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>
`loadConfig` in configuration.cts was superseded by config-loader.cts
(ADR-857 phase 2e, #885). Exhaustive grep confirms no caller imports
loadConfig from configuration.cjs — all live callers use config-loader.cjs
or the core.cjs back-compat re-export. configuration.cts now provides only
the pure normalization and defaults primitives (normalizeLegacyKeys,
mergeDefaults, migrateOnDisk, CONFIG_DEFAULTS) that config-loader.cts
depends on. Updated CONTEXT.md and docs/INVENTORY.md to reflect the
narrowed module surface.
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>
* docs(#894): ADR-894 Capability declaration format + registry generation
ADR-857 rollout phase 3a (design-only). Resolve ADR-857's deferred open
question — the on-disk Capability declaration format — as a reviewable design
ADR before any generator code.
Specifies: the capabilities/<id>/capability.json folder layout (migration-staged
ownership — declarations reference existing stems until the phase-6 move); the
capability.json schema for role:feature (skills/agents/hooks/federated config/
loopHooks) and role:runtime (the six closed projection-primitive axes); the 12
named Loop Extension Points; the gen-capability-registry.cjs generator design
(validation + cross-capability invariants + --write/--check drift gate, mirroring
gen-inventory-manifest); the generated capability-registry.cjs shape (by-id /
by-skill / by-loop-point indexes + requires-closure); and a full worked example
(the UI capability: ui-phase + ui-review + agents + config + two loop hooks).
No code — design artifact only; the generator build, federated config loader
(3b), and loop seam (3c) implement against this contract.
Closes#894
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* docs(#894): amend ADR-894 with grilled capability declaration format
Stress-tested the declaration format before merge; the format changed
materially. Amendments:
- loopHooks[] -> three typed arrays (steps/contributions/gates), each with its
own shape (step: ref+produces/consumes; contribution: fragment+into agent-role;
gate: check+blocking).
- Add the Loop Host Contract (§3): each step publishes its points, agent roles,
and core artifacts so the generator validates hooks against reality, not
trusted strings.
- requires = capability ids only (host implicit); add tier-monotone invariant;
drop the requires:["plan"] error from the example.
- Config federation = atomic move: a migrated key leaves the central schema in
the same PR; presence in both is a collision (invariant stays).
- One registry, role-partitioned indexes (feature indexes vs runtimes index).
- Rework the UI worked example to the split-array shape (2 steps + 1 gate) +
a contribution illustration.
Adds a "Grilling amendments" section recording the six changes.
* docs(#894): amend ADR-894 with round-2 grilling (operational reality)
Second design-grill round, folded in before merge:
- Loop Host Contract is GENERATED from structured workflow markers
(<loop-point>/<agent-role>/<loop-artifact>) via gen-loop-host-contract.cjs —
it can't drift from the real workflows.
- Hook activation `when`: cheap deterministic config-level gating evaluated by
loop.render-hooks; deeper phase-context applicability self-gates inside the
dispatched skill (no phase-context vocabulary to keep honest).
- `tier` is the source of install-profile + cluster membership; profiles and
clusters are generated from tier + requires-closure (/gsd:surface operates on
capabilities) — collapses ADR-857's multiple toggle systems.
- Gate `check` = query | declarative-predicate | agentVerdict; agentVerdict is
forced advisory; only deterministic checks may block.
- byLoopPoint ordering is materialized in the registry; render-hooks filters the
active set + renders. Same-capability hooks degrade gracefully when an entry
step self-gates.
- Rollout: registry-only until atomic per-feature cutover (no double-execution
with still-inlined workflow features).
Updates the Grilling amendments / Consequences / Alternatives / Open questions
sections; reworks the UI example with `when`.
---------
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>
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>
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>
Record the final-state architecture: the five-step loop (Discuss → Plan →
Execute → Verify → Ship) plus shared-infrastructure skills are the privileged
host/core; every other feature is a Capability (plug-in) selectable at install
and toggleable after restart, attaching through ~12 Loop Extension Points.
Adds docs/adr/857-capability-system.md (Status: Proposed) capturing the eight
resolved design decisions, the resolved design details (extension points,
contribution merge, declaration shape, runtime descriptor, deferred trust gate),
alternatives, consequences, and a six-phase rollout. Records the new domain
terms in CONTEXT.md: Capability, Capability Registry, Loop Extension Point,
Runtime Capability.
Runtime/CLI support is itself a Capability (role: runtime) — Claude Code, Codex,
Antigravity tier-1; the seam is declarative-over-primitives so third-party CLI
support lands later as an additive loader, no rework.
Closes#857
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Diataxis review of the 1.4.0 content (52 changesets, multi-runtime maturation
plus native packaging and new flags) against the existing docs base found most
per-feature docs already landed with their PRs. Fill the four remaining gaps,
each in its Diataxis quadrant:
- Reference: FEATURES.md Feature #36 (Multi-Runtime Support) updated in place
with 1.4.0 additions — native skills emission (Cline/Kilo/OpenCode), new
slash-command surfaces (CodeBuddy/Augment/Cursor), cross-runtime lifecycle
hooks for context-headroom tracking, and the Gemini CLI extension package.
- Reference: CONFIGURATION.md gains a dedicated worktree.baseRef entry (values,
.claude/settings.local.json location, auto-set-on-install behaviour).
- How-to: plan-a-phase.md gains an 'override planning granularity for one phase'
section for the --granularity flag.
- Explanation: context-engineering.md gains a 'Lifecycle hooks and context
headroom' section (the why of lifecycle hooks + forked context), cross-linked
from multi-agent-orchestration.md.
Docs-only; documents already-shipped features, so no changeset required
(docs/ is not in the changeset-lint user-facing prefixes).
Closes#849
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>
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
Add docs/how-to/install-minimal-and-add-skills.md covering the --minimal
/ --core-only / --profile=core install, the core/standard/full profiles,
and growing the surface live via /gsd:surface or on reinstall. Register
it in the docs/README.md How-to guides index.
Closes#832
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* 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>
* feat(#776): Gemini hook events (BeforeAgent/AfterAgent/BeforeModel) + hooksConfig.enabled check
Register three new Gemini-CLI hook events on install:
- BeforeAgent: fires before agent planning; wired to gsd-context-monitor
- AfterAgent: fires after final response generation; wired to gsd-context-monitor
- BeforeModel: fires before each LLM call (per-turn); wired to gsd-context-monitor
All three reuse gsd-context-monitor.js (no new hook files). Uninstall cleanup
loop extended to remove the new events. Non-array guard added for robustness
against malformed settings.
Also detect hooksConfig.enabled:false in Gemini settings and emit a clear
warning — without this check, all registered hooks silently do nothing.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore: update changeset pr: 829
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* docs(#776): document Gemini hook events
Add hook coverage table to the Gemini CLI section of install-on-your-runtime.md,
covering the three new events (BeforeAgent/AfterAgent/BeforeModel wired to
gsd-context-monitor) plus a callout for the hooksConfig.enabled:false silent
failure mode detected by the installer.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* feat(#789): elevate CodeBuddy — emit slash commands (+ document subagent/MCP scope)
Emit a CodeBuddy slash-command surface so GSD workflows appear in the
'/' menu, reaching parity with other elevated runtimes.
- Add convertClaudeCommandToCodebuddyCommand and register a commands/
artifact kind for the codebuddy runtime (commands/gsd-<name>.md),
consistent with the Cursor (#785) and Augment (#790) commands surfaces.
- Mark emitted skills user-invocable:false so the commands surface is the
sole '/' entry point (no duplicate /gsd-* entries); skills stay
model-invocable. CodeBuddy's SKILL.md supports this field.
- Normalize $HOME/.codebuddy (bare + slash) path forms in runtime
rewrites so --config-dir/local installs don't leak the default home.
- Report installed commands/ count on install; uninstall prunes gsd-*
commands while preserving user-owned commands.
Scope: subagents (~/.codebuddy/agents/) are already emitted by the
generic agents block (unchanged); no mcp.json is written (gsd ships no
MCP server, and CodeBuddy's mcp.json registers only external servers).
Closes#789
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore(#789): set changeset pr number to 830
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* feat(#778): cross-runtime command enrichment (Gemini {{args}}/!{}, Qwen priority)
Enrich the installer's per-runtime command/skill generators with native,
verified, additive fields:
- Gemini CLI: map Claude's $ARGUMENTS -> Gemini's {{args}} in generated TOML
commands so typed arguments interpolate; inject live .planning/STATE.md into
/gsd:progress via a fixed, injection-safe !{cat .planning/STATE.md 2>/dev/null}
shell block (no interpolated input).
- Qwen Code: emit the optional numeric `priority` field on main-loop skills so
the most-used workflows sort first in the /skills list (higher = earlier per
the Qwen skills spec; the issue's inverse numbering was corrected).
OpenCode per-command model/agent/subtask/variant enrichment was evaluated and
intentionally not implemented: `model` reintroduces the #1156
ProviderModelNotFoundError regression for non-Anthropic providers (the converter
deliberately strips model:), `subtask`/`agent` change execution semantics for
GSD's interactive commands, and `variant` is not in the OpenCode command schema.
Schemas verified against primary docs (Gemini custom-commands, Qwen skills,
OpenCode commands/skills). Adds tests/enh-778-* and how-to + USER-GUIDE docs.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore(#778): set changeset PR number to 825
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* feat(#772): adopt stable Codex hook events + commandWindows for Windows parity
Register three new stable Codex hook events (SubagentStart, Stop,
PostToolUse) wired to gsd-context-monitor.js so Codex installs get
the same context-headroom tracking at subagent and session boundaries
that Claude/Qwen already have.
Add commandWindows field to the SessionStart hook entry on Windows so
Codex uses the .cmd shim directly (Git Bash/MSYS cannot POSIX-exec
node.exe). commandWindows is only emitted on win32; POSIX is unchanged.
Refactor reconcileCodexHooksJsonSessionStart into a generic
reconcileCodexHooksJsonEvent so any event name can be reconciled with
the same dedup/preserve-user-entries logic.
Add gsd-context-monitor.js and .cmd to MANAGED_HOOK_COMMAND_BASENAMES
_BY_SURFACE so idempotent re-runs de-duplicate entries correctly.
30 new tests covering: export surface, event registration for each of
the three events, commandWindows parity (POSIX vs win32), idempotency,
uninstall, and user-entry preservation.
Closes#772
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#772): windows path normalization + docs-lint
- Normalize scriptPath backslashes to forward slashes in
ensureCodexHooksJsonEvent and ensureCodexHooksJsonSessionStart so that
isManagedHookCommand can match stored commands against configDir on
Windows CI runners. path.resolve returns backslash paths on Windows,
but when platform is not 'win32' (e.g. platform:'linux' in tests),
projectManagedHookCommand skips normalization — producing a mismatch
that breaks idempotency deduplication (the same hook entry appended
twice on re-register). Forward-slash paths are always valid in both
Node.js and Codex, so the normalization is safe for all platforms.
- Fix changeset pr: 0 → 827 to resolve fail_malformed_fragment.
- Add Codex hook coverage table to docs/how-to/install-on-your-runtime.md
documenting the SubagentStart/Stop/PostToolUse events + commandWindows
Windows-parity field added by this enhancement.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* feat(#769): emit context:fork + effort: frontmatter on heavy workflow skills
Add `context: fork` and `effort: xhigh` to the three heaviest workflow
commands (plan-phase, execute-phase, autonomous) and `effort: low` to the
two quick-status commands (progress, stats).
On Claude Code, `context: fork` runs the skill in an isolated subagent
context window so the main session's context budget is protected.
`effort: xhigh` / `effort: low` signal the appropriate token-budget tier to
the runtime. Both fields are silently ignored by runtimes that do not
recognise them (Gemini, Codex, Cursor, etc.) — no behaviour change outside
Claude Code.
Update convertClaudeCommandToClaudeSkill in bin/install.js to preserve
`context:` and `effort:` when rewriting source command files to SKILL.md for
a Claude global install. Add install-suite tests to assert the fields are
present in both source commands and the installed SKILL.md output.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* test(#769): tighten regex assertions + add execute/plan-phase effort coverage
Fix low-severity adversarial finding: tighten test regex patterns from
`\s*` to `[ \t]*` so they cannot match across newlines (CRLF parity).
Add missing effort: xhigh assertions for gsd-execute-phase and gsd-plan-phase
SKILL.md install output to complete the black-box coverage gap.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* feat(#774): emit service_tier/model_verbosity in Codex agent TOML + agents/openai.yaml skill chip
- Add service_tier = "flex" and model_verbosity = "low" to the Codex
ConfigProfile TOML for light-tier agents (gsd-research-synthesizer,
gsd-codebase-mapper, gsd-plan-checker, and 8 others identified via
AGENT_DEFAULT_TIERS). Field names/values verified against Codex schema
(profile_toml.rs / config_types.rs Verbosity enum). Non-light agents
are unaffected.
- Add generateCodexSkillMetadataYaml() and writeCodexSkillMetadataFiles():
after installRuntimeArtifacts, iterate every gsd-* skill directory,
read the short-description already emitted in the SKILL.md frontmatter
by convertClaudeCommandToCodexSkill, and write agents/openai.yaml with
interface.display_name and interface.short_description for the Codex
TUI skill picker chip.
- yamlQuote (JSON.stringify) handles all YAML-unsafe chars.
- User-owned gsd-dev-preferences dir is never overwritten.
- Errors per-skill are swallowed so a bad SKILL.md can't abort install.
- agents/openai.yaml is covered by the snapshot/rollback system and
manifest hash (writeManifest hashes skill dirs recursively).
- Uninstall symmetry: _removeGsdEntries removes whole gsd-* dirs.
- 21 new tests in codex-config.test.cjs covering service_tier/verbosity
TOML emission, YAML generation (round-trip via js-yaml), and
writeCodexSkillMetadataFiles including an e2e integration test.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#774): correct docs-lint coverage — proper changeset format + USER-GUIDE entry
Rewrite the changeset fragment from old @opengsd/gsd-core:patch format to the
required type:/pr: schema so the docs-lint parser can consume it. Add a new
"Codex skill picker and agent scheduling (#774)" section to docs/USER-GUIDE.md
describing the flex-tier scheduling and /skills TUI chip enrichments — both are
user-visible and belong in docs rather than behind a docs-exempt marker.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* feat(#768): pre-populate settings.json permissions.allow/deny for Claude Code
Adds mergeClaudePermissions() to bin/install.js which non-destructively
appends GSD's known-safe tool-call patterns to permissions.allow and
defense-in-depth credential-file patterns to permissions.deny during
Claude Code installs. Merge is idempotent (no duplicates on reinstall)
and additive (existing user entries preserved). Uninstall removes only
the exact GSD-owned entries.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore: update changeset pr number to 819
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Add a Gemini CLI extension package so users can install, update, and
remove GSD through Gemini's own extension lifecycle and have it appear in
`gemini extensions list`:
gemini extensions install https://github.com/open-gsd/gsd-core
gemini extensions update gsd-core
gemini extensions uninstall gsd-core
gemini extensions link /path/to/gsd-core # dev
This mirrors the additive Claude Code plugin manifest (#766): a thin,
version-stamped manifest enforced by an in-repo drift test. The extension
ships the context-file payload (GEMINI.md), loaded into every Gemini
session; slash-command/agent/hook TOML projection into the extension is a
documented follow-up. The manual `npx gsd-core --gemini` installer (which
provides the /gsd:* commands) is unchanged — purely additive, no breaking
change.
- gemini-extension.json: name=binName, version tracks package.json,
description, contextFileName=GEMINI.md (minimal; no mcpServers — gsd
ships no MCP server)
- GEMINI.md: Gemini-session context payload
- package.json: add both artifacts to files[] so they publish
- CONTEXT.md: add "Gemini Extension Package" glossary entry
- docs: USER-GUIDE + install-on-your-runtime how-to
- tests/issue-775-gemini-extension.test.cjs: manifest validity, version
parity with package.json, contextFileName existence, files[] publication
Closes#775
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* chore(#771): convert agent color: hex/magenta values to documented named colors
Claude Code's sub-agent `color:` field documents only 8 named colors
(red, blue, green, yellow, purple, orange, pink, cyan). Twelve agent
files used hex values and two used the undocumented `magenta`; convert
each to the nearest documented named color so the intended per-agent
TUI color differentiation is spec-compliant.
- agents/*.md: 14 color values hex/magenta -> nearest named color
- scripts/research-profiles.cjs: update the 3 generated research-agent
profiles (source of truth) so gen-research-agents stays in sync
- docs/AGENTS.md: update documented colors; add missing Color rows for
gsd-nyquist-auditor, gsd-project-researcher, gsd-phase-researcher
- tests/agent-frontmatter.test.cjs: add regression guard asserting every
agent color: is in the documented named-color set
Closes#771
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore(#771): add changeset
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* feat(#784): emit native skills for OpenCode + Kilo runtimes
OpenCode and Kilo share a config schema and both discover on-demand
skills from skills/<name>/SKILL.md. The installer previously emitted
only flat commands (command/) and file-based agents (agents/) for these
runtimes. Add a shared OpenCode-family skill writer that stages each GSD
command as a spec-compliant SKILL.md (name matching the directory,
description 1-1024 chars), wired through the runtime artifact layout so
uninstall cleans skills/ automatically. Skills respect the active
install profile.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#784): correct skill body paths + preserve user dev-preferences
Address adversarial-review findings:
- Add opencode/kilo cases to _applyRuntimeRewrites so staged SKILL.md
bodies are re-pointed from the converter's hardcoded default config dir
to the actual install target (fixes --local / --config-dir installs;
commands/agents already did this by applying pathPrefix pre-conversion).
- Preserve user-owned skills/gsd-dev-preferences across reinstall in
installOpencodeFamilySkills (snapshot+restore around the gsd-* prune),
matching installRuntimeArtifacts.
- Export installOpencodeFamilySkills and add regression tests.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#784): guarantee command/skill body parity, fix kilo-alt double-rewrite
Follow-up adversarial-review found the post-conversion path rewrite could
double-rewrite custom Kilo dirs (kilo -> kilo-alt -> kilo-alt-alt) because
the kilo pathPrefix is a $HOME (non-absolute) superset of the hardcoded
default base. Restructure so OpenCode/Kilo skills mirror copyFlattenedCommands
exactly: stage raw commands, apply pathPrefix BEFORE conversion via a new
shared applyOpencodeFamilyPathPrefix() helper (now used by both the command
and skill writers), then convert. This guarantees byte-for-byte command/
skill body parity for global, --local, and --config-dir installs and removes
the prefix-overlap hazard. Drop the fragile _applyRuntimeRewrites opencode/
kilo case. Strengthen the path regression test.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* refactor(#784): derive opencode/kilo skills from the same staged command set
Pass the installer's _stageSkills() output directly to
installOpencodeFamilySkills instead of re-staging via the layout, so the
command/ and skills/ surfaces always cover the identical profile-resolved
set — including the --minimal/--core-only alias path, which stages
differently from a plain --profile=core. Verified: minimal install now
emits 8 commands and 8 skills.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore(#784): set changeset PR number to 810
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* test(#784): fully escape backslashes in test helper (CodeQL js/incomplete-string-escaping)
Replace the dot-only escape `replace(/[.]/g, '\\.')` with a complete
regex-escape pattern `replace(/[\\.*+?^${}()|[\]]/g, '\\$&')` so all
regex metacharacters (including backslash itself) in `defaultBase` are
safely escaped before interpolation into `new RegExp(...)`.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Cline added a global skills system (~/.cline/skills/<name>/SKILL.md) in
v3.48.0, but gsd treated Cline as rules-only and emitted zero skills
(getGlobalSkillsBase('cline')=null, empty artifact kinds). This makes gsd
emit skills for Cline at global scope, alongside the existing .clinerules.
- runtime-homes: getGlobalSkillsBase('cline') -> ~/.cline/skills (was null)
- runtime-artifact-layout: cline emits a skills kind for GLOBAL scope only
(local stays .clinerules-only), mirroring claude's scope dispatch
- install.js: convertClaudeCommandToClineSkill emits name+description-only
SKILL.md frontmatter (Cline/agentskills.io spec; no Claude-specific
allowed-tools/argument-hint/agent), hyphen-normalized + .cline/-rewritten
body; global cline routed through the skills path while .clinerules is
still written; _applyRuntimeRewrites cline case handles custom
CLINE_CONFIG_DIR; convertClaudeToCliineMarkdown also rewrites bare
~/.claude and CLAUDE_CONFIG_DIR
- docs: install-on-your-runtime.md documents Cline global skills vs local rules
- tests: converter (name+description-only), global emission, skills+.clinerules
coexistence, scope-aware layout, custom-dir paths, idempotency
Closes#782
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* feat(#788): expand Qwen Code hook-event coverage to 4 new events
Register SubagentStop, Stop, PreCompact (gsd-context-monitor.js) and
UserPromptSubmit (gsd-prompt-guard.js) in the Qwen Code installer.
Guard is isQwen-only — Claude Code and all other runtimes are unchanged.
Uninstall loop extended to include the 4 new event names.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(#788): reconcile to 3 Qwen-only events — defer UserPromptSubmit
gsd-prompt-guard exits unless tool_name is Write|Edit (PreToolUse
payload shape); UserPromptSubmit carries raw user-prompt text with no
tool_name field, so wiring it would be a silent no-op. Deferred to a
follow-on issue.
Artifacts made consistent:
- bin/install.js: drop UserPromptSubmit registration block; uninstall
loop drops UPS from event list
- .changeset/788-qwen-hook-events.md: corrected to 3 events + rationale
- docs/how-to/install-on-your-runtime.md: remove UPS row from hook table
- tests/enh-788-qwen-hook-events.test.cjs: assert UPS NOT registered;
fix idempotency suite to persist settings between installs; drop
UPS-specific assertions
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* chore(#788): update changeset PR number to #807
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* test(#788): prune stale install-bucket allowlist entry for enh-788 test
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(#812): honor COPILOT_HOME in Copilot global config-dir resolution
getGlobalConfigDir('copilot') resolved the global config directory using
only --config-dir > COPILOT_CONFIG_DIR > ~/.copilot, ignoring the
COPILOT_HOME env var. Per GitHub's Copilot CLI docs, COPILOT_HOME
overrides the default ~/.copilot location (and user-level hooks are read
from $COPILOT_HOME/hooks/), so a global --copilot install wrote all
artifacts (skills, agents, copilot-instructions.md, the gsd-session.json
hook) to ~/.copilot even when the user relocated their Copilot home,
making them undiscoverable by Copilot CLI.
Mirror the codex/CODEX_HOME branch: precedence is now
--config-dir > COPILOT_CONFIG_DIR > COPILOT_HOME > ~/.copilot. Uninstall
uses the same resolver, so it stays symmetric.
Also: document COPILOT_HOME in the installer --help notes, the
USER-GUIDE env-var table, and the installer-migrations Copilot row; and
clear COPILOT_HOME in the two default-path test suites so they stay
hermetic now that the resolver honors it.
Closes#812
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore(#812): add changeset for PR #814
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* feat(#787): elevate Cline — .clinerules/ dir form, PreToolUse hook, AGENTS.md
Migrate the installer's Cline output from a single-file .clinerules to the
.clinerules/ directory form (.clinerules/gsd.md), which is the prerequisite for
Cline's v3.36 hooks (a path cannot be both a file and a directory). Add a
.clinerules/hooks/PreToolUse lifecycle hook implementing Cline's JSON stdin ->
{cancel,errorMessage,contextModification} protocol; it guards .planning/
artifacts and fails open. On global installs, merge GSD instructions into the
cross-tool ~/.agents/AGENTS.md target (marker-delimited, merge-safe). A legacy
single-file .clinerules is migrated in place; --uninstall removes the new
artifacts and strips the AGENTS.md GSD block.
Also fixes the uninstall targetDir for Cline local installs (it pointed at
./.cline instead of the project root) and re-runs writeManifest after the
Cline artifacts are written so they are hash-tracked.
Self-contained: implemented independently of the #782 Cline skills work.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#787): address review findings
- Scope PreToolUse hook path-walk to PATH_KEY fields only (eliminates false
positive when doc body content mentions .planning/)
- Use lstatSync + isSymbolicLink() for migration guard so GSD never writes
through a user's symlinked .clinerules into an external directory
- Add regression tests for both cases
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* chore(#787): set changeset pr: 803
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* feat(#785): write .cursor/commands/ as Cursor 1.6 slash-command surface
Cursor 1.6 (released 2025-09-12) introduced plain-markdown slash commands
in `.cursor/commands/<name>.md` — no frontmatter, invocable via `/` in the
Agent input. GSD previously emitted only `~/.cursor/skills/` for Cursor.
This PR wires a second artifact kind for `cursor` in
`runtime-artifact-layout.cts`: `convertedCommandsKind('commands', 'gsd-',
'convertClaudeCommandToCursorCommand', configDir)`. The new kind applies the
same `convertClaudeToCursorMarkdown` transforms (tool renames, brand
substitution, slash-command normalisation) and then strips YAML frontmatter
so the output is plain prose. Skills output is unchanged.
`stageCommandsForRuntimeFlat` in `install-profiles.cts` stages each source
`.md` as a flat `<stem>.md` in a temp dir; the existing `_copyStaged` commands
path then prefixes and copies to `<configDir>/commands/`.
`.cursor/mcp.json` is explicitly OUT OF SCOPE: GSD ships no MCP server; the
`mcpServers` schema cannot be usefully populated by the installer.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* refactor(#785): address review nit
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat(#786): elevate Copilot installer with lifecycle hook + AGENTS.md
Emit a self-contained sessionStart hook config (.github/hooks/gsd-session.json
local, ~/.copilot/hooks/gsd-session.json global) and write AGENTS.md at the repo
root (Copilot CLI reads it as primary instructions) alongside
copilot-instructions.md. The hook is an inline `command` hook (no separate hook
script), so it cannot dangle. Uninstall removes both and preserves user content.
Verified against GitHub Copilot CLI primary docs: hooks-configuration (camelCase
events, version+hooks shape, inline bash/powershell command hooks) and
add-custom-instructions (AGENTS.md read at repo root as primary instructions).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore(#786): set changeset pr number to 804
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* feat(#766): distribute gsd-core as a native Claude Code plugin
Add an additive .claude-plugin/plugin.json manifest plus hooks/hooks.json so gsd-core can be installed as a first-class Claude Code plugin (marketplace or zero-friction @skills-dir), with /gsd-core: namespaced commands and lifecycle management — alongside the unchanged npm/file-copy installer.
- .claude-plugin/plugin.json: validated with 'claude plugin validate --strict'
- hooks/hooks.json: mirrors the installer's always-on Claude hook wiring via ${CLAUDE_PLUGIN_ROOT}
- package.json: ship .claude-plugin in the npm tarball
- tests/issue-766-plugin-manifest.test.cjs: manifest + always-on-hook-contract drift guards
- docs: install-on-your-runtime.md + FEATURES.md
Closes#766
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* docs(#766): add ADR-766 + glossary entry for Claude Code Plugin Manifest Module
Record the plugin manifest as the Seam projecting gsd-core's artifact surfaces onto the Claude Code plugin contract (sibling of the Runtime Artifact Layout Module, ADR-3660), with the defined kind->field mapping and the always-on hook projection rule.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* refactor(#60): make runtime config adapter registry explicit
Replace scattered inline `runtime === '...'` config-mutation branching in
bin/install.js with an explicit, typed adapter registry. The new
src/runtime-config-adapter-registry.cts maps each of the 15 supported
runtimes to a config intent { installSurface, writesSharedSettings,
finishPermissionWriter }; install()/finishInstall() dispatch by resolved
intent instead of runtime-name checks (cursor/windsurf/trae collapse to one
profile-marker-only branch).
Behavior-preserving: the same config files are written for the same runtimes
(opencode still writes both settings.json and its permissions; kilo writes
only its permissions; codex minimal-mode and opencode GSD_TEST_MODE guards
unchanged). Unknown runtimes fail loudly via TypeError, with an Object.hasOwn
barrier so prototype-chain keys (__proto__/constructor) also throw rather than
returning a bogus intent. Leads the installer-refactor chain (#58 -> #60 ->
#56), building on ADR-58.
Closes#60
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore(#60): add changeset for runtime config adapter registry
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* docs(#60): register Runtime Config Adapter Registry in CONTEXT.md glossary
Per docs/contributor-standards.md, every new Module/seam must get a
`### <Name>` entry under the domain glossary. Adds the entry for the
runtime-config-adapter-registry seam introduced in this PR (interface,
policy boundary, source file, ADR-58 / #60 cross-references).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
The rc action publishes a release candidate to @next for testing but
never surfaces the curated CHANGELOG section for the version under test —
render only runs destructively at finalize (#715), so there was no safe
way to preview the upcoming notes during the RC window.
Add a --preview mode to scripts/changeset/cli.cjs cmdRender: it renders
the dated release section to stdout via the existing renderChangelog/
serializeChangelog path (with priorChangelog: null, so only the new
section is emitted), reuses the shared injectEmptyPlaceholder helper for
zero-fragment releases, and returns WITHOUT writing CHANGELOG.md or
deleting any .changeset fragment. Wire a "Preview CHANGELOG" step into
the rc job that renders to a file (standalone command, so a malformed
fragment fails the step) and cats it to the job summary and log.
Closes#759
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Record the Runtime Install Policy Module decision and ownership
boundary: install policy projects a pure, typed install plan by
composing artifact placements (ADR-3660) and command text (ADR-0009)
plus per-runtime config intentions, with no filesystem IO; runtime
adapters consume the plan and execute concrete file mutations and
format-specific config rendering. Explicitly records what stays
outside the policy module (TOML/JSON/Markdown serialization, merge
semantics, filesystem effects).
Adds the ADR index row in docs/adr/README.md and a glossary entry in
CONTEXT.md. Leads the installer-refactor chain (#58 -> #60 -> #56).
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* refactor(#651): consolidate verification-status routing into one queryable seam
The passed/gaps_found/human_needed verification status was re-encoded as
bare strings across three prose surfaces (gsd-verifier emits, execute-phase
routes, ship gates), each independently deciding the per-status next action
with no parity coupling — the DEFECT.GENERATIVE-FIX class.
Give the enum one home: src/verification.cts (-> bin/lib/verification.cjs)
exposing `gsd_run query verification.status <phaseDir>` returning a typed
{status, next_action, next_command}. ship.md and execute-phase.md now consume
the query instead of re-deriving the routing in prose; gsd-verifier.md points
at the shared vocabulary as the single emitter (values unchanged).
Also fixes the latent broad-grep status misread (DEFECT.FRONTMATTER-SCALAR-
BROAD-GREP): execute-phase.md read `grep "^status:"` over the whole report, so
a body `status:` line could misroute a valid phase. Extraction is now
frontmatter-scoped in one place. A parity test fails if a verifier status
gains no route. Lands the two CONTEXT.md DEFECT entries captured on the issue.
Closes#651
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore(#651): set changeset pr to 755
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* feat(#52): add agent_skills_security.trusted_global_roots allowlist
Opt-in allowlist so a global: agent skill whose SKILL.md realpath resolves
outside the default global skills base (e.g. ~/.claude/skills) is accepted
when its real target lies under a user-declared trusted root. Default [] is
byte-identical to prior behavior; the symlink-escape guard is preserved and
simply re-applied against each declared root.
- src/security.cts: loadTrustedGlobalRoots — tilde-expand (~ and ~/), reject
project-relative and dangerously broad roots (filesystem/UNC root, homedir),
realpath-canonicalize each root every run and drop non-existent ones.
- src/init.cts: on base-check failure the guard consults the trusted roots
(hoisted out of the loop); emits a stderr NOTE when a skill is accepted via
a trusted root so the widened boundary is visible.
- src/core.cts: thread agent_skills_security through loadConfig.
- config-schema.manifest.json: allow the new key path.
- docs/CONFIGURATION.md: document the option and its security model.
- tests/agent-skills.test.cjs: unit + end-to-end CLI coverage (regression,
feature, negative, broad-root hardening, stderr NOTE).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* docs(#52): add changeset fragment for trusted_global_roots (#754)
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* feat(#25): scope gsd-verifier Step 7b to enumerate-or-single-test; forbid full-suite re-runs
Step 7b's lone test example (`npm test -- --grep "$PHASE_TEST_PATTERN"`) is
mocha/vitest/jest-specific, where `--grep` filters which tests *execute*. Models
generalized it to `cargo test --workspace 2>&1 | grep X` (runs the whole suite,
filters only *output*) and repeated it once per must-have, adding minutes per
verification with no new evidence after the first run.
Replace the example with language-agnostic guidance: prove a test EXISTS via
enumeration (`cargo test -- --list` / `pytest --collect-only` / `npx vitest
list` / `go test -list`), and prove it PASSES via a single named test
(`cargo test <name> -- --exact` / `pytest -k` / `npx vitest run -t`). Add a
Spot-check constraint forbidding more than one full-suite run per verification
or piping a full run through grep per must-have, while still permitting one
saved run + grep when a full run is genuinely required. docs/AGENTS.md gains a
one-line Key-behaviors note, and a new test asserts the Step 7b content.
Scoped per the maintainer decision on the issue: folded into Step 7b (no new
top-level Step 7a) with no VERIFICATION.md label changes.
Closes#25
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore(#25): add Changed changeset fragment for PR #753
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* feat(#703): add --granularity override flag to /gsd:plan-phase
Add a `--granularity <coarse|standard|fine>` flag to /gsd:plan-phase that
overrides the configured planning granularity for a single invocation.
The override is a new highest-priority tier above the existing precedence
chain (granularities[phaseType] -> granularity -> planning.granularity ->
'standard') in resolveGranularityInternal; when the flag is absent, resolution
is byte-for-byte unchanged. cmdInitPlanPhase now resolves with phaseType
'planning' so granularities.planning participates, and emits the resolved
value in the init JSON, which the plan-phase workflow forwards to the planner
prompt. Invalid values are rejected at the CLI boundary via a shared
assertValidGranularityOverride helper.
Closes#703
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore(#703): set changeset pr to 750
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#683): auto-degrade phase execution to sequential on worktree base mismatch
Claude Code forks worktree-isolated executors off the repository default
branch (origin/HEAD), not the orchestrator's HEAD. Running /gsd-execute-phase
on a branch diverged from the default (unmerged milestone/feature branch) left
every executor without the phase's plan files and tripped the
worktree-branch-check guard with `exit 42` — 100% reproducible, all OSes.
- New module src/worktree-base-ref.cts: HEAD-vs-fork-base drift detection
(origin/HEAD with symbolic-ref fallback) and no-clobber worktree.baseRef
management, exposed as `worktree base-check` / `worktree set-baseref`.
- execute-phase.md: pre-dispatch, for Claude Code with worktrees enabled,
auto-degrades the run to sequential on the main tree when a base mismatch
is detected, recommending worktree.baseRef:"head". The exit-42 guard stays
as a backstop.
- Installer: fresh local Claude installs set worktree.baseRef:"head" in
.claude/settings.local.json (no-clobber, respecting an explicit shared
settings.json value); upgrades print an opt-in notice pointing at
`gsd-tools worktree set-baseref`.
- Docs: how-to guide, CLI/config reference, planning-config cross-ref.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#683): auto-apply worktree.baseRef on upgrade; gate fresh+upgrade on use_worktrees
Per maintainer direction: on a local Claude Code UPGRADE, set
worktree.baseRef:"head" automatically (no opt-in notice) when the project's
workflow.use_worktrees is enabled, instead of merely printing a remediation
notice. For consistency the FRESH path is now gated the same way: both paths
compute worktrees-enabled once (bounded walk-up read of .planning/config.json,
default enabled unless workflow.use_worktrees === false) and apply the
no-clobber baseRef only when enabled — never overwriting an explicit value in
settings.local.json or a shared settings.json. gsd-tools worktree set-baseref
remains for manual use. Docs + changeset updated; tests hardened (file-exists
assertions, fresh+disabled case, upgrade idempotency).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#683): measure workflow byte-budget on LF, fixing Windows-only CI failure
The workflow-size-budget test failed only on Windows: git checks out the .md
files as CRLF (no eol=lf in .gitattributes) and byteCount used
fs.statSync().size (raw on-disk bytes), counting an extra \r per line. That
inflated execute-phase.md — the XL high-water-mark file pinned near its ceiling
by the tighten-only ratchet — from 88492 LF bytes to ~90245 on Windows, over
the 90000 XL ceiling, while passing on the LF-checkout Mac/Linux runners.
