Fixes#1692
spawnSync('sleep', ['0.1']) fails silently on Windows (ENOENT),
causing a tight busy-loop during lock contention. Atomics.wait()
provides a cross-platform 100ms blocking wait available in Node 22+.
Internal improvements (refactoring, CI/CD, test quality, dependency
updates, tech debt) had no dedicated template, forcing contributors
to misuse Enhancement or Feature Request forms. This adds a focused
template with appropriate fields and auto-labels (type: chore,
needs-triage).
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* ci: drop Windows runner, add static hardcoded-path detection
Replace the Windows CI runner with a static analysis test that catches
the same class of platform-specific path bugs (C:\, /home/, /Users/,
/tmp/) without requiring an actual Windows machine.
- tests/hardcoded-paths.test.cjs: new static scanner that checks string
literals in all source JS/CJS files for hardcoded platform paths;
runs on Linux/macOS in <100ms and fires on every PR
- .github/workflows/test.yml: remove windows-latest from matrix; switch
macOS smoke-test runner from Node 22 → Node 24 (the declared standard)
- package.json: bump engines.node from >=20.0.0 to >=22.0.0 (Node 20
reached EOL April 2026)
Matrix goes from 4 runners → 3 runners per run:
ubuntu/22 ubuntu/24 macos/24
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(install): apply path replacement in copyCommandsAsClaudeSkills (#1653)
copyCommandsAsClaudeSkills received pathPrefix as a parameter but never
used it — all 51 SKILL.md files kept hardcoded ~/.claude/ paths even on
local (per-project) installs, causing every skill's @-file references
to resolve to a nonexistent global directory.
Add the same three regex replacements that copyCommandsAsCodexSkills
already applies: ~/.claude/ → pathPrefix, $HOME/.claude/ → pathPrefix,
./.claude/ → ./getDirName(runtime)/.
Closes#1653
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Replace the Windows CI runner with a static analysis test that catches
the same class of platform-specific path bugs (C:\, /home/, /Users/,
/tmp/) without requiring an actual Windows machine.
- tests/hardcoded-paths.test.cjs: new static scanner that checks string
literals in all source JS/CJS files for hardcoded platform paths;
runs on Linux/macOS in <100ms and fires on every PR
- .github/workflows/test.yml: remove windows-latest from matrix; switch
macOS smoke-test runner from Node 22 → Node 24 (the declared standard)
- package.json: bump engines.node from >=20.0.0 to >=22.0.0 (Node 20
reached EOL April 2026)
Matrix goes from 4 runners → 3 runners per run:
ubuntu/22 ubuntu/24 macos/24
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>
Replace AI self-identification with env var checks (ANTIGRAVITY_AGENT,
CLAUDE_CODE_ENTRYPOINT) to correctly determine which review CLI to skip.
Fixes incorrect skip behavior when running non-Claude models inside
the Antigravity client.
* chore: ignore .worktrees directory
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(install): remove marketing taglines from runtime selection prompt
Closes#1654
The runtime selection menu had promotional copy appended to some
entries ("open source, the #1 AI coding platform on OpenRouter",
"open source, free models"). Replaced with just the name and path.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* test(kilo): update test to assert marketing tagline is removed
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(tests): use process.execPath so tests pass in shells without node on PATH
Three test patterns called bare `node` via shell, which fails in Claude Code
sessions where `node` is not on PATH:
- helpers.cjs string branch: execSync(`node ...`) → execFileSync(process.execPath)
with a shell-style tokenizer that handles quoted args and inner-quote stripping
- hooks-opt-in.test.cjs: spawnSync('bash', ...) for hooks that call `node`
internally → spawnHook() wrapper that injects process.execPath dir into PATH
- concurrency-safety.test.cjs: exec(`node ...`) for concurrent patch test
→ exec(`"${process.execPath}" ...`)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: resolve#1656 and #1657 — bash hooks missing from dist, SDK install prompt
#1656: Community bash hooks (gsd-session-state.sh, gsd-validate-commit.sh,
gsd-phase-boundary.sh) were never included in HOOKS_TO_COPY in build-hooks.js,
so hooks/dist/ never contained them and the installer could not copy them to
user machines. Fixed by adding the three .sh files to the copy array with
chmod +x preservation and skipping JS syntax validation for shell scripts.
