Files
msd-core/gsd-core/workflows/code-review.md
Tom Boucher ff4a57b78c chore(#1671): migrate the remaining 13 LARGE/XL workflows to the fragment model — Phase 6.3 (#3030)
* chore(#2994): fragmentize progress.md forensic audit onto the fragment model

Extract the --forensic-gated forensic_audit step to
workflows/progress/steps/forensic-audit.md behind a section marker, and
repair progress.md's init line to forward --forensic so the atom is
actually true in production rather than only under direct CLI tests.

progress.md shrinks 32630 -> 27207 bytes.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

* chore(#2994): fragmentize the four manifest-wired workflows

new-project, quick, new-milestone and progress each already had a
dedicated cmdInit* entry point but zero marked sections. Extract nine
gated bodies to workflows/<wf>/steps/ behind section markers and repair
each init line to forward its flags.

Fold --full into the discuss/research/validate facts inside cmdInitQuick
so the when= grammar never sees an OR, per the chunked-mode precedent.

Fixes found while working, per the no-defer rule:
- cmdInitProgress passed no phase info to buildSectionManifestField, so
  state:phase-mvp-mode was permanently false — an atom in the vocabulary
  whose fact could never be computed.
- the quick init router folded flag tokens into the free-text
  description, which the new forwarding would have corrupted.
- a #2508 dispatch note was nested inside quick.md's Agent(prompt=)
  fence, leaking orchestrator guidance into the subagent prompt.
- progress.md had a 3-vs-4 backtick outer-fence imbalance.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

* chore(#2994): fragmentize verify-work.md and admit state:ui-phase-active

Wire cmdInitVerifyWork to buildSectionManifestField — it was a dedicated
entry point that never emitted a manifest — and mark two sections.

state:ui-phase-active folds (plan:pre hooks include an active ui step) OR
(the phase dir holds a *-UI-SPEC.md) into one boolean in init.cts, so the
grammar still sees a single operator-free atom. The inner Playwright-MCP
check stays as prose inside the fragment: it is live session state and no
init seam can precompute it.

The MVP false-branch note is a real fallback, not redundant prose, so it
sits outside the marker — gating it away would delete the text needed
precisely when MVP mode is off.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

* test(#2994): follow moved workflow content in drift guards

Retarget every guard that asserted on content this branch moved into
workflows/<wf>/steps/, mirroring 815b3d897. Each retargeted assertion was
verified to still fail when its step file is blanked, so none was
weakened into vacuity.

Three assertions in verify-mvp-uat were genuinely red. Three more were
worse than red — passing for the wrong reason:
- quick-commit-boundary and worktree-cleanup anchored on indexOf('Step
  5.6'), which matched a later cross-reference and sliced 16069 chars
  that coincidentally held the asserted substrings. Replaced with an
  expandWorkflowSections helper that splices step content back in place.
- phase6-review-capabilities lost its end boundary and widened to EOF.
- playwright-ui-verify matched 'UI' in an unrelated bullet and 'fall
  back' in a subagent-dispatch line after the real content moved.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

* chore(#2994): fragmentize code-review and complete-milestone, admit three atoms

Add dedicated cmdInitCodeReview and cmdInitCompleteMilestone entry points
alongside the shared generic ones rather than modifying them — init.phase-op
and init.manager carry a CRITICAL blast radius (179 dependents, 24
processes) and stay byte-identical for their other callers.

Admit flag:--fix, state:fallow-enabled and state:git-create-tag, each with
a consuming section and a fact its own entry point computes.

Both sections had the resolver-in-body hazard: the fallow config-gate and
the git.create_tag check each sat inside the very block being gated, so
gating would have disabled the resolver that decides the gate. Both are
hoisted into init and the bodies now consume the resolved fact.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

* test(#2994): retarget code-review and milestone drift guards, fix two red tests

Retarget guards that asserted on content moved into steps/, proving
non-vacuity by blanking each step file and confirming failure.

Also fixes two genuinely red tests found while working, per the no-defer
rule:
- workflow-fragments' frozen-vocabulary lock was missing
  state:ui-phase-active, so commit 7ef7f8336 shipped red. Lint and build
  both passed over it, which is why neither is sufficient verification.
- code-review's quick.md capability-hook assertion carried a stale
  delimiter after the 18ff35d20 extraction.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

* chore(#2994): fragmentize autonomous.md and admit state:plan-strategy-converge

Five sections share one atom, the pattern plan-phase already uses for
flag:--research-phase. The atom folds --converge OR --cross-ai into a
single boolean in cmdInitAutonomous so the grammar stays operator-free.

cmdInitAutonomous is additive; init.milestone-op, init.manager and
init.phase-op are untouched and still consumed. The $PLAN_STRATEGY bash
resolver is deliberately retained — ungated local-planning bullets still
read it, so the init-side fact supplements it rather than replacing it.

converge-fail-fast required splitting one bash fence so the always-run
CONVERGENCE_ARGS construction stays outside the marker. All three
flag-absent fallbacks were left outside their markers.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

* chore(#2994): fragmentize review and discuss-phase-assumptions

Admit state:reviewer-instances-configured (two peripheral notes share it;
the core reviewer-lane dispatch stays unmarked — it is the workflow's
primary always-evaluated logic, not an optional branch) and
state:auto-advance-active, which folds --auto OR two config keys into one
boolean so the grammar stays operator-free.

discuss-phase-assumptions was the highest-risk edit in this PR. Its
auto_advance step is a full if/elif/else; gating it whole would have
deleted the flag-absent fallback needed exactly when --auto is off. Split
verified exact: resolvers 636-651 and the 'End here' fallback 668-669 both
stay outside the marker; only 653-667 is gated.

Adds emitted-drift acks for the two files that grew — review.md (+55 B)
and autonomous.md (+737 B from 80799211c, which had none and would have
red-gated the push.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

* chore(#2994): fragmentize docs-update, update, transition and new-milestone Part A

Completes the 13-workflow rollout. Three of these had no init call at all
and gained a dedicated entry point plus their first gsd_run query line.

Admits state:is-monorepo and adds state:next-channel, state:workstream-active
and state:flat-mode. Vocabulary 26 -> 30 atoms.

Part A of new-milestone applies when NO workstream is active — the negation
of state:workstream-active. Rather than teach the grammar negation, which is
the Greenspun drift the frozen list exists to prevent, it gets a separate
positively-phrased atom whose fact is the inverse. Part B, which always runs,
stays outside the marker.

flag:--verify-only is deliberately NOT admitted: docs-update has no
contiguous purely-additive region for it, and an atom without a consuming
section is dead vocabulary. Evidence recorded in the slice report.

update.md reuses its existing resolved $GSD_TOOLS rather than prepending the
canonical preamble, which would have clobbered it.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

* fix(#2994): stop automated-ui-verification re-resolving its own gate, retire dead vocabulary

Two defects the new tests caught.

The automated-ui-verification step re-ran gsd_run loop render-hooks and
recomputed UI_PHASE_ACTIVE inside a body that is only read when that fact
is already true — the circular self-disabling pattern this design forbids,
introduced by 3c654b168. cmdInitVerifyWork now exposes ui_phase_active and
the step consumes it. Its launcher preamble goes too: no gsd_run remains.
The Playwright-MCP check stays as prose — that is live session state.

Dead vocabulary predating this PR: flag:--full and state:needs-codebase-map
were admitted with a gate-1 claim that never materialized. flag:--full is
removed, redundant once quick folds it into discuss/research/validate.
state:needs-codebase-map gets the real consumer it always lacked, gating
new-project's codebase-map offer. Vocabulary 30 -> 29, and no atom is now
without a consuming section.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

* test(#2994): add the atom-admission, inversion and resolver-hoist gates

The two existing parity guards prove vocabulary/predicate symmetry but
never that a fact is computed — an atom no cmdInit* assembles evaluates
false forever. These close that hole:

- per-atom satisfiability for all 29 atoms, plus an anti-vacuity assertion
  so the loop cannot silently cover zero atoms
- dead-vocabulary check against the shipped manifest
- inversion guard: the flag-absent fallbacks in discuss-phase-assumptions
  and verify-work must stay outside their markers
- data-driven resolver-hoist guard over the shipped manifest, so a future
  extraction cannot reintroduce the circular class
- compound-fold coverage (--full, --cross-ai, --rc, config-only --auto)
- null-vs-[] degraded/computed distinction, and flag value shapes

Also repairs the frozen-vocabulary lock, which was stale and red for the
seven atoms earlier commits on this branch shipped.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

* docs(#2994): add changeset for the fragment-model rollout

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

* test(#2994): cite the issue on the two new allow-test-rule exemptions

ADR-456 requires an issue ref on the same line as the annotation.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

* docs(#2994): correct the atom-count claims after retiring flag:--full

The vocabulary doc comments still said 30 entries; it is 29 since
flag:--full was removed as dead vocabulary.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

* fix(#2994): dedupe the phase-fallback block and harden --ws parsing

Review findings.

MAJOR: the three new init entry points each pasted a verbatim copy of the
guardedFindPhase/guardedGetRoadmapPhase fallback, taking the repo from four
copies to seven — DEFECT.GENERATIVE-FIX. Extracted applyRoadmapFallback and
folded six of the seven; each call site keeps its own field-set via a
closure. Duplication removed rather than papered over with a parity test.
cmdInitPhaseOp stays out: its fallback omits has_reviews, so it is not a
byte-identical copy, and it is CRITICAL-radius.

LOW, pre-existing: GSD_WS captured [^[:space:]]+ and expands unquoted, so a
workstream name holding glob metacharacters would expand against the
filesystem. Narrowed to [A-Za-z0-9._-]+. The unquoted expansion is kept —
it must word-split into two args and vanish when empty.

Also restores the vocabulary ordering convention, and fixes a masked test
bug the mandated run surfaced: the flag-forwarding guard checked only the
first init line per workflow, but new-milestone has two, so a real failure
was reporting exit 0.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

* fix(#2994): drop the stale new-milestone emitted-drift ack

new-milestone.md was acked for a +406 B growth measured against an
intermediate commit. Net against origin/next it SHRANK by 8 bytes, so
nothing needed the ack and it explained nothing — which the differential
attribution check reports as a stale acknowledgment, not a pass.

update.md's entry stays: it genuinely grew +703 B.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

* fix(#2994): resolve the 15 failures from the full matrix run

All 15 were real and identical on both lanes.

REAL REGRESSION: autonomous.md hit 41479 chars against the #2196 guard's
40960 cap — a CHARS cap distinct from the LARGE tier byte cap, which the
five section stubs pushed it over. Extracted the 3a.5 UI Design Contract
body to references/; now 39968 chars, and the file nets -795 B vs base, so
its growth ack is deleted rather than left stale.

