Files
msd-core/gsd-core/workflows/transition.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

21 KiB

<internal_workflow>

This is an INTERNAL workflow — NOT a user-facing command.

There is no /gsd-transition command. This workflow is invoked automatically by execute-phase during auto-advance, or inline by the orchestrator after phase verification. Users should never be told to run /gsd-transition.

Valid user commands for phase progression:

  • /gsd:discuss-phase {N} — discuss a phase before planning
  • /gsd:plan-phase {N} — plan a phase
  • /gsd:execute-phase {N} — execute a phase
  • /gsd:progress — see roadmap progress

</internal_workflow>

<required_reading>

Read these files NOW:

  1. .planning/STATE.md
  2. .planning/PROJECT.md
  3. .planning/ROADMAP.md
  4. Current phase's plan files (*-PLAN.md)
  5. Current phase's summary files (*-SUMMARY.md)

</required_reading>

Mark current phase complete and advance to next. This is the natural point where progress tracking and PROJECT.md evolution happen.

"Planning next phase" = "current phase is done"

Before transition, read project state:

cat .planning/STATE.md 2>/dev/null || true
cat .planning/PROJECT.md 2>/dev/null || true

Parse current position to verify we're transitioning the right phase. Note accumulated context that may need updating after transition.

Check current phase has all plan summaries:

(ls .planning/phases/XX-current/*-PLAN.md 2>/dev/null || true) | sort
(ls .planning/phases/XX-current/*-SUMMARY.md 2>/dev/null || true) | sort

Verification logic:

  • Count PLAN files
  • Count SUMMARY files
  • If counts match: all plans complete
  • If counts don't match: incomplete
cat .planning/config.json 2>/dev/null || true

Check for verification debt in this phase:

# Run a preliminary frontmatter check via awk — the runtime launcher is not yet
# defined at this step, so avoid any runtime tool calls here.
# awk extracts only the status: field between the two --- fences to avoid
# false positives from historical body text (e.g. previous_status: gaps_found).
VERIFY_STATUS=$(awk 'NR==1&&/^---$/{in_fm=1;next}in_fm&&/^---$/{exit}in_fm&&/^status: /{print $2}' \
  .planning/phases/XX-current/*-VERIFICATION.md 2>/dev/null | head -1)

If VERIFY_STATUS is not passed:

Stop before confirming:

Verification incomplete: ${VERIFY_STATUS:-missing}

Resolve before transition. Review: `/gsd:audit-uat`

This preliminary check blocks obviously unresolved verification before the launcher is available. gsd-tools.cjs query phase.complete remains the authoritative stale-aware gate and fail-closes unless canonical verification status is passed.

If all plans complete:

⚡ Auto-approved: Transition Phase [X] → Phase [X+1]
Phase [X] complete — all [Y] plans finished.

Proceeding to mark done and advance...

Proceed directly to cleanup_handoff step.

Ask: "Phase [X] complete — all [Y] plans finished. Ready to mark done and move to Phase [X+1]?"

Wait for confirmation before proceeding.

If plans incomplete:

SAFETY RAIL: always_confirm_destructive applies here. Skipping incomplete plans is destructive — ALWAYS prompt regardless of mode.

Present:

Phase [X] has incomplete plans:
- {phase}-01-SUMMARY.md ✓ Complete
- {phase}-02-SUMMARY.md ✗ Missing
- {phase}-03-SUMMARY.md ✗ Missing

⚠️ Safety rail: Skipping plans requires confirmation (destructive action)

Options:
1. Continue current phase (execute remaining plans)
2. Mark complete anyway (skip remaining plans)
3. Review what's left

Wait for user decision.

Check for lingering handoffs:

ls .planning/phases/XX-current/.continue-here*.md 2>/dev/null || true

If found, delete them — phase is complete, handoffs are stale.

Delegate ROADMAP.md and STATE.md updates to gsd-tools.cjs query phase.complete:

_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%/*}" >> "$CLAUDE_ENV_FILE" 2>/dev/null || true; fi
TRANSITION=$(gsd_run query phase.complete "${current_phase}")

The CLI handles:

  • Marking the phase checkbox as [x] complete with today's date
  • Updating plan count to final (e.g., "3/3 plans complete")
  • Updating the Progress table (Status → Complete, adding date)
  • Advancing STATE.md to next phase (Current Phase, Status → Ready to plan, Current Plan → Not started)
  • Detecting if this is the last phase in the milestone

Extract from result: completed_phase, plans_executed, next_phase, next_phase_name, is_last_phase.

If prompts were generated for the phase, they stay in place. The completed/ subfolder pattern from create-meta-prompts handles archival.

Evolve PROJECT.md to reflect learnings from completed phase.

Read phase summaries:

cat .planning/phases/XX-current/*-SUMMARY.md

Assess requirement changes:

  1. Requirements validated?

    • Any Active requirements shipped in this phase?
    • Move to Validated with phase reference: - ✓ [Requirement] — Phase X
  2. Requirements invalidated?

    • Any Active requirements discovered to be unnecessary or wrong?
    • Move to Out of Scope with reason: - [Requirement] — [why invalidated]
  3. Requirements emerged?

    • Any new requirements discovered during building?
    • Add to Active: - [ ] [New requirement]
  4. Decisions to log?

    • Extract decisions from SUMMARY.md files
    • Add to Key Decisions table with outcome if known
  5. "What This Is" still accurate?

    • If the product has meaningfully changed, update the description
    • Keep it current and accurate

Update PROJECT.md:

Make the edits inline. Update "Last updated" footer:

---
*Last updated: [date] after Phase [X]*

Example evolution:

Before:

### Active

- [ ] JWT authentication
- [ ] Real-time sync < 500ms
- [ ] Offline mode

### Out of Scope

- OAuth2 — complexity not needed for v1

After (Phase 2 shipped JWT auth, discovered rate limiting needed):

### Validated

- ✓ JWT authentication — Phase 2

### Active

- [ ] Real-time sync < 500ms
- [ ] Offline mode
- [ ] Rate limiting on sync endpoint

### Out of Scope

- OAuth2 — complexity not needed for v1

Step complete when:

  • Phase summaries reviewed for learnings
  • Validated requirements moved from Active
  • Invalidated requirements moved to Out of Scope with reason
  • Emerged requirements added to Active
  • New decisions logged with rationale
  • "What This Is" updated if product changed
  • "Last updated" footer reflects this transition

Scan LEARNINGS.md files from recent phases for recurring patterns and surface promotion candidates to the developer.

Invoke the graduation helper:

@~/.claude/gsd-core/workflows/graduation.md

This step is fully delegated to graduation.md. It handles guard checks (feature flag, window size, threshold), clustering, backlog filtering, HITL prompting, promotion writes, and STATE.md updates.

This step is always non-blocking: graduation candidates are surfaced for the developer's decision; no action is required to continue the transition. If the graduation scan produces no qualifying clusters, it prints a single [graduation: no qualifying clusters] line and returns.

Step complete when:

  • graduation.md guard checks passed (or skipped with silent no-op)
  • Recurring clusters surfaced (or [graduation: no qualifying clusters] printed)
  • Each cluster resolved as Promote / Defer / Dismiss (or all skipped)

Note: Basic position updates (Current Phase, Status, Current Plan, Last Activity) were already handled by gsd-tools.cjs query phase.complete in the update_roadmap_and_state step.

Verify the updates are correct by reading STATE.md. If the progress bar needs updating, use:

PROGRESS=$(gsd_run query progress.bar --raw)

Update the progress bar line in STATE.md with the result.

Step complete when:

  • Phase number incremented to next phase (done by phase complete)
  • Plan status reset to "Not started" (done by phase complete)
  • Status shows "Ready to plan" (done by phase complete)
  • Progress bar reflects total completed plans

Update Project Reference section in STATE.md.

## Project Reference

See: .planning/PROJECT.md (updated [today])

**Core value:** [Current core value from PROJECT.md]
**Current focus:** [Next phase name]

Update the date and current focus to reflect the transition.

Review and update Accumulated Context section in STATE.md.

Decisions:

  • Note recent decisions from this phase (3-5 max)
  • Full log lives in PROJECT.md Key Decisions table

Blockers/Concerns:

  • Review blockers from completed phase
  • If addressed in this phase: Remove from list
  • If still relevant for future: Keep with "Phase X" prefix
  • Add any new concerns from completed phase's summaries

Example:

Before:

### Blockers/Concerns

- ⚠️ [Phase 1] Database schema not indexed for common queries
- ⚠️ [Phase 2] WebSocket reconnection behavior on flaky networks unknown

After (if database indexing was addressed in Phase 2):

### Blockers/Concerns

- ⚠️ [Phase 2] WebSocket reconnection behavior on flaky networks unknown

Step complete when:

  • Recent decisions noted (full log in PROJECT.md)
  • Resolved blockers removed from list
  • Unresolved blockers kept with phase prefix
  • New concerns from completed phase added

Update Session Continuity section in STATE.md to reflect transition completion.

Format:

Last session: [today]
Stopped at: Phase [X] complete, ready to plan Phase [X+1]
Resume file: None

Step complete when:

  • Last session timestamp updated to current date and time
  • Stopped at describes phase completion and next phase
  • Resume file confirmed as None (transitions don't use resume files)

MANDATORY: Verify milestone status before presenting next steps.

Use the transition result from gsd-tools.cjs query phase.complete:

The is_last_phase field from the phase complete result tells you directly:

  • is_last_phase: false → More phases remain → Go to Route A
  • is_last_phase: true → Last phase done → Check for workstream collisions first

The next_phase and next_phase_name fields give you the next phase details.

If you need additional context, use:

ROADMAP=$(gsd_run query roadmap.analyze)

This returns all phases with goals, disk status, and completion info.

Section-manifest gate (#2994): gsd_run is already established above (update_roadmap_and_state step) — fetch the dedicated init.transition bundle for the workstream-collision-check gate below:

INIT_TRANSITION=$(gsd_run query init.transition)
if [[ "$INIT_TRANSITION" == @file:* ]]; then INIT_TRANSITION=$(cat "${INIT_TRANSITION#@file:}"); fi

Extract from INIT_TRANSITION: other_active_workstreams, section_manifest.


If section_manifest (from INIT_TRANSITION) is null or "workstream-collision-check" is in its included list: read and execute gsd-core/workflows/transition/steps/workstream-collision-check.md. Otherwise (flat mode) skip — do not read the file; go directly to Route B.


Route A: More phases remain in milestone

Read ROADMAP.md to get the next phase's name and goal.

Check if next phase has CONTEXT.md:

ls .planning/phases/*[X+1]*/*-CONTEXT.md 2>/dev/null || true

If next phase exists:

If CONTEXT.md exists:

Phase [X] marked complete.

Next: Phase [X+1] — [Name]

⚡ Auto-continuing: Plan Phase [X+1] in detail

Exit skill and invoke SlashCommand("/gsd:plan-phase [X+1] --auto ${GSD_WS}")

If CONTEXT.md does NOT exist:

Phase [X] marked complete.

Next: Phase [X+1] — [Name]

⚡ Auto-continuing: Discuss Phase [X+1] first

Exit skill and invoke SlashCommand("/gsd:discuss-phase [X+1] --auto ${GSD_WS}")

If CONTEXT.md does NOT exist:

## ✓ Phase [X] Complete

---

## ▶ Next Up — [${PROJECT_CODE}] ${PROJECT_TITLE}

**Phase [X+1]: [Name]** — [Goal from ROADMAP.md]

`/clear` then:

`/gsd:discuss-phase [X+1] ${GSD_WS}` — gather context and clarify approach

---

**Also available:**
- `/gsd:plan-phase [X+1] ${GSD_WS}` — skip discussion, plan directly
- `/gsd:plan-phase --research-phase [X+1] ${GSD_WS}` — investigate unknowns

---

If CONTEXT.md exists:

## ✓ Phase [X] Complete

---

## ▶ Next Up — [${PROJECT_CODE}] ${PROJECT_TITLE}

**Phase [X+1]: [Name]** — [Goal from ROADMAP.md]
<sub>✓ Context gathered, ready to plan</sub>

`/clear` then:

`/gsd:plan-phase [X+1] ${GSD_WS}`

---

**Also available:**
- `/gsd:discuss-phase [X+1] ${GSD_WS}` — revisit context
- `/gsd:plan-phase --research-phase [X+1] ${GSD_WS}` — investigate unknowns

---

Route B1: Workstream done, other workstreams still active

This route is reached when is_last_phase: true AND the collision check found other active workstreams. Do NOT suggest completing the milestone or advancing to the next milestone — other workstreams are still working.

Clear auto-advance chain flag — workstream boundary is the natural stopping point:

gsd_run query config-set workflow._auto_chain_active false

Override auto-advance: do NOT auto-continue to milestone completion. Present the blocking information and stop.

Present (all modes):

## ✓ Phase {X}: {Phase Name} Complete

This workstream's phases are complete. Other workstreams are still active:

| Workstream | Status | Phase | Progress |
|------------|--------|-------|----------|
| {name}     | {status} | {current_phase} | {completed_phases}/{phase_count} |
| ...        | ...    | ...   | ...      |

---

## Next Steps

Archive this workstream:

`/gsd:workstreams complete {current_ws_name} ${GSD_WS}`

See overall milestone progress:

`/gsd:workstreams progress ${GSD_WS}`

<sub>Milestone completion will be available once all workstreams finish.</sub>

---

Do NOT suggest /gsd:complete-milestone or /gsd:new-milestone. Do NOT auto-invoke any further slash commands.

Stop here. The user must explicitly decide what to do next.


Route B: All phases complete (milestone ready to close)

This route is only reached when:

  • is_last_phase: true AND no other active workstreams exist (or flat mode)

Clear auto-advance chain flag — milestone boundary is the natural stopping point:

gsd_run query config-set workflow._auto_chain_active false
Phase {X} marked complete.

🎉 Milestone {version} is 100% complete — all {N} phases finished!

⚡ Auto-continuing: Complete milestone and archive

Exit skill and invoke SlashCommand("/gsd:complete-milestone {version} ${GSD_WS}")

## ✓ Phase {X}: {Phase Name} Complete

🎉 Milestone {version} is 100% complete — all {N} phases finished!

---

## ▶ Next Up — [${PROJECT_CODE}] ${PROJECT_TITLE}

**Complete Milestone {version}** — archive and prepare for next

`/clear` then:

`/gsd:complete-milestone {version} ${GSD_WS}`

---

**Also available:**
- Review accomplishments before archiving

---

<implicit_tracking> Progress tracking is IMPLICIT: planning phase N implies phases 1-(N-1) complete. No separate progress step—forward motion IS progress. </implicit_tracking>

<partial_completion>

If user wants to move on but phase isn't fully complete:

Phase [X] has incomplete plans:
- {phase}-02-PLAN.md (not executed)
- {phase}-03-PLAN.md (not executed)

Options:
1. Mark complete anyway (plans weren't needed)
2. Defer work to later phase
3. Stay and finish current phase

Respect user judgment — they know if work matters.

If marking complete with incomplete plans:

  • Update ROADMAP: "2/3 plans complete" (not "3/3")
  • Note in transition message which plans were skipped

</partial_completion>

<success_criteria>

Transition is complete when:

  • Current phase plan summaries verified (all exist or user chose to skip)
  • Any stale handoffs deleted
  • ROADMAP.md updated with completion status and plan count
  • PROJECT.md evolved (requirements, decisions, description if needed)
  • STATE.md updated (position, project reference, context, session)
  • Progress table updated
  • User knows next steps

</success_criteria>