Files
msd-core/gsd-core/workflows/next.md
Tom Boucher 342590c70e refactor(#3184): milestone windowing has one owner and a decidable failure signal (#3209)
* test(#3184): failing-first milestone-window single-owner suite

Covers the 50 input classes in the phase test matrix: scope classification
(genuinely-empty vs truncated vs unscoped vs unreadable), the section-end
owner's level boundaries, consumer-output identity per ADR-3180 Decision 4(c),
the milestone.complete refusal with negative proof that no directory moved,
the version-token boundary defect, drift-guard behavior, and three fast-check
properties over document-shaped generators.

Committed alone so the remote runner records the failure before the fix lands.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015kfkRFNUESoBspUYcAQaT3

* refactor(#3184): milestone windowing routes through one owner

Three copies of the milestone section-end walk lived in roadmap-parser.cts —
two distinct computeSectionEnd function nodes plus an inline third in
getMilestonePhaseFilter's versionOverride branch. computeMilestoneSectionEnd is
now the sole owner and the other two are deleted, not kept in sync by comment.

The whole-repo drift guard found what the epic did not: state.cts held three
more re-derivations of the same vocabulary — two byte-identical milestone
bounding checks carrying a defect neither reported copy has (no boundary after
the version token, so v2.0 matched inside v2.0.1), and a milestone-sectioning
predicate. All three route through the owner now.

A composition-level duplicate appeared inside this change's own first pass:
getMilestonePhaseFilter and cmdMilestoneComplete each re-assembled a window out
of the owner's primitives, and had already diverged on whether to skip a closed
milestone heading. sliceMilestoneWindow is the one composition.

Windows now carry the ADR-3180 SCOPE discriminator, so a truncated window is
distinguishable from a genuinely empty milestone — those were output-identical,
which is the whole failure class. roadmap analyze emits it (#3165), and
milestone complete refuses to archive on anything but COMPLETE rather than
pass-all moving every phase directory on disk (#3166). The pass-all degrade is
preserved where its premise holds: making the filter deny-all would trade a
silent over-inclusive answer for a silent under-inclusive one on the read paths
that count with it.

extractCurrentMilestone keeps its signature — 200+ affected symbols across 41
files and 25 process flows — and is a one-line wrapper over the scoped owner.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015kfkRFNUESoBspUYcAQaT3

* fix(#3184): fence-aware phase detection and one heading-selection owner

Review fixes from the two orthogonal passes.

The blocker: hasPhaseEntries matched ATX phase headings fence-aware via
tokenizeHeadings but tested the #2199 bullet form against un-stripped markdown,
so a fenced EXAMPLE of the bullet syntax counted as a real phase. A genuinely
empty milestone then classified TRUNCATED and milestone complete refused a
legitimate archive — a false positive in the destructive direction, worse than
the defect this phase set out to fix. Both that path and getMilestonePhaseFilter
own pre-existing bullet scan now run on stripFencedCode, since leaving one meant
the owner file gave two different answers to the same question.

The selection rule — locate, prefer the non-closed heading, else the first — had
been written three more times inside the file whose thesis is single ownership.
selectMilestoneHeading owns it; all three sites route through it. The copies were
behaviorally identical, so this is de-duplication with no observable change,
verified by probing that all three paths select the same heading.

roadmap analyze emitting a scope no consumer read left #3165's actual symptom
alive, so Route 0 in next.md now treats a non-complete scope as scan-failed
rather than as a clean empty scan, and the ADR amendment no longer overstates
what shipped.

Also: the scope refusal moved above the archive-directory create, so a refusal
leaves nothing on disk; the versionOverride comment names all four consumers;
COMMANDS.md documents the new guard beside its sibling.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015kfkRFNUESoBspUYcAQaT3

* test(#2658): exclude the changelog from the malformed-path scan

The gate walks every emitted .md/.js/.cjs file in an installed tree and asserts
none contains `.claude/.trae/rules` or `.trae/.trae/rules`. CHANGELOG.md ships
into that tree, and its #2658 entry quotes both malformed paths while describing
the fix that removed them — so the release note documenting the fix trips the
fix's own regression test. Red on next before this branch.

The installer is correct: a probe over a real --trae --local install found 621
emitted files, exactly one hit, and it was gsd-core/CHANGELOG.md. The scan scope
was the defect, not the product.

Excluded by exact relative path rather than by loosening the patterns or skipping
all markdown — the emitted agent and command markdown is precisely what #2658 was
about, so the gate stays strong everywhere it matters.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015kfkRFNUESoBspUYcAQaT3

* test(#3184): regenerate install-tree fixtures for the shared drift scanner

scripts/lib/ ships in the npm package and installer, so extracting the shared
tree-walk into scripts/lib/drift-scan.cjs adds one path to every runtime's
install tree. Regenerated via npm run gen:install-tree; the delta is exactly
that one path per fixture.

The two drift guards themselves do not ship (scripts/lint-*.cjs is excluded),
so only the extracted library moves. This matches the existing
scripts/lib/allowlist-ratchet.cjs precedent, which is likewise a lint-only
helper carried in the shipped tree.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015kfkRFNUESoBspUYcAQaT3

* fix(#3184): restore the #730 sub-milestone boundary and narrow the refusal

The remote runner caught two regressions this branch introduced. Both were mine,
and neither review pass found them — only running the existing suite did.

The version-token boundary. I replaced locateMilestoneHeadings' \b with
(?![\w.-]), reasoning that v2.0 matching inside v2.0.1 was the same defect #2562
fixed in isMilestoneShippedInRoadmap. It is not the same question. A milestone
state of v8.0 legitimately selects the '## v8.0-B' sub-milestone section over a
closed v8.0-A sibling (#730), and \b is what allows it while the stricter
boundary forbids it — nine tests in roadmap-phase-fallback said so. Reverted to
\b; the state.cts consolidation is now a straight merge with no behavior change,
and the v2.0/v2.0.1 ambiguity is left exactly as it was. The ADR amendment and
the design doc no longer claim otherwise.

The refusal scope. I refused whenever the window was not COMPLETE, but #3166 is
about the TRUNCATED window specifically — the heading is found and the section
closes before the phase region, so pass-all archives everything. UNREADABLE and
UNSCOPED are pre-existing, legitimately handled states, and refusing on them
broke 'handles missing ROADMAP.md gracefully' and three archive tests. Narrowed
to TRUNCATED; docs corrected to match.

One of the new tests was also wrong: its fixture gave the shipped and current
milestones' phases the same numeric id, and the filter matches on that id, so it
could not have distinguished the two windows. Fixture corrected to exercise what
it claims to.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015kfkRFNUESoBspUYcAQaT3

* fix(#3184): enumerate drift-scan.cjs for uninstall

The installer copies scripts/lib/ wholesale, but uninstall removes an explicit
set — deliberately, so a user's own helpers in that directory survive. The
extracted drift-scan.cjs was copied in and never enumerated, so it outlived
uninstall, left the directory non-empty, and the rmdir that follows failed.

Added to GSD_SCRIPTS_LIB_FILES, following allowlist-ratchet.cjs, which is
likewise a lint-only helper that ships there and is enumerated. Verified with a
real install-then-uninstall into a temp target: scripts/lib/ held exactly the
three GSD files and was gone afterwards.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015kfkRFNUESoBspUYcAQaT3

* test(#3184): assert install and uninstall agree on scripts/lib and scripts/changeset

Found while shipping this phase, and fixed here rather than noted.

install() copies scripts/lib/ and scripts/changeset/ into the target WHOLESALE —
the comment at the copy site literally says "and any future lib helpers".
uninstall() removes them by hardcoded enumeration, deliberately, so a user's own
helpers in those directories survive. A wholesale writer paired with an
enumerated remover cannot stay in sync by construction: any file added to either
directory ships to every user and is then orphaned in their repo forever, since
it survives uninstall, leaves the directory non-empty, and the rmdir that follows
fails. Nothing reported this. 31,225 tests were green over it.

That is the same divergence class this epic exists to delete, sitting in the
installer, so it gets the same remedy CLAUDE.md prescribes for it: a parity
assertion that fails the moment the two surfaces disagree. The test compares each
directory's real contents against its enumeration and names the offending file
plus the constant to add it to.

Both enumerations are hoisted to module scope and exported, so the test asserts
on the actual arrays rather than pattern-matching the installer's source — no
allow-test-rule annotation needed. Proven non-vacuous both ways: empty diff on
the current tree, correct report when an unenumerated file is injected.

scripts/changeset/ turned out to carry the identical defect and is covered too.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015kfkRFNUESoBspUYcAQaT3

* chore(#3184): backfill changeset PR number

Also narrows the wording to match the shipped behavior: the refusal fires on a
truncated window specifically, not on any non-complete scope.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015kfkRFNUESoBspUYcAQaT3

---------

Co-authored-by: sim <sim@local>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-08 09:50:35 -04:00

21 KiB

Detect current project state and automatically advance to the next logical GSD workflow step. Reads project state to determine: discuss → plan → execute → verify → complete progression.

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

Read project state to determine current position:
_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
# Get state snapshot
gsd_run query state.json 2>/dev/null || echo "{}"

Also read:

  • .planning/STATE.md — current phase, progress, plan counts
  • .planning/ROADMAP.md — milestone structure and phase list

Extract:

  • current_phase — which phase is active
  • plan_of / plans_total — plan execution progress
  • progress — overall percentage
  • status — active, paused, etc.

If no .planning/ directory exists:

No GSD project detected. Run `/gsd:new-project` to get started.

Exit.

Run hard-stop checks before routing. Exit on first hit unless `--force` was passed.

If --force flag was passed, skip all gates, Route 0, and the prior-phase completeness prompt. Print a one-line warning: ⚠ --force: skipping safety gates Then proceed directly to determine_next_action. (Route 0 and prior_phase_completeness are NOT reached under --force.)

Gate 1: Unresolved checkpoint Check if .planning/.continue-here.md exists:

[ -f .planning/.continue-here.md ]

If found:

⛔ Hard stop: Unresolved checkpoint

`.planning/.continue-here.md` exists — a previous session left
unfinished work that needs manual review before advancing.

Read the file, resolve the issue, then delete it to continue.
Use `--force` to bypass this check.

Exit (do not route).

Gate 2: Error state Check if STATE.md contains status: error or status: failed: If found:

⛔ Hard stop: Project in error state

STATE.md shows status: {status}. Resolve the error before advancing.
Run `/gsd:health` to diagnose, or manually fix STATE.md.
Use `--force` to bypass this check.

Exit.

Gate 3: Unchecked verification Check if the current phase has a VERIFICATION.md with any FAIL items that don't have overrides: If found:

⛔ Hard stop: Unchecked verification failures

VERIFICATION.md for phase {N} has {count} unresolved FAIL items.
Address the failures or add overrides before advancing to the next phase.
Use `--force` to bypass this check.

Exit.

After all three hard-stop gates pass, continue to resume_incomplete_phase.

**Hard invariant: any phase with PLAN.md files lacking matching SUMMARY.md files must be completed before `/gsd:progress --next` routes to any forward action.**

This catches the common failure mode where a session died mid-execution (hang, token exhaustion, API connection drop) and STATE.md's current_phase got advanced past the phase that actually has unfinished work. Without this gate, /gsd:progress --next would route by current_phase and silently skip the partially-executed phase.

Skip if --no-resume was passed (fall through to prior_phase_completeness). (--force already bypassed all gates and Route 0 at safety_gates — it never reaches this step.)

Why Route 0 runs here (after Gates 1-3, before the prior-phase defer prompt): This step is a hard invariant independent of current_phase's value — it must run before any routing rule that reads current_phase. Gates 1-3 are cheap repo/state validity checks that must always run — skipping them on the resume path would risk advancing into a broken-state project. The prior-phase completeness-scan DEFER PROMPT, however, must NOT run in the default (no-flag) case when Route 0 is about to resume the phase automatically: that would force a double-decision (prompt first, then resume anyway), overriding the user's choice. Route 0 placed here means: default = resume silently (no defer prompt); --no-resume = skip Route 0 and fall through to the prior-phase defer prompt in prior_phase_completeness; --force = jump straight to determine_next_action at safety_gates (never reaches Route 0 or prior_phase_completeness at all).

