Skip to content

Add latency and recall-budget gates to assistant harness #41

Description

@tsotchke

Goal
Make speed and retrieval cost first-class release gates so assistant improvements cannot silently make the 486 path less usable.

Acceptance criteria

  • Stress and recall reports define per-profile budgets for retrieval time, total reply time, candidate rows, and candidate bytes.
  • Budget failures are clear and include the measured values and configured limits.
  • QEMU gates keep separate thresholds from future physical-machine thresholds.
  • Release notes and capability reports summarize the active budgets.

Evidence gate
python3 scripts/benchmark_assistant_recall.py
python3 scripts/stress_assistant_behavior.py --log qemu/evidence/assistant_stress_486.log
python3 scripts/build_assistant_capability_report.py
python3 scripts/verify_assistant_packs.py

Boundary
No physical hardware validation is claimed by this issue.

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    assistant-usabilityAssistant shell behavior, memory, routing, and operator workflowenhancementNew feature or requestrelease-follow-upPost-preview release hardening and evidence workrelease-gateCI, evidence, reproducibility, and release verification gates

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions