hardening intent. Downstream effect: planner output in v1.38.4–v1.40.x exhibited weaker adherence to user decisions and requirement coverage, as observed in #3087. Restored: `CRITICAL: User Decision Fidelity`, `CRITICAL: Never Simplify User Decisions`, `Multi-Source Coverage Audit (MANDATORY in every plan set)`, `Audit ALL four source types`, `Discovery is MANDATORY`, `ALWAYS split if:`, `requirements MUST list`, `CRITICAL: Every requirement ID MUST appear`, `ALWAYS use the Write tool`, and `CRITICAL — File naming convention`. Closes #3087.
**Milestone close now repairs missing STATE narrative sections** — when `## Current Position` or `## Operator Next Steps` headings are absent, milestone completion appends canonical sections so state remains deterministic and consistently points operators to `/gsd-new-milestone`.
**Progress routing command guidance remains canonical** — pre-planning assumption checks in progress routing now consistently assert and document `/gsd-discuss-phase` as the replacement path, with tests enforcing structured slash-command token checks.
**`ai-integration-phase` Steps 7+8 now enforce sequential execution and Edit-only tool discipline** — when `gsd-ai-researcher` and `gsd-domain-researcher` were dispatched in parallel (an optimization an orchestrator could reasonably make since the sections appeared disjoint), `gsd-domain-researcher`'s `Write` call at finalization silently replaced the entire AI-SPEC.md with its pre-researcher copy, losing Sections 3/4. Confirmed at 40% incidence rate (2 of 5 agents on a real run). Fix adds an explicit sequential ordering note to Steps 7+8 ("MUST run sequentially — wait for Step 7 to complete before spawning Step 8") and injects Edit-only tool discipline into both agent prompts ("Use the Edit tool exclusively — NEVER use Write on this file"). Closes #3096.
**Executor agents now detect and halt on cwd-drift out of worktrees (#3097)** — when a Bash call `cd`'d out of a worktree, `[ -f .git ]` became false (main repo's `.git` is a directory), silently skipping all HEAD/branch guards and allowing commits to land on the main repo's branch. Adds step 0a (cwd-drift sentinel using `git rev-parse --git-dir` + a per-worktree sentinel file at `.git/worktrees/<name>/gsd-spawn-toplevel`) to `gsd-executor.md`'s `task_commit_protocol`. Closes #3097.
---
type: Fixed
pr: 3099
---
**Executor agents now detect absolute paths that resolve outside the worktree (#3099)** — absolute paths constructed from the orchestrator's `pwd` (main repo root) resolved to the main repo when used in Edit/Write calls from a worktree, silently losing work. Adds step 0b (absolute-path guard using `WT_ROOT=$(git rev-parse --show-toplevel)`) with a clear warning and instructions to prefer relative paths. Both guards are documented in `references/worktree-path-safety.md` (loaded into every executor spawn prompt via `<execution_context>`). Closes #3099.
**`secure-phase` no longer rubber-stamps SECURITY.md for legacy phases with no `<threat_model>` blocks** — Step 3's short-circuit previously exited to Step 6 (write clean SECURITY.md) whenever `threats_open: 0`, regardless of whether zero threats meant "all mitigated" or "none were ever written". Legacy phases authored before `<threat_model>` blocks became canonical now trigger **retroactive-STRIDE mode** in Step 5: the auditor builds a register from implementation files before verifying mitigations. Step 2c now tracks `register_authored_at_plan_time` and Step 3 gates the skip on both `threats_open: 0 AND register_authored_at_plan_time: true`. Closes #3120.
**`gsd-sdk query commands` no longer returns "Unknown command"** — `commands` was referenced in `references/workstream-flag.md` and by agent tooling for verb discovery but had no SDK handler. A new `commandsList` handler in the native registry returns a sorted JSON array of all registered verb strings. `check.decision-coverage-plan` and `check.decision-coverage-verify` were already registered in the SDK native registry; the remaining gap was the `commands` introspection verb. Closes #3121.
**`global:` skill resolution now uses the correct runtime home directory** — `buildAgentSkillsBlock()` hardcoded `globalSkillsBase` to `~/.claude/skills` regardless of the active runtime, causing every `global:` skill lookup to silently fail on non-Claude runtimes (Cursor, Gemini, Codex, Windsurf, etc.). Introduces `get-shit-done/bin/lib/runtime-homes.cjs` — a first-class runtime→directory mapping module covering all 15 supported runtimes with their canonical env-var overrides. Notable specifics: Hermes Agent uses a nested `skills/gsd/<skillName>/` layout (#2841); Cline is rules-based and returns `null` (no skills directory); `CLAUDE_CONFIG_DIR` env var was previously missing for Claude. Warning messages now show the actual runtime-specific path. Closes #3126.
**`state.begin-phase` is now idempotent** — when called on a phase already in-flight (e.g. `--wave N` resume), it no longer overwrites `Current Plan`, `stopped_at` narrative, `Plan: N of M` body line, or `Last Activity Description` with stale values from the last `plan-phase` run. An idempotency guard reads the current `Status` field before writing: if it already contains `Executing Phase N`, only the `Last Activity` date and a resume-specific activity line are updated; all execution-progress fields are preserved. First-time execution (Status ≠ Executing) continues to write all fields as before. Closes #3127.
**`roadmap.cjs` plan_count now correctly detects `{N}-PLAN-{NN}-{slug}.md` files** — the manager-dashboard plan-count filter matched only `*-PLAN.md` and `PLAN.md`, missing the slug-form layout (`5-PLAN-01-setup.md`) that `gsd-plan-phase` actually writes. `init manager` returned `plan_count: 0` / `disk_status: "discussed"` for fully-planned phases, causing the manager to recommend and dispatch redundant background planner agents. Same regex flaw as #2893 (fixed in `phase.cjs` via PR #2896); `roadmap.cjs` was missed in that sweep. Fix applies the same `looksLikePlanFile` logic (with `PLAN-OUTLINE` and `pre-bounce` exclusions) to `countPhasePlansAndSummaries`. Closes #3128.
**`gsd-validate-commit.sh` community hook now catches all git commit forms** — the previous `[[ "$CMD" =~ ^git[[:space:]]+commit ]]` bash regex silently bypassed Conventional Commits enforcement for `git -C /path commit`, `GIT_AUTHOR_NAME=x git commit`, and `/usr/bin/git commit`. Introduces `hooks/lib/git-cmd.js` — a token-walk classifier (`isGitSubcommand(cmd, sub)`) that correctly handles env-prefix assignments, `-C path` working-directory flags, full-path executables, `--git-dir=` options, and all git global boolean flags. The hook now delegates detection to this module — the single source of truth for all hooks that gate on git subcommands. Closes #3129.
**`update.md` npx invocations hardened against cache-stale and Bash-tool token-routing failures** — the previous `npx -y get-shit-done-cc@latest` form had two failure modes: (1) npx serving a cached older version instead of `@latest`, and (2) Bash-tool wrappers misrouting the `@` token, producing `Unknown command: "get-shit-done-cc@latest"`. All three sibling invocations (local, global, unknown/fallback) now use `npx -y --package=get-shit-done-cc@latest -- get-shit-done-cc` — the `--package=` flag forces a fresh registry fetch and the `--` separator prevents token misrouting. Closes #3130.
**`/gsd-capture --backlog` now has a workflow to load** — PR #2824 consolidated `add-backlog` into the `--backlog` flag on `/gsd-capture` and wired `commands/gsd/capture.md` to delegate to `workflows/add-backlog.md` via `execution_context`. The workflow file was never created, leaving the routing with no implementation to load. Restores `get-shit-done/workflows/add-backlog.md` with the full process from the deleted `commands/gsd/add-backlog.md`: find next 999.x slot via `phase.next-decimal`, write ROADMAP entry before creating the phase directory (preserving the #2280 ordering invariant), create `.planning/phases/{N}-{slug}/`, and commit. Also fixes `docs/INVENTORY.md` which incorrectly attributed `--backlog` routing to `add-todo.md`. Adds a broad regression test that every `execution_context``@`-reference in any `commands/gsd/*.md` resolves to an existing workflow file, preventing this class of gap from silently re-appearing. Closes #3135.
**Gemini local install no longer duplicates `/gsd:*` commands across user and workspace scopes** — when GSD is already installed at the user scope (`~/.gemini/commands/gsd/`) and you run `npx get-shit-done-cc --gemini --local` in a project, the installer now skips writing `commands/gsd/` to `<project>/.gemini/` and prints a one-line warning explaining why. Previously, both scopes received the same 65 command files, and Gemini's conflict detector renamed every `/gsd:*` command to `/workspace.gsd:*` and `/user.gsd:*`, breaking the documented namespace. Closes #3037.
/gsd-reapply-patches Step 5 verifier now resolves at runtime — moved scripts/verify-reapply-patches.cjs to get-shit-done/bin/ which is shipped by the installer. The legacy scripts/ directory is not copied to user installs. See #2994.
**`gsd-sdk query <subcommand> --help` now reaches the handler instead of returning top-level usage.** The query argv parser harvested `--help` as a global flag and `main()` short-circuited dispatch — there was no path to discover what arguments a query subcommand accepts. The parser now leaves `--help` in `queryArgv` so the handler/fallback can render contextual help. The `gsd-tools.cjs` fallback now renders top-level usage on `--help` (instead of erroring), preserving #1818's anti-hallucination invariant by NOT executing the destructive command. See #3019.
**Alias-family handler maps moved to dedicated catalog module** — keeps command keys/order while reducing createRegistry coupling and improving family-level locality.
**Installer no longer prints `✓ GSD SDK ready` when the shim is unreachable from the user's runtime shells.** The previous check used `process.env.PATH` from the install subprocess, which often differs from the user's later interactive shells (POSIX `~/.local/bin` not in login shell, node-version-manager PATH shims). Added `getUserShellPath()` helper that probes `$SHELL -lc 'printf %s "$PATH"'` and `isGsdSdkOnPath(pathString?)` overload that accepts an explicit PATH; the install-time check now downgrades to the actionable `⚠` diagnostic from PR #3014 when install-PATH and user-shell-PATH disagree. Windows cross-shell support tracked separately. See #3020.
**`docs/issue-driven-orchestration.md` — recipe for driving GSD from a tracker issue** — new guide that maps Symphony-style orchestration concepts (workflow, isolated agent workspace, proof-of-work, human review gate, follow-up capture) onto existing GSD primitives (`/gsd-new-workspace`, `/gsd-manager`, `/gsd-autonomous`, `/gsd-verify-work`, `/gsd-review`, `/gsd-ship`, `STATE.md`, phase artifacts). Documentation only — no new commands, no daemon, no tracker integration.
/gsd-reapply-patches Step 5 verifier now resolves at runtime — moved scripts/verify-reapply-patches.cjs to get-shit-done/bin/ which is shipped by the installer. The legacy scripts/ directory is not copied to user installs. See #2994.
Managed JS hooks now resolve under GUI/minimal-PATH runtimes — installer emits process.execPath (absolute, quoted, forward-slash-normalized) as the runner for every .js hook command instead of bare node. See #2979.
Post-install path smoke test for workflow-invoked scripts — audits every node ${GSD_HOME}/...cjs invocation in workflows resolves at the runtime-installed path. See #2995.
milestone complete now scopes phase stats to the explicit version argument and errors when that version is missing from a versioned ROADMAP milestone section.
**Actionable diagnostic when `gsd-sdk` is not on PATH after install** — Windows users (and others on multi-shell setups) reported that the previous "GSD SDK files are present but `gsd-sdk` is not on your PATH" warning gave them no way to fix it: no path to look at, no shell-specific commands, no mention of the npx-cache caveat. New `formatSdkPathDiagnostic({ shimDir, platform, runDir })` helper returns a typed IR with the resolved shim location, platform-specific PATH-export commands (PowerShell / cmd.exe / Git Bash on Windows; `export PATH` on POSIX), and an npx-specific note when running under an `_npx` cache segment (where the shim may be written to a temp dir that won't persist). The console renderer in `bin/install.js` emits the lines from the IR; tests assert on the typed fields directly. (#3011)
**Documentation: MCP tool schema as a context-budget concern (#3025).** Adds new sections to `get-shit-done/references/context-budget.md` and `docs/USER-GUIDE.md` explaining that every enabled MCP server injects its tool schema into every turn — heavyweight servers (browser/playwright, Mac-tools, Windows-tools) can cost 20k+ tokens each, often dwarfing what `model_profile` tuning saves. The toggle lives in `.claude/settings.json` (`enabledMcpjsonServers` / `disabledMcpjsonServers`) and is a Claude Code harness concern, not a GSD concern. Includes a pre-phase audit checklist (browser, platform-specific, cross-project, duplicates) and notes the multiplier interaction with `model_profile`. Companion to #3023 (per-phase-type model map) and #3024 (dynamic routing); together they cover the three biggest cost levers.
SDK config-set/config-get and init responses no longer echo plaintext API keys. New sdk/src/query/secrets.ts ports SECRET_CONFIG_KEYS masking from CJS; init bundles only mask string values to preserve the boolean availability-flag contract. See #2997.
/gsd-update queries wrong npm package names — moved package name into a deterministic check-latest-version.cjs script and updated the workflow to use ${GSD_DIR} from get_installed_version. See #2992.
**PR templates now point at the changeset workflow** — the `Fix`, `Enhancement`, and `Feature` PR templates previously asked contributors to tick `CHANGELOG.md updated`, which contradicted the post-#2978 rule that `CHANGELOG.md` must not be edited directly. Each checkbox now references `npm run changeset` (and the `no-changelog` opt-out where applicable).
**`models` block in `.planning/config.json` for per-phase-type model selection (#3023).** A new resolution layer between per-agent `model_overrides` and the `model_profile` tier table. Six named slots (`planning` / `discuss` / `research` / `execution` / `verification` / `completion`) accept tier aliases (`opus` / `sonnet` / `haiku` / `inherit`). Lets you express "Opus for planning, Sonnet for the rest" in two lines without learning the agent taxonomy. Fully backward compatible — configs without `models` behave exactly as today.
gsd-pristine/ is now populated by the installer when local patches are detected — saveLocalPatches calls a new populatePristineDir helper that runs the install transform pipeline into a tmp staging dir and copies modified files into pristineDir. The reapply-patches Step 5 verifier no longer falls back to its over-broad heuristic. See #2998.
SDK config-set/config-get and init responses no longer echo plaintext API keys. New sdk/src/query/secrets.ts ports SECRET_CONFIG_KEYS masking from CJS; init bundles only mask string values to preserve the boolean availability-flag contract. See #2997.
Post-install path smoke test for workflow-invoked scripts — audits every node ${GSD_HOME}/...cjs invocation in workflows resolves at the runtime-installed path. See #2995.
Query module architecture deepened with compatibility-preserving seams — command policy now derives from command definitions, and dispatch/topology/registry seams are consolidated for better locality while preserving existing query behavior.
**Query fallback orchestration now shared** — CLI and SDK query dispatch now use one planning seam for native vs CJS fallback decisions with behavior parity preserved.
**`/gsd-research-phase` consolidated into `/gsd-plan-phase --research-phase <N>`** — the standalone research command's slash-command stub was never registered (#3042). Rather than restore the orphan, the research-only capability now lives as a flag on `/gsd-plan-phase`. New modifiers: `--view` prints existing `RESEARCH.md` to stdout without spawning, `--research` forces refresh, otherwise prompts `update / view / skip` when `RESEARCH.md` already exists. Also scrubs four other stale slash-command references (`/gsd-check-todos`, `/gsd-new-workspace`, `/gsd-status`, residual `/gsd-plan-milestone-gaps`) across English + 4 localized doc sets (#3044). Closes #3042 and #3044.
**Re-wired 4 orphaned workflows as flags on parent commands** — six workflows were mis-categorised as "outright deleted dead skills" during the #2790 consolidation; two were caught by prior PRs (#3045, #3038) and four are fixed here. New flags: `/gsd-discuss-phase --assumptions` (surfaces Claude's implementation assumptions before planning), `/gsd-pause-work --report` (generates a post-session summary in `.planning/reports/`), `/gsd-manager --analyze-deps` (scans ROADMAP phases for dependency relationships before parallel execution), `/gsd-import --from-gsd2` (reverse-migrates a GSD-2 `.gsd/` project back to GSD v1 `.planning/` format). Also sweeps 29 stale `/gsd-*` command references across 27 user-facing files (English + 4 locales). Closes #3131.
**`/gsd-code-review-fix` and `/gsd-plan-milestone-gaps` no longer surface as "Unknown command"** — both were consolidated by #2790 (`/gsd-code-review --fix` and inline gap planning in `/gsd-audit-milestone` respectively), but several user-facing surfaces still emitted the old slash forms in their offer text. Fixed audit-milestone offer blocks, gsd-complete-milestone routing, code-review/execute-phase offer text, gsd-code-fixer agent role card, and the doc surfaces (USER-GUIDE, FEATURES, INVENTORY, AGENTS, CONFIGURATION). Closes #3029, closes #3034.
gsd-code-fixer worktree no longer fails on the same-branch checkout — the agent now creates a new gsd-reviewfix/ branch via git worktree add -b and fast-forwards the user's branch on cleanup. See #2990.
Extended no-source-grep lint to catch var-binding readFileSync.includes() pattern. Tests now fail when source-grep is hidden behind a parser wrapper. See #2982.
**Dispatch policy seam now returns a structured result contract** across native and fallback query execution paths (`ok`, typed error `kind`, `details`, and final `exit_code`), with CLI consuming the unified result instead of mixed throw/result handling.
**Query static command registrations now split into domain catalog modules** — preserves command order/strings while improving registry locality and maintenance.
**`GSDTools` query execution internals now use deep Module seams** — refactors runtime composition, native/subprocess adapters, and output projection behind stable public interfaces for better locality and testability.
Migrated 8 test files from raw text matching (`stdout.includes(...)`, `assert.match(stderr, ...)`) to typed-IR assertions per CONTRIBUTING.md. Adds shared `ERROR_REASON` enum and `--json-errors` flag in `core.cjs`, typed `GRAPHIFY_REASON` in `graphify.cjs`, pure `buildSdkFailFastReport()` IR builder in `bin/install.js`, and Claude Code JSON envelope output (`hookSpecificOutput` with typed fields) for `gsd-session-state.sh` and `gsd-phase-boundary.sh`. Tests now assert on structured fields (`reason`, `context`, `state_present`, `planning_modified`, etc.) instead of substring matching. See #2974.
**Optional update banner for non-GSD statusline users** — when the installer detects you've declined or kept a non-GSD statusline, it now offers an opt-in `SessionStart` banner that surfaces update availability via the existing `~/.cache/gsd/gsd-update-check.json` cache. Silent when up-to-date, rate-limits failure diagnostics to once per 24h, removed cleanly by `npx get-shit-done-cc --uninstall`.
/gsd-profile-user --refresh writes dev-preferences.md to ~/.claude/skills/gsd-dev-preferences/SKILL.md instead of the legacy commands/gsd/ directory. Installer migrates any preserved legacy file to the new location. See #2973.
/gsd-update queries wrong npm package names — moved package name into a deterministic check-latest-version.cjs script and updated the workflow to use ${GSD_DIR} from get_installed_version. See #2992.
Managed JS hooks now resolve under GUI/minimal-PATH runtimes — installer emits process.execPath (absolute, quoted, forward-slash-normalized) as the runner for every .js hook command instead of bare node. See #2979.
Extended no-source-grep lint to catch var-binding readFileSync.includes() pattern. Tests now fail when source-grep is hidden behind a parser wrapper. See #2982.
- [ ] Fix is scoped to the reported bug — no unrelated changes included
- [ ] Regression test added (or explained why not)
- [ ] All existing tests pass (`npm test`)
- [ ]CHANGELOG.md updated if this is a user-facing fix
- [ ]`.changeset/` fragment added if this is a user-facing fix (`npm run changeset -- --type Fixed --pr <NNN> --body "..."`) — or `no-changelog` label applied
- **`release-sdk` hotfix re-run no longer fails at `Dry-run publish validation` when the version is already on npm** — the `Detect prior publish (reconciliation mode)` step sets `skip_publish=true` when the package version is already on the registry, and the actual publish step honors that gate. The `Dry-run publish validation` step was missing the same guard, so any operator re-run of an already-published hotfix (the typical recovery path when later steps fail mid-flight) hit `npm publish --dry-run` first and got `npm error You cannot publish over the previously published versions: X.Y.Z` — `npm publish --dry-run` contacts the registry and rejects existing-version targets even though it doesn't actually publish. The dry-run validation step is now gated on the same `steps.prior_publish.outputs.skip_publish != 'true'` condition as the publish step. The rehearsal still runs on first publishes (where it has value); it skips only in the specific reconciliation case where the publish itself would be skipped. Trigger run: [25233855236](https://github.com/gsd-build/get-shit-done/actions/runs/25233855236/job/73995605643). Regression covered by `tests/bug-2987-dry-run-validation-skip-on-reconciliation.test.cjs`. (#2987)
- **`release-sdk` hotfix flow hardened against silent classifier failures, missing-classifier-at-base-tag, and a vestigial merge-back PR step** — three issues surfaced by CodeRabbit's post-merge review of #2981 plus a production failure on the v1.39.1 release run. **(1)** `scripts/diff-touches-shipped-paths.cjs` reused exit code `1` for both the legitimate "no shipped paths" classifier result and Node's default uncaught-throw exit, so any tooling failure was indistinguishable from a normal skip. The script now uses `0` (shipped), `1` (not shipped), `2` (classifier error) with `try`/`catch` + `uncaughtException`/`unhandledRejection` handlers routing all failure paths to exit `2`. **(2)** The workflow's `git checkout -b "$BRANCH" "$BASE_TAG"` overwrote the working tree with the base tag's contents *before* the cherry-pick loop ran the classifier — but base tags predating the classifier's introduction (notably v1.39.0) don't have the file in their tree, so `node scripts/diff-touches-shipped-paths.cjs` would exit non-zero and silently drop every commit, producing an empty hotfix release. The classifier is now staged into `$RUNNER_TEMP` at the top of `Prepare hotfix branch` (before any working-tree-mutating git command), and the loop references that staged copy. The cherry-pick loop snapshots `$PIPESTATUS` into a local array (`PIPE_RC=("${PIPESTATUS[@]}")`) immediately after the classifier pipeline — under bracketed `set +e`/`set -e` — and dispatches via explicit `case`: `0` proceeds, `1` skips into `NON_SHIPPED_SKIPPED`, anything else emits `::error::shipped-paths classifier failed for $SHA (exit N)` and fails the workflow. CodeRabbit on PR #2984 caught a subtler bug in the first iteration: `pipeline \|\| true; RC=${PIPESTATUS[1]}` is broken because `\|\| true` runs `true` as its own one-command pipeline on the failure paths, overwriting `PIPESTATUS` to `(0)` and leaving `${PIPESTATUS[1]}` unset. The array-snapshot form is invariant against this. The same hardening also surfaces `git diff-tree`'s exit code (via `PIPE_RC[0]`); a non-zero diff-tree result now also fails the workflow rather than feeding partial input to the classifier. **(3)** Removed the `Open merge-back PR (hotfix only)` step. The auto-cherry-pick hotfix flow only picks commits already on main (`git cherry HEAD origin/main` outputs the unmerged ones), so by construction every code commit on the hotfix branch is already on main. The only hotfix-branch-only commit is the version-bump chore, which would either no-op against main or rewind main's in-progress version. The step also failed in production with `GitHub Actions is not permitted to create or approve pull requests (createPullRequest)` (org policy) on run [25232968975](https://github.com/gsd-build/get-shit-done/actions/runs/25232968975). The `pull-requests: write` permission previously granted to the release job has been dropped in line with least-privilege. The run-summary line that previously echoed `Merge-back PR opened against main` has been replaced with `No merge-back PR (auto-picked commits are already on main)` so operators reading the summary see an accurate non-action statement (CodeRabbit on PR #2984). Regression covered by `tests/bug-2983-classifier-exit-codes-and-base-tag-staging.test.cjs` (15 assertions across exit-code semantics, classifier staging, error dispatch, PIPESTATUS-snapshot hardening, diff-tree fail-fast, merge-back removal, and run-summary accuracy). (#2983)
- **`release-sdk` hotfix only cherry-picks commits that change what actually ships** — the `fix:`/`chore:` filter in `Prepare hotfix branch` was too broad: it picked any commit with that conventional-commit type regardless of whether the diff could affect the published npm package. CI-only fixes (release-sdk.yml itself, hotfix tooling, test-only commits) were getting cherry-picked into hotfix branches even though they cannot change the tarball — and the subset touching `.github/workflows/*` then caused the prepare job's `git push` to be rejected by GitHub because the default `GITHUB_TOKEN` lacks the `workflow` scope, aborting the run. v1.39.1 hit this on PR #2977 (run [25232010071](https://github.com/gsd-build/get-shit-done/actions/runs/25232010071)). The loop now pre-skips any candidate commit whose `git diff-tree` output doesn't intersect the npm tarball's shipped paths (entries in `package.json``files`, plus `package.json` itself, which `npm pack` always includes). Skipped commits land in a new `NON_SHIPPED_SKIPPED` summary bucket framed as informational — non-shipping commits cannot affect the package, so the skip needs no operator action. The shipped-paths classifier lives in `scripts/diff-touches-shipped-paths.cjs` so its rules (file-OR-directory prefix matching `npm pack` semantics, the always-shipped rule for `package.json`, the lockfile-not-shipped rule) are unit-testable. Regression covered by `tests/bug-2980-hotfix-only-picks-shipping-changes.test.cjs`. (#2980)
- **`release-sdk` hotfix workflow fails on real run with `npm error Version not changed`** — the `release` job's `Bump in-tree version (not committed)` step ran `npm version "$VERSION"` without `--allow-same-version`, so it errored on real (non-dry-run) hotfix runs because `prepare` had already committed the bump on the hotfix branch. The release job's checkout `ref` is asymmetric — `BRANCH` (already bumped) on real runs vs `BASE_TAG` (older version) on dry-runs — which is why dry-run never caught the bug. Both `npm version` calls in that step now pass `--allow-same-version`, matching the existing pattern in `release.yml:326`. (#2976)
- **`gsd-sdk query agent-skills` emits raw `<agent_skills>` block instead of JSON-wrapped string** — workflows that embed via `$(gsd-sdk query agent-skills <agent>)` were receiving a JSON-quoted string literal mid-prompt (e.g. `"<agent_skills>\n…"`), silently breaking all `<agent_skills>` injection into spawned subagents. The CLI dispatcher now honors an opt-in `format: 'text'` field on `QueryResult` and writes such results raw via `process.stdout.write`; `--pick` always returns JSON regardless. (#2917)
- **`sketch --wrap-up` now dispatches correctly** — `/gsd-sketch --wrap-up` was silently no-oping because the flag dispatch wiring was omitted when the micro-skill entry point was absorbed in #2790. (#2949)
- **`help.md` no longer advertises eight slash commands removed by the #2824 consolidation** — `/gsd-do`, `/gsd-note`, `/gsd-check-todos`, `/gsd-plant-seed`, `/gsd-research-phase`, `/gsd-list-phase-assumptions`, `/gsd-plan-milestone-gaps`, and `/gsd-join-discord` were removed when 86 skills were folded into 59. `help.md` was not updated alongside, so users typing the documented commands hit *Unknown command*. Each entry is now either rewritten to the surviving flag-based dispatcher (e.g., `/gsd-do …` → `/gsd-progress --do "…"`, `/gsd-note` → `/gsd-capture --note`, `/gsd-plant-seed` → `/gsd-capture --seed`, `/gsd-check-todos` → `/gsd-capture --list`) or removed for skills with no replacement. A regression test now asserts every `/gsd-*` reference in `help.md` has a matching `commands/gsd/*.md` stub. (#2954)
- **`--sdk` install on Windows now writes a callable `gsd-sdk` shim** — `npx get-shit-done-cc@latest --claude --global --sdk` on Windows previously left `gsd-sdk` off PATH because `trySelfLinkGsdSdk` returned `null` unconditionally on `win32` (a missed gap from #2775's POSIX self-link, not an intentional deferral). The function now dispatches to a Windows counterpart that writes the standard npm shim triple (`gsd-sdk.cmd`, `gsd-sdk.ps1`, and a Bash wrapper) to npm's global bin, so `gsd-sdk` resolves in a fresh shell across cmd.exe, PowerShell, and Cygwin/MSYS/Git-Bash. A new regression guard in `tests/no-unconditional-win32-skip.test.cjs` blocks any future `if (process.platform === 'win32') return null;` skip-only branches in `bin/install.js`. (#2962)
- **`/gsd-reapply-patches` Step 5 gate is now deterministic — no more silent content drops** — the prior gate parsed a Claude-generated *Hunk Verification Table* whose `verified: yes` rows were filled in without actually checking content presence, leading to merged files that lost user-added blocks (e.g., a `<visual_companion>` section, an `--execute-only` flag block) while the workflow reported success. The gate now invokes a Node script (`scripts/verify-reapply-patches.cjs`) that diffs each backup against the pristine baseline, computes the user-added significant lines, and asserts each one is present in the merged file. Exits non-zero with a per-file diagnostic on any miss; the workflow halts and surfaces the JSON output to the user. The verifier ignores low-signal lines (too short, pure whitespace, decorative comments) so trivial differences don't trigger false failures. Out of scope here: the manifest-baseline tightening described in #2969 Failure 1 — that's separate work. (#2969)
### Added — 1.40.0-rc.1
- **Six namespace meta-skills with keyword-tag descriptions** — replace the flat 86-skill
listing with two-stage hierarchical routing. Model sees 6 namespace routers
@@ -36,49 +25,6 @@ Format follows [Keep a Changelog](https://keepachangelog.com/en/1.1.0/).
in-flight, idle, and progress display. All fields default to undefined so existing
STATE.md files keep rendering. Write-side and status-line wiring follow in a later
RC. (#2833)
### Changed — 1.40.0-rc.1
- **Hotfix release flow now auto-incorporates fixes from `main` and bundles the SDK** — `hotfix.yml create` auto-cherry-picks every `fix:`/`chore:` commit on `origin/main` not yet shipped (oldest-first; patch-equivalents skipped via `git cherry`; `feat:`/`refactor:` excluded; conflicts halt with the offending SHA; run summary lists every included SHA). `hotfix.yml finalize` adds the `install-smoke` cross-platform gate, bundles `sdk-bundle/gsd-sdk.tgz` inside the CC tarball (parity with `release-sdk.yml`), tightens the `next` dist-tag re-point, and marks the GitHub Release `--latest`. `release-sdk.yml` gains `action: publish | hotfix` plus an `auto_cherry_pick` toggle, with a new `prepare` job that branches `hotfix/X.YY.Z` from the highest existing `vX.YY.*` tag and runs the same cherry-pick logic — idempotent if the branch was pre-prepared via `hotfix.yml`. Hotfix `vX.YY.Z` is now defined as everything in `vX.YY.{Z-1}` plus every `fix:`/`chore:` since that base, so each tag is the cumulative-fix anchor for the next. (#2955)
- **Planning workspace seam extracted from `core.cjs` into `planning-workspace.cjs`** — path/workstream/lock behavior now lives in a dedicated module (`planningDir`, `planningPaths`, `planningRoot`, active-workstream routing, `withPlanningLock`). `core.cjs` keeps compatibility re-exports while call-sites migrate to direct imports, improving locality and reducing coupling. (#2900)
- **Skill surface consolidated 86 → 59 `commands/gsd/*.md` entries** — four new
grouped skills (`capture`, `phase`, `config`, `workspace`) replace clusters of
micro-skills. Six existing parents absorb wrap-up and sub-operations as flags:
- **PRs missing `Closes #NNN` are auto-closed** — the `Issue link required` workflow
now auto-closes PRs opened without a closing keyword that links a tracking issue,
posting a comment that points to the contribution guide. (#2872)
### Fixed
- **Stale deleted command references updated across workflow files** — `help.md`, `do.md`, `settings.md`, `discuss-phase.md`, `new-project.md`, `plan-phase.md`, `spike.md`, and `sketch.md` referenced command names removed in #2790; updated to new consolidated equivalents. (#2950)
### Fixed — 1.40.0-rc.1
- **`spike --wrap-up` now dispatches correctly** — `/gsd-spike --wrap-up` was silently no-oping because the flag dispatch wiring was omitted when the micro-skill entry point was absorbed in #2790. (#2948)
- **`config-get context_window` returns `200000` when key absent** — querying an unset `context_window` previously exited 1 with "Key not found", surfacing a confusing error in planning logs even though the workflow fallback worked correctly. `cmdConfigGet` now consults a `SCHEMA_DEFAULTS` map and returns the documented default (`200000`, exit 0) for absent schema-defaulted keys; unknown absent keys still error as before. (#2943)
- **`gap-analysis` now parses non-`REQ-` requirement IDs and ignores traceability table headers** — `parseRequirements()` no longer hard-codes the `REQ-` prefix and now accepts uppercase prefixed IDs such as `TST-01`, `BACK-07`, and `INSP-04`; markdown table header rows (for example `| REQ-ID | ... |`) are excluded so header tokens are not reported as phantom uncovered requirements. Added regression coverage for mixed-prefix REQUIREMENTS files with traceability tables. (#2897)
- **Gemini slash commands namespaced as `/gsd:<cmd>` instead of `/gsd-<cmd>`** —
Gemini CLI namespaces commands under `gsd:`, so `/gsd-plan-phase` was unexecutable.
