Scans `gsd-ns-<router>/skills/<stem>/SKILL.md` in addition to the
existing flat `<stem>/SKILL.md` layout, so gsd-health and gsd-settings
report the correct concrete skill count on nested-layout runtimes
(cline, qwen, hermes, augment, trae, antigravity).
Guard: descent into a `skills/` subdir is restricted to `gsd-ns-*`
router directories — unrelated user dirs that happen to have a
`skills/` subdir are not traversed. Dual-routed concretes (same name
under two routers) are deduped within each root.
Adds a negative-case regression test: verifies that a non-`gsd-ns-*`
dir (e.g. `my-tool/`, `gsd-settings/`) with its own `skills/`
subdir does NOT contribute nested entries to the manifest.
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
PR #883 nested Claude skills 3 levels deep under gsd-ns-*/skills/<stem>/SKILL.md.
Claude Code's Skill tool scans only one level under ~/.claude/skills/ — nested
concrete skills were never listed and Skill(skill="gsd-plan-phase") calls failed.
Revert to flat layout: all ~61 concrete skills at ~/.claude/skills/gsd-<name>/SKILL.md.
The 6 other runtimes confirmed as non-recursive scanners (cline, qwen, hermes, augment,
trae, antigravity) retain their nested layout — only Claude changes.
Tradeoff: ~61 top-level skill dirs return to the flat install, but they are discoverable
and invokable. Nested concretes were invisible to the Skill tool entirely.
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
`context: fork` strips the `Agent` tool from a subagent's environment.
Spawning orchestrators (`/gsd-autonomous`, `/gsd-execute-phase`,
`/gsd-plan-phase`) depend on `Agent` to dispatch sub-agents; running
them forked silently disables the core capability they exist to provide
(#921). Remove `context: fork` from all three command frontmatter files.
`effort: xhigh` (introduced by #769) is preserved.
The `<runtime_compatibility>` Agent-availability guard added by #913 was
checking whether `Agent` was present *before* attempting the call. On
runtimes where the tool list is dynamically resolved this produced
false-negative aborts in sessions that have the tool (#922). Replace
the introspection-based pattern with an attempt-based gate: always
attempt the `Agent()` call; stop only if a real tool-unavailable error
is returned. This preserves #853's backgrounded-session close-off and
#913's intent of preventing inline role-collapse, while eliminating
false negatives.
Tests updated: enh-769-context-fork-effort.install.test.cjs asserts the
three orchestrators lack `context: fork` and that the converter still
passes the field through for non-orchestrator commands; plan-phase-drift-
guard.test.cjs adds four assertions for the attempt-based gate language;
workflow-size-budget unchanged (budgets not exceeded).
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Read `data.hook_event_name` from the stdin payload and fall back to the
Gemini/non-Gemini heuristic only when the field is absent or blank.
Fixes Claude Code rejecting output with "expected Stop but got PostToolUse"
when the monitor is called by Stop, SubagentStop, or PreCompact hooks.
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Add the loop.render-hooks resolver: the first registry-consuming query.
`gsd-tools loop render-hooks <point>` validates the point against the
authoritative canonical 12, reads the registry's materialized byLoopPoint
hooks, filters them by activation, and emits a JSON envelope {point,
activeHooks, rendered} with ordered markdown.
Activation resolves each hook's `when` key by precedence: loadConfig value
(post-cutover federated) -> raw config.json workstream/root single-key lookup
(pre-cutover central override) -> registry configSchema default (so a
default:true capability hook is active out-of-the-box) -> inactive. Guarded
single-value reads only (no merged object built from untrusted keys).
Registry-only: no workflow calls the resolver yet (wiring is the phase-6
cutover). Completes the phase-3 trio.
Closes#918
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
The bug #1998 subtest "checkbox updated when archived milestones exist in
<details>" flaked under the high-concurrency docker run (~672 test files in
parallel): the current-milestone checkbox was left unchecked.
Root cause: `gsd-tools phase complete` writes ROADMAP.md as its LAST step,
after a read-heavy parse/lock sequence. Under heavy parallel CPU/IO
contention the test's tight `timeout: 10000` fired mid-parse and SIGTERM'd
the subprocess before that write landed, leaving ROADMAP.md pristine (both
phases `- [ ]`). The bare `catch {}` silently swallowed the kill, so a
timeout masqueraded as a "checkbox not checked" assertion failure. All I/O
is scoped to each test's tmpDir, so there is no cross-process race — the
timeout was the sole cause.
