fix: detect Revit floor frames deterministically
This commit is contained in:
4
SKILL.md
4
SKILL.md
@@ -52,7 +52,7 @@ The Agent owns interpretation. Scripts are tools for evidence and repeatable exe
|
||||
|
||||
The pipeline is designed so a first pass either succeeds or STOPS at a loud gate. Do not hand over a model unless every line below has evidence (a report line, a gate status, or an image):
|
||||
|
||||
1. Read report clean: every `Warnings` entry resolved. `multi_frame_sheet` -> ran `detect_sheet_frames.py` and used its clip/offset config; `cached_xref_content` -> the XREF content is CACHED as in-file block definitions, expand blocks (≈bind) instead of asking for a re-export; `likely_xref_shell` (no cached content) -> user re-exported with XREFs bound.
|
||||
1. Read report clean: every `Warnings` entry resolved by the Agent. `multi_frame_sheet` -> ran `detect_sheet_frames.py` and used its clip/offset config; `cached_xref_content` -> the XREF content is CACHED as in-file block definitions, expand blocks (≈bind) instead of asking for a re-export; `likely_xref_shell` (no cached content) -> user re-exported with XREFs bound. Detection warnings are internal work signals, not a human approval queue: only ask the user when the drawing itself lacks the source/XREF or two materially different interpretations remain after all deterministic checks.
|
||||
2. Frame alignment proven: detect report shows `grid-aligned, votes x>=3 y>=3` per floor (any `WEAK grid match` floor was verified on its overlay SVG).
|
||||
3. Audit exit code 0, and gates `floors_aligned` / `glazing_captured` / `no_annotation_layers_classified` all PASS. `floors_aligned` also cross-checks every floor's wall profile against the group's reference floor (a strong correlation peak at a non-zero shift = "self-consistent but misplaced", the 13号 F3 错槽 pattern that envelope centers cannot see). Never pass `--no-strict-gates` to proceed.
|
||||
Leak gates (SKIP unless armed — arm them on every new project, they are the cross-evidence net): `--frames <detect out-config>` arms `frame_ledger` (every detected plan frame must be used by the config or listed in `discarded_frames` with a reason — silently ignored frames are where wings vanish); config `declared_areas_m2` arms `area_declared` (model footprint area vs 经济技术指标表/标注, ±15% default — 1#B lost half the building and only the site plan showed it); config `expected_storeys_above_ground` arms `storey_count` (vs 总图 `22F` labels / elevation ladder).
|
||||
@@ -84,7 +84,7 @@ The pipeline is designed so a first pass either succeeds or STOPS at a loud gate
|
||||
- Use `references/pipeline.md` and `references/building_spec_schema.md`.
|
||||
- Map CAD layers to normalized categories: `walls`, `glazing`, `roof`, `columns`, `beams`, `railings`, `doors`, `detail_lines`, `floor_lines`, and `grid`.
|
||||
- Identify one drawing per floor or split sheets that contain multiple floor plans side by side.
|
||||
- MULTI-FRAME SHEETS (the common Chinese pattern: one DWG per building holding ALL its plans + elevations + sections stacked in modelspace): run `scripts/detect_sheet_frames.py` on the sanitized DXF. It finds `XX平面图` title texts (filtering catalog rows and title-block copies; titles INSIDE cached-xref blocks are scanned too), prefers title-block frame INSERTs (`A0_V1`/`A0+0.5_V1`/`*图框*`… world bboxes) as clip windows — pitch-sized windows halve elongated sheets (13号 加长A0 held two towers in one frame) — refines each clip to the wall bbox inside it, and computes per-floor `offset`s by voting-based grid-line correlation (label-free; TArch grids live on layer `DOTE`, not `AXIS`). When a frame has NO axis geometry at all, it falls back to wall-profile correlation (length-weighted wall-position histograms, x and y independently, coverage+peak-ratio gated) before surrendering to the clip-corner anchor — clip corners track wall bboxes and drift by whole bays when balconies differ. Auxiliary-titled frames (非机动坡道/无障碍改造/人防…) are flagged and never become the alignment reference (a bike-ramp frame once anchored a whole tower to nothing). Never model such a file as one floor (all sheets superimpose) and never stack frames without offsets (floors staircase away diagonally — the classic broken output). Multi-floor titles (四、六、八层平面图 / 十一至十四层平面图) are expanded into one config entry per storey sharing the frame's clip/offset — hand-copying N entries is where floors silently vanished (13号 b2). Read its report: `WEAK grid match` floors need overlay verification; `wall-correlated` floors deserve one overlay check too; elevation/section frames are listed for floor heights with a PER-FRAME `ladder:` of DIM_ELEV values plus a `suggested storey table` line (uniform-step chain) — the suggestion is evidence, not a decision: fill `z`/`height` yourself after checking the 剖面 ladder (stair sections beat at half-storey rhythm; podium/machine floors differ). Frame clips can swallow the sheet above/below (refine bbox includes between-sheet strips): if a floor's footprint depth is ~2-4x its siblings, cluster its wall y-midpoints and cut the clip band to the plan's own row.
