golem15/msd-core
4
0
Fork 0
Code Issues 1 Pull Requests Actions 2 Packages Projects Releases Wiki Activity

fix(tools): write large JSON payloads to tmpfile to prevent truncation (closes #493)

Browse Source 
When init commands include many file contents (state, roadmap, requirements,
etc.), the JSON output can exceed Claude Code's Bash tool buffer (~50KB),
causing parse errors. The output() function now auto-detects large payloads
and writes to a tmpfile, returning @file:/path instead. All workflows that
consume init output handle both formats.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Lex Christopherson
2026-02-15 11:35:39 -06:00
parent bc13b4919f
commit 8d977328e4
4 changed files with 37 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
get-shit-done/workflows/execute-plan.md
View File

@@ -15,7 +15,15 @@ Read config.json for planning behavior settings.
Load execution context (uses `init execute-phase` for full context, including file contents):
```bash
INIT=$(node ~/.claude/get-shit-done/bin/gsd-tools.cjs init execute-phase "${PHASE}" --include state,config)
INIT_RAW=$(node ~/.claude/get-shit-done/bin/gsd-tools.cjs init execute-phase "${PHASE}" --include state,config)
# Large payloads are written to a tmpfile — output starts with @file:/path
if [[ "$INIT_RAW" == @file:* ]]; then
INIT_FILE="${INIT_RAW#@file:}"
INIT=$(cat "$INIT_FILE")
rm -f "$INIT_FILE"
else
INIT="$INIT_RAW"
fi
```
Extract from init JSON: `executor_model`, `commit_docs`, `phase_dir`, `phase_number`, `plans`, `summaries`, `incomplete_plans`.