Consolidate all 7 duplicated `phase complete` call sites (suites #1998,
#2005, #2526) into a shared runPhaseComplete() helper that:
1. raises the timeout to 60s so the test's own timer never kills the
subprocess under load;
2. never silently swallows a signal/timeout kill (rethrows loudly with
captured output) while still tolerating a clean non-zero exit for the
ROADMAP-asserting tests via { tolerateExit: true }.
No retry loop. Verified with 3x `gsd-test --reset` full docker runs
(13207 tests / 2311 suites each, 0 failures, flaky subtest green every
round).
Closes#916
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Build the federated config merge: each capability owns its config-key slice
(ADR-857 decision 3 / ADR-894), and loadConfig merges them defensively. The
registry now emits a full configSchema index ({key:{owner,type,default,
description}}, generator-validated); a new src/federated-config.cts resolves
federated keys defensively (skip central keys -> pending-migration warning,
skip malformed slices -> warning never throw, else type-checked user override
?? default, with nested dotted-path lookup and enum validation); and loadConfig
applies the overlay on every return path.
Wired as a provably-empty no-op channel: every UI-pilot key is still central,
so validKeys is empty and loadConfig returns byte-identical output on all paths
(identity return when the overlay is empty; shared CONFIG_DEFAULTS never
mutated). Registry-only; no key is cut over; nothing in the live loop changes.
Closes#910
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Three-part fix for the top-level inline collapse bug:
1. plan-phase.md: add <runtime_compatibility> block after
</available_agent_types> that makes the Agent-availability
requirement explicit; workflow fails-closed (stops with a clear
log) in genuinely Agent-less contexts.
2. plan-phase.md: rename 7 "ORCHESTRATOR RULE — CODEX RUNTIME"
labels to "ALL RUNTIMES" so the spawn guard applies universally
(not just when Codex is detected).
3. execute-phase.md: scope the existing "Other runtimes" inline-
fallback prose to non-Claude contexts, preserving the #853
backgrounded-agent behaviour for Claude Code background agents.
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
syncStateFrontmatter was silently dropping current_phase, current_phase_name,
current_plan, and progress when body annotations were absent (e.g. after an
agent or tool rewrote the body). These scalars can only be derived from body
annotations — when absent, buildStateFrontmatter returns nothing for those
keys. Added existingFm fallbacks mirroring the same pattern already applied in
cmdStateJson, so every writeStateMd call preserves the existing values instead
of stripping them. Also extended cmdStateJson with the same fallbacks for the
three non-progress scalars.
Adds regression test (7 cases) + lint-test-file-count allowlist entry.
Closes#905
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
buildRoadmapPhaseVariants() only matched heading-style phases (## Phase N:),
silently skipping the supported checklist format (- [x] **Phase N: name**).
This caused W007 false-positives for every on-disk phase dir when the project
uses a checklist ROADMAP. Fix adds a second regex pass (mirroring the existing
buildNotStartedPhaseVariants() approach). Also refactors the duplicate
inline heading-only regex in cmdValidateConsistency() to delegate to
buildRoadmapPhaseVariants() (DRY). Regression test in
tests/bug-892-validate-checklist-roadmap-phases.test.cjs covers both paths.
Closes#892
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
- Updated `gsd-core/workflows/_runtime-launcher.snippet.sh` with 15 new
`elif` arms covering Hermes, Cursor, Codex, Gemini, Copilot, Windsurf,
Augment, Trae, Qwen, CodeBuddy, Cline, Grok, Antigravity, OpenCode, and
Kilo (respecting each runtime's env-var override with a `$HOME`-relative
default).
- Re-ran `scripts/sync-runtime-launcher.cjs` to propagate the expanded
snippet into all `gsd-core/workflows/*.md` files (~70 files).
- Manually applied the same snippet update to `commands/gsd/import.md`
(1 occurrence) and `commands/gsd/graphify.md` (5 occurrences) — these
are not covered by the sync script.
- Updated `tests/workflow-size-budget.test.cjs` budgets (XL/LARGE/DEFAULT
+ discuss-phase target) to account for the ~3 KB snippet expansion.
- Added regression test `tests/bug-891-non-claude-runtime-home-fallback.test.cjs`
(6 tests: structural probe presence, ordering, behavioral HERMES_HOME
env-var + default-path stubs, resolution order, and workflow propagation).
- Added `.changeset/891-launcher-non-claude-runtime-homes.md` (Fixed).
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Wrap the {phase} substitution in normalizePhaseName() at both fix sites:
- src/init.cts — cmdInitExecutePhase branch_name output
- src/commands.cts — cmdCommit pre-execution branch derivation
When project_code is set (e.g. "CK"), extractPhaseToken returns the
full prefixed token "CK-01" as phase_number. Without normalization the
generated branch was "gsd/phase-CK-01-foundation"; after this fix it is
"gsd/phase-01-foundation", matching the documented {phase} contract
(padded numeric only).
Adds a regression test in tests/init.test.cjs.
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Replace the inline LOOP_HOST_CONTRACT constant in the Capability Registry
generator with a generated-from-workflows contract (ADR-894 §3). The contract
is now derived from inert `<!-- gsd:loop-host ... -->` marker blocks in the five
step workflows, emitted as the committed gsd-core/bin/lib/loop-host-contract.cjs,
and required by gen-capability-registry.cjs — one source of truth, no drift.
Drift guards in gen-loop-host-contract.cjs: per-step point ownership (each step
must declare exactly its canonical loop points), multiple-block + duplicate-key
hard errors, and a word-boundary agent-role cross-check. Contract content is
byte-identical to the former constant; registry-only, nothing wired into the
live loop.
Closes#903
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* feat(#896): Capability Registry generator + UI pilot (ADR-857 phase 3a-impl)
First phase-3 code: the Capability Registry generation pipeline, built against
the ADR-894 contract and NOT wired into the live loop (registry-only, per the
staged-cutover design).
- capabilities/ui/capability.json — the UI pilot (ADR-894 worked example): 2
skills, 2 agents, 3 config keys, 2 steps + 1 gate, with `when` activation.
- scripts/gen-capability-registry.cjs — --write/--check generator. Hand-rolled
schema validation (envelope + role-typed feature/runtime bodies + typed
steps/contributions/gates + when + gate-check variants); cross-capability
invariants (single ownership; requires exist+acyclic+tier-monotone; config-key
ownership exclusive, collision-vs-central as a pending-migration warning);
hooks validated against an inline LOOP_HOST_CONTRACT (3a-impl-2 swaps its
source to the generated-from-workflows contract); GLOBAL point-ordered
consumes-satisfiability; materialized byLoopPoint ordering (produces/consumes
topo-sort); emits gsd-core/bin/lib/capability-registry.cjs (role-partitioned
indexes + requiresClosure). Prototype-pollution guards (Object.create(null) +
inline literal key checks) + fragment.path traversal guard.
- gsd-core/bin/lib/capability-registry.cjs — committed generated artifact
(mirrors package-identity.cjs: script-generated, tracked, linted, regenerated
on build, drift-tested), wired via the new `gen:capability-registry` build step.
- tests/capability-registry.test.cjs — 72 tests: schema + invariant + hook +
ordering + adversarial (path-traversal, proto-pollution, runtime body,
self-consume, cycles, collisions) + committed-file staleness guard.
New-CLI-module checklist (INVENTORY 97->98, MANIFEST, ARCHITECTURE), CONTEXT.md
"Capability Registry" un-[Planned]'d. Nothing wired into install/surface/loop.
Gates: lint, code-review (4 bugs fixed), security-review (path-traversal +
prototype-pollution fixed), codex adversarial-review ×3 (8+ findings fixed,
confirmed sound), clean-build docker 13190 pass / 0 fail.
Closes#896
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#896): CRLF-agnostic --check for capability-registry staleness (Windows)
The committed capability-registry.cjs staleness guard failed on Windows CI only:
git checks out the committed .cjs as CRLF (autocrlf, no .gitattributes) while the
generator emits LF, so the byte-for-byte --check comparison mismatched. Normalize
line endings on both sides of the --check comparison (no .gitattributes change,
no change to the LF the generator writes). Adds a regression test simulating the
Windows CRLF checkout.
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Three test files copy-pasted the concrete-skill->namespace-router CHILD_ROUTER
map verbatim, and two more duplicated an identical local parseRouterRequires
regex. Introduce tests/helpers/nested-layout.cjs that derives the child->router
map from the authoritative commands/gsd/ns-*.md requires: lists once, reusing
the production parseRequires (now exported from install-profiles) plus a
nestedSkillPath(skillsRoot, prefix, stem) helper. Refactor all five test files
to import from it.
Test-only + a single internal export addition; no production behavior change.
Closes#887
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
ADR-857 rollout phase 2e — the largest core.cts extraction. Move the
configuration-loading subsystem (loadConfig + _getConfigDefault/
_getNestedConfigDefault/CONFIG_DEFAULTS/_deepMergeConfig, isGitIgnored +
_gitIgnoredCache, _warnUnknownProfileOverrides + RUNTIME_OVERRIDE_TIERS + the
dedup Sets, _resetRuntimeWarningCacheForTests) out of core.cts into a new leaf
module src/config-loader.cts. core.cts re-exports the public surface
(loadConfig, isGitIgnored, CONFIG_DEFAULTS, RUNTIME_OVERRIDE_TIERS,
_resetRuntimeWarningCacheForTests); 12+ callers unchanged.
