gm-skill 2.0.1561 → 2.0.1563

package/AGENTS.md

@@ -22,7 +22,7 @@ Skills encode environment-specific constraints that override general knowledge.
 
 # Architecture & Philosophy
 
-This repo IS the published `gm-skill` npm package: repo root = package root, no factory, no build step generating a separate output dir. `skills/gm-skill/SKILL.md` is the entry point; orchestration logic lives in rs-plugkit, served on demand via the `instruction` verb. Agent-facing prose (phase instruction text + gate/residual messages) is externalized to an editable bundle in `gm-plugkit/instructions/`, shipped by gm-plugkit and provisioned into `.gm/instructions/<key>.md`; `rs-plugkit/src/prose.rs` serves the bundle entry per key and falls back to the compiled `const` when absent -- so editing prose is a gm-plugkit republish with no Rust rebuild. The bundle .md and the rs-plugkit `src/orchestrator/instructions/<key>.rs` consts are kept byte-aligned by `gm-plugkit/scripts/sync-instruction-consts.mjs` (regenerates each `<key>.rs` as `pub const TEXT` from the .md). Detail in rs-learn (`recall: string-externalization project`).
+This repo IS the published `gm-skill` npm package: repo root = package root, no factory, no build step generating a separate output dir. `skills/gm-skill/SKILL.md` is the entry point; orchestration logic lives in rs-plugkit, served on demand via the `instruction` verb. Agent-facing prose (phase instruction + gate/residual text) is externalized to an editable `gm-plugkit/instructions/` bundle, so editing prose is a gm-plugkit republish with no Rust rebuild. Mechanism (prose.rs per-key fallback to compiled const; sync-instruction-consts.mjs byte-aligns the .md and the rs-plugkit consts) in rs-learn (`recall: string-externalization project`).
 
 ## WASM-only
 
@@ -40,7 +40,7 @@ Agents dispatch verbs by writing `.gm/exec-spool/in/<verb>/<N>.txt` and reading
 
 - **Orchestrator verbs**: `instruction`, `transition`, `phase-status`, `mutable-resolve`, `memorize-fire`, `residual-scan`, `auto-recall`.
 - **Wasm-direct verbs**: fs/kv/exec/fetch/env, recall, codesearch, memorize(+prune), health, filter, full git verb family. Enumeration in rs-learn (`recall: wasm-direct plugkit verbs full list`).
-- **memorize-prune**: deletes bad/superseded memories (a wrong recall hit is worse than a miss). `{key}`/`{keys:[...]}` deletes; `{query}` returns review-only candidates to judge before re-dispatching stale keys -- never a blind similarity-delete. Spec in rs-learn (`recall: memorize-prune verb two-mode spec`).
+- **memorize-prune**: prunes bad/superseded memories (`{key}`/`{keys}` deletes; `{query}` returns review-only candidates to judge first). Spec in rs-learn (`recall: memorize-prune verb two-mode spec`).
 - **git verbs**: git is a first-class spool surface, never a shell command; `git_finalize {message}` is the bundled COMPLETE-phase push surface, `git_push` the only admissible raw push (porcelain-gated, rebase-retry). A git-dominant `bash`/`powershell` body is gated (`deviation.bash-git-bypass`). Per-verb shapes + host_git `.exe` resolution in rs-learn (`recall: git verbs rs-plugkit spool surface`).
 - **filter**: pure stdout -> compact-stdout transform, in-wasm, no subprocess; pipe raw command output through it before it enters context. Spec in rs-learn (`recall: filter verb rs-plugkit spool spec`).
 
@@ -132,7 +132,7 @@ Every skill's `allowed-tools:` is reduced to `Skill, Read, Write` (plus the SKIL
 
 **rs-learn observability**: learning-pipeline state changes emit `evt:` lines to `.gm/exec-spool/.watcher.log` + gm-log; recall replies carry per-hit scoring fields. Surface + taxonomy + flags in rs-learn (`recall: rs-learn observability taxonomy`).
 
-**Bootstrap contract (skill-init + SKILL.md auto-refresh + project wiring)**: `bootstrapPlugkit`/`ensureReady` initialize wasm hook-free (failures non-fatal), sha256-rewrite stale installed SKILL.md, and seed per-project `CLAUDE.md` (`@AGENTS.md`) + `.gm/next-step.md`; the wiring lives in `gm-plugkit/bootstrap.js::ensureReady` (the consumer-project watcher boot path), not only repo-root `bin`/`lib`. Detail in rs-learn (`recall: skill-initiated bootstrap contract`, `recall: SKILL.md auto-refresh`).
+**Bootstrap contract**: `ensureReady` initializes wasm hook-free, sha256-rewrites a stale installed SKILL.md, and seeds per-project `CLAUDE.md`/`.gm/next-step.md`. Detail in rs-learn (`recall: skill-initiated bootstrap contract`, `recall: SKILL.md auto-refresh`).
 
 ## Cascade pipeline
 
@@ -144,8 +144,6 @@ Three npm packages publish from this repo: `gm-skill` (harness), `gm-plugkit` (b
 
 **To update every possible thing**: push to the relevant repo. No manual version bumps, no local cargo builds -- never run `cargo update`/`cargo build` locally, push and let CI build.
 
-**Timeout enforcement**: every `exec_js` dispatch carries a positive `timeoutMs`; the host treats missing or zero as a hard error.
-
 ## Spool-dispatch architecture replaces hooks
 
 Orchestration state is tracked via `.gm/` marker files, not hook events; the CLI layer calls `checkDispatchGates()` before tool execution to gate Write/Edit/git. Marker set (`prd.yml, mutables.yml, needs-gm, gm-fired-<sessionId>, residual-check-fired`) + SpoolDispatcher mechanism in rs-learn (`recall: gate enforcement layer`, `recall: spool dispatch gates marker files`).
@@ -156,7 +154,7 @@ Orchestration state is tracked via `.gm/` marker files, not hook events; the CLI
 
 **Dead-watcher recovery uses `bun x gm-plugkit@latest spool`, never direct-node boot** (mechanism in rs-learn: `recall: dead-watcher recovery bun x not direct-node`).
 
-**The first verb after a genuine multi-minute IDLE is `instruction`, to reset the long-gap clock**: the gate fires on genuine idle only (>300s since the last instruction AND >300s since any verb), so active back-to-back work verbs keep the chain alive without an interleaved `instruction` -- do not inject defensive instruction dispatches between active work. A true wait (version download, overnight, long external CI watch) trips it, and the first verb back is `instruction`. When the wait is self-inflicted and predictable (a blocking `TaskOutput`/`gh run watch`), dispatch `instruction` immediately BEFORE entering the wait, not only after. Mechanism in rs-learn (`recall: first verb after multi-minute wait instruction long-gap`).
+**The first verb after a genuine multi-minute IDLE is `instruction`, to reset the long-gap clock**: the gate fires on genuine idle only (>300s since the last instruction AND >300s since any verb), so active back-to-back work verbs keep the chain alive without an interleaved `instruction` -- do not inject defensive instruction dispatches between active work. A true wait (version download, overnight, long external CI watch) trips it, and the first verb back is `instruction`. When the wait is self-inflicted and predictable (a blocking `TaskOutput`/`gh run watch`), dispatch `instruction` immediately BEFORE entering the wait, not only after. "Work verbs"/"any verb" here means SPOOL dispatches -- platform `Bash`/`Read`/`Edit`/`Grep` do NOT reset the clock, so a long investigation run purely in them (the audit `gmsniff`/`ccsniff` sweep + source reading/editing exceeding 300s) trips a false `mid-chain-stall` even while actively working; interleave a `prd-add` (convert each finding as it emerges per density-grows-along-the-walk) or an `instruction` to keep the clock warm. Mechanism in rs-learn (`recall: first verb after multi-minute wait instruction long-gap`).
 
