* feat(#3841): assert gsd-tools identity before any state-mutating verb only this package publishes. The path-based branches — a project-local install, a runtime config directory — had no such guarantee; they trusted their configured location. This closes them. Mechanism: once resolution finishes, and before any verb runs, the preamble probes the tool it picked with `runtime-identity --raw` and matches the answer with a shell `case` pattern ANCHORED to the start of the compact payload (`{"packageName":"@opengsd/gsd-core"`). An unanchored substring match accepts the decoy `{"packageName":"get-shit-done-cc","note":"@opengsd/gsd-core"}`, which any colliding package could publish. The outcome is exported as the two-valued `GSD_IDENTITY_STATUS` (`ok`/`unverified`), so the gate is asserted on a VALUE rather than on warning prose. Rollout is warn-then-fail per the #3146 ruling: `unverified` prints one line naming BOTH causes and continues, because `no_identity_verb` cannot tell a foreign package from an `@opengsd/gsd-core` older than the verb, and at rollout the old-version case is the common one. The blocker was byte budget, not design. The preamble is inlined into 112 shipped files and several sat within single-digit bytes of frozen ceilings (`gsd-verifier.md` 16 bytes, `gsd-executor.md` 33, `execute-phase.md` 234); a first attempt broke five of them. What made room was collapsing the resolver's twenty near-identical `elif [ -f … ]` arms into one candidate-list helper (`_gsd_at`), which buys far more than the assertion costs. The preamble is now 2,624 bytes against 4,500 — a net 1,876 bytes SMALLER per inlined file, so every capped file moved away from its ceiling rather than toward it. No cap raised, no size-budget exception added, no override token emitted. Resolution order, every runtime-home probe, the `unset -f gsd_run` re-source fix, the fail-closed `exit 1`, and the `CLAUDE_ENV_FILE` persistence are all preserved byte-for-byte in substring terms; the snippet still begins with `_GSD_SHIM_NAME=` and still ends with `fi`, which the parity extractors anchor on. `gsd-core/references/gsd-run-resolver.md` is re-synced byte-equal. Also fixes two stale claims found in passing: CONTEXT.md and FEATURES.md both described an `[ -x ]` guard as the load-bearing re-source defense. That guard was tried and REMOVED in #3831 — it rejected the bare function name, fell through every branch, and hit `exit 1`, which kills a sourced caller's shell. `unset -f gsd_run` is the actual mechanism. Refs #3841 Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> * fix(#3841): pair the anchor's brace by requiring a closed identity payload The matrix went red on `tests/new-project-mvp-prompt.test.cjs` — "new-project.md has unbalanced braces: net depth 2" — plus a knock-on report from its parent `bug #1516` describe, which is the same failure counted once at the child and once at the block. Root cause: that guard (:182-189, mirroring #3784 bd53925f) walks characters and increments on `{`, decrements on `}`, with no awareness of shell quoting. It scans `new-project.md` PLUS every `new-project/steps/*.md`, and both `new-project.md` and `steps/auto-mode-config.md` carry one inlined preamble copy — hence net 2 from a snippet that was off by exactly one. The unpaired brace was the `{` inside the single-quoted `case` pattern of the identity anchor, which is correct shell and invisible to a text scanner. Fix in the snippet, not the guard. The pattern now anchors at BOTH ends: `'{"packageName":"@opengsd/gsd-core"'*'}'`. That balances 51/51 with a brace that does real work rather than a cosmetic pair — a truncated payload whose prefix matches now fails too, where before it verified. Safe for any future additive field: a JSON object's own closing brace is always the last character, whatever type the last value has, which is pinned by two negative-space tests (a nested object and an array-valued last key must both still verify). Cost: +3 bytes, against the 1,873 the resolver fold already gave back. The alternative considered and rejected was dropping the literal `{` for a `?