gm-skill 2.0.1623 → 2.0.1625

package/AGENTS.md

@@ -104,7 +104,7 @@ Every skill's `allowed-tools:` is reduced to `Skill, Read, Write` (plus the SKIL
 
 **Every possible aspect that can be checked for jank is a PRD row; the architecture is pliable**: at PLAN, for every surface the prompt concerns, enumerate every aspect checkable for `jank` -- every immaturity, unfinished edge, half-wired path -- across gui/ux/ui/client-state/server-state/the boundary and any surface reached, each its own row including a profiling row and a security row per surface. `jank` is load-bearing: hunt the rough/unpolished/almost-done, not only outright bugs. Scoped to the prompt's concern + its reachable closure, exhaustive within it. Every issue found opens its own debug-and-repair plan spooled the same turn; every quick improvement is spooled too. `pliable`: every architectural change that clearly improves or reduces maintenance burden is a spooled plan -- replacing bespoke code with native functionality or a popular well-maintained library is encouraged ONLY when it nets a smaller maintained surface (a heavy dep for a few lines is the guarded failure mode). Fan-out is the spool-native shape (parallel `prd-add`/`codesearch`/`exec_js`, plugkit task-spawn), never the platform's Task/Explore subagent. One tell-tale AI design element (boilerplate flourish, over-hedged comment, generic scaffold name, machine-authored shape) spawns a full-codebase sweep plan -- scan/per-cluster/fix-and-verify rows, exhaustive over every file, never a one-off fix.
 
-**Client-side debugging exposes globals and evaluates in-browser, never blind-restarts**: surface the relevant state as a `window.*` global and read it live via the `browser` verb's `page.evaluate`, running experiments in the browser, rather than blind experimentation + server restarts. The live page is the debugger; the same `browser` surface that witnesses an edit also diagnoses it.
+**Client-side debugging exposes globals and evaluates in-browser, never blind-restarts**: the live page is the debugger (rs-learn: `recall: client-side-debug-globals-live-page`).
 
 **Mundane user-facing output is suppressed or stripped to the bone**: drop articles, preamble, play-by-play; boot-probe narration, dispatch echoes, restating prose just read, status recaps do not ship. What survives is substantive: a real finding, a decision + one-line reason, a blocker, the single-line PRD-read declaration. Terse = fewer/shorter words, NEVER zero tool calls and NEVER silent work -- the turn still ends in the chain-advancing tool call.
 
@@ -162,7 +162,7 @@ Orchestration state is tracked via `.gm/` marker files, not hook events; the CLI
 
 **Apparent tooling failure is mechanical self-recovery, NEVER a question for the user and never an a/b-test/blind-restart.** A missing spool response / stale watcher is the agent's own job: honor a future `busy_until` else boot the watcher and re-dispatch -- the spooler is sound by construction, so asking the user to do what a verb can do is a paper-spirit violation. Recovery mechanics (atomic `.status.json`, `FailedToOpenSocket` retry, debug-via-`window.*`-globals) in rs-learn (`recall: spooler self-recovery mechanics`).
 
-**Process-of-elimination is the debugging paradigm EVERYWHERE, and manual real-services witness is the verification paradigm EVERYWHERE.** Every debug -- code, wasm, cascade, browser, the spooler itself -- enumerates candidate causes as mutables and eliminates each by a witness read against real input (`exec_js`/`codesearch`/`Read`/`browser page.evaluate`), each elimination revealing the next, never guess-and-restart/a-b-test/shotgun. Every verification is manual labour against the real thing -- the single mock-free `test.js`, the live page, the real service, the live wasm -- never an automated unit/mock suite standing in for the real-services witness (the conventional-testing tell-tale gm replaces). Stated in `instructions/execute.md` (the served EXECUTE prose) so it reaches every LLM in-session.
+**Process-of-elimination is the debugging paradigm EVERYWHERE, and manual real-services witness is the verification paradigm EVERYWHERE** -- both stated in `instructions/execute.md` (served EXECUTE prose). Detail in rs-learn (`recall: process-of-elimination manual-real-services-witness paradigm`).
 