Scan ALL phases in ROADMAP order (lowest-numbered to highest) for incomplete-execution state. Use gsd_run query roadmap.analyze to get the phase list, then for each phase number N query gsd_run query find-phase <N> JSON and inspect its plans and summaries arrays. A phase is incomplete-execution when plans.length > summaries.length (at least one PLAN.md has no matching SUMMARY.md).

Stop at the first such phase. Record its phase number as INCOMPLETE_PHASE. This is the lowest-numbered phase that needs continued execution.

Illustrative bash:

INCOMPLETE_PHASE=""
ROADMAP_JSON=$(gsd_run query roadmap.analyze)
ROADMAP_SCOPE=$(echo "$ROADMAP_JSON" | jq -r '.scope // "complete"')
if [ $? -ne 0 ] || [ -z "$ROADMAP_JSON" ]; then
  echo "⚠ WARNING: resume-incomplete-phase scan could not run (roadmap.analyze failed)." >&2
  echo "  The incomplete-phase invariant (#160) could not be verified." >&2
  echo "  Proceeding to prior-phase completeness check — review project state carefully." >&2
  # Fall through to prior_phase_completeness rather than silently skipping
elif [ "$ROADMAP_SCOPE" != "complete" ]; then
  # #3184/#3165: roadmap.analyze succeeded and returned a well-formed document,
  # but its milestone window did not see all of its input, so `.phases[]` is a
  # NON-answer rather than a real empty. Looping it would run the invariant over
  # a phase list the scan could not populate and report "clean" — the silent
  # disarm #3165 reports. Treated as scan-failed, same as an outright failure.
  echo "⚠ WARNING: resume-incomplete-phase scan could not be scoped (roadmap.analyze scope: $ROADMAP_SCOPE)." >&2
  echo "  The milestone window did not cover the whole ROADMAP, so the phase list is incomplete." >&2
  echo "  The incomplete-phase invariant (#160) could not be verified — review project state carefully." >&2
  # Fall through to prior_phase_completeness rather than silently passing
else
  for PHASE_NUM in $(echo "$ROADMAP_JSON" | jq -r '.phases[] | (.number // .phase_number // empty)'); do
    PHASE_JSON=$(gsd_run query find-phase "$PHASE_NUM")
    if [ $? -ne 0 ] || [ -z "$PHASE_JSON" ]; then
      echo "⚠ WARNING: Could not query phase $PHASE_NUM — skipping in resume scan." >&2
      continue
    fi
    PLAN_COUNT=$(echo "$PHASE_JSON" | jq '(.plans // []) | length')
    SUMMARY_COUNT=$(echo "$PHASE_JSON" | jq '(.summaries // []) | length')
    if [ "${PLAN_COUNT:-0}" -gt "${SUMMARY_COUNT:-0}" ]; then
      INCOMPLETE_PHASE="$PHASE_NUM"
      break
    fi
  done
fi

If INCOMPLETE_PHASE is non-empty: route to /gsd:execute-phase $INCOMPLETE_PHASE and exit. Display a one-line notice before invoking:

▶ Resuming incomplete Phase ${INCOMPLETE_PHASE} (plans without summaries detected)
  /gsd:execute-phase ${INCOMPLETE_PHASE}
  (use --no-resume to skip this check and defer via the prior-phase prompt)

Then invoke via SlashCommand. Do not continue to subsequent steps.

If INCOMPLETE_PHASE is empty: continue to prior_phase_completeness.

**Prior-phase completeness scan (runs when `--no-resume` was passed and Route 0 was skipped, or when Route 0 found no incomplete-execution phases in the default case). NOT reached under `--force` — that flag jumps directly to `determine_next_action` at `safety_gates`.**

Prior-phase completeness scan: Scan all phases that precede the current phase in ROADMAP.md order for incomplete work. For each prior phase number N, use gsd_run query find-phase <N> JSON (plans, summaries, incomplete_plans, etc.) to inspect that phase.

Detect three categories of incomplete work:

  1. Plans without summaries — a PLAN.md exists in a prior phase directory but no matching SUMMARY.md exists (execution started but not completed).
  2. Verification failures not overridden — a prior phase has a VERIFICATION.md with FAIL items that have no override annotation.
  3. CONTEXT.md without plans — a prior phase directory has a CONTEXT.md but no PLAN.md files (discussion happened, planning never ran).

If no incomplete prior work is found, continue to determine_next_action silently with no interruption.

If incomplete prior work is found, show a structured completeness report:

⚠ Prior phase has incomplete work

Phase {N} — "{name}" has unresolved items:
  • Plan {N}-{M} ({slug}): executed but no SUMMARY.md
  [... additional items ...]

Advancing before resolving these may cause:
  • Verification gaps — future phase verification won't have visibility into what prior phases shipped
  • Context loss — plans that ran without summaries leave no record for future agents

Options:
  [C] Continue and defer these items to backlog
  [S] Stop and resolve manually (recommended)
  [F] Force advance without recording deferral

Choice [S]:

If the user chooses "Stop" (S or Enter/default): Exit without routing.

If the user chooses "Continue and defer" (C):

  1. For each incomplete item, create a backlog entry in ROADMAP.md under ## Backlog using the existing 999.x numbering scheme:
### Phase 999.{N}: Follow-up — Phase {src} incomplete plans (BACKLOG)

**Goal:** Resolve plans that ran without producing summaries during Phase {src} execution
**Source phase:** {src}
**Deferred at:** {date} during /gsd:progress --next advancement to Phase {dest}
**Plans:**
- [ ] {N}-{M}: {slug} (ran, no SUMMARY.md)
  1. Commit the deferral record:
gsd_run query commit "docs: defer incomplete Phase {src} items to backlog" \
  --files .planning/ROADMAP.md
  1. Continue routing to determine_next_action immediately — no second prompt.

If the user chooses "Force" (F): Continue to determine_next_action without recording deferral.

Check for pending spike/sketch work and surface a notice (does not change routing):
# Check for pending spikes (verdict: PENDING in any README)
PENDING_SPIKES=$(grep -rl 'verdict: PENDING' .planning/spikes/*/README.md 2>/dev/null | wc -l | tr -d ' ')

# Check for pending sketches (winner: null in any README)
PENDING_SKETCHES=$(grep -rl 'winner: null' .planning/sketches/*/README.md 2>/dev/null | wc -l | tr -d ' ')

If either count is > 0, display before routing:

⚠ Pending exploratory work:
  {PENDING_SPIKES} spike(s) with unresolved verdicts in .planning/spikes/
  {PENDING_SKETCHES} sketch(es) without a winning variant in .planning/sketches/

  Resume with `/gsd:spike` or `/gsd:sketch`, or continue with phase work below.

Only show lines for non-zero counts. If both are 0, skip this notice entirely.

Apply routing rules based on state:

Route 1: No phases exist yet → discuss If ROADMAP has phases but no phase directories exist on disk: → Next action: /gsd:discuss-phase <first-phase>

Route 2: Phase exists but has no CONTEXT.md or RESEARCH.md → discuss If the current phase directory exists but has neither CONTEXT.md nor RESEARCH.md: → Next action: /gsd:discuss-phase <current-phase>

Route 3: Phase has context but no plans → plan If the current phase has CONTEXT.md (or RESEARCH.md) but no PLAN.md files: → Next action: /gsd:plan-phase <current-phase> (or /gsd:plan-review-convergence <current-phase> when PLAN_STRATEGY=converge)

Route 4: Phase has plans but incomplete summaries → execute If plans exist but not all have matching summaries: → Next action: /gsd:execute-phase <current-phase>

Route 5: All plans have summaries → verify and complete If all plans in the current phase have summaries: → Next action: /gsd:verify-work

Route 6: Phase complete, next phase exists → advance If the current phase is complete and the next phase exists in ROADMAP: → Next action: /gsd:discuss-phase <next-phase>

Route 7: All phases complete → complete milestone If all phases are complete: → Next action: /gsd:complete-milestone

Route 8: Paused → resume If STATE.md shows paused_at: → Next action: /gsd:resume-work

Parse the arguments passed to this workflow to detect the plan strategy and build convergence pass-through args:
PLAN_STRATEGY="local"
if echo "$ARGUMENTS" | grep -qE '(^|[[:space:]])\-\-(converge|cross-ai)([[:space:]]|$)'; then
  PLAN_STRATEGY="converge"
fi

CONVERGENCE_ARGS=""
# Lane flags derived from the declared roster (#2800/#2272); --all and --text are convergence
# controls, not reviewer lanes, so they stay literal.
for REVIEW_FLAG in $(gsd_run review-lane flags) --all --text; do
  if echo "$ARGUMENTS" | grep -qE "(^|[[:space:]])${REVIEW_FLAG}([[:space:]]|$)"; then
    CONVERGENCE_ARGS="${CONVERGENCE_ARGS} ${REVIEW_FLAG}"
  fi
done

MAX_CYCLES_ARG=""
if echo "$ARGUMENTS" | grep -qE '\-\-max-cycles\s+[0-9]+'; then
  MAX_CYCLES_ARG=$(echo "$ARGUMENTS" | grep -oE '\-\-max-cycles\s+[0-9]+' | awk '{print $2}')
  CONVERGENCE_ARGS="${CONVERGENCE_ARGS} --max-cycles ${MAX_CYCLES_ARG}"
fi

If PLAN_STRATEGY is converge, fail fast unless the convergence feature gate is enabled:

if [ "$PLAN_STRATEGY" = "converge" ]; then
  CONVERGENCE_ENABLED=$(gsd_run query config-get workflow.plan_review_convergence 2>/dev/null || echo "false")
  if [ "$CONVERGENCE_ENABLED" != "true" ]; then
    printf '%s\n' \
      '/gsd:progress --next --converge is disabled (workflow.plan_review_convergence=false).' \
      '' \
      'Enable plan convergence with:' \
      '' \
      '  gsd config-set workflow.plan_review_convergence true' \
      '' \
      'Then re-run with --converge.'
    exit 1
  fi
fi

Display the determination:

## GSD Next

**Current:** Phase [N] — [name] | [progress]%
**Status:** [status description]

▶ **Next step:** `/gsd-[command] [args]`
  [One-line explanation of why this is the next step]

Then immediately invoke the determined command via SlashCommand. Do not ask for confirmation — the whole point of /gsd:progress --next is zero-friction advancement.

Route 3 convergence override: When the routing decision is Route 3 (plan) and PLAN_STRATEGY=converge, invoke /gsd:plan-review-convergence <current-phase> ${CONVERGENCE_ARGS} instead of /gsd:plan-phase <current-phase>.

If --auto was passed: after the determined command completes, automatically re-invoke /gsd:progress --next --auto (forwarding --converge/--cross-ai and any reviewer flags if they were originally passed) to continue chaining to the next step. Repeat until one of:

  • A milestone completes (/gsd:complete-milestone is reached)
  • A blocking decision is required (safety gate triggers, prior-phase completeness prompt, user input needed)
  • An error or paused state is detected

When stopping due to a blocker, display:

⛔ Auto-chain stopped: [reason — e.g. safety gate, blocking decision required]

Resume with: `/gsd:progress --next --auto` once resolved.

<success_criteria>

  • Project state correctly detected
  • Gates 1-3 (repo/state validity) run first — always, even on the resume path
  • Route 0 (resume_incomplete_phase) runs AFTER Gates 1-3 and BEFORE the prior-phase defer prompt — no double-decision in the default (no-flag) case
  • Default (no flag): Route 0 resumes incomplete phase silently, exits — user never sees the prior-phase defer prompt
  • --no-resume: Route 0 skipped, prior_phase_completeness defer prompt runs as before
  • --force: everything skipped (Gates, Route 0, prior_phase_completeness) → straight to determine_next_action
  • Scan uses gsd_run (canonical resolver form); errors are surfaced rather than suppressed
  • A roadmap.analyze result whose scope is not complete is treated as scan-failed (warn + fall through), never as a clean empty scan (#3184/#3165)
  • Predicate is plans-without-summaries (plans.length > summaries.length) — consistent with determine_next_action Route 4
  • Next action correctly determined from routing rules
  • Command invoked immediately without user confirmation
  • Clear status shown before invoking
  • --converge routes Route 3 planning through gsd-plan-review-convergence
  • --cross-ai is accepted as an alias for --converge
  • --converge fails fast with enable instructions when workflow.plan_review_convergence=false
  • --converge forwards reviewer selector flags and --max-cycles N
  • Default planning remains gsd-plan-phase when convergence is not requested </success_criteria>