gm-skill 2.0.1693 → 2.0.1695

package/AGENTS.md

@@ -132,7 +132,7 @@ Every skill's `allowed-tools:` reduced to `Skill, Read, Write` (plus SKILL.md bo
 
 **The agent IS the LLM rs-learn calls**: no separate judge model; decisions inline via spool. Internals: rs-learn (`recall: rs-learn self-report core internals`).
 
-**Idempotency contract (f∘f≡f)**: spool dispatch = at-least-once by design (in-memory processed-Map guards only concurrent double-pickup, not cross-time replay/restart), so correctness rests on per-verb convergence: `memorize`/`memorize-fire` content-hash-key+dedup, `git_finalize`/`git_commit` nothing-to-commit/already-pushed, `insert_edge` kv-overwrite-by-id+dedup-guarded-index, `invalidate_edge` early-return, `ensure_managed_gitignore` strip-rebuild-changed-gate, codeinsight digest-gate, publish.yml already-published-skip+porcelain-gated-version-commit-back. Read-only verbs (recall/codesearch/git_status/instruction/health/filter) recompute every dispatch, never cache. `exec_js`/`browser` re-run on replay (at-most-once-by-nature); persistent dedup ledger rejected as net-additive. Detail: rs-learn (`recall: idempotency contract per-verb convergence`).
+**Idempotency contract (f∘f≡f)**: spool dispatch is at-least-once; correctness rests on per-verb convergence (content-hash dedup, nothing-to-commit gates, digest gates); read-only verbs recompute, never cache. Per-verb enumeration: rs-learn (`recall: idempotency contract per-verb convergence`).
 
 **host_exec_js is synchronous**: real per-call `timeoutMs` required (zero/missing = hard error). Detail: rs-learn (`recall: host_exec_js synchronous`).
 
@@ -188,7 +188,7 @@ One-shot system-state probe: dispatch `plugkit health` before assuming any compo
 
 Site build + landing render: single-surface detail, drained to rs-learn (`recall: gm site build details`).
 
-**The site consumes the `anentrypoint-design` SDK pro-rata, never overriding it.** `site/theme.mjs` loads SDK at runtime (`unpkg.com/anentrypoint-design@latest`); local `<style>` carries ONLY render-mode plumbing (flatspace html-class toggles `article-flow`/`landing-cap`, crumb media query) + non-SDK site article-layout rhythm -- never a themed visual component. Every graphic-design change (token, component look, TOC/cli/panel/card/callout styling) made IN the SDK repo (`../anentrypoint-design`, GitHub `AnEntrypoint/design`, npm `anentrypoint-design`) as a token-only sheet, published; site picks up via `@latest`. New local CSS styling a visual component = deviation, belongs in SDK. SDK component sheets lint-gated literal-free (every color `var(--token)`); SDK build prefixes selectors `.ds-247420`-scoped. Mechanism: rs-learn (`recall: design SDK pro-rata consumption`).
+**The site consumes the `anentrypoint-design` SDK pro-rata, never overriding it.** Every visual change lands in the SDK repo, never local CSS; local `<style>` = render-mode plumbing only. Mechanism + repo pointers: rs-learn (`recall: design SDK pro-rata consumption`).
 
 
 @.gm/next-step.md

package/bin/plugkit.version

@@ -1 +1 @@
-0.1.740
+0.1.741

package/bin/plugkit.wasm.sha256

@@ -1 +1 @@
-b9c3b05dfbc9944971dff53e643ca7bdddea3fa822c8d37caf377d50ec17a204  plugkit.wasm
+5fb0db7065cde4b417e566699e68e4f05f4258c5139cb3f2c69365bde83dcdea  plugkit.wasm

package/gm-plugkit/package.json

@@ -1,6 +1,6 @@
 {
   "name": "gm-plugkit",
-  "version": "2.0.1693",
+  "version": "2.0.1695",
   "description": "Bootstrap and daemon-spawn tool for gm plugkit binary. Downloads the correct platform binary, verifies SHA256, and starts the spool watcher daemon. Includes plugkit-wasm-wrapper for WASM-based spool watching.",
   "main": "index.js",
   "bin": {

package/gm-plugkit/plugkit-wasm-wrapper.js

@@ -3814,6 +3814,23 @@ async function runSpoolWatcher(instance, spoolDir) {
   setInterval(() => { try { scanStalledTurns(); } catch (_) {} }, 30000);
   writeStatus();
 
+  setTimeout(() => {
+    try {
+      _writeStatusBusy(360000);
+      const vb = new TextEncoder().encode('codesearch');
+      const bb = new TextEncoder().encode(JSON.stringify({ query: 'index warmup', k: 1 }));
+      const vp = writeWasmInput(instance, vb, 'boot-warmup:codesearch.verb');
+      const bp = writeWasmInput(instance, bb, 'boot-warmup:codesearch.body');
+      const t0 = Date.now();
+      const r = dispatch(vp, vb.length, bp, bb.length);
+      decodeWasmResult(instance, r, 'boot-warmup:codesearch');
+      writeStatus();
+      logEvent('plugkit', 'boot.index-warmup', { ms: Date.now() - t0 });
+    } catch (e) {
+      try { logEvent('plugkit', 'boot.index-warmup-failed', { error: String(e && e.message || e) }); } catch (_) {}
+    }
+  }, 3000);
+
   const TURN_SUMMARY_PATH = path.join(spoolDir, '.turn-summary.json');
   function writeTurnSummary() {
     try {

package/gm-plugkit/plugkit.version

@@ -1 +1 @@
-0.1.739
+0.1.741

package/gm.json

@@ -1,6 +1,6 @@
 {
   "name": "gm",
-  "version": "2.0.1693",
+  "version": "2.0.1695",
   "description": "Spool-dispatch orchestration engine with unified state machine, skills, and automated git enforcement",
   "author": "AnEntrypoint",
   "license": "MIT",
@@ -17,5 +17,5 @@
   "publishConfig": {
     "access": "public"
   },
-  "plugkitVersion": "0.1.740"
+  "plugkitVersion": "0.1.741"
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "gm-skill",
-  "version": "2.0.1693",
+  "version": "2.0.1695",
   "description": "Canonical universal harness — AI-native software engineering via skill-driven orchestration; bootstraps plugkit for task execution and session isolation. Install in any AI coding agent host.",
   "author": "AnEntrypoint",
   "license": "MIT",