REAL DEFECT: docs referenced /gsd-transition, which is not a live
registered command. Reworded.

STALE FIXTURE: the emission byte-identity test hardcoded two marked
workflows; this branch legitimately marks fifteen. Fixture corrected — the
source was right.

The rest were drift guards over the eight workflows the earlier sweep did
not cover, retargeted at where the content now lives with non-vacuity
proven by blanking each step file and confirming failure. The GSD_WS
forwarding guard was checked as a possible real break and is not one: the
charclass narrowing is intact and forwarding works end to end.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

* fix(#2994): drop the ack for a newly-added reference file

A new file's emitted ripple is attributable to the diff that adds it, so
the acknowledgment explained nothing and the differential check reports it
as stale. Removing the last entry removes the fragment — an empty one
signals nothing.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

* fix(#2994): retarget the UI-contract guards and clear two transitive advisories

The §3a.5 extraction that brought autonomous.md under the #2196 char cap
moved its body to references/autonomous-ui-design-contract.md, so ten
guards in autonomous-ui-steps and check-ui-safety-gate were asserting it
against the host. Retargeted via a combined read, each proven non-vacuous
by blanking the reference file and confirming failure.

This class had already bitten twice on this branch because each sweep was
scoped to the workflows touched at that moment, so this one was
exhaustive: ~70 test files across all 13 workflows, zero further broken or
vacuous assertions found.

Also clears two high transitive advisories the matrix flagged on one lane
— fast-uri GHSA-7p8r-x3mc-p8w7 and three ip-address SSRF/trust-boundary
issues. Both pre-date this branch: package-lock.json was untouched until
now, so the production tree was byte-identical to the base. Lockfile-only,
package.json unchanged, verified against a real npm ci install.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

* chore(#2994): backfill changeset pr number to 3030

---------

Co-authored-by: sim <sim@local>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-03 19:59:58 -04:00

32 KiB
Raw Blame History

Review source files changed during a phase for bugs, security issues, and code quality problems. Computes file scope (--files override > SUMMARY.md > git diff fallback), checks config gate, spawns gsd-code-reviewer agent, commits REVIEW.md, and presents results to user. When --fix is passed, delegates to code-review-fix.md after review to auto-apply findings via gsd-code-fixer.

<required_reading> Read all files referenced by the invoking prompt's execution_context before starting. </required_reading>

<available_agent_types>

  • gsd-code-reviewer: Reviews source files for bugs and quality issues
  • gsd-code-fixer: Applies fixes to code review findings (used via dispatch_fix → code-review-fix.md when --fix is passed) </available_agent_types>
Parse arguments and load project state:
_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%/*}" >> "$CLAUDE_ENV_FILE" 2>/dev/null || true; fi
PHASE_ARG="${1}"

# Parse all code-review flags into a structured IR via code-review-flags.cjs.
# This is the canonical flag-parsing surface — do not replicate inline bash parsing
# for --fix/--all/--auto here; the module handles all flag extraction and implication
# logic (e.g., --all and --auto imply --fix). Resolved BEFORE the init call below so
# the section-manifest gate forwards the RESOLVED (post-implication) fix decision, not
# just a literal --fix token check.
FLAGS_JSON=$(node -e "
  const { parseCodeReviewFlags } = require('./gsd-core/bin/lib/code-review-flags.cjs');
  const flags = parseCodeReviewFlags(process.argv.slice(1));
  process.stdout.write(JSON.stringify(flags));
" -- "$@" 2>/dev/null)

# Extract individual flag values from the IR
FIX_FLAG=$(echo "$FLAGS_JSON" | node -e "process.stdout.write(String(JSON.parse(require('fs').readFileSync('/dev/stdin','utf-8')).fix))")
FIX_ALL=$(echo "$FLAGS_JSON" | node -e "process.stdout.write(String(JSON.parse(require('fs').readFileSync('/dev/stdin','utf-8')).all))")
FIX_AUTO=$(echo "$FLAGS_JSON" | node -e "process.stdout.write(String(JSON.parse(require('fs').readFileSync('/dev/stdin','utf-8')).auto))")
DEPTH_OVERRIDE=$(echo "$FLAGS_JSON" | node -e "process.stdout.write(JSON.parse(require('fs').readFileSync('/dev/stdin','utf-8')).depth)")
FILES_OVERRIDE=$(echo "$FLAGS_JSON" | node -e "process.stdout.write(JSON.parse(require('fs').readFileSync('/dev/stdin','utf-8')).files)")

# Forward the resolved fix decision (--fix itself, or --all/--auto implying it) to
# init.code-review so section_manifest's flag:--fix gating (dispatch-fix section)
# matches code-review-flags.cjs's own implication logic rather than a raw token scan.
FIX_PARAM=""
if [ "$FIX_FLAG" = "true" ]; then FIX_PARAM="--fix"; fi

INIT=$(gsd_run query init.code-review "${PHASE_ARG}" $FIX_PARAM)
if [[ "$INIT" == @file:* ]]; then INIT=$(cat "${INIT#@file:}"); fi
AGENT_SKILLS_REVIEWER=$(gsd_run query agent-skills gsd-code-reviewer)
# #2072: resolve the routed model so model_overrides / models.verification are honored
# (the resolver maps gsd-code-reviewer → phaseType "verification"); thread it below.
REVIEWER_MODEL=$(gsd_run query resolve-model gsd-code-reviewer --raw)

Parse from init JSON: phase_found, phase_dir, phase_number, phase_name, padded_phase, commit_docs, fallow_enabled, fallow_scope, fallow_profile, fallow_mcp, fallow_max_crap.

