gm-skill 2.0.1759 → 2.0.1760

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/AGENTS.md CHANGED
@@ -166,7 +166,7 @@ Orchestration state tracked via `.gm/` marker files, not hook events; CLI's `che
166
166
 
167
167
  **Dead-watcher recovery uses `bun x gm-plugkit@latest spool`, never direct-node boot** (mechanism: rs-learn `recall: dead-watcher recovery bun x not direct-node`).
168
168
 
169
- **Starting the spool is one atomic blocking call -- `bun x gm-plugkit@latest spool` daemonizes the watcher AND blocks until `.status.json` heartbeats fresh, returning exit 0 only when serving (loud non-zero on timeout).** No `& + sleep + re-cat` dance; agent writes to `instruction/` the moment the call returns. Wait lives in `gm-plugkit/cli.js` (`waitForWatcherHeartbeat`, `Atomics.wait` sync-sleep), cli-side since `startSpoolDaemon` is sync + shared by non-blocking callers. rs-plugkit carries no server-boot logic -- daemonize lifecycle is entirely gm-plugkit JS, no Rust/cascade rebuild needed.
169
+ **Starting the spool is one atomic blocking call**: `bun x gm-plugkit@latest spool` daemonizes AND blocks until `.status.json` heartbeats fresh (exit 0 only when serving). Cli-side wait mechanics: rs-learn (`recall: atomic spool boot cli-side wait`).
170
170
 
171
171
  **Apparent tooling failure is mechanical self-recovery, NEVER a question for the user and never an a/b-test/blind-restart.** Missing spool response / stale watcher = agent's own job: honor future `busy_until` else boot+re-dispatch -- spooler is sound by construction, 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): rs-learn (`recall: spooler self-recovery mechanics`).
172
172
 
@@ -174,7 +174,7 @@ Orchestration state tracked via `.gm/` marker files, not hook events; CLI's `che
174
174
 
175
175
  **The first verb after a genuine multi-minute IDLE is `instruction`, to reset the long-gap clock**: only spool verbs reset it, so long platform-tool investigation trips false stall -- interleave `instruction`/`prd-add` to stay warm, dispatch `instruction` BEFORE any predictable blocking wait. Threshold + exception: rs-learn (`recall: first verb after multi-minute wait instruction long-gap`).
176
176
 
177
- **A stop-hook firing on a terminal chain does not authorize re-polling**: stop-hook at `phase=COMPLETE AND prd_pending_count=0` -> re-dispatching `instruction`/`phase-status` to "re-confirm" = deviation (`deviation.complete-chain-poll`, `instructions/mod.rs`). Two admissible responses: (a) prose-only turn (COMPLETE in hand), (b) genuinely new work via FRESH `{"prompt":...}` body (resets to PLAN, skill-driven). Repeated same-hook answering = loop; state terminal facts once and stop, or open new work.
177
+ **A stop-hook firing on a terminal chain does not authorize re-polling** (`deviation.complete-chain-poll`): prose-only turn or fresh `{"prompt":...}` only. Detail: rs-learn (`recall: complete-chain-poll stop-hook responses`).
178
178
 
179
179
  Session lifecycle (task/browser persistence across turn-stops, residual-scan trigger conditions): rs-learn (`recall: session lifecycle killSessionTasks residual-scan`).
180
180
 
@@ -1 +1 @@
1
- 0.1.789
1
+ 0.1.790
@@ -1 +1 @@
1
- 3763cee0fd263320a38c823d2469defbcfebad07dce2bb384bbee64d5afba2ae plugkit.wasm
1
+ 574779f54a11e71e56f80e60c9febf6d824b626324759ab657f791aabab4c21c plugkit.wasm
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "gm-plugkit",
3
- "version": "2.0.1759",
3
+ "version": "2.0.1760",
4
4
  "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.",
5
5
  "main": "index.js",
6
6
  "bin": {
@@ -1 +1 @@
1
- 0.1.789
1
+ 0.1.790
package/gm.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "gm",
3
- "version": "2.0.1759",
3
+ "version": "2.0.1760",
4
4
  "description": "Spool-dispatch orchestration engine with unified state machine, skills, and automated git enforcement",
5
5
  "author": "AnEntrypoint",
6
6
  "license": "MIT",
@@ -17,5 +17,5 @@
17
17
  "publishConfig": {
18
18
  "access": "public"
19
19
  },
20
- "plugkitVersion": "0.1.789"
20
+ "plugkitVersion": "0.1.790"
21
21
  }
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "gm-skill",
3
- "version": "2.0.1759",
3
+ "version": "2.0.1760",
4
4
  "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.",
5
5
  "author": "AnEntrypoint",
6
6
  "license": "MIT",