Fix release for 1.1.2: the 14 longest skills keep their later phases after a compaction, a question nobody answered is never taken as an answer, settings read the same from a subfolder, the commit check works for a project in a subfolder of a larger repository, every skill opens with a title, and the shipped allow rules no longer approve deleting a branch or writing files without asking. Details in CHANGELOG.md; upgrade steps in UPGRADING.md (v1.1.2 → v1.1.3). Refs #83 Refs #133 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_0185en4t76fPn7315q4c3nko
2.9 KiB
Active Session State — [project or branch]
` is free-form narrative for humans and for a returning agent that wants detail. No hook ever injects it, so
it may grow — but see Rotation below.
Why the split exists: one append-only file doing both jobs grows without bound, and every consumer then reads a different slice of it: the top, the bottom, or a block nothing writes. They disagree because there is no contract to agree on. With the named regions, every consumer reads the same part.
ROTATION. When the narrative below grows past ~200 lines, move it to
production/session-logs/ and start it fresh:
bash .claude/scripts/rotate-session-state.sh
Nothing is lost — and the commit history already records most of what the
narrative repeats.
-->
Epic: Feature: Task:
Updated: [YYYY-MM-DD]
Branch: [branch]
Current task: [one line — what is actively being worked on]
Next step: [one line — the very next action, concrete enough to resume cold]
Blocked on: [one line, or nothing]
Files in progress: [paths, comma-separated, or none]
Run result: [/dev-story writes its Run result: line here, verbatim, for /story-done to read; other writers leave this line out]
Open questions: [one line each, or none]
Notes
[Free-form. Decisions and their rationale, what was tried and rejected, context that would be expensive to reconstruct. Not machine-read — write for the person or agent picking this up cold.]