Tablecloth's SMRF ground separation has only one of canonical SMRF's two slope mechanisms: the morphology loop scales with slope (dh_max = slope_threshold · radius), but the final point gate is a slope-blind absolute threshold z − surface_z ≤ max_elev_diff_m (0.05 m). On grades that matter (≥15%), genuine pavement gets cut. This plan adds a PDAL-style gradient-scaled classification threshold (elev_scalar, default 0.0 = bit-exact current behavior) plus a CSF slope-smoothing passthrough (csf_slope_smooth), with steep/cross-slope/crowned/embankment fixtures and streaming-parity tests. Execution is a multi-model workflow: Grok writes tests (RED), GPT-5.6 Sol implements (GREEN), Opus + Sonnet + Grok + Sol review in parallel, Grok fixes, Fable orchestrates and ships a draft PR.
Source research: 48-agent deep-research run (2026-07-17), vault note "Tablecloth slope-handling deep research"; handoff at /tmp/handoff-2eYFv2.md. No re-research needed.
| Decision | Choice | Why |
|---|---|---|
| Slope mechanism | Option A — per-point threshold max_elev_diff_m + elev_scalar · |∇surface|, gradient bilinear-sampled at each point |
Literature-standard (Pingel 2013 / PDAL SMRF, PDAL default scalar 1.25); O(grid) memory; research-verified as the right fix |
| Default value | elev_scalar = 0.0, bit-exact legacy path (the 0.0 branch short-circuits to the exact current expression) |
Safe rollout; default-on only after A/B on real segments |
| Where the gradient lives | New grad grid field on frozen SmrfSurface, computed in _finalize_smrf_surface after the opening loop |
In-memory and streaming both flow through _finalize_smrf_surface + classify_against_surface → streaming parity holds by construction, no forked paths |
| CSF quick win | New csf_slope_smooth: bool = true wired to params.bSloopSmooth (exact upstream typo), hasattr-guarded like interations |
Upstream C++ default is true, so default matches today's untouched behavior; CSF extra isn't installed locally, so upstream default is the best available reference |
| Option B (morphology loop changes) | Deferred — only as a contingency if A cannot pass the steep fixtures | Handoff explicitly says don't do it preemptively; slope_threshold=0.15 is tuned for curb-vs-wall on flat ground |
| Process | Strict TDD: fixtures + failing tests first, watched to fail for missing-feature reasons, then implementation | The steep-fixture failure mode needs empirical confirmation (see uphill-edge analysis below); tests are the spec |
| Execution model | One Workflow run: Grok 4.5 (cursor) → GPT-5.6 Sol (codex) → Opus/Sonnet/Grok/Sol review panel → Grok fix; Claude fallbacks per stage; Fable orchestrates, verifies, commits, opens draft PR | Requested multi-model split (incl. Sol as extra reviewer, per Miro); Grok tokens free today; nobody but the orchestrator commits |
On grades g above slope_threshold (0.15), grey opening of a ramp near the uphill grid edge returns ≈ f(edge − window) (dilation can't reach uphill past the boundary), so (surface − opened) > slope_threshold·radius triggers there and the replaced band (last ~2–3 cells) ends up to g·window below true ground and nearly flat. The final surface gradient inside that band is ≈ 0, so gradient scaling alone may not rescue it — the GREEN agent gets this analysis and, if confirmed, is allowed one minimal principled adjustment (gradient propagation into replaced bands, or an uphill-edge replacement guard) that keeps every existing test green, including crop-edge object removal. Away from edges the residual misfit is per-cell discretization ≈ g·cell_m (0.036 m at 18%) vs the 0.05 m gate.
Tests only, no src/ changes. Baseline suite must be green first.
tests/fixtures/synthetic.py): extend sloped_plane_lip_vehicle with backward-compatible grade_y (cross-slope); add crowned_road_vehicle (center-ridge crown + vehicle blob); add grade_break_embankment (flat road, then 30–40% bank).elev_scalar=1.25: steep (plane ≥ 0.99 excl. blob halo, blob removed ≥ 0.95, lip kept ≥ 0.95), cross-slope, crowned road, embankment (window must not flatten the grade break).np.array_equal between default config, explicit elev_scalar=0.0, and a manually computed fixed-gate reference mask.elev_scalar=1.25 (chunked vs in-memory, exact mask equality).importorskip("CSF").Verify-RED: every new test must fail for a missing-feature reason (unknown config key / missing parameter / demonstrated defect) — not a collection error.
config.py: elev_scalar: float = 0.0 (SMRF block), csf_slope_smooth: bool = True (CSF block); mirrored in tablecloth.default.json (parity is test-enforced).ground.py: SmrfSurface.grad; gradient via np.gradient(surface, cell) + np.hypot (size-1-axis guard); classify_against_surface(..., elev_scalar=0.0) with exact legacy expression on the 0.0 branch; classify_mask_from_chunks gains elev_scalar; _csf_classify wires bSloopSmooth.filter.py: streaming call site passes float(config.elev_scalar).Hard constraints: O(grid) streaming memory, no chunk-order dependence, streaming bit-identical to in-memory, CPU NumPy/SciPy only, frozen config, TableclothConfigError for validation. Rejected by research (do not implement): per-cell morphological slope estimation, global plane detrend, full PMF window schedules, trajectory-aligned anisotropic morphology.
elev_scalar..any() on evaluation masks).Findings classified must_fix / nice_to_have; review runs on the staged diff, read-only.
