* docs(#3186): record the disk-strict completion decision in ADR-3180 7.4 The maintainer decided #2957 on 2026-08-08: disk state is authoritative and a ROADMAP checkbox is a human annotation with no machine authority. Section 7.4 still carried the OPEN QUESTION and was marked blocked, so the contract said one thing and the tracker another. Recorded per section 7's own rule - a behavior not stated there is not decided, and amending a rule is an ADR amendment rather than a code change with a comment. The decision comment names Phase 4's PR as the carrier of this edit and makes it an acceptance criterion that the text be in the tree before implementation begins, so this lands first, alone, ahead of any code. Also clears the stale blocked-on-2957 row in the guard roster. * refactor(#3186): one shared phase-completion predicate, disk-strict isPhaseComplete in verification.cts becomes the single owner. It calls readVerificationStatus UNCONDITIONALLY - plan count is not a precondition - so a zero-plan phase with a passing VERIFICATION.md is complete. That is #3168: init gated the read on a plan count and synthesized a not_required sentinel, so phase.complete succeeded while init.manager reported incomplete for the same phase. The guard, built and run before scope was fixed per Amendment 3, found 9 re-derivations where the ADR named 3. Four were unnamed, including one in the prompt layer: mvp-phase.md ORed a ticked checkbox with disk status, which under disk-strict is the divergence itself. Per the #2957 decision, a ticked ROADMAP checkbox is a human annotation with no machine authority. The overrides in roadmap analyze and init manager are deleted rather than generalized; the user's checkbox stays in ROADMAP.md, only its authority goes. scanPhasePlans.completed and buildWorkstreamInventory are deliberately NOT folded - they answer 'are all plans summarized', which is a different question, and folding them would either over-report completion or invert the dependency direction between Phase 1's owner and this one. Verified on the remote runner. * fix(#3186): close seven review findings and record the missing-verdict rule The isolated review reproduced a write-path regression I introduced: migrating cmdRoadmapUpdatePlanProgress dropped its summaryCount>=planCount gate, so a phase with a fresh passing verification plus a newly-added unsummarized plan reported complete AND wrote a checkbox into ROADMAP.md while phase complete refused. The owner stays right per 7.4 - plan count is not a completion precondition - so the gate is restored at the write site as an explicit composition, mirroring the separate 2648 unexecuted-plan gate cmdPhaseComplete already carries. The spec axis was right that my 0.x-split reasoning was too permissive. The 2957 decision names buildStateFrontmatter as one of the three that must converge, and buildWorkstreamInventory combined a summaries-met local with verification data to decide the same verdict - Decision 4(c)'s named bypass, and it reproduced 3168 in a third surface. Both now route through the owner. The raw scanPhasePlans helper stays: it answers are-plans-summarized, which genuinely is a different question. Maintainer decision recorded in 7.4: a missing verdict is not a passing one, so an absent VERIFICATION.md means not complete everywhere. That retires 2645's verifier-disabled tolerance and inverts its Goodhart incentive - deleting the evidence now lowers completion instead of raising it. Guard hardened: block-form count gates and algebraic restatements are caught, and the header now discloses its remaining limits instead of overclaiming. Verified on the remote runner. * fix(#3186): route state sync through the owner and catch bare completed reads The matrix found 52 failures. 51 were fixtures asserting the old semantics: a phase with plans and summaries but no VERIFICATION.md used to count complete and correctly no longer does. Each fixture now carries a passing verification where that is what the test was actually about, rather than having its assertion weakened. The 52nd was a real 10th re-derivation the guard could not see. cmdStateSync destructured scanPhasePlans().completed directly - a bare field read, not a comparison - and used it as a completion verdict, so state sync and state json disagreed on completed_phases for identical disk state. Routed through the owner. Guard gains shape (d): any read of .completed off a scanPhasePlans() result outside plan-scan.cts, in chained, destructured and indirect forms, function scoped with no line window. It cannot tell a summaries-met read from a completion read - that is data flow - so it flags every one and requires a written-reason exemption, which is the same discipline shapes a-c already use. The blind spot is disclosed in the header rather than overclaimed. The emitted-attribution failure was also mine, not pre-existing: the mvp-phase.md checkbox-OR removal moves emitted bytes, acknowledged in tests/emitted-drift-acks. Verified on the remote runner. * test(#3186): give the nested-plans sync fixture a passing verification Last 3 matrix failures were one failure echoing up two describe levels. Phase 01-alpha had plans and summaries but no VERIFICATION.md, so under disk-strict completed stayed 0 and no Progress change was emitted - correct new behavior, not a regression. Added the passing verification rather than dropping the Progress expectation, so the test still covers what #3257 is about: that a nested plans/ layout is counted and not undercounted. Probe against the built lib confirms Progress: 0% -> 50% alongside Total Plans in Phase: 0 -> 3. * chore(#3186): backfill changeset PR number pr:0 placeholder replaced with the real number now that #3306 exists. --------- Co-authored-by: sim <sim@local>
14 KiB
<required_reading>
@/.claude/gsd-core/references/user-story-template.md
@/.claude/gsd-core/references/spidr-splitting.md
@~/.claude/gsd-core/references/planner-mvp-mode.md
</required_reading>
<runtime_note>
Copilot (VS Code): Use vscode_askquestions wherever this workflow calls AskUserQuestion. They are equivalent.
TEXT_MODE fallback: Set TEXT_MODE=true if --text is present in $ARGUMENTS OR text_mode from init JSON is true. When TEXT_MODE is active, replace every AskUserQuestion call with a plain-text numbered list and ask the user to type their choice number.
</runtime_note>
1. Parse and validate phase argument
Extract the phase number from $ARGUMENTS (integer or decimal like 2.1). Optional flag: --force (allow operating on in_progress / completed phases).
If no argument:
ERROR: Phase number required
Usage: /gsd mvp-phase <phase-number>
Example: /gsd mvp-phase 1
Example: /gsd mvp-phase 2.1
Exit.
Normalize per @~/.claude/gsd-core/references/phase-argument-parsing.md (zero-pad integer phases to two digits).
2. Validate phase exists and check status
_GSD_SHIM_NAME="gsd-tools.cjs"; _GSD_RUNTIME_ROOT="${RUNTIME_DIR:-$(git rev-parse --show-toplevel 2>/dev/null || pwd)}"; GSD_TOOLS="${_GSD_RUNTIME_ROOT}/gsd-core/bin/${_GSD_SHIM_NAME}"; if [ -f "$GSD_TOOLS" ]; then gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${_GSD_RUNTIME_ROOT}/.claude/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${_GSD_RUNTIME_ROOT}/.claude/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${_GSD_RUNTIME_ROOT}/.codex/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${_GSD_RUNTIME_ROOT}/.codex/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif command -v gsd-tools >/dev/null 2>&1; then GSD_TOOLS="$(command -v gsd-tools)"; gsd_run() { "$GSD_TOOLS" "$@"; }; elif [ -f "${CLAUDE_CONFIG_DIR:-$HOME/.claude}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${CLAUDE_CONFIG_DIR:-$HOME/.claude}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${HERMES_HOME:-$HOME/.hermes}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${HERMES_HOME:-$HOME/.hermes}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${CURSOR_CONFIG_DIR:-$HOME/.cursor}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${CURSOR_CONFIG_DIR:-$HOME/.cursor}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${CODEX_HOME:-$HOME/.codex}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${CODEX_HOME:-$HOME/.codex}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${GEMINI_CONFIG_DIR:-$HOME/.gemini}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${GEMINI_CONFIG_DIR:-$HOME/.gemini}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${COPILOT_CONFIG_DIR:-$HOME/.copilot}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${COPILOT_CONFIG_DIR:-$HOME/.copilot}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${WINDSURF_CONFIG_DIR:-$HOME/.codeium/windsurf}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${WINDSURF_CONFIG_DIR:-$HOME/.codeium/windsurf}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${AUGMENT_CONFIG_DIR:-$HOME/.augment}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${AUGMENT_CONFIG_DIR:-$HOME/.augment}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${TRAE_CONFIG_DIR:-$HOME/.trae}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${TRAE_CONFIG_DIR:-$HOME/.trae}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${QWEN_CONFIG_DIR:-$HOME/.qwen}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${QWEN_CONFIG_DIR:-$HOME/.qwen}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${CODEBUDDY_CONFIG_DIR:-$HOME/.codebuddy}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${CODEBUDDY_CONFIG_DIR:-$HOME/.codebuddy}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${CLINE_CONFIG_DIR:-$HOME/.cline}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${CLINE_CONFIG_DIR:-$HOME/.cline}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${GROK_AGENTS_HOME:-$HOME/.agents}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${GROK_AGENTS_HOME:-$HOME/.agents}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${ANTIGRAVITY_CONFIG_DIR:-$HOME/.gemini/antigravity}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${ANTIGRAVITY_CONFIG_DIR:-$HOME/.gemini/antigravity}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${OPENCODE_CONFIG_DIR:-${XDG_CONFIG_HOME:-$HOME/.config}/opencode}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${OPENCODE_CONFIG_DIR:-${XDG_CONFIG_HOME:-$HOME/.config}/opencode}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${KILO_CONFIG_DIR:-${XDG_CONFIG_HOME:-$HOME/.config}/kilo}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${KILO_CONFIG_DIR:-${XDG_CONFIG_HOME:-$HOME/.config}/kilo}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; else echo "ERROR: gsd-tools.cjs not found at $GSD_TOOLS and gsd-tools is not on PATH. Run: npx -y @opengsd/gsd-core@latest --claude --local" >&2; exit 1; fi; if [ -n "${CLAUDE_ENV_FILE:-}" ] && [ -n "${GSD_TOOLS:-}" ]; then printf "export PATH='%s':\"\$PATH\"\n" "${GSD_TOOLS%/*}" >> "$CLAUDE_ENV_FILE" 2>/dev/null || true; fi