|
||||
- MULTI-FRAME SHEETS (the common Chinese pattern: one DWG per building holding ALL its plans + elevations + sections stacked in modelspace): run `scripts/detect_sheet_frames.py` on the sanitized DXF. It finds `XX平面图` title texts (filtering catalog rows and title-block copies; titles INSIDE cached-xref blocks are scanned too), and for Revit exports it automatically falls back to floor identities encoded in INSERT names when title-block text sits at paper coordinates. It prefers title-block frame INSERTs (`A0_V1`/`A0+0.5_V1`/`*图框*`… world bboxes) as clip windows — pitch-sized windows halve elongated sheets (13号 加长A0 held two towers in one frame) — refines each clip to the wall bbox inside it, and computes per-floor `offset`s by voting-based grid-line correlation (label-free; TArch grids live on layer `DOTE`, not `AXIS`). When a frame has NO axis geometry at all, it falls back to wall-profile correlation (length-weighted wall-position histograms, x and y independently, coverage+peak-ratio gated) before surrendering to the clip-corner anchor — clip corners track wall bboxes and drift by whole bays when balconies differ. Auxiliary-titled frames (非机动坡道/无障碍改造/人防…) are flagged and never become the alignment reference (a bike-ramp frame once anchored a whole tower to nothing). Never model such a file as one floor (all sheets superimpose) and never stack frames without offsets (floors staircase away diagonally — the classic broken output). Multi-floor titles (四、六、八层平面图 / 十一至十四层平面图) are expanded into one config entry per storey sharing the frame's clip/offset — hand-copying N entries is where floors silently vanished (13号 b2). Read its report: `WEAK grid match` floors need overlay verification; `wall-correlated` floors deserve one overlay check too. `AMBIGUOUS overlapping inferred frames` must be resolved by the CAD Agent with cross-floor overlays and an explicit keep/discard reason in the config; it is not a user-facing soft warning and must not be modeled twice blindly. Elevation/section frames are listed for floor heights with a PER-FRAME `ladder:` of DIM_ELEV values plus a `suggested storey table` line (uniform-step chain) — the suggestion is evidence, not a decision: fill `z`/`height` yourself after checking the 剖面 ladder (stair sections beat at half-storey rhythm; podium/machine floors differ). Frame clips can swallow the sheet above/below (refine bbox includes between-sheet strips): if a floor's footprint depth is ~2-4x its siblings, cluster its wall y-midpoints and cut the clip band to the plan's own row.
|
||||
- Align floors by structural grid or repeated control axes. Use millimeters-to-meters scale (`0.001`) unless the report proves the CAD is already in meters.
|
||||
- Floor keys: `floor_sort_key` treats a leading `B` as basement (sorted below ground). Do not invent keys like `B1F` for "Building 1 Floor" — use per-building specs instead, and set explicit `floor_order` whenever keys are nonstandard.
|
||||
- When CAD linework has enough exterior/interior boundary signal, enable generated footprints for floor slabs and roof caps. Prefer footprint polygons over rectangular floor bounds for visual/digital-twin presentation. Footprints are hulled PER proximity cluster (`footprint_cluster_linkage`, 6 m): a floor holding two disconnected masses (13号 twin towers in one floor key) gets separate hulls — a single concave hull would bridge the void and `use_footprint_slabs` would lay plates across it; genuinely linked wings stay merged because the 连廊 walls connect the clusters.
|
||||
|
||||
Reference in New Issue
Block a user