Two CodeRabbit findings on PR #2920:
1. parseRuntimeInput previously only matched the bare "16" exactly for
the all-runtimes shortcut. Inputs the prompt explicitly encourages —
"16,", "16 1", "1,16" — fell through to per-token parsing and
silently installed only Claude or a partial subset. Move the
ALL_RUNTIMES_OPTION check after tokenization so any token equal to
"16" expands. Added regression coverage in
tests/multi-runtime-select.test.cjs for the four mixed-input forms.
2. The "maps Hermes to ~/.hermes for global installs" test invoked
getGlobalDir('hermes') without isolating HERMES_HOME. On a developer
machine that exports HERMES_HOME the assertion would fail even
though getGlobalDir was behaving correctly. Save/clear/restore the
env var around the assertion, mirroring the pattern the later
describe block already uses.
Full suite: 6128/6128 pass.
Per the issue spec for #2841 and CodeRabbit feedback on PR #2920, the
project-context filename rewrite should produce HERMES.md, not
.hermes.md. Reverts the earlier .hermes.md change at all 5 substitution
sites in bin/install.js and updates the corresponding regression test
in tests/hermes-install.test.cjs to assert HERMES.md.
Full suite: 6127/6127 pass.
Two follow-ups on commit 80f14cac (which hardened quick-branching with a
trunk fixture):
1. quick-branching.test.cjs: add a `defaultBranch` parameter to
setupFixture and run the "branches off origin/HEAD" assertion against
both `main` and `trunk`. The wholesale switch to trunk in 80f14cac
removed coverage of the conventional `main` path; parameterizing
restores it without giving up the symbolic-ref guarantee.
2. bug-2916-handle-branching-default-base.test.cjs: apply the same
parameterization here. handle_branching has the same default-branch
detection logic as Step 2.5, so it deserves the same trunk regression
guard. Previously this file only exercised `main`.
A regression that silently defaults to `main` instead of consulting
`git symbolic-ref refs/remotes/origin/HEAD` now fails the `trunk`
variant in both files.
Tests: 10/10 in the touched suites.
- Restrict the "init parse list includes branch_name" assertion to
the bash blocks inside Step 2 (Initialize) so an unrelated step
that mentions branch_name cannot mask the contract.
- Switch the fixture's default branch from main to trunk so the
symbolic-ref code path is locked in: a regression that silently
defaults to "main" instead of consulting origin/HEAD now fails.
Addresses CodeRabbit review on PR #2921.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Two test files were asserting installer prompt behavior by regex/.includes()
against bin/install.js source. Per CONTRIBUTING.md "no-source-grep"
testing standard, replace with structured assertions:
- tests/kilo-install.test.cjs: import runtimeMap and buildRuntimePromptText
from the install module; assert runtimeMap['11'] === 'kilo' and that the
rendered prompt lists Kilo above OpenCode without marketing copy.
- tests/multi-runtime-select.test.cjs: import runtimeMap, allRuntimes,
parseRuntimeInput, buildRuntimePromptText. Assert exported runtimeMap
matches the canonical option list, allRuntimes contains every runtime
exactly once, prompt text lists Hermes (10), Qwen Code (13), Trae (14),
All (16), and parser splits/dedupes by exercising parseRuntimeInput
rather than regexing source code.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Per spec in #2841, all 86 GSD skills must collapse into a single "gsd"
category in Hermes' system prompt. Previous code passed skills/ as the
install root, producing a flat skills/gsd-*/ layout that inflated
Hermes' loader output to 86 top-level entries.
Changes:
- Install path now writes to skills/gsd/{DESCRIPTION.md, gsd-*/SKILL.md}
- Uninstall removes the entire skills/gsd/ category dir plus any leftover
flat-layout gsd-*/ from older installs (graceful migration)
- writeManifest emits skills/gsd/<skill>/<file> paths for Hermes
- --skills-root hermes returns the nested category path so /gsd-sync-skills
syncs into the right directory
- DESCRIPTION.md at category root carries name/version/description so
Hermes' skill loader surfaces the GSD category in the system prompt
Also extracts promptRuntime's runtimeMap, allRuntimes, parseRuntimeInput,
and buildRuntimePromptText to module scope and exports them so tests can
assert structurally instead of grepping bin/install.js source.
Existing hermes-install tests updated to expect the nested layout and
to verify the category DESCRIPTION.md frontmatter (name, version,
description) using the shared parseFrontmatter helper.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
CodeRabbit nitpick (per project policy `feedback_no_source_grep_tests`):
the prior `tests/quick-branching.test.cjs` asserted branching correctness
by `.includes()`-grepping the raw markdown content for literal command
substrings. Those assertions stayed green even when the underlying
behavior regressed (e.g. when `git checkout -b` was unconditionally run
from the wrong HEAD).
Replace with the same pattern as `bug-2916-handle-branching-default-base
.test.cjs`:
- Structurally extract the Step 2.5 bash block from quick.md by
walking the markdown for fenced ```bash blocks under the heading
(no regex on prose).
- Spin up a fixture git repo with a bare origin, a clone whose
`origin/HEAD` points at `main`, and a checked-out previous-task
branch carrying its own unmerged commit.
- Execute the extracted bash block via `bash -c` and assert that
the new branch's tip equals `origin/main` (0 commits inherited
from the previous-task HEAD).
- Add a reuse test that pre-creates the target branch with its own
commit and verifies the script switches back to it without a
rebase or reset.
The two informational tests (workflow file exists, branching runs
before task-directory creation) are retained, plus the `branch_name`
parsing assertion is rewritten to walk fenced bash blocks rather than
substring-grep arbitrary content.
Four fixes from review of hermes-agent.nousresearch.com docs:
1. SKILL.md frontmatter now declares `version` (required field per
Hermes spec). Plumbed through `convertClaudeCommandToClaudeSkill`
gated on runtime='hermes' so other runtimes' frontmatter is unchanged.
2. Project-context filename rewrite changed from `HERMES.md` (not
discovered by Hermes) to `.hermes.md` (top of Hermes' discovery list:
.hermes.md → AGENTS.md → CLAUDE.md → .cursorrules).
3. README + finishInstall now show `/gsd-help` and `/gsd-new-project`
for Hermes; per docs, Hermes auto-exposes skills as slash commands.
4. Hermes tests now parse SKILL.md frontmatter structurally via the
shared parseFrontmatter helper instead of substring-matching source
text, and assert the version/name/description shape required by
Hermes' skill_view().
Full suite: 6128/6128 pass (3 new structural assertions).
Two existing tests called extractBlockquotes(reportStep) without first
asserting reportStep was non-null. If the workflow file ever loses its
`<step name="report">` block, the test would fail with a confusing
TypeError on the destructuring inside extractBlockquotes instead of a
clear "report step must exist" assertion.
Add assert.ok(reportStep, ...) guards at the two missing call sites
(lines 100 and 130). The other two call sites (lines 75-83) already
had guards.
Addresses CodeRabbit comment on PR #2918.
handle_branching in execute-phase.md (and the equivalent step in quick.md)
created the per-phase branch from whatever branch happened to be checked
out — typically the previous phase's still-unmerged feature branch — so
consecutive phases compounded on top of each other and stayed unpushed.
Detect the default branch via git symbolic-ref refs/remotes/origin/HEAD,
fast-forward it from origin, and fork the new phase branch off that tip.
Existing branches are still reused as-is. Dirty working trees fall back
to current HEAD with a loud warning, and a post-creation guard reports
any inherited commits.
Regression test extracts the bash from the <step name="handle_branching">
block structurally and runs it against a fixture repo where HEAD sits on
a previous-phase branch with extra commits.
Two bugs in the audit-open dispatch case in bin/gsd-tools.cjs:
1. Bare output(...) calls (only core.output is in scope) threw
ReferenceError: output is not defined on every invocation,
blocking the first step of /gsd-complete-milestone.
2. Even after switching to core.output(formattedReport, raw), the
human-readable branch JSON-stringified the formatted text because
core.output only bypasses JSON encoding when called as
core.output(null, true, rawValue).
Fix:
- --json path: core.output(result, raw) — pass the object,
let core.output JSON-stringify (don't pre-stringify).
- text path: core.output(null, true, formatAuditReport(result))
— use the rawValue form to emit verbatim section dividers and
item lists.
Adds tests/bug-2911-audit-open-output-shape.test.cjs which parses
both modes structurally — line-by-line for text mode (asserting the
report headers exist as standalone lines, not as escaped \n inside a
JSON quoted string), and JSON.parse + key-by-key shape assertions for
--json mode (matching the contract returned by auditOpenArtifacts).
The report step in workflows/progress.md had no directive establishing
PROJECT.md/STATE.md/ROADMAP.md as the authoritative sources for the
progress report. When init.progress returned project_exists: false (e.g.
invoked from a subdirectory without .planning/), the model fell back to
whatever was in its session context — including stale CLAUDE.md
## Project blocks — and produced routing output citing the wrong
milestone/phase.
Add a blockquote directive at the top of the report step that names
PROJECT.md, STATE.md, and ROADMAP.md as authoritative and forbids using
the CLAUDE.md ## Project block as a source for any progress report field.
Fixes#2912
Adds Hermes Agent as a supported installation target. Users can run
\`npx get-shit-done-cc --hermes\` to install all 86 GSD commands as
skills under \`~/.hermes/skills/gsd-*/SKILL.md\`, following the same
open skill standard as Claude Code 2.1.88+, Qwen Code, Antigravity,
Trae, Augment, and Codebuddy.
Hermes Agent is an open-source AI agent framework by Nous Research
(NousResearch/hermes-agent, MIT). Its skill loader accepts the Claude
skill format as-is: frontmatter parsed with PyYAML SafeLoader (unknown
keys like \`allowed-tools\` / \`argument-hint\` ignored), body XML tags
(\`<objective>\`, \`<execution_context>\`, \`<process>\`) passed directly
to the model. Compatibility proven end-to-end with all 86 GSD skills
loading cleanly, \`skill_view()\` returning full bodies, and
\`build_skills_system_prompt()\` emitting them into the agent system
prompt — zero Hermes code changes required.
Changes:
- \`bin/install.js\`: --hermes flag, getDirName/getGlobalDir/getConfigDirFromHome
support, HERMES_HOME env var (native to Hermes — used for profile
mode / Docker deploys), install/uninstall pipelines, interactive
picker option 10 (alphabetical: between Gemini and Kilo), .hermes
path replacements in copyCommandsAsClaudeSkills and
copyWithPathReplacement, legacy commands/gsd cleanup, CLAUDE.md ->
HERMES.md and "Claude Code" -> "Hermes Agent" content rewrites in
skills/agents/hooks, runtime-appropriate finish message.
- \`get-shit-done/bin/lib/core.cjs\`: add hermes to KNOWN_RUNTIMES;
add RUNTIME_PROFILE_MAP.hermes with OpenRouter-slug defaults
(Hermes is provider-agnostic; these defaults resolve across
OpenRouter, native Anthropic, and Copilot via Hermes' aggregator-
aware resolver, and are overridable per-tier via
model_profile_overrides.hermes.{opus,sonnet,haiku}).
- \`README.md\`: Hermes Agent in tagline, runtime list, verification
command, install/uninstall examples, \`--hermes\` flag reference.
- \`tests/hermes-install.test.cjs\`: new, 14 tests covering directory
mapping, HERMES_HOME env var precedence, install/uninstall
lifecycle, user-skill preservation, engine cleanup.
- \`tests/hermes-skills-migration.test.cjs\`: new, 11 tests covering
frontmatter conversion, path replacement (~/.claude/ ->
\$HERMES_HOME/skills/), CLAUDE.md -> HERMES.md, "Claude Code" ->
"Hermes Agent", stale skill cleanup, SKILL.md format validation.
- \`tests/multi-runtime-select.test.cjs\`: updated for new option
numbering (hermes=10, kilo=11, opencode=12, qwen=13, trae=14,
windsurf=15, all=16).
- \`tests/kilo-install.test.cjs\`: updated assertions for Kilo having
moved from option 10 to option 11.
Closes#2841
Implementation notes:
- Zero custom code paths: Hermes reuses copyCommandsAsClaudeSkills()
identical to Qwen Code / Antigravity pattern.
- Path replacement: ~/.claude/, \$HOME/.claude/, ./.claude/ ->
.hermes equivalents in skill/agent/hook content.
- Config precedence: --config-dir > HERMES_HOME > ~/.hermes (matches
how Hermes itself resolves its home directory).
- Legacy cleanup: removes commands/gsd/ if present from a prior
install, preserving dev-preferences.md (same as Qwen).
- No external dependencies added.
Testing: 5841 / 5841 tests pass (0 failures, 0 regressions)
- 14 new tests in hermes-install.test.cjs
- 11 new tests in hermes-skills-migration.test.cjs
- multi-runtime-select.test.cjs renumbered + 1 new test (single choice for hermes)
* fix: parse non-REQ IDs in gap-analysis and ignore table headers
* fix: parse requirement IDs from first traceability column only
---------
Co-authored-by: Tom Boucher <thomas.boucher@sas.com>
* fix(#2893): surface non-canonical plan filenames instead of silently returning zero plans
Reporter saw `plan_count: 0` from `/gsd:execute-phase` even though five
plan files existed on disk. Investigation showed the planner had written
files like `01-PLAN-01-foundation.md`, while `phase-plan-index`'s strict
filter (`f.endsWith('-PLAN.md') || f === 'PLAN.md'`) rejected them
silently — collapsing two distinct states into the same `plans: []`
return:
- directory truly has no plans (legit empty)
- directory has plans but the filter rejected them (user/agent error)
The canonical contract is documented in three places:
- `agents/gsd-planner.md` write_phase_prompt step (lines 1063-1080)
- `commands/gsd/plan-phase.md`
- `references/universal-anti-patterns.md` (rule 26)
It mandates `{padded_phase}-{NN}-PLAN.md` and explicitly forbids
`PLAN-NN.md` / `01-PLAN-01.md` / `plan-NN.md` etc. The strict filter is
correct per that contract. The bug is that the executor never tells the
user when the contract was violated — they just see `plan_count: 0`
with no signal.
Fix: add a diagnostic helper `describeNonCanonicalPlans()` that scans
the phase directory for files matching `*PLAN*.md` (the diagnostic net)
that the canonical filter rejected, excluding legit derivatives like
`*-PLAN-OUTLINE.md` and `*-PLAN.pre-bounce.md`. When offenders exist,
return a `warning` field naming each one and citing the canonical
pattern so the user knows what to rename to.
Wired into the three filter sites:
- `phase-plan-index` (the executor's main entry point)
- `phases list --type plans`
- `find-phase`
The strict filter itself is unchanged — existing canonical plans behave
identically. This is purely a diagnostic that converts silent-empty
into loud-with-actionable-error.
Tests:
- `phase-plan-index returns warning for reporter's exact filename
pattern (`01-PLAN-01-foundation.md`)`
- `truly empty dir does not emit a warning`
- `canonical plans + outline + pre-bounce files do not emit a warning`
Closes#2893
* test(#2893): add parity tests for find-phase and phases list --type plans warnings
CodeRabbit's only finding on the prior commit: I wired the warning into
three filter sites (`phase-plan-index`, `find-phase`,
`phases list --type plans`) but only `phase-plan-index` had test
coverage for the warning shape. The other two paths could silently
diverge during future refactors — exactly the silent-drift class of bug
this fix exists to prevent.
Add four parity tests mirroring the existing two:
- find-phase: non-canonical filenames produce a warning naming each
offender + citing the canonical pattern.
- find-phase: canonical plan + derivative files (PLAN-OUTLINE,
pre-bounce) produce no warning.
- phases list --type plans: same non-canonical case, but assert the
warning is prefixed with `${dir}: ` (this path aggregates across
phase directories so each offender is tagged with its dir).
- phases list --type plans: canonical case, no warning.
`node --test tests/phase.test.cjs`: 98/98 pass (was 94, +4 new).
* feat(#2792): namespace meta-skills retargeted at the post-#2790 surface
This branch is now based on #2790's HEAD (the consolidation PR) instead
of main, and every routing table targets the consolidated surface so a
user routed by a namespace meta-skill never lands at a deleted /
folded sub-skill.
Cross-PR inconsistencies the original PR #2825 carried (vs #2790):
- ns-ideate routed to gsd-note / gsd-add-todo / gsd-add-backlog /
gsd-plant-seed → all folded into gsd-capture by #2790. Now routes
to gsd-capture (the parent picks the mode from the user's intent).
- ns-context routed to gsd-scan and gsd-intel → folded into
gsd-map-codebase --fast / --query by #2790. Now routes to those
flag forms.
- ns-manage routed all workspace intent to gsd-list-workspaces (a
list-only entry) → CR also flagged the over-narrow target. #2790
folds into gsd-workspace; routing now points there.
- ns-workflow routed to gsd-research-phase → deleted outright by
#2790. Removed.
- ns-project routed to gsd-plan-milestone-gaps → deleted outright by
#2790. Removed.
- None of the namespaces previously surfaced #2790's new consolidated
skills (gsd-capture, gsd-phase, gsd-config, gsd-workspace,
gsd-progress). All five are now reachable through the routers.
- extract_learnings → extract-learnings (canonicalized by #2858).
Defect fixes within the namespace skills:
- Hyphen-form `name:` (gsd-workflow, …) per the canonical naming
contract — the colon-form addressed CR's drift complaint.
- `Skill` added to allowed-tools on every router. The body instructs
"Invoke the matched skill directly using the Skill tool" — without
Skill in the permission list the meta-skill cannot route at all.
New regression guard in tests/enh-2792-namespace-skills.test.cjs: every
gsd-* token in any namespace router's table column resolves to a
surviving commands/gsd/*.md file (or to a known consolidated parent for
flag-form targets like gsd-map-codebase --fast). This single test would
have caught every dead-end route the original PR shipped with.
Skill-count cap in tests/enh-2790-skill-consolidation.test.cjs now
filters out ns-*.md from its <= 63 cap. Namespace routers are
descriptor-only entries, not part of the consolidation surface that cap
is policing — they have their own contract in
tests/enh-2792-namespace-skills.test.cjs.
INVENTORY.md gains a "Namespace Meta-Skills" section with the 6 router
rows; INVENTORY-MANIFEST.json gains 6 entries; the headline count moves
59 → 65 to match.
