* fix(#813): apply per-runtime skill path rewrites in applySurface
applySurface() re-staged skill artifacts but, unlike installRuntimeArtifacts(),
never applied the per-runtime path rewrites. So /gsd:surface
(profile/enable/disable/reset) overwrote installed SKILL.md bodies with the
converter's default ~/.claude paths instead of the install target (pathPrefix),
silently regressing skill path references for every skillsKind runtime until
the next reinstall.
applySurface now mirrors installRuntimeArtifacts: for kind.kind === 'skills' it
derives pathPrefix the same way and applies applyRuntimeContentRewritesInPlace
on the staged dir before syncing.
- bin/install.js: export applyRuntimeContentRewritesInPlace
- runtime-artifact-layout.cts: carry resolved scope on Layout; export
getInstallExports; type computePathPrefix/applyRuntimeContentRewritesInPlace
on InstallExports
- surface.cts: lazily derive pathPrefix (only when a skills kind exists) and
apply the rewrite via the shared getInstallExports accessor — single source of
truth with install, only skills kinds rewritten (matches install)
- tests: regression test parameterized over cursor + codex asserting
post-applySurface bodies carry the install pathPrefix, not ~/.claude
- CONTEXT.md: glossary updated for the applySurface rewrite parity + scope seam
Closes#813
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore(#813): add changeset fragment for PR #817
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* test(#813): normalize configDir prefix to forward slashes for Windows CI
The #813 regression assertion compared skill bodies against a raw
${configDir}/ prefix, but production derives pathPrefix via
path.resolve(configDir).replace(/\\/g, '/'). On Windows, mkdtempSync
returns backslash paths while the rewritten body uses forward slashes,
so the assertion would fail Windows-only (not covered by local gsd-test).
Normalize the expected prefix the same way production does.
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>
* fix(#783): resolve Kilo global skills base to ~/.kilo/skills
getGlobalSkillsBase('kilo') returned ~/.config/kilo/skills (the XDG config
dir), but Kilo Code discovers global skills from ~/.kilo/skills/ (the .kilo
dir in HOME), independent of the kilo.jsonc config dir. Add a HOME-relative
special case so the resolver matches Kilo's actual discovery path.
The config dir (~/.config/kilo) and the installer's command/ path are
correct and unchanged. This corrects the path used by doctor/status and
agent-skills-block resolution; the installer writes commands (not skills)
for Kilo, so no files were being written to the wrong location.
Closes#783
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore(#783): set changeset pr to 806
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <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>
* refactor(#56): retire legacy runtime directory helpers into runtime-homes projection
Consolidate per-runtime global config-dir resolution onto the single
canonical projection runtime-homes:getGlobalConfigDir. Extend it with the
explicitDir override (CLI --config-dir) and the opencode/kilo
OPENCODE_CONFIG/KILO_CONFIG file-path precedence the installer helpers had,
making it byte-for-behavior equivalent to the old getGlobalDir across all
15 install runtimes.
Delete bin/install.js's getGlobalDir/getOpencodeGlobalDir/getKiloGlobalDir
(and the orphaned local expandTilde), repoint all 9 call-sites, and remove
getGlobalDir from module.exports (net -242 lines in the installer). Migrate
the 5 test importers to the canonical projection; harden default/XDG
assertions against ambient *_CONFIG env vars. getAgentsDir now respects
OPENCODE_CONFIG/KILO_CONFIG consistently with the installer (intentional
convergence). Update CONTEXT.md Installer Module entry.
Completes the installer-refactor chain #58 -> #60 -> #56.
Closes#56
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore(#56): add changeset for runtime directory helper retirement
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>
test.yml had no paths filter and the ci-test-scope classifier treated docs/
and every .github/workflows/* as code_changed, so documentation edits and
product-irrelevant automation tweaks still spun up the full Linux/Windows/macOS
matrix. Narrow the heavy matrix to changes that can actually affect the product
or the test pipeline.
- ci-test-scope.cjs: drop docs/ from code_changed (docs-only -> full skip; the
required-tests fan-in still reports green). Add src/ to code_changed (it was
missing -> a source-only PR previously skipped all tests). Add INERT_WORKFLOWS
allowlist + isInertCi() + an "inert CI" rule, and a product_changed output that
gates the heavy test/coverage jobs. Fail-safe: any workflow not on the inert
allowlist defaults to the full matrix. A module-load assertion throws if a
PROTECTED_WORKFLOWS entry (test/install-smoke/mutation/security-scan/release)
is ever added to the inert set, so a weakening edit fails CI loudly.
- test.yml: keep the static 3-lane matrix (so the H1 shell-policy linter can
still statically verify the Windows lane), gate test/coverage on
product_changed, add a lightweight ubuntu-only test-inert job, and branch the
required-tests fan-in on product_changed.
- docs-required.yml: run docs-parity-live-registry (gated on docs/ changes) so
pure-docs PRs still catch live-registry drift without the matrix.
- tests: cover docs-only, inert-only, src/, pipeline, unknown-workflow fail-safe,
mixed escalation, the code_changed=false -> no-lanes invariant, and protected-
workflow tamper-evidence.
Closes#764
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>
* test(#339): add regression guard for gsd-sdk refs in runtime surfaces
Lock in the already-clean runtime surface so a retired `gsd-sdk`/`GSD_SDK`
reference cannot creep back into a shipped prompt or hook. Scans
gsd-core/workflows, gsd-core/references, commands/gsd, agents, and hooks
(excluding the gitignored dist/ build artifact).
Complements gsd-tools-path-refs.test.cjs, which only catches the
`gsd-sdk query` binary form; this catches any runtime reference. A second
test guards against an empty sweep so a future dir rename can't silently
turn the guard into a no-op.
Intentionally does NOT touch bin/install.js (live stale-package-detection
mechanics per #339 triage) or CI/lint scripts (legitimate stale detection).
Refs #339
* test(#339): split file content on /\r?\n/ for Windows CRLF parity
The windows-test-parity-guard lint requires test files that readFileSync +
split to use /\r?\n/, not '\n', so CRLF files don't leave a trailing \r.
New test files are not in the PR #3649 allowlist.
* test(#339): cover .sh/.json runtime files in workflows surface
Address #691 review: the gsd-core/workflows surface scanned only .md,
silently skipping two deployed runtime files — _runtime-launcher.snippet.sh
(synced into every hook) and discuss-phase/templates/checkpoint.json. Add
.sh/.json so the guard covers all 290 deployed runtime files (was 288/290),
not just the .md subset.
* test(#339): cover templates/contexts surfaces + per-ext empty-sweep guard
Address PR #691 review (trek-e):
- Add gsd-core/templates and gsd-core/contexts to RUNTIME_SURFACES —
both are deep-copied by the installer and runtime-loaded via
@~/.claude/gsd-core/templates/*.md anchors, so a reintroduced gsd-sdk
ref there would have slipped past the guard. (major)
- Reword the bin/install.js exclusion rationale: it has zero gsd-sdk refs
today (subsystem removed in #515, shim retired in #522); the real reason
it is excluded is that it is installer code, not a deployed prompt/hook
surface. (minor)
- Make the empty-sweep guard assert coverage per configured extension, not
per surface — .md files alone kept gsd-core/workflows green even if
.sh/.json were dropped, silently un-covering _runtime-launcher.snippet.sh
and discuss-phase/templates/*.json. (low)
---------
Co-authored-by: Tom Boucher <trekkie@nomorestars.com>
close-draft-prs.yml (on pull_request_target after #760) cannot close fork draft
PRs whose head branch name looks like a Git SHA — GitHub never dispatches
pull_request_target for such branches, and a pull_request run from a fork gets a
read-only token. So a draft PR on a SHA-named fork branch evades the auto-close.
Add close-draft-prs-sweep.yml: a schedule (every 6h) + workflow_dispatch sweep
running in base-repo context with pull-requests: write that paginates open PRs,
filters to non-OWNER/MEMBER/COLLABORATOR drafts, and closes + comments them with
the identical policy/message as the event-driven workflow. Re-fetches each
candidate before mutating (TOCTOU guard), closes before commenting so
enforcement is never gated on the explanatory comment, and core.setFailed on
partial failures. The per-PR workflow remains the fast path; this is the
safety net for the documented residual bypass.
Extends tests/workflow-maintainer-skip.test.cjs with structural guards locking
the triggers, write permission, maintainer carve-out, pagination, and message.
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>
Bare `pull_request` hands fork PRs a read-only GITHUB_TOKEN, so the
close/comment API calls 403 and a first-time/external contributor's draft
PR survives — bypassing the auto-close for exactly the population the job
targets. Switch to `pull_request_target`, which runs in the base-repo
context with a write-capable token even for fork PRs. Safe because the job
never checks out or executes PR-supplied code; it only reads event metadata
and calls the GitHub API. The minimal `permissions: pull-requests: write`
block still constrains the token.
Add a regression guard in tests/workflow-maintainer-skip.test.cjs asserting
the workflow triggers on pull_request_target and not bare pull_request.
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>
CodeQL alert #26 (js/prototype-pollution-utility) kept firing on setConfigValue
because its dataflow does not trace the #663 Set-based, pre-loop keys.some(...)
forbidden-key check as a sanitising barrier on the write site.
- src/config.cts: replace the Set + pre-loop check with inline literal
comparisons (key === '__proto__' || 'prototype' || 'constructor') on the exact
key used to index `current`, immediately before each write (intermediate keys
in the descent loop, plus the final key). Same forbidden set, same error
message and ERROR_REASON.CONFIG_PARSE_FAILED — behaviour unchanged from #663,
but the barrier is now CodeQL-recognised.
- tests/config.test.cjs: add regression tests for schema-valid dynamic-prefix
keys (agent_skills.__proto__, agent_skills.constructor, agent_skills.prototype,
features.__proto__, review.models.constructor) that pass the isValidConfigKey
schema gate and reach the guard. Each asserts the guard's own message fires
(not the schema gate's "Unknown config key") and Object.prototype is not
polluted. The prior #663 tests never reached the guard — their keys are
rejected by the schema gate first — so the guard's real attack surface was
untested.