Body-text references in commands, agents, banners, and patch-reapply hints are now
converted via a roster-checked regex (boundary lookbehind + extension-aware
lookahead + roster lookup, defense-in-depth). The roster fail-loud guard prevents
silent no-op'ing if `commands/gsd/` is ever missing. (#2768, #2783)
sites now wrap descriptions in `yamlQuote(...)` (= `JSON.stringify`, a valid YAML
1.2 double-quoted scalar). (#2876)
- **`gsd-tools` invocations use the absolute installed path** — bare `gsd-tools …`
calls inside skill bodies relied on PATH resolution that is not guaranteed in every
runtime; replaced with the absolute path emitted at install time. (#2851)
- **Codex installer preserves trailing newline when stripping legacy hooks** — the
legacy-hook strip in the Codex installer ran against files with no terminating
newline at EOF and emitted a config that lost the newline, breaking downstream
parsers. (#2866)
### Added
-`--minimal` install flag (alias `--core-only`) writes only the main-loop core skills
(`new-project`, `discuss-phase`, `plan-phase`, `execute-phase`, `help`, `update`) and
zero `gsd-*` subagents. Cuts cold-start system-prompt overhead from ~12k tokens to
@@ -107,7 +53,21 @@ Format follows [Keep a Changelog](https://keepachangelog.com/en/1.1.0/).
on every push to main was rejected because submission rate is too high). Includes an
optional `dry_run` boolean and the same publish-verification gate as `release.yml`. (#2828)
### Changed
### Enhancement
- **Test suite for `config-schema.cjs` is now mutation-resistant** — Stryker measured a 4.62% mutation score on `get-shit-done/bin/lib/config-schema.cjs` (6 killed, 124 survived out of 130). Surviving mutants flagged that existing tests were exercising paths but not verifying outputs: a polarity flip (`return true` → `return false`), a predicate swap (`.some` → `.every`), or a guard removal (`if (VALID_CONFIG_KEYS.has(...)) return true;` → unguarded fallthrough) all passed every test. New `tests/bug-2986-config-schema-mutation-killers.test.cjs` adds 95 tests across four suites that target each surviving mutant class: (1) parameterized `isValidConfigKey('${key}') === true` for every member of `VALID_CONFIG_KEYS` (kills the static-key-fast-path mutation), (2) representative dynamic-pattern keys that match exactly one pattern (kills the `.some` → `.every` mutation, with an inline mutual-exclusivity invariant check), (3) `strictEqual` against the literal boolean `true`/`false` instead of `assert.ok` truthy checks (kills polarity-flip mutations), (4) anchor-tightening cases that differ from valid keys by one character beyond the documented shape (kills regex-loosening mutations on `^`, `$`, and character-class boundaries). Tests use the lib's public surface (typed boolean assertions on `isValidConfigKey` return values), no source-grep. (#2986)
- **Hotfix release flow now auto-incorporates fixes from `main` and bundles the SDK** — `hotfix.yml create` auto-cherry-picks every `fix:`/`chore:` commit on `origin/main` not yet shipped (oldest-first; patch-equivalents skipped via `git cherry`; `feat:`/`refactor:` excluded; conflicts halt with the offending SHA; run summary lists every included SHA). `hotfix.yml finalize` adds the `install-smoke` cross-platform gate, bundles `sdk-bundle/gsd-sdk.tgz` inside the CC tarball (parity with `release-sdk.yml`), tightens the `next` dist-tag re-point, and marks the GitHub Release `--latest`. `release-sdk.yml` gains `action: publish | hotfix` plus an `auto_cherry_pick` toggle, with a new `prepare` job that branches `hotfix/X.YY.Z` from the highest existing `vX.YY.*` tag and runs the same cherry-pick logic — idempotent if the branch was pre-prepared via `hotfix.yml`. Hotfix `vX.YY.Z` is now defined as everything in `vX.YY.{Z-1}` plus every `fix:`/`chore:` since that base, so each tag is the cumulative-fix anchor for the next. (#2955)
- **Planning workspace seam extracted from `core.cjs` into `planning-workspace.cjs`** — path/workstream/lock behavior now lives in a dedicated module (`planningDir`, `planningPaths`, `planningRoot`, active-workstream routing, `withPlanningLock`). `core.cjs` keeps compatibility re-exports while call-sites migrate to direct imports, improving locality and reducing coupling. (#2900)
- **Skill surface consolidated 86 → 59 `commands/gsd/*.md` entries** — four new
grouped skills (`capture`, `phase`, `config`, `workspace`) replace clusters of
micro-skills. Six existing parents absorb wrap-up and sub-operations as flags:
on-demand `Read()` calls gated behind mode routing. Tokens loaded at skill entry drop
from ~13k to near zero; only the branch actually invoked is loaded. (#2606)
### Fixed
### Fix
- **`gsd-pristine/` is now populated by the installer when local patches are detected** — `saveLocalPatches` declared a `pristineDir` variable and JSDoc'd "saves pristine copies (from manifest) to gsd-pristine/ to enable three-way merge during reapply-patches", but no code ever wrote to that directory. Effect: the `/gsd-reapply-patches` Step 5 verifier (#2972) silently degraded to its over-broad fallback heuristic ("every significant backup line"), exactly the silent-success-on-lost-content failure mode #2969 was designed to prevent. Fix: new `populatePristineDir({ packageSrc, pristineDir, modified, runtime, pathPrefix, isGlobal })` helper runs the install transform pipeline (`copyWithPathReplacement`) into a tmp staging dir, then copies out only the modified-file paths into `gsd-pristine/`. `saveLocalPatches` now accepts a `pristineCtx` and calls the helper when local patches are detected; the install entry point passes the package source root, runtime, pathPrefix, and isGlobal so transforms produce byte-identical output to what `copyWithPathReplacement` would have written under normal install. Soft-fails on transform errors (logs a warning, continues with empty pristine — no worse than pre-fix behavior). Pristine reflects the about-to-install version's content, which is what the verifier needs as the "what would survive without the user's modifications" baseline. Regression covered by `tests/bug-2998-pristine-dir-populated.test.cjs` (6 tests across two suites): asserts the helper is exported, returns 0 for empty modified list, writes one pristine file per source-existing path, skips ghost paths without corrupting pristine, and produces deterministic output (two runs with same inputs yield byte-identical pristine — the property `pristine_hashes` in `backup-meta.json` depends on). (#2998)
- **`release-sdk` hotfix re-run no longer fails at `Dry-run publish validation` when the version is already on npm** — the `Detect prior publish (reconciliation mode)` step sets `skip_publish=true` when the package version is already on the registry, and the actual publish step honors that gate. The `Dry-run publish validation` step was missing the same guard, so any operator re-run of an already-published hotfix (the typical recovery path when later steps fail mid-flight) hit `npm publish --dry-run` first and got `npm error You cannot publish over the previously published versions: X.Y.Z` — `npm publish --dry-run` contacts the registry and rejects existing-version targets even though it doesn't actually publish. The dry-run validation step is now gated on the same `steps.prior_publish.outputs.skip_publish != 'true'` condition as the publish step. The rehearsal still runs on first publishes (where it has value); it skips only in the specific reconciliation case where the publish itself would be skipped. Trigger run: [25233855236](https://github.com/gsd-build/get-shit-done/actions/runs/25233855236/job/73995605643). Regression covered by `tests/bug-2987-dry-run-validation-skip-on-reconciliation.test.cjs`. (#2987)
- **`release-sdk` hotfix flow hardened against silent classifier failures, missing-classifier-at-base-tag, and a vestigial merge-back PR step** — three issues surfaced by CodeRabbit's post-merge review of #2981 plus a production failure on the v1.39.1 release run. **(1)** `scripts/diff-touches-shipped-paths.cjs` reused exit code `1` for both the legitimate "no shipped paths" classifier result and Node's default uncaught-throw exit, so any tooling failure was indistinguishable from a normal skip. The script now uses `0` (shipped), `1` (not shipped), `2` (classifier error) with `try`/`catch` + `uncaughtException`/`unhandledRejection` handlers routing all failure paths to exit `2`. **(2)** The workflow's `git checkout -b "$BRANCH" "$BASE_TAG"` overwrote the working tree with the base tag's contents *before* the cherry-pick loop ran the classifier — but base tags predating the classifier's introduction (notably v1.39.0) don't have the file in their tree, so `node scripts/diff-touches-shipped-paths.cjs` would exit non-zero and silently drop every commit, producing an empty hotfix release. The classifier is now staged into `$RUNNER_TEMP` at the top of `Prepare hotfix branch` (before any working-tree-mutating git command), and the loop references that staged copy. The cherry-pick loop snapshots `$PIPESTATUS` into a local array (`PIPE_RC=("${PIPESTATUS[@]}")`) immediately after the classifier pipeline — under bracketed `set +e`/`set -e` — and dispatches via explicit `case`: `0` proceeds, `1` skips into `NON_SHIPPED_SKIPPED`, anything else emits `::error::shipped-paths classifier failed for $SHA (exit N)` and fails the workflow. CodeRabbit on PR #2984 caught a subtler bug in the first iteration: `pipeline \|\| true; RC=${PIPESTATUS[1]}` is broken because `\|\| true` runs `true` as its own one-command pipeline on the failure paths, overwriting `PIPESTATUS` to `(0)` and leaving `${PIPESTATUS[1]}` unset. The array-snapshot form is invariant against this. The same hardening also surfaces `git diff-tree`'s exit code (via `PIPE_RC[0]`); a non-zero diff-tree result now also fails the workflow rather than feeding partial input to the classifier. **(3)** Removed the `Open merge-back PR (hotfix only)` step. The auto-cherry-pick hotfix flow only picks commits already on main (`git cherry HEAD origin/main` outputs the unmerged ones), so by construction every code commit on the hotfix branch is already on main. The only hotfix-branch-only commit is the version-bump chore, which would either no-op against main or rewind main's in-progress version. The step also failed in production with `GitHub Actions is not permitted to create or approve pull requests (createPullRequest)` (org policy) on run [25232968975](https://github.com/gsd-build/get-shit-done/actions/runs/25232968975). The `pull-requests: write` permission previously granted to the release job has been dropped in line with least-privilege. The run-summary line that previously echoed `Merge-back PR opened against main` has been replaced with `No merge-back PR (auto-picked commits are already on main)` so operators reading the summary see an accurate non-action statement (CodeRabbit on PR #2984). Regression covered by `tests/bug-2983-classifier-exit-codes-and-base-tag-staging.test.cjs` (15 assertions across exit-code semantics, classifier staging, error dispatch, PIPESTATUS-snapshot hardening, diff-tree fail-fast, merge-back removal, and run-summary accuracy). (#2983)