Out of scope for this rebase: the gsd-health --context flag (PR #2825
advertised the contract but didn't implement it). That's a separate
feature concern and is left untouched here.
5908/5908 on `npm test`.
* feat(#2792): implement gsd-health --context utilization guard
The original PR #2825 advertised a `--context` flag on gsd-health with a
60%/70% utilization threshold table but never implemented the workflow
logic — CR caught it as a contract leak, the rebase deferred it. This
commit closes the gap with TDD red/green/refactor.
Math layer (pure):
- get-shit-done/bin/lib/context-utilization.cjs
classifyContextUtilization(tokensUsed, contextWindow) →
{ percent, state }
State boundaries use the exact ratio:
< 60% healthy / 60–70% warning / ≥ 70% critical (fracture point)
Display percent rounded for humans. Throws TypeError on non-integer
or out-of-range inputs.
- STATES = Object.freeze({ HEALTHY, WARNING, CRITICAL }) exported
so callers reference the names by symbol, not by literal string.
SDK CLI integration:
- get-shit-done/bin/gsd-tools.cjs
`validate context --tokens-used N --context-window M [--json]`
routes to the classifier, owns the recommendation copy (the
classifier intentionally does not — keeps the renderer free to
evolve without touching the math layer or its tests), and uses
core.output's rawValue path for the sync-flush guarantee.
- sdk/src/query/validate.ts + sdk/src/query/index.ts
TypeScript validateContext handler registered at 'validate.context'
and 'validate context'. Mirrors the CJS classifier inline (15 lines
of arithmetic; not worth a shared cross-language module).
User-facing wiring:
- commands/gsd/health.md frontmatter advertises --context, body
documents the three-state threshold table.
- get-shit-done/workflows/health.md adds a `context_check` step
that's reached only when --context is set. Step calls
`gsd-sdk query validate.context` with self-reported tokensUsed and
contextWindow, prints the SDK output verbatim, and ends. Includes
a TEXT_MODE plain-text fallback for non-Claude runtimes per #2012.
Tests:
- tests/context-utilization.test.cjs (17 tests) — pure-function
contract: state thresholds at every boundary, percent rounding,
input validation, return-shape (no recommendation field — that's
the renderer's job).
- tests/validate-context.test.cjs (9 tests) — SDK CLI plumbing:
arg parsing errors, JSON vs human rendering, recommendation copy
pinned per state.
- tests/enh-2792-namespace-skills.test.cjs (4 new tests) — markdown
contract: --context advertised in argument-hint, threshold table
in command body, context_check step exists in workflow, step
invokes gsd-sdk query validate.context with both flags.
Inventory bookkeeping:
- docs/INVENTORY.md "CLI Modules" 31 → 32; new row for
context-utilization.cjs.
- docs/INVENTORY-MANIFEST.json mirror.
5939/5939 on `npm test`.
Closes#2876 follow-up — CI on main fails because the punctuation test
in tests/gemini-namespacing.test.cjs hardcoded `/gsd-scan` as a known
command, but #2824 (consolidate 86 → 59 skills) removed scan.md from
commands/gsd/. The roster now correctly returns "scan is unknown, leave
unchanged" — the conversion is right, the test fixture is stale.
Swap `scan` for `health` in the punctuation test. Both are bedrock
commands; the test still exercises the original intent (period vs
exclamation handling on adjacent slash commands).
Note added so the next consolidation reviewer knows the swap pattern.
`npm test`: 5936/5936 pass.
* feat(#2833): parseStateMd reads phase-lifecycle frontmatter fields
Extend parseStateMd() to parse 4 new STATE.md frontmatter fields that drive
the phase-lifecycle status-line proposed in #2833:
- active_phase : phase number when orchestrator is in-flight, null when idle
- next_action : recommended next command when idle
- next_phases : YAML flow array of phase numbers for next_action
- progress : nested block with completed_phases / total_phases / percent
All fields default to undefined when absent — formatGsdState() (next commit)
degrades gracefully so existing STATE.md files keep rendering as before.
YAML scope intentionally narrow:
- Only top-level scalar keys (status, milestone, active_phase, next_action)
- Only single-line flow array for next_phases ([...])
- progress block requires 2-space indent for nested keys
Block sequences (- item over multiple lines) and inline comments inside
nested blocks are NOT parsed — keeping the regex-based parser predictable.
Comments outside frontmatter or after the closing --- still work.
Tests: all 27 existing tests still pass (no behavior change for STATE.md
files that don't carry the new fields).
Refs #2833
* feat(#2833): formatGsdState renders phase-lifecycle scenes + opt-in progress bar
Extend formatGsdState() with three lifecycle scenes that activate when the
new STATE.md frontmatter fields (added in the previous commit) are present.
Also append an opt-in progress bar to the milestone segment when
progress.percent is available.
Scenes (first match wins; falls through to the existing path otherwise):
1. active_phase set → 'v2.0 [██░] X% · Phase 4.5 executing'
(status field carries the lifecycle stage:
discussing / planning / executing / verifying)
2. active_phase null + → 'v2.0 [██░] X% · next execute-phase 4.5'
next_action set (idle state — surfaces what the user should
run next without opening STATE.md)
3. percent=100 (or → 'v2.0 [██████████] 100% · milestone complete'
completed=total)
4. (default fallback) → 'v1.9 Code Quality · executing · ph (1/5)'
(existing rendering, byte-for-byte preserved
when none of the new fields are populated)
Backward compat is the design priority:
- STATE.md files without the new fields render identically to v1.38.x
- progress bar is opt-in (empty string when percent absent)
- Each new scene only activates when its specific fields are populated
A new helper renderProgressBar() generates the 10-segment bar that matches
the existing context meter style (so the two bars on the status-line are
visually consistent).
Tests: 27/27 existing tests still pass.
Refs #2833
* test(#2833): cover parseStateMd lifecycle fields + formatGsdState scenes
26 new tests organized in 5 describe blocks, modeled after the existing
enh-2538-statusline-last-command.test.cjs convention:
parseStateMd #2833 lifecycle fields (7 tests)
- reads active_phase / next_action / next_phases / progress.percent
- 'null' literal handled correctly
- YAML flow array parsing (1 item, multiple items)
- progress nested block (3 fields)
- absent fields return undefined
formatGsdState #2833 lifecycle scenes (6 tests)
- Scene 1: active_phase set → 'Phase X.Y <stage>'
- Scene 2: idle + next_action → 'next <action> <phases>' (1+ phases)
- Scene 3: percent=100 OR completed=total → 'milestone complete'
formatGsdState #2833 backward compatibility (4 tests) — CRITICAL
- Legacy STATE.md (no new fields) renders byte-for-byte unchanged
- Empty state, partial state, progress-bar-opt-in all preserved
progress bar rendering (6 tests)
- 0% / 50% / 100% / clamping / opt-in absence
formatGsdState #2833 scene priority (3 tests)
- active_phase wins over next_action when both populated
- next_action wins over fallback when active_phase null
- percent=100 wins over fallback even with phase set
Combined run: 53/53 tests pass (existing 27 + new 26).
Refs #2833
* docs(#2833): describe phase-lifecycle frontmatter fields and rendering scenes
Add docs/STATE-MD-LIFECYCLE.md as the canonical reference for the four new
STATE.md frontmatter fields and the four status-line rendering scenes
introduced by this proposal:
- Frontmatter field reference (active_phase / next_action / next_phases /
progress.percent) with type and population semantics
- Why progress.percent is intentionally the phase dimension and not the
plans dimension (plans dimension trends optimistic when future phases
are unplanned)
- The four rendering scenes including their priority order
- Stage-label convention for Scene 1 (discussing / planning / executing /
verifying matching the four phase orchestrators)
- Frontmatter parsing constraints — frontmatter must start at file head,
no comments inside nested blocks, next_phases is single-line flow only
- Backward-compatibility guarantee (locked in by the test suite)
- Cross-links to the foundation issue #1989 and the read-side issues
this proposal helps close
The document deliberately scopes itself to the read-side (what the hook
parses, what it renders). Write-side SDK and workflow changes that
auto-maintain the fields are out of scope for this PR so each piece can
be reviewed independently — see the issue thread for the full proposal.
Refs #2833
* test(#2833): simplify '0% renders 10 empty segments' assertion
Address CodeRabbit nitpick — drop the convoluted assert.equal that built
the expected value via .replace() and rely on the existing assert.ok
includes-check. The behavior under test is unchanged; the assertion is
just easier to read.