#1657: promptSdk() called installSdk() which ran `npm install -g @gsd-build/sdk`
— a package that does not exist on npm, causing visible errors during interactive
installs. Removed promptSdk(), installSdk(), --sdk flag, and all call sites.
Regression tests in tests/bugs-1656-1657.test.cjs guard both fixes.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: sort runtime list alphabetically after Claude Code
- Claude Code stays pinned at position 1
- Remaining 10 runtimes sorted A-Z: Antigravity(2), Augment(3), Codex(4),
Copilot(5), Cursor(6), Gemini(7), Kilo(8), OpenCode(9), Trae(10), Windsurf(11)
- Updated runtimeMap, allRuntimes, and prompt display in promptRuntime()
- Updated multi-runtime-select, kilo-install, copilot-install tests to match
Also fix#1656 regression test: run build-hooks.js in before() hook so
hooks/dist/ is populated on CI (directory is gitignored; build runs via
prepublishOnly before publish, not during npm ci).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Overhaul CONTRIBUTING.md and all GitHub issue/PR templates to enforce a
structured, approval-gated contribution process that cuts down on drive-by
feature submissions.
Changes:
- CONTRIBUTING.md: add Types of Contributions section defining Fix,
Enhancement, and Feature with escalating requirements and explicit
rejection criteria; add Issue-First Rule section making clear that
enhancements require approved-enhancement and features require
approved-feature label before any code is written; backport gsd-2
testing standards (t.after() per-test cleanup, array join() fixture
pattern, Node 24 as primary CI target, test requirements by change type,
reviewer standards)
- .github/ISSUE_TEMPLATE/enhancement.yml: new template requiring current
vs. proposed behavior, reason/benefit narrative, full scope of changes,
and breaking changes assessment; cannot be clicked through
- .github/ISSUE_TEMPLATE/feature_request.yml: full rewrite requiring solo-
developer problem statement, what is being added, full file-level scope,
user stories, acceptance criteria, maintenance burden assessment, and
alternatives considered; incomplete specs are closed, not revised
- .github/pull_request_template.md: converted from general template to a
routing page directing contributors to the correct typed template;
using the default template for a feature or enhancement is a rejection
reason
- .github/PULL_REQUEST_TEMPLATE/fix.md: new typed template requiring
confirmed-bug label on linked issue and regression test confirmation
- .github/PULL_REQUEST_TEMPLATE/enhancement.md: new typed template with
hard gate on approved-enhancement label and scope confirmation section
- .github/PULL_REQUEST_TEMPLATE/feature.md: new typed template requiring
file inventory, spec compliance checklist from the issue, and scope
confirmation that nothing beyond the approved spec was added
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* chore: ignore .worktrees directory
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(install): remove marketing taglines from runtime selection prompt
Closes#1654
The runtime selection menu had promotional copy appended to some
entries ("open source, the #1 AI coding platform on OpenRouter",
"open source, free models"). Replaced with just the name and path.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* test(kilo): update test to assert marketing tagline is removed
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
The discord.gg/gsd vanity link was lost due to a drop in server boosts.
Updated all references to the permanent invite link discord.gg/mYgfVNfA2r
across READMEs, issue templates, install script, and join-discord command.
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat: add Trae runtime install support
- Add Trae as a supported runtime in bin/install.js
- Update README and ARCHITECTURE documentation for Trae support
- Add trae-install.test.cjs test file
- Update multi-runtime-select tests for Trae compatibility
* feat(trae): add TRAE_CONFIG_DIR environment variable support
Add support for TRAE_CONFIG_DIR environment variable as an additional way to specify the config directory for Trae runtime, following the same precedence pattern as other runtimes.
* fix(trae): improve slash command conversion and subagent type mapping
Update the slash command regex pattern to properly match and convert command names. Change subagent type mapping from "general-purpose" to "general_purpose_task" to match Trae's conventions. Also add comprehensive tests for Trae uninstall cleanup behavior.
* docs: add Trae and Windsurf to supported runtimes in translations
Update Korean, Japanese, and Portuguese README files to include Trae and Windsurf as supported runtimes in the documentation. Add installation and uninstallation instructions for Trae.
* fix: update runtime selection logic and path replacements
- Change 'All' shortcut from option 11 to 12 to accommodate new runtime
- Update path replacement regex to handle gsd- prefix more precisely
- Adjust test cases to reflect new runtime selection numbering
- Add configDir to trae install options for proper path resolution
* test(trae-install): add tests for getGlobalDir function
Add test cases to verify behavior of getGlobalDir function with different configurations:
- Default directory when no env var or explicit dir is provided
- Explicit directory takes priority
- Respects TRAE_CONFIG_DIR env var
- Priority of explicit dir over env var
- Compatibility with other runtimes
* feat(state): add programmatic gates for STATE.md consistency
Adds four enforcement gates to prevent STATE.md drift:
- `state validate`: detects drift between STATE.md and filesystem
- `state sync`: reconstructs STATE.md from actual project state
- `state planned-phase`: records state after plan-phase completes
- Performance Metrics update in `phase complete`
Also fixes ghost `state update-position` command reference in
execute-phase.md (command didn't exist in CLI dispatcher).
Closes#1627
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(state): By Phase table regex ate next section when table body was empty
The lazy [\s\S]*? with a $ lookahead in byPhaseTablePattern would
match past blank lines and capture the next ## section header as table
body when no data rows existed. Replaced with a precise row-matching
pattern ((?:[ \t]*\|[^\n]*\n)*) that only captures pipe-delimited
lines. Added regression assertion to verify row placement.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Allows users to run autonomous mode up to a specific phase number.
After the target phase completes, execution halts instead of advancing.
Closes#1644
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat(i18n): add response_language config for cross-phase language consistency
Adds `response_language` config key that propagates through all init
outputs via withProjectRoot(). Workflows read this field and instruct
agents to present user-facing questions in the configured language,
solving the problem of language preference resetting at phase boundaries.
Usage: gsd-tools config-set response_language "Portuguese"
Closes#1399
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* test(security): allowlist discuss-phase.md for size threshold
discuss-phase.md legitimately exceeds 50K chars due to power mode
and i18n directives — not prompt stuffing.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(hooks): add read-before-edit guidance for non-Claude runtimes
When models that don't natively enforce read-before-edit hit the guard,
the error message now includes explicit instruction to Read first.
This prevents infinite retry loops that burn through usage.
Closes#1628
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(build): register gsd-read-guard.js in HOOKS_TO_COPY and harden tests
The hook was missing from scripts/build-hooks.js, so global installs
would never receive the hook file in hooks/dist/. Also adds tests for
build registration, install uninstall list, and non-string file_path.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* fix: replace /gsd: command format with /gsd- skill format in all suggestions
All next-step suggestions shown to users were still using the old colon
format (/gsd:xxx) which cannot be copy-pasted as skills. Migrated all
occurrences across agents/, commands/, get-shit-done/, docs/, README files,
bin/install.js (hardcoded defaults for claude runtime), and
get-shit-done/bin/lib/*.cjs (generate-claude-md templates and error messages).
Updated tests to assert new hyphen format instead of old colon format.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: migrate remaining /gsd: format to /gsd- in hooks, workflows, and sdk
Addresses remaining user-facing occurrences missed in the initial migration:
- hooks/: fix 4 user-facing messages (pause-work, update, fast, quick)
and 2 comments in gsd-workflow-guard.js
- get-shit-done/workflows/: fix 21 Skill() literal calls that Claude
executes directly (installer does not transform workflow content)
- sdk/prompt-sanitizer.ts: update regex to strip /gsd- format in addition
to legacy /gsd: format; update JSDoc comment
- tests/: update autonomous-ui-steps, prompt-sanitizer to assert new format
Note: commands/gsd/*.md frontmatter (name: gsd:xxx) intentionally unchanged
— installer derives skillName from directory path, not the name field.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(plan-phase): preserve --chain flag in auto-advance sync and handle ui-phase gate in chain mode
Bug 1: step 15 sync-flag check only guarded against --auto, causing
_auto_chain_active to be cleared when plan-phase is invoked without
--auto in ARGUMENTS even though a --chain pipeline was active. Added
--chain to the guard condition, matching discuss-phase behaviour.
Bug 2: UI Design Contract gate (step 5.6) always exited the workflow
when UI-SPEC was missing, breaking the discuss --chain pipeline
silently. When _auto_chain_active is true, the gate now auto-invokes
gsd-ui-phase --auto via Skill() and continues to step 6 without
prompting. Manual invocations retain the existing AskUserQuestion flow.
* fix: remove <sub>/clear</sub> pattern and duplicate old-format command in discuss-phase.md
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
The workstreams command only delegates to `node "$GSD_TOOLS"` via Bash
and formats JSON output. No Write calls appear anywhere in the command body.
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The gsd-verifier was reporting false-positive gaps for items explicitly
scheduled in later phases of the milestone (e.g., reporting a Phase 5
item as a gap during Phase 1 verification). This adds Step 9b to
cross-reference gaps against later phases using `roadmap analyze` and
move matched items to a `deferred` list that does not affect status.
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(phase-resolution): use exact token matching instead of prefix matches
Closes#1635
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(phase-resolution): add case-insensitive flag to project-code strip regex
The strip regex in phaseTokenMatches lacked the `i` flag, so lowercase
project-code prefixes (e.g. `ck-01-name`) were not stripped during the
fallback comparison. This made `phaseTokenMatches('ck-01-name', '01')`
return false when it should return true.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* fix(roadmap): fall back to full ROADMAP.md for backlog and planned phases
Closes#1634
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(roadmap): prevent checklist-only match from blocking full header fallback
When the current milestone had a checklist reference to a phase (e.g.
`- [ ] **Phase 50: Cleanup**`) but the full `### Phase 50:` header
existed in a different milestone, the malformed_roadmap result from the
first searchPhaseInContent call short-circuited the `||` operator and
prevented the fallback to the full roadmap content.
Now a malformed_roadmap result is deferred so the full content search
can find the actual header match.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Address review feedback: LLMs cannot enforce timing between tool calls.
Replace "stagger by ~2 seconds" with concrete, enforceable pattern:
dispatch each Task() one at a time with run_in_background: true. The
round-trip latency of each tool call provides natural spacing for
worktree creation, while agents still run in parallel once created.
Explicitly warn against sending multiple Task() calls in a single
message (which causes simultaneous git worktree add).
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(config): warn on unrecognized keys in config.json instead of silent drop (#1535)
loadConfig() silently ignores any config.json keys not in its known
set, leaving users confused when their settings have no effect. Add a
stderr warning listing unrecognized top-level keys so the problem
surfaces immediately.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(config): derive known keys from VALID_CONFIG_KEYS instead of hardcoded set
Address review feedback: replace hardcoded KNOWN_CONFIG_KEYS with
programmatic derivation from config-set's VALID_CONFIG_KEYS (single
source of truth). New config keys added to config-set are automatically
recognized by loadConfig without a separate update. Add sync test
verifying all VALID_CONFIG_KEYS entries pass without warning.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(hooks): use semver comparison for update check instead of inequality
gsd-check-update.js used `installed !== latest` to determine if an
update is available. This incorrectly flags an update when the installed
version is NEWER than npm (e.g., installing from git ahead of a release).
Replace with proper semver comparison: update_available is true only
when the npm version is strictly newer than the installed version.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(hooks): use semver comparison for update check instead of inequality
gsd-check-update.js used `installed !== latest` to determine if an
update is available. This incorrectly flags an update when the installed
version is NEWER than npm (e.g., installing from git ahead of a release).
Fix:
- Move isNewer() inside the spawned child process (was in parent scope,
causing ReferenceError in production)
- Strip pre-release suffixes before Number() to avoid NaN
- Apply same semver comparison to stale hooks check (line 95)
update_available is now true only when npm version is strictly newer.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* test: add semver comparison tests for gsd-check-update isNewer()
12 test cases covering: major/minor/patch comparison, equal versions,
installed-ahead-of-npm scenario, pre-release suffix stripping,
null/empty handling, two-segment versions.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* docs: explain why isNewer is duplicated in test file
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The Next Up blocks showed the main command first, then /clear as a <sub>
footnote saying 'first'. Users would copy-paste the command before noticing
they should have cleared first. This restructures all 41 instances across
19 workflow files and 2 reference files so /clear appears before the
command as a clear sequential instruction.
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The --chain flag was not checked in plan-phase's auto-advance guard,
causing the ephemeral _auto_chain_active config to be cleared when
discuss-phase chained into plan-phase. This broke the discuss→plan→
execute auto-advance pipeline, requiring manual intervention at each
transition.
Two fixes applied to plan-phase.md step 15:
- Sync-flag guard now checks for both --auto AND --chain before
clearing _auto_chain_active (matching discuss-phase's pattern)
- Added chain flag persistence (config-set _auto_chain_active true)
before auto-advancing, handling direct invocation without prior
discuss-phase
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Adds docs/manual-update.md with step-by-step procedure to install/update
GSD directly from source when npx is unavailable, including runtime flag
table and notes on what the installer preserves.
Adds a [!WARNING] notice at the top of README.md linking to the doc with
the one-liner install command.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* chore: add v1.31.0 npm known-issue notice to issue template config
Adds a top-priority contact link to the issue template chooser so users
are redirected to the Discussions announcement before opening a duplicate
issue about v1.31.0 not being on npm.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(phase-runner): add research gate to block planning on unresolved open questions (#1602)
Plan-phase could proceed to planning even when RESEARCH.md had unresolved
open questions in its ## Open Questions section. This caused agents to
plan and execute with fundamental design decisions still undecided.
- Add `research-gate.ts` with pure `checkResearchGate()` function that
parses RESEARCH.md for unresolved open questions
- Integrate gate into PhaseRunner between research (step 2) and plan
(step 3) using existing `invokeBlockerCallback` pattern
- Add Dimension 11 (Research Resolution) to gsd-plan-checker.md agent
- Gate passes when: no Open Questions section, section has (RESOLVED)
suffix, all individual questions marked RESOLVED, or section is empty
- Gate fires `onBlockerDecision` callback with PhaseStepType.Research
and lists the unresolved questions in the error message
- Auto-approves (skip) when no callback registered (headless mode)
- 18 new tests: 13 unit tests for checkResearchGate, 5 integration
tests for PhaseRunner research gate behavior
Closes#1602
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* chore: add v1.31.0 npm known-issue notice to issue template config
Adds a top-priority contact link to the issue template chooser so users
are redirected to the Discussions announcement before opening a duplicate
issue about v1.31.0 not being on npm.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat(sdk): reduce context prompt sizes with truncation and cache-friendly ordering (#1614)
- Reorder prompt assembly in PromptFactory to place stable content (role,
workflow, phase instructions) before variable content (.planning/ files),
enabling Anthropic prompt caching at 0.1x input cost on cache hits
- Add markdown-aware truncation for oversized context files (headings +
first paragraphs preserved, rest omitted with line counts)
- Add ROADMAP.md milestone extraction to inject only the current milestone
instead of the full roadmap
- Export truncation utilities from SDK public API
- 60 new + updated tests covering truncation, milestone extraction,
cache-friendly ordering, and ContextEngine integration
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* test: add failing tests for planner modular decomposition
- Assert gsd-planner.md is under 45K after extraction (currently ~50K)
- Assert three reference files exist (gap-closure, revision, reviews)
- Assert planner contains reference pointers to each extracted file
- Assert each reference file contains key content from the original mode
* feat(agents): modular decomposition of gsd-planner.md to fix 50K char limit
Extracts three non-standard mode sections from gsd-planner.md into dedicated
reference files loaded on-demand, and calibrates the security scanner to use
a per-file-type threshold (100K for agent source files vs 50K for user input).
