Files
msd-core/gsd-core/workflows/eval-review.md
Tom Boucher 7c649a9970 fix(#3585): close raw-git bypasses of the commit_docs gate (#3590)
* test(#3585): repo-wide guard for unguarded .planning/ git add

Replaces the two-file #1783 scan, which required .planning/ on the git add
line and so was structurally blind to fast.md's `git add -A` and to
new-milestone.md (never scanned).

Extracts the shell tokenizer, comment-position rule and gsd-scan-ignore
marker from the #2269 guard into tests/helpers/shipped-command-scan.cjs so
both guards consume one implementation. Commit-specific logic stays in
commit-files-pathspec.test.cjs; every pre-existing test there passes
unedited.

Fails RED on five sites: fast.md:58, new-milestone.md:262, spec-phase.md:480,
eval-review.md:148, ai-integration-phase.md:263. The last three carry a
markdown prose conditional outside the bash block it claims to guard.

* fix(#3585): close raw-git bypasses of the commit_docs gate

Five shipped workflow steps staged .planning/ with raw git. Two had no
check at all; three had a markdown prose conditional sitting outside the
bash block it claimed to guard, so the block ran unconditionally.

spec-phase, eval-review and ai-integration-phase now route through the
gsd_run query commit seam, which performs the commit_docs and gitignore
checks internally and returns a skipped envelope -- this deletes the raw
git pair rather than wrapping it.

new-milestone stages directories for a later commit and cannot use the
seam, so it takes the executable guard form, fail-open on a tooling error.

fast writes no planning artifacts and has no gsd_run in scope at that
point, so it excludes .planning via pathspec instead of reading config.

Guard now reports 0 offenders.

* test(#3585): pin skipped_gitignored to production behavior

COMMIT_REASON was a test-local frozen enum joined to production only by a
hand-maintained keep-in-sync comment -- the Generative Fix Divergence class,
whose required remedy is a parity assertion.

B1-B3 already pinned SKIPPED_COMMIT_DOCS_FALSE. SKIPPED_GITIGNORED was
pinned by nothing: production could rename it and every test still passed.

G1-G3 drive the gitignore auto-detect path and assert the canonical reason.
The fixture must OMIT .planning/config.json entirely -- with config.json
present the loader resolves commit_docs to false first and cmdCommit returns
skipped_commit_docs_false, never reaching its own isGitIgnored branch.

* docs(#3585): document the planning commit gate and its guard

CONTEXT.md had zero commit_docs entries. Adds a Planning Commit Gate
glossary entry covering the resolution chain, the typed skip envelope, the
measured ordering of the two reason codes, and why the gate is enforceable
only as a text guard.

CONTRIBUTING.md gains the contributor rule for the new guard, with the
prose-is-not-a-guard example that caused three of the five defects.

* fix(#3585): address review findings in the planning-add guard

Spec review (blocker): fast.md excluded .planning unconditionally, changing
behavior for commit_docs=true users and violating epic AC4. Now gated -- the
launcher preamble was MOVED from log_to_state into the commit block rather
than copied, so gsd_run is in scope for +4 lines instead of +4KB, and the
else branch is byte-identical to the previous git add -A.

Security review (major): git -C <dir> add was a false negative because the
flag-skip loop never modelled flags that consume a separate value. Fixed for
-C/-c/--git-dir/--work-tree/--namespace. The fail-closed rule now also covers
$(...) substitution args and --pathspec-from-file, which were opaque in the
same way $VAR is. git commit -a/-am is now classified as reaching, since it
stages every tracked modification.

Self-review: isSkippable treated any NAME= token as a skippable prefix, so
V=$(git add -A) escaped -- the exact divergence the shared-helper extraction
existed to prevent. Adopted the sibling predicate verbatim.

eval, xargs, one-line function bodies and line-continuation remain blind and
are now enumerated as declared limits in the guard docblock and CONTRIBUTING.
The ifDepth clamp is defensive only: a 200k-case differential fuzz found no
reproducing input, so its test is labeled a pin, not a failing-first test.

* test(#3585): acknowledge emitted growth in three workflow files

emitted-attribution has two arms: hash attribution AND per-file growth. The
growth arm needs an acknowledgment even when every moved byte is attributable
to the diff, which is why the first remote run went red on it.

fast.md +417: the launcher preamble moved into the commit block so gsd_run is
in scope for the commit_docs guard, plus the guard itself.
new-milestone.md +281: the executable guard plus one line recording that the
unstaged archive move is deliberate.
spec-phase.md +21: reworded prose describing the skipped envelope.

eval-review.md and ai-integration-phase.md shrank; no entry needed.

* test(#3585): drop duplicate spec-phase ack, shrink its prose instead

The base already acknowledges spec-phase.md (from #2733), and two ack sources
may never name the same path. But a base-side ack is SPENT -- it cannot clear
new growth -- so the two gates were in direct conflict: attribution wanted an
ack, the ack lint forbade one.