The ceilings are explicitly "calibrated against raw `wc -c`" on an LF checkout,
so the measurement should be LF-based on every platform. byteCount now reads the
file and counts Buffer.byteLength after stripping CR, making the budget
platform-independent (a no-op on LF checkouts; verified statSync === normalized
for all 88 workflow files). No ceilings changed. Added a regression test
asserting CRLF and LF content of the same file count identically.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#683): make worktree-base-ref test path mocks Windows-safe (path.join)
tests/worktree-base-ref.test.cjs keyed its injected readFile/writeFile mocks
(and a few expected `file` values) with forward-slash template literals like
`${claudeDir}/settings.local.json`. The module composes those paths with
path.join(), which emits backslashes on Windows, so the mock keys never matched
the module's lookup → readFile returned null → resolveEffectiveBaseRef /
cmdWorktreeBaseCheck / cmdWorktreeSetBaseRef (and the JSONC variants) failed on
the Windows full-test runner only (they passed on Mac/Linux, and the install
tests passed because they use the real filesystem). The module is correct;
only the test fixtures hardcoded '/'.
All mock keys and path assertions now use path.join(base, ...) mirroring the
module, so they match on every platform (no-op on POSIX). 19 path references
across 16 lines.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* refactor(#720): lazy-load MVP-only reference bodies (eager @-import → gated Read)
Convert eager @-imports of MVP-only reference bodies into lazy "Read" instructions
gated on MVP_MODE / WALKING_SKELETON / MVP+TDD, so non-MVP planning/execution runs
no longer pull MVP guidance into context. Covers both the workflow files and the
planner/executor agent definitions (the dominant context-cost path):
- workflows/plan-phase.md: planner-mvp-mode.md + skeleton-template.md (L146/936/937/941)
- workflows/execute-phase.md: execute-mvp-tdd.md halt-report ref, now gated on gate-trip (L191)
- agents/gsd-planner.md: planner-mvp-mode.md, user-story-template.md, skeleton-template.md
- agents/gsd-executor.md: execute-mvp-tdd.md
The dedicated always-MVP mvp-phase workflow keeps its eager imports (intentional).
Behaviour is unchanged; non-MVP runs simply carry less loaded context. Adds a
regression guard mirroring the discuss-phase lazy-load test, and documents the
conformance in docs/ARCHITECTURE.md.
Refs #720
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* docs(#720): add changeset fragment (pr #746)
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Part 2 of 2 of the n/no-process-exit cleanup (completes umbrella #738; part 1
was #739/scripts). Converts the 20 flagged process.exit() calls in the three
hand-written gsd-core/bin CLI entrypoints and flips n/no-process-exit to error.
- New src/cli-exit.cts -> gsd-core/bin/lib/cli-exit.cjs (ExitError + runMain),
the gsd-core-side equivalent of scripts/lib/cli-exit.cjs; registered in
.gitignore, eslint ignores, and the inventory manifest like its siblings.
- gsd-tools.cjs: 13 apply-prompt-budget exits -> throw ExitError; main()->runMain.
- verify-reapply-patches.cjs: 6 exits -> throw ExitError / return verdict; runMain.
- check-latest-version.cjs: 1 exit -> return verdict; runMain.
- eslint.config.mjs: n/no-process-exit warn -> error.
Scope note: the gsd-core/bin/lib/*.cjs modules (core, state, profile-pipeline,
roadmap-command-router, adr-parser, ui-safety-gate) are tsc-generated and
eslint-ignored (ADR-457), so their process.exit calls were never flagged and are
intentionally left untouched. Only the linted hand-written entrypoints are in scope.
Exit codes verified unchanged for all three entrypoints.
Closes#738
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* feat(#159): auto-use existing RESEARCH.md in /gsd:plan-phase --research-phase
When RESEARCH.md already exists in research-only mode and neither --research
nor --view is passed, emit a one-line notice and exit cleanly instead of
prompting update/view/skip. This matches the promptless auto-use of standard
/gsd:plan-phase <N> (§5.1) and removes the §5.0/§5.1 inconsistency, making
AI-agent and CLI invocations non-interactive in the common case. The two
explicit-flag escape hatches (--research to refresh, --view to print) cover
any deviation.
Closes#159
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore(#159): point changeset fragment at PR #718
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* docs(#159): tighten research-phase reference register (Diataxis)
Make the 'no modifier' research-phase entries descriptive rather than
imperative and drop the trailing 'pass --research/--view' clauses, which
duplicated the adjacent --research/--view documentation. Reference docs
describe; the recovery flags are documented in their own entries. The
emitted runtime notice in the workflow keeps naming the flags (in-band
recovery), unchanged.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