 **The first verb after a genuine multi-minute IDLE is `instruction`, to reset the long-gap clock**: only spool verbs reset it, so a long investigation in platform tools trips a false stall -- interleave `instruction`/`prd-add` to stay warm, and dispatch `instruction` BEFORE any predictable blocking wait. Threshold + platform-tool exception in rs-learn (`recall: first verb after multi-minute wait instruction long-gap`).
 

package/bin/install.js

@@ -7,7 +7,6 @@ const os = require('os');
 const readline = require('readline');
 
 const SKILL_NAME = 'gm';
-const AUTOCOMPACT_WINDOW = 380000;
 
 function out(msg) { process.stdout.write(msg + '\n'); }
 function err(msg) { process.stderr.write(msg + '\n'); }
@@ -102,8 +101,6 @@ function applyClaudeSettings(home) {
     const backup = settingsPath + '.bak';
     try { fs.copyFileSync(settingsPath, backup); err(`existing settings.json was malformed; backed up to ${backup}`); } catch (_) {}
   }
-  obj.autoCompactEnabled = true;
-  obj.autoCompactWindow = AUTOCOMPACT_WINDOW;
   obj.effortLevel = 'low';
   obj.alwaysThinkingEnabled = false;
   fs.mkdirSync(path.dirname(settingsPath), { recursive: true });
@@ -116,8 +113,6 @@ function applyClaudeSettings(home) {
 
 const SETTINGS_EXPLAINER = [
   'Claude Code settings applied:',
-  '  autoCompactEnabled = true      keep long sessions coherent by auto-compacting context',
-  `  autoCompactWindow  = ${AUTOCOMPACT_WINDOW}  absolute token count (38% of a 1M window), not a percentage`,
   "  effortLevel        = low       thinking effort lowered",
   '  alwaysThinkingEnabled = false  explicit thinking turned off',
   '',
@@ -136,7 +131,7 @@ async function offerClaudeSettings(home) {
   try {
     out('');
     out('Claude Code detected. gm works best with reasoning-in-code rather than hidden thinking tokens.');
-    out('Offer to set: autoCompactEnabled=true, autoCompactWindow=' + AUTOCOMPACT_WINDOW + ', effortLevel=low, alwaysThinkingEnabled=false.');
+    out('Offer to set: effortLevel=low, alwaysThinkingEnabled=false.');
     const ans = (await ask(rl, 'Apply these Claude Code settings now? [y/N] ')).trim().toLowerCase();
     if (ans === 'y' || ans === 'yes') {
       const r = applyClaudeSettings(home);

package/gm-plugkit/package.json

@@ -1,6 +1,6 @@
 {
   "name": "gm-plugkit",
-  "version": "2.0.1623",
+  "version": "2.0.1625",
   "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

@@ -163,7 +163,6 @@ function dispatchVerbToWasmInternal(instance, verb, body) {
   if (!dispatch) return null;
   const verbBytes = new TextEncoder().encode(verb);
   const bodyBytes = new TextEncoder().encode(body || '');
-  // writeWasmInput re-reads memory.buffer fresh after each alloc (avoids the detached-buffer write bug).
   let verbPtr = 0, bodyPtr = 0;
   try { verbPtr = writeWasmInput(instance, verbBytes, `dispatch_verb(${verb}).verb`); }
   catch (e) { throw new Error(`wasm-alloc-failed for dispatch_verb(${verb}): ${e.message}`); }
@@ -1054,10 +1053,6 @@ function startManagedBrowser(pw, profileDir) {
     '--disable-default-apps',
     '--disable-gpu-process-crash-limit',
   ];
-  // In containers where unprivileged user namespaces are disabled, Chromium's
-  // sandbox cannot initialize and the remote-debugging port never binds (the CDP
-  // "did not become ready" failure). Opt in to running without the sandbox (plus
-  // the small-/dev/shm workaround common in containers) via GM_BROWSER_NO_SANDBOX=1.
   if (process.env.GM_BROWSER_NO_SANDBOX === '1') {
     args.push('--no-sandbox', '--disable-setuid-sandbox', '--disable-dev-shm-usage');
   }
@@ -1375,33 +1370,18 @@ function guardWasmRange(buffer, ptr, len, where) {
   }
 }
 
