gm-qwen 2.0.761 → 2.0.763

package/bin/plugkit.sha256

@@ -1,6 +1,6 @@
-6a915bc5c0926ec49acb4d1e5c995375eeabb06b50293cbe0a4bb86bcc6fe342  plugkit-win32-x64.exe
-6fbb19058635d310ec294b6d80df44ec3f388db99dffb32c424d646bc73d9d1a  plugkit-win32-arm64.exe
-0c15f9bc21051157931a948989469703f8c5cd21d11a6ec07e9b57c0e7447ddb  plugkit-darwin-x64
-5ab363b5ba2ebf13b8e1da988414ed37f20863669a391efb65fa6aa479c4c915  plugkit-darwin-arm64
-db078a3810a17bd6eea8b160e78c8d72bf189962e17e7fdbfe1a65be00674a84  plugkit-linux-x64
-4e0af3b31b3089a79c9f6e6f8d52d5fba56cb42911d479418db1aa9aad7cc858  plugkit-linux-arm64
+6f37a38d23215bec8b6e000dda95bebf41c8fd3d34f47efac8508ce436cea695  plugkit-win32-x64.exe
+bf94a8d39ce8bb2e6565a347fa88ba0061ca471fa968e3bcd645bcabd82c90cf  plugkit-win32-arm64.exe
+9257c8f7f351dae2a25fd706a75d0281aa20878b14b1ce38aa47b84568ea2dde  plugkit-darwin-x64
+5330b8d2681db209d5789fb6d5b6edcb5270f9d50ceac4126751a36995bef435  plugkit-darwin-arm64
+1d4dc8afb691486a643ef92904bb91d59deb7c88d1f05161a8ab1e38e6f6536f  plugkit-linux-x64
+a99817799e17ca2d467cdf6fca7c72c38af2d8ac2a14083c14f9461d4a652719  plugkit-linux-arm64

package/bin/plugkit.version

@@ -1 +1 @@
-0.1.251
+0.1.252

package/gm.json

@@ -1,6 +1,6 @@
 {
   "name": "gm",
-  "version": "2.0.761",
+  "version": "2.0.763",
   "description": "State machine agent with hooks, skills, and automated git enforcement",
   "author": "AnEntrypoint",
   "license": "MIT",
@@ -23,5 +23,5 @@
   "publishConfig": {
     "access": "public"
   },
-  "plugkitVersion": "0.1.251"
+  "plugkitVersion": "0.1.252"
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "gm-qwen",
-  "version": "2.0.761",
+  "version": "2.0.763",
   "description": "State machine agent with hooks, skills, and automated git enforcement",
   "author": "AnEntrypoint",
   "license": "MIT",

package/skills/planning/SKILL.md

@@ -71,9 +71,21 @@ The trigger is functional, not a path-list: any change whose effect is observabl
 
 Propagation: EXECUTE witnesses on edit, EMIT re-witnesses post-write, VERIFY runs the final gate. The plan must encode the rule so all three layers fire.
 
-## SKIP PLANNING (DEFAULT for small work)
+## ORIENT — HARD RULE (before naming any unknown)
 
-Skip if ANY: single-file single-concern edit | trivially bounded <5min | surgical user instructions | bug fix with identified root cause | zero unknowns. Heavy ceremony only for multi-file architectural work.
+Every planning entry begins with ORIENT: a parallel pack of recalls and codesearches that loads what the store already knows about the request. Do this BEFORE you name a single mutable.
+
+Pack: 3–5 `exec:recall <2-6 word query>` calls + 3–5 `exec:codesearch <two words>` calls, fired in one message (parallel). Queries derive from each major noun in the request and each named entity. Hits become `weak_prior`; misses confirm the unknown is genuinely fresh.
+
+Cost rationale: orient is free relative to skipping it. The agent that skips orient pays the same cost in fresh-execution rounds resolving things the store already had — plus the cost of the duplicate work, plus the risk of disagreeing with prior witness. Orient runs in parallel and completes in <1s when the rs-learn HTTP serve is hot. Skipping orient is forced closure.
+
+Exempt only when: literal one-line edit AND user instruction is fully self-contained AND zero recall-able context exists. Tag the exemption explicitly.
+
+## PRD MANDATORY — HARD RULE
+
+Writing `./.gm/prd.yml` is **non-negotiable** for every task whose scope exceeds a literal single-file single-line edit. The PRD captures the covering family (paper IV §2.3 Maximal Cover), the residual complement, the dependency graph for parallelization, and the acceptance criteria. Skipping the PRD costs the same as writing it (the agent enumerates the work mentally either way) and loses three things that are not free to recover: durable trace across compaction, resumability after reboot, and the cover-maximality check.
+
+Exempt only when: literal single-line typo fix OR pure-comment edit OR user-issued one-shot command (e.g., `git status`). Anything multi-step, multi-file, or multi-concern emits a PRD before EXECUTE fires.
 
 ## PLAN PHASE — MUTABLE DISCOVERY