 **A stop-hook firing on a terminal chain does not authorize re-polling**: when a stop-hook fires while already at `phase=COMPLETE` AND `prd_pending_count=0`, re-dispatching `instruction`/`phase-status` to "re-confirm" is a deviation (`deviation.complete-chain-poll`, `instructions/mod.rs`). Two admissible responses: (a) a prose-only turn (COMPLETE is in hand), or (b) genuinely new planned work opened with a FRESH `{"prompt":...}` body (resets phase to PLAN, driven through the skill). Repeatedly answering the same hook is a loop; state the terminal facts once and stop, or open new work.
 
@@ -164,7 +162,7 @@ Orchestration state is tracked via `.gm/` marker files, not hook events; the CLI
 
 ## Spool observability surface
 
-One-shot system-state probe: dispatch `plugkit health` via the file-spool before assuming any component is broken. Three runtime diagnostic files at `.gm/exec-spool/` root (`.status.json`, `.last-session-start.json`, `.bootstrap-error.json`) are readable directly via Read (runtime-data exception). Field enumeration in rs-learn (`recall: plugkit health verb fields`).
+One-shot system-state probe: dispatch `plugkit health` via the file-spool before assuming any component is broken; the runtime diagnostic files at `.gm/exec-spool/` root are readable directly via Read (runtime-data exception). File list + health fields in rs-learn (`recall: spool runtime diagnostic files`, `recall: plugkit health verb fields`).
 
 ## Site Build & Documentation
 

package/bin/plugkit.version

@@ -1 +1 @@
-0.1.645
+0.1.647

package/bin/plugkit.wasm.sha256

@@ -1 +1 @@
-8380b75df694c28fb73d26a67c1cc184c2157feac4d0b8b252bd0a3aa6020c57  plugkit.wasm
+ec5acd688dae137c8fd18434027015b66b8e9934f651cb8c2ba692eda4153ca6  plugkit.wasm

package/gm-plugkit/package.json

@@ -1,6 +1,6 @@
 {
   "name": "gm-plugkit",
-  "version": "2.0.1561",
+  "version": "2.0.1563",
   "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

@@ -411,6 +411,17 @@ function scanStalledTurns() {
   }
 }
 
+// Every spool dispatch is the agent actively driving the chain, including wasm-direct verbs
+// (recall/codesearch/exec_js/git/fetch) that never reach turnTick. Refresh the open turn's stall
+// clock so a Bash-free stretch of pure wasm-direct verbs does not trip a false mid-chain-stall
+// (the recurring audit-fire own-defect). Never create or split a turn -- that stays turnTick's job.
+function touchActiveTurn(sess) {
+  const t = _turns.get(sess || '(no-session)');
+  if (!t) return;
+  t.lastTs = Date.now();
+  t.stallEmitted = false;
+}
+
 let __sessCache = { value: '', mtimeMs: 0, readAt: 0, srcMtimeMs: 0 };
 function readCurrentSess() {
   const now = Date.now();
@@ -479,10 +490,14 @@ function logEvent(sub, event, fields) {
 }
 
 function emitOrchestratorEvents(verb, taskBase, resultStr) {
-  if (!ORCHESTRATOR_VERBS.has(verb)) return;
   let parsed;
-  try { parsed = JSON.parse(resultStr); } catch (_) { return; }
-  if (!parsed || parsed.ok !== true) {
+  try { parsed = JSON.parse(resultStr); } catch (_) { parsed = null; }
+  if (!ORCHESTRATOR_VERBS.has(verb)) {
+    if (parsed && parsed.ok === true) { try { touchActiveTurn(readCurrentSess()); } catch (_) {} }
+    return;
+  }
+  if (!parsed) return;
+  if (parsed.ok !== true) {
     let errData = null;
     if (parsed && typeof parsed.stdout === 'string' && parsed.stdout.length > 0) {
       try { errData = JSON.parse(parsed.stdout); } catch (_) {}

package/gm.json

@@ -1,6 +1,6 @@
 {
   "name": "gm",
-  "version": "2.0.1561",
+  "version": "2.0.1563",
   "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": "0.1.645"
+  "plugkitVersion": "0.1.647"
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "gm-skill",
-  "version": "2.0.1561",
+  "version": "2.0.1563",
   "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",