Cycle-free: config-loader imports only leaves (configuration, config-schema,
planning-workspace, shell-command-projection, core-utils, model-catalog). All
core-internal helpers loadConfig touches moved with it to avoid a cycle. core
keeps CANONICAL_CONFIG_DEFAULTS for its model-resolver functions, which now
resolve loadConfig via the binding — this unblocks the final model-resolver
extraction (2f). core.cts: 1275 -> 792 lines.
Repointed tests/config-field-docs.test.cjs (a docs-parity source check) to read
the CONFIG_DEFAULTS literal from its new home (config-loader.cjs). New-CLI-module
checklist done (.gitignore, eslint, INVENTORY 95->96 + row, manifest,
ARCHITECTURE, CONTEXT.md "Config Loader Module"). Adds tests/config-loader.test.cjs
(27 tests: behavioral + shim-identity + adversarial config fixtures).
Gates: lint, code-review, security-review (prototype-pollution guard confirmed
intact), codex adversarial-review (0 findings; byte-identical move). Mac 4115
pass; clean-build docker: full-suite hit the local mirror's known incremental-tsc
non-determinism on an unrelated re-exported symbol (findPhaseInternal, from
already-merged 2d), but a clean targeted rebuild of the affected file passed
163/0 — CI's clean full matrix is the authoritative gate.
Closes#885
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Emit the 6 gsd-ns-* routers as the only top-level skill bundles and nest
the ~61 concrete skills under <router>/skills/<name>/SKILL.md on runtimes
with confirmed non-recursive skill loaders (claude global, cline, qwen,
hermes, augment, trae, antigravity). Router bodies rewrite their routing
tables from Skill-tool dispatch to a Read skills/<name>/SKILL.md pattern.
Recursive/unconfirmed loaders (cursor, codex, copilot, windsurf, codebuddy,
opencode, kilo) keep the flat layout. Completes the v1.40 namespace
architecture (#2792) so the eager skill listing drops to ~6 entries.
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
ADR-857 rollout phase 2c. Move 11 shared low-level utilities out of core.cts
into a new leaf module src/core-utils.cts: POSIX path normalization (toPosixPath),
filesystem scanning (detectSubRepos, readSubdirectories, getPhaseFileStats,
pathExistsInternal), and small pure helpers (generateSlugInternal,
extractOneLinerFromBody, filterPlanFiles, filterSummaryFiles, timeAgo, and the
private extractCanonicalPlanId). core.cts re-exports the 10 public ones
(callers unchanged); extractCanonicalPlanId stays private (exported from the
leaf for core's fs-search functions).
Cycle-free: core-utils depends only on Node built-ins + already-leafed modules
(phase-id for comparePhaseNum, planning-workspace for findContextMdIn). This is
the shared leaf that unblocks the phase-locator fs-search extraction (2d) —
searchPhaseInDir/findPhaseInternal/getArchivedPhaseDirs can now take their
utilities from a leaf instead of from core.
New-CLI-module checklist done (.gitignore, eslint, INVENTORY 93->94 + row,
manifest, ARCHITECTURE, CONTEXT.md "Core Utilities Module"). Adds
tests/core-utils.test.cjs (88 tests: behavioral + shim-identity + adversarial).
Gates: lint, code-review, security-review, codex adversarial-review (0
findings). Mac 4041 pass; clean-build docker 12935 pass, 0 fail.
Closes#877
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
ADR-857 rollout phase 2b. Move the 6 ROADMAP.md-parsing functions
(stripShippedMilestones, extractCurrentMilestone, replaceInCurrentMilestone,
getRoadmapPhaseInternal, getMilestoneInfo, getMilestonePhaseFilter) + their
interfaces out of core.cts into a new leaf module src/roadmap-parser.cts.
core.cts re-exports them (behavior-preserving); ~9 external callers unchanged.
Resolves the parse/write straddle: roadmap.cts (ROADMAP.md mutation) now imports
its 3 parsing helpers from roadmap-parser.cjs directly instead of reaching
through core. roadmap-parser depends only on leaves (phase-id, planning-workspace,
shell-command-projection) — cycle-free, enabled by phase 2a.
New-CLI-module checklist done (.gitignore, eslint, INVENTORY 92->93 + row,
manifest, ARCHITECTURE, CONTEXT.md "Roadmap Parser Module"). Adds
tests/roadmap-parser.test.cjs (46 tests: behavioral + shim-identity +
adversarial ROADMAP.md fixtures).
Adversarial review surfaced a pre-existing fence-blindness bug in
getMilestonePhaseFilter (matches phase headings inside fenced code blocks);
filed as #875 and left for a separate fix (out of scope for this
behavior-preserving extraction). The two fenced-fixture tests characterize the
current behavior with a #875 reference and flip when it's fixed.