Refs #2884 review comment
* feat(#2790): consolidate 86 gsd-* skills to 59 — zero functional loss
Closes#2790
- `capture.md` — absorbs add-todo (default), note (--note), add-backlog
(--backlog), plant-seed (--seed), check-todos (--list)
- `phase.md` — absorbs add-phase (default), insert-phase (--insert),
remove-phase (--remove), edit-phase (--edit)
- `config.md` — absorbs settings-advanced (--advanced),
settings-integrations (--integrations), set-profile (--profile);
settings.md retained as-is
- `workspace.md` — absorbs new-workspace (--new), list-workspaces
(--list), remove-workspace (--remove)
- `update.md` — adds --sync (absorbs sync-skills) and --reapply
(absorbs reapply-patches)
- `sketch.md` — adds --wrap-up (absorbs sketch-wrap-up)
- `spike.md` — adds --wrap-up (absorbs spike-wrap-up)
- `map-codebase.md` — adds --fast (absorbs scan) and --query (absorbs
intel)
- `code-review.md` — adds --fix (absorbs code-review-fix)
- `progress.md` — adds --next (absorbs next) and --do (absorbs do)
join-discord, research-phase, session-report, from-gsd2,
analyze-dependencies, list-phase-assumptions, plan-milestone-gaps
autonomous.md: updated Skill(skill="gsd:code-review-fix") →
Skill(skill="gsd:code-review", args="--fix --auto") to match
the consolidated skill name
- New: tests/enh-2790-skill-consolidation.test.cjs (48 tests)
- Updated: 14 existing test files redirected from deleted command paths
to their consolidated equivalents
- docs/INVENTORY.md: Commands count 86→59, ghost rows removed, new
consolidated rows added
- docs/INVENTORY-MANIFEST.json: regenerated to match filesystem
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* docs(#2790): add CHANGELOG entry for skill consolidation
* docs(#2790): update COMMANDS.md for 86→59 skill consolidation
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(#2790): address CodeRabbit review findings
- CHANGELOG.md: add --next alongside --do in progress flag list
- config.md: remove trailing space from --profile code span (MD038)
- COMMANDS.md: add required descriptions to /gsd-phase examples;
/gsd-phase without args errors, not interactive
- COMMANDS.md: add --next and --do to /gsd-progress flags table + examples
- test: convert content.includes('--reapply') to structural frontmatter
parse; add allow-test-rule comment for workflow content assertions
- test: replace redundant existsSync duplicate with assertion that verifies
the full consolidated flag surface (--sync | --reapply) in argument-hint
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(#2790): restore reapply-patches workflow and strengthen test assertions
- Create get-shit-done/workflows/reapply-patches.md: the #2790 consolidation
deleted the 14K combined command+workflow file (reapply-patches.md) but
update.md already referenced the workflow via execution_context_extended.
Restoring it fixes a silent behavioral gap where --reapply had no workflow
to load. Includes full three-way merge logic, hunk verification table
(Step 4), and the Hunk Verification Gate (Step 5) that blocks cleanup
until all user-added hunks are confirmed present in the merged output.
- Fix update.md: /gsd-reapply-patches → /gsd-update --reapply (stale ref)
- Fix reapply-verify-hunks.test.cjs: was checking existsSync(update.md) 8×;
now points to the workflow file and asserts real behavioral content
(Post-merge verification, Hunk presence check, Line-count check, backup
reference, per-file tracking, structural ordering)
- Fix reapply-patches.test.cjs: replace content.includes() stubs with
frontmatter-parsed argument-hint assertions; replace 4 existsSync(update.md)
no-ops with real assertions against the workflow content
- Fix edit-phase.test.cjs: /gsd-edit-phase → /gsd-phase (COMMANDS.md now
documents the consolidated command with --edit flag)
- Fix next-safety-gates.test.cjs: split OR predicates into independent
assertions — --next in progress.md and --force in next.md workflow
- Fix workspace.test.cjs: add allow-test-rule comment for routing content
checks (command routing text IS the deployed behavioral contract)
- Fix bug-2439 test: strengthen pre-flight assertion to verify gsd-sdk is
referenced (not just --profile)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: address CodeRabbit review findings (CR round 2)
- INVENTORY.md: update sync-skills.md row to reference /gsd-update --sync
instead of stale /gsd-sync-skills (absorbed in #2790)
- enh-2380-sync-skills.test.cjs: align INVENTORY.md assertion with the
corrected reference; was asserting the old /gsd-sync-skills name while the
manifest test correctly asserted /gsd-update, creating conflicting expectations
in the same suite
- reapply-verify-hunks.test.cjs: add explicit notEqual(-1) assertions for all
three anchors before the ordering check so a missing anchor produces a clear
failure instead of a false positive (writeIdx=-1 < verifyIdx=5 is true)
- bug-2439-set-profile-gsd-sdk-preflight.test.cjs: defer fs.readFileSync until
after the existence assertion; eager describe-level read caused the suite to
crash before the existence test could run, making it effectively dead code
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(#2790): address CR — INVENTORY routing + reapply test contract wording
Two unresolved CodeRabbit findings (Major):
- docs/INVENTORY.md: workflow-file table still pointed at obsolete
/gsd-do, /gsd-next, /gsd-note, /gsd-add-todo, /gsd-add-backlog,
/gsd-check-todos, /gsd-plant-seed slash commands. Re-route to the
consolidated /gsd-progress (--next, --do) and /gsd-capture (--note,
--backlog, --seed, --list) so the inventory is internally consistent.
- tests/reapply-verify-hunks.test.cjs: 'verification tracks per-file
status' asserted on phrasing that doesn't appear in reapply-patches.md
(the 'per-file' substring only matched accidentally via 'sequential
integer per file'). Switch to the actual contract text — Hunk
Verification Table, one row per hunk per file, verified column.
* test(#2790): update CR-INTEGRATION tests for consolidated --fix invocation
After the merge of main (which carries #2843's hyphen-form fix), the
consolidation in this branch absorbs gsd-code-review-fix into gsd-code-review
as the --fix flag. Update the two CR-INTEGRATION tests that previously
asserted on the standalone gsd-code-review-fix skill name to instead assert
on a gsd-code-review invocation carrying --fix in its arg tokens.
Tests still parse Skill() invocations structurally; only the asserted
skill-name + arg-token shape changed.
* test(#2790): scope success_criteria check to the <success_criteria> block
CodeRabbit nitpick: 'success criteria includes verification' did a
whole-file substring check, which can false-pass if the phrase appears
elsewhere in the document. Extract the <success_criteria>...</success_criteria>
block first via extractTagBlock() and assert against that scope only.
* fix(#2790): post-rebase reconciliation with main
- INVENTORY.md/JSON: add reapply-patches workflow row + bump count to 85
- autonomous.md: switch consolidated --fix invocation to hyphen Skill name
- analyze-dependencies test: assert COMMANDS.md does NOT document the
consolidated-away /gsd-analyze-dependencies entry (was: bare .includes())
* fix(#2790): address remaining CR findings — strengthen contract tests
Doc-fixes:
- INVENTORY.md: route transition.md & edit-phase.md rows to consolidated
/gsd-progress --next and /gsd-phase --edit (was: deleted /gsd-next, /gsd-edit-phase)
- config.md --profile branch: document #2439 pre-flight `command -v gsd-sdk`
guard + install hint BEFORE the gsd-sdk invocation (closes opaque
"command not found: gsd-sdk" regression path)
Test discipline (no-source-grep contract):
- bug-2439: replace bare `content.includes('gsd-sdk')` with structured
parse of <context> block + --profile branch; assert pre-flight token,
install hint, #2439 citation, and ordering vs gsd-sdk invocation
- edit-phase: parse INVENTORY.md edit-phase.md row's "Invoked by" column
and assert `/gsd-phase --edit` (not the deleted /gsd-edit-phase)
- next-safety-gates: tighten `--next` documentation contract — require
--next AND --force AND completeness routing (was OR-based, passed when
only --next present)
- reapply-patches: parse argument-hint flag list structurally; scan ALL
<execution_context*> blocks for the @-include of reapply-patches.md;
parse Hunk Verification Table header columns directly; locate Step 5
via heading parsing then assert (i) table reference, (ii) verified=no
gate, (iii) STOP/halt directive, (iv) explicit absent-table halt path
- workspace: parse frontmatter, tokenize argument-hint across multiple
bracketed segments, parse @-include targets from <execution_context>
rather than substring-matching the file body
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(#2876): yamlQuote description in Copilot/Antigravity/Trae/CodeBuddy SKILL.md
A description starting with `[BETA]` (or any YAML flow indicator —
`{`, `*`, `&`, `!`, `|`, `>`, `%`, `@`, backtick) is parsed as a flow
sequence/mapping by YAML 1.2-strict loaders. gh-copilot's frontmatter
loader fails closed:
✖ ~/.copilot/skills/gsd-ultraplan-phase/SKILL.md: failed to parse YAML
frontmatter: Unexpected scalar at node end at line 2, column 21:
description: [BETA] Offload plan phase to Claude Code's ultraplan…
Six emission sites in `bin/install.js` re-wrote the description without
quoting, while the Claude variant (`convertClaudeCommandToClaudeSkill`)
already routed it through `yamlQuote`. Brought all six in line:
- convertClaudeCommandToCopilotSkill
- convertClaudeAgentToCopilotAgent
- convertClaudeCommandToAntigravitySkill
- convertClaudeAgentToAntigravityAgent
- convertClaudeCommandToTraeSkill
- convertClaudeCommandToCodebuddySkill
Each now wraps the value in `yamlQuote(...)` so any leading character is
parser-safe.
Regression test (tests/bug-2876-skill-frontmatter-quote.test.cjs) drives
the four command converters and two agent converters through the
reporter's exact "[BETA] …" description plus a grab-bag of YAML flow
indicators, asserting the emitted `description:` value is a quoted YAML
scalar. Also round-trips the value through `JSON.parse` for converters
that don't apply runtime-name substitution to confirm fidelity.
Updated 7 pre-existing substring assertions in copilot-install.test.cjs
and antigravity-install.test.cjs that hard-coded the unquoted form.
Round trip: 5893/5893 pass on `npm test`.
Closes#2876
* test(#2876): structurally parse frontmatter instead of substring-grep
Addresses CodeRabbit's two nitpicks on PR #2881: the pre-existing
substring assertions in copilot-install.test.cjs (4 sites) and
antigravity-install.test.cjs (3 sites) only got bumped from the unquoted
form (`description: Diagnose...`) to the quoted-prefix form
(`description: "Diagnose...`). Both are still raw-string checks against
rendered YAML and drift on any quoting/order change — exactly what the
project's CONTRIBUTING.md "no-source-grep" testing standard exists to
prevent.
Add `parseFrontmatter()` to tests/helpers.cjs — a small parser that
handles the YAML scalar forms the install converters emit (double-quoted
JSON, single-quoted with `''` escape, bare). Throws if the content has
no closed `---` block so a regression in the emitter shape fails loudly
rather than silently returning {}.
Refactor the 7 description-substring sites to compare on parsed values:
the assertion now reads as `fm.description === 'Diagnose planning
directory health'` rather than `result.includes('description: "Diagnose
planning directory health')`. Same coverage of the #2876 quoting
behavior, no coupling to byte-level quote style.
`npm test`: 5893/5893 pass.
Closes#2876
* test(#2876): make parseFrontmatter delimiter check CRLF/whitespace tolerant
CR nitpick on PR #2881 (review at 03:08:08Z): parseFrontmatter()
splits on '\n' and compares each line strictly to '---'. A
Windows-authored skill file (CRLF endings) leaves a trailing '\r'
on every line, so '---\r' fails the equality check, and the helper
throws "no closed --- block" on perfectly valid input. Same problem
with whitespace-padded delimiter lines.
Switch to splitting on /\r?\n/ and comparing the trimmed line.
Helper is used by tests/copilot-install.test.cjs and
tests/antigravity-install.test.cjs, so this also de-flakes those
suites on Windows runners.
5893/5893 on `npm test`.
* fix(commands): normalize gsd slash namespace drift
* fix(#2855): address CodeRabbit findings on namespace drift PR
Three CR findings, all valid:
1. autonomous.md line 783 still had `gsd:discuss-phase` (the PR's own
normalization missed this line). Switched to `gsd-discuss-phase` and
updated the matching test in autonomous-interactive.test.cjs that was
asserting the now-retired colon form.
2. tests/bug-2543-gsd-slash-namespace.test.cjs source-grepped the
fix-slash-commands.cjs script with .includes() rather than driving
its transform behaviour. Refactored fix-slash-commands.cjs to export
a pure transformContent(src, cmdNames) function, kept the CLI behaviour
unchanged via require.main, and replaced the source-grep block with
five behavioural cases: rewrite, multi-occurrence, idempotence on
canonical input, no-op on gsd-sdk/gsd-tools, and word-boundary safety.
3. tests/bug-2808-skill-hyphen-name.test.cjs matched `name:` anywhere
in SKILL.md; a stray name: in the body could satisfy the assertion.
Scoped the lookup to the YAML frontmatter block via the suggested
diff (parse the leading --- ... --- region first, then find name:
inside it).
Full suite: 5854/5854 passing.
* fix(#2855): address remaining CodeRabbit findings on PR #2858
Three structural concerns flagged on the namespace-drift fix PR:
1. scripts/fix-slash-commands.cjs:24 — `buildPattern([])` compiled
`/gsd:()(?=[^a-zA-Z0-9_-]|$)/g`. The empty capture group still
matches any `/gsd:` token followed by a non-word boundary
(whitespace, EOL, punctuation), rewriting it to a stray `/gsd-`.
Verified live: `transformContent("/gsd:", [])` → `"/gsd-"`. Added
a guard returning null from `buildPattern` on empty input and
updated `transformContent` and `processDir` to no-op when the
pattern is null.
2. tests/autonomous-interactive.test.cjs:44-47 — assertion was
`content.includes('gsd-discuss-phase') && content.includes('INTERACTIVE')`,
which would false-pass on any unrelated co-occurrence (e.g.
`INTERACTIVE=""` initialization plus a stray `gsd-discuss-phase`
prose mention). Replaced with a structural extraction: locate the
`**If \`INTERACTIVE\` is set:**` branch, bound it by the next
`**If` / `<step>` boundary, and assert the
`Skill(skill="gsd-discuss-phase", ...)` invocation lives inside
that region. Tolerates whitespace around `(`, `skill`, and `=`.
3. tests/bug-2808-skill-hyphen-name.test.cjs:104 — colon-call regex
was `Skill\(skill=...` and missed valid formatting like
`Skill(skill = "gsd:cmd")` or `Skill( skill = ...)`. Loosened to
`Skill\(\s*skill\s*=\s*...` so reformatting drift can't slip past
the namespace guard.
Verification: 5854/5854 pass on `npm test` from the rebased branch.
* fix(#2855): drop pre-validation filter that hid namespace drift
CR finding on tests/bug-2808-skill-hyphen-name.test.cjs:128: the test
collected generated skill directories with
`.filter(entry => entry.isDirectory() && entry.name.startsWith('gsd-'))`,
then validated namespace invariants over that filtered list. Anything
that violated the prefix invariant — `gsd:extract-learnings` (colon
form), `extract_learnings` without prefix, `Gsd-foo` mis-cased — would
silently disappear from the iteration and the test would falsely pass.
Drop the `startsWith('gsd-')` filter so every generated directory shows
up. Add explicit assertions before the existing per-skill loop:
- directory list is non-empty (catches a broken converter that
produces nothing)
- every directory begins with `gsd-`
- every directory contains no `:`
- every directory contains no `_`
Re-audited the full PR diff for the same anti-pattern: only this one
site filtered before validating the namespace; bug-2643 and
commands-doc-parity also use `readdirSync().filter()` but only by file
extension, which is correct.
5854/5854 on `npm test`.
* fix(#2855): address remaining CR findings (1 active + 2 nitpicks)
Three findings on PR #2858, all the same root cause: input narrowing
before validation lets drift slip past the guards.
1. tests/bug-2808-...:104 (active) — `colonCallRe` captured local names
with `[a-z0-9-]+`, which excluded the underscore. A drift like
`Skill(skill="gsd:extract_learnings")` (deprecated colon syntax with
the old underscore filename) silently slid through. Broadened the
capture to `[^'"\s)]+` so any malformed local name is surfaced; surrounding pattern (whitespace tolerance, escape support, flags)
unchanged.
2. tests/bug-2643-...:43 (nitpick) — `extractSkillNamesHyphen` and
`extractSkillNamesColon` had the same over-strict capture plus
relied on a single regex over raw bytes, which the project test-
rigor memory bans (`feedback_no_source_grep_tests.md`). Replaced
with `extractSkillCalls(content)` — a small structural extractor
that walks `Skill(` openers, locates each call's matching `)`,
parses the body's `skill = "..."` keyword argument with permissive
whitespace + quoting + escape handling, and returns
`{ name, raw }` records. The two namespace-form helpers become
thin filters over the structured output. Tightened the body class
to `[^'"\\]+` so a trailing escape `\` before the closing quote
(as in `Skill(skill=\"gsd-foo\", …)` written inside another string
context) doesn't get included in the captured name.
3. tests/bug-2543-...:44 (nitpick) — `DOC_SEARCH_FILES` was a hand-
curated 7-entry array. Every doc added in the future would silently
weaken drift detection until someone remembered to extend the list.
Replaced with `discoverDocSearchFiles(ROOT)`: globs every `.md`
under `docs/` and adds `README.md` if present. New docs are picked
up automatically.
Re-audited the diff surface for similar narrowings; no other sites
filter or constrain before validating namespace invariants.
5854/5854 on `npm test`.
* fix(#2855): recurse docs/ tree so localized translations are scanned too
CR finding: discoverDocSearchFiles() stopped at docs/*.md, leaving
localized translation trees (docs/ja-JP/, docs/zh-CN/, docs/ko-KR/,
docs/pt-BR/) and other nested doc collections (docs/skills/,
docs/superpowers/) invisible to the namespace-drift invariant.
Verified the gap: docs/ has 6 nested directories with ~30 .md files
that the previous top-level-only scan was skipping. None contain
/gsd: references today, but a future translation update or new
doc subdir could leak drift.
Switch to an iterative stack walk so every .md under docs/ is scanned
regardless of depth. Stack form (rather than recursion) avoids the
risk of running into the call-stack limit on deep doc trees.
5854/5854 on `npm test`.
---------
Co-authored-by: Tom Boucher <trekkie@nomorestars.com>
* fix(install): use colon namespace for Gemini slash commands and help reference
This fixes unexecutable command recommendations in Gemini CLI by correctly
namespacing slash commands (/gsd: instead of /gsd-) in all installed
artifacts (agents, commands, workflows).
- Implements a lazy command roster discovery to ensure 100% accurate
conversion and protect file paths, URLs, and agent names.
- Adds isolated behavioral and unit tests covering all boundary cases.
- Fixes hardcoded command strings in banners and help output.
Closes#2783
* fix(install): close roster gaps in Gemini /gsd- → /gsd: conversion (#2783)
Addresses adversarial review findings on PR #2768:
- Restore regex boundaries (lookbehind + extension lookahead). Roster-only
matching was insufficient: a URL like `https://example.com/gsd-plan-phase`
ends in a known command and would be incorrectly converted. Boundaries +
roster now agree before any conversion fires.
