* fix: parseMustHavesBlock quoted strings + gsd state complete-phase
Bug #2734: parseMustHavesBlock dropped quoted truths containing ':' because
fully-quoted strings like `"App-side UUIDv4: generated locally"` fell into
the kv-parse branch, the regex failed (value starts with '"'), and current
stayed as empty {}. Fix: detect fully-quoted strings before the ':' check
and extract them directly. Two regression tests added to frontmatter.test.cjs.
Bug #2735: `gsd state complete-phase` subcommand was missing — unknown
subcommands fell through to cmdStateLoad. Added cmdStateCompletePhase to
state.cjs (updates Status, Last Activity, and Current Position to COMPLETE),
exported it, and wired it into the case 'state': dispatch in gsd-tools.cjs.
Closes#2734Closes#2735
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(state): unknown subcommand returns explicit error instead of silent fallthrough
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Closes#2612
- Add gemini, qwen, opencode, and copilot entries to RUNTIME_PROFILE_MAP in core.cjs
- Group B runtimes (kilo, cline, cursor, windsurf, augment, trae, codebuddy, antigravity) intentionally have no built-in map and fall through to the existing unknown-runtime fallback
- Add 40 new tests to tests/issue-2517-runtime-aware-profiles.test.cjs covering each new runtime's three tiers, Group B fall-through, and partial override merge semantics
- Add Section 7 "Runtime Model Tiers" to settings-advanced.md with interactive UI to view and override built-in tier defaults per runtime
- Update docs/CONFIGURATION.md built-in tier table to include all four new runtimes
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Adds a new slash command that lets developers modify any field of an
existing phase in ROADMAP.md without affecting phase number or position.
- commands/gsd/edit-phase.md: command file with --force flag support
- get-shit-done/workflows/edit-phase.md: full workflow with status guard,
depends_on validation, diff+confirmation, and STATE.md update
- tests/edit-phase.test.cjs: 32 tests covering all acceptance criteria
- docs/INVENTORY.md, INVENTORY-MANIFEST.json, COMMANDS.md: registered
Closes#2617
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Adds two tests to review-model-config.test.cjs:
- isValidConfigKey accepts review.models.claude (schema validation)
- round-trip: config-set then config-get for review.models.claude
The dynamic key pattern (^review\.models\.[a-zA-Z0-9_-]+$), the workflow
model-read logic in review.md, and the CONFIGURATION.md docs were already
in place. Only the claude-specific test coverage was missing.
Closes#2688
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Codex 0.124.0 changed the required config.toml hooks format from the old
map-style ([hooks.shell]) to array-of-tables ([[hooks]]). Old GSD installs
that wrote the legacy format now cause a startup parse error on upgrade.
Add migrateCodexHooksMapFormat() which detects non-array [hooks] and
[hooks.TYPE] sections and rewrites them to [[hooks]] entries with an
injected type = "TYPE" key. The migration runs at the start of every Codex
install so affected configs self-heal on the next `gsd install --codex`.
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(config): bump MODEL_ALIAS_MAP and RUNTIME_PROFILE_MAP to claude-opus-4-7
Opus 4.7 shipped Q1 2026 but MODEL_ALIAS_MAP and RUNTIME_PROFILE_MAP.claude.opus
were still pinned to claude-opus-4-6. Users with resolve_model_ids: true received
stale model IDs in logs and agent-tool calls.
Also adds a resolve_model_ids: true test suite — this path had zero coverage,
which is why the stale ID survived undetected.
Closes#2712
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* refactor(config): derive RUNTIME_PROFILE_MAP.claude from MODEL_ALIAS_MAP (coderabbit)
RUNTIME_PROFILE_MAP.claude was duplicating model IDs that MODEL_ALIAS_MAP
already owns. Future model bumps now only require updating MODEL_ALIAS_MAP.
Also fixes stale test assertion (claude-opus-4-6 → claude-opus-4-7).
* fix(tests): update stale claude-opus-4-6 refs to claude-opus-4-7; DRY: derive RUNTIME_PROFILE_MAP.claude from MODEL_ALIAS_MAP
- Update 3 hardcoded `claude-opus-4-6` assertions in tests/issue-2517-runtime-aware-profiles.test.cjs to `claude-opus-4-7`
- Update comment on line 128 that referenced the old model ID
- Replace manual per-tier expansion of RUNTIME_PROFILE_MAP.claude with Object.fromEntries so future alias bumps only require updating MODEL_ALIAS_MAP
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
- Success path: add explicit python3Calls.length === 0 assertion so "no
fallback" is stated directly rather than implied by calls.length === 1
- Fallback path: add explicit calls[0].cmd === 'graphify' assertion so
"graphify precedes python3" is verified by name, not just argument
- Add _deepMergeConfig() with correct null-override semantics
- loadConfig() reads root config.json when GSD_WORKSTREAM is set, then
deep-merges with workstream config (workstream wins on conflict)
- Workstream without config.json falls back to root config entirely
- Migrations and disk writes operate on fileData (on-disk content) only,
never on the merged result, to prevent workstream pollution
- Fixes null-override bug from PR #2717: explicit null in workstream now
correctly overrides root value instead of falling back to root
- Tests: inherit root model_overrides, workstream override, nested
workflow.* deep merge, explicit null override, missing workstream config
Closes#2714
graphify . --update was removed in favor of graphify update . in v0.4.x.
Also improves version detection to try `graphify --version` before
falling back to python3 importlib query.
Closes#2732
* fix(#2722): forensics gh commands pin --repo gsd-build/get-shit-done
gh issue create and gh label list both defaulted to the repo inferred
from $PWD, causing issues to be submitted to the user's current project
instead of this repo. Added --repo gsd-build/get-shit-done to both
commands. Added two regression tests covering both gh calls.
Closes#2722
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(#2723): scope forensics tests to specific gh commands, not whole file
CodeRabbit found that the gh issue create test searched the whole
workflow file, so it would pass even if gh issue create lacked --repo
(because gh label list already contains the repo string elsewhere).
Also replaced the brittle 200-char slice in the label-list test with
a regex. Both tests now use assert.match() with command-scoped regexes.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
377a6d2 deleted sdk/prompts/agents/ and sdk/prompts/workflows/ (13 files)
but did not update 3 test files that reference them, causing ENOENT
failures on every CI run (main and all PRs) since that commit.
Removed:
- sdk/prompts/agents variants describe block (enh-2427-sycophancy-hardening)
- PLAN_PHASE_SDK_PATH constant and headless plan-phase test (post-planning-gaps-2493)
- sdk/prompts/workflows/verify-phase.md describe block (verifier-deferred-items)
The underlying behaviour is covered by the existing main agent/workflow
tests; the SDK variant tests are moot now that the SDK loads installed
files instead of bundled stripped-down copies.
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat(#2500): enrich gsd-codebase-mapper arch-focus ARCHITECTURE.md template
The codebase mapper's arch-focus template was a sparse structural inventory.
After major refactors, the research/ARCHITECTURE.md (created at /gsd-new-project
and never refreshable) went stale while the refreshable codebase version lacked
the visual richness that makes architecture docs useful for planning.
Add to the ARCHITECTURE.md template:
- <!-- refreshed: {date} --> marker at the top (maintainer request)
- ASCII system overview diagram with component boxes and flow arrows
- Component responsibility table (Component / Responsibility / File)
- Primary request path traces with numbered steps and code references
- Architectural constraints section (threading, global state, circular imports)
- Anti-patterns section with codebase-specific patterns and correct alternatives
All existing sections (Pattern Overview, Layers, Key Abstractions, Entry Points,
Error Handling, Cross-Cutting Concerns) are preserved.
7 new tests in tests/enh-2500-codebase-mapper-arch-rich-format.test.cjs verify
each required section is present in the deployed template.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(#2500): resolve CodeRabbit review findings
- Add 'text' language tag to bare ASCII diagram fenced block (markdownlint MD040)
- Tighten data flow test: require '### Primary Request Path' heading, 3+
numbered steps, and file:line reference pattern — prevents loose-match
false positives
- Tighten constraints test: require '## Architectural Constraints' heading
AND Threading / Global state / Circular imports tokens — prevents broad
keyword matches masking regressions
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat(#2306): plan-review-convergence v2 — CYCLE_SUMMARY contract, config gate, local model reviewers
Fixes the false-stall detection bug in the plan→review→replan convergence
loop. REVIEWS.md accumulates history across cycles so raw grep inflated
HIGH counts; HIGH count now comes from a per-cycle CYCLE_SUMMARY contract
emitted in the review agent's return message.
Key changes:
- workflow.plan_review_convergence config gate (disabled by default, same
pattern as workflow.code_review / workflow.nyquist_validation)
- Review agent prompt defines CYCLE_SUMMARY: current_high=<N> contract with
PARTIALLY RESOLVED / FULLY RESOLVED counting rules
- Orchestrator aborts on absent/malformed CYCLE_SUMMARY (distinguishes both)
- Warns when HIGH_COUNT > 0 but ## Current HIGH Concerns section is missing
- Stall detection and --ws forwarding preserved and tested
- Local model reviewers: --ollama, --lm-studio, --llama-cpp flags added to
convergence workflow and review workflow; all three use OpenAI-compatible
/v1/chat/completions endpoint with jq --rawfile for safe JSON encoding
- review.ollama_host / review.lm_studio_host / review.llama_cpp_host config
keys registered and documented (default to localhost:11434/1234/8080)
- review.models.ollama / .lm_studio / .llama_cpp model-name config support
- 58 tests (up from 29 in PR #2339), all passing
Closes#2306Closes#2339
Co-authored-by: Tom Boucher <trekkie@nomorestars.com>
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(ci): sync sdk/src/query/config-schema.ts with CJS schema (#2306)
Add workflow.plan_review_convergence, review.ollama_host,
review.lm_studio_host, and review.llama_cpp_host to the SDK-side
TypeScript mirror — required by the CJS↔SDK parity test (#2653).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(#2306): resolve CodeRabbit review findings
- Anchor HIGH_COUNT extraction with head -1 to prevent multi-match when
agent return message contains multiple CYCLE_SUMMARY lines (e.g. quoted
back from prompt context)
- Replace hardcoded reviewers list in REVIEWS.md frontmatter template with
runtime-derived placeholder — the static list did not reflect which
reviewers were actually invoked
- Broaden workflow.plan_review_convergence docs to include local reviewers
(Ollama, LM Studio, llama.cpp) alongside cloud reviewers
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(ci): restore reviewers frontmatter list with runtime note
The cursor-reviewer.test.cjs (and equivalent per-reviewer tests) assert
that each supported reviewer appears on the reviewers: line — these are
wiring tests that catch when a new reviewer is added to invocation but
not to the REVIEWS.md template. Replacing the list with a placeholder
broke those tests.
Restore the full static list and add an inline comment clarifying that
the actual committed frontmatter should be filtered to only the reviewers
invoked that run — satisfying both the per-reviewer tests and the
CodeRabbit correctness note.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Fixes#2698 — The two separate LF/CRLF .replace() calls in the Codex hooks
migration could not handle mixed line endings (e.g. header in LF, body in
CRLF), leaving stale gsd-update-check blocks after reinstall. Consolidated to
a single \r?\n-aware regex with gm flags that handles LF, CRLF, and mixed
content in one pass.
Fixes#2678 — installSdkIfNeeded() called process.exit(1) unconditionally when
sdk/dist/cli.js was missing, even during --local installs where users cannot
write to global node_modules. Added isLocal option: when true, prints a warning
and returns instead of exiting.
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(#2686): review-fix agent now uses git worktree for isolation
The gsd-code-fixer agent operated directly against the main working tree,
racing any concurrent foreground session for HEAD, the index, and on-disk
files. Added a setup_worktree step (git worktree add /tmp/sv-N-reviewfix
HEAD) as the first action before any file operations, with unconditional
git worktree remove cleanup on exit. Mirrors the pattern used by all other
GSD per-issue agents.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(#2686): address CodeRabbit review — mktemp unique path, branch-aware worktree, tighten test assertions
- Use mktemp -d for unique worktree path (prevents concurrent-run collision)
- Resolve branch via git branch --show-current before worktree add (prevents detached HEAD)
- Error-and-exit on worktree add failure instead of force-removing shared path
- Test: use .exec().index for checkout position (not indexOf on match string)
- Test: match gsd-sdk query commit as well as git commit for ordering assertion
- Test: tighten /tmp path assertion to require actual /tmp/sv- assignment
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* test(#2692): add behavioral --wave N test, annotate source-text assertions
Adds two behavioral tests for wave filtering via phase-plan-index:
- Verifies plans with wave frontmatter are correctly grouped by wave number
- Verifies plans with no wave field default to wave 1
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(#2684,#2676): milestone.complete version validation + parallel milestone phase routing
#2684: Confirms milestone.complete correctly validates and uses its version
argument end-to-end. The inline archive path in milestoneComplete already
forwarded version correctly; regression tests lock in that contract.
#2676: phase.complete applied getMilestonePhaseFilter unconditionally, using
STATE.md's primary milestone to scope the candidate set. When the completed
phase belongs to a parallel (secondary) milestone, the filter excluded all
phases from that milestone, leaving an empty candidate set and incorrectly
returning is_last_phase: true / next_phase: null.
Fix: before applying the milestone filter in Step E, check whether the
completed phase itself appears in the filtered set. If not, skip the filter
for both the directory scan and the ROADMAP.md fallback so phases from the
secondary milestone remain visible for next-phase detection.
Closes#2684Closes#2676
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
VALID_PROFILES was derived solely from Object.keys(MODEL_PROFILES['gsd-planner']),
which only contained the named tiers (quality/balanced/budget/adaptive). The
cmdConfigSetModelProfile validator rejected 'inherit' even though the runtime has
supported it since #1829. Fix: append 'inherit' to VALID_PROFILES and handle it
in getAgentToModelMapForProfile so the agent→model table shows 'inherit' instead
of undefined.
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Adds two behavioral tests for wave filtering via phase-plan-index:
- Verifies plans with wave frontmatter are correctly grouped by wave number
- Verifies plans with no wave field default to wave 1
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* docs(test-standards): enforce no-source-grep rule with CI linter + update CONTRIBUTING.md
Adds scripts/lint-no-source-grep.cjs — a static linter that detects readFileSync
on .cjs source files in tests without an allow-test-rule annotation. Wires it
into CI as a new lint-tests job in test.yml and as npm run lint:tests.
Resolves all 9 existing violations across the test suite:
- Rewrites workspace routing tests (3) as behavioral runGsdTools calls that
verify each command is router-recognized (exit != "Unknown init workflow")
- Adds allow-test-rule annotations with explanatory comments to 7 legitimate
structural tests: architectural invariants (locking, orphan-worktree),
structural regression guards (milestone-regex-global), docs-parity
(config-field-docs), integration-test-input (copilot-install), and
structural-implementation-guards (bug-1891, discuss-mode)
Updates CONTRIBUTING.md Testing Standards section with:
- "Prohibited: Source-Grep Tests" section with the before/after pattern,
root cause analysis of why it breaks (commit 990c3e64), and CI reference
- allow-test-rule exemption table (6 recognized categories with when-to-use)
- "CI Test Quality Checks" table showing lint-tests job and local run command
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: resolve CodeRabbit findings on PR #2700
- CONTRIBUTING.md: "four recognized categories" → "six" (table has 6 rows)
- workspace.test.cjs: use positional args in routing tests (no --name flag)
- lint-no-source-grep.cjs: add source-dir guard to READ_WITH_INLINE_CJS_RE
(mirrors CJS_PATH_CONST_RE's protection against false positives on temp files)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(lint): tighten allow-test-rule and add recursive test discovery
- ALLOW_ANNOTATION now requires at least one non-whitespace char after the
colon so bare '// allow-test-rule:' cannot bypass the lint gate
- findTestFiles() recurses into subdirectories so nested *.test.cjs files
are covered if the tests/ tree ever grows subdirs
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
All workflow, command, reference, template, and tool-output files that
surfaced /gsd:<cmd> as a user-typed slash command have been updated to
use /gsd-<cmd>, matching the Claude Code skill directory name.
Closes#2697
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* test: destroy 9 config-schema.cjs/core.cjs source-grep tests, add behavioral config-set tests (#2691, #2693)
Replace source-grep theater with config-set behavioral tests:
- execute-phase-wave: config-set workflow.use_worktrees replaces VALID_CONFIG_KEYS grep
- inline-plan-threshold: delete redundant source-grep (behavioral test at L36 already covered it)
- plan-bounce: config-set for plan_bounce / plan_bounce_script / plan_bounce_passes replaces 3 key-presence greps
- code-review: config-set for code_review / code_review_depth replaces 2 greps; removes CONFIG_PATH constant
- thinking-partner: config-set features.thinking_partner replaces two greps (config-schema.cjs AND core.cjs)
Behavioral tests survive refactors (no path constants, no file reads). The config-schema.cjs →
core.cjs migration commit 990c3e64 happened because these tests groped source paths.
