Seven `claude plugin eval` cases under evals/, runs: 1, deterministic graders only (regex, tool_used, file_exists), no ablation. Each case tests one thing Voyage promises and stops within minutes, headless: - plan-requires-brief, plan-project-not-initialized, plan-rejects-unknown-export, review-requires-project: argument guards stop before any Agent or Write. - plan-halts-without-phase-signals: a brief_version 2.1 brief without phase_signals halts /trekplan at the sequencing gate, before the swarm. - review-validate-flags-bad-finding-id (known-positive) and review-validate-passes-clean-review (known-negative): /trekreview --validate names REVIEW_BAD_FINDING_ID on a planted bad ID and stays clean on a valid file. Each case's expected_outcome is committed here, before the suite has run. Fixtures are written by an inline scaffold.sh (needs --scaffold): chose inline heredocs because a run cannot read the eval directory, and the add_dirs path mapping is not documented. evals/results/ is ignored. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
63 lines
2 KiB
Text
63 lines
2 KiB
Text
# OS files
|
|
.DS_Store
|
|
Thumbs.db
|
|
Desktop.ini
|
|
|
|
# Node / test artifacts
|
|
node_modules/
|
|
test-results/
|
|
playwright-report/
|
|
blob-report/
|
|
|
|
# `claude plugin eval` run output (aggregate-result.json, report.html). Results are
|
|
# data about one run on one machine; the suite (evals/<case>/) is what is tracked.
|
|
/evals/results/
|
|
|
|
# Editor files
|
|
*.swp
|
|
*.swo
|
|
*~
|
|
.vscode/
|
|
.idea/
|
|
|
|
# Local configuration / session files
|
|
*.local.*
|
|
|
|
# STATE.md — current state-of-play. LOCAL-ONLY per ~/.claude/CLAUDE.md:
|
|
# origin is open/ (an OFFENTLIG/public mirror) → STATE must NEVER be pushed there.
|
|
# Kept local for continuity only. History scrubbed 2026-06-26 (was wrongly tracked 23 commits).
|
|
STATE.md
|
|
|
|
# PLAN.md — the repo's destination layer. LOCAL-ONLY under the same remote rule as STATE.md
|
|
# (operator decision 2026-09-15): it carries destination, open questions and what NOT to build.
|
|
# Anchored to the root: core.ignorecase=true here, so a bare pattern would also swallow the
|
|
# pipeline's lowercase plan.md files (e.g. a new examples/*/plan.md) without a word.
|
|
/PLAN.md
|
|
|
|
# Local planning docs (briefs, design notes, observations) — never committed.
|
|
# Existing tracked files in docs/ predate this rule; new planning docs stay local.
|
|
docs/ultracontinue-brief.md
|
|
docs/ultracontinue-design-notes.md
|
|
|
|
# Ultraplan project directories — briefs, research, plans, progress all local.
|
|
.claude/projects/
|
|
|
|
# --- session/local state (gitignored) — STATE.md is LOCAL-ONLY (open/ = public), se ~/.claude/CLAUDE.md ---
|
|
REMEMBER.md
|
|
ROADMAP.md
|
|
TODO.md
|
|
NEXT-SESSION-PROMPT*.local.md
|
|
*.local.md
|
|
*.local.json
|
|
*.local.sh
|
|
.DS_Store
|
|
.claude/
|
|
|
|
# Operator working documents dropped into docs/ — never part of the published
|
|
# plugin. `origin` is a PUBLIC mirror, and S83 committed one of these with a
|
|
# broad `git add -A docs`, which needed a history rewrite to undo. Ignoring the
|
|
# type is cheaper than remembering not to stage it.
|
|
docs/*.pdf
|
|
# Page renders of those same documents (SLDC-AI-1_1.png etc). Narrow on purpose:
|
|
# legitimate plugin assets may still be .png under docs/.
|
|
docs/SLDC-AI*.png
|