Gates: lint, code-review, security-review, codex adversarial-review (0
correctness findings). gsd-test: clean-build docker + Mac green; the full-suite
docker run's "X is not a function" errors on re-exported symbols were local
incremental-tsc staleness (verified: clean rebuild of the affected files = 195
pass, 0 fail; Mac = 4001 pass).
Closes#870
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
extractCurrentMilestone reads STATE.md via planningDir(cwd), which is
workstream-aware (honours GSD_PROJECT/GSD_WORKSTREAM). The fixtures write
STATE.md to the plain <tmp>/.planning/STATE.md, so a developer shell inside a
GSD workstream (GSD_WORKSTREAM exported) redirected the read to a non-existent
workstream subdir -> version=null -> closed milestone sections leaked into the
slice and assertions failed. Clean CI/Docker env never hit it. Not a Node-26
regex bug; reproduces identically on any Node with GSD_WORKSTREAM set.
- scripts/run-tests.cjs: strip GSD_PROJECT/GSD_WORKSTREAM before spawning test
children so the local runner env matches clean CI/Docker.
- tests/roadmap-phase-fallback.test.cjs: file-level beforeEach/afterEach
save/delete/restore of both vars; new regression test pinning workstream-aware
STATE.md resolution.
- tests/run-tests-harness.test.cjs: guard asserting the runner strips both vars
(so removing the deletion fails clean CI).
Closes#872
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Add tests/issue-57-runtime-install-no-drift.test.cjs protecting the Runtime
Install Policy Module boundary (ADR-58) and the explicit Runtime Config Adapter
Registry (#60), now that #58/#60/#56 have landed and the seam exists.
The guards fail when:
- (AC1) supported-runtime metadata is added to an installer/query call site
(allRuntimes, the interactive runtimeMap menu) without a matching registry
adapter entry — enforced by three-way set equality across allRuntimes,
runtimeMap values, and ALLOWED_CONFIG_RUNTIMES.
- (AC2) config-mutation dispatch escapes the registry: every intent uses a
registry-declared install surface, every permission writer is null or a
registry-known runtime, unknown/prototype-key runtimes fail loudly, and a new
inline 'runtime === "..."' branch against an unregistered runtime is rejected.
Assertions are behavioral (require + reflect on live exports) where behavior can
cover the contract (AC3); two annotated structural guards cover what it cannot.
Existing installer/runtime-policy/runtime-global-skills suites stay green (AC4).
Gates: eslint, lint-test-file-count, full Mac suite (12715 pass / 0 fail) and
Linux Docker (14709 pass / 0 fail) all green; Codex adversarial-review,
/code-review, and /security-review run with findings addressed.
Closes#57
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
ADR-857 rollout phase 2a — the first cut of the core.cts decomposition.
Move the 9 pure phase-id parsing/matching helpers (escapeRegex,
normalizePhaseName, comparePhaseNum, extractPhaseToken, phaseTokenMatches,
phaseMarkdownRegexSource/Exact, getMilestoneFromPhaseId, getPhaseDirFromPhaseId)
out of core.cts into a new leaf module src/phase-id.cts. core.cts re-exports
them (behavior-preserving); its internal callers resolve the destructured
bindings.
Cycle-safe by design: phase-id depends on nothing in core, so re-export creates
no circular require (the property that made phase-1 io.cts clean). This is the
leaf-first ordering — it unblocks the roadmap-parser extraction (2b), which
imports phaseMarkdownRegexSource.
New-CLI-module checklist: .gitignore, eslint.config.mjs ignores, INVENTORY.md
count 91->92 + row, INVENTORY-MANIFEST.json, ARCHITECTURE.md row, CONTEXT.md
"Phase Id Module" glossary entry. Adds tests/phase-id.test.cjs (63 behavioral
tests incl. shim-identity + adversarial inputs).
Gates: lint, code-review, security-review, codex adversarial-review (all 0
findings), and gsd-test-both (14814 pass on Mac + Linux Docker, 0 fail).
Closes#865
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#853): gate manager/autonomous bg dispatch by runtime
/gsd-manager and /gsd-autonomous --interactive dispatched Plan/Execute
via Agent(run_in_background=true). On Claude Code a backgrounded agent
has no Agent/Task tool, so it cannot spawn the nested subagents those
pipelines need — per-plan worktree-isolated executors, the plan-checker,
and the verifier. The phases reported complete but isolation and
independent verification silently never ran, even with use_worktrees /
plan_check / verifier enabled.