Resolved by removing the growth rather than the conflict. spec-phase.md's +21
was purely a prose reword; rewritten shorter, the file now shrinks 36 bytes
against base and needs no acknowledgment at all.

fast.md and new-milestone.md have no base ack and keep theirs.

* chore(#3585): backfill changeset pr number to 3590

---------

Co-authored-by: sim <sim@local>
2026-08-17 13:34:55 -04:00

10 KiB
Raw Blame History

Retroactive audit of an implemented AI phase's evaluation coverage. Standalone command that works on any GSD-managed AI phase. Produces a scored EVAL-REVIEW.md with gap analysis and remediation plan.

Use after /gsd:execute-phase to verify that the evaluation strategy from AI-SPEC.md was actually implemented. Mirrors the pattern of /gsd:ui-review and /gsd:validate-phase.

<required_reading> @~/.claude/gsd-core/references/ai-evals.md </required_reading>

0. Initialize

_GSD_SHIM_NAME="gsd-tools.cjs"; _GSD_RUNTIME_ROOT="${RUNTIME_DIR:-$(git rev-parse --show-toplevel 2>/dev/null || pwd)}"; GSD_TOOLS="${_GSD_RUNTIME_ROOT}/gsd-core/bin/${_GSD_SHIM_NAME}"; if [ -f "$GSD_TOOLS" ]; then gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${_GSD_RUNTIME_ROOT}/.claude/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${_GSD_RUNTIME_ROOT}/.claude/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${_GSD_RUNTIME_ROOT}/.codex/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${_GSD_RUNTIME_ROOT}/.codex/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif command -v gsd-tools >/dev/null 2>&1; then GSD_TOOLS="$(command -v gsd-tools)"; gsd_run() { "$GSD_TOOLS" "$@"; }; elif [ -f "${CLAUDE_CONFIG_DIR:-$HOME/.claude}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${CLAUDE_CONFIG_DIR:-$HOME/.claude}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${HERMES_HOME:-$HOME/.hermes}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${HERMES_HOME:-$HOME/.hermes}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${CURSOR_CONFIG_DIR:-$HOME/.cursor}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${CURSOR_CONFIG_DIR:-$HOME/.cursor}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${CODEX_HOME:-$HOME/.codex}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${CODEX_HOME:-$HOME/.codex}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${GEMINI_CONFIG_DIR:-$HOME/.gemini}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${GEMINI_CONFIG_DIR:-$HOME/.gemini}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${COPILOT_CONFIG_DIR:-$HOME/.copilot}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${COPILOT_CONFIG_DIR:-$HOME/.copilot}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${WINDSURF_CONFIG_DIR:-$HOME/.codeium/windsurf}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${WINDSURF_CONFIG_DIR:-$HOME/.codeium/windsurf}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${AUGMENT_CONFIG_DIR:-$HOME/.augment}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${AUGMENT_CONFIG_DIR:-$HOME/.augment}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${TRAE_CONFIG_DIR:-$HOME/.trae}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${TRAE_CONFIG_DIR:-$HOME/.trae}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${QWEN_CONFIG_DIR:-$HOME/.qwen}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${QWEN_CONFIG_DIR:-$HOME/.qwen}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${CODEBUDDY_CONFIG_DIR:-$HOME/.codebuddy}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${CODEBUDDY_CONFIG_DIR:-$HOME/.codebuddy}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${CLINE_CONFIG_DIR:-$HOME/.cline}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${CLINE_CONFIG_DIR:-$HOME/.cline}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${GROK_AGENTS_HOME:-$HOME/.agents}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${GROK_AGENTS_HOME:-$HOME/.agents}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${ANTIGRAVITY_CONFIG_DIR:-$HOME/.gemini/antigravity}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${ANTIGRAVITY_CONFIG_DIR:-$HOME/.gemini/antigravity}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${OPENCODE_CONFIG_DIR:-${XDG_CONFIG_HOME:-$HOME/.config}/opencode}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${OPENCODE_CONFIG_DIR:-${XDG_CONFIG_HOME:-$HOME/.config}/opencode}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${KILO_CONFIG_DIR:-${XDG_CONFIG_HOME:-$HOME/.config}/kilo}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${KILO_CONFIG_DIR:-${XDG_CONFIG_HOME:-$HOME/.config}/kilo}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; else echo "ERROR: gsd-tools.cjs not found at $GSD_TOOLS and gsd-tools is not on PATH. Run: npx -y @opengsd/gsd-core@latest --claude --local" >&2; exit 1; fi; if [ -n "${CLAUDE_ENV_FILE:-}" ] && [ -n "${GSD_TOOLS:-}" ]; then printf "export PATH='%s':\"\$PATH\"\n" "${GSD_TOOLS%/*}" >> "$CLAUDE_ENV_FILE" 2>/dev/null || true; fi
RESPONSE_LANGUAGE=$(gsd_run query config-get response_language --default "" 2>/dev/null || echo "")
INIT=$(gsd_run query init.phase-op "${PHASE_ARG}")
if [[ "$INIT" == @file:* ]]; then INIT=$(cat "${INIT#@file:}"); fi

If response_language is set: All user-facing questions, prompts, and explanations in this workflow MUST be presented in {response_language}. Technical terms, code, file paths, and subagent prompts stay in English — only user-facing output is translated.