Input sanitization (defense-in-depth):

# Validate PADDED_PHASE contains only digits and optional dot (e.g., "02", "03.1")
if ! [[ "$PADDED_PHASE" =~ ^[0-9]+(\.[0-9]+)?$ ]]; then
  echo "Error: Invalid phase number format: '${PADDED_PHASE}'. Expected digits (e.g., 02, 03.1)."
  # Exit workflow
fi

Phase validation (before config gate): If phase_found is false, report error and exit:

Error: Phase ${PHASE_ARG} not found. Run /gsd:progress to see available phases.

This runs BEFORE config gate check so user errors are surfaced immediately regardless of config state.

If FILES_OVERRIDE is set, split by comma into array:

if [ -n "$FILES_OVERRIDE" ]; then
  IFS=',' read -ra FILES_ARRAY <<< "$FILES_OVERRIDE"
fi
Check if code review is active via the capability registry:
EXECUTE_POST_HOOKS_JSON=$(gsd_run loop render-hooks execute:post --raw)

Resolve active step hooks from EXECUTE_POST_HOOKS_JSON where kind == "step" and ref.skill == "code-review".

If no active code-review step hook exists:

Code review skipped (code-review capability inactive)

Exit workflow.

Default is active through the Capability Registry schema — only skip when the registry resolves no active code-review step hook. This check runs AFTER phase validation so invalid phase errors are shown first.

Determine review depth with priority order:
  1. DEPTH_OVERRIDE from --depth flag (highest priority)
  2. Config value: gsd-tools.cjs query config-get workflow.code_review_depth 2>/dev/null
  3. Default: "standard"
if [ -n "$DEPTH_OVERRIDE" ]; then
  REVIEW_DEPTH="$DEPTH_OVERRIDE"
else
  CONFIG_DEPTH=$(gsd_run query config-get workflow.code_review_depth 2>/dev/null || echo "")
  REVIEW_DEPTH="${CONFIG_DEPTH:-standard}"
fi

Validate depth value:

case "$REVIEW_DEPTH" in
  quick|standard|deep)
    # Valid
    ;;
  *)
    echo "Warning: Invalid depth '${REVIEW_DEPTH}'. Valid values: quick, standard, deep. Using 'standard'."
    REVIEW_DEPTH="standard"
    ;;
esac
Three-tier scoping with explicit precedence:

Tier 1 — --files override (highest precedence per D-08):

If FILES_OVERRIDE is set (from --files flag):

if [ -n "$FILES_OVERRIDE" ]; then
  REVIEW_FILES=()
  REPO_ROOT=$(git rev-parse --show-toplevel 2>/dev/null)
  
  for file_path in "${FILES_ARRAY[@]}"; do
    # Security: validate path is within repository (prevent path traversal)
    ABS_PATH=$(realpath -m "${file_path}" 2>/dev/null || echo "${file_path}")
    if [[ "$ABS_PATH" != "$REPO_ROOT"* ]]; then
      echo "Error: File path outside repository, skipping: ${file_path}"
      continue
    fi
    
    # Validate path exists (relative to repo root)
    if [ -f "${REPO_ROOT}/${file_path}" ] || [ -f "${file_path}" ]; then
      REVIEW_FILES+=("$file_path")
    else
      echo "Warning: File not found, skipping: ${file_path}"
    fi
  done
  
  echo "File scope: ${#REVIEW_FILES[@]} files from --files override"
fi

Skip SUMMARY/git scoping entirely when --files is provided.

Tier 2 — SUMMARY.md extraction (primary per D-01):

If --files NOT provided:

if [ -z "$FILES_OVERRIDE" ]; then
  SUMMARIES=$(ls "${PHASE_DIR}"/*-SUMMARY.md 2>/dev/null)
  REVIEW_FILES=()
  
  if [ -n "$SUMMARIES" ]; then
    for summary in $SUMMARIES; do
      # Extract key_files.created and key_files.modified using node for reliable YAML parsing
      # This avoids fragile awk parsing that breaks on indentation differences
      EXTRACTED=$(node -e "
        const fs = require('fs');
        const content = fs.readFileSync('$summary', 'utf-8');
        const match = content.replace(/\r\n/g, '\n').match(/^---\n([\s\S]*?)\n---/);
        if (!match) { process.exit(0); }
        const yaml = match[1];
        const files = [];
        let inSection = null;
        for (const line of yaml.split('\n')) {
          if (/^\s+created:/.test(line)) { inSection = 'created'; continue; }
          if (/^\s+modified:/.test(line)) { inSection = 'modified'; continue; }
          if (/^\s*[\w-]+:/.test(line) && !/^\s*-/.test(line)) { inSection = null; continue; }
          if (inSection && /^\s+-\s+(.+)/.test(line)) {
            let raw = line.match(/^\s+-\s+(.+)/)[1].trim();
            raw = raw.replace(/^['"]|['"]$/g, '');
            raw = raw.replace(/\s+\([^)]*\)\s*$/, '');
            raw = raw.split(/\s+—\s/)[0].trim();
            // #2666: accept root-level paths (no `/`) and known extensionless build
            // files, not only nested paths with a trailing extension. The pre-fix
            // guard required BOTH a directory separator AND a trailing dot-extension,
            // which silently dropped every repository-root file (Dockerfile,
            // renovate.json, AGENTS.md, package.json, .gitlab-ci.yml, …) and every
            // extensionless build file anywhere in the tree (**/Dockerfile, **/Makefile).
            // Prose bullets are rejected by the known-filename / has-extension
            // distinction, with the post-processing existence check (`[ -f ]`) as a
            // backstop — a prose string is never a real file on disk.
            const KNOWN_EXTENSIONLESS_BUILD_FILES = new Set([
              'dockerfile', 'containerfile', 'makefile', 'justfile', 'procfile',
            ]);
            const hasExtension = /\.[A-Za-z0-9]+$/.test(raw);
            const basename = raw.split('/').pop().toLowerCase();
            if (hasExtension || KNOWN_EXTENSIONLESS_BUILD_FILES.has(basename)) {
              files.push(raw);
            }
          }
        }
        if (files.length) console.log(files.join('\n'));
      " 2>/dev/null)
      
      # Add extracted files to REVIEW_FILES array
      if [ -n "$EXTRACTED" ]; then
        while IFS= read -r file; do
          if [ -n "$file" ]; then
            REVIEW_FILES+=("$file")
          fi
        done <<< "$EXTRACTED"
      fi
    done
    
    if [ ${#REVIEW_FILES[@]} -eq 0 ]; then
      echo "Warning: SUMMARY artifacts found but contained no file paths. Falling back to git diff."
    fi
  fi
fi

Tier 3 — Git diff fallback (per D-02) and SUMMARY/diff cross-check (per #2666):

If no SUMMARY.md files found OR no files extracted from them, fall back to the git diff. Additionally, whenever a reliable diff base is available, cross-check the SUMMARY scope against the diff and warn about (then add) any changed files the SUMMARY extractor did not surface — so a partial SUMMARY result can no longer silently mask the rest of the phase.

# Compute diff base from phase commits — fail closed if no reliable base found
PHASE_COMMITS=$(git log --oneline --all --grep="${PADDED_PHASE}" --format="%H" 2>/dev/null)
DIFF_BASE=""
if [ -n "$PHASE_COMMITS" ]; then
  DIFF_BASE=$(echo "$PHASE_COMMITS" | tail -1)^
  # Verify the parent commit exists (first commit in repo has no parent)
  if ! git rev-parse "${DIFF_BASE}" >/dev/null 2>&1; then
    DIFF_BASE=$(echo "$PHASE_COMMITS" | tail -1)
  fi
fi

if [ ${#REVIEW_FILES[@]} -eq 0 ]; then
  # Full git-diff fallback (per D-02): SUMMARY scoping yielded nothing.
  if [ -n "$DIFF_BASE" ]; then
    # Run git diff with specific exclusions (per D-03)
    DIFF_FILES=$(git diff --name-only "${DIFF_BASE}..HEAD" -- . \
      ':!.planning/' ':!ROADMAP.md' ':!STATE.md' \
      ':!*-SUMMARY.md' ':!*-VERIFICATION.md' ':!*-PLAN.md' \
      ':!package-lock.json' ':!yarn.lock' ':!Gemfile.lock' ':!poetry.lock' 2>/dev/null)

    while IFS= read -r file; do
      [ -n "$file" ] && REVIEW_FILES+=("$file")
    done <<< "$DIFF_FILES"

    echo "File scope: ${#REVIEW_FILES[@]} files from git diff (base: ${DIFF_BASE})"
  else
    # Fail closed — no reliable diff base found. Do not use arbitrary HEAD~N.
    echo "Warning: No phase commits found for '${PADDED_PHASE}'. Cannot determine reliable diff scope."
    echo "Use --files flag to specify files explicitly: /gsd:code-review ${PHASE_ARG} --files=file1,file2,..."
  fi
elif [ -n "$DIFF_BASE" ]; then
  # #2666 cross-check: SUMMARY yielded a non-empty (possibly partial) scope.
  # Warn about — and add — any changed files the SUMMARY extractor did not surface,
  # so a partial result can no longer silently ship an incomplete review scope.
  DIFF_FILES=$(git diff --name-only "${DIFF_BASE}..HEAD" -- . \
    ':!.planning/' ':!ROADMAP.md' ':!STATE.md' \
    ':!*-SUMMARY.md' ':!*-VERIFICATION.md' ':!*-PLAN.md' \
    ':!package-lock.json' ':!yarn.lock' ':!Gemfile.lock' ':!poetry.lock' 2>/dev/null)

  # Build a newline-delimited list of already-scoped files for exact membership
  # testing (portable — bash 3.2 on macOS has no associative arrays). grep -Fxq
  # matches the WHOLE line exactly, so a short basename (e.g. root `Dockerfile`)
  # does NOT substring-match a longer scoped path (e.g. `docker/Dockerfile`).
  IN_SCOPE=$(printf '%s\n' "${REVIEW_FILES[@]}")