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>
`extractCurrentMilestone()` scoped the current-milestone window to its
`## Phases` checklist subsection and terminated at the milestone's own
`## Milestone … (Phase Details)` heading, so the `### Phase N:` detail
headers fell outside scope. Every parser-backed command — `init.phase-op`
(and thus `/gsd:discuss-phase`, `/gsd:plan-phase`), `state`, `roadmap list`,
and `validate health` (W006) — therefore could not resolve phases of any
milestone after the first until a `.planning/phases/` directory already
existed, blocking discuss/plan.
The parser now additionally includes the current milestone's `(Phase Details)`
section in scope, located via the already-computed version matches and anchored
(boundary-aware) to the selected milestone's version token so sibling
sub-milestones sharing a version prefix do not cross-pollinate. The existing
heading selection and primary window are unchanged.
Adds tests/bug-730-milestone-phase-details-scope.test.cjs covering the
two-milestone reproduction, first-milestone non-regression, direct
getRoadmapPhaseInternal resolution, validate-health W006 visibility, a
three-milestone roadmap, and the closed-sibling sub-milestone case.
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* refactor(#712): replace Codex slash-command denylist lookbehind with positive-boundary match
The hyphen-style /gsd-<cmd> -> $gsd-<cmd> conversion in
convertSlashCommandsToCodexSkillMentions used a negative-lookbehind DENYLIST
enumerating characters that must NOT precede a real mention. #637 -> #704 showed
this is an unbounded treadmill: each new unanticipated preceding char (/, ., word
chars, then }, )) leaked the same path-corruption bug class, and a backtick-wrapped
path (`/gsd-core/workflows/update.md`) still leaked through.
Replace it with a POSITIVE two-boundary definition of a mention:
1. Left: opens at start-of-string, whitespace, or an inline-prose delimiter
(backtick/quote/paren/bracket).
2. Right: the command token is not followed by a path separator `/` (a path
continues, a command does not). The (?![a-z0-9/-]) lookahead also blocks
regex backtracking to a shorter command.
This closes the whole class by construction (no preceding-char denylist to
maintain) and fixes the backtick-wrapped-path corruption the #704 test
documented as a pre-existing gap, while preserving conversion of legitimate
backtick-wrapped mentions (e.g. CONTEXT.md's `/gsd-execute-phase` lists).
The colon-style /gsd: replace is intentionally left unguarded (it never appears
as a filesystem path segment) and is annotated as such.
Tests assert the regex directly (function now exported) across a convert/
don't-convert matrix plus one end-to-end pipeline assertion for the headline
backtick-path case.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore(#712): add changeset fragment for PR #747
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>
Part 1 of 2 of the n/no-process-exit cleanup (umbrella #738): convert every
process.exit() call in standalone scripts/** CLIs to the rule-compliant pattern.
- New shared helper scripts/lib/cli-exit.cjs: ExitError(code,message) + runMain()
which translates a thrown ExitError / returned number into process.exitCode
(never process.exit()), flushing output and still firing process.on('exit').
- main()-based entrypoints: throw new ExitError(code) for errors, return <code>
for verdicts; invoked via runMain(main). Child exit codes preserved via return.
- top-level-only scripts: imperative body extracted into main() so mid-flow
aborts (throw ExitError) actually halt; pure consts/helpers stay at module scope.
- diff-touches-shipped-paths.cjs: stdin event handling restructured to an async
read so the whole flow runs under runMain; uncaughtException/unhandledRejection
nets replaced by an in-band catch that preserves EXIT_ERROR=2.
Exit codes verified unchanged for every converted script (success/error/help and
the 0/1/2 semantic codes in diff-touches). Rule stays warn here; flipped to error
in part 2 (#738) once gsd-core/bin/** is also clean.
Refs #739
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#706): skip rescueSummaryArtifacts when SUMMARY is already committed
rescueSummaryArtifacts now probes `git cat-file -e HEAD:<path>` before
copying a SUMMARY.md into the main checkout. When the file is already
committed on the worktree branch, copying it as an untracked file causes
`git merge --no-ff` to abort with "untracked working tree files would be
overwritten by merge" — a permanent merge_failed cleanup-wave failure.
Fail-closed on timeout: if cat-file is unreliable we skip rescue (the
merge will surface the collision as it did before, which is recoverable).
Adds 4 new test cases in worktree-safety.test.cjs covering:
- committed SUMMARY skipped, merge succeeds (#706 regression case)
- committed SUMMARY skipped even when timeout (fail-closed)
- uncommitted SUMMARY still rescued (existing contract preserved)
- rescue failure on ENOSPC still propagates (unchanged)
Closes#706
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* chore: add changeset for #706
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(#706): treat cat-file exit 128 as uncertain — skip rescue (fail-closed)
The previous guard skipped rescue only when `exitCode === 0` (committed) or
`timedOut`. Any other non-zero exit, including `128` (fatal git error: corrupt
object store, unborn HEAD, missing repo), fell through and PROCEEDED with
rescue — potentially re-creating the #706 untracked-file merge collision.
Fix: rescue ONLY when `exitCode === 1` (cat-file definitively reports the
object absent). All other outcomes — 0 (committed), 128 (fatal), null/SIGTERM
(timeout), or any other code — are treated as "uncertain → skip rescue".
Also corrects the JSDoc bullet that still referenced `git ls-files
--error-unmatch` (the old mechanism); updated to `git cat-file -e HEAD:<relPath>`.
Regression test added: asserts rescue is SKIPPED when cat-file returns exit 128,
leaving the merge to surface the issue safely rather than silently copying an
already-committed file.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* chore: link changeset to PR #709
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(#704): exclude } and ) from Codex path-rewrite lookbehind
Shell variable expressions like \${VAR}/gsd-core/ and command-substitution
paths like \$(cmd)/gsd-local-patches were being rewritten to \$gsd-core and
\$gsd-local-patches respectively because the negative lookbehind in
convertSlashCommandsToCodexSkillMentions did not include } or ).
Add both characters to the lookbehind set:
(?<![a-zA-Z0-9./})])
Also adds regression test:
tests/bug-704-codex-launcher-path-corruption.test.cjs
Closes#704
* chore: add changeset for #704
* test: use RUNTIME_ROOT_PATH in assertion to eliminate dead-code lint warning
Replace the partial hard-coded fragment '}/gsd-core/bin/' with the
existing RUNTIME_ROOT_PATH const so the assertion both compiles clean
(no unused variable) and self-documents which canonical launcher path
must survive Codex conversion intact (#704).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* chore: link changeset to PR #710
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Replace raw setTimeout/Atomics.wait synchronization sleeps in 4 test files
with a shared async delay()/waitFor() poll-for-condition helper in
tests/helpers.cjs, then flip local/no-magic-sleep-in-tests and
no-restricted-syntax from warn to error so the debt can't regrow.
- tests/helpers.cjs: add delay(ms) + waitFor(predicate, opts), exported
- bug-1974: setTimeout backoff -> await delay()
- config.test: drop Atomics.wait sleep(); async retry via await delay()
- graphify: waitForBuildStatus/cleanupHookRepo async via await delay()
- locking-bugs: 3 Atomics.wait poll loops -> await waitFor()
- eslint.config.mjs: ratchet both rules warn -> error
Refs #733
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
The 5 no-control-regex warnings are all the same intentional ANSI-color-strip
pattern /\x1b\[[0-9;]*m/g across 5 test files. The \x1b (ESC) control char is
the required leading byte of an ANSI SGR sequence, so matching it is the whole
point of stripping color codes from captured CLI/console output. Add an inline
eslint-disable-next-line with justification at each site (not a refactor — the
control char is essential, not accidental), then flip no-control-regex from
warn to error so the debt can't regrow.
Refs #736
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Pay down pre-existing error→warn lint debt. Removes dead imports/vars, unused functions, redundant regex/string escapes, and stale eslint-disable directives; converts unused `catch (_e)` to optional catch binding (src/*.cts).
No behavior change. Lint 345→125 warnings (0 errors); deferred categories (n/no-process-exit, test-sleeps, control-regex) tracked in #732 for follow-up. Full test suite green (0 failures); code-review verified all removals unused and all escape fixes semantics-preserving.
Closes#732
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>
* feat(#717): re-base workflow size budget on bytes + document quality rationale
Re-base tests/workflow-size-budget.test.cjs from line counts to byte
counts (matches Codex's 32,768-byte project_doc_max_bytes cap; deterministic,
no tokenizer). Tier ceilings: XL=90000, LARGE=54000, DEFAULT=38000, GRACE=3000;
discuss-phase target re-expressed as <30 KB. The #597 tighten-only ratchet and
per-file budget semantics are preserved unchanged — only the unit swaps.
byteCount() uses fs.statSync().size to match `wc -c` (includes trailing
newline), deliberately not lineCount()'s newline-stripping.
Document the context-rot / attention-budget QUALITY rationale (independent of
prompt caching) in the test JSDoc and docs/ARCHITECTURE.md, plus the
Goodhart caveat: the byte budget measures one file, so the real goal is
bounded *loaded* context — eager @-imports game the proxy; legitimate
extraction is lazy. Update CONTEXT.md RULESET.WORKFLOW_SIZE_BUDGET to bytes and
remove a stale duplicate ruleset entry that still said "1800 lines".
Defers the #3182 MVP-mode split (tracked separately): MVP is a cross-cutting
concern woven through plan-phase/execute-phase, not a discrete extractable mode.
Closes#717
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* docs(#717): add changeset fragment for byte-budget re-base
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* feat(#656): add Research Store module (content-addressed cache, TTL staleness)
Content-addressed research cache behind a clock seam: researchKey (sha256, deterministic), putResearch/getResearch ({hit,stale}, never throws), ttlForSource (curated HIGH 30d / MED 7d / web LOW 1d), two-tier resolveStorePath (curated -> ~/.gsd/research-cache, web/synthesis -> project .planning/research/.cache). 28 behavioral + property tests; boundary coverage at ttl-1/ttl/ttl+1.
Issue #656. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(#656): add Research Provider module (waterfall + confidence + plan)
Single source of truth for the Balanced provider waterfall (docs Context7->Ref->Jina, web Exa+Tavily, fallback Perplexity/Brave, Firecrawl scrape-only). classifyConfidence stamps HIGH|MEDIUM|LOW by provider (never throws). providerAvailability maps config flags to usable providers. planResearch checks the Research Store (injected seam) and returns cache-hits + a per-question fetch plan, falling through the waterfall to the always-available websearch terminal. 22 behavioral + property tests.
Issue #656. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(#656): add Package Legitimacy module (registry-API verdicts, slopcheck optional)
Replaces the pip-install-or-degrade slopcheck prose gate with code: classifyPackage (pure, never throws) computes OK|SUS|SLOP from tunable thresholds (minAgeDays 30, minWeeklyDownloads 1000, requireRepo). checkPackages queries injectable npm/PyPI/crates registry adapters (real https with 5s timeout, degraded-not-thrown on failure); slopcheck is one optional adapter that can only escalate severity, never degrade to [ASSUMED]. 34 behavioral + property tests; boundary coverage on age and downloads (limit-1/limit/limit+1).
Known follow-up: real npm adapter must add api.npmjs.org last-week downloads fetch (currently null -> unknown-downloads). Issue #656. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(#656): detect Tavily/Ref/Perplexity/Jina provider keys; complete npm downloads adapter
config: add tavily_search/ref_search/perplexity/jina availability flags (env var or ~/.gsd/<x>_api_key), mirroring brave_search/exa_search/firecrawl, so the Research Provider waterfall can gate them. package-legitimacy: real npm adapter now fetches api.npmjs.org last-week downloads (bounded, degraded-not-thrown) so weeklyDownloads is populated. +12 config tests; 34 legitimacy tests unchanged.
Issue #656. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(#656): expose Research seam via gsd-tools query (research-plan, research-store, package-legitimacy)
Routes the L2-hybrid surface so agents reach it as CLI: 'query research-store get/put' (cache, HOME-sandboxable), 'query research-plan --input' (cache-hits + fetch plan from planResearch), 'query package-legitimacy check --ecosystem' (async registry verdicts). Commands skip .planning root resolution and appear in top-level usage. 5 behavioral runGsdTools tests; command-contract unchanged (335).
Issue #656. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* docs(#656): document Research module (CONTEXT predicates, ADR-0656, architecture, changeset)
Adds GSD-RESEARCH.* + DEFECT.RESEARCH-PROVIDER-PROSE-DRIFT predicates to CONTEXT.md, ADR-0656 recording the L2-hybrid seam decision, a docs/ARCHITECTURE.md Research Module subsection, and an Added changeset fragment (pr:0, backfill on PR). Notes the #657 deferrals (agent collapse + install.js MCP mapping).
Issue #656. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* chore(#656): sync inventory for research modules
Regenerate INVENTORY-MANIFEST.json and bump docs/INVENTORY.md CLI Modules count 82->85 with rows for research-store/research-provider/package-legitimacy (DEFECT.INVENTORY-DRIFT).
Issue #656. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* chore(#656): eslint-ignore generated research .cjs artifacts (ADR-457)
research-store/research-provider/package-legitimacy .cjs are tsc-generated from src/*.cts, so they belong in the ESLint ignore block (lint the .cts source, not the emitted .cjs). Fixes tests/551-eslint-bin-lib-coverage.
Issue #656. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* chore(#656): backfill changeset pr number to #664
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* chore(#656): satisfy eslint lint-tests gate
Fix 20 eslint errors in the new research files: use helpers.cleanup() instead of raw fs.rmSync() in tests (local/no-raw-rmsync-in-tests, Windows-EBUSY retry budget); drop redundant '| string' union members and unnecessary type assertions; deterministic object normalization in researchKey (no-base-to-string). Logic unchanged; 6180 tests still green.
Issue #656. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(#656): harden package legitimacy per review (W1/W2/I3/I4)
W1: httpsGet now reads statusCode; npm/PyPI/crates map 404 -> exists:false -> SLOP (registry-existence is the #1 slopsquatting defense; previously only npm caught it). Transport made injectable (_setHttpGet) for hermetic 404 tests. W2: suspicious-postinstall is now terminal SLOP independent of the optional slopcheck adapter, and the regex drops the bare https?:// arm (over-fired on esbuild/sharp/node-gyp) for shell-exec/download-exec signatures only. I3: checkPackages now threads version to registry.lookup and adapters verify that specific version exists. I4: moreServerVerdict -> moreSevereVerdict. +11 regression tests (all RED-first); 45 total green.
Addresses review by @davesienkowski on #664. Issue #656. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(#656): research-store tier coherence + freshness + version TTL (W4/I1/I2/I4)
I1: tier now derives from source (curated -> user ~/.gsd, else -> project .planning), not kind, so put-tier and get-tier can't diverge; kind is a key component only. W4: getResearch searches both tiers and returns the freshest (non-stale preferred), never letting a stale curated entry shadow a fresh web one; blank version caps TTL at 1 day (no 30d on version-blind keys). I2: atomic platformWriteSync instead of raw fs.writeFileSync on the shared global path. I4: dropped the dead ttlForSource arm. CLI get now searches both tiers. +5 RED-first regression tests; 38 green.
Addresses review by @davesienkowski on #664. Issue #656. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(#656): expose classifyConfidence as a CLI route, killing dead code (W3)
Adds 'gsd-tools query classify-confidence --provider X [--verified]' so research agents get the confidence tier FROM CODE (provider waterfall + verification lever) instead of asserting it in prose. classifyConfidence previously had no runtime caller. HIGH means 'trusted provider'; --verified raises web results to MEDIUM (verification semantics documented in ADR-0656). +4 behavioral tests.
Addresses review by @davesienkowski on #664 (W3). Issue #656. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(#656): close Codex adversarial-review findings (path-traversal, version-age, malformed-cache)
HIGH: research key must be 64-hex sha256 (isValidResearchKey) + resolved-path containment check in put/get + CLI validation -> blocks '../../x' arbitrary-file-write. HIGH: package legitimacy now derives publishedAt from the REQUESTED version (npm time[version], PyPI releases[version] upload_time, crates versions[].created_at) so a new malicious version of an old package can't inherit old age and evade 'too-new'. MEDIUM: getResearch validates entry shape (finite fetched_at + positive ttl + required fields) -> malformed cache entry is a miss, not fresh-forever. +regression tests (RED-first); 111 green.
Codex adversarial review (required pre-PR gate). Issue #656. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(#656): close code-review correctness findings
(1) package-legitimacy CLI now rejects unknown --flags instead of silently consuming the following package as a flag value; only --ecosystem takes a value. (2) crates recent_downloads (90-day) normalized to a weekly figure before the minWeeklyDownloads threshold (was ~13x too lenient). (3) research-plan --input validates parsed JSON is an object with an Array questions before destructuring -> clean usage error instead of an uncaught TypeError on null/bad input. (4) research-store put rejects a flag value that is itself a --flag (no more storing '--source' as content). (5) planResearch skips questions whose text is not a non-empty string instead of emitting question:undefined. +13 RED-first regression tests; 143 green.
Code-review gate. Issue #656. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* refactor(#657): extract researcher documentation_lookup to shared @-reference
6 researcher agents carried a near-duplicate <documentation_lookup> block; consolidate into gsd-core/references/research-documentation-lookup.md (@-included). Unifies the ctx7 CLI fallback to the safer 'command -v ctx7' guard (drops silent 'npx --yes ctx7@latest' execution in 5 agents). Behavior-preserving dedup; inventory 63->64 references. Phase A of the agent collapse.
Issue #657. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* refactor(#657): extract researcher philosophy + verification-protocol to shared @-references
philosophy and the pitfalls+pre-submission-checklist common-core were near-duplicated in project/phase researchers; consolidate into gsd-core/references/research-{philosophy,verification-protocol}.md (@-included). phase-researcher keeps its 3 extra checklist items inline. Pre-submission domains checklist made agent-agnostic so project-researcher doesn't lose features/architecture coverage. Write-contract intentionally left inline (bug-214 tests assert it verbatim). Inventory 64->66 refs. Behavior-preserving. Phase A.
Issue #657. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(#657): wire gsd-phase-researcher to the Research seam (Phase B / S1)
The phase researcher now CALLS the code seam instead of carrying inline mechanics: provider waterfall -> 'gsd-tools query research-plan' (+ research-store put to cache digests); confidence-tier prose -> 'gsd-tools query classify-confidence'; slopcheck pip-install protocol -> 'gsd-tools query package-legitimacy check'. This makes the Research module a real runtime consumer (validates the seam end-to-end, addresses reviewer S1) and removes the duplicated waterfall/confidence/slopcheck prose. RESEARCH.md output contract, commit step, structured returns, and Phase-A @-includes unchanged. package-legitimacy-gate.test.cjs rewritten prose-grep -> behavioral (asserts the seam invocation).
Issue #657. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(#657): wire gsd-project-researcher to the seam + add tavily/ref/jina MCP tools (Phase C.1)
project-researcher now calls gsd-tools query research-plan / classify-confidence (+ research-store put) instead of the inline provider waterfall + confidence-tier prose (mirrors the phase-researcher rewire; no package-legitimacy — phase-only). Output contract (STACK/FEATURES/ARCHITECTURE/PITFALLS/SUMMARY.md + sections, no-commit, structured returns, Phase-A @-includes) unchanged. Adds mcp__tavily/ref/jina__* to the project/phase/ui researcher tools frontmatter (Balanced provider set) so install.js MCP mapping (C.2) has a consumer.
Issue #657. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* test(#657): cover tavily/ref/jina MCP install handling + frontmatter parity guard (Phase C.2)
Investigation: exa/firecrawl have no explicit per-runtime tool-mapping — every mcp__<server>__* except context7 rides the generic passthrough (Copilot lowercases; OpenCode/Cursor/Windsurf/Augment keep as-is; Gemini auto-discovers). tavily/ref/jina are handled identically, no install path broken. Added 12 copilot-install passthrough tests + a mcp-tool-inheritance parity guard (tavily co-declared with exa, jina with firecrawl, ref present across the 3 web researchers) so the MCP set can't drift. No io.github registry ids invented (none sourceable in-repo); documented as a follow-up. 488 tests green.
Issue #657. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(#657): profiles as source of truth for researcher agents + drift-guard (Phase C.3)
scripts/research-profiles.cjs declares each of the 7 researcher agents' identity + contract (name, description, color, tools, required @-includes, required gsd-tools seam calls, output-contract markers). scripts/gen-research-agents.cjs --check validates every committed agent against its profile; --write regenerates ONLY the frontmatter from profiles (body untouched) and is a verified no-op against the current agents (zero diff = fidelity). tests/research-agent-profiles.test.cjs is the DEFECT.GENERATIVE-FIX drift guard. Design note: profiles govern the generatable/contract surface rather than destructively regenerating the disparate operational prose bodies (those were deduped via @-includes in Phase A). scripts/ is not inventoried (no inventory change).
Issue #657. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(#657): complete agent provider-dispatch + parity guard; align legitimacy field; validate profiles
Adversarial-review findings: (HIGH) the seam-wired agents' Step-C dispatch only mapped 6 providers, so a planResearch result of jina/ref/perplexity/brave (reachable via the waterfall fallbacks) had no handling -> agent stall; completed both agents' dispatch to all 9 PROVIDER_WATERFALL ids + a catch-all, and added a parity test asserting agent dispatch stays in sync with research-provider PROVIDER_WATERFALL (DEFECT.GENERATIVE-FIX). (MEDIUM) phase-researcher package-legitimacy JSON example used 'package' but the module returns 'name' -> aligned. (LOW) gen-research-agents checkAgent now returns a clear failure for a malformed profile instead of throwing. +parity/validation tests (RED-first).
Issue #657. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(#656): make classifyConfidence verification-evidence-driven (W3)
Confidence conflated provider authority with claim verification — context7/ref
stamped HIGH purely by provider identity, and the only verification lever was a
self-set --verified flag. Split into two axes: provider authority (static) +
verification evidence (code-computed). HIGH now requires ground-truth
corroboration (legitimacyVerdict OK), independent of provider; authority alone
caps at MEDIUM; SLOP caps at LOW; the self-reported --verified is demoted to a
MEDIUM-only web lever. HIGH = corroborated-against-authoritative-source, not a
correctness guarantee. Adds --legitimacy-verdict to the classify-confidence CLI;
updates CONTEXT.md predicate + ADR-0656 (tier set unchanged, ADR-consistent).
Addresses davesienkowski's W3 review on #664.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#656): bind classify-confidence verdict to code, closing CLI self-grading
Adversarial review found the new --legitimacy-verdict flag was caller-supplied,
so an agent could self-assert OK->HIGH without any real legitimacy check —
reintroducing the exact self-grading hole W3 closes. Remove the free flag; the
CLI now computes the verdict via checkPackages only when --package/--ecosystem
is given (code-computed, not agent-asserted). Update the stale CLI test
(context7 alone -> MEDIUM) and extend the property test to vary legitimacyVerdict.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Adds --only N and --text to the COMMANDS.md reference table and the
run-phases-autonomously how-to guide, revised to fit the Diataxis
framework (reference: factual/parallel rows; how-to: goal-framed sections).
* feat(#690): wire CHANGELOG render into release finalize job
CHANGELOG promotion has always been a manual operator step, which is why
1.3.0/1.3.1 shipped unpromoted (#690). PR #694 added a `verify` latch that
fails a release lacking a dated heading, but nothing performed the promotion.
Wire `changeset render` into the finalize job, after build/test and before
the verify gate, committing the promoted CHANGELOG so it ships with the
release. Add a `--allow-empty` flag to cmdRender so a zero-fragment release
still emits a dated heading (with a '_No notable changes._' placeholder)
instead of writing nothing and tripping the verify gate.
Note: requires the changeset-archive cleanup (separate PR) to land first, so
the first render consumes only genuinely-unreleased fragments.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore(#713): set changeset pr number to 715
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
CHANGELOG promotion was a manual operator step that was never run, so 463
fragments for work already shipped in <=1.3.1 accumulated in .changeset/.
Their notes were already hand-curated into the dated [1.2.0]/[1.3.0]/[1.3.1]
CHANGELOG sections (#690 backfill, PR #694). Rendering them now would
duplicate and mis-attribute shipped work.
Move them to .changeset/archived/ (read non-recursively by all changeset
tooling, so never rendered), keeping only the 3 genuinely-unreleased
fragments at the top level. Prep for wiring `render` into the release
finalize job (#690 follow-up).
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#669): /gsd-review --cursor actually invokes cursor-agent
The Cursor reviewer branch in review.md never ran the agent:
- detection probed `cursor` (the IDE launcher) instead of the headless
`cursor-agent` binary
- the invocation used the two-token `cursor agent` (the IDE treats `agent`
as a file-path argument, so the agent never starts)
- the prompt was piped via stdin, but `cursor-agent -p` reads the prompt
from a command-line argument, and `2>/dev/null` hid the empty result
Probe `cursor-agent`; invoke `cursor-agent -p --mode ask --trust
--output-format text` with the prompt passed as a file-path-reference
argument (avoids the OS arg-length limit on large prompts); capture stderr
so failures are diagnosable. Invert tests/cursor-reviewer.test.cjs to assert
the corrected contract, with negative guards against the two-token form and
the stdin pipe. The sibling `agy` reviewer already used the argument form.
Closes#669
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore(#669): set changeset pr number to 686
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
`/gsd-review --agy` hung indefinitely on large prompts. agy's print mode runs the
full tool-enabled agent, and on a big, file-path-rich prompt its agentic Cascade
loops on the code_search/grep tool and never converges; the transcript fallback
only runs after agy exits, so it can't recover a run that never exits.
The agy CLI exposes no per-tool deny (that lives in the Antigravity SDK), but it
does expose --print-timeout — agy's native print-mode cap. Pass it explicitly so a
stalled run self-terminates through the tool's own mechanism; a non-zero exit
discards any partial output so the existing transcript fallback / "review failed"
stub take over. Adds a regression test.
Closes#687
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#685): set windowsHide on all Windows child-process spawns
A visible "gsd-core" console window flashed on Windows whenever a gsd-core
child process spawned without `windowsHide: true`. The most visible offenders
fire on every SessionStart / `/clear` (execNpm's `shell:true` npm view via the
update-check worker) and on every Edit/Write/MultiEdit in a worktree (the
worktree-path guard's git probe).
Add `windowsHide: true` to every external-binary spawn in the runtime source:
- hooks/gsd-context-monitor.js (record-session spawn)
- hooks/gsd-worktree-path-guard.js (SPAWNOPT)
- hooks/gsd-workflow-guard.js (git branch --show-current)
- src/shell-command-projection.cts (execGit / execNpm / execTool)
- src/check-command-router.cts (git log execFileSync)
- src/roadmap-upgrade.cts (git status/rev-parse/reset/clean execSync)
gsd-check-update.js already had it (the precedent). probeTty's tty call is
POSIX-only and intentionally untouched. Adds a regression test that asserts
each site plus a repo-wide completeness guard so a future external-binary
spawn that omits windowsHide fails CI. No behavior change off-Windows.
Closes#685
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore(#685): set changeset pr number to 688
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#705): route hardcoded $HOME gsd-tools invocations in agents/commands through gsd_run
The hardcoded `node "$HOME/.claude/gsd-core/bin/gsd-tools.cjs" <cmd>` form
(fixed for workflows in #621/#637) survived in agent/command surfaces and
misresolves on global/shim-only installs. Route every agent-executed
invocation through the resolved `gsd_run` launcher in gsd-phase-researcher,
gsd-planner (load_graph_context extracted to a shared reference to stay under
the planner size budget), import, and graphify. Add a regression guard over
agents/ + commands/ + gsd-core/references/ bash blocks. User-facing display
messages and docs are intentionally left untouched.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#705): use repo changeset fragment format (type: Fixed, pr: 707)
The hand-written fragment used the standard changesets package format
(package: bump) which lacks the type:/pr: frontmatter the repo's
docs-required lint consumes (fail_malformed_fragment / missing_type).
Regenerated via scripts/changeset/new.cjs.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#637): route 3 more workflows through gsd_run launcher (hardcoded $HOME sweep)
The hardcoded `node "$HOME/.claude/gsd-core/bin/gsd-tools.cjs"` invocation form
fixed in plan-phase.md (#621) survived in three more workflows. Same bug class:
on a global/shim-only install with no project-local runtime, the hardcoded path
can miss a working install, so the step reports the tool "not found" instead of
resolving it via the launcher. #3668 introduced gsd_run resolution; these sites
were missed.
- plan-review-convergence.md: convert the 3 hardcoded invocations (init,
roadmap get-phase, state planned-phase) to gsd_run. File already carried the
canonical preamble (first gsd_run is the earlier convergence-enabled check).
- ingest-docs.md, spec-phase.md: convert their hardcoded invocations to gsd_run
and inject the canonical launcher preamble via
`node scripts/sync-runtime-launcher.cjs` (these files previously had no
gsd_run and no preamble). The injected preamble is byte-equal to
_runtime-launcher.snippet.sh and precedes the first gsd_run call, per
runtime-launcher-parity invariant (B).
- Add tests/bug-637-workflow-no-hardcoded-home-tool.test.cjs: repo-wide
regression guard asserting NO workflow .md invokes gsd-tools via a hardcoded
$HOME path. Generalizes the plan-phase-only guard from #621 — the parity test
guards retired $GSD_SDK / bare /gsd-tools tokens but not this form, which is
how it survived across four files. Fails on the pre-fix files, passes after.
runtime-launcher-parity 7/7; full unit suite green (3477 pass / 0 fail).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* chore(#637): add changeset fragment for PR #642
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* test(#637): update stale bug-2801 assertion to expect gsd_run
bug-2801 pinned ingest-docs.md to the hardcoded node "$HOME/.../gsd-tools.cjs" init form, which #637 replaces with the gsd_run launcher. Flip the assertion to expect gsd_run init ingest-docs; the bare-gsd-tools rejection and CLI-handler tests are unchanged, and bug-637's repo-wide guard now owns the no-hardcoded-$HOME invariant.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Tom Boucher <trekkie@nomorestars.com>
