CalvinBackup/gstack
1
0
Fork 0
mirror of https://github.com/garrytan/gstack.git synced 2026-09-16 18:05:31 +02:00
Code Issues Packages Projects Releases Wiki Activity

fix(review,autoplan): require explicit run_in_background: false on specialist agents

Browse Source 
Claude Code v2.1.198 made subagents run in the background by default, which
inverted the old "do not use the flag" guidance: review-army specialists and
autoplan dual voices silently launched in the background and the merge step
could proceed before they completed — regressing the #497 fix. The generated
guidance now instructs an explicit run_in_background: false, and a static
tripwire fails the free suite if the inert inverted phrasing ever returns to
any generated SKILL.md.

Fixes #2440.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Garry Tan
2026-08-14 20:20:48 -07:00
co-authored by Claude Fable 5
parent 5084f85e00
commit e684948efe
7 changed files with 78 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files
autoplan/SKILL.md
+4 -3
View File
@@ -1154,9 +1154,10 @@ Override: every AskUserQuestion → auto-decide using the 6 principles.
Duplicates → reject (P4). Borderline (3-5 files) → mark TASTE DECISION.
- All 10 review sections: run fully, auto-decide each issue, log every decision.
- Dual voices: always run BOTH Claude subagent AND Codex if available (P6).
Run them sequentially in foreground. First the Claude subagent (Agent tool,
foreground — do NOT use run_in_background), then Codex (Bash). Both must
complete before building the consensus table.
Run them sequentially in foreground. First the Claude subagent (Agent tool
with run_in_background: false — subagents default to BACKGROUND since
Claude Code v2.1.198, so the flag must be explicitly false), then Codex
(Bash). Both must complete before building the consensus table.
**Codex CEO voice** (via Bash):
```bash
autoplan/SKILL.md.tmpl
+4 -3
View File
@@ -290,9 +290,10 @@ Override: every AskUserQuestion → auto-decide using the 6 principles.
Duplicates → reject (P4). Borderline (3-5 files) → mark TASTE DECISION.
- All 10 review sections: run fully, auto-decide each issue, log every decision.
- Dual voices: always run BOTH Claude subagent AND Codex if available (P6).
Run them sequentially in foreground. First the Claude subagent (Agent tool,
foreground — do NOT use run_in_background), then Codex (Bash). Both must
complete before building the consensus table.
Run them sequentially in foreground. First the Claude subagent (Agent tool
with run_in_background: false — subagents default to BACKGROUND since
Claude Code v2.1.198, so the flag must be explicitly false), then Codex
(Bash). Both must complete before building the consensus table.
**Codex CEO voice** (via Bash):
```bash