  MISSING_FROM_SUMMARY=()
  while IFS= read -r file; do
    [ -z "$file" ] && continue
    # Exact whole-line match; grep nonzero-exit => not in scope.
    if printf '%s\n' "${REVIEW_FILES[@]}" | grep -Fxq -- "$file" 2>/dev/null; then
      : # already scoped
    else
      MISSING_FROM_SUMMARY+=("$file"); REVIEW_FILES+=("$file")
    fi
  done <<< "$DIFF_FILES"

  if [ ${#MISSING_FROM_SUMMARY[@]} -gt 0 ]; then
    echo "Warning: SUMMARY scope was missing ${#MISSING_FROM_SUMMARY[@]} changed file(s) the git diff surfaced; adding them to the review scope:"
    printf '  - %s\n' "${MISSING_FROM_SUMMARY[@]}"
  fi
fi

Post-processing (all tiers):

  1. Expand tilde paths: SUMMARY.md key-files entries may record a ~/...-prefixed path (e.g. ~/.claude/gsd-core/workflows/verify-phase.md). Bash only tilde-expands a literal ~ written in source text, never one arriving as the value of an already-expanded variable, so every later [ -f "$file" ] check must see a real, expanded path or it misclassifies the file as deleted.
EXPANDED_FILES=()
for file in "${REVIEW_FILES[@]}"; do
  case "$file" in
    "~/"*) file="${HOME}${file#\~}" ;;
  esac
  EXPANDED_FILES+=("$file")
done
REVIEW_FILES=("${EXPANDED_FILES[@]}")
  1. Apply exclusions (per D-03): Remove paths matching planning artifacts
FILTERED_FILES=()
for file in "${REVIEW_FILES[@]}"; do
  # Skip planning directory and specific artifacts
  if [[ "$file" == .planning/* ]] || \
     [[ "$file" == ROADMAP.md ]] || \
     [[ "$file" == STATE.md ]] || \
     [[ "$file" == *-SUMMARY.md ]] || \
     [[ "$file" == *-VERIFICATION.md ]] || \
     [[ "$file" == *-PLAN.md ]]; then
    continue
  fi
  FILTERED_FILES+=("$file")
done
REVIEW_FILES=("${FILTERED_FILES[@]}")
  1. Filter deleted files: Remove paths that don't exist on disk
EXISTING_FILES=()
DELETED_COUNT=0
for file in "${REVIEW_FILES[@]}"; do
  if [ -f "$file" ]; then
    EXISTING_FILES+=("$file")
  else
    DELETED_COUNT=$((DELETED_COUNT + 1))
  fi
done
REVIEW_FILES=("${EXISTING_FILES[@]}")

if [ $DELETED_COUNT -gt 0 ]; then
  echo "Filtered $DELETED_COUNT deleted files from review scope"
fi
  1. Deduplicate: Remove duplicate paths (portable — bash 3.2+ compatible, handles spaces in paths)
DEDUPED=()
while IFS= read -r line; do
  [ -n "$line" ] && DEDUPED+=("$line")
done < <(printf '%s\n' "${REVIEW_FILES[@]}" | sort -u)
REVIEW_FILES=("${DEDUPED[@]}")
  1. Sort: Alphabetical sort for reproducible agent input (already sorted by sort -u above)

Log final scope and warn if large:

if [ -n "$FILES_OVERRIDE" ]; then
  TIER="--files override"
elif [ -n "$SUMMARIES" ] && [ ${#REVIEW_FILES[@]} -gt 0 ]; then
  TIER="SUMMARY.md"
else
  TIER="git diff"
fi
echo "File scope: ${#REVIEW_FILES[@]} files from ${TIER}"

# Warn if file count is very large — may exceed agent context or produce superficial review
if [ ${#REVIEW_FILES[@]} -gt 50 ]; then
  echo "Warning: ${#REVIEW_FILES[@]} files is a large review scope."
  echo "Consider using --files to narrow scope, or --depth=quick for a faster pass."
  if [ "$REVIEW_DEPTH" = "deep" ]; then
    echo "Switching from deep to standard depth for large file count."
    REVIEW_DEPTH="standard"
  fi
fi
If REVIEW_FILES is empty: ``` No source files changed in phase ${PHASE_ARG}. Skipping review. ``` Exit workflow. Do NOT spawn agent or create REVIEW.md. Optional structural cross-module pass powered by fallow.

Parse fallow_enabled, fallow_scope, fallow_profile, fallow_mcp, fallow_max_crap from the init JSON as FALLOW_ENABLED, FALLOW_SCOPE, FALLOW_PROFILE, FALLOW_MCP, FALLOW_MAX_CRAP. These are resolved once by init.code-review at init time — consuming the pre-resolved values here (instead of a config-get call inside this step) avoids gating this section's own inclusion on a fact its own body would otherwise compute (see state:fallow-enabled in docs/reference/workflow-fragments.md).

Defaults are fail-closed and opt-in:

  • enabled=false (skip entirely)
  • scope=phase
  • profile=standard (maps to --max-crap 30; minimal=50, standard=30, strict=15 — fallow has no native profile concept)
  • mcp=false

If section_manifest is null or "structural-pre-pass" is in its included list: read and execute gsd-core/workflows/code-review/steps/structural-pre-pass.md. Otherwise skip — do not read the file.

When disabled, set:

FALLOW_JSON_PATH=""
Compute the review output path: ```bash REVIEW_PATH="${PHASE_DIR}/${PADDED_PHASE}-REVIEW.md" ```

Compute DIFF_BASE for agent context (in case agent needs it):

PHASE_COMMITS=$(git log --oneline --all --grep="${PADDED_PHASE}" --format="%H" 2>/dev/null)
if [ -n "$PHASE_COMMITS" ]; then
  DIFF_BASE=$(echo "$PHASE_COMMITS" | tail -1)^
else
  DIFF_BASE=""
fi

Build files_to_read block for agent:

FILES_TO_READ=""
for file in "${REVIEW_FILES[@]}"; do
  FILES_TO_READ+="- ${file}\n"
done

Build config block for agent:

CONFIG_FILES=""
for file in "${REVIEW_FILES[@]}"; do
  CONFIG_FILES+="  - ${file}\n"
done

Build structural findings block for agent:

STRUCTURAL_FINDINGS_BLOCK=""
MAX_FINDINGS_SIZE=50000
if [ -n "$FALLOW_JSON_PATH" ] && [ -f "$FALLOW_JSON_PATH" ]; then
  # Normalize fallow's raw report into the compact {summary, findings[]} contract
  # the reviewer consumes (real fallow schema -> normalized findings).
  FALLOW_NORMALIZED_PATH="${PHASE_DIR}/FALLOW-normalized.json"
  FALLOW_SRC="$FALLOW_JSON_PATH" FALLOW_OUT="$FALLOW_NORMALIZED_PATH" node -e "
    const fs = require('fs');
    const { normalizeFallowReportFile } = require('./gsd-core/bin/lib/fallow-runner.cjs');
    const n = normalizeFallowReportFile(process.env.FALLOW_SRC);
    fs.writeFileSync(process.env.FALLOW_OUT, JSON.stringify(n, null, 2));
  " 2>/dev/null && FALLOW_EMBED_PATH="$FALLOW_NORMALIZED_PATH" || FALLOW_EMBED_PATH="$FALLOW_JSON_PATH"
  FALLOW_JSON_SIZE=$(wc -c < "$FALLOW_EMBED_PATH" | tr -d '[:space:]')
  if [ "$FALLOW_JSON_SIZE" -le "$MAX_FINDINGS_SIZE" ]; then
    # Escape any literal closing tag before embedding; the closing tag literal is escaped to prevent prompt-structure breakage if a fallow finding's file path or message contains the sequence.
    SAFE_FALLOW_JSON=$(sed 's#</structural_findings>#<\/structural_findings>#g' "$FALLOW_EMBED_PATH")
    STRUCTURAL_FINDINGS_BLOCK=$(printf '<structural_findings>\n%s\n</structural_findings>\n' "$SAFE_FALLOW_JSON")
  else
    echo "Warning: skipping structural findings embed (${FALLOW_JSON_SIZE} bytes > ${MAX_FINDINGS_SIZE} bytes). Re-run with narrower scope/profile if needed."
  fi
fi

Spawn the gsd-code-reviewer agent:

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

Runtime-aware dispatch (#2508 Phase 4). GSD workflows dispatch specialized subagents by role. Before dispatching on a built-in-only runtime (kimi-code — three built-ins only), resolve the role to a built-in via gsd_run query resolve-dispatch-type --requested <role> --raw. On named-dispatch runtimes (Claude/OpenCode/…) the role is returned unchanged; on kimi-code it maps to coder/explore/plan by role-suffix. The persona rides ${AGENT_SKILLS_<ROLE>} (Phase 3) regardless. See @gsd-core/references/runtime-aware-dispatch.md.

Model omission (#2517). Omit the model parameter entirely when the value it would carry (REVIEWER_MODEL) is "inherit" or empty. An empty value 404s on runtimes without native tier aliases — the default on non-Claude runtimes. Omitting it inherits the orchestrator's model. See @gsd-core/references/model-profile-resolution.md.

Agent(subagent_type="gsd-code-reviewer", model="{REVIEWER_MODEL}", prompt="
<files_to_read>
${FILES_TO_READ}
</files_to_read>

${STRUCTURAL_FINDINGS_BLOCK}

<config>
depth: ${REVIEW_DEPTH}
phase_dir: ${PHASE_DIR}
review_path: ${REVIEW_PATH}
${DIFF_BASE:+diff_base: ${DIFF_BASE}}
files:
${CONFIG_FILES}
</config>

Review the listed source files at ${REVIEW_DEPTH} depth. Write findings to ${REVIEW_PATH}.
Do NOT commit the output — the orchestrator handles that.
${AGENT_SKILLS_REVIEWER}")

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.

Agent failure handling:

If the Agent() call fails (agent error, timeout, or exception):

Error: Code review agent failed: ${error_message}

No REVIEW.md created. You can retry with /gsd:code-review ${PHASE_ARG} or check agent logs.

Do NOT proceed to commit_review step. Do NOT create a partial or empty REVIEW.md. Exit workflow.

After agent completes successfully, verify REVIEW.md was created and has valid structure:
if [ -f "${REVIEW_PATH}" ]; then
  # Validate REVIEW.md has valid YAML frontmatter with status field
  HAS_STATUS=$(REVIEW_PATH="${REVIEW_PATH}" node -e "
    const fs = require('fs');
    const content = fs.readFileSync(process.env.REVIEW_PATH, 'utf-8');
    const match = content.replace(/\r\n/g, '\n').match(/^---\n([\s\S]*?)\n---/);
    if (match && /status:/.test(match[1])) { console.log('valid'); } else { console.log('invalid'); }
  " 2>/dev/null)
  
  if [ "$HAS_STATUS" = "valid" ]; then
    echo "REVIEW.md created at ${REVIEW_PATH}"
    
    if [ "$COMMIT_DOCS" = "true" ]; then
      gsd_run query commit \
        "docs(${PADDED_PHASE}): add code review report" \
        --files "${REVIEW_PATH}"
    fi
  else
    echo "Warning: REVIEW.md exists but has invalid or missing frontmatter (no status field)."
    echo "Agent may have produced malformed output. Not committing. Review manually: ${REVIEW_PATH}"
  fi
else
  echo "Warning: Agent completed but REVIEW.md not found at ${REVIEW_PATH}. This may indicate an agent issue."
  echo "No REVIEW.md to commit. Please retry with /gsd:code-review ${PHASE_ARG}"
fi

If section_manifest is null or "dispatch-fix" is in its included list: read and execute gsd-core/workflows/code-review/steps/dispatch-fix.md. Otherwise skip — do not read the file; proceed to present_results.

Read the REVIEW.md YAML frontmatter to extract finding counts.

Extract frontmatter between --- delimiters first to avoid matching values in the review body:

# Extract only the YAML frontmatter block (between first two --- lines)
FRONTMATTER=$(REVIEW_PATH="${REVIEW_PATH}" node -e "
  const fs = require('fs');
  const content = fs.readFileSync(process.env.REVIEW_PATH, 'utf-8');
  const match = content.replace(/\r\n/g, '\n').match(/^---\n([\s\S]*?)\n---/);
  if (match) process.stdout.write(match[1]);
" 2>/dev/null)

# Parse fields from frontmatter only (not full file)
STATUS=$(echo "$FRONTMATTER" | grep "^status:" | cut -d: -f2 | xargs)
FILES_REVIEWED=$(echo "$FRONTMATTER" | grep "^files_reviewed:" | cut -d: -f2 | xargs)
CRITICAL=$(echo "$FRONTMATTER" | grep -E "^[[:space:]]*(critical|blocker):" | head -1 | cut -d: -f2 | xargs)
WARNING=$(echo "$FRONTMATTER" | grep "warning:" | head -1 | cut -d: -f2 | xargs)
INFO=$(echo "$FRONTMATTER" | grep "info:" | head -1 | cut -d: -f2 | xargs)
TOTAL=$(echo "$FRONTMATTER" | grep "total:" | head -1 | cut -d: -f2 | xargs)

Display inline summary to user:

═══════════════════════════════════════════════════════════════

  Code Review Complete: Phase ${PHASE_NUMBER} (${PHASE_NAME})

───────────────────────────────────────────────────────────────

  Depth:           ${REVIEW_DEPTH}
  Files Reviewed:  ${FILES_REVIEWED}
  
  Findings:
    Critical:  ${CRITICAL}
    Warning:   ${WARNING}
    Info:      ${INFO}
    ──────────
    Total:     ${TOTAL}

───────────────────────────────────────────────────────────────

If status is "clean":

✓ No issues found. All ${FILES_REVIEWED} files pass review at ${REVIEW_DEPTH} depth.

Full report: ${REVIEW_PATH}

If total findings > 0:

⚠ Issues found. Review the report for details.

Full report: ${REVIEW_PATH}

Next steps:
  /gsd:code-review ${PHASE_NUMBER} --fix  — Auto-fix issues
  cat ${REVIEW_PATH}                     — View full report

If critical > 0 or warning > 0, list top 3 issues inline:

echo "Top issues:"
grep -A 3 "^### CR-\|^### BL-\|^### WR-" "${REVIEW_PATH}" | head -n 12

Note on tests: Automated tests for this command and workflow are planned for Phase 4 (Pipeline Integration & Testing, requirement INFR-03). Phase 2 focuses on correct implementation; Phase 4 adds regression coverage across platforms.

═══════════════════════════════════════════════════════════════

<platform_notes> Windows: This workflow uses bash features (arrays, process substitution). On Windows, it requires Git Bash or WSL. Native PowerShell is not supported. The CI matrix (Ubuntu/macOS/Windows) runs under Git Bash on Windows runners, which provides bash compatibility.

macOS: macOS ships with bash 3.2 (GPL licensing). This workflow does NOT use mapfile (bash 4+ only) — all array construction uses portable while IFS= read -r loops compatible with bash 3.2. The --files path validation uses realpath -m which requires GNU coreutils (install via brew install coreutils). Without coreutils, the path guard falls back to fail-closed behavior (rejects paths it cannot verify), so security is maintained but valid relative paths may be rejected. If --files validation fails unexpectedly on macOS, install coreutils or use absolute paths. </platform_notes>

<success_criteria>

  • Phase validated before config gate check
  • Capability gate checked (execute:post code-review hook)
  • --fix/--all/--auto flags parsed via code-review-flags.cjs typed IR (not ad-hoc bash)
  • Depth resolved with validation (quick|standard|deep)
  • File scope computed with 3 tiers: --files > SUMMARY.md > git diff
  • Malformed/missing SUMMARY.md handled gracefully with fallback
  • Deleted files filtered from scope
  • Files deduplicated and sorted
  • Empty scope results in skip (no agent spawn)
  • Agent spawned with explicit file list, depth, review_path, diff_base
  • Agent failure handled without partial commits
  • REVIEW.md committed if created
  • When --fix: dispatch_fix step delegates to code-review-fix.md with --all/--auto forwarded
  • Results presented inline with next step suggestion (review-only path) </success_criteria>