Skip to content

v1.6 — Final submission: Workbench + server-side policy gate

Choose a tag to compare

@a252937166 a252937166 released this 10 Jul 15:40
· 4 commits to master since this release

Final Qwen Cloud Hackathon Track 1 submission (exact SHA: 9013606, CI green on this commit).

Highlights:

  • Conversation Workbench is the default product interface; Memory Lab isolates the constellation and Judge Demo
  • Per-turn Memory Decision Audit (selected/rejected, score waterfall, injected context, ops — replayable from history, exportable as JSON)
  • Server-side memory policy gate: a standing procedural rule denies a risky action BEFORE generation — verdict injected into the prompt, streamed to the UI, persisted in the turn audit
  • Responsive evidence: below 1280px sessions/evidence become drawers (never display:none'd) — reachable on 1024px laptops and phones
  • Streaming Stop, graph label pinning, store metadata (importance / created / used), workbench empty-state onboarding
  • Atomic belief revision & consolidation, deferred reinforcement, cluster purity guard
  • 14-spec Playwright E2E across 3 viewports; 10/10 belief-revision and 10/10 critical-recall stability; benchmark re-run 5/5 on final code
  • Live: https://engram.hackthon.site · ?seed=devops · ?judge=1 · demo video (1:52): https://youtu.be/s0cigCj991U

JUDGING.md · proof-of-deployment · evaluation