- **`release-sdk` hotfix only cherry-picks commits that change what actually ships** — the `fix:`/`chore:` filter in `Prepare hotfix branch` was too broad: it picked any commit with that conventional-commit type regardless of whether the diff could affect the published npm package. CI-only fixes (release-sdk.yml itself, hotfix tooling, test-only commits) were getting cherry-picked into hotfix branches even though they cannot change the tarball — and the subset touching `.github/workflows/*` then caused the prepare job's `git push` to be rejected by GitHub because the default `GITHUB_TOKEN` lacks the `workflow` scope, aborting the run. v1.39.1 hit this on PR #2977 (run [25232010071](https://github.com/gsd-build/get-shit-done/actions/runs/25232010071)). The loop now pre-skips any candidate commit whose `git diff-tree` output doesn't intersect the npm tarball's shipped paths (entries in `package.json``files`, plus `package.json` itself, which `npm pack` always includes). Skipped commits land in a new `NON_SHIPPED_SKIPPED` summary bucket framed as informational — non-shipping commits cannot affect the package, so the skip needs no operator action. The shipped-paths classifier lives in `scripts/diff-touches-shipped-paths.cjs` so its rules (file-OR-directory prefix matching `npm pack` semantics, the always-shipped rule for `package.json`, the lockfile-not-shipped rule) are unit-testable. Regression covered by `tests/bug-2980-hotfix-only-picks-shipping-changes.test.cjs`. (#2980)
- **`release-sdk` hotfix workflow fails on real run with `npm error Version not changed`** — the `release` job's `Bump in-tree version (not committed)` step ran `npm version "$VERSION"` without `--allow-same-version`, so it errored on real (non-dry-run) hotfix runs because `prepare` had already committed the bump on the hotfix branch. The release job's checkout `ref` is asymmetric — `BRANCH` (already bumped) on real runs vs `BASE_TAG` (older version) on dry-runs — which is why dry-run never caught the bug. Both `npm version` calls in that step now pass `--allow-same-version`, matching the existing pattern in `release.yml:326`. (#2976)
- **Stale deleted command references updated across workflow files** — `help.md`, `do.md`, `settings.md`, `discuss-phase.md`, `new-project.md`, `plan-phase.md`, `spike.md`, and `sketch.md` referenced command names removed in #2790; updated to new consolidated equivalents. (#2950)
- **`spike --wrap-up` now dispatches correctly** — `/gsd-spike --wrap-up` was silently no-oping because the flag dispatch wiring was omitted when the micro-skill entry point was absorbed in #2790. (#2948)
- **`config-get context_window` returns `200000` when key absent** — querying an unset `context_window` previously exited 1 with "Key not found", surfacing a confusing error in planning logs even though the workflow fallback worked correctly. `cmdConfigGet` now consults a `SCHEMA_DEFAULTS` map and returns the documented default (`200000`, exit 0) for absent schema-defaulted keys; unknown absent keys still error as before. (#2943)
- **`gap-analysis` now parses non-`REQ-` requirement IDs and ignores traceability table headers** — `parseRequirements()` no longer hard-codes the `REQ-` prefix and now accepts uppercase prefixed IDs such as `TST-01`, `BACK-07`, and `INSP-04`; markdown table header rows (for example `| REQ-ID | ... |`) are excluded so header tokens are not reported as phantom uncovered requirements. Added regression coverage for mixed-prefix REQUIREMENTS files with traceability tables. (#2897)
- **Gemini slash commands namespaced as `/gsd:<cmd>` instead of `/gsd-<cmd>`** —
Gemini CLI namespaces commands under `gsd:`, so `/gsd-plan-phase` was unexecutable.
Body-text references in commands, agents, banners, and patch-reapply hints are now
converted via a roster-checked regex (boundary lookbehind + extension-aware
lookahead + roster lookup, defense-in-depth). The roster fail-loud guard prevents
silent no-op'ing if `commands/gsd/` is ever missing. (#2768, #2783)
sites now wrap descriptions in `yamlQuote(...)` (= `JSON.stringify`, a valid YAML
1.2 double-quoted scalar). (#2876)
- **`gsd-tools` invocations use the absolute installed path** — bare `gsd-tools …`
calls inside skill bodies relied on PATH resolution that is not guaranteed in every
runtime; replaced with the absolute path emitted at install time. (#2851)
- **Codex installer preserves trailing newline when stripping legacy hooks** — the
legacy-hook strip in the Codex installer ran against files with no terminating
newline at EOF and emitted a config that lost the newline, breaking downstream
parsers. (#2866)
- **GSD slash command namespace drift cleaned up across docs, workflows, and autocomplete** — remaining active `/gsd:<cmd>` references now use canonical `/gsd-<cmd>`, escaped workflow `Skill(skill=\"gsd:...\")` prompts now use hyphenated skill names, `scripts/fix-slash-commands.cjs` rewrites retired colon syntax to hyphen syntax, and the extract-learnings command file now uses `extract-learnings.md` so generated Claude/Qwen skill autocomplete exposes `gsd-extract-learnings` instead of `gsd-extract_learnings`. (#2855)
- **`extractCurrentMilestone` no longer truncates ROADMAP.md at heading-like lines inside fenced code blocks** — the milestone-end search now scans line-by-line while tracking ` ``` ` / `~~~` fence state, so a line like `# Ops runbook (v1.0 compat)` inside a code block no longer acts as a milestone boundary. Previously, any phase defined after such a block was invisible to `roadmap analyze`, `roadmap get-phase`, `/gsd-autonomous`, and all phase-number commands. (#2787)
- **Codex install no longer corrupts existing `~/.codex/config.toml`** — the installer
@@ -320,10 +307,19 @@ Format follows [Keep a Changelog](https://keepachangelog.com/en/1.1.0/).
pre-existing sentinel force-removes the orphan worktree before starting fresh, making
on-demand `Read()` calls gated behind mode routing. Tokens loaded at skill entry drop
from ~13k to near zero; only the branch actually invoked is loaded. (#2606)
## [1.39.1] - 2026-05-01
Hotfix release. Cherry-picks user-facing fixes from `main` onto the v1.39.0 stable
line. Install: `npm install -g get-shit-done-cc@latest` (or `@1.39.1` to pin).
### Fixed
- **`gsd-sdk query agent-skills` emits raw `<agent_skills>` block instead of JSON-wrapped string** — workflows that embed via `$(gsd-sdk query agent-skills <agent>)` were receiving a JSON-quoted string literal mid-prompt (e.g. `"<agent_skills>\n…"`), silently breaking all `<agent_skills>` injection into spawned subagents. The CLI dispatcher now honors an opt-in `format: 'text'` field on `QueryResult` and writes such results raw via `process.stdout.write`; `--pick` always returns JSON regardless. (#2917)
- **`sketch --wrap-up` now dispatches correctly** — `/gsd-sketch --wrap-up` was silently no-oping because the flag dispatch wiring was omitted when the micro-skill entry point was absorbed in #2790. (#2949)
- **`help.md` no longer advertises eight slash commands removed by the #2824 consolidation** — `/gsd-do`, `/gsd-note`, `/gsd-check-todos`, `/gsd-plant-seed`, `/gsd-research-phase`, `/gsd-list-phase-assumptions`, `/gsd-plan-milestone-gaps`, and `/gsd-join-discord` were removed when 86 skills were folded into 59. `help.md` was not updated alongside, so users typing the documented commands hit *Unknown command*. Each entry is now either rewritten to the surviving flag-based dispatcher (e.g., `/gsd-do …` → `/gsd-progress --do "…"`, `/gsd-note` → `/gsd-capture --note`, `/gsd-plant-seed` → `/gsd-capture --seed`, `/gsd-check-todos` → `/gsd-capture --list`) or removed for skills with no replacement. A regression test now asserts every `/gsd-*` reference in `help.md` has a matching `commands/gsd/*.md` stub. (#2954)
- **`--sdk` install on Windows now writes a callable `gsd-sdk` shim** — `npx get-shit-done-cc@latest --claude --global --sdk` on Windows previously left `gsd-sdk` off PATH because `trySelfLinkGsdSdk` returned `null` unconditionally on `win32` (a missed gap from #2775's POSIX self-link, not an intentional deferral). The function now dispatches to a Windows counterpart that writes the standard npm shim triple (`gsd-sdk.cmd`, `gsd-sdk.ps1`, and a Bash wrapper) to npm's global bin, so `gsd-sdk` resolves in a fresh shell across cmd.exe, PowerShell, and Cygwin/MSYS/Git-Bash. A new regression guard in `tests/no-unconditional-win32-skip.test.cjs` blocks any future `if (process.platform === 'win32') return null;` skip-only branches in `bin/install.js`. (#2962)
- **`/gsd-reapply-patches` Step 5 gate is now deterministic — no more silent content drops** — the prior gate parsed a Claude-generated *Hunk Verification Table* whose `verified: yes` rows were filled in without actually checking content presence, leading to merged files that lost user-added blocks (e.g., a `<visual_companion>` section, an `--execute-only` flag block) while the workflow reported success. The gate now invokes a Node script (`scripts/verify-reapply-patches.cjs`) that diffs each backup against the pristine baseline, computes the user-added significant lines, and asserts each one is present in the merged file. Exits non-zero with a per-file diagnostic on any miss; the workflow halts and surfaces the JSON output to the user. The verifier ignores low-signal lines (too short, pure whitespace, decorative comments) so trivial differences don't trigger false failures. Out of scope here: the manifest-baseline tightening described in #2969 Failure 1 — that's separate work. (#2969)
Canonical command metadata Interface powering alias, catalog, and semantics generation.
### Query Runtime Context Module
Module owning query-time context resolution for `projectDir` and `ws`, including precedence and validation policy used by query adapters.
### Native Dispatch Adapter Module
Adapter Module that satisfies native query dispatch at the Dispatch Policy seam, so policy modules consume a focused dispatch Interface instead of closure-wired call sites.
### Query CLI Output Module
Module owning projection from dispatch results/errors to CLI `{ exitCode, stdoutChunks, stderrLines }` output contract.
### Query Execution Policy Module
Module owning query transport routing policy projection (`preferNative`, fallback policy, workstream subprocess forcing) at execution seam.
Canonical command normalization and resolution Interface (`query-command-resolution-strategy`) used by internal query/transport paths after dead-wrapper convergence.
### Command Topology Module
Module owning command resolution, policy projection (`mutation`, `output_mode`), unknown-command diagnosis, and handler Adapter binding at one seam for query dispatch.
### Query Pre-Project Config Policy Module
Module policy that defines query-time behavior when `.planning/config.json` is absent: use built-in defaults for parity-sensitive query Interfaces, and emit parity-aligned empty model ids for pre-project model resolution surfaces.
---
## Recurring PR mistakes (distilled from CodeRabbit reviews, 2026-05-05)
### Tests — no source-grep
- **Rule**: never bind `readFileSync` result to a var then call `.includes()` / `.match()` / `.startsWith()` on it. CI runs `scripts/lint-no-source-grep.cjs` and exits 1.
- **Escape**: add `// allow-test-rule: <reason>` anywhere in the file to exempt the whole file. Use when reading product markdown or runtime output (not `.cjs` source).
- **Pattern to reach for instead**: call the exported function, capture stdout/JSON, assert on typed fields.
### Tests — no unescaped RegExp interpolation
-`new RegExp(\`prefix${someVar}\`)` — if `someVar` can contain `.` or other metacharacters (e.g. phase id `5.1`), the pattern is wrong. Always `escapeRegex(someVar)`. The `escapeRegex` utility is in `core.cjs` and already imported in most modules.
### Tests — no dead regex branches in `.includes()`
-`src.includes('foo.*bar')` is always false — `.*` is a regex metacharacter, not a wildcard in `includes`. Either use `new RegExp('foo.*bar').test(src)` or delete the branch.
### Tests — guard top-level `readFileSync` against ENOENT
- Module-level `const src = fs.readFileSync(...)` throws before any `test()` registers, aborting the runner with an unhandled exception instead of a named failure. Wrap in try/catch and rethrow with a helpful message.
### Changesets — `pr:` field must be the PR number, not the issue number
- The `pr:` key in `.changeset/*.md` frontmatter must reference the PR introducing the fix (e.g. `3142`), not the issue it closes (e.g. `3120`). Changelog tooling links to GitHub PRs by this value.
### Shell hooks — never interpolate `$VAR` into single-quoted JS strings
-`node -e "require('$HOOK_DIR/lib/foo.js')"` breaks silently if `$HOOK_DIR` contains a single quote (POSIX-legal). Pass paths via env vars: `GIT_CMD_LIB="$HOOK_DIR/lib/foo.js" node -e "require(process.env.GIT_CMD_LIB)"`.
### Shell guards — `[ -f .git ]` does not detect worktrees from main repo
- In the main repo `.git` is a directory, so `[ -f .git ]` is false and the entire guard is skipped. Use `git rev-parse --git-dir` and match `*.git/worktrees/*` in a `case` statement instead.
### Shell guards — absolute-path containment must use `root/` prefix, not glob
-`[[ "$PATH" != "$ROOT"* ]]` matches sibling prefixes (`/repo-extra` passes when `ROOT=/repo`). Use `[[ "$P" != "$ROOT" && "$P" != "$ROOT/"* ]]`. Also: check `[ -z "$ROOT" ]` and exit 1 before the containment test. Warn → fail-closed for security-relevant path checks.
- When a heading says `(N shipped)` and a footnote says `N-1 top-level references`, update the footnote. CodeRabbit catches this every time.
---
## Workflow learnings (distilled from triage + PR cycle, 2026-05-05)
### Skill consolidation gap class — missing workflow files
- When a command absorbs a micro-skill as a flag (e.g. `capture --backlog`), the old command's process steps must be ported to a `get-shit-done/workflows/<name>.md` file. The routing wrapper in `commands/gsd/*.md` declares an `execution_context``@`-reference to that workflow — if the file doesn't exist the agent loads nothing and has no steps to follow.
- **Detection**: `tests/bug-3135-capture-backlog-workflow.test.cjs` adds a broad regression — every `execution_context``@`-reference in any `commands/gsd/*.md` must resolve to an existing file on disk. This test will catch all future gaps of this class immediately.
- **Prior art**: `reapply-patches.md` was the first gap found and fixed in PR #2824 itself. `add-backlog.md` was missed in the same PR and caught later in #3135. Run the regression test after every consolidation PR.
### CodeRabbit thread resolution — stale threads after allow-test-rule fixes
- After adding `// allow-test-rule:` to silence lint, CodeRabbit's existing inline threads remain open even though the acknowledged fix is in place. Resolve them via `resolveReviewThread` GraphQL mutation before merging — open threads block clean merge history and mislead future reviewers.
### PR discipline — split unrelated changes into separate PRs
- A bug fix and a docs rewrite committed to the same branch produce a noisy diff and a PR that reviewers can't cleanly approve. Cherry-pick doc changes to a dedicated branch (`docs/`) immediately, then force-push the original branch to remove the commit. One concern per PR.
### INVENTORY.md must be updated alongside every workflow file addition/removal
-`docs/INVENTORY.md` tracks the shipped workflow count (`## Workflows (N shipped)`) and has one row per file. Adding or removing a workflow without updating INVENTORY produces an internally inconsistent doc.
- Also update `docs/INVENTORY-MANIFEST.json` — it is the machine-readable manifest and must stay in sync with the filesystem.
- When a flag absorbs a micro-skill, the old skill's `Invoked by` attribution in INVENTORY must move to the new parent (e.g. `add-todo.md` incorrectly claimed `/gsd-capture --backlog` until #3135 corrected it).
### README — keep root README as storyline only; all detail lives in docs/
- Every removed detail section needs a link to the canonical doc that covers it. All doc links must resolve before committing.
- Markdownlint rules to watch: MD001 (heading level skip — don't use `###` directly inside admonitions; use bold instead), MD040 (fenced code blocks must declare a language identifier).
### Issue triage — always check for existing work before filing as new
- Before writing an agent brief for a confirmed bug, check: (1) local branches (`git branch -a | grep <issue>`), (2) untracked/modified files on that branch, (3) stash, (4) open PRs with matching head branch. A crash may have left work 90% done — recover and commit rather than re-implementing.
- Any `gsd-sdk query` verb implemented only in the SDK native registry (no `gsd-tools.cjs` mirror) must be added to `NO_CJS_SUBPROCESS_REASON` in `sdk/src/golden/golden-policy.ts`. Without this entry the golden-policy test fails, treating the verb as a missing implementation rather than an intentional SDK-only path.
The following files are maintainer-owned coding standards and must be treated as canonical when contributing:
-`CONTEXT.md` — domain language and module naming standards
-`docs/adr/` — Architecture Decision Records (ADRs) for accepted architectural decisions
Contributor requirements:
- Read `CONTEXT.md` before naming or refactoring modules/interfaces/seams.
- Use `CONTEXT.md` vocabulary consistently in code comments, tests, issue/PR text, and docs for the touched area.
- Check relevant ADRs in `docs/adr/` before proposing or implementing architectural changes.
- If a change intentionally revisits an ADR decision, call it out explicitly in the linked issue and PR rationale.
- Do not rewrite maintainer intent in `CONTEXT.md`/ADRs as part of drive-by cleanup; propose focused updates tied to approved scope.
**Every PR must link to an approved issue.** PRs without a linked issue are closed without review, no exceptions.
- **No draft PRs** — draft PRs are automatically closed. Only open a PR when it is complete, tested, and ready for review. If your work is not finished, keep it on your local branch until it is.
@@ -91,6 +105,23 @@ PRs that arrive without a properly-labeled linked issue are closed automatically
- **CI must pass** — all matrix jobs (Ubuntu × Node 22, 24; macOS × Node 24) must be green
- **Scope matches the approved issue** — if your PR does more than what the issue describes, the extra changes will be asked to be removed or moved to a new issue
## CHANGELOG Entries — Drop a Fragment
**Do not edit `CHANGELOG.md` directly.** Two PRs that both append to a `### Fixed` block always conflict on merge — git can't pick a serialization order without a human. Instead, every PR with user-facing changes drops a fragment file in `.changeset/`.
```bash
npm run changeset -- --type Fixed --pr <YOUR_PR_NUMBER> \
--body "**\`/gsd-foo\` no longer drops trailing slashes** — explain the user-visible change."
```
This writes `.changeset/<adjective>-<noun>-<noun>.md`. Three random words → concurrent PRs never collide. Allowed `type:` values follow [Keep a Changelog](https://keepachangelog.com/): `Added`, `Changed`, `Deprecated`, `Removed`, `Fixed`, `Security`.
Fragments are consolidated into `CHANGELOG.md` at release time by the release workflow. See [`.changeset/README.md`](.changeset/README.md) for the format spec and [#2975](https://github.com/gsd-build/get-shit-done/issues/2975) for the rationale.
**CI enforcement:** the `Changeset Required` workflow (`scripts/changeset/lint.cjs`) fails any PR that touches `bin/`, `get-shit-done/`, `agents/`, `commands/`, `hooks/`, or `sdk/src/` without a `.changeset/*.md` fragment.
**Opt-out:** PRs with no user-facing impact (test refactors, lint config changes, CI tweaks, formatting-only changes) can add the `no-changelog` label. The lint honors it. When unsure whether a change is user-facing, **add the fragment**.
## Testing Standards
All tests use Node.js built-in test runner (`node:test`) and assertion library (`node:assert`). **Do not use Jest, Mocha, Chai, or any external test framework.**
@@ -487,6 +518,14 @@ Run locally before pushing: `npm run lint:tests`
### Test Requirements by Contribution Type
### Architecture-Aware Testing Requirements
When work touches architecture, routing, policy, registry assembly, or command semantics:
- Write tests against module **interfaces** and seam behavior, not implementation trivia.
- Prefer invariant/contract tests that protect ADR-backed behavior and `CONTEXT.md` terminology.
