gm-qwen 2.0.772 → 2.0.774
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/gm.json +1 -1
- package/package.json +1 -1
- package/skills/gm/SKILL.md +4 -2
- package/skills/planning/SKILL.md +4 -2
package/gm.json
CHANGED
package/package.json
CHANGED
package/skills/gm/SKILL.md
CHANGED
|
@@ -55,9 +55,11 @@ When scope exceeds reach, construct a maximal cover of the request — not a ref
|
|
|
55
55
|
|
|
56
56
|
Refusal is forced closure. So is *distributed* refusal — shipping a single bounded subset while other witnessable subsets exist. Both bypass witnessed execution.
|
|
57
57
|
|
|
58
|
-
**Required move when scope exceeds reach**: construct a *covering family* of bounded subsets — every subset of the request that is witnessable from this session — and write the family into the PRD. Execute every member.
|
|
58
|
+
**Required move when scope exceeds reach**: construct a *covering family* of bounded subsets — every subset of the request that is witnessable from this session — and write the family into the PRD. Execute every member.
|
|
59
59
|
|
|
60
|
-
|
|
60
|
+
**Residuals the agent judges within the spirit of the original ask AND completable from this session are self-authorized — expand the PRD with them and execute, do not stop to ask.** The judgment is the agent's honest read of what the user probably wanted, paired with reachability from this session. Only residuals genuinely outside the original ask, or genuinely unreachable, are name-and-stop. When expanding under self-authorization, the agent declares its judgment in the response ("treating X as in-scope because Y") so the user can correct mid-chain. Silent expansion without the declaration is the failure mode this rule guards against.
|
|
61
|
+
|
|
62
|
+
The discipline is enforced by what is delivered, not by which words appear. Before closing the turn, check that committed work + named out-of-spirit residuals equals the witnessable closure of the request. Anything witnessable that falls in neither set means the cover is not yet maximal — re-enter planning to expand it. The cover is *maximal*, not *complete*: completeness would require reaching scope outside the session, which is dishonest. Maximality reaches everything inside the session, which is the whole obligation.
|
|
61
63
|
|
|
62
64
|
## FIX ON SIGHT — HARD RULE
|
|
63
65
|
|
package/skills/planning/SKILL.md
CHANGED
|
@@ -53,9 +53,11 @@ Asking is last-resort: destructive-irreversible without PRD coverage, OR user in
|
|
|
53
53
|
|
|
54
54
|
When scope exceeds reach, expand the cover. Don't refuse. Don't ship one slice with the rest abandoned as "follow-up" — that's distributed refusal: the same failure dressed up as triage.
|
|
55
55
|
|
|
56
|
-
**Required move when scope exceeds reach**: construct a *covering family* — every bounded subset of the request that is witnessable from this session — and write the family into the PRD as separate items, with the dependency graph explicit so independent members parallelize. Execute every member.
|
|
56
|
+
**Required move when scope exceeds reach**: construct a *covering family* — every bounded subset of the request that is witnessable from this session — and write the family into the PRD as separate items, with the dependency graph explicit so independent members parallelize. Execute every member.
|
|
57
57
|
|
|
58
|
-
|
|
58
|
+
**Residuals the agent judges within the spirit of the original ask AND completable from this session are self-authorized — expand the PRD with them and execute, do not stop to ask.** The judgment is the agent's honest read of what the user probably wanted, paired with reachability from this session. Only residuals genuinely outside the original ask, or genuinely unreachable from this session, are name-and-stop. When expanding under self-authorization, the agent declares its judgment in the response ("treating X as in-scope because Y") so the user can correct mid-chain. Silent expansion without the declaration is the failure mode this rule guards against.
|
|
59
|
+
|
|
60
|
+
Enforcement is on what is delivered, not on which words appear. Before closing the turn, check that committed work + named out-of-spirit residuals = witnessable closure of the request. Gap = cover not yet maximal → re-enter PLAN to expand.
|
|
59
61
|
|
|
60
62
|
## FIX ON SIGHT — HARD RULE
|
|
61
63
|
|