| summary |
Changelog for scaffold evolution. |
| read_when |
Preparing a release or reviewing history. |
|
| system4d |
| container |
compass |
engine |
fog |
Release log for this extension package. |
Track meaningful deltas per version. |
Document changes at release boundaries. |
Versioning policy may evolve with team preference. |
|
All notable changes to this project should be documented here.
- evalset: add JSON to HTML report export helper (802e7d2)
- Added
/evalset MVP command with subcommands:
init to generate a starter fixed-task-set dataset
run to evaluate one variant against a dataset
compare to evaluate baseline vs candidate system prompts
- Added example files in
examples/:
fixed-task-set.json
fixed-task-set-v2.json
fixed-task-set-v3.json
evalset-compare-sample-embedded.html
evalset-compare-sample.png
system-baseline.txt
system-candidate.txt
- Added report output support to
.evalset/reports/*.json with per-case and aggregate metrics.
- Added run identity metadata to reports (
runId, datasetHash, casesHash, variantHash).
- Reduced session message payload size by storing only lightweight report metadata instead of full report bodies.
- Added
scripts/export-evalset-report-html.mjs and npm run evalset:export-html for repeatable JSON -> static HTML report exports.
- Clarified
/evalset invocation docs: use pi -p (or pi -e ... -p) for non-interactive runs; /evalset is not a standalone shell binary.
- Added the same non-interactive invocation note to
/evalset help output.
- Declared publish-time runtime artifacts with
package.json files whitelist and documented peer/runtime dependency behavior in README.
- Initial production-ready scaffold generated from template v2.