Files
msd-core/get-shit-done/workflows/validate-phase.md
Tom Boucher 2b9fa009d3 fix(#373): replace unquoted $GSD_SDK with space-safe gsd_run launcher (#379)
* fix(#373): replace unquoted $GSD_SDK with space-safe gsd_run launcher

Workflow bash blocks resolved the runtime as GSD_SDK="node $GSD_TOOLS" and
invoked it unquoted ($GSD_SDK query ...). On install paths containing spaces
(e.g. /Volumes/Mini Me/...) the unquoted expansion word-split into
`node /Volumes/Mini gsd-tools.cjs ...`, failing with "Cannot find module
'/Volumes/Mini'" and getting masked by `2>/dev/null || echo "{}"` into a
silent empty state.

Replace the string variable with a single-line shell launcher that defines a
gsd_run function, invokes the runtime with a fully-quoted path and "$@", and
preserves the local-cjs / installed-gsd-tools-on-PATH fallback (#3668) plus
the loud not-found error and install hint. The launcher uses _GSD_SHIM_NAME
indirection so no workflow emits the /gsd-tools substring that the do.md
dispatcher-parity scanner would misread, and is single-line to stay within
the per-file progressive-disclosure line budgets (#2551).

The canonical launcher lives in
get-shit-done/workflows/_runtime-launcher.snippet.sh, is propagated once per
file by scripts/sync-runtime-launcher.cjs, and is locked by
tests/runtime-launcher-parity.test.cjs (fails CI on drift, on a reappearing
$GSD_SDK token, or on a /gsd-tools substring). Dependent workflow-assertion
tests are updated from $GSD_SDK to gsd_run, and the runtime launcher is
registered in CONTEXT.md.

Fixes #373

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* ci(#373): add changeset fragment and allow-test-rule for parity guard

The runtime-launcher parity test is a structural drift guard that reads
workflow markdown to assert the canonical launcher is present and the
retired $GSD_SDK / /gsd-tools tokens are absent; annotate it with
allow-test-rule per the no-source-grep lint escape hatch. Add the required
.changeset fragment for this user-facing fix.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* test(#373): make parity PATH-fallback assertion cross-platform (Windows)

Subtest (E) compared GSD_TOOLS against the Node-side absolute temp path,
but the value originates from git-bash which reports the POSIX form, so the
prefix comparison failed on windows-latest while the launcher itself worked
(the installed stub was invoked). Assert the resolved binary by normalized
suffix (/bin/gsd-tools, not .cjs) instead of the absolute prefix; the
behavioral stub-invocation assertion is unchanged.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-27 20:21:05 -04:00

6.4 KiB

Audit Nyquist validation gaps for a completed phase. Generate missing tests. Update VALIDATION.md.

<required_reading> @~/.claude/get-shit-done/references/ui-brand.md </required_reading>

<available_agent_types> Valid GSD subagent types (use exact names — do not fall back to 'general-purpose'):

  • gsd-nyquist-auditor — Validates verification coverage </available_agent_types>

0. Initialize

_GSD_SHIM_NAME="gsd-tools.cjs"; GSD_TOOLS="${RUNTIME_DIR:-$(git rev-parse --show-toplevel 2>/dev/null || pwd)}/get-shit-done/bin/${_GSD_SHIM_NAME}"; if [ -f "$GSD_TOOLS" ]; then gsd_run() { node "$GSD_TOOLS" "$@"; }; elif command -v gsd-tools >/dev/null 2>&1; then GSD_TOOLS="$(command -v gsd-tools)"; gsd_run() { "$GSD_TOOLS" "$@"; }; else echo "ERROR: gsd-tools.cjs not found at $GSD_TOOLS and gsd-tools is not on PATH. Run: npx -y @opengsd/get-shit-done-redux@latest --claude --local" >&2; exit 1; fi
INIT=$(gsd_run query init.phase-op "${PHASE_ARG}")
if [[ "$INIT" == @file:* ]]; then INIT=$(cat "${INIT#@file:}"); fi
AGENT_SKILLS_AUDITOR=$(gsd_run query agent-skills gsd-nyquist-auditor)

Parse: phase_dir, phase_number, phase_name, phase_slug, padded_phase.

AUDITOR_MODEL=$(gsd_run query resolve-model gsd-nyquist-auditor --raw)
NYQUIST_CFG=$(gsd_run query config-get workflow.nyquist_validation --raw)

If NYQUIST_CFG is false: exit with "Nyquist validation is disabled. Enable via /gsd:settings."

Display banner: GSD > VALIDATE PHASE {N}: {name}

1. Detect Input State

VALIDATION_FILE=$(ls "${PHASE_DIR}"/*-VALIDATION.md 2>/dev/null | head -1)
SUMMARY_FILES=$(ls "${PHASE_DIR}"/*-SUMMARY.md 2>/dev/null)
  • State A (VALIDATION_FILE non-empty): Audit existing
  • State B (VALIDATION_FILE empty, SUMMARY_FILES non-empty): Reconstruct from artifacts
  • State C (SUMMARY_FILES empty): Exit — "Phase {N} not executed. Run /gsd:execute-phase {N} ${GSD_WS} first."

2. Discovery

2a. Read Phase Artifacts

Read all PLAN and SUMMARY files. Extract: task lists, requirement IDs, key-files changed, verify blocks.

2b. Build Requirement-to-Task Map

Per task: { task_id, plan_id, wave, requirement_ids, has_automated_command }

2c. Detect Test Infrastructure

State A: Parse from existing VALIDATION.md Test Infrastructure table. State B: Filesystem scan:

find . -name "pytest.ini" -o -name "jest.config.*" -o -name "vitest.config.*" -o -name "pyproject.toml" 2>/dev/null | head -10
find . \( -name "*.test.*" -o -name "*.spec.*" -o -name "test_*" \) -not -path "*/node_modules/*" 2>/dev/null | head -40

2d. Cross-Reference

Match each requirement to existing tests by filename, imports, test descriptions. Record: requirement → test_file → status.

3. Gap Analysis

Classify each requirement:

Status Criteria
COVERED Test exists, targets behavior, runs green
PARTIAL Test exists, failing or incomplete
MISSING No test found

Build: { task_id, requirement, gap_type, suggested_test_path, suggested_command }

No gaps → skip to Step 6, set nyquist_compliant: true.

4. Present Gap Plan

Text mode (workflow.text_mode: true in config or --text flag): Set TEXT_MODE=true if --text is present in $ARGUMENTS OR text_mode from init JSON is true. When TEXT_MODE is active, replace every AskUserQuestion call with a plain-text numbered list and ask the user to type their choice number. This is required for non-Claude runtimes (OpenAI Codex, Gemini CLI, etc.) where AskUserQuestion is not available. Call AskUserQuestion with gap table and options:

  1. "Fix all gaps" → Step 5
  2. "Skip — mark manual-only" → add to Manual-Only, Step 6
  3. "Cancel" → exit

5. Spawn gsd-nyquist-auditor

Agent(
  prompt="Read ~/.claude/agents/gsd-nyquist-auditor.md for instructions.\n\n" +
    "<files_to_read>{PLAN, SUMMARY, impl files, VALIDATION.md}</files_to_read>" +
    "<gaps>{gap list}</gaps>" +
    "<test_infrastructure>{framework, config, commands}</test_infrastructure>" +
    "<constraints>Never modify impl files. Max 3 debug iterations. Escalate impl bugs.</constraints>" +
    "${AGENT_SKILLS_AUDITOR}",
  subagent_type="gsd-nyquist-auditor",
  model="{AUDITOR_MODEL}",
  description="Fill validation gaps for Phase {N}"
)

ORCHESTRATOR RULE — CODEX RUNTIME: After calling Agent() above, stop working on this task immediately. Do not read more files, edit code, or run tests related to this task while the subagent is active. Wait for the subagent to return its result. This prevents duplicate work, conflicting edits, and wasted context. Only resume when the subagent result is available.

Handle return:

  • ## GAPS FILLED → record tests + map updates, Step 6
  • ## PARTIAL → record resolved, move escalated to manual-only, Step 6
  • ## ESCALATE → move all to manual-only, Step 6

6. Generate/Update VALIDATION.md

State B (create):

  1. Read template from ~/.claude/get-shit-done/templates/VALIDATION.md
  2. Fill: frontmatter, Test Infrastructure, Per-Task Map, Manual-Only, Sign-Off
  3. Write to ${PHASE_DIR}/${PADDED_PHASE}-VALIDATION.md

State A (update):

  1. Update Per-Task Map statuses, add escalated to Manual-Only, update frontmatter
  2. Append audit trail:
## Validation Audit {date}
| Metric | Count |
|--------|-------|
| Gaps found | {N} |
| Resolved | {M} |
| Escalated | {K} |

7. Commit

git add {test_files}
git commit -m "test(phase-${PHASE}): add Nyquist validation tests"

gsd_run query commit "docs(phase-${PHASE}): add/update validation strategy"

8. Results + Routing

Compliant:

GSD > PHASE {N} IS NYQUIST-COMPLIANT
All requirements have automated verification.
▶ Next: /gsd:audit-milestone ${GSD_WS}

Partial:

GSD > PHASE {N} VALIDATED (PARTIAL)
{M} automated, {K} manual-only.
▶ Retry: /gsd:validate-phase {N} ${GSD_WS}

Display /clear reminder.

<success_criteria>

  • Nyquist config checked (exit if disabled)
  • Input state detected (A/B/C)
  • State C exits cleanly
  • PLAN/SUMMARY files read, requirement map built
  • Test infrastructure detected
  • Gaps classified (COVERED/PARTIAL/MISSING)
  • User gate with gap table
  • Auditor spawned with complete context
  • All three return formats handled
  • VALIDATION.md created or updated
  • Test files committed separately
  • Results with routing presented </success_criteria>