- Smarter trailing lookahead `(?!\.[a-z])` distinguishes file extensions
(`.cjs`, `.md`) from sentence-ending punctuation (`.` at end of input or
before whitespace), so `/gsd-help.` correctly converts.
- Fail loud on missing roster. `commands/gsd/` not found previously fell
through to an empty Set, silently no-op'ing every conversion — exactly the
bug this code exists to prevent. Now emits a one-shot console.warn (gated
on GSD_TEST_MODE) before returning the empty set.
- Drop unnecessary `i` flag — GSD commands are always lowercase; matching
uppercase tokens against a lowercase roster always misses anyway.
- Export `_resetGsdCommandRoster` for test isolation against the module-level
cache.
Test additions pin the actual safety property of the roster check by using
KNOWN command names embedded in URLs and sub-paths — the cases the prior
tests didn't reach because they used `gsd-tools` (not in roster). Added a
roster-load assertion that fails loudly if the empty-Set fallback path
silently neutralises conversions.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* fix(install): centralize <sub> stripping and add structural test assertions
CodeRabbit findings on the prior commit:
- (actionable) Centralizing the Gemini conversion through
convertClaudeToGeminiMarkdown dropped the stripSubTags() call that the
inline command path used to make before TOML conversion. Move stripSubTags
inside convertClaudeToGeminiMarkdown so command/agent/non-command Gemini
outputs all have <sub> consistently stripped. Remove the now-redundant
stripSubTags call in convertClaudeToGeminiAgent (single source of truth).
- (nitpick) Replace `.includes()` checks in the TOML test with structured
parsing — JSON-decode each TOML value and assert on parsed fields, per
the project's "tests parse, never grep" convention.
- (nitpick) Strengthen the install behavioral test to read a real installed
artifact (.gemini/commands/gsd/plan-phase.toml), parse it, and assert the
prompt body actually contains a /gsd: reference and no unconverted
/gsd-plan-phase. A directory-only check would have passed even if every
conversion silently no-op'd.
- Add a regression test that <sub> tags are stripped through the
convertClaudeToGeminiMarkdown pipeline.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
---------
Co-authored-by: Tom Boucher <trekkie@nomorestars.com>
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
* fix(#2851): replace bare gsd-tools invocations with absolute path
`gsd-tools` is not a published bin entry — package.json declares only
get-shit-done-cc and gsd-sdk. The shipped invocation pattern is
`node "$HOME/.claude/get-shit-done/bin/gsd-tools.cjs" <subcommand>`,
used by every other workflow file.
Two leaked bare invocations:
- get-shit-done/workflows/plan-phase.md §13e (gap-analysis)
— reported in #2851; gap-analysis silently skipped on every plan-phase run
- get-shit-done/workflows/ingest-docs.md §finalize (commit)
— caught by the new structural test; ingest-docs commit step was broken
Both updated to canonical absolute-path form.
Adds tests/bug-2851-workflow-bare-gsd-tools.test.cjs which parses every
markdown file under get-shit-done/workflows/, extracts shell-fenced code
blocks, tokenizes each line, and asserts no token in command position is
the bare string `gsd-tools` (the trailing `.cjs` is a different token).
The test also asserts plan-phase.md's gap-analysis call uses the canonical
`node …/gsd-tools.cjs` form.
Closes#2851
* fix(#2851): catch third bare gsd-tools call in ingest-docs.md init
After the first commit, the structural test was strengthened to detect
bare `gsd-tools` inside `$(...)` and backtick command-substitution forms.
The improved test surfaced a third leak:
ingest-docs.md:55: INIT=$(gsd-tools init ingest-docs)
Fixed to canonical form
INIT=$(node "$HOME/.claude/get-shit-done/bin/gsd-tools.cjs" init ingest-docs)
plus the standard `@file:` handoff line that every other workflow uses
when capturing INIT (required by tests/windows-robustness.test.cjs).
Updated tests/bug-2801-ingest-docs-handler.test.cjs to match either
the bare `gsd-tools init ingest-docs` or canonical
`gsd-tools.cjs" init ingest-docs` form — the test's intent is to verify
the dispatch handler is wired, not to lock the bare-bin form that #2851
removes.
Closes#2851
* test(#2851): tighten ingest-docs and gap-analysis assertions to canonical form
CodeRabbit caught two soft assertions in the regression tests:
1. tests/bug-2801: the init-ingest-docs assertion accepted both the
legacy bare `gsd-tools` form and the canonical node-path form.
Since #2851 is the fix that removes the bare form, the test should
only accept the canonical absolute-path invocation. Switched to
parsed-bash-block extraction with an anchored regex on the full
`node "$HOME/.claude/get-shit-done/bin/gsd-tools.cjs"` path.
2. tests/bug-2851: the gap-analysis assertion used two loose
.includes()/word-boundary checks. Replaced with a single
assert.match() against the full canonical path so non-canonical
forms fail.
* test(#2851): env-assignment skip accepts lowercase identifiers too
CodeRabbit caught: the cmdIdx-skip regex /^[A-Z_][A-Z0-9_]*=/ only
matched uppercase variable names, so a line like `tmp=1 gsd-tools init`
would tokenize to ['tmp=1','gsd-tools','init'], the regex would fail on
'tmp=1', cmdIdx would stay at 0, and the command-position check would
compare 'tmp=1' against 'gsd-tools' — false negative.
POSIX shell variable names are [A-Za-z_][A-Za-z0-9_]*. Widen the regex
to match the actual lexical rule. Existing uppercase forms still work
(FOO=bar gsd-tools); now lowercase forms (tmp=1 gsd-tools) and mixed
case forms are also detected.
* fix(#2866): Codex installer strips legacy hooks at end-of-file without trailing newline
The four shape-strip regexes in `bin/install.js` (Codex install path)
required `\r?\n` at end. A stale GSD hook block sitting at end-of-file
without a trailing newline (common — many editors strip them, and the
legacy installer never wrote one) failed every shape, the installer
saw `gsd-check-update` already present, skipped writing the new
Nested-AoT block, and Codex 0.125+ refused to load with
invalid type: map, expected a sequence in `hooks`
Root cause + fix
================
Each shape's terminator changed from `\r?\n` to `(?:\r?\n|$)`, so
end-of-file is also a valid terminator.
Strip logic was lifted into a new pure helper
`stripStaleGsdHookBlocks(configContent)` that the install pipeline now
calls in place of the inline replace chain. The helper is exported via
the GSD_TEST_MODE module.exports for direct unit-test coverage.
Regression test
===============
`tests/bug-2866-codex-strip-no-trailing-newline.test.cjs` exercises
all four historical shapes (Shape 1 — pre-#1755 gsd-update-check;
Shape 2 — flat [[hooks]]+gsd-check-update; Shape 3 — single
[[hooks.SessionStart]] without nested .hooks; Shape 4 — correct
two-block nested) twice each: once with a trailing newline (regression
guard against the existing behavior) and once at end-of-file without a
trailing newline (the reporter's exact repro).
It also asserts:
- the helper is a no-op when no GSD reference is present, and
- Shape 4 strip does not leave an orphaned [[hooks.SessionStart]]
header behind (the same ordering invariant the inline code relied on).
The helper is loaded via `package.json` `bin` field, not a hardcoded
path — `tests/bug-2866-codex-strip-no-trailing-newline.test.cjs`
parses package.json and resolves `pkg.bin['get-shit-done-cc']` to
require the installer.
Closes#2866
* test(#2866): assert TOML structure, not raw-text substrings
CodeRabbit caught the strip assertions using `.includes()` against
raw TOML output. Added a small line-structural parseTomlShape() helper
(table headers + dotted-path key/value map, comments stripped) and
rewrote the assertions to:
- Verify no [[hooks.* table header survives the strip
- Verify no key carries a stale gsd-(update|check)-(check|update) value
- Verify history.persistence is preserved as the parsed string "save-all"
Behaviour is unchanged (the strip function under test is not modified).
The assertions now check structural shape rather than substring presence,
which catches re-shaping regressions that text matching would miss.
No new dependencies — the parser is local to the test and handles only
the small well-formed TOML these tests construct.
* refactor(#2866): replace regex hook strip with TOML AST removal
Per CR feedback on PR #2870: the regex-driven `stripStaleGsdHookBlocks`
implementation was fragile to whitespace, indentation, and key-ordering
variations the regression test never exercised. Variations the regex
silently leaked (verified before the rewrite):
- Shape 4 with an extra blank line between parent/child tables
- Shape 2/3 with `command` ordered before `event`
- Shape 3 with an extra `timeout = 5000` key — worse than a leak: the
regex matched only the command line, leaving `timeout = 5000`
orphaned outside any TOML table (invalid TOML)
- Tight whitespace `event="SessionStart"` (no spaces around `=`)
The structural rewrite uses the TOML parser already present in this file
(`getTomlTableSections` + `getTomlLineRecords` + `parseTomlValue` +
`removeContentRanges` + `collapseTomlBlankLines`):
1. Find every section whose path is `hooks` or starts with `hooks.`.
2. For each, walk the section's line records and parse `command` values
structurally — match by basename equality (`gsd-update-check.js` or
`gsd-check-update.js`), never by regex on raw bytes.
3. Detect orphaned `[[hooks.SessionStart]]` parents: empty body and a
stale child immediately follows → mark for removal.
4. Extend each removal range backward through any preceding
`# GSD Hooks` marker line (detected via line records, not text scan).
5. Remove ranges atomically and collapse resulting blank-line runs.
Legacy hook basenames are hoisted to template-literal constants so the
existing `install-hooks-copy.test.cjs` quoted-literal guard continues to
catch accidental *registration* of the inverted filename, while strip
detection (which legitimately needs both names) bypasses it.
Test coverage added: 8 new sub-tests exercising the four whitespace/
ordering variations (with and without trailing newline) plus a
`[[hooks.UserPromptSubmit]]` user-authored hook to guarantee the strip
only touches GSD-managed sections. 20/20 in the file, 5867/5867 in the
full suite.
* fix(#2838): SUMMARY rescue handles gitignored .planning explicitly
The pre-fix rescue used `git ls-files --modified --others --exclude-standard`
to detect uncommitted SUMMARY.md before worktree removal. When projects
gitignore .planning/, --exclude-standard filters out the very files the
rescue is meant to save, the rescue branch is skipped, and `git worktree
remove --force` permanently deletes the SUMMARY.
Replace both rescue blocks (quick.md, execute-phase.md) with a
filesystem-level find + cp rescue that bypasses gitignore entirely and
avoids the worktree↔main commit/merge cascade. cmp -s makes it idempotent.
Adds tests/bug-2838-summary-rescue-gitignored-planning.test.cjs which
extracts each rescue block, runs it against a real temp repo with a
gitignored .planning/, and asserts the SUMMARY survives worktree removal.
* test(#2838): assert rescue block exits 0 in idempotency test
CodeRabbit (Minor): the idempotency test pre-creates the destination
SUMMARY.md, so even a syntax/runtime error in the rescue block would
silently false-pass. Add an explicit r.status === 0 assertion.
* fix(#2836): audit-open quick SUMMARY filename + UAT terminal-status drift
Fixes two convention drifts in bin/lib/audit.cjs that produced false-positive
"open" items at every milestone close:
1. scanQuickTasks: looked for bare `SUMMARY.md`, but workflows/quick.md
mandates `${quick_id}-SUMMARY.md`. Now matches either filename so quick
tasks created via the documented workflow are recognized.
2. scanUatGaps: only treated `status: complete` as terminal, but
workflows/execute-phase.md uses `status: resolved` post-gap-closure.
Now treats both `complete` and `resolved` as terminal, with `result:
all_pass` as a fallback when status is absent.
Also reconciles workflows/help.md one-liner that referenced bare
`SUMMARY.md` so docs match the authoritative quick.md workflow.
Adds tests/bug-2836-audit-open-summary-uat-drift.test.cjs with 6
structural regression tests covering both fixes plus no-regression cases.
* refactor(#2836): hoist TERMINAL_UAT_STATUSES outside scanUatGaps loop
Address CodeRabbit nitpick: the Set was being recreated on each UAT file
iteration. Hoist to module scope so it is constructed once.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
* fix(#2829): gsd-sdk resolvable in local-mode installs
Local-mode installs previously short-circuited installSdkIfNeeded() the
moment opts.isLocal was true, leaving every `gsd-sdk query …` call site
unable to resolve the binary on PATH. The published tarball ships
sdk/dist/cli.js and bin/gsd-sdk.js regardless of mode, and the shim
resolves the CLI relative to its own __dirname — so the same self-link
strategy that powers npx-cache global installs (#2775) also works for
local installs. We now run the shared self-link path whenever the dist
is present, and only fall back to a non-fatal warning + early return
when the dist is genuinely missing (preserving the #2678 contract).
* test(#2829): correct precondition comment about ~/.local/bin
Address CodeRabbit feedback — the test does not create ~/.local/bin,
so reword the inline precondition to "any HOME bin candidate remains
off-PATH" to match what the test actually sets up.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
* fix(#2835): align CR-INTEGRATION tests with hyphen namespace
PR #2819 changed autonomous.md skill invocations from `gsd:code-review`
(colon) to `gsd-code-review` (hyphen). Tests still asserted the legacy
colon form against the user-installed plugin dir (which lags the repo).
Switch tests to:
- Read autonomous.md from the canonical repo WORKFLOWS_DIR (not the
plugin install location, which can be stale)
- Parse `Skill(skill="...")` invocations structurally instead of
substring matching, and assert the canonical hyphen form is present
while explicitly rejecting the legacy colon form.
Closes#2835
* test(#2835): parse Skill() invocations structurally in CR-INTEGRATION tests
Replace raw-text regex/.includes() assertions with a proper parser that
walks autonomous.md, skips escaped string contexts, and yields
[{ skill, args }] objects. The three CR-INTEGRATION tests now assert
against parsed fields and tokenized args (not substring matches),
addressing CodeRabbit feedback on PR #2843.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
* fix(#2831): expand HOME in OpenCode skill/template paths
OpenCode does not shell-expand $HOME in @file references on any platform —
the literal `@$HOME/...` path is resolved relative to the config command/
dir, producing `command/$HOME/...` (file not found). The previous fix for
#2376 only guarded Windows; extend to all platforms.
Closes#2831
* test(#2831): assert behavior via exported computePathPrefix, not source grep
Addresses CodeRabbit review on PR #2842:
- Extracts pathPrefix logic into a named, test-exported computePathPrefix
helper in bin/install.js (no behavior change at the call site).
- Rewrites bug-2376 and bug-2831 regression tests to call the exported
function directly instead of regex-matching install.js source text,
per the repo's no-source-grep testing standard.
- Wraps temp-dir test setup in try/finally so cleanup runs on assertion
failures (no leaked tmp dirs).
* fix(#2839): make /gsd-code-review-fix cleanup transactional
Cleanup tail in agents/gsd-code-fixer.md previously did 'git worktree
remove' without any recovery marker. If the process was killed between
fix commits and worktree removal, the orphan worktree + branch survived
with no resume path — the next run had no way to discover or finish
the cleanup.
Introduce a recovery sentinel at ${phase_dir}/.review-fix-recovery-pending.json
with strict ordering:
- Sentinel written AFTER 'git worktree add' succeeds (never points at a
worktree that does not exist).
- Sentinel removed ONLY AFTER 'git worktree remove' returns successfully
(interruption between commits and removal leaves a sentinel behind).
- New runs detect a pre-existing sentinel, force-remove the recorded
orphan worktree, then drop the stale sentinel before continuing —
making the agent self-healing after a crash.
Closes#2839
* fix(#2839): harden sentinel JSON parse and scope ordering assertion
Address CodeRabbit review feedback on PR #2846:
- agents/gsd-code-fixer.md: Guard the recovery-sentinel JSON parse with
try/catch so a corrupted/truncated sentinel (a realistic crash artifact)
emits a warning and yields an empty prior_wt instead of aborting setup.
This preserves the self-healing recovery path even when the sentinel
itself is the casualty of the original crash.
- tests/bug-2839-review-fix-transactional-cleanup.test.cjs: Scope the
cleanup-ordering assertion to the cleanup-tail section of the
setup_worktree step rather than first global occurrences. Previously
the assertion could pass on pre-recovery references even if cleanup-tail
ordering regressed. The regex also now accepts the shell-variable form
(\`rm -f \"\$sentinel\"\`) used in the cleanup tail.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
Adds Hermes Agent as a supported installation target. Users can run
\`npx get-shit-done-cc --hermes\` to install all 86 GSD commands as
skills under \`~/.hermes/skills/gsd-*/SKILL.md\`, following the same
open skill standard as Claude Code 2.1.88+, Qwen Code, Antigravity,
Trae, Augment, and Codebuddy.
Hermes Agent is an open-source AI agent framework by Nous Research
(NousResearch/hermes-agent, MIT). Its skill loader accepts the Claude
skill format as-is: frontmatter parsed with PyYAML SafeLoader (unknown
keys like \`allowed-tools\` / \`argument-hint\` ignored), body XML tags
(\`<objective>\`, \`<execution_context>\`, \`<process>\`) passed directly
to the model. Compatibility proven end-to-end with all 86 GSD skills
loading cleanly, \`skill_view()\` returning full bodies, and
\`build_skills_system_prompt()\` emitting them into the agent system
prompt — zero Hermes code changes required.
Changes:
- \`bin/install.js\`: --hermes flag, getDirName/getGlobalDir/getConfigDirFromHome
support, HERMES_HOME env var (native to Hermes — used for profile
mode / Docker deploys), install/uninstall pipelines, interactive
picker option 10 (alphabetical: between Gemini and Kilo), .hermes
path replacements in copyCommandsAsClaudeSkills and
copyWithPathReplacement, legacy commands/gsd cleanup, CLAUDE.md ->
HERMES.md and "Claude Code" -> "Hermes Agent" content rewrites in
skills/agents/hooks, runtime-appropriate finish message.
- \`get-shit-done/bin/lib/core.cjs\`: add hermes to KNOWN_RUNTIMES;
add RUNTIME_PROFILE_MAP.hermes with OpenRouter-slug defaults
(Hermes is provider-agnostic; these defaults resolve across
OpenRouter, native Anthropic, and Copilot via Hermes' aggregator-
aware resolver, and are overridable per-tier via
model_profile_overrides.hermes.{opus,sonnet,haiku}).
