Files
get-shit-done/get-shit-done/workflows/validate-phase.md
Tom Boucher b1a670e662 fix(#2697): replace retired /gsd: prefix with /gsd- in all user-facing text (#2699)
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>
2026-04-25 10:59:33 -04:00

5.5 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

INIT=$(gsd-sdk query init.phase-op "${PHASE_ARG}")
if [[ "$INIT" == @file:* ]]; then INIT=$(cat "${INIT#@file:}"); fi
AGENT_SKILLS_AUDITOR=$(gsd-sdk query agent-skills gsd-nyquist-auditor)

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

AUDITOR_MODEL=$(gsd-sdk query resolve-model gsd-nyquist-auditor --raw)
NYQUIST_CFG=$(gsd-sdk 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

Task(
  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}"
)

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-sdk 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>