Skip to content

[T-058] S-LSE strategy (warm-up + straddle level-set estimation) #116

Closed

Description

@CodewithJha

Task T-058 · Milestone M5 — Intelligent selection · Size S · Priority P1 · Epic #5

Implements FR-SEL-004 · PR-15

Branch feat/t-058-s-lse-strategy-warm-up — one task = one branch = one PR (doc 32 §6)

Summary

Implement LevelSetStrategy (S-LSE, selection/lse.py): warm-up then straddle-only batches.

Context / motivation

Boundary-focused ablation; isolates the contribution of boundary refinement to risk-map accuracy (MET-08).

Scope

In scope

  • Entry point S-LSE, phase=boundary.

Implementation guidance

  • Reuse warmup.py and optimize.py.
  • Standards: respect the layering contracts (doc 16 §2) and conventions in doc 34; no hard-coded tunables — thresholds/defaults come from typed settings (doc 27); no magic numbers (ruff PLR2004); public APIs typed (mypy strict) and documented.

Acceptance criteria

  • Boundary accuracy on multi_mode_6d better than S-RANDOM at equal budget (benchmark test, thresholds file).
  • Contract suite passes.
  • Tests listed below added and green in CI; coverage of new code meets the gate in doc 18 §3.
  • Docs, config reference and CHANGELOG Unreleased updated where behaviour, keys or interfaces changed.
  • Definition of Done (doc 32 §3) satisfied.

Tests required

  • tests/benchmark/test_lse_boundary.py.

Dependencies

Blocked by: #114 (T-056c), #103 (T-052)

Blocks: #122 (T-061)

Parallelization notes

Files / paths owned by this task — avoid editing other paths; shared files (pyproject.toml entry points, cli/main.py, api/routers/__init__.py, router.tsx, docker/compose.yaml, ci.yml) are append-only:

  • backend/src/roboprobe/selection/lse.py

Parallel with T-057.

Definition of Done

Per doc 32 §3 and AGENTS.md §5: lint, format, mypy strict and import-linter green; tests added and passing; docs updated; PR template completed with Closes #<this issue>; Conventional Commit messages referencing T-058 (doc 16 §6); commits authored only by the repository owner identity (AGENTS.md §4); CI green; reviewer checklist (doc 32 §5.1) satisfied.

References

Design docs: doc 07 §7 · doc 07 §5.4

Requirements: FR-SEL-004 · PR-15 (traceability: doc 28)

External:

Metadata

Metadata

Assignees

No one assigned

    Labels

    area:selectionScenario selection strategies (BO, LSE, PROBE, baselines)milestone:M5M5 — Intelligent selectionpriority:P1Required for milestone exitsize:S<= 1 daytaskChild task of a milestone epictype:featureNew functionality

    Projects

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions