golem15/msd-core
4
0
Fork 0
Code Issues 1 Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'next' into kimi-runtime-support

Browse Source
This commit is contained in:
Colin Johnson
2026-06-09 10:15:41 -04:00
committed by GitHub
parent c6c3a51277 86845340dc
commit 27aca73b6e
22 changed files with 641 additions and 104 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
.changeset/921-922-orchestrators-no-fork.md Normal file
View File

@@ -0,0 +1,5 @@
---
type: Fixed
pr: 921
---
**`/gsd-plan-phase`, `/gsd-execute-phase`, `/gsd-autonomous` no longer carry `context: fork`** — these are spawning orchestrators; a forked subagent context has no `Agent` tool, preventing them from spawning the subagents they require. `effort: xhigh` is preserved. Fixes `/gsd:autonomous` halting with "running as a forked subagent" on 1.4.1 (#921). Also replaces the introspection-based Agent-availability check in `plan-phase`'s `<runtime_compatibility>` block with an attempt-based gate: the workflow now always attempts the `Agent()` call and only stops if a real tool-unavailable error is returned, eliminating false-negative aborts in top-level sessions (#922).

5
.changeset/924-claude-flat-skill-layout.md Normal file
View File

@@ -0,0 +1,5 @@
---
type: Fixed
pr: 924
---
**Claude global install reverted to flat skill layout so concrete skills are discoverable.** PR #883 introduced nested skill layout for Claude (`~/.claude/skills/gsd-ns-<router>/skills/<stem>/SKILL.md`), but Claude Code's skill discovery scans only one level under `~/.claude/skills/` — nested concrete skills were never listed in the Skill-tool available-skills list and direct `Skill(skill="gsd-plan-phase")` calls stopped working. This fix reverts Claude to the flat layout (`~/.claude/skills/gsd-<name>/SKILL.md`) so all ~61 concrete skills are top-level and immediately discoverable. The 6 other runtimes that confirmed non-recursive scanning (cline, qwen, hermes, augment, trae, antigravity) retain their nested layout. (#924)

5
.changeset/925-context-monitor-hook-event-name.md Normal file
View File

@@ -0,0 +1,5 @@
---
type: Fixed
pr: 926
---
**`gsd-context-monitor.js` now echoes the actual invoking hook event name** — instead of hardcoding `hookEventName: "PostToolUse"` (or `"AfterTool"` for Gemini), the hook reads `data.hook_event_name` from the stdin payload and falls back to the runtime heuristic only when the field is absent or blank; this fixes Claude Code rejecting hook output with `"expected Stop but got PostToolUse"` when the monitor is invoked by the Stop, SubagentStop, or PreCompact hooks registered in PR #821. (#925)