Both workflows now resolve the runtime (config-get runtime, default
claude) before dispatching: run plan/execute INLINE on Claude Code so
the nested pipeline runs, and background-dispatch only on runtimes where
a backgrounded agent can still nest. Mirrors execute-phase.md's existing
Codex fail-closed precedent. Reconciles the stale unconditional
background/overlap/lean-context claims elsewhere in both workflows and
in the docs. Adds a content regression test pinning the gate.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* docs(#853): add changeset for runtime-gated bg dispatch
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#856): remove gsd-cmd-rewrites temp dirs after install
applyRuntimeContentRewritesForCommandsInPlace() returns a fresh
mkdtemp dir under os.tmpdir() (gsd-cmd-rewrites-*) with rewritten
command markdown. installRuntimeArtifacts() copied from it but never
removed it, leaking one temp dir per commands kind per install — on
tmpfs /tmp hosts these accumulate and consume RAM-backed storage.
Wrap the per-kind copy in try/finally and rmSync the temp dir (only
when it differs from the staged source, i.e. the commands kind) once
the copy completes or fails. dest creation moved inside the try so a
mkdir failure still triggers cleanup.
Regression test isolates os.tmpdir() to a private TMPDIR root and
asserts no gsd-cmd-rewrites-* dir survives the install.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* docs(#856): add changeset for installer temp-dir cleanup
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
ADR-857 rollout phase 1. Move the CLI I/O primitives — output(), error(),
ERROR_REASON, setJsonErrorMode/getJsonErrorMode, and the output() large-payload
temp-file spillover helpers (GSD_TEMP_DIR, ensureGsdTempDir, reapStaleTempFiles)
— out of the 2271-line core.cts god-module into a new, small src/io.cts. core.cts
re-exports them so existing consumers are unaffected (behavior-preserving).
Repoint src/profile-pipeline.cts to import output/error/reapStaleTempFiles from
io directly; graphify/intel/audit were verified not to import these symbols. Net:
the leaf feature modules no longer depend on core just for I/O — the enabling
first cut toward Capability extraction.
New-CLI-module checklist: .gitignore (bin/lib/io.cjs), eslint.config.mjs ignores,
INVENTORY.md count 90→91 + io.cjs row, INVENTORY-MANIFEST.json, ARCHITECTURE.md
core.cjs/io.cjs rows, CONTEXT.md "I/O Module" glossary entry. Adds tests/io.test.cjs
(28 behavioral tests incl. shim-identity and the @file: spillover branch).
Gates: lint, code-review, security-review, codex adversarial-review, and
gsd-test-both (14742 pass on Mac + Linux Docker, 0 fail) all green.
Closes#859
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#834): derive installer --help skill counts from PROFILES
The installer --help text undercounted profile skill counts: it claimed
"core — 7 main-loop skills" and "standard — ~13 skills" when the real
counts in PROFILES (bin/lib/install-profiles.cjs) are 8 and 14. The
`surface` skill was added to core after the help string was written, and
standard was never updated.
Derive the core and standard counts from PROFILES.core.length and
PROFILES.standard.length so the help text cannot drift again. Replace the
stale hardcoded "all 66 skills" (actually 67) on the full line with
drift-proof "all skills" — full is the '*' sentinel with no array length
and no cheap authoritative total in the help path.
Add regression tests that run `node bin/install.js --help` and assert the
printed core/standard counts equal the PROFILES lengths, plus a guard
that the full line carries no hardcoded numeric count.
Closes#834
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore(#834): add changeset for installer --help count fix
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
The PR Gate workflow's only job, size-check, labeled every PR with
size/S–size/XL based on lines changed. Those labels aren't used in any
review, triage, or automation flow, so the workflow was pure noise.
- Delete .github/workflows/pr-gate.yml
- Drop size-check from required status checks in both rulesets so PRs
don't block forever on a check that never reports
- Remove pr-gate.yml from INERT_WORKFLOWS (ci-test-scope.cjs) and the
knownInert list (ci-test-scope.test.cjs)
- Remove "PR Gate / size-check" from setup-branch-protection.sh
Closes#846
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#844): sync runtime manifest versions on npm version bump
The release workflow bumps package.json via `npm version` but never
stamped the runtime-integration manifests that must track it
(.claude-plugin/plugin.json #766, gemini-extension.json #775), so the
first RC/finalize whose version diverged from the -dev stream failed the
test suite before tagging/publishing.
Add scripts/sync-manifest-versions.cjs (single VERSIONED_MANIFESTS
registry) wired to a `version` npm lifecycle hook that stamps + stages
the manifests on every `npm version` — covering all four release bump
sites and local bumps with no workflow edits. A regression guard test
fails if any repo JSON whose version matches package.json is not
registered, forcing future version-bearing manifests into the sync.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* docs(#844): add changeset for manifest version sync fix
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* feat(#770): register Claude Code lifecycle hooks (SubagentStop/Stop/PreCompact/FileChanged)
Wire three new context-tracking events (SubagentStop, Stop, PreCompact) to
gsd-context-monitor so context-headroom warnings surface at model-stop and
subagent-finalisation moments — not just on PostToolUse. Add a new
FileChanged hook (gsd-config-reload.js) that hot-reloads .planning/config.json
context mid-session when the user edits it, injecting a config summary as
hookSpecificOutput.additionalContext. Updates plugin manifest hooks.json,
managed-hooks-registry, installer-migration-report allowlist, and
shell-command-projection cleanup tables. Tests: 21 new assertions in
enh-770-claude-hook-events.test.cjs; enh-788 and issue-766 test suites updated.
Closes#770
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* docs(#770): document newly-registered Claude Code lifecycle hooks
Add a Hook coverage table to the Claude Code npm installer section of
docs/how-to/install-on-your-runtime.md describing SubagentStop, Stop,
PreCompact, and the new FileChanged (gsd-config-reload.js) hook that
hot-reloads .planning/config.json mid-session. Also fixes the changeset
frontmatter (adds type: Added + pr: 821) so docs-lint can consume the
fragment.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#770): add gsd-config-reload.js to INVENTORY.md and regenerate manifest
The feat commit added hooks/gsd-config-reload.js but did not bump the
Hooks count in docs/INVENTORY.md (14→15) or add the new row, and did not
regenerate docs/INVENTORY-MANIFEST.json. Both inventory-counts and
inventory-manifest-sync tests failed across the full CI matrix.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#770): make lifecycle-hook tests deterministic on scoped runner
Replace the shared hooks/dist/ ensemble setup (ensureHooksDist /
teardownHooksDist) in the Claude hook tests with per-test isolation:
pre-populate each test's own tmpDir/.claude/hooks/ with stub files and
pass installerMigrations:[] to install() so the first-time-baseline
migration does not remove the stubs before the copy step can run.
Root cause: hooks/dist/ is gitignored and absent on a fresh npm ci.
ensureHooksDist() created it and teardownHooksDist() deleted it, but
with --test-concurrency=4 both test files ran concurrently as separate
Node.js worker processes sharing the same filesystem. One file's
afterEach teardown deleted hooks/dist/ while the other file's install()
was copying from it, producing an ENOENT (reproduced 2/10 runs locally).
The additional issue: even with pre-placed stubs surviving the copy race,
the 000-first-time-baseline migration classified hooks/gsd-*.js as
bundled-gsd-hook artifacts, auto-removed them, and the copy step never
re-ran (hooks/dist/ absent) — leaving contextMonitorFile missing and all
hook registrations silently skipped (the 'got: []' symptom).
Fix: pre-populate targetDir/hooks/ per-test (isolated temp dir) AND pass
installerMigrations:[] so the baseline scan is skipped. The Qwen suites
already used this pattern correctly; the Claude suites are aligned to it.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#770): ship gsd-config-reload.js by adding it to build-hooks HOOKS_TO_COPY
The #770 feature added hooks/gsd-config-reload.js and registered it in
MANAGED_HOOKS, the installer, INVENTORY, and the test EXPECTED_ALL_HOOKS
list — but never added it to scripts/build-hooks.js HOOKS_TO_COPY. As a
result the hook was never copied into hooks/dist/ during the build, so:
- the hook would never ship to users (real production bug — the
FileChanged config-reload feature was dead-on-arrival), and
- install-minimal-hooks.test.cjs #1755 ("all expected hooks are copied
from hooks/dist/ to target", ".js hooks are executable after copy",
"manifest contains .js hook entries") failed on any environment with
a clean checkout (no pre-existing hooks/dist/): coverage, full test
macos-22/macos-24, test ubuntu-24.
The failures were masked locally only by a stale hooks/dist/ left from a
prior build (build-hooks copies into dist without clearing it). On CI's
fresh `npm ci` there is no dist, so the omission surfaced.
