mirror of
https://github.com/openclaw/openclaw.git
synced 2026-07-15 03:16:05 +00:00
* fix(qa): seed memory scenarios through SQLite * fix(active-memory): initialize SQLite recall sessions * test(active-memory): model missing harness reservation * fix(active-memory): clean up transient recall sessions * fix(active-memory): isolate concurrent recall sessions * fix(active-memory): discard transient SQLite recalls * fix(active-memory): preserve transient recall boundaries * fix(active-memory): retry transient recall cleanup * fix(active-memory): always clean transient recall workspaces * chore: drop release-owned changelog entry
QA Scenarios
Seed QA assets for the private qa-lab extension.
Files:
scenarios/index.yaml- canonical QA scenario pack, kickoff mission, and operator identity.scenarios/<theme>/*.yaml- one runnable scenario per YAML file.frontier-harness-plan.md- big-model bakeoff and tuning loop for harness work.convex-credential-broker/- standalone Convex v1 lease broker for pooled live credentials.
Key workflow:
qa suiteis the executable frontier subset / regression loop.qa manualis the scoped personality and style probe after the executable subset is green.qa coverageprints the scenario coverage inventory from scenario YAML.
Operator workflows:
- Use the
openclaw-qa-testingskill for QA Lab live lanes, Convex credential pool operations, and WhatsApp live credential setup/replacement.
Keep this folder in git. Add new scenarios here before wiring them into automation.