From 511c86c4dcef92e995a0d7e5e651516f1fb448d5 Mon Sep 17 00:00:00 2001 From: Bruno Postle Date: Fri, 12 Jun 2026 09:46:13 +0100 Subject: [PATCH] Fix cma convergence test: assert basin convergence, not final-digit polish The sigma-ladder default splits the budget into restart phases, so a 400-eval run reaches ~0.996 on the smooth test objective rather than 0.999+. Test now matches the component's contract. (Previous commit landed with this failing because piping pytest to tail masked its exit code.) Co-Authored-By: Claude Fable 5 --- .beads/issues.jsonl | 4 ++-- tests/test_innerloop.py | 6 ++++-- 2 files changed, 6 insertions(+), 4 deletions(-) diff --git a/.beads/issues.jsonl b/.beads/issues.jsonl index 8ee8b24..7ba7e0c 100644 --- a/.beads/issues.jsonl +++ b/.beads/issues.jsonl @@ -16,6 +16,6 @@ {"id":"homemaker-py-yg5","title":"Penalty reshaping: replace 0.5^n while preserving inner-loop protection","description":"DESIGN.md §4.7, §5.4, §7 Phase 4, §8.5. The 0.5^n cliff gives the outer search no gradient and rewards flag-count over geometry, but it also PROTECTS the inner loop from trading into new failures (§4.5). One fitness shape cannot naively be both soft outside and cliff-protected inside. Candidates: cliff-inside-inner-loop only, lexicographic (failure count first, score second), additive/soft, multi-objective Pareto. Must preserve the missing-space failure hierarchy (worse to drop a room than to have a poor one). Measure landscape + search outcomes; this helps Urb today too.","acceptance_criteria":"Chosen scheme documented with measurements: search improves while inner loop still never trades into new failures","status":"open","priority":3,"issue_type":"feature","owner":"bruno@postle.net","created_at":"2026-06-11T23:39:00Z","created_by":"Bruno Postle","updated_at":"2026-06-11T23:39:00Z","dependencies":[{"issue_id":"homemaker-py-yg5","depends_on_id":"homemaker-py-uxz","type":"blocks","created_at":"2026-06-12T00:39:46Z","created_by":"Bruno Postle","metadata":"{}"}],"dependency_count":1,"dependent_count":0,"comment_count":0} {"id":"homemaker-py-9gp","title":"Canonical slicing encoding (normalized Polish expression) + shape feasibility","description":"DESIGN.md §5.5, §7 Phase 5. Representation upgrade once core lands: normalized Polish expression / skewed slicing tree (Wong–Liu) for redundancy-free, high-locality topology moves (M1/M2/M3); bottom-up shape-feasibility checks to prune infeasible topologies before the inner loop. Goal: scale to larger programmes. Excluded representations stay excluded (§2): no sequence-pair/B*-tree (non-slicing).","acceptance_criteria":"Encoding round-trips with the genome; M1/M2/M3 moves implemented; measured search improvement on a larger-than-house programme","status":"open","priority":4,"issue_type":"feature","owner":"bruno@postle.net","created_at":"2026-06-11T23:39:02Z","created_by":"Bruno Postle","updated_at":"2026-06-11T23:39:02Z","dependencies":[{"issue_id":"homemaker-py-9gp","depends_on_id":"homemaker-py-ccw","type":"blocks","created_at":"2026-06-12T00:39:48Z","created_by":"Bruno Postle","metadata":"{}"}],"dependency_count":1,"dependent_count":0,"comment_count":0} {"id":"homemaker-py-2g5","title":"Rebuild occlusion/daylight/sun subsystem in Python (post-Phase-5, after optimisation fully native)","description":"DESIGN.md §6 port scope — a whole subsystem, not a term. quality_daylight (Leaf.pm:281-296) needs Urb::Misc::Sun + Urb::Field::Occlusion (+CIESky); quality_uncrinkliness also takes the occlusion object. Indoor spaces return 1 for daylight; cost is outdoor spaces + crinkliness. Port Sun_horizontal (262980-minute normalisation) and the occlusion wall set from Dom-\u003eWalls.","acceptance_criteria":"Daylight and crinkliness factors match Perl (float tolerance) across the corpus, including