Add allow-test-rule: source-text-is-the-product annotations to legitimate product-content tests:
autonomous-allowed-tools, agent-frontmatter, agent-skills-awareness, bug-2334, bug-2346,
execute-phase-wave (MD reads), plan-bounce (workflow reads). Annotations explain WHY text
inspection is the right level of testing for AI instruction files.
Closes#2691Closes#2693
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* test: address CodeRabbit findings on #2696
- agent-frontmatter.test.cjs: move allow-test-rule annotation from block comment
to standalone // line comment so rule scanners can detect it
- thinking-partner.test.cjs: strengthen config-set test with config-get read-back
assertion to verify the value was persisted, not just accepted (exit 0)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* test: tighten thinking_partner config assertion per CodeRabbit (#2696)
Replace config-get output substring check (includes('true') false-positive
risk) with a direct JSON read of .planning/config.json, asserting the
exact persisted value via strictEqual. This also validates the config file
was created, catching silent key-acceptance without persistence.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(#2661): unconditional plan-checkbox sync in execute-plan
Checkpoint A in execute-plan.md was wrapped in a "Skip in parallel mode"
guard that also short-circuited the parallelization-without-worktrees
case. With `parallelization: true, use_worktrees: false`, only
Checkpoint C (phase.complete) then remained, and any interruption
between the final SUMMARY write and phase complete left ROADMAP.md
plan checkboxes stale.
Remove the guard: `roadmap update-plan-progress` is idempotent and
atomically serialized via readModifyWriteRoadmapMd's lockfile, so
concurrent invocations from parallel plans converge safely.
Checkpoint B (worktree-merge post-step) and Checkpoint C
(phase.complete) become redundant after A is unconditional; their
removal is deferred to a follow-up per the RCA.
Closes#2661
* fix(#2661): gate ROADMAP sync on use_worktrees=false to preserve single-writer contract
Adversarial review of PR #2682 found that unconditionally removing the
IS_WORKTREE guard violates the single-writer contract for shared
ROADMAP.md established by commit dcb50396 (PR #1486). The lockfile only
serializes within a single working tree; separate worktrees have
separate ROADMAP.md files that diverge.
Restore the worktree guard but document its intent explicitly: the
in-handler sync runs only when use_worktrees=false (the actual #2661
reproducer). Worktree mode relies on the orchestrator's post-merge
update at execute-phase.md lines 815-834, which is the documented
single-writer for shared tracking files.
Update tests to assert both branches of the gate:
- use_worktrees: false mode runs the sync (the #2661 case)
- use_worktrees: true mode does NOT run the in-handler sync
- handler-level idempotence and lockfile contention tests retained,
scope clarified to within-tree concurrency only
* fix(#2660): capture prose after label in extractOneLinerFromBody
The regex `\*\*([^*]+)\*\*` matched the first bold span, so for the new
SUMMARY template `**One-liner:** Real prose here.` it captured the label
`One-liner:` instead of the prose. MILESTONES.md then wrote bullets like
`- One-liner:` with no content.
Handle both template forms:
- Labeled: `**One-liner:** prose` → prose
- Bare: `**prose**` → prose (legacy)
Empty prose after a label returns null so no bogus bullets are emitted.
Note: existing MILESTONES.md entries generated under the bug are not
regenerated here — that is a follow-up.
Closes#2660
* fix(#2660): normalize CRLF before one-liner extraction
Windows-authored SUMMARY files use CRLF line endings; the LF-only regex
in extractOneLinerFromBody would fail to match. Normalize \r\n and \r
to \n before stripping frontmatter and matching the one-liner pattern.
Adds test case (h) covering CRLF input.
* fix(#2659): qualify bare output() calls in audit-open handler
The audit-open dispatch case in bin/gsd-tools.cjs previously called bare
output() on both --json and text branches, which crashed with
ReferenceError: output is not defined. The core module is imported as
`const core`, so every other case uses core.output(). HEAD already
qualifies the calls correctly; this commit adds a regression test that
invokes `audit-open` and `audit-open --json` through runGsdTools and
asserts a clean exit plus non-empty stdout (and an explicit check that
the failure mode is not ReferenceError). The test fails on any revision
where either call reverts to bare output().
Closes#2659
* test(#2659): assert valid JSON output in --json mode
CodeRabbit nit: tighten --json regression coverage by parsing stdout
and asserting the result is a JSON object/array, not just non-empty.
* fix(#2636): surface gsd-sdk query failures and add workflow↔handler parity check
Root cause: workflows invoked `gsd-sdk query agent-skills <slug>` with a
trailing `2>/dev/null`, swallowing stderr and exit code. When the installed
`@gsd-build/sdk` npm was stale (pre-query), the call resolved to an empty
string and `agent_skills.<slug>` config was never injected into spawn
prompts — silently. The handler exists on main (sdk/src/query/skills.ts),
so this is a publish-drift + silent-fallback bug, not a missing handler.
Fix:
- Remove bare `2>/dev/null` from every `gsd-sdk query agent-skills …`
invocation in workflows so SDK failures surface to stderr.
- Apply the same rule to other no-fallback calls (audit-open, write-profile,
generate-* profile handlers, frontmatter.get in commands). Best-effort
cleanup calls (config-set workflow._auto_chain_active false) keep
exit-code forgiveness via `|| true` but no longer suppress stderr.
Parity tests:
- New: tests/bug-2636-gsd-sdk-query-silent-swallow.test.cjs — fails if any
`gsd-sdk query agent-skills … 2>/dev/null` is reintroduced.
- Existing: tests/gsd-sdk-query-registry-integration.test.cjs already
asserts every workflow noun resolves to a registered handler; confirmed
passing post-change.
Note: npm republish of @gsd-build/sdk is a separate release concern and is
not included in this PR.
* fix(#2636): address review — restore broken markdown fences and shell syntax
The previous commit's mass removal of '2>/dev/null' suffixes also
collapsed adjacent closing code fences and 'fi' tokens onto the
command line, producing malformed markdown blocks and 'truefi' /
'true fi' shell syntax errors in the workflows.
Repaired sites:
- commands/gsd/quick.md, thread.md (frontmatter.get fences)
- workflows/complete-milestone.md (audit-open fence)
- workflows/profile-user.md (write-profile + generate-* fences)
- workflows/verify-work.md (audit-open --json fence)
- workflows/execute-phase.md (truefi -> true / fi)
- workflows/plan-phase.md, discuss-phase-assumptions.md,
discuss-phase/modes/chain.md (true fi -> true / fi)
All 5450 tests pass.
* fix(#2645): emit [[agents]] array-of-tables in Codex config.toml
Codex ≥0.116 rejects `[agents.<name>]` map tables with `invalid type:
map, expected a sequence`. Switch generateCodexConfigBlock to emit
`[[agents]]` array-of-tables with an explicit `name` field per entry.
Strip + merge paths now self-heal on reinstall — both the legacy
`[agents.gsd-*]` map shape (pre-#2645 configs) and the new
`[[agents]]` with `name = "gsd-*"` shape are recognized and replaced,
while user-authored `[[agents]]` entries are preserved.
Fixes#2645
* fix(#2645): use TOML-aware parser to strip managed [[agents]] sections
CodeRabbit flagged that the prior regex-based stripper for [[agents]]
array-of-tables only matched headers at column 0 and stopped at any line
beginning with `[`. An indented [[agents]] header would not terminate the
preceding match, so a managed `gsd-*` block could absorb a following
user-authored agent and silently delete it.
Replace the ad-hoc regex with the existing TOML-aware section parser
(getTomlTableSections + removeContentRanges) so section boundaries are
authoritative regardless of indentation. Same logic applies to legacy
[agents.gsd-*] map sections.
Add a comprehensive mixed-shape test covering multiple GSD entries (both
legacy map and new array-of-tables, double- and single-quoted names)
interleaved with multiple user-authored agents in both shapes — verifies
all GSD entries are stripped and every user entry is preserved.
installCodexConfig() applied a narrow path-only regex pass before
generateCodexAgentToml(), skipping the convertClaudeToCodexMarkdown() +
neutralizeAgentReferences(..., 'AGENTS.md') pipeline used on the .md emit
path. Result: emitted Codex agent TOMLs carried stale Claude-specific
references (CLAUDE.md, .claude/skills/, .claude/commands/, .claude/agents/,
.claudeignore, bare "Claude" agent-name mentions).
Route the TOML path through convertClaudeToCodexMarkdown and extend that
pipeline to cover bare .claude/<subdir>/ references and .claudeignore
(both previously unhandled on the .md path too). The $HOME/.claude/
get-shit-done prefix substitution still runs first so the absolute Codex
install path is preserved before the generic .claude → .codex rewrite.
Regression test: tests/issue-2639-codex-toml-neutralization.test.cjs —
drives installCodexConfig against a fixture containing every flagged
marker and asserts the emitted TOML contains zero CLAUDE.md / .claude/
/ .claudeignore occurrences and that Claude Code / Claude Opus product
names survive.
Fixes#2639
Flat-skills installs write SKILL.md files under gsd-<cmd>/ dirs, but
Claude Code resolves skills by their frontmatter `name:`, not directory
name. PR #2595 normalized every `/gsd-<cmd>` to `/gsd:<cmd>` across
workflows — including inside `Skill(skill="...")` args — but the
installer still emitted `name: gsd-<cmd>`, so every Skill() call on a
flat-skills install resolved to nothing.
Fix: emit `name: gsd:<cmd>` (colon form) in
`convertClaudeCommandToClaudeSkill`. Keep the hyphen-form directory
name for Windows path safety.
Codex stays on hyphen form: its adapter invokes skills as `$gsd-<cmd>`
(shell-var syntax) and a colon would terminate the variable name.
`convertClaudeCommandToCodexSkill` uses `yamlQuote(skillName)` directly
and is untouched.
- Extract `skillFrontmatterName(dirName)` helper (exported for tests).
- Update claude-skills-migration and qwen-skills-migration assertions
that encoded the old hyphen emission.
- Add `tests/bug-2643-skill-frontmatter-name.test.cjs` asserting every
`Skill(skill="gsd:<cmd>")` reference in workflows resolves to an
emitted frontmatter name.
Full suite: 5452/5452 passing.
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
loadConfig's multiRepo migration and filesystem-sync writers targeted the
top-level parsed.sub_repos, but KNOWN_TOP_LEVEL (the unknown-key validator's
allowlist) only recognizes planning.sub_repos (canonical per #2561). Each
migration/sync therefore persisted a key the next loadConfig call warned was
unknown.
Redirect both writers to parsed.planning.sub_repos, ensuring parsed.planning
is initialized first. Also self-heal legacy/buggy installs by stripping any
stale top-level sub_repos on load, preserving its value as the
planning.sub_repos seed if that slot is empty.
Tests cover: (a) canonical planning.sub_repos emits no warning, (b) multiRepo
migration writes to planning.sub_repos with no top-level residue,
(c) filesystem sync relocates to planning.sub_repos, (d) stale top-level
sub_repos from older buggy installs is stripped on load.
Closes#2638
v1.38.3 shipped without sdk/dist/ because the outer `files` whitelist
and `prepublishOnly` chain had drifted. The `gsd-sdk` bin shim then
fell through to a stale @gsd-build/sdk@0.1.0 (pre-`query`), breaking
every workflow that called `gsd-sdk query <noun>` on fresh installs.
Current package.json already restores `sdk/dist` + `build:sdk`
prepublish; this PR locks the fix in with:
- tests/bug-2647-outer-tarball-sdk-dist.test.cjs — asserts `files`
includes `sdk/dist`, `prepublishOnly` invokes `build:sdk`, the
shim resolves sdk/dist/cli.js, `npm pack --dry-run` lists
sdk/dist/cli.js, and the built CLI exposes a `query` subcommand.
- scripts/verify-tarball-sdk-dist.sh — packs, extracts, installs
prod deps, and runs `node sdk/dist/cli.js query --help` against
the real tarball output.
- .github/workflows/release.yml — runs the verify script in both
next and stable release jobs before `npm publish`.
Partial fix for #2649 (same root cause on the sibling sdk package).
Fixes#2647
The SDK's config-set kept its own hand-maintained allowlist (28-key
drift vs. get-shit-done/bin/lib/config-schema.cjs), so documented
keys accepted by the CJS config-set — planning.sub_repos,
workflow.code_review_command, workflow.security_*, review.models.*,
model_profile_overrides.*, etc. — were rejected with
"Unknown config key" when routed through the SDK.
Changes:
- New sdk/src/query/config-schema.ts mirrors the CJS schema exactly
(exact-match keys + dynamic regex sources).
- config-mutation.ts imports VALID_CONFIG_KEYS / DYNAMIC_KEY_PATTERNS
from the shared module instead of rolling its own set and regex
branches.
- Drop hand-coded agent_skills.* / features.* regex branches —
now schema-driven so claude_md_assembly.blocks.*, review.models.*,
and model_profile_overrides.<runtime>.<tier> are also accepted.
- Add tests/config-schema-sdk-parity.test.cjs (node:test) as the
CI drift guard: asserts CJS VALID_CONFIG_KEYS set-equals the
literal set parsed from config-schema.ts, and that every CJS
dynamic pattern source has an identical counterpart in the SDK.
Parallel to the CJS↔docs parity added in #2479.
- Vitest #2653 specs iterate every CJS key through the SDK
validator, spot-check each dynamic pattern, and lock in
planning.sub_repos.
- While here: add workflow.context_coverage_gate to the CJS schema
(already in docs and SDK; CJS previously rejected it) and sync
the missing curated typo-suggestions (review.model, sub_repos,
plan_checker, workflow.review_command) into the SDK.
Fixes#2653.
The /gsd:new-milestone workflow Step 5 rewrote STATE.md's Current Position
body but never touched the YAML frontmatter, so every downstream reader
(state.json, getMilestoneInfo, progress bars) kept reporting the stale
milestone until the first phase advance forced a resync. Asymmetric with
milestone.complete, which uses readModifyWriteStateMdFull.
Add a new `state milestone-switch` handler (both SDK and CJS) that atomically:
- Stomps frontmatter milestone/milestone_name with caller-supplied values
- Resets status to 'planning' and progress counters to zero
- Rewrites the ## Current Position section to the new-milestone template
- Preserves Accumulated Context (decisions, blockers, todos)
Wire the workflow Step 5 to invoke `state.milestone-switch` instead of the
manual body rewrite. Note the flag is `--milestone` not `--version`:
gsd-tools reserves `--version` as a globally-invalid help flag.
Red vitest in sdk/src/query/state-mutation.test.ts asserts the frontmatter
reset. Regression guard via node:test in tests/bug-2630-*.test.cjs runs
through gsd-tools end-to-end.
Fixes#2630
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Root cause shared with #2647: a broken 1.38.3 tarball shipped without
sdk/dist/. The pre-#2441-decouple installer reacted by running
spawnSync('npm.cmd', ['install'], { cwd: sdkDir }) inside the npx cache
on Windows, where the cache is read-only, producing the misleading
"Failed to npm install in sdk/" error.
Defensive changes here (user-facing behavior only; packaging fix lives
in the sibling PR for #2647):
- Classify the install context (classifySdkInstall): detect npx cache
paths, node_modules-based installs, and dev clones via path heuristics
plus a side-effect-free write probe. Exported for test.
- Rewrite the dist-missing error to branch on context:
tarball + npxCache -> "don't touch npx cache; npm i -g ...@latest"
tarball (other) -> upgrade path + clone-build escape hatch
dev-clone -> keep existing cd sdk && npm install && npm run build
- Preserve the invariant that the installer never shells out to
npm install itself — users always drive that.
- Add tests/bug-2649-sdk-fail-fast.test.cjs covering the classifier and
both failure messages, with spawnSync/execSync interceptors that
assert no nested npm install is attempted.
Cross-ref: #2647 (packaging).
Fixes#2649
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The Codex and OpenCode install paths read `model_overrides` only from
`~/.gsd/defaults.json` (global). A per-project override set in
`.planning/config.json` — the reporter's exact setup for
`gsd-codebase-mapper` — was silently dropped, so the child agent inherited
the runtime's default model regardless of `model_overrides`.
Neither runtime has an inline `model` parameter on its spawn API
(Codex `spawn_agent(agent_type, message)`, OpenCode `task(description,
prompt, subagent_type, task_id, command)`), so the per-agent model must
reach the child via the static config GSD writes at install time. That
config was being populated from the wrong source.
Fix: add `readGsdEffectiveModelOverrides(targetDir)` which merges
`~/.gsd/defaults.json` with per-project `.planning/config.json`, with
per-project keys winning on conflict. Both install sites now call it and
walk up from the install root to locate `.planning/` — matching the
precedence `readGsdRuntimeProfileResolver` already uses for #2517.
Also update the Codex Task()->spawn_agent mapping block so it no longer
says "omit" without context: it now documents that per-agent overrides
are embedded in the agent TOML and notes the restriction that Codex
only permits `spawn_agent` when the user explicitly requested sub-agents
(do the work inline otherwise).
Regression tests (`tests/bug-2256-model-overrides-transport.test.cjs`)
cover: global-only, project-only, project-wins-on-conflict, walking up
from a nested `targetDir`, Codex TOML `model =` emission, and OpenCode
frontmatter `model:` emission.
Closes#2256
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
/gsd:manager's background execute-phase Task fails with
"Stream idle timeout - partial response received" on multi-plan phases
(Claude Code + Opus 4.7 at ~200K+ cache_read) because the long subagent
never emits tokens fast enough between large tool_results — the SSE layer
times out mid-assistant-turn and the harness retries hit the same TTFT
wall after prompt cache TTL expires.
Root cause: no orchestrator-level activity at wave/plan boundaries.
Fix (maintainer-approved A+B):
- A (wave boundary): execute-phase.md now emits a `[checkpoint]`
heartbeat before each wave spawns and after each wave completes.
- B (plan boundary): also emit `[checkpoint]` before each Task()
dispatch and after each executor returns (complete/failed/checkpoint).
Heartbeats are literal assistant-text lines (no tool call) with a
monotonic `{P}/{Q} plans done` counter so partial-transcript recovery
tools can grep progress even when a run dies mid-phase.
Docs: COMMANDS.md /gsd-manager section documents the marker format.
Tests: tests/bug-2410-stream-checkpoint-heartbeats.test.cjs (12 cases)
asserts the heartbeats exist at every boundary and in the right workflow
step. Full suite: 5422 node:test cases pass. Pre-existing vitest
failures on main are unrelated to this change.
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(#2620): detect HOME-relative PATH entries before suggesting absolute export
When the installer reported `gsd-sdk` not on PATH and suggested
appending an absolute `export PATH="/home/user/.npm-global/bin:$PATH"`
line to the user's rc file, a user who had the equivalent
`export PATH="$HOME/.npm-global/bin:$PATH"` already in their shell
profile would get a duplicate entry — the installer only compared the
absolute form.
Add `homePathCoveredByRc(globalBin, homeDir, rcFileNames?)` to
`bin/install.js` and export it for test-mode callers. The helper scans
`~/.zshrc`, `~/.bashrc`, `~/.bash_profile`, `~/.profile`, grepping each
file for `export PATH=` / bare `PATH=` lines and substituting the
common HOME forms (\$HOME, \${HOME}, leading ~/) with the real home
directory before comparing each resolved PATH segment against
globalBin. Trailing slashes are normalised so `.npm-global/bin/`
matches `.npm-global/bin`. Missing / unreadable / malformed rc files
are swallowed — the caller falls back to the existing absolute
suggestion.
Tests cover $HOME, \${HOME}, and ~/ forms, absolute match,
trailing-slash match, commented-out lines, missing rc files, and
unreadable rc files (directory where a file is expected).
Closes#2620
* fix(#2620): skip relative PATH segments in homePathCoveredByRc
CodeRabbit flagged that the helper unconditionally resolved every
non-$-containing segment against homeAbs via path.resolve(homeAbs, …),
which silently turns a bare relative segment like `bin` or
`node_modules/.bin` into `$HOME/bin` / `$HOME/node_modules/.bin`. That
is wrong: bare PATH segments depend on the shell's cwd at lookup time,
not on $HOME — so the helper was returning true for rc files that do
not actually cover globalBin.
Guard the compare with path.isAbsolute(expanded) after HOME expansion.
Only segments that are absolute on their own (or that became absolute
via $HOME / \${HOME} / ~ substitution) are compared against targetAbs.
Relative segments are skipped.
Add two regression tests covering a bare `bin` segment and a nested
`node_modules/.bin` segment; both previously returned true when home
happened to contain a matching subdirectory and now correctly return
false.
Closes#2620 (CodeRabbit follow-up)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(#2620): wire homePathCoveredByRc into installer suggestion path
CodeRabbit flagged that homePathCoveredByRc was added in the previous
commit but never called from the installer, so the user-facing PATH
warning stayed unchanged — users with `export PATH="$HOME/.npm-global/bin:$PATH"`
in their rc would still get a duplicate absolute-path suggestion.
Add `maybeSuggestPathExport(globalBin, homeDir)` that:
- skips silently when globalBin is already on process.env.PATH;
- prints a "try reopening your shell" diagnostic when homePathCoveredByRc
returns true (the directory IS on PATH via an rc entry — just not in
the current shell);
- otherwise falls through to the absolute-path
`echo 'export PATH="…:$PATH"' >> ~/.zshrc` suggestion.
Call it from installSdkIfNeeded after the sdk/dist check succeeds,
resolving globalBin via `npm prefix -g` (plus `/bin` on POSIX). Swallow
any exec failure so the installer keeps working when npm is weird.
Export maybeSuggestPathExport for tests. Add three new regression tests
(installer-flow coverage per CodeRabbit nitpick):
- rc covers globalBin via $HOME form → no absolute suggestion emitted
- rc covers only an unrelated directory → absolute suggestion emitted
- globalBin already on process.env.PATH → no output at all
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(#2619): prevent extractCurrentMilestone from truncating on phase-vX.Y headings
extractCurrentMilestone sliced ROADMAP.md to the current milestone by
looking for the next milestone heading with a greedy regex:
^#{1,N}\s+(?:.*v\d+\.\d+|✅|📋|🚧)
Any heading that mentioned a version literal matched — including phase
headings like "### Phase 12: v1.0 Tech-Debt Closure". When the current
milestone was at the same heading level as the phases (### 🚧 v1.1 …),
the slice terminated at the first such phase, hiding every phase that
followed from phase.insert, validate.health W007, and other SDK commands.
Fix: add a `(?!Phase\s+\S)` negative lookahead so phase headings can
never be treated as milestone boundaries. Phase headings always start
with the literal `Phase `, so this is a clean exclusion.
Applied to:
- get-shit-done/bin/lib/core.cjs (extractCurrentMilestone)
- sdk/src/query/roadmap.ts (extractCurrentMilestone + extractNextMilestoneSection)
Regression tests:
- tests/roadmap-phase-fallback.test.cjs: extractCurrentMilestone does not
truncate on phase heading containing vX.Y (#2619)
- sdk/src/query/roadmap.test.ts: extractCurrentMilestone bug-2619: does
not truncate at a phase heading containing vX.Y
Closes#2619
* fix(#2619): make milestone-boundary Phase lookahead case-insensitive
CodeRabbit follow-up on #2619: the negative lookahead `(?!Phase\s+\S)`
in the SDK milestone-boundary regex was case-sensitive, so headings like
`### PHASE 12: v1.0 Tech-Debt` or `### phase 12: …` still truncated the
milestone slice. Add the `i` flag (now `gmi`).
The sibling CJS regex in get-shit-done/bin/lib/core.cjs already uses the
`mi` flag, so it is already case-insensitive; added a regression test to
lock that in.
- sdk/src/query/roadmap.ts: change flags from `gm` → `gmi`
- sdk/src/query/roadmap.test.ts: add PHASE/phase regression test
- tests/roadmap-phase-fallback.test.cjs: add PHASE/phase regression test
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(sdk): decouple SDK from build-from-source install path, close#2441 and #2453
Ship sdk/dist prebuilt in the tarball and replace the npm-install-g
sub-install with a parent-package bin shim (bin/gsd-sdk.js). npm chmods
bin entries from a packed tarball correctly, eliminating the mode-644
failure (#2453) and the full class of NPM_CONFIG_PREFIX/ignore-scripts/
corepack/air-gapped failure modes that caused #2439 and #2441.
Changes:
- sdk/package.json: prepublishOnly runs `rm -rf dist && tsc && chmod +x
dist/cli.js` (stale-build guard + execute-bit fix at publish time)
- package.json: add "gsd-sdk": "bin/gsd-sdk.js" bin entry; add sdk/dist
to files so the prebuilt CLI ships in the tarball
- bin/gsd-sdk.js: new back-compat shim — resolves sdk/dist/cli.js relative
to the package root and delegates via `node`, so all existing PATH call
sites (slash commands, agents, hooks) continue to work unchanged (S1 shim)
- bin/install.js: replace installSdkIfNeeded() build-from-source + global-
install dance with a dist-verify + chmod-in-place guard; delete
resolveGsdSdk(), detectShellRc(), emitSdkFatal() helpers now unused
- .github/workflows/install-smoke.yml: add smoke-unpacked job that strips
execute bit from sdk/dist/cli.js before install to reproduce the exact
#2453 failure mode
- tests/bug-2441-sdk-decouple.test.cjs: new regression tests asserting all
invariants (no npm install -g from sdk/, shim exists, sdk/dist in files,
prepublishOnly has rm -rf + chmod)
- tests/bugs-1656-1657.test.cjs: update stale assertions that required
build-from-source behavior (now asserts new prebuilt-dist invariants)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* chore(release): bump to 1.38.2, wire release.yml to build SDK dist
- Bump version 1.38.1 -> 1.38.2 for the #2441/#2453 fix shipped in 0f6903d.
- Add `build:sdk` script (`cd sdk && npm ci && npm run build`).
- `prepublishOnly` now runs hooks + SDK builds as a safety net.
- release.yml (rc + finalize): build SDK dist before `npm publish` so the
published tarball always ships fresh `sdk/dist/` (kept gitignored).
- CHANGELOG: document 1.38.2 entry and `--sdk` flag semantics change.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* ci: build SDK dist before tests and smoke jobs
sdk/dist/ is gitignored (built fresh at publish time via release.yml),
but both the test suite and install-smoke jobs run `bin/install.js`
or `npm pack` against the checked-out tree where dist doesn't exist yet.
- test.yml: `npm run build:sdk` before `npm run test:coverage`, so tests
that spawn `bin/install.js` don't hit `installSdkIfNeeded()`'s fatal
missing-dist check.
- install-smoke.yml (both smoke and smoke-unpacked): build SDK before
pack/chmod so the published tarball contains dist and the unpacked
install has a file to strip exec-bit from.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(sdk): lift SDK runtime deps to parent so tarball install can resolve them
The SDK's runtime deps (ws, @anthropic-ai/claude-agent-sdk) live in
sdk/package.json, but sdk/node_modules is NOT shipped in the parent
tarball — only sdk/dist, sdk/src, sdk/prompts, and sdk/package.json are.
When a user runs `npm install -g get-shit-done-cc`, npm installs the
parent's node_modules but never runs `npm install` inside the nested
sdk/ directory.
Result: `node sdk/dist/cli.js` fails with ERR_MODULE_NOT_FOUND for 'ws'.
The smoke tarball job caught this; the unpacked variant masked it
because `npm install -g <dir>` copies the entire workspace including
sdk/node_modules (left over from `npm run build:sdk`).
Fix: declare the same deps in the parent package.json so they land in
<pkg>/node_modules, which Node's resolution walks up to from
<pkg>/sdk/dist/cli.js. Keep them declared in sdk/package.json too so
the SDK remains a self-contained package for standalone dev.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(lockfile): regenerate package-lock.json cleanly
The previous `npm install` run left the lockfile internally inconsistent
(resolved esbuild@0.27.7 referenced but not fully written), causing
`npm ci` to fail in CI with "Missing from lock file" errors.
Clean regen via rm + npm install fixes all three failed jobs
(test, smoke, smoke-unpacked), which were all hitting the same
`npm ci` sync check.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(deps): remove unused esbuild + vitest from root devDependencies
Both were declared but never imported anywhere in the root package
(confirmed via grep of bin/, scripts/, tests/). They lived in sdk/
already, which is the only place they're actually used.
The transitive tree they pulled in (vitest → vite → esbuild 0.28 →
@esbuild/openharmony-arm64) was the root of the CI npm ci failures:
the openharmony platform package's `optional: true` flag was not being
applied correctly by npm 10 on Linux runners, causing EBADPLATFORM.
After removal: 800+ transitive packages → 155. Lockfile regenerated
cleanly. All 4170 tests pass.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(sdk): pretest:coverage builds sdk; tighten shim test assertions
Add "pretest:coverage": "npm run build:sdk" so npm run test:coverage
works in clean checkouts where sdk/dist/ hasn't been built yet.
Tighten the two loose shim assertions in bug-2441-sdk-decouple.test.cjs:
- forwards-to test now asserts path.resolve() is called with the
'sdk','dist','cli.js' path segments, not just substring presence
- node-invocation test now asserts spawnSync(process.execPath, [...])
pattern, ruling out matches in comments or the shebang line
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: address PR review — pretest:coverage + tighten shim tests
Review feedback from trek-e on PR 2457:
1. pretest:coverage + pretest hooks now run `npm run build:sdk` so
`npm run test[:coverage]` in a clean checkout produces the required
sdk/dist/ artifacts before running the installer-dependent tests.
CI already does this explicitly; local contributors benefit.
2. Shim tests in bug-2441-sdk-decouple.test.cjs tightened from loose
substring matches (which would pass on comments/shebangs alone) to
regex assertions on the actual path.resolve call, spawnSync with
process.execPath, process.argv.slice(2), and process.exit pattern.
These now provide real regression protection for #2453-class bugs.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix: correct CHANGELOG entry and add [1.38.2] reference link
Two issues in the 1.38.2 CHANGELOG entry:
- installSdkIfNeeded() was described as deleted but it still exists in
bin/install.js (repurposed to verify sdk/dist/cli.js and fix execute bit).
Corrected the description to say 'repurposes' rather than 'deletes'.
- The reference-link block at the bottom of the file was missing a [1.38.2]
compare URL and [Unreleased] still pointed to v1.37.1...HEAD. Added the
[1.38.2] link and updated [Unreleased] to compare/v1.38.2...HEAD.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(sdk): double-cast WorkflowConfig to Record for strict tsc build
TypeScript error on main (introduced in #2611) blocks `npm run build`
in sdk/, which now runs as part of this PR's tarball build path. Apply
the double-cast via `unknown` as the compiler suggests.
Same fix as #2622; can be dropped if that lands first.
* test: remove bug-2598 test obsoleted by SDK decoupling
The bug-2598 test guards the Windows CVE-2024-27980 fix in the old
build-from-source path (npm spawnSync with shell:true + formatSpawnFailure
diagnostics). This PR removes that entire code path — installSdkIfNeeded
no longer spawns npm, it just verifies the prebuilt sdk/dist/cli.js
shipped in the tarball.
The test asserts `installSdkIfNeeded.toString()` contains a
formatSpawnFailure helper. After decoupling, no such helper exists
(nothing to format — there's no spawn). Keeping the test would assert
invariants of the rejected architecture.
The original #2598 defect (silent failure of npm spawn on Windows) is
structurally impossible in the shim path: bin/gsd-sdk.js invokes
`node sdk/dist/cli.js` directly via child_process.spawn with an
explicit argv array. No .cmd wrapper, no shell delegation.
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: Tom Boucher <trekkie@nomorestars.com>
* feat(#2492): add gates ensuring discuss-phase decisions are translated and verified
Two gates close the loop between CONTEXT.md `<decisions>` and downstream
work, fixing #2492:
- Plan-phase **translation gate** (BLOCKING). After requirements
coverage, refuses to mark a phase planned when a trackable decision
is not cited (by id `D-NN` or by 6+-word phrase) in any plan's
`must_haves`, `truths`, or body. Failure message names each missed
decision with id, category, text, and remediation paths.
- Verify-phase **validation gate** (NON-BLOCKING). Searches plans,
SUMMARY.md, files modified, and recent commit subjects for each
trackable decision. Misses are written to VERIFICATION.md as a
warning section but do not change verification status. Asymmetry is
deliberate — fuzzy-match miss should not fail an otherwise green
phase.
Shared helper `parseDecisions()` lives in `sdk/src/query/decisions.ts`
so #2493 can consume the same parser.
Decisions opt out of both gates via `### Claude's Discretion` heading
or `[informational]` / `[folded]` / `[deferred]` tags.
Both gates skip silently when `workflow.context_coverage_gate=false`
(default `true`).
Closes#2492
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(#2492): make plan-phase decision gate actually block (review F1, F8, F9, F10, F15)
- F1: replace `${context_path}` with `${CONTEXT_PATH}` in the plan-phase
gate snippet so the BLOCKING gate receives a non-empty path. The
variable was defined in Step 4 (`CONTEXT_PATH=$(_gsd_field "$INIT" ...)`)
and the gate snippet referenced the lowercase form, leaving the gate to
run with an empty path argument and silently skip.
- F15: wrap the SDK call with `jq -e '.data.passed == true' || exit 1` so
failure halts the workflow instead of being printed and ignored. The
verify-phase counterpart deliberately keeps no exit-1 (non-blocking by
design) and now carries an inline note documenting the asymmetry.
- F10: tag the JSON example fence as `json` and the options-list fence as
`text` (MD040).
- F8/F9: anchor the heading-presence test regexes to `^## 13[a-z]?\\.` so
prose substrings like "Requirements Coverage Gate" mentioned in body
text cannot satisfy the assertion. Added two new regression tests
(variable-name match, exit-1 guard) so a future revert is caught.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(#2492): tighten decision-coverage gates against false positives and config drift (review F3,F4,F5,F6,F7,F16,F18,F19)
- F3: forward `workstream` arg through both gate handlers so workstream-scoped
`workflow.context_coverage_gate=false` actually skips. Added negative test
that creates a workstream config disabling the gate while the root config
has it enabled and asserts the workstream call is skipped.
- F4: restrict the plan-phase haystack to designated sections — front-matter
`must_haves` / `truths` / `objective` plus body sections under headings
matching `must_haves|truths|tasks|objective`. HTML comments and fenced
code blocks are stripped before extraction so a commented-out citation or
a literal example never counts as coverage. Verify-phase keeps the broader
artifact-wide haystack by design (non-blocking).
- F5: reject decisions with fewer than 6 normalized words from soft-matching
(previously only rejected when the resulting phrase was under 12 chars
AFTER slicing — too lenient). Short decisions now require an explicit
`D-NN` citation, with regression tests for the boundary.
- F6: walk every `*-SUMMARY.md` independently and use `matchAll` with the
`/g` flag so multiple `files_modified:` blocks across multiple summaries
are all aggregated. Previously only the first block in the concatenated
string was parsed, silently dropping later plans' files.
- F7: validate every `files_modified` path stays inside `projectDir` after
resolution (rejects absolute paths, `../` traversal). Cap each file read
at 256 KB. Skipped paths emit a stderr warning naming the entry.
- F16: validate `workflow.context_coverage_gate` is boolean in
`loadGateConfig`; warn loudly on numeric or other-shaped values and
default to ON. Mirrors the schema-vs-loadConfig validation gap from
#2609.
- F18: bump verify-phase `git log -n` cap from 50 to 200 so longer-running
phases are not undercounted. Documented as a precision-vs-recall tradeoff
appropriate for a non-blocking gate.
- F19: tighten `QueryResult` / `QueryHandler` to be parameterized
(`<T = unknown>`). Drops the `as unknown as Record<string, unknown>`
casts in the gate handlers and surfaces shape mismatches at compile time
for callers that pass a typed `data` value.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(#2492): harden decisions parser and verify-phase glob (review F11,F12,F13,F14,F17,F20)
- F11: strip fenced code blocks from CONTEXT.md before searching for
`<decisions>` so an example block inside ``` ``` is not mis-parsed.
- F12: accept tab-indented continuation lines (previously required a leading
space) so decisions split with `\t` continue cleanly.
- F13: parse EVERY `<decisions>` block in the file via `matchAll`, not just
the first. CONTEXT.md may legitimately carry more than one block.
- F14: `decisions.parse` handler now resolves a relative path against
`projectDir` — symmetric with the gate handlers — and still accepts
absolute paths.
- F17: replace `ls "${PHASE_DIR}"/*-CONTEXT.md | head -1` in verify-phase.md
with a glob loop (ShellCheck SC2012 fix). Also avoids spawning an extra
subprocess and survives filenames with whitespace.
- F20: extend the unicode quote-stripping in the discretion-heading match
to cover U+2018/2019/201A/201B and the U+201C-F double-quote variants
plus backtick, so any rendering of "Claude's Discretion" collapses to
the same key.
Each fix has a regression test in `decisions.test.ts`.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* feat: add unified post-planning gap checker (closes#2493)
Adds a unified post-planning gap checker as Step 13e of plan-phase.md.
After all plans are generated and committed, scans REQUIREMENTS.md and
CONTEXT.md <decisions> against every PLAN.md in the phase directory and
emits a single Source | Item | Status table.
Why
- The existing Requirements Coverage Gate (§13) blocks/re-plans on REQ
gaps but emits two separate per-source signals. Issue #2493 asks for
one unified report after planning so that requirements AND
discuss-phase decisions slipping through are surfaced in one place
before execution starts.
What
- New workflow.post_planning_gaps boolean config key, default true,
added to VALID_CONFIG_KEYS, CONFIG_DEFAULTS, hardcoded.workflow, and
cmdConfigSet (boolean validation).
- New get-shit-done/bin/lib/decisions.cjs — shared parser for
CONTEXT.md <decisions> blocks (D-NN entries). Designed for reuse by
the related #2492 plan/verify decision gates.
- New get-shit-done/bin/lib/gap-checker.cjs — parses REQUIREMENTS.md
(checkbox + traceability table forms), reads CONTEXT.md decisions,
walks PHASE_DIR/*-PLAN.md, runs word-boundary coverage detection
(REQ-1 must not match REQ-10), formats a sorted report.
- New gsd-tools gap-analysis CLI command wired through gsd-tools.cjs.
- workflows/plan-phase.md gains §13e between §13d (commit plans) and
§14 (Present Final Status). Existing §13 gate preserved — §13e is
additive and non-blocking.
- sdk/prompts/workflows/plan-phase.md gets an equivalent
post_planning_gaps step for headless mode.
- Docs: CONFIGURATION.md, references/planning-config.md, INVENTORY.md,
INVENTORY-MANIFEST.json all updated.
Tests
- tests/post-planning-gaps-2493.test.cjs: 30 test cases covering step
insertion position, decisions parser, gap detector behavior
(covered/not-covered, false-positive guard, missing-file
resilience, malformed-input resilience, gate on/off, deterministic
natural sort), and full config integration.
- Full suite: 5234 / 5234 pass.
Design decisions
- Numbered §13e (sub-step), not §14 — §14 already exists (Present
Final Status); inserting before it preserves downstream auto-advance
step numbers.
- Existing §13 gate kept, not replaced — §13 blocks/re-plans on
REQ gaps; §13e is the unified post-hoc report. Per spec: "default
behavior MUST be backward compatible."
- Word-boundary ID matching avoids REQ-1 matching REQ-10 and avoids
brittle semantic/substring matching.
- Shared decisions.cjs parser so #2492 can reuse the same regex.
- Natural-sort keys (REQ-02 before REQ-10) for deterministic output.
- Boolean validation in cmdConfigSet rejects non-boolean values
matches the precedent set by drift_threshold/drift_action.
Closes#2493
* fix(#2493): expose post_planning_gaps in loadConfig() + sync schema example
Address CodeRabbit review on PR #2610:
- core.cjs loadConfig(): return post_planning_gaps from both the
config.json branch and the global ~/.gsd/defaults.json fallback so
callers can rely on config.post_planning_gaps regardless of whether
the key is present (comment 3127977404, Major).
- docs/CONFIGURATION.md: add workflow.post_planning_gaps to the Full
Schema JSON example so copy/paste users see the new toggle alongside
security_block_on (comment 3127977392, Minor).
- tests/post-planning-gaps-2493.test.cjs: regression coverage for
loadConfig() — default true when key absent, honors explicit
true/false from workflow.post_planning_gaps.
* feat: make model profiles runtime-aware for Codex/non-Claude runtimes (closes#2517)
Adds an optional top-level `runtime` config key plus a
`model_profile_overrides[runtime][tier]` map. When `runtime` is set,
profile tiers (opus/sonnet/haiku) resolve to runtime-native model IDs
(and reasoning_effort where supported) instead of bare Claude aliases.
Codex defaults from the spec:
opus -> gpt-5.4 reasoning_effort: xhigh
sonnet -> gpt-5.3-codex reasoning_effort: medium
haiku -> gpt-5.4-mini reasoning_effort: medium
Claude defaults mirror MODEL_ALIAS_MAP. Unknown runtimes fall back to
the Claude-alias safe default rather than emit IDs the runtime cannot
accept. reasoning_effort is only emitted into Codex install paths;
never returned from resolveModelInternal and never written to Claude
agent frontmatter.
Backwards compatible: any user without `runtime` set sees identical
behavior — the new branch is gated on `config.runtime != null`.
Precedence (highest to lowest):
1. per-agent model_overrides
2. runtime-aware tier resolution (when `runtime` is set)
3. resolve_model_ids: "omit"
4. Claude-native default
5. inherit (literal passthrough)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(#2517): address adversarial review of #2609 (findings 1-16)
Addresses all 16 findings from the adversarial review of PR #2609.
Each finding is enumerated below with its resolution.
CRITICAL
- F1: readGsdRuntimeProfileResolver(targetDir) now probes per-project
.planning/config.json AND ~/.gsd/defaults.json with per-project winning,
so the PR's headline claim ("set runtime in project config and Codex
TOML emit picks it up") actually holds end-to-end.