Fix: add 'gsd-config-reload.js' to HOOKS_TO_COPY so build-hooks stages it
into hooks/dist/ alongside the other JS hooks. Verified by removing
hooks/dist/ and rerunning the full suite green (0 fail).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#770): make config prototype-pollution beforeEach deterministic on scoped runner
Root cause: the #663 and alert-#26 prototype-pollution describe blocks
seeded .planning/config.json in beforeEach via a bare
runGsdTools('config-ensure-section') whose result was discarded. That
command runs in a spawned gsd-tools child; on the scoped CI lane
(--test-concurrency=4, config.test.cjs scheduled alongside the heavy
install/tarball suites that #770 pulled into the targeted set) the child
can be transiently killed under resource pressure (non-zero exit, empty
stderr — an OS-level kill, not an app error). The swallowed failure left
config.json absent, so the first subtest's readConfig() threw ENOENT
opening <tmp>/.planning/config.json. Only 1 of 4 subtests failed,
confirming a per-invocation transient, not a deterministic miss; the full
suite schedules files differently so config.test.cjs did not collide with
those heavy neighbors → passed there.
Fix: add ensureConfigReady(tmpDir) which retries config-ensure-section on
ANY failure or missing file and throws a clear diagnostic if it still
cannot create config.json, then use it in both prototype-pollution
beforeEach blocks. Setup is now deterministic under load; the #663/alert-#26
security assertions are unchanged.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* feat(#836): no-LLM duplicate-issue detection + challenge + 1-day auto-close
Adds a deterministic (no-LLM) duplicate-issue governance lifecycle:
- scripts/issue-dedupe.cjs: pure, unit-tested module (tokenize, Sørensen–Dice
title similarity, scoreCandidates, renderChallengeComment, shouldClose) with
fail-safe destructive-action guards.
- duplicate-check.yml (issues:opened): scores new-issue title against open
issues, posts a challenge comment + applies the pending `possible-duplicate`
label on a clear match.
- duplicate-sweep.yml (daily cron): closes possible-duplicate issues whose
challenge comment is >24h old with no human reply and no 👎 veto; honors
exempt labels; re-checks the label immediately before close (TOCTOU guard);
strips the label on close to avoid reopen loops.
- remove-duplicate-label.yml (issue_comment:created): clears the label and
applies needs-maintainer-review when any human responds.
- bug_report.yml / docs_issue.yml: add the required "I searched existing
issues" preflight checkbox so all five forms force a pre-search attestation.
- docs/agents/triage-labels.md: document the label + lifecycle.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore(#836): add changeset fragment for duplicate-issue detection
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
CI test-scope detection diffed changed files with a two-dot
`git diff --name-only base head`, where base is the moving tip of `next`.
A PR branch cut from a slightly older `next` surfaced every product file
`next` had gained since the merge-base, flipping product_changed/full_matrix
and running the full Windows/macOS matrix + coverage on docs-only PRs.
Switch to a three-dot `git diff --name-only base...head` (vs the merge-base),
matching GitHub's PR "Files changed" semantics. Add a regression test that
builds a stale-base topology, plus a guard test pinning `fetch-depth: 0` on
the `changes` job (required for the merge-base to be locally available).
Closes#837
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Adds an opt-in --next (alias --rc) flag to /gsd-update targeting the @next RC dist-tag (ADR #660), with a {latest,next} allowlist enforced at three layers, channel-aware version check + banner, and byte-for-byte unchanged default @latest behavior.
Closes#815
* feat(#777): register Cursor-native hooks (.cursor/hooks.json) for session-start/post-tool parity
- Add gsd-cursor-session-start.js: injects STATE.md presence reminder (or
new-project nudge) into Cursor sessions via the sessionStart hook event
- Add gsd-cursor-post-tool.js: emits an additional_context nudge when
write-class tool calls touch .planning/ files (postToolUse hook event)
- Add 'cursor-hooks-json' installSurface to runtime-config-adapter-registry;
writeCursorHooksJson/reconcileCursorHooksJson write the canonical
{ version: 1, hooks: { sessionStart, postToolUse } } JSON shape with
idempotent reconciliation that preserves user-owned hook entries
- Hook scripts are copied with /gsd:→gsd- rewrite so installed files
contain no colon-form slash-command refs (bug-376 invariant)
- 20 new tests in tests/cursor-hooks.test.cjs cover all reconciler paths,
entry helpers, removal, runtime adapter surface, and hook script behavior
- Update CONTEXT.md, ARCHITECTURE.md, installer-migrations.md, and
000-first-time-baseline.cts to include Cursor hooks.json surface
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#777): build hooks/dist on demand in bug-376 test for scoped/windows CI
hooks/dist is gitignored and only produced by `npm run build:hooks`.
The CI scoped (ubuntu-latest/node-22) and windows (windows-latest/node-24)
test jobs do NOT run build:hooks before executing tests, so bug-376's
prerequisite suite was failing with "hooks/dist not found" on both legs.
Add ensureHooksDist() helper (mirrors bug-3357 pattern) that builds
hooks/dist on demand in the before() hooks of prerequisite and Suite 3.
Also add ensureHooksDist() call to Suite 3's before() so the snapshot
step is also hermetic.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