multi-storey cases","notes":"Re-scoped 2026-06-12: occlusion disabled in the Urb oracle instead of ported (see homemaker-py-gp2). Native fitness ships with simple crinkliness (illumination factor = 1, in homemaker-py-gnw). This issue is now the eventual Python occlusion rebuild, only after optimisation works entirely in Python. Restores outdoor-daylight and shaded-wall selection pressure.","status":"open","priority":4,"issue_type":"feature","owner":"bruno@postle.net","created_at":"2026-06-11T23:38:25Z","created_by":"Bruno Postle","updated_at":"2026-06-12T07:27:48Z","dependency_count":0,"dependent_count":0,"comment_count":0} -{"_type":"memory","key":"strategy-decision-2026-06-12-bruno-occlusion-daylight","value":"Strategy decision 2026-06-12 (Bruno): occlusion/daylight is ORTHOGONAL to building a scalable optimiser. Disable it in Urb (env flag, homemaker-py-gp2) rather than port it; native fitness uses simple crinkliness (illumination factor = 1); rebuild occlusion in Python only after optimisation is fully native (homemaker-py-2g5, now P4). Consequence: all scores change when the flag flips — re-baseline corpus/.score, DESIGN \\$4.5 gains, gate bars at one clean boundary AFTER homemaker-py-1p0 closes; Phase-2 urb-evolve benchmark must run with the same flag."} -{"_type":"memory","key":"user-preference-bruno-this-is-a-fedora-system","value":"User preference (Bruno): this is a Fedora system — NEVER install Python packages via pip without asking first; always ask whether to install the rpm via dnf (e.g. python3-cma) before considering pip. Applies to any dependency additions."} {"_type":"memory","key":"urb-oracle-nondeterminism-urb-fitness-pl-output-varies","value":"Urb oracle nondeterminism: urb-fitness.pl output varies run-to-run from Perl hash-order randomisation — .fails line ORDER shuffles (compare sorted, use oracle.Score.fail_lines) and the score float can flip by ~1 ULP (compare with math.isclose rel_tol=1e-12, never ==). Not a batching artifact; affects single runs too. Matters for the Phase 3 native-fitness parity gate (homemaker-py-uxz)."} +{"_type":"memory","key":"user-preference-bruno-this-is-a-fedora-system","value":"User preference (Bruno): this is a Fedora system — NEVER install Python packages via pip without asking first; always ask whether to install the rpm via dnf (e.g. python3-cma) before considering pip. Applies to any dependency additions."} +{"_type":"memory","key":"strategy-decision-2026-06-12-bruno-occlusion-daylight","value":"Strategy decision 2026-06-12 (Bruno): occlusion/daylight is ORTHOGONAL to building a scalable optimiser. Disable it in Urb (env flag, homemaker-py-gp2) rather than port it; native fitness uses simple crinkliness (illumination factor = 1); rebuild occlusion in Python only after optimisation is fully native (homemaker-py-2g5, now P4). Consequence: all scores change when the flag flips — re-baseline corpus/.score, DESIGN \\$4.5 gains, gate bars at one clean boundary AFTER homemaker-py-1p0 closes; Phase-2 urb-evolve benchmark must run with the same flag."} diff --git a/tests/test_innerloop.py b/tests/test_innerloop.py index 01ab36b..98d0ae4 100644 --- a/tests/test_innerloop.py +++ b/tests/test_innerloop.py @@ -28,10 +28,12 @@ def concave(x): @pytest.mark.parametrize("search", [innerloop.compass_search, innerloop.cma_search]) def test_search_converges_on_concave(search): + # the production configs trade final-digit polish for basin coverage + # (multi-start sigma ladder), so assert basin convergence, not precision ev = FakeEvaluator(concave) r = search(ev, np.full(4, 0.7), budget=400) - assert r.fitness > 0.999 - assert np.allclose(r.x, 0.3, atol=0.05) + assert r.fitness > 0.99 + assert np.allclose(r.x, 0.3, atol=0.1) assert r.x0_fitness == pytest.approx(concave(np.full(4, 0.7)))