8616839cab
CHANGELOG promotion was a manual operator step that was never run, so 463 fragments for work already shipped in <=1.3.1 accumulated in .changeset/. Their notes were already hand-curated into the dated [1.2.0]/[1.3.0]/[1.3.1] CHANGELOG sections (#690 backfill, PR #694). Rendering them now would duplicate and mis-attribute shipped work. Move them to .changeset/archived/ (read non-recursively by all changeset tooling, so never rendered), keeping only the 3 genuinely-unreleased fragments at the top level. Prep for wiring `render` into the release finalize job (#690 follow-up). Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
6 lines
534 B
Markdown
6 lines
534 B
Markdown
---
|
|
type: Fixed
|
|
pr: 582
|
|
---
|
|
Six writer agents (`gsd-eval-planner`, `gsd-ai-researcher`, `gsd-domain-researcher`, `gsd-phase-researcher`, `gsd-ui-researcher`, `gsd-debug-session-manager`) now carry `Edit` alongside `Write` in their `tools:` frontmatter, so the Edit-only discipline in their spawn prompts is enforceable. Previously, without `Edit`, they fell back to whole-file `Write` and silently clobbered sibling sections of shared files such as `AI-SPEC.md`. Same bug class as #571 (fixed for `gsd-doc-writer` in #575). See #581.
|