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

AUDITOR_MODEL=$(gsd_run query resolve-model gsd-eval-auditor --pick model 2>/dev/null || true)
AGENT_SKILLS_AUDITOR=$(gsd_run query agent-skills gsd-eval-auditor)

Display banner:

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 GSD ► EVAL AUDIT — PHASE {N}: {name}
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

1. Detect Input State

SUMMARY_FILES=$(ls "${PHASE_DIR}"/*-SUMMARY.md 2>/dev/null)
AI_SPEC_FILE=$(ls "${PHASE_DIR}"/*-AI-SPEC.md 2>/dev/null | head -1)
EVAL_REVIEW_FILE=$(ls "${PHASE_DIR}"/*-EVAL-REVIEW.md 2>/dev/null | head -1)

State A — AI-SPEC.md + SUMMARY.md exist: Full audit against spec State B — SUMMARY.md exists, no AI-SPEC.md: Audit against general best practices State C — No SUMMARY.md: Exit — "Phase {N} not executed. Run /gsd:execute-phase {N} first."

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. If EVAL_REVIEW_FILE non-empty: Use AskUserQuestion:

  • header: "Existing Eval Review"
  • question: "EVAL-REVIEW.md already exists for Phase {N}."
  • options:
    • "Re-audit — run fresh audit"
    • "View — display current review and exit"

If "View": display file, exit. If "Re-audit": continue.

If State B (no AI-SPEC.md): Warn:

No AI-SPEC.md found for Phase {N}.
Audit will evaluate against general AI eval best practices rather than a phase-specific plan.
Consider running /gsd:ai-integration-phase {N} before implementation next time.

Continue (non-blocking).

2. Gather Context Paths

Build file list for auditor:

  • AI-SPEC.md (if exists — the planned eval strategy)
  • All SUMMARY.md files in phase dir
  • All PLAN.md files in phase dir

3. Spawn gsd-eval-auditor

◆ Spawning eval auditor... (runs in a subagent — no output until it returns, ~1–5 min; expected, not a freeze)

Build prompt:

Read ~/.claude/agents/gsd-eval-auditor.md for instructions.

<objective>
Conduct evaluation coverage audit of Phase {phase_number}: {phase_name}
{If AI-SPEC exists: "Audit against AI-SPEC.md evaluation plan."}
{If no AI-SPEC: "Audit against general AI eval best practices."}
</objective>

<required_reading>
- {summary_paths}
- {plan_paths}
- {ai_spec_path if exists}
</required_reading>

<input>
ai_spec_path: {ai_spec_path or "none"}
phase_dir: {phase_dir}
phase_number: {phase_number}
phase_name: {phase_name}
padded_phase: {padded_phase}
state: {A or B}
</input>

${AGENT_SKILLS_AUDITOR}

Spawn as Task with model AUDITOR_MODEL.

4. Parse Auditor Result

Read the written EVAL-REVIEW.md. Extract:

  • overall_score
  • verdict (PRODUCTION READY | NEEDS WORK | SIGNIFICANT GAPS | NOT IMPLEMENTED)
  • critical_gap_count

5. Display Summary

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 GSD ► EVAL AUDIT COMPLETE — PHASE {N}: {name}
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

◆ Score: {overall_score}/100
◆ Verdict: {verdict}
◆ Critical Gaps: {critical_gap_count}
◆ Output: {eval_review_path}

{If PRODUCTION READY:}
  Next step: /gsd:plan-phase (next phase) or deploy

{If NEEDS WORK:}
  Address critical gaps in EVAL-REVIEW.md, then re-run /gsd:eval-review {N}

{If SIGNIFICANT GAPS or NOT IMPLEMENTED:}
  Review AI-SPEC.md evaluation plan. Critical eval dimensions are not implemented.
  Do not deploy until gaps are addressed.

6. Commit

gsd_run query commit "docs({phase_slug}): add EVAL-REVIEW.md — score {overall_score}/100 ({verdict})" --files "${EVAL_REVIEW_FILE}"

<success_criteria>

  • Phase execution state detected correctly
  • AI-SPEC.md presence handled (with or without)
  • gsd-eval-auditor spawned with correct context
  • EVAL-REVIEW.md written (by auditor)
  • Score and verdict displayed to user
  • Appropriate next steps surfaced based on verdict
  • Committed if commit_docs enabled </success_criteria>