RESPONSE_LANGUAGE=$(gsd_run query config-get response_language --default "" 2>/dev/null || echo "")
PHASE_INFO=$(gsd_run query roadmap.get-phase "${PHASE}")
PHASE_FOUND=$(echo "$PHASE_INFO" | jq -r '.found')
PHASE_NAME=$(echo "$PHASE_INFO" | jq -r '.phase_name')
PHASE_GOAL=$(echo "$PHASE_INFO" | jq -r '.goal')
PHASE_MODE=$(echo "$PHASE_INFO" | jq -r '.mode // ""')
ANALYZE=$(gsd_run query roadmap.analyze)
if [[ "$ANALYZE" == @file:* ]]; then ANALYZE=$(cat "${ANALYZE#@file:}"); fi
DISK_STATUS=$(echo "$ANALYZE" | jq -r --arg p "$PHASE" '.phases[] | select((.phase_number|tostring)==$p) | .disk_status' | head -1)
# ADR-3180 §7.4 (issue #3186, disk-strict, #2957): DISK_STATUS alone decides
# completion — a ROADMAP checkbox carries no machine authority and is never
# ORed in here. `roadmap.analyze`'s `disk_status` already routes through the
# canonical owner (`isPhaseComplete`), so this is the same predicate the read
# and write paths both use.
if [[ "$DISK_STATUS" == "complete" ]]; then
STATUS="completed"
elif [[ "$DISK_STATUS" == "planned" || "$DISK_STATUS" == "partial" ]]; then
STATUS="in_progress"
else
STATUS="not_started"
fi
If response_language is set: All user-facing questions, prompts, and explanations in this workflow MUST be presented in {response_language}. Technical terms, code, file paths, and subagent prompts stay in English — only user-facing output is translated.
If PHASE_FOUND is false: error and exit. Suggest /gsd add-phase or /gsd insert-phase to create the phase first.
Status guard. If the phase is in_progress (has plans but not complete) or completed, refuse unless --force is in $ARGUMENTS:
ERROR: Phase ${PHASE} is currently ${STATUS}.
Converting an active or completed phase to MVP mode mid-flight will
invalidate any existing plans and summaries.
To proceed anyway: /gsd mvp-phase ${PHASE} --force
Already-MVP guard. If PHASE_MODE is already mvp, surface this and ask whether to re-prompt the user story or abort:
"Phase ${PHASE} is already in MVP mode with goal: «${PHASE_GOAL}». Re-run user-story prompts and SPIDR check?"
Use AskUserQuestion with options [Re-prompt / Abort]. On Abort, exit cleanly. On Re-prompt, proceed.
3. User story prompts
Run three sequential AskUserQuestion calls. Each is free-text. After all three, assemble into the canonical sentence per @~/.claude/gsd-core/references/user-story-template.md:
Prompt 1 — As a:
"As a [user role]?" (Examples: "new user", "admin", "signed-in customer", "API consumer")
Prompt 2 — I want to:
"I want to [capability]?" (Examples: "register and log in", "upload a CSV", "see my dashboard")
Prompt 3 — So that:
"So that [outcome]?" (Examples: "I can access my account", "I can bulk-import contacts", "I can see at a glance what needs attention")
Assemble:
USER_STORY="As a ${ROLE}, I want to ${CAPABILITY}, so that ${OUTCOME}."
If any of the three answers is empty or whitespace-only, error and re-prompt that single field. Do NOT proceed with a partial story.
Validate via the centralized User Story validator. The verb owns the canonical regex /^As a .+, I want to .+, so that .+\.$/ and surfaces per-error guidance:
USER_STORY_RESULT=$(gsd_run query user-story.validate --story "$USER_STORY")
if [ "$(echo "$USER_STORY_RESULT" | jq -r '.valid')" != "true" ]; then
echo "$USER_STORY_RESULT" | jq -r '.errors[]' >&2
# Re-prompt the offending field(s) per surfaced errors, then re-run validation.
# Do not abort the workflow on first invalid draft.
RE_PROMPT_USER_STORY=true
fi
This guarantees the goal stored in ROADMAP.md will satisfy the same guard the verifier applies later.
If RE_PROMPT_USER_STORY=true, re-run only the offending prompt field(s), rebuild USER_STORY, and validate again before continuing.
4. SPIDR splitting check
Run the SPIDR rules from @~/.claude/gsd-core/references/spidr-splitting.md. Briefly:
Trigger evaluation. Check the assembled USER_STORY against the four size signals from the reference (compound capabilities, multi-actor, length > 120 chars, vague capability). If none fire, skip SPIDR entirely — go to step 5.
If SPIDR triggers.
a) Restate the story to the user:
"Your story: «${USER_STORY}»
This story has [signal description, e.g., 'two compound capabilities joined by and']. Splitting it into multiple phases will produce a cleaner Walking Skeleton and reduce the risk of mid-phase scope creep.
Want to walk through SPIDR splitting?"
Use AskUserQuestion with options [Yes, walk through SPIDR / No, proceed with the story as-is].
If "No": skip SPIDR, go to step 5.
If "Yes": continue to (b).
b) Ask which SPIDR axis fits best:
"Which axis best fits how to split this story?"
Use AskUserQuestion with the five options from spidr-splitting.md (Spike / Paths / Interfaces / Data / Rules). Each option includes its targeted question as the description so the user can pick by understanding what each axis means.
c) Walk through the chosen axis with one targeted question (not all five). For example, if the user picked "Paths":
"Does this feature have a happy path and one or more error/edge paths?"
Free-text response. Workflow parses to identify the split.
d) Produce a split proposal. Example:
"Proposed split (Paths axis):
- Phase ${PHASE} (this one): Happy path — ${HAPPY_STORY}
- Phase ${PHASE+1} (new): Edge case — ${EDGE_STORY}
Accept this split?"
Use AskUserQuestion [Accept / Modify / Reject].
- Accept:
USER_STORYbecomes the first split's story (${HAPPY_STORY}in the example). Surface the remaining splits as a list of/gsd add-phaseinvocations the user can run after this command completes — do NOT auto-create the new phases (preserve user control over numbering). - Modify: re-prompt the splits one more time, then accept or reject.
- Reject: revert
USER_STORYto the original, proceed without splitting.
5. Update ROADMAP.md
Read ROADMAP.md. Find the section for Phase ${PHASE}. Apply two edits:
Edit 1 — Update Goal line.
Find: **Goal:** ${OLD_GOAL_TEXT}
Replace with: **Goal:** ${USER_STORY}
Edit 2 — Insert Mode line.
If **Mode:** already exists in the section (replacing or re-running), update it to **Mode:** mvp.
If **Mode:** does not exist, insert **Mode:** mvp on the line immediately after **Goal:**.
Show the user a unified diff (lines being changed) and ask:
"Apply these changes to ROADMAP.md?"
Use AskUserQuestion [Apply / Cancel]. On Cancel, exit without writing.
On Apply, write the updated ROADMAP.md atomically (read-edit-write).
6. Verify the write
NEW_MODE=$(gsd_run query roadmap.get-phase "${PHASE}" --pick mode)
NEW_GOAL=$(gsd_run query roadmap.get-phase "${PHASE}" --pick goal)
Assert:
NEW_MODEequalsmvpNEW_GOALequals the assembled user story
If either assertion fails, surface the discrepancy to the user and exit. Do not proceed to plan-phase delegation with a half-applied write.
7. Delegate to /gsd plan-phase
Invoke /gsd plan-phase ${PHASE} (no flags). Phase 1's MVP_MODE resolution chain (CLI flag → roadmap mode → config → false) will detect the new **Mode:** mvp line and run plan-phase in vertical-slice mode automatically.
The Walking Skeleton gate (also from Phase 1) will fire automatically if ${PHASE} == "01" and there are zero prior phase summaries.
8. Surface deferred phase splits (if any)
If SPIDR produced a split in step 4, append a final user-facing message:
"SPIDR split deferred phases.
Your original story was split. The first slice is now planned via plan-phase. To create the remaining slice(s) as new phases, run:
/gsd add-phase— for the next slice: «${SPLIT_2_STORY}»/gsd add-phase— for the next slice: «${SPLIT_3_STORY}»Each will be added to the end of the current milestone. You can then run
/gsd mvp-phase <new-phase-number>on each to plan them as MVP slices."
9. Exit
Workflow ends. The phase is now in MVP mode with a planned PLAN.md, optionally with deferred follow-up phases surfaced for the user.