Skip to content

[MM-02] Add Maka-native memory benchmark datasets and deterministic graders #781

Description

@bug-superman

MM-02: Add Maka-native memory benchmark datasets and deterministic graders

Parent

#771

Checkpoint

MC-0 Measurement foundation

What to build

Define deterministic continuity and durable-memory lifecycle datasets with stable loaders, hashes, graders, and failure classifications.

Acceptance criteria

  • Continuity dataset covers distant facts, exact values, large tool results, tool adjacency, compact/resume/fork, and overflow recovery.
  • Lifecycle dataset covers remember, evidence promotion, one-off rejection, conflict, dedupe, scope, privacy, deletion, and stale handling.
  • Dataset hashes are stable across machines and fixture ordering.
  • Graders separate task failure, infrastructure failure, privacy violation, and artifact failure.
  • Golden answers and negative cases produce deterministic scores.

Required tests

  • Schema validation
  • hash determinism
  • grader golden fixtures
  • malformed fixture handling
  • privacy hard-gate classification

Benchmark

Run graders against synthetic perfect, partial, leaking, and malformed outputs only; paid models are not required.

Blocked by

Rollout and rollback

Dataset packages are additive and versioned; never mutate a frozen dataset version.

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

    No labels
    No labels

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions