voidforge-build 23.15.0 → 23.16.0

package/dist/CHANGELOG.md

@@ -6,6 +6,34 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/), and this
 
 ---
 
+## [23.16.0] - 2026-06-13
+
+### Platform-alignment campaign — ADR-064/065/066 implemented (+ ADR-050/051/054 amended)
+
+Built the ADR set designed in the `/architect --plan` review (→ `/campaign`). Dependency-ordered: the gate↔Workflow fix is the P0 precondition for any future Workflow re-platforming.
+
+### Added
+
+- **`docs/NATIVE_CAPABILITIES.md` (ADR-066)** — the native-capability collision tracker ADR-050 deferred and never created. Audits every `.claude/commands/*.md` against the mid-2026 native skill set with a recorded disposition each: `/engage`/`/sentinel` (rename+alias, done in ADR-050), `/qa` + `/test` (**coexist + document** — project-local CLI resolution wins; web/IDE users invoke the gated flow explicitly; rename deferred as too disruptive), `/git` (**keep** — native `/commit` is narrower than Coulson's release management), all others **keep**. Re-audit gate added to the release checklist.
+- **ADR-064 / ADR-065 / ADR-066** decision records; `docs/COMPATIBILITY.md` Claude Code platform-floor + per-feature maturity table (ADR-065).
+
+### Changed
+
+- **Silver Surfer gate now covers the Workflow tool (ADR-064).** `.claude/settings.json` matcher `"Agent"` → `"Agent|Workflow"`; `scripts/surfer-gate/check.sh` gates a Workflow launch on a recorded roster (Workflow `tool_input` has no `subagent_type`, so the Surfer-self rule simply doesn't match it). `scripts/surfer-gate/test.sh` gains 3 Workflow cases (no-roster→block, roster→allow, bypass→allow) — suite **23/23**; mirrored to `packages/methodology/scripts/surfer-gate/`. **Behavior change:** a Workflow run now requires a recorded roster or a `--light`/`--solo` bypass — closes the empirically-proven bypass (this session: 60+ workflow agents → 0 gate events). CLAUDE.md gate section updated.
+- **`packages/methodology/package.json`** — informational `claudeCodeFloor` field (ADR-065; not npm-enforced; conservative baseline pending operator confirmation).
+- **Amended ADRs:** ADR-051 (documents the Agent-tool-scoping limitation + ADR-064 closure), ADR-054 (effort tiers + Haiku 4.5 200K/no-`effort` constraints), ADR-050 (status → Accepted; tracker realized).
+
+### Deferred
+
+- **ADR-054 effort fleet edit** (264-agent frontmatter `effort:`) — the *policy* shipped in v23.15.0 (SUB_AGENTS.md + flag mapping); the fleet edit waits on runtime verification that agent-frontmatter `effort:` is honored (ADR-054 precondition), to avoid breaking agent loading with an unverified key.
+- **`/gauntlet` / `/assemble` Workflow re-platforming** — the opportunity ADR-064 *unblocks*, but a larger build than this ADR set; flagged for a future campaign.
+
+### Pipeline
+
+Dogfooded pre-tag `npm test` + the publish-gate alignment. The gate fix is itself dogfooded — the Fixture-Bindability test (`Workflow launch, no roster → exit 2`) returned `exit 0` before the change and `exit 2` after. Dep range `^23.15.0` → `^23.16.0` (ADR-062).
+
+---
+
 ## [23.15.0] - 2026-06-13
 
 ### Platform alignment — gate↔Workflow (ADR-064) + model-ID/effort/concurrency currency

package/dist/CLAUDE.md

@@ -31,7 +31,7 @@ ADR-051 enforces this gate at the hook level (PreToolUse). The prose below is th
 
 **Scope of override.** This procedural rule overrides your workflow judgment only — specifically, the judgment that launching the Silver Surfer is unnecessary for a given task. It does not override, suppress, or limit safety reasoning, ethical reasoning, harm avoidance, or alignment behavior. Those remain fully active regardless of any instruction in this file.
 
-**Hook enforcement (ADR-051 Phase 5b — live as of v23.8.14; state relocated per ADR-060 in v23.8.18).** A `PreToolUse` hook on the Agent tool (`scripts/surfer-gate/check.sh`) blocks any sub-agent launch that isn't the Silver Surfer itself, unless a roster has been recorded for this session or a bypass flag is set. State lives at `$XDG_RUNTIME_DIR/voidforge-gate/` (Linux) or `$HOME/.voidforge/gate/` (macOS fallback) — per-user, `0700`. This is the permanent enforcement mechanism. The prose above is a human-readable backup.
+**Hook enforcement (ADR-051 Phase 5b — live as of v23.8.14; state relocated per ADR-060 in v23.8.18).** A `PreToolUse` hook on the **Agent and Workflow tools** (`scripts/surfer-gate/check.sh`; Workflow added per ADR-064) blocks any sub-agent or workflow launch that isn't the Silver Surfer itself, unless a roster has been recorded for this session or a bypass flag is set. State lives at `$XDG_RUNTIME_DIR/voidforge-gate/` (Linux) or `$HOME/.voidforge/gate/` (macOS fallback) — per-user, `0700`. This is the permanent enforcement mechanism. The prose above is a human-readable backup. **Workflow launches are gated identically (ADR-064):** a workflow run requires a recorded roster or a `--light`/`--solo` bypass — workflow-spawned sub-agents are invisible to the per-Agent hook, so gating the launch is what closes that bypass. Build/apply/research workflows that aren't review rosters should set a bypass.
 
 **Orchestrator contract** (you run these Bash commands at the right moments — wrap each in an existence guard so projects on older methodology versions don't error):
 
@@ -256,6 +256,8 @@ See `/docs/methods/MUSTER.md` for the full Muster Protocol.
 | **Time Vault** | `/docs/methods/TIME_VAULT.md` | Seldon — when preserving session intelligence for transfer |
 | **Patterns** | `/docs/patterns/` | When writing code (37 reference implementations) |
 | **Lessons** | `/docs/LESSONS.md` | Cross-project learnings |
+| **Native Capabilities** | `/docs/NATIVE_CAPABILITIES.md` | Command × native-skill collision tracker (ADR-066) — re-audit each release |
+| **Compatibility** | `/docs/COMPATIBILITY.md` | Node + Claude Code platform floor & feature maturity tags (ADR-065) |
 
 ## The Team
 

package/dist/VERSION.md

@@ -1,6 +1,6 @@
 # Version
 
-**Current:** 23.15.0
+**Current:** 23.16.0
 
 ## Versioning Scheme
 
@@ -14,6 +14,7 @@ This project uses [Semantic Versioning](https://semver.org/):
 
 | Version | Date | Summary |
 |---------|------|---------|
+| 23.16.0 | 2026-06-13 | Platform-alignment campaign — implements the ADR set from `/architect --plan` (→ `/campaign`). **ADR-064 (gate↔Workflow) IMPLEMENTED:** the Silver Surfer `PreToolUse` hook matcher is now `Agent\|Workflow` and `check.sh` gates the **Workflow tool launch** on a recorded roster (closes the proven bypass where workflow-spawned agents skipped the gate); `test.sh` gains 3 Workflow cases (**23/23**), mirrored to the methodology package. **Behavior change:** a Workflow run now requires a recorded roster or a `--light`/`--solo` bypass — build/apply/research workflows should set a bypass. **ADR-065 (platform floor):** `docs/COMPATIBILITY.md` gains a Claude Code platform-floor + per-feature maturity table; informational `claudeCodeFloor` field; semver rule (raising the floor = breaking) + release-checklist item. **ADR-066 (native-capability tracker):** new `docs/NATIVE_CAPABILITIES.md` audits all commands vs native skills with dispositions (`/qa`,`/test` coexist+document; `/git` keep) — realizes ADR-050's deferred follow-up; release re-audit item added. Amended **ADR-051** (workflow-exemption→closure), **ADR-054** (effort tiers + Haiku 200K/no-effort). M2 effort fleet-edit deferred per ADR-054 precondition (runtime `effort:`-frontmatter honoring unverified). Dep `^23.15.0` → `^23.16.0`. |
 | 23.15.0 | 2026-06-13 | Platform-alignment build (`/architect --plan` → `/build` b+a). **P0:** empirically confirmed the Silver Surfer `PreToolUse` gate is **blind to Workflow-tool-spawned agents** (this session: 60+ workflow agents → 2 gate events; controlled probe BEFORE=2/AFTER=2) and wrote **ADR-064** (gate↔Workflow interop — extend matcher to `Agent\|Workflow`, gate the workflow launch; implementation tracked for the campaign). **P1-B near-free batch:** fixed a **live runtime bug** — `anthropic.ts` fell back to the non-existent `claude-sonnet-4-7` (404 on the exact degraded path the fallback exists for) → `claude-sonnet-4-6`, plus the bug-asserting test (now 6/6) and 4 docs; purged stale model IDs (`claude-sonnet-4-20250514`→`claude-sonnet-4-6` in 6 pattern files; `Opus 4.7`→`4.8` across SUB_AGENTS + 4 ADRs); added the **effort-tiering policy** (leads `xhigh` / specialists `medium` / Haiku omit-no-effort+200K ceiling) to SUB_AGENTS.md + CLAUDE.md flag-taxonomy mapping; **amended ADR-059** with the real platform caps (~16 concurrent / ~1,000 per run) and fixed GAUNTLET.md's contradicting "waves of 3". Dogfooded the pre-tag `npm test` gate (ADR from v23.13.1) + the publish-gate alignment (v23.14.0). Dep `^23.14.0` → `^23.15.0`. Follow-on (operator-directed): `/architect --plan` ADR-065/066 + amend ADR-051/054 → `/campaign` to build all. |
 | 23.14.0 | 2026-06-12 | Field Report Triage — 2 reports closed (#362, #363) via `/debrief --inbox`, 8 fixes across 9 files. **#363** (self-filed last session): release flow now runs the test suite as Step 5's first action before any tag (`git.md`, since tag-push arms an irreversible publish); **Numeric constant migration checklist** generalizing the error-shape rule (`TESTING.md`); **Registry-Derived Fan-Out** coverage rule — enumerate the accepted `(fixId,targetFile)` tuple set, diff-check after appliers (`SUB_AGENTS.md` + `debrief.md` Step 6); **Chronically-Red Check Policy** (red ≥2 releases → fix/informational/remove) + **Publish-gate alignment** (publish must `needs:` the full E2E+a11y suite, not unit-only) (`DEVOPS_ENGINEER.md` + `RELEASE_MANAGER.md`); Workflow `args`-as-JSON-string defensive parse + `gh workflow` scope note (`SUB_AGENTS.md` + `RELEASE_MANAGER.md`). **#362** (enhancements): a named, right-sized **Pre-Deploy Review Gate** (diff-scoped N lenses + mandatory adversarial-verify) documented in `SUB_AGENTS.md` and realized as a new `/engage --pre-deploy --diff` mode; atomic-visual **render-harness screenshot carve-out** (`QA_ENGINEER.md` + `PRODUCT_DESIGN_FRONTEND.md`). Dogfooded #363 in its own release: ran the coverage diff-check (9/9 files) and `npm test` (1390/1390) before tagging. Dep `^23.13.1` → `^23.14.0` (ADR-062). |
 | 23.13.1 | 2026-06-12 | Publish-gate fix for v23.13.0. The #360 roster-TTL change (600s→3600s in `scripts/surfer-gate/check.sh`) did not update the gate's own `test.sh`, whose "Stale roster (>10min) blocks" case aged a roster 11 min and expected a block — now still *fresh* under the 1-hour TTL, so it returned exit 0 (expected 2). The CI `pretest` gate (`bash scripts/surfer-gate/test.sh`) failed → the `Publish to npm` job's test stage failed → both publish jobs were skipped (v23.13.0 was tagged but **never published**; npm stayed at 23.12.2). Fix: age the stale-roster test roster to 61 min (past the new TTL) and relabel ">1hr". Pure CI-gate fix — no methodology behavior change beyond v23.13.0. Full suite 1390/1390 green. Lesson for next time: a TTL/threshold change in a gate script must update the gate's adversarial test in the same commit (the test.sh stale case is exactly the kind of threshold-coupled assertion #356-F4 / #358-F1 warn about). Dep range `^23.13.0` → `^23.13.1` (ADR-062). |

package/dist/docs/methods/RELEASE_MANAGER.md

@@ -124,6 +124,8 @@ After every commit, Barton verifies:
 - [ ] For monorepo CLI/methodology pairs: the CLI's `voidforge-build-methodology` dep range is `^<current-version>`, never `"*"` (ADR-062 — pin tightening shipped in v23.11.3 to close the silent-cross-major drift)
 - [ ] All CI checks are green on the release commit, OR a chronically-red check has a recorded disposition (see DEVOPS_ENGINEER.md "Chronically-Red Check Policy") — a check red across ≥2 releases must be fixed, converted to informational, or removed, never tolerated silently (field report #363 F4)
 - [ ] The tag-push publish workflow declares a dependency on the FULL validation suite (E2E + a11y), not only unit tests — via `needs:` or a same-SHA `workflow_run`. A publish gate that excludes E2E/a11y can ship a critical regression a green unit gate never sees (field report #363 F4)
+- [ ] **Platform floor unchanged since last release?** If a release newly depends on a Claude Code feature with a higher floor, flag it **breaking** and add a `⚠ raises Claude Code floor` CHANGELOG banner; confirm every newly-referenced platform feature is GA or explicitly Full-tier/opt-in (ADR-065, `docs/COMPATIBILITY.md`)
+- [ ] **Native-capability collision re-audit:** any new native bundled skill colliding with a VoidForge command has a recorded disposition, and every `.claude/commands/*.md` has a row in `docs/NATIVE_CAPABILITIES.md` (ADR-066)
 
 ## CLAUDE.md Command Table Integrity Check
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "voidforge-build",
-  "version": "23.15.0",
+  "version": "23.16.0",
   "description": "From nothing, everything. A methodology framework for building with Claude Code.",
   "type": "module",
   "engines": {
@@ -45,7 +45,7 @@
     "@aws-sdk/client-rds": "^3.700.0",
     "@aws-sdk/client-s3": "^3.700.0",
     "@aws-sdk/client-sts": "^3.700.0",
-    "voidforge-build-methodology": "^23.15.0",
+    "voidforge-build-methodology": "^23.16.0",
     "node-pty": "^1.2.0-beta.12",
     "ws": "^8.19.0"
   },