- Ensure tests validate canonical behavior through the defined seam (for example: structured result contracts, canonical command metadata, and adapter parity), not source-text coupling.
- If ADRs define expected behavior, tests should assert those expectations directly.
The required tests differ depending on what you are contributing:
**Bug Fix:** A regression test is required. Write the test first — it must demonstrate the original failure before your fix is applied, then pass after the fix. A PR that fixes a bug without a regression test will be asked to add one. "Tests pass" does not prove correctness; it proves the bug isn't present in the tests that exist.
@@ -80,7 +80,7 @@ GSD가 그걸 고칩니다. Claude Code를 신뢰할 수 있게 만드는 컨텍
전체 목록은 [v1.39.0 릴리스 노트](https://github.com/gsd-build/get-shit-done/releases/tag/v1.39.0)를 참고하세요.
- **`--minimal` 설치 프로파일** — 별칭 `--core-only`. 메인 루프 6개 스킬(`new-project`, `discuss-phase`, `plan-phase`, `execute-phase`, `help`, `update`)만 설치하고 `gsd-*` 서브에이전트는 설치하지 않음. 콜드 스타트 시스템 프롬프트 오버헤드를 ~12k 토큰에서 ~700 토큰으로 축소(≥94% 감소). 32K–128K 컨텍스트의 로컬 LLM이나 토큰 과금 API에 유용.
- **`/gsd-edit-phase`** — `ROADMAP.md`에 있는 기존 단계의 임의 필드를 그 자리에서 수정(번호와 위치는 변경되지 않음). `--force`는 확인 diff를 건너뛰고, `depends_on` 참조를 검증하며 쓰기 시 `STATE.md`도 갱신.
- **`/gsd-phase --edit`** — `ROADMAP.md`에 있는 기존 단계의 임의 필드를 그 자리에서 수정(번호와 위치는 변경되지 않음). `--force`는 확인 diff를 건너뛰고, `depends_on` 참조를 검증하며 쓰기 시 `STATE.md`도 갱신.
- **머지 후 빌드 & 테스트 게이트** — `execute-phase` 5.6 단계가 `workflow.build_command` 설정을 우선 자동 감지하고, 없으면 Xcode(`.xcodeproj`), Makefile, Justfile, Cargo, Go, Python, npm 순으로 폴백. Xcode/iOS 프로젝트는 `xcodebuild build` 및 `xcodebuild test`를 자동 실행. 병렬·직렬 모드 모두에서 동작.
- **런타임별 리뷰 모델 선택** — `review.models.<cli>`로 각 외부 리뷰 CLI(codex, gemini 등)가 플래너/실행 프로파일과 독립적으로 자체 모델을 선택할 수 있음.
- **워크스트림 설정 상속** — `GSD_WORKSTREAM`이 설정되면 루트 `.planning/config.json`을 먼저 로드한 뒤 워크스트림 설정을 딥 머지(충돌 시 워크스트림 우선). 워크스트림 설정에서 명시적 `null`은 루트 값을 덮어씀.
@@ -396,7 +396,7 @@ claude --dangerously-skip-permissions
@@ -78,7 +78,7 @@ Quality gates embutidos capturam problemas reais: detecção de schema drift sin
Lista completa nas [notas de release v1.39.0](https://github.com/gsd-build/get-shit-done/releases/tag/v1.39.0).
- **Perfil de instalação `--minimal`** — alias `--core-only`. Instala apenas os 6 skills do loop principal (`new-project`, `discuss-phase`, `plan-phase`, `execute-phase`, `help`, `update`) e nenhum subagente `gsd-*`. Reduz o overhead do system prompt no cold-start de ~12k para ~700 tokens (≥94% de redução). Útil para LLMs locais com contexto de 32K–128K e APIs cobradas por token.
- **`/gsd-edit-phase`** — edita qualquer campo de uma fase existente em `ROADMAP.md` no lugar, sem alterar o número ou a posição. `--force` pula o diff de confirmação; referências em `depends_on` são validadas e o `STATE.md` é atualizado na escrita.
- **`/gsd-phase --edit`** — edita qualquer campo de uma fase existente em `ROADMAP.md` no lugar, sem alterar o número ou a posição. `--force` pula o diff de confirmação; referências em `depends_on` são validadas e o `STATE.md` é atualizado na escrita.
- **Build & test gate pós-merge** — o passo 5.6 de `execute-phase` agora detecta automaticamente o comando de build em `workflow.build_command`, com fallback para Xcode (`.xcodeproj`), Makefile, Justfile, Cargo, Go, Python ou npm. Projetos Xcode/iOS rodam `xcodebuild build` e `xcodebuild test` automaticamente. Funciona em modo paralelo e serial.
- **Modelo de review por runtime** — `review.models.<cli>` permite que cada CLI externa de review (codex, gemini, etc.) escolha seu próprio modelo, independente do perfil de planner/executor.
- **Herança de configuração de workstream** — quando `GSD_WORKSTREAM` está definido, o `.planning/config.json` raiz é carregado primeiro e merge-deep com o config da workstream (workstream vence em conflito). Um `null` explícito no config da workstream sobrescreve corretamente o valor raiz.
@@ -259,7 +259,7 @@ Validação manual orientada para confirmar que a feature realmente funciona com
Ou deixe o GSD decidir:
```
/gsd-next
/gsd-progress --next
```
### Modo rápido
@@ -327,7 +327,7 @@ Cada tarefa gera commit próprio, facilitando `git bisect`, rollback e rastreabi
| `/gsd-execute-phase <N>` | Executa planos em ondas paralelas |
| `/gsd-verify-work [N]` | UAT manual |
| `/gsd-ship [N] [--draft]` | Cria PR da fase validada |
| `/gsd-next` | Avança automaticamente para o próximo passo |
| `/gsd-progress --next` | Avança automaticamente para o próximo passo |
| `/gsd-fast <text>` | Tarefas triviais sem planejamento |
| `/gsd-complete-milestone` | Fecha o marco e marca release |
| `/gsd-new-milestone [name]` | Inicia próximo marco |
@@ -339,7 +339,7 @@ Cada tarefa gera commit próprio, facilitando `git bisect`, rollback e rastreabi
| `/gsd-quick [--full] [--discuss] [--research]` | Execução rápida com garantias do GSD (`--full` ativa todas as etapas, `--validate` ativa apenas verificação) |
| `/gsd-health [--repair]` | Verifica e repara `.planning/` |
@@ -370,7 +370,7 @@ Você pode configurar no `/gsd-new-project` ou ajustar depois com `/gsd-settings
description: Applies fixes to code review findings from REVIEW.md. Reads source files, applies intelligent fixes, and commits each fix atomically. Spawned by /gsd-code-review-fix.
description: Applies fixes to code review findings from REVIEW.md. Reads source files, applies intelligent fixes, and commits each fix atomically. Spawned by /gsd-code-review --fix.
tools: Read, Edit, Write, Bash, Grep, Glob
color: "#10B981"
# hooks:
@@ -10,7 +10,7 @@ color: "#10B981"
<role>
You are a GSD code fixer. You apply fixes to issues found by the gsd-code-reviewer agent.
Spawned by `/gsd-code-review-fix` workflow. You produce REVIEW-FIX.md artifact in the phase directory.
Spawned by `/gsd-code-review --fix` workflow. You produce REVIEW-FIX.md artifact in the phase directory.
Your job: Read REVIEW.md findings, fix source code intelligently (not blind application), commit each fix atomically, and produce REVIEW-FIX.md report.
@@ -231,39 +231,63 @@ test -n "$branch" || { echo "Detached HEAD is not supported for review-fix (#268
1. Parse `padded_phase` and `phase_dir` from the `<config>` block (needed for the path and for the sentinel location).
2. Resolve the current branch: `branch=$(git branch --show-current)`. If empty (detached HEAD), print an error and exit — detached-HEAD state is not supported; commits made in a detached-HEAD worktree would not advance the branch.
3. **Recovery check (#2839):** If `${phase_dir}/.review-fix-recovery-pending.json` already exists, a prior run was interrupted. Parse the JSON, attempt to remove the orphan worktree it points at (best-effort, with `--force`), then delete the stale sentinel before continuing. This makes a re-run of `/gsd-code-review-fix` self-healing.
3. **Recovery check (#2839, #2990):** If `${phase_dir}/.review-fix-recovery-pending.json` already exists, a prior run was interrupted. Parse the JSON, attempt to remove the orphan worktree it points at (best-effort, with `--force`), and delete the stale `reviewfix_branch` (best-effort, with `git branch -D`), then delete the stale sentinel before continuing. This makes a re-run of `/gsd-code-review --fix` self-healing.
4. Create a unique worktree path: `wt=$(mktemp -d "/tmp/sv-${padded_phase}-reviewfix-XXXXXX")`. The `mktemp` suffix ensures concurrent runs for the same phase do not collide.
5. Run `git worktree add "$wt" "$branch"` — this attaches the worktree to the current branch so commits advance it.
6. **Write the recovery sentinel** at `${phase_dir}/.review-fix-recovery-pending.json` containing `{worktree_path, branch, padded_phase, started_at}`. Doing this AFTER `git worktree add` ensures the sentinel only ever points at a real worktree.
7. All subsequent file reads, edits, and commits happen inside `$wt`.
5. Run `git worktree add -b "$reviewfix_branch" "$wt" "$branch"` — this creates a NEW branch (`gsd-reviewfix/${padded_phase}-$$`) starting from the current branch tip and attaches the worktree to that new branch. Attaching to a new branch (rather than `$branch` directly) is what allows the worktree to coexist with the user's checkout — git refuses to check out the same branch in two worktrees by default (#2990). Commits made inside the worktree advance `$reviewfix_branch`; the cleanup tail fast-forwards `$branch` to `$reviewfix_branch` so the user's branch ends up with the agent's commits.
6. **Write the recovery sentinel** at `${phase_dir}/.review-fix-recovery-pending.json` containing `{worktree_path, branch, reviewfix_branch, padded_phase, started_at}`. Doing this AFTER `git worktree add` ensures the sentinel only ever points at a real worktree. The sentinel includes `reviewfix_branch` so recovery can clean both the orphan worktree AND its temp branch.
7. All subsequent file reads, edits, and commits happen inside `$wt` (which is on `$reviewfix_branch`, not `$branch`).
**If `git worktree add` fails**, surface the error and exit — do not force-remove the path, as another concurrent run may be holding it. Do not write the sentinel (the worktree does not exist).
**If `git worktree add` fails**, surface the error and exit — do not force-remove the path, as another concurrent run may be holding it. Do not write the sentinel (the worktree does not exist). Do not delete `$reviewfix_branch` either; if `-b` failed, no temp branch was created.