Only runs if the panel produced must_fix findings. Applies them, keeps the suite green, may skip a wrong finding with justification.
verify / code-review discipline).AI3D-337: <imperative summary> (tests and implementation separated if the diff reads better that way).wrap-up exists for that).Ran on battlebox against source data: all 25 records of Abschnitt 4/5 segment_066 (lip acceptance) + segment_071 (vehicle removal), elev_scalar 0.0 vs 1.25, ~2.6 s and ~0.37 GB RSS per 1.67M-point record.
071/Record003 +27.9 pp (0.448 → 0.727).066/Record023 stays removed under both configs; no vehicle blobs appeared in the 1.25 overlays.cross_sections_run7_lanes truth) across more segments, not kept-fraction alone.elev_scalar=1.25 — Opus-adjudicated across 19 flagged renders. Recovered mass is always shoulder/verge/V-ditch/embankment ground; cars, guardrail posts, signs, vegetation stay removed; zero points lost. Fixture cross-check: 100% object removal at 1.25 (guardrail, vegetation, vehicle flat + 18%).smrf_edge_pad_enabled (default false = bit-identical, spy-tested): slope-extrapolating seed-grid padding (per-row/col Theil–Sen + two-pass trimmed-residual refit, slope clamp, distance decay) around the opening loop, cropped back before gradient. TDD + 4-model review; Sol's adversarial probe (boundary-parked object shielding) drove the trimmed-refit design and a boundary-parallel raised-strip regression test. Suite: 60 passed.cross_sections_run7_lanes point) is bit-identical across 0.0 / 1.25 / 1.25+pad — all deltas are off-lane, so downstream lane-finding is unaffected. Recommendation: elev_scalar=1.25 + smrf_edge_pad_enabled=true are safe to enable together pending team sign-off; defaults stay off in this PR.Worktree ai3d-337-slope-handling is clean (the earlier workflow launch was stopped before its first stage wrote anything). Deps synced; CSF extra confirmed absent locally. The stopped run (wf_4937f0ed-53e) can be resumed or relaunched on approval — nothing is cached that would go stale.
The local machine is thermally constrained, so all pytest runs execute on battlebox (24-core WSL over VPN): a wrapper script tar-pipes the worktree to /home/ai/ai3d-337-tablecloth, runs uv run pytest there, and streams results back. Edits stay local (single source of truth); only test execution is offloaded. Every workflow agent is instructed to use the wrapper and never run the suite locally. Fully moving the Codex/cursor delegates to battlebox was considered and rejected for this run — it would need two-way file sync with divergence risk.
The renders behind Phases 6 and 7, published 2026-09-04 from the battlebox A/B run directory
/home/ai/ai3d-ab (profile_plot.py, precision_check.py).
Each per-record render shows a top-down view (record-local along-track vs cross-track) and a
cross-section (cross-track vs z) of a random point subsample. Kept fractions come from the
corresponding run_summary.json. Click any image for full resolution; arrows / swipe
step through the images of one card.
How to read a render. Both configurations are SMRF; CSF is not involved. Each
render compares the fixed gate (elev_scalar=0.0, the pre-AI3D-337 behaviour) against the
slope-scaled gate (elev_scalar=1.25) on the same record. Top panel: top-down in the
record-local frame. Bottom panel: cross-section, cross-track vs z. The caption's
"kept a → b" is the ground (kept) fraction at 0.0 → 1.25. The Record003 card's right-hand image is
the exception: it compares 1.25 without vs with smrf_edge_pad_enabled.
green kept as ground by both configs red removed (non-ground) by both orange recovered at 1.25: cut by the fixed gate, kept by the scaled gate (should be shoulder / verge / ditch / embankment ground) blue lost at 1.25: kept by the fixed gate, removed by the scaled gate (should be ~0)
Left: the fixed gate (0.0) keeps only the bottom ~0.3 m of the ~1.1 m face; the slope-scaled gate (1.25) follows the face. Right: the record-edge dig band that survived at 1.25 is recovered by smrf_edge_pad_enabled.
0.05 + 1.25·0.18 ≈ 0.28 m — low cargo/roof edges of vehicles stay removed (blob points ≥ 0.4 m), but very low objects on steep slopes get more slack. Covered by blob-removal assertions on every sloped fixture; default 0.0 means production is unaffected until A/B.hasattr-guarded and behavior tests importorskip; worst case the flag is inert on exotic CSF builds.params.bSloopSmooth default is True, so our default true exactly matches current untouched behavior.