An allow-test-rule annotation citing a category that does not apply is worse
than no annotation, because it reads as reviewed. Eight were confirmed by
reading the assertions each one covered, and auditing the rest found five more
plus one refutation — a converter test whose wording described the wrong
mechanism while the covered assertion genuinely was deployed-text.
The instructive one used the CANONICAL string for the same mistake: STATE.md
command output labelled as a deployed artifact. A canonical string is not
evidence the category fits, which is why normalising strings alone would have
laundered the problem rather than fixed it. Every mapping the audit had inferred
rather than code-verified was spot-checked before rewriting, and the ones that
turned out not to fit were re-annotated rather than relabelled.
Fourteen STATE.md assertions had a typed extractor available all along and now
use it; their annotations came out because nothing needs exempting. Eight
assertions genuinely need a production change first — CLI stdout and stderr with
no structured mode — and are tagged pending-migration-to-typed-ir citing #3090,
which is what that category is for. It had zero real uses before this, while one
file carried a real citation to migration issue #2974 under a non-canonical tag.
Six annotations covered assertions that do no text matching at all. An exemption
for a violation that does not exist is noise that makes the real ones harder to
audit; those are removed.
atomic-write-coverage gains the annotation it always warranted — its own
docstring describes a structural-regression-guard while the file carried none.
Fifty-nine non-canonical strings across roughly thirty files are normalised, and
the allow-test-rule allowlist is regenerated to match. 472 annotations became
463: every one now uses a canonical category, and the two remaining
non-canonical strings are ESLint RuleTester fixtures, not annotations.
Refs #3057
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Final phase of #2584 (ADR-1239 Codex-binding amendment). execute-phase now negotiates dispatch.isolation and dispatches through the matching adapter, so a wave's independent plans run concurrently on six runtimes instead of one — with no runtime=== branch in the scheduler.
harness-worktree passes the host's declared isolation flag (claude, cursor); orchestrator-worktree creates the worktree via the Phase-2 verb and spawns the executor into it with the resolved argv/cwd (codex, opencode, kimi, kimi-code); none stays sequential. Undeclared/unknown/unresolvable isolation degrades to none — never an unisolated parallel run.
Fixes two shipped Phase-2 descriptors that per-host research found would fail at spawn: kimi lacked its headless flag (would launch the interactive TUI and hang the orchestrator), and kimi-code named a non-existent binary (Kimi Code installs as 'kimi'). Adds the worktree-path root confinement Phase 2 deferred here, and leading-dash guards on the resolver's prompt/cwd matching the existing git-argument guard.
Closes#2627
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Fold all runtime==='kimi'/isKimi logic branches into descriptor-driven
hostBehaviors (localInstallDeferred, verificationStyle, agentManifestStyle,
reapplyCommand, doneBannerStyle) + add 'kimi' to _DESCRIPTOR_AGENTS_RUNTIMES.
Kimi's skills/kimi-agents dispatch was already descriptor-driven (converter-by-
name + kimi-agents kind). Zero isKimi/runtime==='kimi' branches remain.
UPGRADE 1 (native hook bus): new hooksSurface 'kimi-hooks-toml' + a marker-
delimited config.toml [[hooks]] emitter (buildKimiHooksTomlBlock/writeKimiHooksToml
in runtime-hooks-surface.cts; resolveKimiHooksTomlDir in runtime-homes.cts).
GSD's lifecycle hooks now wire into Kimi's native ~/.kimi/config.toml (Context7-
confirmed path) at SessionStart/PreToolUse/Stop/PreCompact/SubagentStart/
SubagentStop — kimi becomes a hooks/ consumer (the 3 && !isKimi exclusion guards
removed). config.toml holds absolute install paths so it's golden-excluded via
an exact relative-path (.kimi/config.toml), not a basename (which would blind
Codex's config.toml). New hooksSurface value added to the closed enum in
capability-validator + runtime-config-adapter-registry.
UPGRADE 2 (background dispatch): flip dispatch.backgroundDispatch true (Kimi's
Agent tool takes run_in_background; root agent already gets the Agent tool), so
negotiation no longer flattens dispatch. subagentToolkit stays 'undocumented'
per AC (coder/explore/plan have distinct tool policies).
MCP transport explicitly deferred (no installer-driven MCP for any runtime).
Golden: only kimi.json changes (hooks/ scripts now installed); all 15 others +
claude-local byte-identical (kilo/zcode keep their own exclusions). Tests:
kimi-imperative-reference (adapter/axes/fail-closed/hostBehaviors + source-grep
guard) + kimi-upgrades (config.toml [[hooks]] SessionStart + marker idempotency
+ backgroundDispatch negotiation). CONTEXT.md glossary + matrix + how-to updated;
changeset (Added).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Fold trae logic branches into descriptor-driven reads: skipSharedHooksInstall
gates (dropped && !isTrae), and the case 'trae' path-rewrite arm now computes
the self-alias from the descriptor-driven dirName (.trae). Dead isTrae bindings
removed from uninstall/writeManifest/finishInstall. trae's skills dispatch was
already descriptor-driven (converter-by-name). RUNTIME_CONTENT_DISPATCH.trae is
left as a runtime-keyed table registration (its regex/callback rewrites can't be
a byte-identical descriptor map — matches cursor/windsurf/cline). trae stays in
RUNTIME_FLAG_IDS: isTrae still gates the agents-converter selection (agents out
of scope; removal gated on the cross-runtime agents-dispatch migration).
Byte-identical golden parity for all 16 runtimes.
UPGRADE: SOLO stage/trigger metadata — emitted Trae SKILL.md now carries
stage: workflow (descriptor-gated via hostBehaviors.soloStageMetadata) so
Trae's SOLO Agent can auto-invoke GSD skills at the corresponding stage. Field
shape is best-effort/inferred (Trae publishes no formal schema). trae.json
golden regenerated.
Tests: trae-imperative-reference (adapter/axes/fail-closed shouldFlattenDispatch
+ no runtime==='trae' source-grep, isTrae exempted for agents) + trae-upgrades
(stage: workflow on installed SKILL.md, descriptor-gated). Matrix note +
changeset added.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Fold remaining isKilo logic branches into descriptor-driven reads:
finishPermissionWriter (uninstall cleanup), skipSharedHooksInstall (hooks
copy), and a skills converter-name registry (the artifactLayout.converter
field is now load-bearing, not decorative). frontmatterDialect stays the
documented dispatch key for frontmatter (no descriptor field for it). Dead
isKilo destructure bindings removed. Byte-identical golden parity for all 16
runtimes (opencode, which shares kilo's combined-family path, verified clean).
UPGRADE 1 (hook bus): install .kilo/plugins/gsd-core.js native plugin +
extensionEvents:"kilo" + EXTENSION_EVENT_SURFACES.kilo (OpenCode-fork bus).
UPGRADE 2 (active model): populate runtimeTierDefaults.kilo + thread
modelOverride through convertClaudeToKiloFrontmatter — model no longer stripped
from agents. UPGRADE 3 (MCP): document the gsd-core MCP companion under kilo's
mcp config key. UPGRADE 4 (named dispatch): agents/*.md mode:subagent roster is
the Task-tool dispatch surface (tested); subagentToolkit stays 'undocumented'
per AC so dispatch degrades to 'degraded' by design.
Model-catalog single-source edit ripples the shared model-catalog.json hash
into all 16 golden fixtures (expected). Inline defect fixes (no-defer): stale-
bake-guard resolveAgentDir 'agent'->'agents' (was a silent no-op for opencode/
codex), hardcoded 'Removed OpenCode plugin' uninstall log -> generic, and the
connect-gsd-mcp-server.md OpenCode mcpServers->mcp doc error.
Tests: kilo-imperative-reference (adapter/axes/fail-closed/degradation/
hostBehaviors + widened isKilo source-grep across 4 modules) + kilo-upgrades
(plugin parity+load, model-override converter, agents dispatch surface, MCP
doc). Matrix + how-to + config docs updated; changeset added.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* feat(#1928): remove sunset gemini cli runtime, redirect to antigravity
Google sunset Gemini CLI on 2026-06-18; Antigravity CLI is its official successor (already a first-class GSD runtime). Remove the gemini runtime from the enum (16->15), aliases, labels, config-home fragment, install path, converters (convertClaudeToGemini{Markdown,Toml,Agent}, convertSlashCommandsToGeminiMentions), capability descriptor, gemini-extension.json, RULESET.GEMINI.*, and the interactive menu (renumbered, no gap).