- F2: resolveTierEntry field-merges user overrides with built-in defaults.
The CONFIGURATION.md string-shorthand example
`{ codex: { opus: "gpt-5-pro" } }`
now keeps reasoning_effort from the built-in entry. Partial-object
overrides like `{ opus: { reasoning_effort: 'low' } }` keep the
built-in model. Both paths regression-tested.
MAJOR
- F3: resolveReasoningEffortInternal gates strictly on the
RUNTIMES_WITH_REASONING_EFFORT allowlist regardless of override
presence. Override + unknown-runtime no longer leaks reasoning_effort.
- F4: runtime:"claude" is now a no-op for resolution (it is the implicit
default). It no longer hijacks resolve_model_ids:"omit". Existing
tests for `runtime:"claude"` returning Claude IDs were rewritten to
reflect the no-op semantics; new test asserts the omit case returns "".
- F5: _readGsdConfigFile in install.js writes a stderr warning on JSON
parse failure instead of silently returning null. Read failure and
parse failure are warned separately. Library require is hoisted to top
of install.js so it is not co-mingled with config-read failure modes.
- F6: install.js requires for core.cjs / model-profiles.cjs are hoisted
to the top of the file with __dirname-based absolute paths so global
npm install works regardless of cwd. Test asserts both lib paths exist
relative to install.js __dirname.
- F7: docs/CONFIGURATION.md `runtime` row no longer lists `opencode` as
a valid runtime — install-path emission for non-Codex runtimes is
explicitly out of scope per #2517 / #2612, and the doc now points at
#2612 for the follow-on work. resolveModelInternal still accepts any
runtime string (back-compat) and falls back safely for unknown values.
- F8: Tests now isolate HOME (and GSD_HOME) to a per-test tmpdir so the
developer's real ~/.gsd/defaults.json cannot bleed into assertions.
Same pattern CodeRabbit caught on PRs #2603 / #2604.
- F9: `runtime` and `model_profile_overrides` documented as flat-only
in core.cjs comments — not routed through `get()` because they are
top-level keys per docs/CONFIGURATION.md and introducing nested
resolution for two new keys was not worth the edge-case surface.
- F10/F13: loadConfig now invokes _warnUnknownProfileOverrides on the
raw parsed config so direct .planning/config.json edits surface
unknown runtime values (e.g. typo `runtime: "codx"`) and unknown
tier values (e.g. `model_profile_overrides.codex.banana`) at read
time. Warnings only — preserves back-compat for runtimes added
later. Per-process warning cache prevents log spam across repeated
loadConfig calls.
MINOR / NIT
- F11: Removed dead `tier || 'sonnet'` defensive shortcut. The local
is now `const alias = tier;` with a comment explaining why `tier`
is guaranteed truthy at that point (every MODEL_PROFILES entry
defines `balanced`, the fallback profile).
- F12: Extracted resolveTierEntry() in core.cjs as the single source
of truth for runtime-aware tier resolution. core.cjs and bin/install.js
both consume it — no duplicated lookup logic between the two files.
- F14: Added regression tests for findings #1, #2, #3, #4, #6, #10, #13
in tests/issue-2517-runtime-aware-profiles.test.cjs. Each must-fix
path has a corresponding test that fails against the pre-fix code
and passes against the post-fix code.
- F15: docs/CONFIGURATION.md `model_profile` row cross-references
#1713 / #1806 next to the `adaptive` enum value.
- F16: RUNTIME_PROFILE_MAP remains in core.cjs as the single source of
truth; install.js imports it through the exported resolveTierEntry
helper rather than carrying its own copy. Doc files (CONFIGURATION.md,
USER-GUIDE.md, settings.md) intentionally still embed the IDs as text
— code comment in core.cjs flags that those doc files must be updated
whenever the constant changes.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* refactor(workflows): extract discuss-phase modes/templates/advisor for progressive disclosure (closes#2551)
Splits 1,347-line workflows/discuss-phase.md into a 495-line dispatcher plus
per-mode files in workflows/discuss-phase/modes/ and templates in
workflows/discuss-phase/templates/. Mirrors the progressive-disclosure
pattern that #2361 enforced for agents.
- Per-mode files: power, all, auto, chain, text, batch, analyze, default, advisor
- Templates lazy-loaded at the step that produces the artifact (CONTEXT.md
template at write_context, DISCUSSION-LOG.md template at git_commit,
checkpoint.json schema when checkpointing)
- Advisor mode gated behind `[ -f $HOME/.claude/get-shit-done/USER-PROFILE.md ]`
— inverse of #2174's --advisor flag (don't pay the cost when unused)
- scout_codebase phase-type→map selection table extracted to
references/scout-codebase.md
- New tests/workflow-size-budget.test.cjs enforces tiered budgets across
all workflows/*.md (XL=1700 / LARGE=1500 / DEFAULT=1000) plus the
explicit <500 ceiling for discuss-phase.md per #2551
- Existing tests updated to read from the new file locations after the
split (functional equivalence preserved — content moved, not removed)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(#2607): align modes/auto.md check_existing with parent (Update it, not Skip)
CodeRabbit flagged drift between the parent step (which auto-selects "Update
it") and modes/auto.md (which documented "Skip"). The pre-refactor file had
both — line 182 said "Skip" in the overview, line 250 said "Update it" in the
actual step. The step is authoritative. Fix the new mode file to match.
Refs: PR #2607 review comment 3127783430
* test(#2607): harden discuss-phase regression tests after #2551 split
CodeRabbit identified four test smells where the split weakened coverage:
- workflow-size-budget: assertion was unreachable (entered if-block on match,
then asserted occurrences === 0 — always failed). Now unconditional.
- bug-2549-2550-2552: bounded-read assertion checked concatenated source, so
src.includes('3') was satisfied by unrelated content in scout-codebase.md
(e.g., "3-5 most relevant files"). Now reads parent only with a stricter
regex. Also asserts SCOUT_REF exists.
- chain-flag-plan-phase: filter(existsSync) silently skipped a missing
modes/chain.md. Now fails loudly via explicit asserts.
- discuss-checkpoint: same silent-filter pattern across three sources. Now
asserts each required path before reading.
Refs: PR #2607 review comments 3127783457, 3127783452, plus nitpicks for
chain-flag-plan-phase.test.cjs:21-24 and discuss-checkpoint.test.cjs:22-27
* docs(#2607): fix INVENTORY count, context.md placeholders, scout grep portability
- INVENTORY.md: subdirectory note said "50 top-level references" but the
section header now says 51. Updated to 51.
- templates/context.md: footer hardcoded XX-name instead of declared
placeholders [X]/[Name], which would leak sample text into generated
CONTEXT.md files. Now uses the declared placeholders.
- references/scout-codebase.md: no-maps fallback used grep -rl with
"\\|" alternation (GNU grep only — silent on BSD/macOS grep). Switched
to grep -rlE with extended regex for portability.
Refs: PR #2607 review comments 3127783404, 3127783448, plus nitpick for
scout-codebase.md:32-40
* docs(#2607): label fenced examples + clarify overlay/advisor precedence
- analyze.md / text.md / default.md: add language tags (markdown/text) to
fenced example blocks to silence markdownlint MD040 warnings flagged by
CodeRabbit (one fence in analyze.md, two in text.md, five in default.md).
- discuss-phase.md: document overlay stacking rules in discuss_areas — fixed
outer→inner order --analyze → --batch → --text, with a pointer to each
overlay file for mode-specific precedence.
- advisor.md: add tie-breaker rules for NON_TECHNICAL_OWNER signals — explicit
technical_background overrides inferred signals; otherwise OR-aggregate;
contradictory explanation_depth values resolve by most-recent-wins.
Refs: PR #2607 review comments 3127783415, 3127783437, plus nitpicks for
default.md:24, discuss-phase.md:345-365, and advisor.md:51-56
* fix(#2607): extract codebase_drift_gate body to keep execute-phase under XL budget
PR #2605 added 80 lines to execute-phase.md (1622 -> 1702), pushing it over
the XL_BUDGET=1700 line cap enforced by tests/workflow-size-budget.test.cjs
(introduced by this PR). Per the test's own remediation hint and #2551's
progressive-disclosure pattern, extract the codebase_drift_gate step body to
get-shit-done/workflows/execute-phase/steps/codebase-drift-gate.md and leave
a brief pointer in the workflow. execute-phase.md is now 1633 lines.
Budget is NOT relaxed; the offending workflow is tightened.
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