- \`README.md\`: Hermes Agent in tagline, runtime list, verification
command, install/uninstall examples, \`--hermes\` flag reference.
- \`tests/hermes-install.test.cjs\`: new, 14 tests covering directory
mapping, HERMES_HOME env var precedence, install/uninstall
lifecycle, user-skill preservation, engine cleanup.
- \`tests/hermes-skills-migration.test.cjs\`: new, 11 tests covering
frontmatter conversion, path replacement (~/.claude/ ->
\$HERMES_HOME/skills/), CLAUDE.md -> HERMES.md, "Claude Code" ->
"Hermes Agent", stale skill cleanup, SKILL.md format validation.
- \`tests/multi-runtime-select.test.cjs\`: updated for new option
numbering (hermes=10, kilo=11, opencode=12, qwen=13, trae=14,
windsurf=15, all=16).
- \`tests/kilo-install.test.cjs\`: updated assertions for Kilo having
moved from option 10 to option 11.
Closes#2841
Implementation notes:
- Zero custom code paths: Hermes reuses copyCommandsAsClaudeSkills()
identical to Qwen Code / Antigravity pattern.
- Path replacement: ~/.claude/, \$HOME/.claude/, ./.claude/ ->
.hermes equivalents in skill/agent/hook content.
- Config precedence: --config-dir > HERMES_HOME > ~/.hermes (matches
how Hermes itself resolves its home directory).
- Legacy cleanup: removes commands/gsd/ if present from a prior
install, preserving dev-preferences.md (same as Qwen).
- No external dependencies added.
Testing: 5841 / 5841 tests pass (0 failures, 0 regressions)
- 14 new tests in hermes-install.test.cjs
- 11 new tests in hermes-skills-migration.test.cjs
- multi-runtime-select.test.cjs renumbered + 1 new test (single choice for hermes)
* fix(#2787): track fenced code blocks in extractCurrentMilestone
The milestone-end search used a multiline regex against the raw
restContent string. Lines inside fenced code blocks (``` or ~~~)
that matched the milestone-heading pattern (e.g. `# note v1.0`)
prematurely set sectionEnd, hiding all phases after the block from
roadmap analyze, roadmap get-phase, and every downstream command.
Replace the regex match with a line-by-line scan that tracks fence
state. Lines inside an open fence are skipped regardless of content.
Adds three regression tests covering backtick fences, tilde fences,
and the roadmap get-phase code path.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(#2787): track fence delimiter instead of toggling bare boolean
Replace the inFence boolean with fenceChar/fenceLen tracking so that
indented fences (up to 3 leading spaces) and mixed-delimiter content
(~~~ inside a backtick fence) are parsed correctly. A closing fence
is only recognised when it uses the same character as the opening
delimiter and has at least the same run length, matching the CommonMark
spec.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(#2787): require fence-only closing line — reject info-string lines as closers
A closing fence delimiter must contain only optional trailing whitespace.
A line like \`\`\`js inside an open fence has an info string and must not
close it. The previous regex /^\s{0,3}([`~]{3,})/ matched the opening of any
such line, so the closing check could toggle fenceChar off on an info-string
line and expose subsequent heading-like content to the milestone-end detector.
Fix: capture the trailing portion of every fence-candidate line and only clear
fenceChar when trailing matches /^\s*$/ (per CommonMark §4.5).
Adds a regression test covering the ```text / ```js nesting scenario.
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(#2791): GSD_WORKSTREAM env var respected by gsd-sdk query + gsd-tools bin alias
Two fixes for gsd-sdk binary issues:
**Issue 1 — Binary name collision:**
Both `get-shit-done-cc` and `@gsd-build/sdk` declare `bin: { "gsd-sdk": ... }`.
Added `"gsd-tools": "bin/gsd-sdk.js"` to `package.json` bin so users with the
collision can invoke `gsd-tools query <cmd>` as a conflict-free alternative.
**Issue 2 — Query registry not workstream-aware:**
`gsd-sdk query` commands ignored `GSD_WORKSTREAM` env var, always reading from
the root `.planning/` even when a workstream was active. `gsd-tools.cjs` reads
`GSD_WORKSTREAM` via `planningDir()`, so all ~35 `gsd-sdk query` call sites in
workflow files were broken in workstream-scoped projects.
Fix: added env var fallback in `sdk/src/cli.ts` — when `--ws` is not provided,
`GSD_WORKSTREAM` is used (with name validation; invalid values are silently
ignored, matching CJS behaviour).
Regression test: `tests/bug-2791-sdk-workstream-env.test.cjs`
Closes#2791
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(#2791): address CodeRabbit — precedence test, invalid env fallback assertion, bash fence
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(#2805): add regression test — archived phase fallback already fixed in source
getPhaseInfoWithFallback already discards archived disk matches when the
current ROADMAP lists the phase (line 133: phaseInfo?.archived &&
roadmapPhase?.found). The regression test confirms this behavior and
prevents the bug from being reintroduced by future refactors.
Regression test: tests/bug-2805-archived-phase-fallback.test.cjs
(3 tests: phase_dir null, phase_found true, phase_name from ROADMAP)
* fix(#2805): address CodeRabbit — exact phase_name assertion, bash fence
* fix(#2788): audit-uat reads frontmatter human_verification array
parseVerificationItems only searched the body for a '## Human Verification'
section. gsd-verifier writes items to the frontmatter human_verification:
YAML array, so audit-uat returned total_items: 0 for all such files.
Two fixes:
1. Read frontmatter human_verification: array first (via extractFrontmatter);
return those items if present (primary path for gsd-verifier output).
2. Relax the body-section heading regex to accept underscore separators and
parenthetical suffixes (e.g. '## human_verification (action required)').
Regression test: tests/bug-2788-audit-uat-frontmatter.test.cjs
* fix(#2788): address CodeRabbit — trim whitespace entries, support hyphenated headings, bash fence
* fix(#2801): add ingest-docs handler to gsd-tools init dispatch
The `/gsd-ingest-docs` workflow was broken because `workflows/ingest-docs.md`
called `gsd-sdk query init.ingest-docs` but the installed binary is `gsd-tools`,
and `gsd-tools init` had no `ingest-docs` case in its dispatch switch.
- Added `cmdInitIngestDocs` function to `init.cjs` and exported it; returns
`project_exists`, `planning_exists`, `has_git`, `project_path`, `commit_docs`
- Added `case 'ingest-docs'` to the `init` switch in `gsd-tools.cjs`
- Updated `workflows/ingest-docs.md` to call `gsd-tools init ingest-docs`
(line 55) and `gsd-tools commit` (line 292) instead of `gsd-sdk query ...`
- Regression test: `tests/bug-2801-ingest-docs-handler.test.cjs`
Closes#2801
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(#2801): address CodeRabbit — commit_docs assertion, broader gsd-sdk detection, bash fence
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(#2808): SKILL.md name uses hyphen form for Claude Code autocomplete
skillFrontmatterName() was converting gsd-<cmd> to gsd:<cmd> (colon) so
installed SKILL.md files had name: gsd:add-phase etc. Claude Code surfaces
this name in autocomplete, showing the deprecated colon form to users even
though the hyphen form is canonical everywhere else.
Root cause: the colon form was needed because workflows called
Skill(skill="gsd:<cmd>"). All 4 remaining colon-form Skill() calls in
autonomous.md and execute-phase.md are updated to hyphen form.
skillFrontmatterName() now returns the hyphen dir name unchanged.
Updated 4 existing tests that asserted colon form.
Regression test: tests/bug-2808-skill-hyphen-name.test.cjs
* fix(#2808): address CodeRabbit — bash/text fences, structured test assertions, fail-loud on errors
* fix(#2796): roadmap update-plan-progress accepts --phase flag form
roadmap-update-plan-progress used positional-only arg parsing: args[0].
When execute-phase.md:228 calls it with --phase <N>, args[0] was the
literal string "--phase", which findPhase received as the phase number.
findPhase returned found:false, causing updated:false with no write.
ROADMAP.md plan checkboxes silently never advanced.
Fix: check for --phase <value> first; fall back to the first non-flag
positional argument for backward-compatible direct calls.
Regression test: tests/bug-2796-arg-parsing-regression.test.cjs
* fix(#2796): address CodeRabbit — guard --phase against flag-like values, bash fence
* fix(#2803): honor --default flag in SDK config-get handler
The gsd-sdk query config-get handler ignored the --default <value> flag.
Missing keys always threw 'Key not found' (exit 1), making 8 workflow
sites that rely on config-get --default fall through to error paths.
The CJS path (gsd-tools.cjs) honored --default since #1893; this ports
that behavior to the SDK configGet handler.
Regression test: tests/bug-2803-config-get-default-flag.test.cjs
* fix(#2803): address CodeRabbit — require --default value, keep missing config.json as error, bash fence
* fix(#2798): add regression test — context_window key already in VALID_CONFIG_KEYS
context_window was already added to both VALID_CONFIG_KEYS allowlists
(CJS and SDK) in a prior fix. The regression test confirms it stays there
and that config-set context_window succeeds end-to-end.
Regression test: tests/bug-2798-context-window-config-key.test.cjs
* fix(#2798): address CodeRabbit — add bash language to release notes fence