**Cleanup tail (transactional, ALWAYS — even on failure):** After writing REVIEW-FIX.md and before returning to the orchestrator, run the two-step cleanup in this exact order:
**Cleanup tail (transactional, ALWAYS — even on failure):** After writing REVIEW-FIX.md and before returning to the orchestrator, run the cleanup in this exact order:
```bash
# Step 1: drop the worktree FIRST. If this succeeds and the process is then
# killed, the next run finds a sentinel pointing at a worktree that no longer
# exists — the recovery branch handles this gracefully (best-effort remove +
# sentinel delete). If we reversed the order (sentinel removed first, then
# worktree remove), an interruption between the two steps would leave NO
# sentinel and an orphan worktree — exactly the bug from #2839.
# Step 1 (#2990): fast-forward $branch to capture the commits the agent
# made on $reviewfix_branch. Run from the main repo (not $wt) — the user's
# checkout owns $branch. --ff-only ensures we never silently drop or
# rewrite history if the user committed to $branch concurrently; on
# divergence, this fails loudly and the temp branch is left for the
# user to inspect/merge manually. We deliberately resolve the main repo
# path via `git worktree list --porcelain` rather than assuming $PWD,
# because the agent ran inside $wt.
# Strip the literal "worktree " prefix and print the rest of the line, then
# exit on the first match. This preserves paths that contain spaces
# (awk '$2' would truncate "/path/with spaces/repo" to "/path/with").
# Step 4: drop the recovery sentinel ONLY after `git worktree remove`
# returns successfully. This atomic-ish ordering is what makes the
# cleanup tail transactional from the orchestrator's perspective.
rm -f "$sentinel"
```
This cleanup is unconditional — register it mentally as a finally-block obligation. If the agent exits early (config error, no findings, etc.), still run the two-step cleanup tail (`git worktree remove "$wt" --force` followed by `rm -f "$sentinel"`) before exit. The sentinel must NEVER be removed before `git worktree remove` succeeds.
This cleanup is unconditional — register it mentally as a finally-block obligation. If the agent exits early (config error, no findings, etc.), still run the cleanup tail in order (fast-forward → worktree remove → temp branch delete → sentinel rm) before exit. The sentinel must NEVER be removed before `git worktree remove` succeeds. The temp branch must NEVER be deleted while the fast-forward is in a diverged state.
</step>
<step name="load_context">
@@ -528,9 +584,9 @@ _Iteration: {N}_
<critical_rules>
**ALWAYS run inside the isolated worktree** — set up via `branch=$(git branch --show-current)` + `wt=$(mktemp -d "/tmp/sv-${padded_phase}-reviewfix-XXXXXX")` + `git worktree add "$wt" "$branch"` at the very start (see `setup_worktree` step). Using `mktemp` ensures concurrent runs do not collide. Attaching to `$branch` (not `HEAD`) ensures commits advance the branch. Every file read, edit, and commit must happen inside `$wt`. Run `git worktree remove "$wt" --force` unconditionally when done (treat it as a finally block). If `git worktree add` fails, exit with an error rather than force-removing a path another run may hold. This prevents racing the foreground session on the shared main working tree (#2686).
**ALWAYS run inside the isolated worktree** — set up via `branch=$(git branch --show-current)` + `wt=$(mktemp -d "/tmp/sv-${padded_phase}-reviewfix-XXXXXX")` + `git worktree add -b "$reviewfix_branch" "$wt" "$branch"` at the very start (see `setup_worktree` step). Using `mktemp` ensures concurrent runs do not collide. Attaching to a NEW branch `$reviewfix_branch` (not `$branch` directly) is required because git refuses to check out the same branch in two worktrees by default — `$branch` is already checked out in the user's main repo (#2990). Commits advance `$reviewfix_branch`; the cleanup tail fast-forwards `$branch` to `$reviewfix_branch` so the user's branch ends up with the agent's commits. Every file read, edit, and commit must happen inside `$wt`. Run the four-step cleanup tail unconditionally when done (treat it as a finally block). If `git worktree add` fails, exit with an error rather than force-removing a path another run may hold. This prevents racing the foreground session on the shared main working tree (#2686).
**ALWAYS run the transactional cleanup tail in order** (#2839): `git worktree remove "$wt" --force` MUST happen BEFORE `rm -f "$sentinel"` (the recovery sentinel at `${phase_dir}/.review-fix-recovery-pending.json`). The sentinel is written AFTER `git worktree add` succeeds and removed only AFTER `git worktree remove` returns successfully. This ordering is what makes the cleanup tail transactional — an interruption between commits and `git worktree remove` leaves the sentinel behind so a future run, `/gsd-resume-work`, or `/gsd-progress` can detect and complete the recovery. Reversing the order recreates the orphan-worktree bug.
**ALWAYS run the transactional cleanup tail in order** (#2839, #2990): the cleanup is four steps with strict ordering. (1) `git -C "$main_repo" merge --ff-only "$reviewfix_branch"` — fast-forward the user's branch to capture the agent's commits; on divergence, fail loudly and preserve the temp branch. (2) `git worktree remove "$wt" --force`. (3) `git -C "$main_repo" branch -D "$reviewfix_branch"` ONLY if the fast-forward succeeded; otherwise leave the temp branch for manual merge. (4) `rm -f "$sentinel"` (the recovery sentinel at `${phase_dir}/.review-fix-recovery-pending.json`). The sentinel is written AFTER `git worktree add` succeeds and removed only AFTER `git worktree remove` returns successfully. The temp branch is deleted only when the fast-forward succeeded. This ordering is what makes the cleanup tail transactional — an interruption between commits and `git worktree remove` leaves the sentinel behind (with `reviewfix_branch` recorded) so a future run, `/gsd-resume-work`, or `/gsd-progress` can detect and complete the recovery. Reversing the order recreates the orphan-worktree bug.
**ALWAYS use the Write tool to create files** — never use `Bash(cat << 'EOF')` or heredoc commands for file creation.
[ -z "$WT_ROOT" ] && { echo "FATAL: could not determine worktree root" >&2; exit 1; }
# Verify absolute path containment with boundary safety (not glob prefix which allows siblings)
if [[ "$ABS_PATH" != "$WT_ROOT" && "$ABS_PATH" != "$WT_ROOT/"* ]]; then
echo "FATAL: $ABS_PATH is outside the worktree ($WT_ROOT) — use a relative path or recompute from WT_ROOT" >&2
exit 1
fi
```
Prefer **relative paths** for all Edit/Write operations inside a worktree. When an absolute path
is unavoidable, always derive it from `git rev-parse --show-toplevel` run inside the worktree,
not from a `pwd` captured in the orchestrator context.
**0. Pre-commit HEAD safety assertion (worktree mode only, MANDATORY before every commit — #2924):**
When running inside a Claude Code worktree (`.git` is a file, not a directory), assert HEAD is on a per-agent branch BEFORE staging or committing. If HEAD has drifted onto a protected ref, HALT — never self-recover via `git update-ref refs/heads/<protected>`:
@@ -747,7 +747,7 @@ The `tasks` array in the result shows each task's completeness:
**For manual validation of specificity** (`verify.plan-structure` checks structure, not content quality), use structured extraction instead of grepping raw XML:
@@ -49,7 +49,7 @@ Before planning, discover project context:
</project_context>
<context_fidelity>
## User Decision Fidelity
## CRITICAL: User Decision Fidelity
The orchestrator provides user decisions in `<user_decisions>` tags from `/gsd-discuss-phase`.
@@ -73,7 +73,7 @@ The orchestrator provides user decisions in `<user_decisions>` tags from `/gsd-d
</context_fidelity>
<scope_reduction_prohibition>
## Never Simplify User Decisions — Split Instead
## CRITICAL: Never Simplify User Decisions — Split Instead
**PROHIBITED language/patterns in task actions:**
- "v1", "v2", "simplified version", "static for now", "hardcoded for now"
@@ -94,11 +94,11 @@ Do NOT silently omit features. Instead:
3. The orchestrator presents the split to the user for approval
4. After approval, plan each sub-phase within budget
## Multi-Source Coverage Audit
## Multi-Source Coverage Audit (MANDATORY in every plan set)
@~/.claude/get-shit-done/references/planner-source-audit.md for full format, examples, and gap-handling rules.
Perform this audit for every plan set before finalizing. Check all four source types: **GOAL** (ROADMAP phase goal), **REQ** (phase_req_ids from REQUIREMENTS.md), **RESEARCH** (RESEARCH.md features/constraints), **CONTEXT** (D-XX decisions from CONTEXT.md).
Audit ALL four source types before finalizing: **GOAL** (ROADMAP phase goal), **REQ** (phase_req_ids from REQUIREMENTS.md), **RESEARCH** (RESEARCH.md features/constraints), **CONTEXT** (D-XX decisions from CONTEXT.md).
Every item must be COVERED by a plan. If ANY item is MISSING → return `## ⚠ Source Audit: Unplanned Items Found` to the orchestrator with options (add plan / split phase / defer with developer confirmation). Never finalize silently with gaps.
@@ -582,7 +582,7 @@ Only include what Claude literally cannot do.
## The Process
**Step 0: Extract Requirement IDs**
Read ROADMAP.md `**Requirements:**` line for this phase. Strip brackets if present (e.g., `[AUTH-01, AUTH-02]` → `AUTH-01, AUTH-02`). Distribute requirement IDs across plans — each plan's `requirements` frontmatter field lists the IDs its tasks address. Every requirement ID MUST appear in at least one plan. Plans with an empty `requirements` field are invalid.
Read ROADMAP.md `**Requirements:**` line for this phase. Strip brackets if present (e.g., `[AUTH-01, AUTH-02]` → `AUTH-01, AUTH-02`). Distribute requirement IDs across plans — each plan's `requirements` frontmatter field MUST list the IDs its tasks address.**CRITICAL:** Every requirement ID MUST appear in at least one plan. Plans with an empty `requirements` field are invalid.
**Security (when `security_enforcement` enabled — absent = enabled):** Identify trust boundaries in this phase's scope. Map STRIDE categories to applicable tech stack from RESEARCH.md security domain. For each threat: assign disposition (mitigate if ASVS L1 requires it, accept if low risk, transfer if third-party). Every plan MUST include `<threat_model>` when security_enforcement is enabled.
@@ -560,7 +560,7 @@ When files are written and returning to orchestrator:
### Files Ready for Review
User can review actual files in the editor or via SDK queries (e.g. `node ./node_modules/@gsd-build/sdk/dist/cli.js query roadmap.analyze` and `query state.load`) instead of ad-hoc shell `cat`.
User can review actual files in the editor or via SDK queries (e.g. `gsd-sdk query roadmap.analyze` and `gsd-sdk query state.load`) instead of ad-hoc shell `cat`.
{If gaps found during creation:}
Some files were not shown because too many files have changed in this diff
Show More
Reference in New Issue
Block a user
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.