Structural changes:
- Extract <gap_closure_mode> → get-shit-done/references/planner-gap-closure.md
- Extract <revision_mode> → get-shit-done/references/planner-revision.md
- Extract <reviews_mode> → get-shit-done/references/planner-reviews.md
- Add <load_mode_context> step in execution_flow (conditional lazy loading)
- gsd-planner.md: 50,112 → 45,352 chars (well under new 45K target)
Security scanner fix:
- Split agent file check: injection patterns (unchanged) + separate 100K size limit
- The 50K strict-mode limit was designed for user-supplied input, not trusted source files
- Agent files still have a size guard to catch accidental bloat
Partially addresses #1495
* fix(tests): normalize CRLF before measuring planner file size
Windows git checkouts add \r per line, inflating String.length by ~1150 chars
for a 1,400-line file. The 45K threshold test failed on windows-latest because
45,352 chars (Linux) became 46,507 chars (Windows). Apply the same CRLF
normalization pattern used in tests/reachability-check.test.cjs.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
- Add severity column (blocking/advisory) to Critical Anti-Patterns table
in .continue-here.md template in pause-work.md
- Document that blocking anti-patterns trigger a mandatory understanding
check when discuss-phase or execute-phase resumes work
- Add check_blocking_antipatterns step to discuss-phase.md: parses
.continue-here.md for blocking rows and requires three-question
understanding demonstration before proceeding
- Add identical enforcement step to execute-phase.md
- Tests: tests/anti-pattern-enforcement.test.cjs (12 assertions, all pass)
Closes#1491
* test(#1488): add failing tests for methodology artifact type
- Test artifact-types.md exists with methodology type documented
- Test shape, lifecycle, location fields are present
- Test discuss-phase-assumptions.md consumes METHODOLOGY.md
- Test pause-work.md Required Reading includes METHODOLOGY.md
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat(#1488): add methodology artifact type with consumption mechanisms
- Create get-shit-done/references/artifact-types.md documenting all GSD
artifact types including the new methodology type
- Methodology artifact: standing reference of named interpretive lenses,
located at .planning/METHODOLOGY.md, lifecycle Created → Active → Superseded
- Add load_methodology step to discuss-phase-assumptions.md so active lenses
are read before assumption analysis and applied to surfaced findings
- Add METHODOLOGY.md to pause-work.md Required Reading template so resuming
agents inherit the project's analytical orientation
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat(planner): add reachability_check step to prevent unreachable code
Closes#1495
* fix: trim gsd-planner.md below 50000-char limit after rebase
The reachability_check addition pushed the file to 50,275 chars when
merged with the assign_waves additions from #1600. Condense both sections
while preserving all logic; file is now 49,859 chars.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(security): normalize CRLF before prompt-stuffing length check
On Windows, git checks out files with CRLF line endings. JavaScript's
String.length counts \r characters, so a 49,859-byte file measures as
51,126 chars on Windows — falsely tripping the 50,000-char security
scanner. Normalize CRLF → LF before measuring in security.cjs and in
the reachability-check test.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: trim gsd-planner.md to stay under 50000-char limit after merge with main
After rebasing onto main (which added mcp_tool_usage block), combined content
reached 50031 chars. Remove suggested log format from assign_waves rule to
bring file to 49972 chars, well under the 50000-char security scanner limit.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(agents): explicitly instruct agents to use available MCP tools
GSD executor and planner agents were not mentioning available MCP servers
in their task instructions, causing subagents to skip Context7 and other
configured MCP tools even when available.
Closes#1388
* fix(tests): make copilot executor tool assertion dynamic
Hardcoded tools: ['read', 'edit', 'execute', 'search'] assertion broke
when mcp__context7__* was added to gsd-executor.md frontmatter. Replace
with per-tool presence checks so adding new tools never breaks the test.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Adds a .clinerules file at the repo root so Cline (VS Code AI extension)
understands GSD's architecture, coding standards, and workflow constraints.
Closes#1509
When Playwright-MCP is available in the session, GSD UI verification
steps can be automated via screenshot comparison instead of manual
checkbox review. Falls back to manual flow when Playwright is not
configured.
Closes#1420
Analyzes ROADMAP.md phases for file overlap and semantic dependencies,
then suggests Depends on entries before running /gsd:manager. Complements
the files_modified overlap detection added in the executor (PR #1600).
Closes#1530
* ci: re-run CI with Windows pointer lifecycle fix in main
* fix: orchestrator owns STATE.md/ROADMAP.md writes in parallel worktree mode (#1571)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