-// Decode a packed (ptr,len) i64 dispatch result into a JS string, the ONE correct way.
-// Two bugs this consolidates (they only surface once the wasm memory grows past a threshold --
-// e.g. a large .gm state file -> a big plugkit_alloc -> the memory grows past ~2GB / the linear
-// memory is re-grown mid-dispatch):
-//   1. SIGNED i64 result. dispatch_verb returns an i64; a high bit set (large ptr or a packed
-//      len in the top 32 bits) makes `result` a NEGATIVE BigInt. `result >> 32n` on a negative
-//      BigInt arithmetic-shifts in sign bits -> a garbage/negative len, and the low-word mask can
-//      misread too. Normalize to unsigned 64-bit FIRST: BigInt.asUintN(64, result).
-//   2. DETACHED buffer. `instance.exports.memory.buffer` captured before plugkit_alloc/dispatch is
-//      a STALE ArrayBuffer once the wasm linear memory grows (the old buffer detaches). Reading the
-//      result against it throws 'Start offset N is outside the bounds of the buffer'. Always re-read
-//      instance.exports.memory.buffer FRESH at the moment of the view, never reuse a captured one.
 function decodeWasmResult(instance, result, where) {
-  const u = BigInt.asUintN(64, BigInt(result));   // (1) normalize the i64 to unsigned before splitting
+  const u = BigInt.asUintN(64, BigInt(result));
   const ptr = Number(u & 0xffffffffn);
   const len = Number(u >> 32n);
   if (ptr === 0 || len === 0) return '';
-  const buffer = instance.exports.memory.buffer;  // (2) FRESH buffer (post-grow), never a stale capture
+  const buffer = instance.exports.memory.buffer;
   guardWasmRange(buffer, ptr, len, where);
   const out = new TextDecoder().decode(new Uint8Array(buffer, ptr, len));
   try { instance.exports.plugkit_free(ptr, len); } catch (_) {}
   return out;
 }
 
-// Write input bytes into wasm memory, re-reading memory.buffer FRESH after the alloc so a memory
-// grow during plugkit_alloc never leaves us writing into a detached buffer (the write-side half of
-// the detached-buffer bug). Returns the ptr (caller frees) or throws on alloc failure.
 function writeWasmInput(instance, bytes, where) {
   if (bytes.length === 0) return 0;
   const ptr = instance.exports.plugkit_alloc(bytes.length);
@@ -3275,7 +3255,6 @@ async function runSpoolWatcher(instance, spoolDir) {
         }
       }
 
-      // writeWasmInput re-reads memory.buffer fresh after each alloc (detached-buffer write fix).
       const verbPtr = writeWasmInput(instance, verbBytes, `spool-dispatch:${verb}.verb`);
       const bodyPtr = writeWasmInput(instance, bodyBytes, `spool-dispatch:${verb}.body`);
 
@@ -3283,8 +3262,6 @@ async function runSpoolWatcher(instance, spoolDir) {
       const result = dispatch(verbPtr, verbBytes.length, bodyPtr, bodyBytes.length);
       clearVerbActive();
 
-      // decodeWasmResult normalizes the i64 (BigInt.asUintN), re-reads the buffer FRESH (post-grow),
-      // guards the range, AND frees the result ptr -- so the (ptr,len) free below is dropped.
       let resultStr = decodeWasmResult(instance, result, `spool-dispatch:${verb}`);
 
       if (autoRecallPayload) {
@@ -3338,7 +3315,6 @@ async function runSpoolWatcher(instance, spoolDir) {
 
       try { instance.exports.plugkit_free(verbPtr, verbBytes.length); } catch (_) {}
       try { instance.exports.plugkit_free(bodyPtr, bodyBytes.length); } catch (_) {}
-      // (the result ptr is freed inside decodeWasmResult above)
 
       try { if (fs.existsSync(filePath)) fs.unlinkSync(filePath); } catch (_) {}
       unmarkProcessed(key);

package/gm.json

@@ -1,6 +1,6 @@
 {
   "name": "gm",
-  "version": "2.0.1623",
+  "version": "2.0.1625",
   "description": "Spool-dispatch orchestration engine with unified state machine, skills, and automated git enforcement",
   "author": "AnEntrypoint",
   "license": "MIT",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "gm-skill",
-  "version": "2.0.1623",
+  "version": "2.0.1625",
   "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",

package/skills/gm/SKILL.md

@@ -85,3 +85,5 @@ The chain is not COMPLETE until changes are on origin. Commit and push at the en
 **Prune bad memory on sight -- a wrong recall hit is worse than a miss.** A stale/superseded/wrong `recall` or `auto_recall` hit gets `memorize-prune {key}` (deletes text + embedding). For an uncertain set, `memorize-prune {query}` returns review-only candidates; judge, then re-dispatch the stale `{keys:[...]}` -- never a blind similarity-delete.
 
 On turn entry plugkit attaches an `auto_recall` pack derived from the prompt; read its hits alongside `recall_hits` (the phase+PRD-subject pack). It fires once per turn entry on its own -- do not re-trigger it.
+
+If the instructions amount to doing more than one step or imply it, use or create a workflow, or set a goal to track progress, and if subagents are available fan out subagents that use gm for everything, up to 8 in parallel