--gemini now prints an explicit deprecation notice citing the 2026-06-18 sunset and redirects to --antigravity (no silent alias, per the issue's Hyrum's-Law rejection). Antigravity is preserved throughout: its GEMINI.md contextFileName, .gemini/antigravity config home, the shared convertGeminiToolName/claudeToGeminiTools tool vocabulary, and the 'gemini' hookEvents dialect it declares. GEMINI.md retargeted as Antigravity's context file.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* chore(#1928): backfill changeset PR number (#1996)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* chore(#1928): drop Gemini CLI from issue templates (review nit)
Removes the sunset Gemini CLI runtime from the two GitHub issue-template
runtime lists that the removal PR missed, per @davesienkowski's review nit:
- feature_request.yml: 'Applicable runtimes' checkbox (a user could otherwise
request a feature for a runtime GSD no longer supports)
- bug_report.yml: 'Runtime' dropdown + the stale ~/.gemini/settings.json
retrieval-help line
Leaves the post-removal templates fully consistent with the Antigravity redirect.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Final epic-#1969 batch. Fold 22 issue-named files: the 4 genuine repo-wide invariant
scans (551-eslint-bin-lib-coverage, bug-3054 stale /gsd-next, bug-3810 no-gsd-sdk-runtime-refs,
feat-3593 cli-negative-universal) into a NEW shared repo-invariants.test.cjs; the other 18 as
singletons into their nearest module suite (model-resolver, codex-config, runtime-converters,
security, state-transition, worktree-safety, roadmap-parser, etc.). Verbatim block-scoped
describe wrappers; 334 subtests conserved 1:1.
Host-env pre-check (B2+B6): the 6 CLI folds into GSD_TEST_MODE-setting hosts (model-resolver/
codex-config/runtime-converters) are benign — each origin independently sets GSD_TEST_MODE=1
itself (idempotent), unlike the B6 real-install case.
Regenerates regression-name allowlist (222->213), ratchets file-count allowlist (state 17->16),
makes 7 relocated allow-test-rule exemptions issue-ref-compliant (ADR-456; prunes stale ids).
Repoints 2 tests/ refs in docs/TESTING-SUITES.md. lint:ci green.
Part of epic #1969. Closes#1977.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Fold 94 issue-named command/module regression files into the canonical test file
that owns each subject-under-test, across 52 existing suites (state, config, frontmatter,
roadmap-parser, capability-registry, shell-command-projection-dispatch, plan-phase-drift-guard,
health-validation, runtime-converters, commands, etc.). Verbatim block-scoped describe
wrappers; 881 subtests conserved 1:1. No new test files.
Host-env pre-check (per B2): the only GSD_WORKSTREAM/GSD_PROJECT-touching destinations
(intel, planning-workspace) clear those vars hermetically, so folded CLI tests are safe.
Regenerates regression-name allowlist (222->162), ratchets file-count allowlist across
8 buckets (validate entry removed after dropping <=2), makes 34 relocated allow-test-rule
exemptions issue-ref-compliant (ADR-456; prunes 34 stale ids). Repoints CONTEXT.md +
ADR-0002/443/1235/3524 test-file references. lint:ci green.
Part of epic #1969. Closes#1972.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The back-merge of next carried #1559/#1565 (audit installer compatibility
exports), which removed convertGeminiToolName from bin/install.js's
module.exports. This PR's regression test destructured it from
require('../bin/install.js'), so after the merge it was undefined →
"TypeError: convertGeminiToolName is not a function" across all test lanes.
Rewrite the regression to assert the user-visible behavior through the
still-exported convertClaudeToGeminiAgent: a Skill/SlashCommand/AskUserQuestion
tools entry must not appear in the emitted Gemini frontmatter (the lowercase
fallback would emit invalid tool names that abort agent load — #1394/#3362),
while mapped tools (Read→read_file, WebFetch→web_fetch) survive. Folds the
dropped AskUserQuestion/ask_user coverage into the behavior test and removes
the internal-function import, so the test no longer depends on a private export
#1559 intentionally pruned. The exclusion fix itself is unchanged.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Addresses review: the regression unit test required the tsc build artifact
(gsd-core/bin/lib/runtime-artifact-conversion.cjs) instead of the live install
path. Destructure convertGeminiToolName from the existing ../bin/install.js
import so a stale build can't false-green while the live copy is broken, and
assert the full AskUserQuestion/ask_user exclusion group.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
convertGeminiToolName lowercased any unmapped Claude tool, so Skill and
SlashCommand became an invalid `skill`/`slashcommand` tool name. Gemini CLI
has no such built-in tool, so frontmatter validation failed (tools.N: Invalid
tool name) and aborted the entire agent load — 22 of 34 GSD agents were dead
on Gemini.
Add Skill and SlashCommand to the same `return null` exclusion branch that
already handles AskUserQuestion, in both the canonical src converter and the
hand-maintained bin/install.js copy that runs on the live --gemini install
path. Antigravity reuses this converter (it runs on the Gemini backend) and is
intentionally covered by the same exclusion — it surfaces GSD skills via the
skill surface (SKILL.md), not the agent tools: allowlist — locked by an added
Antigravity regression test.
Co-Authored-By: Claude Opus 4.8 (1M context) <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>
* docs: sync ARCHITECTURE.md command count to 74
commands/gsd/ has 74 .md files; the two count references in
ARCHITECTURE.md still said 73. Fixes the command-count-sync
regression test.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: embed model_overrides in Codex TOML and OpenCode agent files (#2256)
Codex and OpenCode use static agent files (TOML / markdown frontmatter)
rather than inline Task(model=...) parameters, so model_overrides set in
~/.gsd/defaults.json was silently ignored — all subagents fell through to
the runtime's default model.
Fix: at install time, read model_overrides from ~/.gsd/defaults.json and
embed the matching model ID into each agent file:
- Codex: model = "..." field in the agent TOML (generateCodexAgentToml)
- OpenCode: model: ... field in agent frontmatter (convertClaudeToOpencodeFrontmatter)
Also adds readGsdGlobalModelOverrides() helper and passes the result
through installCodexConfig() and the OpenCode agent install loop.
Closes#2256
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat(commands): add gsd:inbox command for GitHub issue/PR triage
inbox.md was created but not committed, causing the command count
to read 73 in git while ARCHITECTURE.md correctly stated 74.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* refactor(tests): standardize to node:assert/strict and t.after() per CONTRIBUTING.md
- Replace require('node:assert') with require('node:assert/strict') across
all 73 test files to enforce strict equality (no type coercion)
- Replace try/finally cleanup blocks with t.after() hooks in core.test.cjs
and hooks-opt-in.test.cjs per the test lifecycle standards
- Utility functions in codex-config and security-scan retain try/finally
as that is appropriate for per-function resource guards, not lifecycle hooks
Closes#1674
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* perf(tests): add --test-concurrency=4 to test runner for parallel file execution
Node.js --test-concurrency controls how many test files run as parallel child
processes. Set to 4 by default, configurable via TEST_CONCURRENCY env var.
Fixes tests at a known level rather than inheriting os.availableParallelism()
which varies across CI environments.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(security): allowlist verify.test.cjs in prompt-injection scanner
tests/verify.test.cjs uses <human>...</human> as GSD phase task-type
XML (meaning "a human should verify this step"), which matches the
scanner's fake-message-boundary pattern for LLM APIs. This is a
false positive — add it to the allowlist alongside the other test files
that legitimately contain injection-adjacent patterns.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Keep Kilo skill path rewrites consistent and avoid rewriting valid string-valued OpenCode permission configs while preserving resolved config-dir handling.
Honor KILO_CONFIG across installer and workflow resolution, preserve Claude agent tool intent as explicit Kilo permissions, and rewrite relative .claude references during Kilo conversion.
* fix: universal agent name replacement for non-Claude runtimes (#766)
Adds neutralizeAgentReferences() shared function that all non-Claude
runtime converters call to replace Claude-specific references:
- 'Claude' (standalone agent name) → 'the agent'
- 'CLAUDE.md' → runtime-specific file (AGENTS.md, GEMINI.md, COPILOT.md)
- Removes 'Do NOT load full AGENTS.md' (harmful for AGENTS.md runtimes)
Preserves: 'Claude Code' (product), 'Claude Opus/Sonnet/Haiku' (models),
'claude-' prefixes (packages, CSS classes).
Integrated into: OpenCode, Gemini, Copilot, Antigravity, and Codex
converters. Claude Code converter unchanged (references are correct).
Includes 7 new tests covering all replacement rules.
Closes#766
* fix: use copilot-instructions.md instead of COPILOT.md for Copilot runtime
Addresses review from Solvely-Colin: Copilot's actual instruction file
is copilot-instructions.md, not COPILOT.md. The neutralizer was mapping
CLAUDE.md -> COPILOT.md which would reference a non-existent file.
- install.js: pass 'copilot-instructions.md' to neutralizeAgentReferences
- runtime-converters.test.cjs: update test to validate correct filename
OpenCode does not recognize 'model: inherit' as a valid model identifier —
it throws ProviderModelNotFoundError when spawning any GSD subagent.
Changes:
- Remove 'model: inherit' injection for OpenCode agents in install.js
- Strip 'model:' field entirely during OpenCode frontmatter conversion
(OpenCode uses its configured default model when no model is specified)
- Update tests to verify model: inherit is NOT added
This fixes all 15 GSD agent definitions and the gsd-set-profile command
for OpenCode users.
Fixes#1156