` glob. It balances too, but weakens the anchor from "must be an opening brace" to "must be any one character", and the anchor is the entire point. Two guards added so this cannot recur silently: - runtime-launcher-parity (F0) pins brace balance at the SNIPPET, so the next edit to that pattern fails on the file it broke instead of surfacing three files downstream in a test whose name mentions neither the launcher nor this issue. It also asserts depth never goes negative, since a `}` preceding its `{` nets to zero while being unbalanced at every prefix. - runtime-identity gains behavioral truncated-payload and trailing-garbage fixtures, so the added `}` is proven load-bearing rather than merely present. Verified: snippet 51/51 braces; new-project combined net depth 0; the seven other preamble-bearing files with nonzero depth are unchanged from merged next (their own prose, not the preamble, and not in any guard's scan set); all 112 inlined copies and the resolver reference re-synced byte-equal; sync:launcher idempotent on the second run. Refs #3841 Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> * chore(#3841): backfill changeset PR number Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> --------- Co-authored-by: sim <sim@local> Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
16 KiB
<required_reading> Read all files referenced by the invoking prompt's execution_context before starting. </required_reading>
<available_agent_types> Valid GSD subagent types (use exact names — do not fall back to 'general-purpose'):
- gsd-integration-checker — Checks cross-phase integration </available_agent_types>
0. Initialize Milestone Context
_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}"; _gsd_at() { for _p; do if [ -f "$_p" ]; then GSD_TOOLS="$_p"; return 0; fi; done; return 1; }; if _gsd_at "${_GSD_RUNTIME_ROOT}/gsd-core/bin/${_GSD_SHIM_NAME}" "${_GSD_RUNTIME_ROOT}/.claude/gsd-core/bin/${_GSD_SHIM_NAME}" "${_GSD_RUNTIME_ROOT}/.codex/gsd-core/bin/${_GSD_SHIM_NAME}"; then gsd_run() { node "$GSD_TOOLS" "$@"; }; elif unset -f gsd_run; _G="$(command -v gsd_run)"; then GSD_TOOLS="$_G"; gsd_run() { "$GSD_TOOLS" "$@"; }; elif _gsd_at "${CLAUDE_CONFIG_DIR:-$HOME/.claude}/gsd-core/bin/${_GSD_SHIM_NAME}" "${HERMES_HOME:-$HOME/.hermes}/gsd-core/bin/${_GSD_SHIM_NAME}" "${CURSOR_CONFIG_DIR:-$HOME/.cursor}/gsd-core/bin/${_GSD_SHIM_NAME}" "${CODEX_HOME:-$HOME/.codex}/gsd-core/bin/${_GSD_SHIM_NAME}" "${GEMINI_CONFIG_DIR:-$HOME/.gemini}/gsd-core/bin/${_GSD_SHIM_NAME}" "${COPILOT_CONFIG_DIR:-$HOME/.copilot}/gsd-core/bin/${_GSD_SHIM_NAME}" "${WINDSURF_CONFIG_DIR:-$HOME/.codeium/windsurf}/gsd-core/bin/${_GSD_SHIM_NAME}" "${AUGMENT_CONFIG_DIR:-$HOME/.augment}/gsd-core/bin/${_GSD_SHIM_NAME}" "${TRAE_CONFIG_DIR:-$HOME/.trae}/gsd-core/bin/${_GSD_SHIM_NAME}" "${QWEN_CONFIG_DIR:-$HOME/.qwen}/gsd-core/bin/${_GSD_SHIM_NAME}" "${CODEBUDDY_CONFIG_DIR:-$HOME/.codebuddy}/gsd-core/bin/${_GSD_SHIM_NAME}" "${CLINE_CONFIG_DIR:-$HOME/.cline}/gsd-core/bin/${_GSD_SHIM_NAME}" "${GROK_AGENTS_HOME:-$HOME/.agents}/gsd-core/bin/${_GSD_SHIM_NAME}" "${ANTIGRAVITY_CONFIG_DIR:-$HOME/.gemini/antigravity}/gsd-core/bin/${_GSD_SHIM_NAME}" "${OPENCODE_CONFIG_DIR:-${XDG_CONFIG_HOME:-$HOME/.config}/opencode}/gsd-core/bin/${_GSD_SHIM_NAME}" "${KILO_CONFIG_DIR:-${XDG_CONFIG_HOME:-$HOME/.config}/kilo}/gsd-core/bin/${_GSD_SHIM_NAME}"; then gsd_run() { node "$GSD_TOOLS" "$@"; }; else echo "ERROR: gsd-tools.cjs not found at $GSD_TOOLS and gsd_run is not on PATH. Run: npx -y @opengsd/gsd-core@latest --claude --local" >&2; exit 1; fi; GSD_IDENTITY_STATUS=unverified; case "$(gsd_run runtime-identity --raw 2>/dev/null || true)" in '{"packageName":"@opengsd/gsd-core"'*'}') GSD_IDENTITY_STATUS=ok;; esac; export GSD_IDENTITY_STATUS; [ "$GSD_IDENTITY_STATUS" = ok ] || echo "WARNING: \"$GSD_TOOLS\" did not prove it is @opengsd/gsd-core - it is either a different package or an @opengsd/gsd-core older than the runtime-identity verb. See docs/how-to/diagnose-a-foreign-gsd-tools.md" >&2; 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
INIT=$(gsd_run query init.milestone-op)
if [[ "$INIT" == @file:* ]]; then INIT=$(cat "${INIT#@file:}"); fi
AGENT_SKILLS_CHECKER=$(gsd_run query agent-skills gsd-integration-checker)
Extract from init JSON: milestone_version, milestone_name, phase_count, completed_phases, commit_docs.
Resolve integration checker model:
integration_checker_model=$(gsd_run query resolve-model gsd-integration-checker --raw)
1. Determine Milestone Scope
# Get phases in milestone (sorted numerically, handles decimals)
gsd_run query phases.list
- Parse version from arguments or detect current from ROADMAP.md
- Identify all phase directories in scope
- Extract milestone definition of done from ROADMAP.md
- Extract requirements mapped to this milestone from REQUIREMENTS.md
2. Read All Phase Verifications
For each phase directory, read the VERIFICATION.md:
# For each phase, use find-phase to resolve the directory (handles archived phases)
PHASE_INFO=$(gsd_run query find-phase 01 --raw)
# Extract directory from JSON, then read VERIFICATION.md from that directory
# Repeat for each phase number from ROADMAP.md
From each VERIFICATION.md, extract:
- Status: passed | gaps_found
- Critical gaps: (if any — these are blockers)
- Non-critical gaps: tech debt, deferred items, warnings
- Anti-patterns found: TODOs, stubs, placeholders
- Requirements coverage: which requirements satisfied/blocked
If a phase is missing VERIFICATION.md, flag it as "unverified phase" — this is a blocker.
3. Spawn Integration Checker
With phase context collected:
Extract MILESTONE_REQ_IDS from REQUIREMENTS.md traceability table — all REQ-IDs assigned to phases in this milestone.
Print: "Spawning integration checker (runs in a subagent — no output until it returns, ~1–5 min; expected, not a freeze)"
Model omission (#2517). Omit the
modelparameter entirely when the value it would carry (integration_checker_model) is"inherit"or empty. An empty value 404s on runtimes without native tier aliases — the default on non-Claude runtimes. Omitting it inherits the orchestrator's model. See @gsd-core/references/model-profile-resolution.md.
Agent(
prompt="Check cross-phase integration and E2E flows.
Phases: {phase_dirs}
Phase exports: {from SUMMARYs}
API routes: {routes created}
Milestone Requirements:
{MILESTONE_REQ_IDS — list each REQ-ID with description and assigned phase}
MUST map each integration finding to affected requirement IDs where applicable.
<!-- #2508 runtime-aware-dispatch -->
> **Runtime-aware dispatch (#2508 Phase 4).** GSD workflows dispatch specialized subagents by role. Before dispatching on a built-in-only runtime (kimi-code — three built-ins only), resolve the role to a built-in via `gsd_run query resolve-dispatch-type --requested <role> --raw`. On named-dispatch runtimes (Claude/OpenCode/…) the role is returned unchanged; on kimi-code it maps to `coder`/`explore`/`plan` by role-suffix. The persona rides `${AGENT_SKILLS_<ROLE>}` (Phase 3) regardless. See @gsd-core/references/runtime-aware-dispatch.md.
Verify cross-phase wiring and E2E user flows.
${AGENT_SKILLS_CHECKER}",
subagent_type="gsd-integration-checker",
model="{integration_checker_model}"
)
ORCHESTRATOR RULE — CODEX RUNTIME: After calling Agent() above, stop working on this task immediately. Do not read more files, edit code, or run tests related to this task while the subagent is active. Wait for the subagent to return its result. This prevents duplicate work, conflicting edits, and wasted context. Only resume when the subagent result is available.
4. Collect Results
Combine:
- Phase-level gaps and tech debt (from step 2)
- Integration checker's report (wiring gaps, broken flows)
5. Check Requirements Coverage (3-Source Cross-Reference)
MUST cross-reference three independent sources for each requirement:
5a. Parse REQUIREMENTS.md Traceability Table
Extract all REQ-IDs mapped to milestone phases from the traceability table:
- Requirement ID, description, assigned phase, current status, checked-off state (
[x]vs[ ])
5b. Parse Phase VERIFICATION.md Requirements Tables
For each phase's VERIFICATION.md, extract the expanded requirements table:
- Requirement | Source Plan | Description | Status | Evidence
- Map each entry back to its REQ-ID
5c. Extract SUMMARY.md Frontmatter Cross-Check
For each phase's SUMMARY.md, extract requirements-completed from YAML frontmatter:
# #2962: zsh aborts the block on an unmatched for-list glob (nomatch); bash passes it through. nullglob both.
shopt -s nullglob 2>/dev/null; setopt NULL_GLOB 2>/dev/null
for summary in .planning/phases/*-*/*-SUMMARY.md; do
[ -e "$summary" ] || continue
gsd_run query summary-extract "$summary" --fields requirements_completed --pick requirements_completed
done
5d. Status Determination Matrix
For each REQ-ID, determine status using all three sources:
| VERIFICATION.md Status | SUMMARY Frontmatter | REQUIREMENTS.md | → Final Status |
|---|---|---|---|
| passed | listed | [x] |
satisfied |
| passed | listed | [ ] |
satisfied (update checkbox) |
| passed | missing | any | partial (verify manually) |
| gaps_found | any | any | unsatisfied |
| missing | listed | any | partial (verification gap) |
| missing | missing | any | unsatisfied |
5e. FAIL Gate and Orphan Detection
REQUIRED: Any unsatisfied requirement MUST force gaps_found status on the milestone audit.
Orphan detection: Requirements present in REQUIREMENTS.md traceability table but absent from ALL phase VERIFICATION.md files MUST be flagged as orphaned. Orphaned requirements are treated as unsatisfied — they were assigned but never verified by any phase.
5.5. Nyquist Compliance Discovery
Skip if the Nyquist capability is inactive.
VERIFY_POST_HOOKS_JSON=$(gsd_run loop render-hooks verify:post --raw)
Resolve active step hooks from VERIFY_POST_HOOKS_JSON where kind == "step" and ref.skill == "validate-phase".
If no active validate-phase step hook exists: skip entirely.
For each phase directory, check *-VALIDATION.md. If exists, parse frontmatter (status, nyquist_compliant, wave_0_complete).
Classify per phase:
| Status | Condition |
|---|---|
| COMPLIANT | status: validated and nyquist_compliant: true and all tasks green |
| PARTIAL | status: validated and (nyquist_compliant: false or red/pending) |
| NOT-VALIDATED | status: draft (or absent) — validate-phase has not yet reconciled this file (#2117) |
| MISSING | No VALIDATION.md |
NOT-VALIDATED vs PARTIAL (#2117): A phase reads
status: draftwhen it was seeded by plan-phase but never reconciled by validate-phase, OR when itsVALIDATION.mdpredates thestatusfield (files written before #2117 staydraftwhether or not validation ran). In both casesnyquist_compliantis not authoritative, so this is a coverage TODO ("run validate-phase") — not a compliance failure. Re-running validate-phase promotes the file tostatus: validatedand yields the real COMPLIANT/PARTIAL verdict. Onlystatus: validated+nyquist_compliant: falseis a genuine PARTIAL.
Add to audit YAML: nyquist: { compliant_phases, partial_phases, not_validated_phases, missing_phases, overall }
Discovery only — never auto-calls /gsd:validate-phase.
6. Aggregate into v{version}-MILESTONE-AUDIT.md
Create .planning/v{version}-v{version}-MILESTONE-AUDIT.md with:
---
milestone: {version}
audited: {timestamp}
status: passed | gaps_found | tech_debt
scores:
requirements: N/M
phases: N/M
integration: N/M
flows: N/M
gaps: # Critical blockers
requirements:
- id: "{REQ-ID}"
status: "unsatisfied | partial | orphaned"
phase: "{assigned phase}"
claimed_by_plans: ["{plan files that reference this requirement}"]
completed_by_plans: ["{plan files whose SUMMARY marks it complete}"]
verification_status: "passed | gaps_found | missing | orphaned"
evidence: "{specific evidence or lack thereof}"
integration: [...]
flows: [...]
tech_debt: # Non-critical, deferred
- phase: 01-auth
items:
- "TODO: add rate limiting"
- "Warning: no password strength validation"
- phase: 03-dashboard
items:
- "Deferred: mobile responsive layout"
---
Plus full markdown report with tables for requirements, phases, integration, tech debt.
Status values:
passed— all requirements met, no critical gaps, minimal tech debtgaps_found— critical blockers existtech_debt— no blockers but accumulated deferred items need review
7. Present Results
Route by status (see <offer_next>).
<offer_next> Output this markdown directly (not as a code block). Route based on status:
If passed:
✓ Milestone {version} — Audit Passed
Score: {N}/{M} requirements satisfied Report: .planning/v{version}-MILESTONE-AUDIT.md
All requirements covered. Cross-phase integration verified. E2E flows complete.
▶ Next Up — [${PROJECT_CODE}] ${PROJECT_TITLE}
Complete milestone — archive and tag
/clear then:
/gsd:complete-milestone {version}
If gaps_found:
⚠ Milestone {version} — Gaps Found
Score: {N}/{M} requirements satisfied Report: .planning/v{version}-MILESTONE-AUDIT.md
Unsatisfied Requirements
{For each unsatisfied requirement:}
- {REQ-ID}: {description} (Phase {X})
- {reason}
Cross-Phase Issues
{For each integration gap:}
- {from} → {to}: {issue}
Broken Flows
{For each flow gap:}
- {flow name}: breaks at {step}
Nyquist Coverage
| Phase | VALIDATION.md | Compliant | Action |
|---|---|---|---|
| {phase} | exists/missing | true/false/partial | /gsd:validate-phase {N} |
Phases needing validation: run /gsd:validate-phase {N} for each flagged phase.
▶ Next Up — [${PROJECT_CODE}] ${PROJECT_TITLE}
Close the gaps inline — gap planning happens as part of this audit's output (see the Unsatisfied Requirements, Cross-Phase Issues, Broken Flows, and Nyquist Coverage sections above). Insert one closure phase per gap (or per group of related gaps) using the standard phase chain:
/clear then:
/gsd:phase --insert "Close gap: — " /gsd:discuss-phase /gsd:plan-phase /gsd:execute-phase
For Nyquist-coverage gaps flagged in the table above, prefer running
/gsd:validate-phase <N> for each flagged phase (and /gsd:secure-phase <N> if SECURITY.md was flagged) before inserting a new closure phase —
they may close the gap retroactively without a new phase.
Also available:
- cat .planning/v{version}-MILESTONE-AUDIT.md — see full report
- /gsd:complete-milestone {version} — proceed anyway (accept tech debt)
If tech_debt (no blockers but accumulated debt):
⚡ Milestone {version} — Tech Debt Review
Score: {N}/{M} requirements satisfied Report: .planning/v{version}-MILESTONE-AUDIT.md
All requirements met. No critical blockers. Accumulated tech debt needs review.
Tech Debt by Phase
{For each phase with debt:} Phase {X}: {name}
- {item 1}
- {item 2}
Total: {N} items across {M} phases
▶ Options
A. Complete milestone — accept debt, track in backlog
/gsd:complete-milestone {version}
B. Plan a cleanup phase — address the debt above before completing. Insert a closure phase using the standard chain:
/clear then:
/gsd:phase --insert "Address tech debt: " /gsd:discuss-phase /gsd:plan-phase /gsd:execute-phase
</offer_next>
<success_criteria>
- Milestone scope identified
- All phase VERIFICATION.md files read
- SUMMARY.md
requirements-completedfrontmatter extracted for each phase - REQUIREMENTS.md traceability table parsed for all milestone REQ-IDs
- 3-source cross-reference completed (VERIFICATION + SUMMARY + traceability)
- Orphaned requirements detected (in traceability but absent from all VERIFICATIONs)
- Tech debt and deferred gaps aggregated
- Integration checker spawned with milestone requirement IDs
- v{version}-MILESTONE-AUDIT.md created with structured requirement gap objects
- FAIL gate enforced — any unsatisfied requirement forces gaps_found status
- Nyquist compliance scanned for all milestone phases (if enabled)
- Missing VALIDATION.md phases flagged with validate-phase suggestion
- Results presented with actionable next steps </success_criteria>